495a5e5409
Model: fpadovani/dan-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
30090 lines
826 KiB
JSON
30090 lines
826 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.252923488138991,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.823197078704834,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 13.4375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.3319,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8702.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.829868984222412,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 15.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.2442,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17355.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.871206903457642,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 14.625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.055,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 25975.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.015691137313842,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 20.5,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.6199,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 35099.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 6.097980880737305,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 21.75,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 12.4018,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 44526.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 9.22457389831543,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 5.375,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 11.1046,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 53856.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.673493671417237,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 3.15625,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.6655,
|
|
"mean_token_accuracy": 0.0008215151203330607,
|
|
"num_tokens": 63583.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.704101467132569,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.3643,
|
|
"mean_token_accuracy": 0.038832120783627036,
|
|
"num_tokens": 71894.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.683347702026367,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 2.859375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.049,
|
|
"mean_token_accuracy": 0.043674240633845327,
|
|
"num_tokens": 81234.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.607063961029052,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7618,
|
|
"mean_token_accuracy": 0.04232829064130783,
|
|
"num_tokens": 90759.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.514880847930907,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.612,
|
|
"mean_token_accuracy": 0.04196392707526684,
|
|
"num_tokens": 100765.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.509155654907227,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.4891,
|
|
"mean_token_accuracy": 0.04262847602367401,
|
|
"num_tokens": 110317.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.529613208770751,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.3861,
|
|
"mean_token_accuracy": 0.04258695356547833,
|
|
"num_tokens": 119665.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.530327224731446,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.2863,
|
|
"mean_token_accuracy": 0.04265623725950718,
|
|
"num_tokens": 128083.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.505690383911134,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.2254,
|
|
"mean_token_accuracy": 0.04184907637536526,
|
|
"num_tokens": 137168.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.455103874206543,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.0861,
|
|
"mean_token_accuracy": 0.04463305622339249,
|
|
"num_tokens": 146023.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.415075778961182,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.074,
|
|
"mean_token_accuracy": 0.0408624455332756,
|
|
"num_tokens": 154392.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.39247169494629,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.907,
|
|
"mean_token_accuracy": 0.04568507187068462,
|
|
"num_tokens": 163673.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.380887985229492,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.8612,
|
|
"mean_token_accuracy": 0.04349003247916698,
|
|
"num_tokens": 172879.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.331772422790527,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.738,
|
|
"mean_token_accuracy": 0.04735205471515656,
|
|
"num_tokens": 183378.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.24242639541626,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.6205,
|
|
"mean_token_accuracy": 0.05316540449857712,
|
|
"num_tokens": 192255.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.131509399414062,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.4857,
|
|
"mean_token_accuracy": 0.055044937133789065,
|
|
"num_tokens": 202118.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.957079792022705,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.3159,
|
|
"mean_token_accuracy": 0.05693938583135605,
|
|
"num_tokens": 210536.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.808850955963134,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.1694,
|
|
"mean_token_accuracy": 0.05625454857945442,
|
|
"num_tokens": 219577.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.689696979522704,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.0917,
|
|
"mean_token_accuracy": 0.05639561228454113,
|
|
"num_tokens": 227676.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.504155826568603,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.9152,
|
|
"mean_token_accuracy": 0.06222889423370361,
|
|
"num_tokens": 236692.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.237131118774414,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.901,
|
|
"mean_token_accuracy": 0.053731896728277204,
|
|
"num_tokens": 246143.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.096350193023682,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.7313,
|
|
"mean_token_accuracy": 0.061722924932837486,
|
|
"num_tokens": 255263.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.774121379852295,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.6964,
|
|
"mean_token_accuracy": 0.058184793964028356,
|
|
"num_tokens": 264219.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.612203598022461,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.6437,
|
|
"mean_token_accuracy": 0.05833452381193638,
|
|
"num_tokens": 274819.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.410180759429931,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.5712,
|
|
"mean_token_accuracy": 0.05876019336283207,
|
|
"num_tokens": 284382.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.265682983398438,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.5376,
|
|
"mean_token_accuracy": 0.06281311847269536,
|
|
"num_tokens": 294457.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.116789722442627,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.4582,
|
|
"mean_token_accuracy": 0.058620238304138185,
|
|
"num_tokens": 303788.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.073031854629516,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.4559,
|
|
"mean_token_accuracy": 0.0672534491866827,
|
|
"num_tokens": 312815.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.08813018798828,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.4682,
|
|
"mean_token_accuracy": 0.0674412775784731,
|
|
"num_tokens": 323599.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.976608514785767,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.4279,
|
|
"mean_token_accuracy": 0.0645599164068699,
|
|
"num_tokens": 332788.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.931798505783081,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.4383,
|
|
"mean_token_accuracy": 0.06663466952741146,
|
|
"num_tokens": 342528.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.9960370540618895,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.3634,
|
|
"mean_token_accuracy": 0.07428645715117455,
|
|
"num_tokens": 350404.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.821600151062012,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.2994,
|
|
"mean_token_accuracy": 0.06746574863791466,
|
|
"num_tokens": 360806.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.909206867218018,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3168,
|
|
"mean_token_accuracy": 0.06789615079760551,
|
|
"num_tokens": 370236.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.853248739242554,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.2841,
|
|
"mean_token_accuracy": 0.07116037532687187,
|
|
"num_tokens": 380409.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.860307741165161,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.2027,
|
|
"mean_token_accuracy": 0.0794663280248642,
|
|
"num_tokens": 389797.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.719875431060791,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1302,
|
|
"mean_token_accuracy": 0.07808805145323276,
|
|
"num_tokens": 398867.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.7590044975280765,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3234,
|
|
"mean_token_accuracy": 0.07359835654497146,
|
|
"num_tokens": 409921.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.673631000518799,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.1328,
|
|
"mean_token_accuracy": 0.08627882376313209,
|
|
"num_tokens": 418962.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.64231309890747,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1542,
|
|
"mean_token_accuracy": 0.07698500528931618,
|
|
"num_tokens": 428111.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.689408874511718,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.1785,
|
|
"mean_token_accuracy": 0.0806326750665903,
|
|
"num_tokens": 437370.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.6315025806427,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0577,
|
|
"mean_token_accuracy": 0.08123884871602058,
|
|
"num_tokens": 446687.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.64709963798523,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2263,
|
|
"mean_token_accuracy": 0.07417257204651832,
|
|
"num_tokens": 455306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.604256057739258,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.1418,
|
|
"mean_token_accuracy": 0.07368349954485894,
|
|
"num_tokens": 465491.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.6127721786499025,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1261,
|
|
"mean_token_accuracy": 0.08081023842096328,
|
|
"num_tokens": 475782.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.605498552322388,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1321,
|
|
"mean_token_accuracy": 0.0829504206776619,
|
|
"num_tokens": 484901.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.480518579483032,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.0694,
|
|
"mean_token_accuracy": 0.07500050067901612,
|
|
"num_tokens": 493742.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.610927629470825,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.086,
|
|
"mean_token_accuracy": 0.07933647558093071,
|
|
"num_tokens": 502959.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.507209444046021,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0187,
|
|
"mean_token_accuracy": 0.08608514666557313,
|
|
"num_tokens": 512003.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.5971019744873045,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1144,
|
|
"mean_token_accuracy": 0.08404356315732002,
|
|
"num_tokens": 520680.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.484663248062134,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0336,
|
|
"mean_token_accuracy": 0.08570652380585671,
|
|
"num_tokens": 529001.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.444897890090942,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0136,
|
|
"mean_token_accuracy": 0.09252469018101692,
|
|
"num_tokens": 537309.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.436733818054199,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9432,
|
|
"mean_token_accuracy": 0.08575214147567749,
|
|
"num_tokens": 546436.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.373424291610718,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0205,
|
|
"mean_token_accuracy": 0.08929547369480133,
|
|
"num_tokens": 555634.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.337024974822998,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8664,
|
|
"mean_token_accuracy": 0.08913953229784966,
|
|
"num_tokens": 564781.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.392226839065552,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0876,
|
|
"mean_token_accuracy": 0.08700757548213005,
|
|
"num_tokens": 575130.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.466950368881226,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0072,
|
|
"mean_token_accuracy": 0.08388047441840171,
|
|
"num_tokens": 584030.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.381117963790894,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9283,
|
|
"mean_token_accuracy": 0.08811081871390343,
|
|
"num_tokens": 593079.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.281032371520996,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8652,
|
|
"mean_token_accuracy": 0.10489550679922104,
|
|
"num_tokens": 601830.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.323091983795166,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8333,
|
|
"mean_token_accuracy": 0.09269191026687622,
|
|
"num_tokens": 610296.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.244619131088257,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8653,
|
|
"mean_token_accuracy": 0.08757187873125076,
|
|
"num_tokens": 619762.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.36158595085144,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8867,
|
|
"mean_token_accuracy": 0.08732209205627442,
|
|
"num_tokens": 629271.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.3284117698669435,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9949,
|
|
"mean_token_accuracy": 0.08122688755393029,
|
|
"num_tokens": 638425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.380646419525147,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9775,
|
|
"mean_token_accuracy": 0.08487723991274834,
|
|
"num_tokens": 647322.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.31452112197876,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9627,
|
|
"mean_token_accuracy": 0.08671952188014984,
|
|
"num_tokens": 656511.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.3450275421142575,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8999,
|
|
"mean_token_accuracy": 0.08400550261139869,
|
|
"num_tokens": 667039.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.224361610412598,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7735,
|
|
"mean_token_accuracy": 0.0921957716345787,
|
|
"num_tokens": 676065.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.357305717468262,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9248,
|
|
"mean_token_accuracy": 0.08780089169740676,
|
|
"num_tokens": 684344.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.180531406402588,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.8688,
|
|
"mean_token_accuracy": 0.08930155485868455,
|
|
"num_tokens": 692839.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.284558629989624,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8487,
|
|
"mean_token_accuracy": 0.09052183702588082,
|
|
"num_tokens": 702689.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.155199098587036,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8362,
|
|
"mean_token_accuracy": 0.08517579063773155,
|
|
"num_tokens": 711579.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.187967967987061,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7925,
|
|
"mean_token_accuracy": 0.09016783386468888,
|
|
"num_tokens": 720469.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.122943782806397,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7687,
|
|
"mean_token_accuracy": 0.08865757063031196,
|
|
"num_tokens": 730326.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.173013639450073,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7587,
|
|
"mean_token_accuracy": 0.09741819649934769,
|
|
"num_tokens": 738992.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.070012474060059,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8013,
|
|
"mean_token_accuracy": 0.09208141937851906,
|
|
"num_tokens": 748387.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.231819820404053,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7421,
|
|
"mean_token_accuracy": 0.09340555220842361,
|
|
"num_tokens": 757712.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.06294436454773,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7005,
|
|
"mean_token_accuracy": 0.09443574398756027,
|
|
"num_tokens": 766626.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.136194896697998,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6657,
|
|
"mean_token_accuracy": 0.09597866535186768,
|
|
"num_tokens": 775942.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.111518144607544,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7432,
|
|
"mean_token_accuracy": 0.09417268559336663,
|
|
"num_tokens": 784680.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.168673133850097,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.09111174866557122,
|
|
"num_tokens": 794107.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.135743093490601,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.79,
|
|
"mean_token_accuracy": 0.09644902572035789,
|
|
"num_tokens": 803584.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.1497382640838625,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7676,
|
|
"mean_token_accuracy": 0.092482028901577,
|
|
"num_tokens": 812460.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.023286437988281,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7414,
|
|
"mean_token_accuracy": 0.09485919401049614,
|
|
"num_tokens": 821946.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.057104301452637,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6867,
|
|
"mean_token_accuracy": 0.08957326710224152,
|
|
"num_tokens": 831781.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.06196608543396,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6303,
|
|
"mean_token_accuracy": 0.09696827605366706,
|
|
"num_tokens": 840903.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.991696548461914,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7556,
|
|
"mean_token_accuracy": 0.09650159776210784,
|
|
"num_tokens": 850545.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.060777759552002,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7266,
|
|
"mean_token_accuracy": 0.09582033678889275,
|
|
"num_tokens": 860606.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.0842451572418215,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7709,
|
|
"mean_token_accuracy": 0.09876812249422073,
|
|
"num_tokens": 868767.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.999656438827515,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6226,
|
|
"mean_token_accuracy": 0.09780478551983833,
|
|
"num_tokens": 877820.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.04571213722229,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7835,
|
|
"mean_token_accuracy": 0.08980523273348809,
|
|
"num_tokens": 887035.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.02214469909668,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7462,
|
|
"mean_token_accuracy": 0.0942918598651886,
|
|
"num_tokens": 896249.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.005578708648682,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6631,
|
|
"mean_token_accuracy": 0.088001199811697,
|
|
"num_tokens": 905307.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.922316265106201,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6487,
|
|
"mean_token_accuracy": 0.0977574922144413,
|
|
"num_tokens": 914587.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.8909790992736815,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5553,
|
|
"mean_token_accuracy": 0.10295188128948211,
|
|
"num_tokens": 923361.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.975408411026001,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6912,
|
|
"mean_token_accuracy": 0.09353699833154679,
|
|
"num_tokens": 931698.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.927935075759888,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6488,
|
|
"mean_token_accuracy": 0.09546012356877327,
|
|
"num_tokens": 940141.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.855420064926148,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.09668388590216637,
|
|
"num_tokens": 948926.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.977548837661743,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6822,
|
|
"mean_token_accuracy": 0.09463226422667503,
|
|
"num_tokens": 957995.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.9774463176727295,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6742,
|
|
"mean_token_accuracy": 0.09843497723340988,
|
|
"num_tokens": 968004.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.957279062271118,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.7089,
|
|
"mean_token_accuracy": 0.09921421632170677,
|
|
"num_tokens": 977931.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.856095695495606,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6626,
|
|
"mean_token_accuracy": 0.09421706050634385,
|
|
"num_tokens": 986904.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.8645508766174315,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6068,
|
|
"mean_token_accuracy": 0.09787782728672027,
|
|
"num_tokens": 997482.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.911374950408936,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6184,
|
|
"mean_token_accuracy": 0.10066768899559975,
|
|
"num_tokens": 1007196.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.884297323226929,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7243,
|
|
"mean_token_accuracy": 0.09924571886658669,
|
|
"num_tokens": 1016435.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.889643764495849,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.10183246359229088,
|
|
"num_tokens": 1026299.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.843575668334961,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5463,
|
|
"mean_token_accuracy": 0.10173309668898582,
|
|
"num_tokens": 1034672.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.805506658554077,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5295,
|
|
"mean_token_accuracy": 0.11204413995146752,
|
|
"num_tokens": 1042786.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.775815105438232,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5225,
|
|
"mean_token_accuracy": 0.10164727568626404,
|
|
"num_tokens": 1052709.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.816510200500488,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.0973842978477478,
|
|
"num_tokens": 1061880.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.891012907028198,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5677,
|
|
"mean_token_accuracy": 0.09752165898680687,
|
|
"num_tokens": 1071234.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.905015516281128,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7021,
|
|
"mean_token_accuracy": 0.0992009960114956,
|
|
"num_tokens": 1081252.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.769313478469849,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5571,
|
|
"mean_token_accuracy": 0.10143707543611527,
|
|
"num_tokens": 1090642.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.751708698272705,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5311,
|
|
"mean_token_accuracy": 0.10075362771749496,
|
|
"num_tokens": 1099918.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.845557498931885,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5647,
|
|
"mean_token_accuracy": 0.09541338533163071,
|
|
"num_tokens": 1109521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.70610933303833,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4294,
|
|
"mean_token_accuracy": 0.11414572820067406,
|
|
"num_tokens": 1118140.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.723880195617676,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5889,
|
|
"mean_token_accuracy": 0.1042640283703804,
|
|
"num_tokens": 1127591.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.8105981826782225,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5607,
|
|
"mean_token_accuracy": 0.09807760342955589,
|
|
"num_tokens": 1136223.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.805627489089966,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4641,
|
|
"mean_token_accuracy": 0.10856227055191994,
|
|
"num_tokens": 1146367.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.634521865844727,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4683,
|
|
"mean_token_accuracy": 0.10519542768597603,
|
|
"num_tokens": 1156230.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.817045211791992,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.58,
|
|
"mean_token_accuracy": 0.10044590011239052,
|
|
"num_tokens": 1166106.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.7388416767120365,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5653,
|
|
"mean_token_accuracy": 0.10486629605293274,
|
|
"num_tokens": 1174887.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.71886944770813,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5369,
|
|
"mean_token_accuracy": 0.11368259638547898,
|
|
"num_tokens": 1184027.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.694011211395264,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4874,
|
|
"mean_token_accuracy": 0.10772749111056328,
|
|
"num_tokens": 1194632.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.656815147399902,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4208,
|
|
"mean_token_accuracy": 0.11698552221059799,
|
|
"num_tokens": 1204601.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.726843070983887,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6166,
|
|
"mean_token_accuracy": 0.10057807937264443,
|
|
"num_tokens": 1213288.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.657552337646484,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5653,
|
|
"mean_token_accuracy": 0.10514772906899453,
|
|
"num_tokens": 1222768.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.744826745986939,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5451,
|
|
"mean_token_accuracy": 0.10463840067386627,
|
|
"num_tokens": 1232421.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.6112964153289795,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.4243,
|
|
"mean_token_accuracy": 0.11523082107305527,
|
|
"num_tokens": 1241230.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.793651056289673,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5711,
|
|
"mean_token_accuracy": 0.10192721858620643,
|
|
"num_tokens": 1250879.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.692268371582031,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4367,
|
|
"mean_token_accuracy": 0.11580214574933052,
|
|
"num_tokens": 1259073.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.604025888442993,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.10393711403012276,
|
|
"num_tokens": 1269174.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.712643575668335,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6139,
|
|
"mean_token_accuracy": 0.10357280150055885,
|
|
"num_tokens": 1279366.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.651198530197144,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4171,
|
|
"mean_token_accuracy": 0.10862385183572769,
|
|
"num_tokens": 1288879.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.577065515518188,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3147,
|
|
"mean_token_accuracy": 0.11318397149443626,
|
|
"num_tokens": 1298098.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.5543561458587645,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.485,
|
|
"mean_token_accuracy": 0.1087345264852047,
|
|
"num_tokens": 1306960.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.727486610412598,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5461,
|
|
"mean_token_accuracy": 0.10284490808844567,
|
|
"num_tokens": 1317252.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.565056228637696,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.11380289196968078,
|
|
"num_tokens": 1326712.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.661278581619262,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4932,
|
|
"mean_token_accuracy": 0.10850499421358109,
|
|
"num_tokens": 1336205.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.617316246032715,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4705,
|
|
"mean_token_accuracy": 0.10904657989740371,
|
|
"num_tokens": 1345347.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.533994197845459,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4027,
|
|
"mean_token_accuracy": 0.10399781167507172,
|
|
"num_tokens": 1354267.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.5597916603088375,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4472,
|
|
"mean_token_accuracy": 0.10820634737610817,
|
|
"num_tokens": 1363949.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.6761926174163815,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4872,
|
|
"mean_token_accuracy": 0.1058058723807335,
|
|
"num_tokens": 1374405.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.449610376358033,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3896,
|
|
"mean_token_accuracy": 0.11227544099092483,
|
|
"num_tokens": 1384156.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.624826717376709,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.394,
|
|
"mean_token_accuracy": 0.11085910871624946,
|
|
"num_tokens": 1393896.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.4982311725616455,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2944,
|
|
"mean_token_accuracy": 0.11603493541479111,
|
|
"num_tokens": 1403842.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.578821229934692,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4013,
|
|
"mean_token_accuracy": 0.11297919154167176,
|
|
"num_tokens": 1412644.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.474055290222168,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3473,
|
|
"mean_token_accuracy": 0.12095814496278763,
|
|
"num_tokens": 1421815.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.541539335250855,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.10714265555143357,
|
|
"num_tokens": 1431572.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.482412481307984,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3723,
|
|
"mean_token_accuracy": 0.11449380144476891,
|
|
"num_tokens": 1440609.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.595385599136352,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.10856133922934533,
|
|
"num_tokens": 1451193.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.449068069458008,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2807,
|
|
"mean_token_accuracy": 0.11979811117053032,
|
|
"num_tokens": 1459772.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.479738807678222,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.395,
|
|
"mean_token_accuracy": 0.10759104117751121,
|
|
"num_tokens": 1469251.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.606679821014405,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5059,
|
|
"mean_token_accuracy": 0.11142713129520417,
|
|
"num_tokens": 1478090.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.525738525390625,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3508,
|
|
"mean_token_accuracy": 0.11475891843438149,
|
|
"num_tokens": 1488231.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.5654744625091555,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4112,
|
|
"mean_token_accuracy": 0.11717421114444733,
|
|
"num_tokens": 1496904.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.42963719367981,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.3443,
|
|
"mean_token_accuracy": 0.1201884925365448,
|
|
"num_tokens": 1506006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.449509525299073,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2919,
|
|
"mean_token_accuracy": 0.11583777889609337,
|
|
"num_tokens": 1515826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.541458606719971,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3781,
|
|
"mean_token_accuracy": 0.11131022721529008,
|
|
"num_tokens": 1525001.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.363485288619995,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3647,
|
|
"mean_token_accuracy": 0.11138168722391129,
|
|
"num_tokens": 1533647.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.46032567024231,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3677,
|
|
"mean_token_accuracy": 0.11274689063429832,
|
|
"num_tokens": 1542461.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.431656455993652,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.11651496887207032,
|
|
"num_tokens": 1552249.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.488580369949341,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4204,
|
|
"mean_token_accuracy": 0.11872618049383163,
|
|
"num_tokens": 1561570.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.569738483428955,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4492,
|
|
"mean_token_accuracy": 0.1142809510231018,
|
|
"num_tokens": 1572263.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.341160726547241,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2765,
|
|
"mean_token_accuracy": 0.11415041461586953,
|
|
"num_tokens": 1580828.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.458345603942871,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.269,
|
|
"mean_token_accuracy": 0.11674099043011665,
|
|
"num_tokens": 1589858.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.500254964828491,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.11778875812888145,
|
|
"num_tokens": 1598822.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.364452123641968,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2859,
|
|
"mean_token_accuracy": 0.11785781309008599,
|
|
"num_tokens": 1607508.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.370275688171387,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3014,
|
|
"mean_token_accuracy": 0.12148084938526153,
|
|
"num_tokens": 1616986.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.499317264556884,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3641,
|
|
"mean_token_accuracy": 0.11438111290335655,
|
|
"num_tokens": 1626940.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.419982290267944,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3283,
|
|
"mean_token_accuracy": 0.11768875047564506,
|
|
"num_tokens": 1636249.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.475973129272461,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.373,
|
|
"mean_token_accuracy": 0.12241241857409477,
|
|
"num_tokens": 1645943.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.43145170211792,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.11863628476858139,
|
|
"num_tokens": 1655119.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.374294900894165,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.11957648620009423,
|
|
"num_tokens": 1663635.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.394734907150268,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1718,
|
|
"mean_token_accuracy": 0.13117269724607467,
|
|
"num_tokens": 1672360.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.220319652557373,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.251,
|
|
"mean_token_accuracy": 0.1205068476498127,
|
|
"num_tokens": 1681750.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.459862565994262,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2708,
|
|
"mean_token_accuracy": 0.12147213593125343,
|
|
"num_tokens": 1690434.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.326650142669678,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.11960572525858879,
|
|
"num_tokens": 1699982.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.262086200714111,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.2058,
|
|
"mean_token_accuracy": 0.12053424194455147,
|
|
"num_tokens": 1709251.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.2985471248626705,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2876,
|
|
"mean_token_accuracy": 0.11529200449585915,
|
|
"num_tokens": 1718556.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.278677320480346,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.12173248827457428,
|
|
"num_tokens": 1728265.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.385457515716553,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2542,
|
|
"mean_token_accuracy": 0.12272520884871482,
|
|
"num_tokens": 1737537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.194164800643921,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1366,
|
|
"mean_token_accuracy": 0.1311381496489048,
|
|
"num_tokens": 1747357.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.393703508377075,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3576,
|
|
"mean_token_accuracy": 0.11244316771626472,
|
|
"num_tokens": 1757462.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.308323192596435,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.1857,
|
|
"mean_token_accuracy": 0.12801790982484818,
|
|
"num_tokens": 1766127.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.3302711009979244,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2864,
|
|
"mean_token_accuracy": 0.12558708786964418,
|
|
"num_tokens": 1775106.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.346054887771606,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.279,
|
|
"mean_token_accuracy": 0.12811500430107117,
|
|
"num_tokens": 1785626.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.297150611877441,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3037,
|
|
"mean_token_accuracy": 0.11734841465950012,
|
|
"num_tokens": 1795064.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.315353155136108,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2704,
|
|
"mean_token_accuracy": 0.12119710147380829,
|
|
"num_tokens": 1804429.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.390869808197022,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2921,
|
|
"mean_token_accuracy": 0.12317592203617096,
|
|
"num_tokens": 1813542.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.2793159008026125,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.2056,
|
|
"mean_token_accuracy": 0.12073831930756569,
|
|
"num_tokens": 1824172.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.2364945888519285,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2292,
|
|
"mean_token_accuracy": 0.12011673152446747,
|
|
"num_tokens": 1832989.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.346784162521362,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1914,
|
|
"mean_token_accuracy": 0.12780134081840516,
|
|
"num_tokens": 1842345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.243885612487793,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2414,
|
|
"mean_token_accuracy": 0.12187250629067421,
|
|
"num_tokens": 1851952.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.214503812789917,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2285,
|
|
"mean_token_accuracy": 0.12935626581311227,
|
|
"num_tokens": 1861029.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.397096061706543,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.3104,
|
|
"mean_token_accuracy": 0.12734212428331376,
|
|
"num_tokens": 1869650.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.451109504699707,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.3661,
|
|
"mean_token_accuracy": 0.12487528920173645,
|
|
"num_tokens": 1879078.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.1340961933135985,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.2023,
|
|
"mean_token_accuracy": 0.12111020982265472,
|
|
"num_tokens": 1888596.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.2194208145141605,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.2084,
|
|
"mean_token_accuracy": 0.13148325234651564,
|
|
"num_tokens": 1897342.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.287281084060669,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.1531,
|
|
"mean_token_accuracy": 0.13133467957377434,
|
|
"num_tokens": 1905685.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.356633090972901,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.3405,
|
|
"mean_token_accuracy": 0.12002272456884384,
|
|
"num_tokens": 1915195.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.303962469100952,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.3341,
|
|
"mean_token_accuracy": 0.11654869839549065,
|
|
"num_tokens": 1925156.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.244997501373291,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.12304776981472969,
|
|
"num_tokens": 1934521.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.287100887298584,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.12770192176103592,
|
|
"num_tokens": 1944160.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.196858263015747,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.13160740509629248,
|
|
"num_tokens": 1953022.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.052315664291382,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.1283707305788994,
|
|
"num_tokens": 1961544.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.301678705215454,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.2221,
|
|
"mean_token_accuracy": 0.12650251016020775,
|
|
"num_tokens": 1970319.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.141233491897583,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.13388170525431634,
|
|
"num_tokens": 1979582.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.205691766738892,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.2144,
|
|
"mean_token_accuracy": 0.1302635855972767,
|
|
"num_tokens": 1988422.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.159866285324097,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.1003,
|
|
"mean_token_accuracy": 0.13204355984926225,
|
|
"num_tokens": 1998125.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.109376859664917,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.13217169865965844,
|
|
"num_tokens": 2006993.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.156049728393555,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.1508,
|
|
"mean_token_accuracy": 0.13903949335217475,
|
|
"num_tokens": 2016901.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.173201704025269,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1903,
|
|
"mean_token_accuracy": 0.1270303227007389,
|
|
"num_tokens": 2026397.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.2164756774902346,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.1260007508099079,
|
|
"num_tokens": 2035241.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.195575380325318,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.128,
|
|
"mean_token_accuracy": 0.12700524181127548,
|
|
"num_tokens": 2044559.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.161809253692627,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.13099708110094072,
|
|
"num_tokens": 2055368.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.134675312042236,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.0976,
|
|
"mean_token_accuracy": 0.1294672280550003,
|
|
"num_tokens": 2064405.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.23328275680542,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 6.157,
|
|
"mean_token_accuracy": 0.13345658630132676,
|
|
"num_tokens": 2073341.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.192983865737915,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 6.2798,
|
|
"mean_token_accuracy": 0.12386398613452912,
|
|
"num_tokens": 2081701.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.240271043777466,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 6.0968,
|
|
"mean_token_accuracy": 0.1338454693555832,
|
|
"num_tokens": 2090662.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.076743459701538,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 6.1238,
|
|
"mean_token_accuracy": 0.1278868205845356,
|
|
"num_tokens": 2100351.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.224796867370605,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1608,
|
|
"mean_token_accuracy": 0.13114732205867768,
|
|
"num_tokens": 2108776.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.155978584289551,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.2038,
|
|
"mean_token_accuracy": 0.13971752375364305,
|
|
"num_tokens": 2117235.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.197133541107178,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.064,
|
|
"mean_token_accuracy": 0.1335673935711384,
|
|
"num_tokens": 2126482.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.223146295547485,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.13484406024217604,
|
|
"num_tokens": 2135949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.113941478729248,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 6.144,
|
|
"mean_token_accuracy": 0.12856294363737106,
|
|
"num_tokens": 2144887.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.211896467208862,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.0844,
|
|
"mean_token_accuracy": 0.12648672610521317,
|
|
"num_tokens": 2153159.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.130585336685181,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.13049330040812493,
|
|
"num_tokens": 2162408.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.195689630508423,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.1135,
|
|
"mean_token_accuracy": 0.12888743430376054,
|
|
"num_tokens": 2171407.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.045321702957153,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 5.9866,
|
|
"mean_token_accuracy": 0.13812673091888428,
|
|
"num_tokens": 2180281.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.090527582168579,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.13660623878240585,
|
|
"num_tokens": 2188901.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.258664798736572,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.2479,
|
|
"mean_token_accuracy": 0.12757005020976067,
|
|
"num_tokens": 2199284.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.136487579345703,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 6.0703,
|
|
"mean_token_accuracy": 0.13646215051412583,
|
|
"num_tokens": 2208013.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.13501935005188,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 6.1115,
|
|
"mean_token_accuracy": 0.13660111427307128,
|
|
"num_tokens": 2217444.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.019062089920044,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.0133,
|
|
"mean_token_accuracy": 0.13833465054631233,
|
|
"num_tokens": 2226596.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.099384546279907,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.12789982706308364,
|
|
"num_tokens": 2235441.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.202890872955322,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.1548,
|
|
"mean_token_accuracy": 0.12868092879652976,
|
|
"num_tokens": 2244783.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.064100122451782,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 6.022,
|
|
"mean_token_accuracy": 0.13114323765039443,
|
|
"num_tokens": 2254484.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.059143877029419,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.0315,
|
|
"mean_token_accuracy": 0.14302524775266648,
|
|
"num_tokens": 2263394.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 5.966811752319336,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.0015,
|
|
"mean_token_accuracy": 0.1347162365913391,
|
|
"num_tokens": 2272826.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.1172199726104735,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.0999,
|
|
"mean_token_accuracy": 0.1349620133638382,
|
|
"num_tokens": 2282169.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.115842723846436,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.0753,
|
|
"mean_token_accuracy": 0.13311911448836328,
|
|
"num_tokens": 2291432.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.1954936504364015,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 6.0596,
|
|
"mean_token_accuracy": 0.13753374814987182,
|
|
"num_tokens": 2300576.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.036804676055908,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.13158197253942489,
|
|
"num_tokens": 2310790.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.110608148574829,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.0361,
|
|
"mean_token_accuracy": 0.13192710280418396,
|
|
"num_tokens": 2319831.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 5.955552101135254,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 5.8805,
|
|
"mean_token_accuracy": 0.1360246866941452,
|
|
"num_tokens": 2329474.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.155193710327149,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 6.1836,
|
|
"mean_token_accuracy": 0.12781498804688454,
|
|
"num_tokens": 2338179.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.051835298538208,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.13405870422720909,
|
|
"num_tokens": 2346899.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.139889907836914,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.1316,
|
|
"mean_token_accuracy": 0.12390393391251564,
|
|
"num_tokens": 2356077.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.071658563613892,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 6.0648,
|
|
"mean_token_accuracy": 0.13771045356988906,
|
|
"num_tokens": 2365224.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.026415109634399,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 5.9646,
|
|
"mean_token_accuracy": 0.1458335816860199,
|
|
"num_tokens": 2375187.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.1658729076385494,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 6.176,
|
|
"mean_token_accuracy": 0.13546312600374222,
|
|
"num_tokens": 2383460.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.111374711990356,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 6.0838,
|
|
"mean_token_accuracy": 0.13621672317385675,
|
|
"num_tokens": 2392701.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 5.987979984283447,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.13854891061782837,
|
|
"num_tokens": 2401516.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.11806287765503,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 5.9854,
|
|
"mean_token_accuracy": 0.13647850081324578,
|
|
"num_tokens": 2410799.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.110712957382202,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 5.9572,
|
|
"mean_token_accuracy": 0.14616322070360183,
|
|
"num_tokens": 2419431.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 5.93685736656189,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.14728242307901382,
|
|
"num_tokens": 2427848.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 5.979397869110107,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 5.959,
|
|
"mean_token_accuracy": 0.1351412981748581,
|
|
"num_tokens": 2437960.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.161928987503051,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 6.0822,
|
|
"mean_token_accuracy": 0.14213989973068236,
|
|
"num_tokens": 2445835.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 5.935327577590942,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.964,
|
|
"mean_token_accuracy": 0.13782545179128647,
|
|
"num_tokens": 2454556.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.0836340427398685,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 6.0365,
|
|
"mean_token_accuracy": 0.13404568061232566,
|
|
"num_tokens": 2465301.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.053523588180542,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.0297,
|
|
"mean_token_accuracy": 0.13495606705546379,
|
|
"num_tokens": 2474085.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.07110185623169,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 5.9504,
|
|
"mean_token_accuracy": 0.1391334593296051,
|
|
"num_tokens": 2482439.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 5.964626693725586,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.14017563462257385,
|
|
"num_tokens": 2491877.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.162881469726562,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.1053,
|
|
"mean_token_accuracy": 0.13479262962937355,
|
|
"num_tokens": 2501669.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 5.949451684951782,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9907,
|
|
"mean_token_accuracy": 0.1403600715100765,
|
|
"num_tokens": 2511612.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.037490463256836,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 5.9322,
|
|
"mean_token_accuracy": 0.13493305146694184,
|
|
"num_tokens": 2520791.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.008893966674805,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.14006343558430673,
|
|
"num_tokens": 2529834.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.06941442489624,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.14169224575161934,
|
|
"num_tokens": 2539053.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 5.955056619644165,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 6.0424,
|
|
"mean_token_accuracy": 0.1379003144800663,
|
|
"num_tokens": 2549475.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.158879232406616,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.14125851467251777,
|
|
"num_tokens": 2558718.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 5.925163269042969,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.14257999509572983,
|
|
"num_tokens": 2567454.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 5.924022912979126,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.1416394293308258,
|
|
"num_tokens": 2575989.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 5.990731525421142,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 6.0301,
|
|
"mean_token_accuracy": 0.13861346766352653,
|
|
"num_tokens": 2585240.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.079441165924072,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 6.0616,
|
|
"mean_token_accuracy": 0.1348680131137371,
|
|
"num_tokens": 2593286.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.117265033721924,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 6.0306,
|
|
"mean_token_accuracy": 0.13561518117785454,
|
|
"num_tokens": 2602992.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 5.919422197341919,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.13701212778687477,
|
|
"num_tokens": 2611469.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.091077470779419,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.14297242164611818,
|
|
"num_tokens": 2621456.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 5.908285808563233,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.13964127004146576,
|
|
"num_tokens": 2630355.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 5.949282217025757,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.9258,
|
|
"mean_token_accuracy": 0.14554690718650817,
|
|
"num_tokens": 2639508.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 5.863205432891846,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.15139148458838464,
|
|
"num_tokens": 2648056.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.016834783554077,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 6.0407,
|
|
"mean_token_accuracy": 0.13517623394727707,
|
|
"num_tokens": 2657731.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.055109977722168,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.14319568127393723,
|
|
"num_tokens": 2666424.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.784654045104981,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.8094,
|
|
"mean_token_accuracy": 0.14697549343109131,
|
|
"num_tokens": 2674646.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.079193449020385,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 6.0074,
|
|
"mean_token_accuracy": 0.139281989634037,
|
|
"num_tokens": 2683295.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 5.972242116928101,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.9096,
|
|
"mean_token_accuracy": 0.14578085839748384,
|
|
"num_tokens": 2692220.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.005794477462769,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 6.1122,
|
|
"mean_token_accuracy": 0.1357429787516594,
|
|
"num_tokens": 2702095.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.048544406890869,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.13224004432559014,
|
|
"num_tokens": 2711440.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.103414249420166,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.14071377664804458,
|
|
"num_tokens": 2720564.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 5.971002054214478,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.13812775090336799,
|
|
"num_tokens": 2729442.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 5.980379676818847,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9752,
|
|
"mean_token_accuracy": 0.1382712244987488,
|
|
"num_tokens": 2738683.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.91906156539917,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.9438,
|
|
"mean_token_accuracy": 0.13993872255086898,
|
|
"num_tokens": 2747888.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 5.954296398162842,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.8147,
|
|
"mean_token_accuracy": 0.14942429587244987,
|
|
"num_tokens": 2756667.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 5.962799215316773,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.9992,
|
|
"mean_token_accuracy": 0.1386643148958683,
|
|
"num_tokens": 2765116.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.863136100769043,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.8534,
|
|
"mean_token_accuracy": 0.144050994515419,
|
|
"num_tokens": 2774259.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 5.9968834400177,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 5.8827,
|
|
"mean_token_accuracy": 0.14217742010951043,
|
|
"num_tokens": 2782988.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 5.882682275772095,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8867,
|
|
"mean_token_accuracy": 0.14646163433790207,
|
|
"num_tokens": 2791409.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.024690246582031,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9582,
|
|
"mean_token_accuracy": 0.1408964402973652,
|
|
"num_tokens": 2800644.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 5.89728102684021,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.1505585491657257,
|
|
"num_tokens": 2809838.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.996928453445435,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.14650033861398698,
|
|
"num_tokens": 2818972.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 5.950346803665161,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.9019,
|
|
"mean_token_accuracy": 0.14394040852785112,
|
|
"num_tokens": 2827733.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.0365362644195555,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9959,
|
|
"mean_token_accuracy": 0.14076455160975457,
|
|
"num_tokens": 2837300.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 5.97183837890625,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.9156,
|
|
"mean_token_accuracy": 0.14617259949445724,
|
|
"num_tokens": 2846076.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.862637710571289,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.8334,
|
|
"mean_token_accuracy": 0.14296823143959045,
|
|
"num_tokens": 2855523.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 5.930409288406372,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.13584407344460486,
|
|
"num_tokens": 2864277.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.0211245059967045,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.14090201109647751,
|
|
"num_tokens": 2873561.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.93624324798584,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8459,
|
|
"mean_token_accuracy": 0.14749322459101677,
|
|
"num_tokens": 2882449.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 5.935066652297974,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.1558266080915928,
|
|
"num_tokens": 2890862.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.831592226028443,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.14984015226364136,
|
|
"num_tokens": 2899611.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.008182621002197,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.9418,
|
|
"mean_token_accuracy": 0.1445327214896679,
|
|
"num_tokens": 2908111.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.0264496326446535,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.9131,
|
|
"mean_token_accuracy": 0.1450109988451004,
|
|
"num_tokens": 2917194.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 5.816270923614502,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.14895178824663163,
|
|
"num_tokens": 2926684.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.822729587554932,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.8401,
|
|
"mean_token_accuracy": 0.14757028147578238,
|
|
"num_tokens": 2936094.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 5.919861888885498,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.859,
|
|
"mean_token_accuracy": 0.14859411120414734,
|
|
"num_tokens": 2944389.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.91385817527771,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.14679256677627564,
|
|
"num_tokens": 2954466.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 5.983486795425415,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 6.0562,
|
|
"mean_token_accuracy": 0.13626678064465522,
|
|
"num_tokens": 2965403.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.138475179672241,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 6.067,
|
|
"mean_token_accuracy": 0.14294126704335214,
|
|
"num_tokens": 2975896.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.808540487289429,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.9174,
|
|
"mean_token_accuracy": 0.1457381658256054,
|
|
"num_tokens": 2984937.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.846891403198242,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.14553934037685395,
|
|
"num_tokens": 2994052.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 5.9891563892364506,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.15324456840753556,
|
|
"num_tokens": 3003274.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 5.889054298400879,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.1483180269598961,
|
|
"num_tokens": 3011440.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 5.936949825286865,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.9529,
|
|
"mean_token_accuracy": 0.14169826358556747,
|
|
"num_tokens": 3021032.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 5.959151649475098,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.14800066351890565,
|
|
"num_tokens": 3030160.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 5.9255006313323975,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.14852431640028954,
|
|
"num_tokens": 3039098.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.966451215744018,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.1453654244542122,
|
|
"num_tokens": 3048679.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.845665216445923,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.14851621985435487,
|
|
"num_tokens": 3057613.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.967752313613891,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 6.0021,
|
|
"mean_token_accuracy": 0.144612093269825,
|
|
"num_tokens": 3066291.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 5.970147180557251,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.14115611016750335,
|
|
"num_tokens": 3075897.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.9527112483978275,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.8823,
|
|
"mean_token_accuracy": 0.1441874161362648,
|
|
"num_tokens": 3085193.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 5.956134605407715,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.14315434247255326,
|
|
"num_tokens": 3094335.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.917848062515259,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.9943,
|
|
"mean_token_accuracy": 0.13993434682488443,
|
|
"num_tokens": 3103964.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 5.977165699005127,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.14386510774493216,
|
|
"num_tokens": 3113321.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.884727621078492,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.8754,
|
|
"mean_token_accuracy": 0.14615907445549964,
|
|
"num_tokens": 3122467.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.038534307479859,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.14586948603391647,
|
|
"num_tokens": 3131239.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.816018295288086,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.14061915054917334,
|
|
"num_tokens": 3140568.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 5.981604433059692,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.9145,
|
|
"mean_token_accuracy": 0.14344506785273553,
|
|
"num_tokens": 3151227.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.8707318782806395,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.15050104558467864,
|
|
"num_tokens": 3159865.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.816216993331909,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.7766,
|
|
"mean_token_accuracy": 0.15594457387924193,
|
|
"num_tokens": 3169832.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.904452180862426,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.14405087232589722,
|
|
"num_tokens": 3180357.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.952069711685181,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8289,
|
|
"mean_token_accuracy": 0.14626632928848265,
|
|
"num_tokens": 3189663.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.891729259490967,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.9203,
|
|
"mean_token_accuracy": 0.14412349686026574,
|
|
"num_tokens": 3199578.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.98569164276123,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.1546083763241768,
|
|
"num_tokens": 3208839.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.880684232711792,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.1447443701326847,
|
|
"num_tokens": 3217449.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.84385576248169,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.1476930148899555,
|
|
"num_tokens": 3226561.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.956462335586548,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8734,
|
|
"mean_token_accuracy": 0.1562822014093399,
|
|
"num_tokens": 3235400.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.929642915725708,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.9135,
|
|
"mean_token_accuracy": 0.14424390718340874,
|
|
"num_tokens": 3244862.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.870706796646118,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.8317,
|
|
"mean_token_accuracy": 0.14855084866285323,
|
|
"num_tokens": 3254370.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 5.925116539001465,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.14976725578308106,
|
|
"num_tokens": 3264079.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.893246698379516,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.14768336340785027,
|
|
"num_tokens": 3273315.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.878500699996948,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.8005,
|
|
"mean_token_accuracy": 0.1478862389922142,
|
|
"num_tokens": 3282045.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.899237442016601,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.9011,
|
|
"mean_token_accuracy": 0.14373476877808572,
|
|
"num_tokens": 3291596.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.820509672164917,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.7256,
|
|
"mean_token_accuracy": 0.1517377719283104,
|
|
"num_tokens": 3300407.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.867762184143066,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.15600597709417344,
|
|
"num_tokens": 3309848.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.801882362365722,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.1472492039203644,
|
|
"num_tokens": 3319031.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.922190523147583,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.8236,
|
|
"mean_token_accuracy": 0.14326767176389693,
|
|
"num_tokens": 3327918.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.751756238937378,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8449,
|
|
"mean_token_accuracy": 0.14434421062469482,
|
|
"num_tokens": 3337071.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.079517030715943,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.9039,
|
|
"mean_token_accuracy": 0.14523821473121643,
|
|
"num_tokens": 3346334.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 5.8847856521606445,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.8307,
|
|
"mean_token_accuracy": 0.1462329663336277,
|
|
"num_tokens": 3354932.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.716736555099487,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.15522432029247285,
|
|
"num_tokens": 3364345.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.929656648635865,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.8707,
|
|
"mean_token_accuracy": 0.1472846657037735,
|
|
"num_tokens": 3372918.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.718468713760376,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.7288,
|
|
"mean_token_accuracy": 0.1567766509950161,
|
|
"num_tokens": 3381815.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.843803644180298,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7803,
|
|
"mean_token_accuracy": 0.14712713211774825,
|
|
"num_tokens": 3391057.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.03563289642334,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.961,
|
|
"mean_token_accuracy": 0.1439568117260933,
|
|
"num_tokens": 3401254.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.808206081390381,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8897,
|
|
"mean_token_accuracy": 0.14927712976932525,
|
|
"num_tokens": 3411031.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.898315477371216,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.1547455981373787,
|
|
"num_tokens": 3420154.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.990719413757324,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.912,
|
|
"mean_token_accuracy": 0.1456889122724533,
|
|
"num_tokens": 3429285.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.868764209747314,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.8969,
|
|
"mean_token_accuracy": 0.14278291612863542,
|
|
"num_tokens": 3438065.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.021544933319092,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.145746049284935,
|
|
"num_tokens": 3447534.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.836647796630859,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.8529,
|
|
"mean_token_accuracy": 0.15536943227052688,
|
|
"num_tokens": 3456435.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.903014087677002,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.8192,
|
|
"mean_token_accuracy": 0.15386642515659332,
|
|
"num_tokens": 3464982.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.938276910781861,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.9591,
|
|
"mean_token_accuracy": 0.14135469049215316,
|
|
"num_tokens": 3474585.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.797132873535157,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.1504616156220436,
|
|
"num_tokens": 3483164.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.866785955429077,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.7921,
|
|
"mean_token_accuracy": 0.15038491189479827,
|
|
"num_tokens": 3492984.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.715900993347168,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.15855061560869216,
|
|
"num_tokens": 3500356.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.965412521362305,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.1494261384010315,
|
|
"num_tokens": 3509792.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.812705039978027,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.7588,
|
|
"mean_token_accuracy": 0.1485971011221409,
|
|
"num_tokens": 3519340.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.796240758895874,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.155721578001976,
|
|
"num_tokens": 3528846.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.790179777145386,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.15263200104236602,
|
|
"num_tokens": 3537766.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.85261492729187,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.8082,
|
|
"mean_token_accuracy": 0.1515938565135002,
|
|
"num_tokens": 3546724.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.695097827911377,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.721,
|
|
"mean_token_accuracy": 0.15915379524230958,
|
|
"num_tokens": 3555599.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.895123863220215,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7653,
|
|
"mean_token_accuracy": 0.15158458054065704,
|
|
"num_tokens": 3564754.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.59046483039856,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.15768528878688812,
|
|
"num_tokens": 3573166.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.958360719680786,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.14737681299448013,
|
|
"num_tokens": 3581602.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.824247026443482,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.16191418766975402,
|
|
"num_tokens": 3590946.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.746830797195434,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.778,
|
|
"mean_token_accuracy": 0.1522221401333809,
|
|
"num_tokens": 3599888.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.830930376052857,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.7984,
|
|
"mean_token_accuracy": 0.15850079655647278,
|
|
"num_tokens": 3609773.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.804241085052491,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.15674369931221008,
|
|
"num_tokens": 3618820.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.864436960220337,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.1484947569668293,
|
|
"num_tokens": 3629010.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.776125764846801,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.771,
|
|
"mean_token_accuracy": 0.15559061765670776,
|
|
"num_tokens": 3636915.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.798781251907348,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1556951105594635,
|
|
"num_tokens": 3646011.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.862015438079834,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.15725564807653428,
|
|
"num_tokens": 3655059.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.859493160247803,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.8152,
|
|
"mean_token_accuracy": 0.15456283688545228,
|
|
"num_tokens": 3664553.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.841559171676636,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.7509,
|
|
"mean_token_accuracy": 0.1524602711200714,
|
|
"num_tokens": 3673604.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.810849189758301,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.15616438090801238,
|
|
"num_tokens": 3682634.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.778779172897339,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.1506836846470833,
|
|
"num_tokens": 3691961.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.758075857162476,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7759,
|
|
"mean_token_accuracy": 0.14631137028336524,
|
|
"num_tokens": 3701412.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.8458953380584715,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.1556076392531395,
|
|
"num_tokens": 3710449.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.8543816089630125,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.7846,
|
|
"mean_token_accuracy": 0.14759426265954972,
|
|
"num_tokens": 3718654.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.727865552902221,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.7796,
|
|
"mean_token_accuracy": 0.1492263525724411,
|
|
"num_tokens": 3728660.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.855515861511231,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.8027,
|
|
"mean_token_accuracy": 0.15391339361667633,
|
|
"num_tokens": 3738085.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.804375648498535,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.15261952951550484,
|
|
"num_tokens": 3747727.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.843009185791016,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.8405,
|
|
"mean_token_accuracy": 0.14722344428300857,
|
|
"num_tokens": 3757864.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.736613512039185,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.15391422659158707,
|
|
"num_tokens": 3766843.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.846935081481933,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.15506419092416762,
|
|
"num_tokens": 3776171.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.807502889633179,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.7536,
|
|
"mean_token_accuracy": 0.15907568335533143,
|
|
"num_tokens": 3785545.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.7233068466186525,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.15531886667013167,
|
|
"num_tokens": 3794110.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.827488946914673,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.8275,
|
|
"mean_token_accuracy": 0.15153776109218597,
|
|
"num_tokens": 3803727.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.832465267181396,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.14992659762501717,
|
|
"num_tokens": 3812904.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.044683599472046,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.8619,
|
|
"mean_token_accuracy": 0.14960845410823823,
|
|
"num_tokens": 3822009.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.7061169147491455,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.16072025448083876,
|
|
"num_tokens": 3830877.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.975783109664917,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.8733,
|
|
"mean_token_accuracy": 0.1454279713332653,
|
|
"num_tokens": 3839876.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.8507367134094235,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.15541226267814637,
|
|
"num_tokens": 3848769.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.8066075325012205,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.15266919434070586,
|
|
"num_tokens": 3857676.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.805453491210938,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.15749767869710923,
|
|
"num_tokens": 3867098.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.636935901641846,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.15111172050237656,
|
|
"num_tokens": 3876247.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.827657556533813,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.7641,
|
|
"mean_token_accuracy": 0.15805181115865707,
|
|
"num_tokens": 3885747.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.9260594844818115,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.15000726729631425,
|
|
"num_tokens": 3896077.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.862950849533081,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.1381701298058033,
|
|
"num_tokens": 3906323.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.887103509902954,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.15319084525108337,
|
|
"num_tokens": 3915510.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.845855331420898,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.15369762405753135,
|
|
"num_tokens": 3924799.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.783837032318115,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.7876,
|
|
"mean_token_accuracy": 0.1510419577360153,
|
|
"num_tokens": 3933675.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.8255650997161865,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.7387,
|
|
"mean_token_accuracy": 0.15646950602531434,
|
|
"num_tokens": 3942086.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.797743606567383,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.7548,
|
|
"mean_token_accuracy": 0.15239814668893814,
|
|
"num_tokens": 3950626.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.686432552337647,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.16219130754470826,
|
|
"num_tokens": 3959006.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.741449356079102,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.7499,
|
|
"mean_token_accuracy": 0.15800593346357344,
|
|
"num_tokens": 3968177.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.87012619972229,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.7029,
|
|
"mean_token_accuracy": 0.15574318766593934,
|
|
"num_tokens": 3977052.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.694927978515625,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.712,
|
|
"mean_token_accuracy": 0.15181038826704024,
|
|
"num_tokens": 3985101.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.757119941711426,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.16106333136558532,
|
|
"num_tokens": 3992936.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.815750551223755,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.8182,
|
|
"mean_token_accuracy": 0.15310252755880355,
|
|
"num_tokens": 4001702.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.8231817245483395,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.15513441413640977,
|
|
"num_tokens": 4011639.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.750963401794434,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.16204652339220046,
|
|
"num_tokens": 4021420.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.661520290374756,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6915,
|
|
"mean_token_accuracy": 0.14866186380386354,
|
|
"num_tokens": 4030869.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.72034273147583,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.16509579569101335,
|
|
"num_tokens": 4039573.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.606214094161987,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.15629229545593262,
|
|
"num_tokens": 4048684.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.723562002182007,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.8047,
|
|
"mean_token_accuracy": 0.15196271240711212,
|
|
"num_tokens": 4057968.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.904633522033691,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.7148,
|
|
"mean_token_accuracy": 0.15125639140605926,
|
|
"num_tokens": 4068057.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.75338134765625,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.15991646945476531,
|
|
"num_tokens": 4077141.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.744376277923584,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.7003,
|
|
"mean_token_accuracy": 0.15504838824272155,
|
|
"num_tokens": 4085227.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.732967853546143,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.16520010381937028,
|
|
"num_tokens": 4093674.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.81893310546875,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.1498129650950432,
|
|
"num_tokens": 4103466.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.882892417907715,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.1567348837852478,
|
|
"num_tokens": 4111833.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.696685934066773,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.7082,
|
|
"mean_token_accuracy": 0.1504954993724823,
|
|
"num_tokens": 4121546.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.723720836639404,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.16130448281764984,
|
|
"num_tokens": 4130408.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.756785297393799,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.8075,
|
|
"mean_token_accuracy": 0.15824081003665924,
|
|
"num_tokens": 4139793.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.864732646942139,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6672,
|
|
"mean_token_accuracy": 0.16205901950597762,
|
|
"num_tokens": 4148192.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.560827684402466,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.15886650383472442,
|
|
"num_tokens": 4157960.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.59301118850708,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.16533980667591094,
|
|
"num_tokens": 4166356.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.80047197341919,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.8187,
|
|
"mean_token_accuracy": 0.14628092870116233,
|
|
"num_tokens": 4176139.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.802434635162354,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.15827721282839774,
|
|
"num_tokens": 4185583.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.715236043930053,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.78,
|
|
"mean_token_accuracy": 0.1517994225025177,
|
|
"num_tokens": 4194275.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.754878044128418,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.7196,
|
|
"mean_token_accuracy": 0.15217152535915374,
|
|
"num_tokens": 4203424.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.72383394241333,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6788,
|
|
"mean_token_accuracy": 0.15740089416503905,
|
|
"num_tokens": 4212452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.798124599456787,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.7826,
|
|
"mean_token_accuracy": 0.15464788377285005,
|
|
"num_tokens": 4221639.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.684769153594971,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.15623509585857392,
|
|
"num_tokens": 4231362.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.801016712188721,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.15280152559280397,
|
|
"num_tokens": 4241035.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.819127893447876,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.6748,
|
|
"mean_token_accuracy": 0.15776295959949493,
|
|
"num_tokens": 4250275.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.641567945480347,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.14925756752490998,
|
|
"num_tokens": 4259952.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.823996067047119,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.1649850994348526,
|
|
"num_tokens": 4269985.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.620763301849365,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.1591414988040924,
|
|
"num_tokens": 4278317.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.700749444961548,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6617,
|
|
"mean_token_accuracy": 0.15998956114053725,
|
|
"num_tokens": 4286633.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.732091760635376,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6416,
|
|
"mean_token_accuracy": 0.15784741938114166,
|
|
"num_tokens": 4295696.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.74935622215271,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.7175,
|
|
"mean_token_accuracy": 0.15652929842472077,
|
|
"num_tokens": 4305139.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.68619704246521,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.1622218132019043,
|
|
"num_tokens": 4314029.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.705938053131104,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.7354,
|
|
"mean_token_accuracy": 0.15496601909399033,
|
|
"num_tokens": 4323667.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.8132116317749025,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.1555030509829521,
|
|
"num_tokens": 4333456.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.796841716766357,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.15186412781476974,
|
|
"num_tokens": 4342527.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.733500623703003,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6578,
|
|
"mean_token_accuracy": 0.15209388211369515,
|
|
"num_tokens": 4351294.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.716574573516846,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.664,
|
|
"mean_token_accuracy": 0.15844270288944245,
|
|
"num_tokens": 4361596.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.748371124267578,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.15820184350013733,
|
|
"num_tokens": 4370917.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.66724534034729,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.15223393589258194,
|
|
"num_tokens": 4380244.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.791155099868774,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.1528972566127777,
|
|
"num_tokens": 4389852.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.754044246673584,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.7307,
|
|
"mean_token_accuracy": 0.15377760976552962,
|
|
"num_tokens": 4399743.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.829539442062378,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.6773,
|
|
"mean_token_accuracy": 0.1586298957467079,
|
|
"num_tokens": 4408661.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.641575002670288,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.16201509684324264,
|
|
"num_tokens": 4417671.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.734684228897095,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.7229,
|
|
"mean_token_accuracy": 0.15162376314401627,
|
|
"num_tokens": 4426850.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.829426002502442,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.15216446965932845,
|
|
"num_tokens": 4435769.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.81864972114563,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.7407,
|
|
"mean_token_accuracy": 0.15777725130319595,
|
|
"num_tokens": 4445521.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.732977390289307,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.7357,
|
|
"mean_token_accuracy": 0.1560164675116539,
|
|
"num_tokens": 4454674.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.858603000640869,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.15934987515211105,
|
|
"num_tokens": 4464035.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.726704406738281,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.6002,
|
|
"mean_token_accuracy": 0.1607057973742485,
|
|
"num_tokens": 4472055.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.669188404083252,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.16063073128461838,
|
|
"num_tokens": 4480669.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.813586473464966,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.7006,
|
|
"mean_token_accuracy": 0.16175678223371506,
|
|
"num_tokens": 4489481.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.664542865753174,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.16573526561260224,
|
|
"num_tokens": 4497508.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.650903415679932,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6594,
|
|
"mean_token_accuracy": 0.16277491748332978,
|
|
"num_tokens": 4506373.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.782987022399903,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.7177,
|
|
"mean_token_accuracy": 0.15605076253414155,
|
|
"num_tokens": 4516283.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.701898193359375,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.1695755124092102,
|
|
"num_tokens": 4524276.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.653223943710327,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.667,
|
|
"mean_token_accuracy": 0.16021030247211457,
|
|
"num_tokens": 4532951.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.747987127304077,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.1644655093550682,
|
|
"num_tokens": 4542229.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.686886167526245,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.5713,
|
|
"mean_token_accuracy": 0.16310817152261733,
|
|
"num_tokens": 4551126.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.611570644378662,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.679,
|
|
"mean_token_accuracy": 0.16197994947433472,
|
|
"num_tokens": 4560628.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.785298919677734,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.7268,
|
|
"mean_token_accuracy": 0.15670448988676072,
|
|
"num_tokens": 4570184.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.70731635093689,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.16156910210847855,
|
|
"num_tokens": 4580357.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.839704275131226,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.7768,
|
|
"mean_token_accuracy": 0.1487571582198143,
|
|
"num_tokens": 4589965.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.740112066268921,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.16340472996234895,
|
|
"num_tokens": 4598753.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.633929061889648,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6597,
|
|
"mean_token_accuracy": 0.16298450231552125,
|
|
"num_tokens": 4608698.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.745545530319214,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.7676,
|
|
"mean_token_accuracy": 0.1568822406232357,
|
|
"num_tokens": 4618137.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.694258832931519,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.16162560731172562,
|
|
"num_tokens": 4627468.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.601826763153076,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.167683382332325,
|
|
"num_tokens": 4636659.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.648157739639283,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.1581842228770256,
|
|
"num_tokens": 4644969.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.7688682079315186,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.15401836931705476,
|
|
"num_tokens": 4653930.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.706395292282105,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.1635697916150093,
|
|
"num_tokens": 4663146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.644166040420532,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.15531763583421707,
|
|
"num_tokens": 4671874.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.625101566314697,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.578,
|
|
"mean_token_accuracy": 0.1623372033238411,
|
|
"num_tokens": 4680811.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.786676645278931,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.1630154401063919,
|
|
"num_tokens": 4689977.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.6473369121551515,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.1666818454861641,
|
|
"num_tokens": 4698479.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.558276653289795,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.5995,
|
|
"mean_token_accuracy": 0.1562129810452461,
|
|
"num_tokens": 4707575.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.7299939632415775,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.1641583114862442,
|
|
"num_tokens": 4717015.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.690065193176269,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.15410696864128112,
|
|
"num_tokens": 4726466.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.794637441635132,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.16310942322015762,
|
|
"num_tokens": 4736497.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.648622655868531,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.1570078417658806,
|
|
"num_tokens": 4745693.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.650327682495117,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.17139142453670503,
|
|
"num_tokens": 4754274.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.747675991058349,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.7886,
|
|
"mean_token_accuracy": 0.15042773261666298,
|
|
"num_tokens": 4765607.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.7171971797943115,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.16136786639690398,
|
|
"num_tokens": 4775291.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.59135890007019,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.5037,
|
|
"mean_token_accuracy": 0.16423833072185517,
|
|
"num_tokens": 4783859.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.5703614234924315,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.16074053645133973,
|
|
"num_tokens": 4792891.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.6992326259613035,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.15850717574357986,
|
|
"num_tokens": 4801551.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.765617036819458,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.617,
|
|
"mean_token_accuracy": 0.1606222003698349,
|
|
"num_tokens": 4810430.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.609820175170898,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.1620870128273964,
|
|
"num_tokens": 4819156.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.7782470703125,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6495,
|
|
"mean_token_accuracy": 0.15833018720149994,
|
|
"num_tokens": 4827724.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.689379119873047,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.5754,
|
|
"mean_token_accuracy": 0.16985357105731963,
|
|
"num_tokens": 4836954.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.694972991943359,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.6895,
|
|
"mean_token_accuracy": 0.15483302474021912,
|
|
"num_tokens": 4847504.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.720165061950683,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.6209,
|
|
"mean_token_accuracy": 0.16614843010902405,
|
|
"num_tokens": 4856105.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.61157546043396,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.6128,
|
|
"mean_token_accuracy": 0.16402403861284257,
|
|
"num_tokens": 4866118.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.756872844696045,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.6501,
|
|
"mean_token_accuracy": 0.16168341040611267,
|
|
"num_tokens": 4875242.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.771356153488159,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.16138535365462303,
|
|
"num_tokens": 4884726.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.623738479614258,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.15921541154384614,
|
|
"num_tokens": 4893178.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.808769464492798,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.16165247559547424,
|
|
"num_tokens": 4903126.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.619534492492676,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.17080911844968796,
|
|
"num_tokens": 4912069.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.607888507843017,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.16749428808689118,
|
|
"num_tokens": 4921014.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.537565088272094,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.16741064935922623,
|
|
"num_tokens": 4930382.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.759979391098023,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.15423294603824617,
|
|
"num_tokens": 4939672.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.817228889465332,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.15111590325832366,
|
|
"num_tokens": 4949186.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.6610682010650635,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15599125772714614,
|
|
"num_tokens": 4958155.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.574031972885132,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.16694373190402984,
|
|
"num_tokens": 4966524.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.665495204925537,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.5993,
|
|
"mean_token_accuracy": 0.16144806295633315,
|
|
"num_tokens": 4976066.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.661115884780884,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.17269045412540435,
|
|
"num_tokens": 4984957.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.5876758098602295,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.1622341826558113,
|
|
"num_tokens": 4994430.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.5405677318572994,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.623,
|
|
"mean_token_accuracy": 0.1629298061132431,
|
|
"num_tokens": 5003893.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.660926103591919,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.1635463997721672,
|
|
"num_tokens": 5014083.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.621028232574463,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.16685888916254044,
|
|
"num_tokens": 5023025.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.596793222427368,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15907337963581086,
|
|
"num_tokens": 5032620.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.791715097427368,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.15750645697116852,
|
|
"num_tokens": 5041773.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.659903049468994,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.6808,
|
|
"mean_token_accuracy": 0.1559741899371147,
|
|
"num_tokens": 5051450.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.641678237915039,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.1551765412092209,
|
|
"num_tokens": 5061172.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.652740812301635,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5455,
|
|
"mean_token_accuracy": 0.1640415072441101,
|
|
"num_tokens": 5071161.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.610337162017823,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1642090708017349,
|
|
"num_tokens": 5080884.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.643430471420288,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.5696,
|
|
"mean_token_accuracy": 0.16299497783184053,
|
|
"num_tokens": 5090164.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.54939866065979,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.1628969594836235,
|
|
"num_tokens": 5098700.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.79123969078064,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.769,
|
|
"mean_token_accuracy": 0.14941132217645645,
|
|
"num_tokens": 5107713.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.765942716598511,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.15038875490427017,
|
|
"num_tokens": 5117532.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.685317707061768,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.5187,
|
|
"mean_token_accuracy": 0.16634505540132521,
|
|
"num_tokens": 5126891.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.571315050125122,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.4884,
|
|
"mean_token_accuracy": 0.16462970823049544,
|
|
"num_tokens": 5135608.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.643984651565551,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.15804445147514343,
|
|
"num_tokens": 5145055.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.702338075637817,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.16131939738988876,
|
|
"num_tokens": 5154742.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.640383243560791,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15742480158805847,
|
|
"num_tokens": 5163876.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.638509082794189,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.1609307512640953,
|
|
"num_tokens": 5173614.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.70156888961792,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.1623079940676689,
|
|
"num_tokens": 5182061.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.7618965148925785,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.14517047330737115,
|
|
"num_tokens": 5191661.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.767496252059937,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.15727835297584533,
|
|
"num_tokens": 5200624.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.6672691822052,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.15578907281160354,
|
|
"num_tokens": 5209741.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.71718430519104,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.16819592118263244,
|
|
"num_tokens": 5218877.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.673211860656738,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.6996,
|
|
"mean_token_accuracy": 0.15367967188358306,
|
|
"num_tokens": 5229153.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.635143899917603,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.16222159564495087,
|
|
"num_tokens": 5238561.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.709632921218872,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.16289447247982025,
|
|
"num_tokens": 5248135.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.6386292457580565,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.5654,
|
|
"mean_token_accuracy": 0.16689260303974152,
|
|
"num_tokens": 5257286.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.671214628219604,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.7306,
|
|
"mean_token_accuracy": 0.15510661229491235,
|
|
"num_tokens": 5266595.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.700104284286499,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.5257,
|
|
"mean_token_accuracy": 0.1626771479845047,
|
|
"num_tokens": 5275651.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.505528211593628,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.16999822109937668,
|
|
"num_tokens": 5284596.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.670961904525757,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.16004635393619537,
|
|
"num_tokens": 5292410.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.590500545501709,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.16961989551782608,
|
|
"num_tokens": 5301124.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.697359323501587,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.6064,
|
|
"mean_token_accuracy": 0.16648687422275543,
|
|
"num_tokens": 5310571.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.662830972671509,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.16593839973211288,
|
|
"num_tokens": 5319746.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.622473859786988,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.6595,
|
|
"mean_token_accuracy": 0.16147310808300971,
|
|
"num_tokens": 5329734.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.6491858005523685,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.17032976001501082,
|
|
"num_tokens": 5338405.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.620096254348755,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.6705,
|
|
"mean_token_accuracy": 0.1593254551291466,
|
|
"num_tokens": 5348179.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.836646986007691,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.7065,
|
|
"mean_token_accuracy": 0.15110059678554535,
|
|
"num_tokens": 5358035.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.599517440795898,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.17012663632631303,
|
|
"num_tokens": 5366713.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.542704105377197,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.16873355507850646,
|
|
"num_tokens": 5375245.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.587150430679321,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.16696805357933045,
|
|
"num_tokens": 5384097.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.721682119369507,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.15409955456852914,
|
|
"num_tokens": 5393611.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.687287282943726,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.6073,
|
|
"mean_token_accuracy": 0.16065794229507446,
|
|
"num_tokens": 5402332.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.523683404922485,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.1698683112859726,
|
|
"num_tokens": 5411415.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.7273612976074215,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.17287943363189698,
|
|
"num_tokens": 5419742.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.498819160461426,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.17199851274490358,
|
|
"num_tokens": 5428689.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.7247068881988525,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.1559805117547512,
|
|
"num_tokens": 5438096.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.657676792144775,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.16129023730754852,
|
|
"num_tokens": 5446726.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.5872002124786375,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.6677,
|
|
"mean_token_accuracy": 0.15905494391918182,
|
|
"num_tokens": 5456275.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.700059175491333,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.16636704355478288,
|
|
"num_tokens": 5466135.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.551216793060303,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.17257890850305557,
|
|
"num_tokens": 5474882.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.448128414154053,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.17420113384723662,
|
|
"num_tokens": 5484856.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.69349365234375,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15520315021276473,
|
|
"num_tokens": 5493840.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.653994464874268,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.16332905516028404,
|
|
"num_tokens": 5502655.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.607406282424927,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.5109,
|
|
"mean_token_accuracy": 0.17501745223999024,
|
|
"num_tokens": 5511640.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.5393799304962155,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.4996,
|
|
"mean_token_accuracy": 0.1669514074921608,
|
|
"num_tokens": 5520704.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.605220365524292,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5816,
|
|
"mean_token_accuracy": 0.16140030473470687,
|
|
"num_tokens": 5531090.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.445592117976193,
|
|
"eval_loss": 5.563920497894287,
|
|
"eval_mean_token_accuracy": 0.17285948360267395,
|
|
"eval_num_tokens": 5531090.0,
|
|
"eval_runtime": 27.6695,
|
|
"eval_samples_per_second": 1364.789,
|
|
"eval_steps_per_second": 170.621,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.619354915618897,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.6279,
|
|
"mean_token_accuracy": 0.16189804971218108,
|
|
"num_tokens": 5539905.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.790455722808838,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.66,
|
|
"mean_token_accuracy": 0.15732589215040207,
|
|
"num_tokens": 5549052.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.793611192703247,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.6652,
|
|
"mean_token_accuracy": 0.1621344655752182,
|
|
"num_tokens": 5558156.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.588698101043701,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.574,
|
|
"mean_token_accuracy": 0.1657869517803192,
|
|
"num_tokens": 5567367.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.6186281681060795,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.16135193556547164,
|
|
"num_tokens": 5576883.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.7037670612335205,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.5479,
|
|
"mean_token_accuracy": 0.16849476248025894,
|
|
"num_tokens": 5586050.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.73937029838562,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.719,
|
|
"mean_token_accuracy": 0.15612117648124696,
|
|
"num_tokens": 5595933.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.689214468002319,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.16068582087755204,
|
|
"num_tokens": 5604832.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.606196403503418,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.16500435769557953,
|
|
"num_tokens": 5614077.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.654494285583496,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.16322938948869706,
|
|
"num_tokens": 5622971.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.576167821884155,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.16635890752077104,
|
|
"num_tokens": 5631356.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.55122127532959,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.5086,
|
|
"mean_token_accuracy": 0.16659390032291413,
|
|
"num_tokens": 5641095.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.564494895935058,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.17219194620847703,
|
|
"num_tokens": 5651311.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.630851888656617,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.16819642186164857,
|
|
"num_tokens": 5659957.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.5410982131958,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.16320393234491348,
|
|
"num_tokens": 5668876.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.545115947723389,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.16713176518678666,
|
|
"num_tokens": 5677809.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.5903150081634525,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17611153572797775,
|
|
"num_tokens": 5687055.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.475444793701172,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.16294189989566804,
|
|
"num_tokens": 5696394.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.687202072143554,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16350055485963821,
|
|
"num_tokens": 5704372.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.4938570022583,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.4259,
|
|
"mean_token_accuracy": 0.17429800778627397,
|
|
"num_tokens": 5713535.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.456874084472656,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.17394353300333024,
|
|
"num_tokens": 5722559.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.599130296707154,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.547,
|
|
"mean_token_accuracy": 0.16444521844387056,
|
|
"num_tokens": 5731765.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.572427988052368,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.4365,
|
|
"mean_token_accuracy": 0.18244351595640182,
|
|
"num_tokens": 5739989.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.59587516784668,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.17085543423891067,
|
|
"num_tokens": 5748461.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.626722288131714,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.16824812889099122,
|
|
"num_tokens": 5757495.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.670326280593872,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.16008122116327286,
|
|
"num_tokens": 5767951.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.680183029174804,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1659947469830513,
|
|
"num_tokens": 5777021.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.572238922119141,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.5446,
|
|
"mean_token_accuracy": 0.16491442322731018,
|
|
"num_tokens": 5785794.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.611316061019897,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.17236423194408418,
|
|
"num_tokens": 5794480.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.437555170059204,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.18060459941625595,
|
|
"num_tokens": 5802341.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.53844838142395,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.16787216514348985,
|
|
"num_tokens": 5811365.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.558381080627441,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.17300861477851867,
|
|
"num_tokens": 5819957.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.53677339553833,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.1693764254450798,
|
|
"num_tokens": 5828378.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.64333815574646,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.5793,
|
|
"mean_token_accuracy": 0.16261188238859176,
|
|
"num_tokens": 5837310.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.55024790763855,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.17094084322452546,
|
|
"num_tokens": 5845945.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.5680609226226805,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.16151418387889863,
|
|
"num_tokens": 5855954.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.720606994628906,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.15828690603375434,
|
|
"num_tokens": 5865327.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.719430017471313,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.6038,
|
|
"mean_token_accuracy": 0.16542584747076033,
|
|
"num_tokens": 5873959.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.533983564376831,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.4574,
|
|
"mean_token_accuracy": 0.17117766588926314,
|
|
"num_tokens": 5882566.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.5592443466186525,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.5055,
|
|
"mean_token_accuracy": 0.1669450059533119,
|
|
"num_tokens": 5891407.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.60461163520813,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17221603840589522,
|
|
"num_tokens": 5900123.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.5325319290161135,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.1720262810587883,
|
|
"num_tokens": 5909043.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.637628793716431,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.16693660020828247,
|
|
"num_tokens": 5918728.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.648838138580322,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.16625168174505234,
|
|
"num_tokens": 5927281.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.529385042190552,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.17687633484601975,
|
|
"num_tokens": 5935696.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.519879579544067,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.16781273633241653,
|
|
"num_tokens": 5944858.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.741100788116455,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.6246,
|
|
"mean_token_accuracy": 0.1606270983815193,
|
|
"num_tokens": 5954243.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.536730432510376,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.16611584275960922,
|
|
"num_tokens": 5963318.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.564297723770141,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.17894322723150252,
|
|
"num_tokens": 5971487.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.509364891052246,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.17391130924224854,
|
|
"num_tokens": 5979981.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.6284205436706545,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.1685034915804863,
|
|
"num_tokens": 5989427.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.515089416503907,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.16262538433074952,
|
|
"num_tokens": 5999434.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.607756948471069,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.5435,
|
|
"mean_token_accuracy": 0.16143085807561874,
|
|
"num_tokens": 6008963.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.676263093948364,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.15726133584976196,
|
|
"num_tokens": 6017693.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.591120767593384,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.16171587631106377,
|
|
"num_tokens": 6027943.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.644890785217285,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.5546,
|
|
"mean_token_accuracy": 0.16676364094018936,
|
|
"num_tokens": 6036750.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.55715970993042,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.17173196673393248,
|
|
"num_tokens": 6045722.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.5623070240020756,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.1611317977309227,
|
|
"num_tokens": 6055001.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.6479048252105715,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.5473,
|
|
"mean_token_accuracy": 0.1628773733973503,
|
|
"num_tokens": 6063420.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.502745962142944,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.16666587591171264,
|
|
"num_tokens": 6073075.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.6657538414001465,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.16148816794157028,
|
|
"num_tokens": 6083035.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.520883941650391,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16716577261686325,
|
|
"num_tokens": 6090980.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.501849842071533,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.170765620470047,
|
|
"num_tokens": 6099402.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.643212795257568,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.17255675792694092,
|
|
"num_tokens": 6109251.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.637518215179443,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.15654925331473352,
|
|
"num_tokens": 6119005.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.625385427474976,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.168638151884079,
|
|
"num_tokens": 6127566.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.5461078643798825,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.1676493614912033,
|
|
"num_tokens": 6137189.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.64869122505188,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.5612,
|
|
"mean_token_accuracy": 0.1613749474287033,
|
|
"num_tokens": 6147038.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.587482118606568,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.16784363389015197,
|
|
"num_tokens": 6155770.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.560370349884034,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.524,
|
|
"mean_token_accuracy": 0.16733328104019166,
|
|
"num_tokens": 6164030.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.487758684158325,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.4619,
|
|
"mean_token_accuracy": 0.16856031417846679,
|
|
"num_tokens": 6173046.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.645107221603394,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.1745447725057602,
|
|
"num_tokens": 6182193.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.584012460708618,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.1712668612599373,
|
|
"num_tokens": 6190791.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.609999179840088,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.1656983897089958,
|
|
"num_tokens": 6199245.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.507687950134278,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.1721063256263733,
|
|
"num_tokens": 6208420.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.61139760017395,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.16631663143634795,
|
|
"num_tokens": 6217059.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.538406038284302,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.4275,
|
|
"mean_token_accuracy": 0.17101717442274095,
|
|
"num_tokens": 6225955.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.52253565788269,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.1696779116988182,
|
|
"num_tokens": 6235989.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.645891809463501,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1621383935213089,
|
|
"num_tokens": 6244821.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.566744995117188,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.6931,
|
|
"mean_token_accuracy": 0.16034929305315018,
|
|
"num_tokens": 6254157.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.738871717453003,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.6091,
|
|
"mean_token_accuracy": 0.1633436217904091,
|
|
"num_tokens": 6263807.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.5871929168701175,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.5241,
|
|
"mean_token_accuracy": 0.17041266113519668,
|
|
"num_tokens": 6273075.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.594843816757202,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.16699558347463608,
|
|
"num_tokens": 6282079.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.517852783203125,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.514,
|
|
"mean_token_accuracy": 0.16514699906110764,
|
|
"num_tokens": 6291957.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.594090270996094,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.1670241139829159,
|
|
"num_tokens": 6301144.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.57917799949646,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.17103310972452163,
|
|
"num_tokens": 6310654.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.5719961643219,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.170123153924942,
|
|
"num_tokens": 6319562.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.5296674251556395,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.1664817675948143,
|
|
"num_tokens": 6329056.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.548776292800904,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.17050102949142457,
|
|
"num_tokens": 6337857.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.552810192108154,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.4435,
|
|
"mean_token_accuracy": 0.16510596126317978,
|
|
"num_tokens": 6346876.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.532234477996826,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.169155353307724,
|
|
"num_tokens": 6356200.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.622051954269409,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1686449870467186,
|
|
"num_tokens": 6365761.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.538770389556885,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.5776,
|
|
"mean_token_accuracy": 0.16255938410758972,
|
|
"num_tokens": 6375326.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.648449420928955,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.16999968513846397,
|
|
"num_tokens": 6384662.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.5590479373931885,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.494,
|
|
"mean_token_accuracy": 0.16821259111166,
|
|
"num_tokens": 6393576.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.578520345687866,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.4442,
|
|
"mean_token_accuracy": 0.17245304733514785,
|
|
"num_tokens": 6402436.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.55627121925354,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.16973026543855668,
|
|
"num_tokens": 6411471.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.6449315547943115,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.16155346035957335,
|
|
"num_tokens": 6421355.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.545068979263306,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.1627734988927841,
|
|
"num_tokens": 6430579.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.560308027267456,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.1718488723039627,
|
|
"num_tokens": 6439939.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.518435144424439,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.1709216669201851,
|
|
"num_tokens": 6448598.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.572875738143921,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.16180262267589568,
|
|
"num_tokens": 6457647.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.482194232940674,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.17720404118299485,
|
|
"num_tokens": 6466391.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.519830751419067,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17875840663909912,
|
|
"num_tokens": 6475252.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.581446790695191,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.5141,
|
|
"mean_token_accuracy": 0.16880967915058137,
|
|
"num_tokens": 6484959.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.558564567565918,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.5838,
|
|
"mean_token_accuracy": 0.1725819930434227,
|
|
"num_tokens": 6495221.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.506700468063355,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.1691438838839531,
|
|
"num_tokens": 6504390.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.481767988204956,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.17185622900724412,
|
|
"num_tokens": 6514105.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.554193353652954,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.1658230811357498,
|
|
"num_tokens": 6523673.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.5826500415802,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17110901027917863,
|
|
"num_tokens": 6532158.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.557160758972168,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.5548,
|
|
"mean_token_accuracy": 0.16146010607481004,
|
|
"num_tokens": 6541580.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.58383092880249,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.1715245321393013,
|
|
"num_tokens": 6550298.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.671181774139404,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.6423,
|
|
"mean_token_accuracy": 0.1643599845468998,
|
|
"num_tokens": 6560774.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.6066991806030275,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1764713555574417,
|
|
"num_tokens": 6568946.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.569188070297241,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.5869,
|
|
"mean_token_accuracy": 0.16506663262844085,
|
|
"num_tokens": 6579798.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.546876001358032,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.4352,
|
|
"mean_token_accuracy": 0.16500298976898192,
|
|
"num_tokens": 6589309.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.606908178329467,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.16275236755609512,
|
|
"num_tokens": 6598835.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.657209491729736,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.1674236461520195,
|
|
"num_tokens": 6608167.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.4105946063995365,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.17718791365623474,
|
|
"num_tokens": 6616904.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.476817989349366,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.17451889514923097,
|
|
"num_tokens": 6625841.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.500431299209595,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.1821831837296486,
|
|
"num_tokens": 6633755.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.499605131149292,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.481,
|
|
"mean_token_accuracy": 0.17698049694299697,
|
|
"num_tokens": 6642372.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.665440702438355,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.17390639185905457,
|
|
"num_tokens": 6652271.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.537015962600708,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.16500245183706283,
|
|
"num_tokens": 6661463.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.605558681488037,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.1709505945444107,
|
|
"num_tokens": 6671423.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.5377373695373535,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.16418076828122138,
|
|
"num_tokens": 6680218.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.4533233642578125,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.4554,
|
|
"mean_token_accuracy": 0.16532421708106995,
|
|
"num_tokens": 6689117.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.557939243316651,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.1704023465514183,
|
|
"num_tokens": 6698024.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.60575761795044,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.16607705354690552,
|
|
"num_tokens": 6706253.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.681532382965088,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.16927950829267502,
|
|
"num_tokens": 6716440.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.574979066848755,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.17709684371948242,
|
|
"num_tokens": 6725263.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.4725415229797365,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.5857,
|
|
"mean_token_accuracy": 0.16625414788722992,
|
|
"num_tokens": 6735023.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.616141366958618,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.1685444086790085,
|
|
"num_tokens": 6744659.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.57385892868042,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1631895735859871,
|
|
"num_tokens": 6753844.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.567027425765991,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.17073792219161987,
|
|
"num_tokens": 6762574.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.649561262130737,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.6345,
|
|
"mean_token_accuracy": 0.1632675498723984,
|
|
"num_tokens": 6772991.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.517704200744629,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.16668988019227982,
|
|
"num_tokens": 6781380.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.524003982543945,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.1661317154765129,
|
|
"num_tokens": 6791125.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.672194337844848,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.1653213694691658,
|
|
"num_tokens": 6801038.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.461750936508179,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.1715899422764778,
|
|
"num_tokens": 6810049.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.51236925125122,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16919803619384766,
|
|
"num_tokens": 6819375.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.621548652648926,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.5203,
|
|
"mean_token_accuracy": 0.1661919519305229,
|
|
"num_tokens": 6828872.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.496156454086304,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.4009,
|
|
"mean_token_accuracy": 0.17521113753318787,
|
|
"num_tokens": 6838698.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.474640941619873,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.525,
|
|
"mean_token_accuracy": 0.17458565533161163,
|
|
"num_tokens": 6848147.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.586211156845093,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.1678055003285408,
|
|
"num_tokens": 6857777.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.558766460418701,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.17062433809041977,
|
|
"num_tokens": 6866340.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.511882162094116,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.1747218683362007,
|
|
"num_tokens": 6875670.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.596552181243896,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16636160612106324,
|
|
"num_tokens": 6885722.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.552028846740723,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.16789107471704484,
|
|
"num_tokens": 6894267.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.624865961074829,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.5182,
|
|
"mean_token_accuracy": 0.158856088668108,
|
|
"num_tokens": 6904488.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.531492900848389,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.1683632478117943,
|
|
"num_tokens": 6913329.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.519823312759399,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.17840514183044434,
|
|
"num_tokens": 6921722.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.622691059112549,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.5234,
|
|
"mean_token_accuracy": 0.17229442149400712,
|
|
"num_tokens": 6931183.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.582337999343872,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.1696538582444191,
|
|
"num_tokens": 6939813.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.6612132549285885,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.6299,
|
|
"mean_token_accuracy": 0.16207285374403,
|
|
"num_tokens": 6950227.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.546162462234497,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.1773684024810791,
|
|
"num_tokens": 6959971.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.462558126449585,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.17802790701389312,
|
|
"num_tokens": 6968557.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.589730453491211,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.17268655300140381,
|
|
"num_tokens": 6978058.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.557629013061524,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.17178971618413924,
|
|
"num_tokens": 6986549.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.5617804527282715,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17168736606836318,
|
|
"num_tokens": 6995907.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.513281345367432,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.1667625993490219,
|
|
"num_tokens": 7006195.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.4175151824951175,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.17235345691442489,
|
|
"num_tokens": 7015223.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.5245832920074465,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.17326589077711105,
|
|
"num_tokens": 7024191.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.429194736480713,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.17181134819984437,
|
|
"num_tokens": 7032947.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.534834289550782,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.333,
|
|
"mean_token_accuracy": 0.1813531905412674,
|
|
"num_tokens": 7041422.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.5460773468017575,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.16053829938173295,
|
|
"num_tokens": 7051051.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.490616798400879,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.175313900411129,
|
|
"num_tokens": 7060116.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.624402809143066,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.16506005823612213,
|
|
"num_tokens": 7068759.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.41002345085144,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.17519752979278563,
|
|
"num_tokens": 7078321.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.59229097366333,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.17415895462036132,
|
|
"num_tokens": 7088126.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.495071697235107,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.16729627251625062,
|
|
"num_tokens": 7096948.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.383945178985596,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.3991,
|
|
"mean_token_accuracy": 0.17286474704742433,
|
|
"num_tokens": 7106867.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.511750364303589,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.1696945309638977,
|
|
"num_tokens": 7115971.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.57295298576355,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.1746579512953758,
|
|
"num_tokens": 7124659.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.586831712722779,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.6524,
|
|
"mean_token_accuracy": 0.16620706468820573,
|
|
"num_tokens": 7133456.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.535101461410522,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.17057373225688935,
|
|
"num_tokens": 7142649.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.619561052322387,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.16672575026750563,
|
|
"num_tokens": 7153151.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.502790641784668,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1734729528427124,
|
|
"num_tokens": 7161638.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.493521595001221,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.4303,
|
|
"mean_token_accuracy": 0.1750929281115532,
|
|
"num_tokens": 7170832.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.491485261917115,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.1764598712325096,
|
|
"num_tokens": 7180025.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.5754554271698,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.17411546036601067,
|
|
"num_tokens": 7189287.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.603695440292358,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.1673969268798828,
|
|
"num_tokens": 7198438.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.409713411331177,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.17143895775079726,
|
|
"num_tokens": 7208006.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.584083938598633,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16895750910043716,
|
|
"num_tokens": 7216975.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.5208659172058105,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16583355739712716,
|
|
"num_tokens": 7225664.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.565141344070435,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1687723606824875,
|
|
"num_tokens": 7234780.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.550216579437256,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.1774860978126526,
|
|
"num_tokens": 7242648.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.367749166488648,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.4683,
|
|
"mean_token_accuracy": 0.1734187424182892,
|
|
"num_tokens": 7251856.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.658477258682251,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.17640756517648698,
|
|
"num_tokens": 7260552.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.52726149559021,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.1719620943069458,
|
|
"num_tokens": 7270328.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.438219451904297,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.17517218589782715,
|
|
"num_tokens": 7279797.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.579410600662231,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.16999913454055787,
|
|
"num_tokens": 7290205.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.531829833984375,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.17171881347894669,
|
|
"num_tokens": 7298544.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.451128578186035,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.17368571907281877,
|
|
"num_tokens": 7307662.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.569617891311646,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.4979,
|
|
"mean_token_accuracy": 0.1646683320403099,
|
|
"num_tokens": 7317085.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.573373508453369,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.17162806242704393,
|
|
"num_tokens": 7326190.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.546729230880738,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.1697179466485977,
|
|
"num_tokens": 7336143.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.567217826843262,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.16804200112819673,
|
|
"num_tokens": 7346024.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.536852121353149,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.16853790283203124,
|
|
"num_tokens": 7355477.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.608371210098267,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17802691608667373,
|
|
"num_tokens": 7364720.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.42276668548584,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.1722881615161896,
|
|
"num_tokens": 7373793.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.514430809020996,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.16925701051950454,
|
|
"num_tokens": 7383886.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.647746133804321,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.16909781023859977,
|
|
"num_tokens": 7393617.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.511100721359253,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.18106982558965684,
|
|
"num_tokens": 7401949.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.340199756622314,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.17852676808834075,
|
|
"num_tokens": 7410180.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.602356719970703,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.1651108369231224,
|
|
"num_tokens": 7420506.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.607547473907471,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.4913,
|
|
"mean_token_accuracy": 0.1773996263742447,
|
|
"num_tokens": 7429644.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.612040662765503,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.17017731964588165,
|
|
"num_tokens": 7439129.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.4839338779449465,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.5053,
|
|
"mean_token_accuracy": 0.17029713541269303,
|
|
"num_tokens": 7449355.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.56695556640625,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.1702693894505501,
|
|
"num_tokens": 7458763.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.539506673812866,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.17542738765478133,
|
|
"num_tokens": 7467697.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.481296968460083,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.16871478855609895,
|
|
"num_tokens": 7476728.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.515885925292968,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.17235045433044432,
|
|
"num_tokens": 7486794.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.618357086181641,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.17357994019985198,
|
|
"num_tokens": 7496286.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.474039125442505,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.4542,
|
|
"mean_token_accuracy": 0.17892095372080802,
|
|
"num_tokens": 7505670.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.562310600280762,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.17938163354992867,
|
|
"num_tokens": 7514702.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.54784574508667,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.17029086202383042,
|
|
"num_tokens": 7523705.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.482650947570801,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.1778412491083145,
|
|
"num_tokens": 7532491.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.489047718048096,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.16939541548490525,
|
|
"num_tokens": 7540761.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.589512634277344,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.4827,
|
|
"mean_token_accuracy": 0.1699928969144821,
|
|
"num_tokens": 7550897.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.49046139717102,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.1745118945837021,
|
|
"num_tokens": 7559982.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.518819141387939,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.16522257626056672,
|
|
"num_tokens": 7569358.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.5108489990234375,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17053637355566026,
|
|
"num_tokens": 7578437.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.44957389831543,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.1758326917886734,
|
|
"num_tokens": 7587528.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.625531435012817,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.4328,
|
|
"mean_token_accuracy": 0.18261457085609437,
|
|
"num_tokens": 7595991.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.461813974380493,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.3865,
|
|
"mean_token_accuracy": 0.17654262781143187,
|
|
"num_tokens": 7604538.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.406788349151611,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.17029373198747635,
|
|
"num_tokens": 7613853.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.491995239257813,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.3651,
|
|
"mean_token_accuracy": 0.17852593064308167,
|
|
"num_tokens": 7623538.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.483587026596069,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.17738809436559677,
|
|
"num_tokens": 7632121.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.5288893699646,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.1706435889005661,
|
|
"num_tokens": 7640779.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.489064121246338,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.16829655468463897,
|
|
"num_tokens": 7649138.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.43375883102417,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.18074534982442855,
|
|
"num_tokens": 7658510.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.4592814445495605,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.18564201146364212,
|
|
"num_tokens": 7666946.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.445179462432861,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.17630248218774797,
|
|
"num_tokens": 7675572.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.374283218383789,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.17325544804334642,
|
|
"num_tokens": 7684719.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.452366304397583,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.16606821864843369,
|
|
"num_tokens": 7694370.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.538264179229737,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.16647274494171144,
|
|
"num_tokens": 7703572.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.54348931312561,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.17307280451059343,
|
|
"num_tokens": 7712732.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.545743179321289,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.16450876593589783,
|
|
"num_tokens": 7722213.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.567177391052246,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.16758489459753037,
|
|
"num_tokens": 7732228.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.551746988296509,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.16597847491502762,
|
|
"num_tokens": 7741662.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.602847003936768,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.17829289734363557,
|
|
"num_tokens": 7749608.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.340467071533203,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.4167,
|
|
"mean_token_accuracy": 0.17135734856128693,
|
|
"num_tokens": 7758387.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.479982471466064,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.16724161356687545,
|
|
"num_tokens": 7768103.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.4644652843475345,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.2988,
|
|
"mean_token_accuracy": 0.17720498591661454,
|
|
"num_tokens": 7776826.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.408760690689087,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.419,
|
|
"mean_token_accuracy": 0.1694740518927574,
|
|
"num_tokens": 7785866.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.6010815620422365,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.16579159647226333,
|
|
"num_tokens": 7795140.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.424951791763306,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.17311078310012817,
|
|
"num_tokens": 7804256.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.505328559875489,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.18129236549139022,
|
|
"num_tokens": 7812295.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.6016477108001705,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.17255054265260697,
|
|
"num_tokens": 7821208.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.403783226013184,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.4886,
|
|
"mean_token_accuracy": 0.16946886703372002,
|
|
"num_tokens": 7830542.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.468491840362549,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.18574574887752532,
|
|
"num_tokens": 7839469.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.495815372467041,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.17240444272756578,
|
|
"num_tokens": 7849350.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.512340116500854,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.3893,
|
|
"mean_token_accuracy": 0.1797077938914299,
|
|
"num_tokens": 7858882.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.492542552947998,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.17558517456054687,
|
|
"num_tokens": 7868704.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.568697166442871,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.17207656651735306,
|
|
"num_tokens": 7878103.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.341040420532226,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.18514634370803834,
|
|
"num_tokens": 7887228.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.495812606811524,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.17493630200624466,
|
|
"num_tokens": 7897205.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.463666105270386,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.17855667918920518,
|
|
"num_tokens": 7906336.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.425225639343262,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.17622471898794173,
|
|
"num_tokens": 7914773.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.416539430618286,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.3227,
|
|
"mean_token_accuracy": 0.181936876475811,
|
|
"num_tokens": 7922759.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.421218681335449,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.33,
|
|
"mean_token_accuracy": 0.17022594213485717,
|
|
"num_tokens": 7932199.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.403014087677002,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17926559150218963,
|
|
"num_tokens": 7941045.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.430142784118653,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.18629411309957505,
|
|
"num_tokens": 7949339.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.44664740562439,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.17302195131778716,
|
|
"num_tokens": 7958182.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.492476940155029,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.17579357475042343,
|
|
"num_tokens": 7966711.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.4342657089233395,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.1751624494791031,
|
|
"num_tokens": 7974864.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.4517271518707275,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.16784718185663222,
|
|
"num_tokens": 7984812.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.4975443363189695,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.434,
|
|
"mean_token_accuracy": 0.16960262209177018,
|
|
"num_tokens": 7994862.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.454056358337402,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.17012314200401307,
|
|
"num_tokens": 8003943.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.456601524353028,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.17089642137289046,
|
|
"num_tokens": 8012841.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.4201741218566895,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.1764964520931244,
|
|
"num_tokens": 8021766.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.509561347961426,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.17222451120615007,
|
|
"num_tokens": 8030491.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.377471208572388,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.3375,
|
|
"mean_token_accuracy": 0.17822521328926086,
|
|
"num_tokens": 8039325.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.492970132827759,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.4225,
|
|
"mean_token_accuracy": 0.17352834790945054,
|
|
"num_tokens": 8048673.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.6428838729858395,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.16775976866483688,
|
|
"num_tokens": 8057934.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.385854768753052,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.1815803900361061,
|
|
"num_tokens": 8066923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.499070501327514,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.16589635163545607,
|
|
"num_tokens": 8076263.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.543005561828613,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.1719420939683914,
|
|
"num_tokens": 8085741.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.430317115783692,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.1729919657111168,
|
|
"num_tokens": 8094646.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.463187503814697,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.1726178929209709,
|
|
"num_tokens": 8103215.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.4622879981994625,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.1726316198706627,
|
|
"num_tokens": 8112381.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.422245883941651,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.17220450937747955,
|
|
"num_tokens": 8121139.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.507014894485474,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.16886930018663407,
|
|
"num_tokens": 8130011.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.4787599563598635,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.17649679034948348,
|
|
"num_tokens": 8138757.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.397525072097778,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.172449491918087,
|
|
"num_tokens": 8147862.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.484035444259644,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.3451,
|
|
"mean_token_accuracy": 0.18334268629550934,
|
|
"num_tokens": 8156754.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.413478517532349,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18084121197462083,
|
|
"num_tokens": 8165647.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.431940793991089,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.174612420797348,
|
|
"num_tokens": 8174811.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.43572039604187,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17819695621728898,
|
|
"num_tokens": 8184270.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.539177322387696,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.1732149139046669,
|
|
"num_tokens": 8193209.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.62060956954956,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16869076937437058,
|
|
"num_tokens": 8202502.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.546969890594482,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.17091006189584732,
|
|
"num_tokens": 8212226.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.5280375480651855,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.4079,
|
|
"mean_token_accuracy": 0.17574627101421356,
|
|
"num_tokens": 8220729.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.452630853652954,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.4652,
|
|
"mean_token_accuracy": 0.1738543137907982,
|
|
"num_tokens": 8230385.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.495773553848267,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.17303333729505538,
|
|
"num_tokens": 8240057.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.340406799316407,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.18496009856462478,
|
|
"num_tokens": 8249903.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.464671802520752,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.17637877762317658,
|
|
"num_tokens": 8259334.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.3831353187561035,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.18332188874483107,
|
|
"num_tokens": 8268543.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.516524982452393,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.17564595937728883,
|
|
"num_tokens": 8278257.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.46676197052002,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18334500193595887,
|
|
"num_tokens": 8287506.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.370918893814087,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.182416196167469,
|
|
"num_tokens": 8295803.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.386123561859131,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.1722537860274315,
|
|
"num_tokens": 8305344.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.535409212112427,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.16697886884212493,
|
|
"num_tokens": 8315226.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.498746633529663,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.1674830958247185,
|
|
"num_tokens": 8324614.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.3684216976165775,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.17755249738693238,
|
|
"num_tokens": 8334014.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.432075262069702,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.17807306349277496,
|
|
"num_tokens": 8343038.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.534339857101441,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.16782399713993074,
|
|
"num_tokens": 8353170.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.49351806640625,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.3361,
|
|
"mean_token_accuracy": 0.18302312940359117,
|
|
"num_tokens": 8362240.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.361939573287964,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17659430652856828,
|
|
"num_tokens": 8370723.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.353510475158691,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.18136699199676515,
|
|
"num_tokens": 8379282.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.375656175613403,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.19318119585514068,
|
|
"num_tokens": 8387918.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.548627471923828,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.1697971135377884,
|
|
"num_tokens": 8397755.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.497386264801025,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.4646,
|
|
"mean_token_accuracy": 0.17076701074838638,
|
|
"num_tokens": 8408229.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.427838087081909,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.17245035618543625,
|
|
"num_tokens": 8417039.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.42997784614563,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.1772854745388031,
|
|
"num_tokens": 8426656.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.5097325325012205,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.1768176957964897,
|
|
"num_tokens": 8435254.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.303733777999878,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.1777205228805542,
|
|
"num_tokens": 8444594.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.355650806427002,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.2771,
|
|
"mean_token_accuracy": 0.18417982757091522,
|
|
"num_tokens": 8453737.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.469804000854492,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.3665,
|
|
"mean_token_accuracy": 0.17435781806707382,
|
|
"num_tokens": 8463033.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.415114831924439,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1721029609441757,
|
|
"num_tokens": 8472875.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.531055068969726,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.16320496201515197,
|
|
"num_tokens": 8482281.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.556277322769165,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.4176,
|
|
"mean_token_accuracy": 0.1776779368519783,
|
|
"num_tokens": 8490871.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.384867572784424,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.17717715203762055,
|
|
"num_tokens": 8499765.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.410521936416626,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18398708254098892,
|
|
"num_tokens": 8508163.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.484644365310669,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.17248052060604097,
|
|
"num_tokens": 8517791.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.41528902053833,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.3477,
|
|
"mean_token_accuracy": 0.1795007422566414,
|
|
"num_tokens": 8526051.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.43937463760376,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.3687,
|
|
"mean_token_accuracy": 0.17532350718975068,
|
|
"num_tokens": 8536102.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.432383728027344,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.3781,
|
|
"mean_token_accuracy": 0.16846679151058197,
|
|
"num_tokens": 8544566.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.533143711090088,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.1642456069588661,
|
|
"num_tokens": 8555397.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.570744943618775,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.1791091486811638,
|
|
"num_tokens": 8564184.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.567000961303711,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.1724994361400604,
|
|
"num_tokens": 8572967.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.394959306716919,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.3859,
|
|
"mean_token_accuracy": 0.17433421611785888,
|
|
"num_tokens": 8581946.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.366177749633789,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.18927239775657653,
|
|
"num_tokens": 8590528.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.448218202590942,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.17978343069553376,
|
|
"num_tokens": 8600399.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.4937997341156,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.17784634977579117,
|
|
"num_tokens": 8609620.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.337210035324096,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.18280318081378938,
|
|
"num_tokens": 8618077.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.354756498336792,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.3177,
|
|
"mean_token_accuracy": 0.18373266011476516,
|
|
"num_tokens": 8626672.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.448664379119873,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1821853294968605,
|
|
"num_tokens": 8635997.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.444197797775269,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.16682087033987045,
|
|
"num_tokens": 8645296.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.477824544906616,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.17398236244916915,
|
|
"num_tokens": 8654772.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.435440587997436,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17901189625263214,
|
|
"num_tokens": 8664279.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.4493427753448485,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.1713800996541977,
|
|
"num_tokens": 8673405.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.4495786190032955,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.17766857296228408,
|
|
"num_tokens": 8682254.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.473398065567016,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.18520117402076722,
|
|
"num_tokens": 8690751.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.514026927947998,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.16697628647089005,
|
|
"num_tokens": 8700485.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.420544815063477,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.16980446875095367,
|
|
"num_tokens": 8709650.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.374988794326782,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.17936188727617264,
|
|
"num_tokens": 8719090.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.456218910217285,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17431129068136214,
|
|
"num_tokens": 8728563.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.582469940185547,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.3821,
|
|
"mean_token_accuracy": 0.17387064397335053,
|
|
"num_tokens": 8737587.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.496310997009277,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.17855045199394226,
|
|
"num_tokens": 8747377.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.516774272918701,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.4181,
|
|
"mean_token_accuracy": 0.17951357066631318,
|
|
"num_tokens": 8756471.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.376832675933838,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.1693958595395088,
|
|
"num_tokens": 8765445.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.581160211563111,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.4503,
|
|
"mean_token_accuracy": 0.1728968620300293,
|
|
"num_tokens": 8774946.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.478467082977295,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.17615725547075273,
|
|
"num_tokens": 8783652.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.364590787887574,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.1788276180624962,
|
|
"num_tokens": 8792633.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.34464955329895,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.1825534701347351,
|
|
"num_tokens": 8802376.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.389295625686645,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.3487,
|
|
"mean_token_accuracy": 0.18201276659965515,
|
|
"num_tokens": 8812122.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.443384647369385,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.17886264026165008,
|
|
"num_tokens": 8821111.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.4228722095489506,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.17484676614403724,
|
|
"num_tokens": 8830354.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.367304134368896,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18212662786245346,
|
|
"num_tokens": 8839500.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.448452091217041,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.174194598197937,
|
|
"num_tokens": 8849632.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.622716903686523,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.1704885631799698,
|
|
"num_tokens": 8858383.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.349063301086426,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.2539,
|
|
"mean_token_accuracy": 0.18768793791532518,
|
|
"num_tokens": 8866755.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.398096561431885,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1728242516517639,
|
|
"num_tokens": 8876896.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.594376134872436,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.17692140489816666,
|
|
"num_tokens": 8886029.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.4225725650787355,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.17887427508831025,
|
|
"num_tokens": 8895396.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.404714584350586,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18620169758796692,
|
|
"num_tokens": 8904125.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.404704236984253,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.16959863007068635,
|
|
"num_tokens": 8913011.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.402275943756104,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.1808636337518692,
|
|
"num_tokens": 8921596.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.448325061798096,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.17477848529815673,
|
|
"num_tokens": 8931267.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.298576974868775,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.18315067142248154,
|
|
"num_tokens": 8940082.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.485443592071533,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.17353947907686235,
|
|
"num_tokens": 8949838.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.467548894882202,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.17952940315008165,
|
|
"num_tokens": 8958510.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.433662223815918,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.17126011699438096,
|
|
"num_tokens": 8968372.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.3494861125946045,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.18010528683662413,
|
|
"num_tokens": 8977121.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.4491739749908445,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.1782987281680107,
|
|
"num_tokens": 8986643.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.380730676651001,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.18655198961496353,
|
|
"num_tokens": 8994925.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.299397134780884,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.3264,
|
|
"mean_token_accuracy": 0.1842572957277298,
|
|
"num_tokens": 9003844.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.466626310348511,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.17607323825359344,
|
|
"num_tokens": 9013351.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.445525598526001,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.17783276438713075,
|
|
"num_tokens": 9023488.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.423844528198242,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1794862851500511,
|
|
"num_tokens": 9033018.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.3908610343933105,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18037871420383453,
|
|
"num_tokens": 9041572.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.5957917213439945,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16397008448839187,
|
|
"num_tokens": 9051505.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.426666593551635,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.3448,
|
|
"mean_token_accuracy": 0.17821265608072281,
|
|
"num_tokens": 9061168.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.2480797290802,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.17862533032894135,
|
|
"num_tokens": 9069776.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.4414534091949465,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.1817397803068161,
|
|
"num_tokens": 9078995.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.348909711837768,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.18326059132814407,
|
|
"num_tokens": 9088291.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.423943901062012,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.17726942151784897,
|
|
"num_tokens": 9097013.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.427419185638428,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.17360134273767472,
|
|
"num_tokens": 9106909.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.4259748458862305,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.1686091035604477,
|
|
"num_tokens": 9116056.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.408644199371338,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.1770440310239792,
|
|
"num_tokens": 9124968.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.380485582351684,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.17902038991451263,
|
|
"num_tokens": 9134423.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.514896488189697,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.17550164312124253,
|
|
"num_tokens": 9144179.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.399398517608643,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.4532,
|
|
"mean_token_accuracy": 0.16906047165393828,
|
|
"num_tokens": 9154045.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.315214443206787,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.1848849982023239,
|
|
"num_tokens": 9162922.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.340002155303955,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.2502,
|
|
"mean_token_accuracy": 0.18313726782798767,
|
|
"num_tokens": 9172327.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.3172860622406,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.18388236463069915,
|
|
"num_tokens": 9180830.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.461140155792236,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.17659415304660797,
|
|
"num_tokens": 9190787.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.486403846740723,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.17391360849142073,
|
|
"num_tokens": 9199554.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.36230354309082,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.17479039132595062,
|
|
"num_tokens": 9209309.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.442480516433716,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.1775646835565567,
|
|
"num_tokens": 9218529.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.397161149978638,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17779555320739746,
|
|
"num_tokens": 9226924.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.345029497146607,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.3549,
|
|
"mean_token_accuracy": 0.17008619159460067,
|
|
"num_tokens": 9237602.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.487488460540772,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.17842262536287307,
|
|
"num_tokens": 9246209.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.351472520828247,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.17697940915822982,
|
|
"num_tokens": 9255464.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.360794496536255,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.17424386441707612,
|
|
"num_tokens": 9265520.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.464559745788574,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.3214,
|
|
"mean_token_accuracy": 0.17781623601913452,
|
|
"num_tokens": 9274916.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.3971545696258545,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.16885341703891754,
|
|
"num_tokens": 9284684.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.437297439575195,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.17992314845323562,
|
|
"num_tokens": 9294020.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.44114055633545,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.17765092402696608,
|
|
"num_tokens": 9303730.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.491128301620483,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.3023,
|
|
"mean_token_accuracy": 0.18014814406633378,
|
|
"num_tokens": 9312851.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.286890840530395,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.18571052104234695,
|
|
"num_tokens": 9321143.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.420368099212647,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.18008437752723694,
|
|
"num_tokens": 9329843.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.440558433532715,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.1702857494354248,
|
|
"num_tokens": 9339549.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.469025373458862,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.17415655851364137,
|
|
"num_tokens": 9348220.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.442413854598999,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17110524326562881,
|
|
"num_tokens": 9357440.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.430461072921753,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1753034397959709,
|
|
"num_tokens": 9366457.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.400099229812622,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.17686941027641295,
|
|
"num_tokens": 9375432.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.373173713684082,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.1831916391849518,
|
|
"num_tokens": 9383353.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.457636070251465,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.18044039607048035,
|
|
"num_tokens": 9393012.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.423114776611328,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.18421694189310073,
|
|
"num_tokens": 9401394.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.394059324264527,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.1817804366350174,
|
|
"num_tokens": 9410310.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.39257287979126,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.18167548775672912,
|
|
"num_tokens": 9418625.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.394883108139038,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.3929,
|
|
"mean_token_accuracy": 0.1777561068534851,
|
|
"num_tokens": 9428722.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.47434630393982,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.17843445241451264,
|
|
"num_tokens": 9438447.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.42354383468628,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.1818290963768959,
|
|
"num_tokens": 9447457.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.45627236366272,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.4273,
|
|
"mean_token_accuracy": 0.16493106931447982,
|
|
"num_tokens": 9456837.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.535893726348877,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.4572,
|
|
"mean_token_accuracy": 0.17140540033578872,
|
|
"num_tokens": 9465733.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.390489768981934,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.17633309215307236,
|
|
"num_tokens": 9473978.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.351325464248657,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.17647748738527297,
|
|
"num_tokens": 9482914.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.422978019714355,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.1877748489379883,
|
|
"num_tokens": 9492060.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.443538570404053,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.17866956144571305,
|
|
"num_tokens": 9501186.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.574661493301392,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.1690126046538353,
|
|
"num_tokens": 9509727.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.42094612121582,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.3256,
|
|
"mean_token_accuracy": 0.17340917736291886,
|
|
"num_tokens": 9519203.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.414110565185547,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.3311,
|
|
"mean_token_accuracy": 0.17890969663858414,
|
|
"num_tokens": 9529277.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.462023019790649,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17907025516033173,
|
|
"num_tokens": 9538215.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.25904860496521,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.2621,
|
|
"mean_token_accuracy": 0.18161898702383042,
|
|
"num_tokens": 9547570.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.332035541534424,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.18879634886980057,
|
|
"num_tokens": 9556383.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.3860182762146,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.17788449823856353,
|
|
"num_tokens": 9566793.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.480335807800293,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.3536,
|
|
"mean_token_accuracy": 0.17622597217559816,
|
|
"num_tokens": 9576079.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.371386861801147,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.1782429724931717,
|
|
"num_tokens": 9586318.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.322963571548462,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.18290005922317504,
|
|
"num_tokens": 9594453.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.249912071228027,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.19170199036598207,
|
|
"num_tokens": 9603677.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.418201875686646,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.18029106706380843,
|
|
"num_tokens": 9612353.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.4223198890686035,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.18232962340116501,
|
|
"num_tokens": 9621607.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.448773145675659,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.18682206571102142,
|
|
"num_tokens": 9630155.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.41499433517456,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.18273041546344757,
|
|
"num_tokens": 9639418.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.419114255905152,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.3182,
|
|
"mean_token_accuracy": 0.18026842623949052,
|
|
"num_tokens": 9648030.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.3935081481933596,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.18045262098312378,
|
|
"num_tokens": 9657746.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.3888349533081055,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.18024140894412993,
|
|
"num_tokens": 9667840.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.423379707336426,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.1786363258957863,
|
|
"num_tokens": 9677595.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.356011819839478,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.2595,
|
|
"mean_token_accuracy": 0.1844140723347664,
|
|
"num_tokens": 9685515.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.284841680526734,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.17957810014486314,
|
|
"num_tokens": 9694238.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.479930448532104,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.17708906382322312,
|
|
"num_tokens": 9703388.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.435586261749267,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.1767055243253708,
|
|
"num_tokens": 9713085.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.474288082122802,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.3355,
|
|
"mean_token_accuracy": 0.1808098629117012,
|
|
"num_tokens": 9721733.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.453846549987793,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.1813710704445839,
|
|
"num_tokens": 9731478.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.362984895706177,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.17717154771089555,
|
|
"num_tokens": 9742058.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.367059230804443,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.1790708914399147,
|
|
"num_tokens": 9751034.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.445749044418335,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.1745736002922058,
|
|
"num_tokens": 9760692.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.384193801879883,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.1801637202501297,
|
|
"num_tokens": 9769759.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.279079961776733,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.18109699487686157,
|
|
"num_tokens": 9778597.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.284571599960327,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.19418197721242905,
|
|
"num_tokens": 9787259.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.396327638626099,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.17595013231039047,
|
|
"num_tokens": 9796297.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.453844833374023,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.2087,
|
|
"mean_token_accuracy": 0.18681780248880386,
|
|
"num_tokens": 9805217.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.399526929855346,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.17481513768434526,
|
|
"num_tokens": 9814788.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.303859996795654,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.222,
|
|
"mean_token_accuracy": 0.17701069712638856,
|
|
"num_tokens": 9823238.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.353955793380737,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.3696,
|
|
"mean_token_accuracy": 0.17349862605333327,
|
|
"num_tokens": 9832619.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.402960634231567,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.1838441640138626,
|
|
"num_tokens": 9841505.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.365970706939697,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.3379,
|
|
"mean_token_accuracy": 0.17293965220451354,
|
|
"num_tokens": 9851062.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.319137334823608,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.1796301320195198,
|
|
"num_tokens": 9860080.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.39782829284668,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.17141228467226027,
|
|
"num_tokens": 9870968.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.35687894821167,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.19018529802560807,
|
|
"num_tokens": 9879243.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.345486211776733,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.18337069302797318,
|
|
"num_tokens": 9889203.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.429203176498413,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.18169282972812653,
|
|
"num_tokens": 9898989.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.344571208953857,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.1815692037343979,
|
|
"num_tokens": 9908030.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.496398973464966,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.519,
|
|
"mean_token_accuracy": 0.17015313506126403,
|
|
"num_tokens": 9917331.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.472272443771362,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.1850770518183708,
|
|
"num_tokens": 9925418.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.437618064880371,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.17590898126363755,
|
|
"num_tokens": 9934525.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.3954144477844235,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.17028524577617646,
|
|
"num_tokens": 9944087.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.46848349571228,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18230461627244948,
|
|
"num_tokens": 9953005.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.417088222503662,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.17799917757511138,
|
|
"num_tokens": 9961963.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.3552844524383545,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.2903,
|
|
"mean_token_accuracy": 0.18317030221223832,
|
|
"num_tokens": 9970654.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.469633722305298,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.18050043284893036,
|
|
"num_tokens": 9979625.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.3770270347595215,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.186361426115036,
|
|
"num_tokens": 9988584.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.2812597274780275,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.1931207850575447,
|
|
"num_tokens": 9997315.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.296917819976807,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.18080750852823257,
|
|
"num_tokens": 10006431.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.411590051651001,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.3017,
|
|
"mean_token_accuracy": 0.18361044079065322,
|
|
"num_tokens": 10015960.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.426028060913086,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18067145794630052,
|
|
"num_tokens": 10025948.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.4195390224456785,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.17844995409250258,
|
|
"num_tokens": 10034358.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.446758174896241,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.17786922454833984,
|
|
"num_tokens": 10044887.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.2796142578125,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.2354,
|
|
"mean_token_accuracy": 0.18258257806301117,
|
|
"num_tokens": 10054026.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.367075252532959,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.17856134474277496,
|
|
"num_tokens": 10063089.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.5954488754272464,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.1661436840891838,
|
|
"num_tokens": 10073816.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.362226915359497,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.1795751541852951,
|
|
"num_tokens": 10082407.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.411347723007202,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.1772495448589325,
|
|
"num_tokens": 10091423.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.3414701461792,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.17482586354017257,
|
|
"num_tokens": 10101381.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.3897545337677,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17848258167505265,
|
|
"num_tokens": 10111000.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.51628360748291,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.17876617163419722,
|
|
"num_tokens": 10120380.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.328547382354737,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.18223776817321777,
|
|
"num_tokens": 10129236.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.5399939060211185,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.1796054482460022,
|
|
"num_tokens": 10138851.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.37919282913208,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18308076858520508,
|
|
"num_tokens": 10148030.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.351871967315674,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.18655598014593125,
|
|
"num_tokens": 10156362.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.436561489105225,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.1759396404027939,
|
|
"num_tokens": 10165603.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.40022840499878,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.1788477197289467,
|
|
"num_tokens": 10175577.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.345335578918457,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.18754889219999313,
|
|
"num_tokens": 10184736.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.342322206497192,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.316,
|
|
"mean_token_accuracy": 0.18536394238471984,
|
|
"num_tokens": 10194154.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.4188093662261965,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.17856865227222443,
|
|
"num_tokens": 10203773.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.396222543716431,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.18030931800603867,
|
|
"num_tokens": 10212260.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.3702692031860355,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17512561082839967,
|
|
"num_tokens": 10221042.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.424762439727783,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.1812494784593582,
|
|
"num_tokens": 10230336.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.431757879257202,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.4368,
|
|
"mean_token_accuracy": 0.1741185799241066,
|
|
"num_tokens": 10241655.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.343291521072388,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.18161144405603408,
|
|
"num_tokens": 10250926.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.370347738265991,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1780700668692589,
|
|
"num_tokens": 10260034.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.453782367706299,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.17498396188020707,
|
|
"num_tokens": 10269170.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.44244704246521,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.1836057037115097,
|
|
"num_tokens": 10278385.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.429437446594238,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18313779979944228,
|
|
"num_tokens": 10287678.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.380919170379639,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.17414292246103286,
|
|
"num_tokens": 10296579.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.444692945480346,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.1867544546723366,
|
|
"num_tokens": 10305812.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.416404581069946,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.17334588319063188,
|
|
"num_tokens": 10314735.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.404338455200195,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.174786077439785,
|
|
"num_tokens": 10323415.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.472856664657593,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.18797911256551741,
|
|
"num_tokens": 10331670.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.402751874923706,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.17441252171993255,
|
|
"num_tokens": 10340609.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.316213083267212,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19350895285606384,
|
|
"num_tokens": 10349035.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.323163414001465,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.18771445751190186,
|
|
"num_tokens": 10358005.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.358368301391602,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.17518524080514908,
|
|
"num_tokens": 10366791.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.3897875308990475,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.4229,
|
|
"mean_token_accuracy": 0.17349654883146287,
|
|
"num_tokens": 10376485.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.4193414688110355,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.337,
|
|
"mean_token_accuracy": 0.1830342084169388,
|
|
"num_tokens": 10385962.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.375597143173218,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.18273811936378478,
|
|
"num_tokens": 10394314.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.326365375518799,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.18153406903147698,
|
|
"num_tokens": 10403733.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.369768476486206,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.17268814146518707,
|
|
"num_tokens": 10413979.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.455648899078369,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.17913062870502472,
|
|
"num_tokens": 10422630.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.3129785537719725,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.19069661051034928,
|
|
"num_tokens": 10431422.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.407472419738769,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.1760818988084793,
|
|
"num_tokens": 10440953.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.336132574081421,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.18437761962413787,
|
|
"num_tokens": 10449331.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.3497191905975345,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.18434551656246184,
|
|
"num_tokens": 10458021.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.471211719512939,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.18104884326457976,
|
|
"num_tokens": 10466743.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.345020341873169,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.18051659911870957,
|
|
"num_tokens": 10475537.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.492947149276733,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.17569617182016373,
|
|
"num_tokens": 10485257.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.471468591690064,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.18662190884351731,
|
|
"num_tokens": 10494449.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.367533349990845,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.3658,
|
|
"mean_token_accuracy": 0.17808520942926406,
|
|
"num_tokens": 10504216.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.453322029113769,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.1843886598944664,
|
|
"num_tokens": 10512676.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.36357626914978,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18708961457014084,
|
|
"num_tokens": 10521587.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.407714462280273,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.17724160701036454,
|
|
"num_tokens": 10530043.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.332644748687744,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.195,
|
|
"mean_token_accuracy": 0.18853996247053145,
|
|
"num_tokens": 10539491.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.338552856445313,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.21,
|
|
"mean_token_accuracy": 0.18114500492811203,
|
|
"num_tokens": 10547893.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.420573902130127,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.1755267933011055,
|
|
"num_tokens": 10557597.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.4395363330841064,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.2929,
|
|
"mean_token_accuracy": 0.18169630765914918,
|
|
"num_tokens": 10566349.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.403287315368653,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.18082840144634246,
|
|
"num_tokens": 10574897.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.421693181991577,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1854931116104126,
|
|
"num_tokens": 10583233.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.257638454437256,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.2115,
|
|
"mean_token_accuracy": 0.1813637986779213,
|
|
"num_tokens": 10592202.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.33853554725647,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.17970952838659288,
|
|
"num_tokens": 10601221.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.459839248657227,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.17642758935689926,
|
|
"num_tokens": 10610983.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.473546266555786,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.1791031002998352,
|
|
"num_tokens": 10619378.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.433433723449707,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.18506969809532164,
|
|
"num_tokens": 10628288.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.428299617767334,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.1701508119702339,
|
|
"num_tokens": 10639433.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.355684995651245,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.1857157438993454,
|
|
"num_tokens": 10649654.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.3672160625457765,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18063102960586547,
|
|
"num_tokens": 10658620.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.387696599960327,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.1807701528072357,
|
|
"num_tokens": 10667942.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.285345268249512,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.1784549370408058,
|
|
"num_tokens": 10676895.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.532047176361084,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.1725636303424835,
|
|
"num_tokens": 10685986.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.472192573547363,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.18568273782730102,
|
|
"num_tokens": 10694430.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.282784032821655,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.17912789583206176,
|
|
"num_tokens": 10702997.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.38949728012085,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.18065113425254822,
|
|
"num_tokens": 10711652.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.496825456619263,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.17776526212692262,
|
|
"num_tokens": 10721749.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.397292232513427,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.17844431102275848,
|
|
"num_tokens": 10729678.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.380484914779663,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.17817786931991578,
|
|
"num_tokens": 10740276.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.3566937923431395,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.1754148170351982,
|
|
"num_tokens": 10749249.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.469118213653564,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.1886957809329033,
|
|
"num_tokens": 10758888.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.273655605316162,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18605542778968812,
|
|
"num_tokens": 10768156.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.278586053848267,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.18633593171834945,
|
|
"num_tokens": 10776762.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.447524738311768,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.17448019236326218,
|
|
"num_tokens": 10785495.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.384194087982178,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.1862630292773247,
|
|
"num_tokens": 10794400.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.349345016479492,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.18068427443504334,
|
|
"num_tokens": 10803138.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.395100116729736,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1752660870552063,
|
|
"num_tokens": 10813583.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.316332530975342,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18534980863332748,
|
|
"num_tokens": 10822532.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.319725513458252,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.3016,
|
|
"mean_token_accuracy": 0.18608538955450057,
|
|
"num_tokens": 10832256.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.3289566993713375,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.18748476803302766,
|
|
"num_tokens": 10840909.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.372947549819946,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.18154753595590592,
|
|
"num_tokens": 10849931.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.364373111724854,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.18243797421455382,
|
|
"num_tokens": 10859518.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.352173852920532,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.1771364316344261,
|
|
"num_tokens": 10868567.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.324528312683105,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.19510713815689087,
|
|
"num_tokens": 10877463.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.327762222290039,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.1772697314620018,
|
|
"num_tokens": 10886228.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.468494606018067,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17341220527887344,
|
|
"num_tokens": 10895415.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.3670299530029295,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.2754,
|
|
"mean_token_accuracy": 0.1696104109287262,
|
|
"num_tokens": 10904146.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.351732397079468,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.17885888516902923,
|
|
"num_tokens": 10914027.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.350140905380249,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.19121921807527542,
|
|
"num_tokens": 10923065.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.4460278987884525,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.407,
|
|
"mean_token_accuracy": 0.1723595902323723,
|
|
"num_tokens": 10932752.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.426205968856811,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.18056864738464357,
|
|
"num_tokens": 10942536.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.310159063339233,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.2472,
|
|
"mean_token_accuracy": 0.18073009699583054,
|
|
"num_tokens": 10952258.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.361242389678955,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.17866345047950744,
|
|
"num_tokens": 10961590.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.437377309799194,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.18697986453771592,
|
|
"num_tokens": 10971380.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.291711235046387,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.1789490357041359,
|
|
"num_tokens": 10979510.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.360995960235596,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.2772,
|
|
"mean_token_accuracy": 0.18087197691202164,
|
|
"num_tokens": 10988921.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.389206314086914,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.18446117490530015,
|
|
"num_tokens": 10998644.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.250856828689575,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.1854647397994995,
|
|
"num_tokens": 11006975.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.3128009796142575,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.1824902191758156,
|
|
"num_tokens": 11016011.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.439278030395508,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.17257942259311676,
|
|
"num_tokens": 11025600.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.371862173080444,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.18732891231775284,
|
|
"num_tokens": 11034747.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.168086645437029,
|
|
"eval_loss": 5.272536754608154,
|
|
"eval_mean_token_accuracy": 0.19146194885189163,
|
|
"eval_num_tokens": 11034747.0,
|
|
"eval_runtime": 27.4648,
|
|
"eval_samples_per_second": 1374.96,
|
|
"eval_steps_per_second": 171.893,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.394799995422363,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.1796693503856659,
|
|
"num_tokens": 11043461.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.376993131637573,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.3624,
|
|
"mean_token_accuracy": 0.18350306749343873,
|
|
"num_tokens": 11053632.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.350661516189575,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.18089560121297837,
|
|
"num_tokens": 11062620.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.324182462692261,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.17761649787425995,
|
|
"num_tokens": 11071105.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.406068515777588,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.2631,
|
|
"mean_token_accuracy": 0.19173841178417206,
|
|
"num_tokens": 11079926.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.341655635833741,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.17975347489118576,
|
|
"num_tokens": 11089395.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.341538000106811,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1858112931251526,
|
|
"num_tokens": 11098464.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.436836290359497,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.3628,
|
|
"mean_token_accuracy": 0.18345711678266524,
|
|
"num_tokens": 11107861.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.264323425292969,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.1859588786959648,
|
|
"num_tokens": 11116453.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.344191026687622,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.3059,
|
|
"mean_token_accuracy": 0.18284351974725724,
|
|
"num_tokens": 11125166.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.512290000915527,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.17712332904338837,
|
|
"num_tokens": 11134560.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.374829244613648,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.2323,
|
|
"mean_token_accuracy": 0.18858323246240616,
|
|
"num_tokens": 11143994.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.292056083679199,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.18212510496377946,
|
|
"num_tokens": 11152234.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.347263526916504,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.18932535350322724,
|
|
"num_tokens": 11161334.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.229281902313232,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.1679,
|
|
"mean_token_accuracy": 0.17916332483291625,
|
|
"num_tokens": 11170510.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.277205610275269,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.19500905573368071,
|
|
"num_tokens": 11179378.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.34964804649353,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.17949633449316024,
|
|
"num_tokens": 11189534.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.319961977005005,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.2073,
|
|
"mean_token_accuracy": 0.1925006777048111,
|
|
"num_tokens": 11197827.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.285190200805664,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.18829721659421922,
|
|
"num_tokens": 11206759.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.317176580429077,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.18879591822624206,
|
|
"num_tokens": 11216021.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.352275466918945,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.18401817828416825,
|
|
"num_tokens": 11224936.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.258750486373901,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.1853033795952797,
|
|
"num_tokens": 11233905.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.326344060897827,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.2003,
|
|
"mean_token_accuracy": 0.1920333117246628,
|
|
"num_tokens": 11242470.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.311832761764526,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.17805823534727097,
|
|
"num_tokens": 11251861.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.367962598800659,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.18427685350179673,
|
|
"num_tokens": 11260830.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.274614429473877,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.18828731626272202,
|
|
"num_tokens": 11269906.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.392090368270874,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.18325559794902802,
|
|
"num_tokens": 11279471.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.494892406463623,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.17832857221364976,
|
|
"num_tokens": 11288586.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.371882963180542,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.18487958014011383,
|
|
"num_tokens": 11297768.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.271016025543213,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.187505404651165,
|
|
"num_tokens": 11307096.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.2447319507598875,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.1980063021183014,
|
|
"num_tokens": 11315518.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.287977123260498,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.18654987812042237,
|
|
"num_tokens": 11324232.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.291946649551392,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.1816413149237633,
|
|
"num_tokens": 11332923.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.396589136123657,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.18228267282247543,
|
|
"num_tokens": 11342350.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.327940893173218,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.1379,
|
|
"mean_token_accuracy": 0.1896440178155899,
|
|
"num_tokens": 11350982.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.320274305343628,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.18778664916753768,
|
|
"num_tokens": 11360637.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.281010341644287,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.1879116863012314,
|
|
"num_tokens": 11368783.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.260682153701782,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.18889974802732468,
|
|
"num_tokens": 11378359.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.3671022891998295,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.18173590898513795,
|
|
"num_tokens": 11387235.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.400910234451294,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.18128463476896287,
|
|
"num_tokens": 11396400.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.402005577087403,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18878876864910127,
|
|
"num_tokens": 11405589.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.29880199432373,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17831768691539765,
|
|
"num_tokens": 11414983.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.375881719589233,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.1887017771601677,
|
|
"num_tokens": 11423172.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.417163419723511,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.18309810310602187,
|
|
"num_tokens": 11432758.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.248141956329346,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.18524384051561354,
|
|
"num_tokens": 11441754.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.318865442276001,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.18242405503988265,
|
|
"num_tokens": 11451176.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.402262163162232,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.18198805004358293,
|
|
"num_tokens": 11461353.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.390100288391113,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.17699251919984818,
|
|
"num_tokens": 11470103.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.353792905807495,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.19344995766878129,
|
|
"num_tokens": 11480348.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.366096448898316,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.18386424630880355,
|
|
"num_tokens": 11490836.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.267794942855835,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.19093482792377472,
|
|
"num_tokens": 11500344.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.4199565887451175,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.18004805445671082,
|
|
"num_tokens": 11509624.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.363396215438843,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.17866567373275757,
|
|
"num_tokens": 11519915.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.339620590209961,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.18377067893743515,
|
|
"num_tokens": 11528918.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.312790298461914,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.2752,
|
|
"mean_token_accuracy": 0.18144809901714326,
|
|
"num_tokens": 11537396.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.415223217010498,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.17622718214988708,
|
|
"num_tokens": 11547196.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.396162748336792,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.18347851037979127,
|
|
"num_tokens": 11556126.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.36080379486084,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.3083,
|
|
"mean_token_accuracy": 0.1859940469264984,
|
|
"num_tokens": 11565622.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.297771167755127,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.18722766786813735,
|
|
"num_tokens": 11576052.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.355345773696899,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.16857851147651673,
|
|
"num_tokens": 11585907.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.287508487701416,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18631986975669862,
|
|
"num_tokens": 11594802.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.292425870895386,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19151604771614075,
|
|
"num_tokens": 11604026.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.32039098739624,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.1752871811389923,
|
|
"num_tokens": 11614209.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.335412788391113,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.1697,
|
|
"mean_token_accuracy": 0.18593906611204147,
|
|
"num_tokens": 11622492.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.362774753570557,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.207,
|
|
"mean_token_accuracy": 0.18361861407756805,
|
|
"num_tokens": 11631106.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.334519529342652,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.18772526681423188,
|
|
"num_tokens": 11639748.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.312885999679565,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.18425588458776473,
|
|
"num_tokens": 11648524.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.372761058807373,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.248,
|
|
"mean_token_accuracy": 0.178777277469635,
|
|
"num_tokens": 11658439.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.339153194427491,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.18067725151777267,
|
|
"num_tokens": 11666319.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.301879787445069,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.1856699615716934,
|
|
"num_tokens": 11675506.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.319541597366333,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.1835037186741829,
|
|
"num_tokens": 11685613.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.319072628021241,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1810879200696945,
|
|
"num_tokens": 11694896.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.491897201538086,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.17695481777191163,
|
|
"num_tokens": 11703599.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.344759941101074,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.1957557275891304,
|
|
"num_tokens": 11712155.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.273065137863159,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.18458784073591233,
|
|
"num_tokens": 11721224.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.3125457763671875,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.18925199061632156,
|
|
"num_tokens": 11729733.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.3117241859436035,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.17879771590232849,
|
|
"num_tokens": 11738840.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.356008720397949,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.3318,
|
|
"mean_token_accuracy": 0.1799089327454567,
|
|
"num_tokens": 11748632.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.310668516159057,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19112634360790254,
|
|
"num_tokens": 11756707.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.355916213989258,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.18032287508249284,
|
|
"num_tokens": 11765346.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.340433788299561,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.1888291731476784,
|
|
"num_tokens": 11773663.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.372768115997315,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.1827616810798645,
|
|
"num_tokens": 11783782.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.398755311965942,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.18580945432186127,
|
|
"num_tokens": 11792241.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.3338744163513185,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.3103,
|
|
"mean_token_accuracy": 0.17886969894170762,
|
|
"num_tokens": 11801576.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.31033148765564,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.188408163189888,
|
|
"num_tokens": 11810710.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.397537183761597,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.17591421604156493,
|
|
"num_tokens": 11820099.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.3122954845428465,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.1716,
|
|
"mean_token_accuracy": 0.18763360679149627,
|
|
"num_tokens": 11828846.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.272968387603759,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.1852931261062622,
|
|
"num_tokens": 11837935.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.34056282043457,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.1879839390516281,
|
|
"num_tokens": 11846984.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.253386402130127,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.18641676306724547,
|
|
"num_tokens": 11856114.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.310311222076416,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.3302,
|
|
"mean_token_accuracy": 0.18253034204244614,
|
|
"num_tokens": 11866623.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.37350287437439,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.18385156393051147,
|
|
"num_tokens": 11876445.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.384360313415527,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.17601316720247268,
|
|
"num_tokens": 11885411.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.3778462409973145,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18532623797655107,
|
|
"num_tokens": 11894803.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.297641801834106,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.2744,
|
|
"mean_token_accuracy": 0.18821530789136887,
|
|
"num_tokens": 11904299.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.235662508010864,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.1875820815563202,
|
|
"num_tokens": 11914197.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.400727891921997,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.3529,
|
|
"mean_token_accuracy": 0.1850871503353119,
|
|
"num_tokens": 11923610.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.395964241027832,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.18822776824235915,
|
|
"num_tokens": 11932896.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.292629766464233,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1863493502140045,
|
|
"num_tokens": 11941343.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.30104546546936,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.1853145882487297,
|
|
"num_tokens": 11950412.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.289846134185791,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.19622760713100434,
|
|
"num_tokens": 11959021.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.367030763626099,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18347511291503907,
|
|
"num_tokens": 11968725.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.335864305496216,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.2373,
|
|
"mean_token_accuracy": 0.17939867675304413,
|
|
"num_tokens": 11977775.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.379273796081543,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.3014,
|
|
"mean_token_accuracy": 0.180289189517498,
|
|
"num_tokens": 11988010.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.261785268783569,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.1917942926287651,
|
|
"num_tokens": 11997284.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.341743993759155,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.183339224755764,
|
|
"num_tokens": 12005516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.3298993587493895,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.186410990357399,
|
|
"num_tokens": 12014236.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.3112791061401365,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.18704894930124283,
|
|
"num_tokens": 12022201.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.334233808517456,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.3534,
|
|
"mean_token_accuracy": 0.1755892276763916,
|
|
"num_tokens": 12032421.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.419464063644409,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.18279391378164292,
|
|
"num_tokens": 12041443.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.299913644790649,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.18709085285663604,
|
|
"num_tokens": 12050753.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.299720525741577,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.2164,
|
|
"mean_token_accuracy": 0.184294630587101,
|
|
"num_tokens": 12059886.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.289112997055054,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.2209,
|
|
"mean_token_accuracy": 0.1795896425843239,
|
|
"num_tokens": 12068695.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.289681816101075,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.1453,
|
|
"mean_token_accuracy": 0.18942635357379914,
|
|
"num_tokens": 12077552.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.463022994995117,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.18367442786693572,
|
|
"num_tokens": 12085994.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.388846778869629,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.1829482540488243,
|
|
"num_tokens": 12095342.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.213991975784301,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.18362866789102555,
|
|
"num_tokens": 12104578.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.146052742004395,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.19359901547431946,
|
|
"num_tokens": 12113614.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.4128223896026615,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.3453,
|
|
"mean_token_accuracy": 0.18435679525136947,
|
|
"num_tokens": 12123328.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.384577131271362,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.1866936355829239,
|
|
"num_tokens": 12133011.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.469799757003784,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17317648231983185,
|
|
"num_tokens": 12142398.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.417175436019898,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.16581220924854279,
|
|
"num_tokens": 12152210.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.388317823410034,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.1858538344502449,
|
|
"num_tokens": 12162083.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.433413791656494,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.1742522731423378,
|
|
"num_tokens": 12172024.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.428104543685913,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.17468141615390778,
|
|
"num_tokens": 12181474.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.425901985168457,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.3075,
|
|
"mean_token_accuracy": 0.1809348151087761,
|
|
"num_tokens": 12190622.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.315758991241455,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.3024,
|
|
"mean_token_accuracy": 0.18531003296375276,
|
|
"num_tokens": 12199282.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.305345439910889,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.18667261004447938,
|
|
"num_tokens": 12208536.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.39209303855896,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.2755,
|
|
"mean_token_accuracy": 0.1802435338497162,
|
|
"num_tokens": 12217716.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.259994697570801,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.18910439759492875,
|
|
"num_tokens": 12226214.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.279370307922363,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.1201,
|
|
"mean_token_accuracy": 0.19275906234979628,
|
|
"num_tokens": 12235005.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.25799880027771,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.18881827145814895,
|
|
"num_tokens": 12243085.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.421213436126709,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.17473243325948715,
|
|
"num_tokens": 12252826.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.40093355178833,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.17674487233161926,
|
|
"num_tokens": 12261166.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.298817110061646,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.18788901716470718,
|
|
"num_tokens": 12270695.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.434196329116821,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.3661,
|
|
"mean_token_accuracy": 0.1773197114467621,
|
|
"num_tokens": 12280486.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.424243497848511,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1849601835012436,
|
|
"num_tokens": 12289246.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.122715139389038,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.18086159825325013,
|
|
"num_tokens": 12297562.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.3659802913665775,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.1803388088941574,
|
|
"num_tokens": 12307647.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.42486891746521,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.282,
|
|
"mean_token_accuracy": 0.18235939145088195,
|
|
"num_tokens": 12317840.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.329939699172973,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18844126164913177,
|
|
"num_tokens": 12327340.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.260721683502197,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.18876503109931947,
|
|
"num_tokens": 12336269.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.442825603485107,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.17961659133434296,
|
|
"num_tokens": 12345197.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.43170132637024,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.2684,
|
|
"mean_token_accuracy": 0.183046917617321,
|
|
"num_tokens": 12355312.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.3082623958587645,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.18221138715744017,
|
|
"num_tokens": 12364354.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.375804042816162,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17645538002252578,
|
|
"num_tokens": 12373512.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.373493480682373,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.1795360788702965,
|
|
"num_tokens": 12383087.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.34245867729187,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.19321381896734238,
|
|
"num_tokens": 12392097.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.346031045913696,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 5.2188,
|
|
"mean_token_accuracy": 0.1921417385339737,
|
|
"num_tokens": 12401806.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.3388477802276615,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.1802361339330673,
|
|
"num_tokens": 12412111.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.190551090240478,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.19084409177303313,
|
|
"num_tokens": 12421451.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.178379869461059,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 5.0914,
|
|
"mean_token_accuracy": 0.19183809757232667,
|
|
"num_tokens": 12430535.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.332199239730835,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.17987142205238343,
|
|
"num_tokens": 12439727.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.314920043945312,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.1334,
|
|
"mean_token_accuracy": 0.19156450480222703,
|
|
"num_tokens": 12448889.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.208768129348755,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.1141,
|
|
"mean_token_accuracy": 0.19008472561836243,
|
|
"num_tokens": 12457529.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.298174905776977,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.186704021692276,
|
|
"num_tokens": 12466379.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.298062181472778,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.18568971008062363,
|
|
"num_tokens": 12475317.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.388056898117066,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.17674677073955536,
|
|
"num_tokens": 12483882.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.393543100357055,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1825995609164238,
|
|
"num_tokens": 12493782.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.22726674079895,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.0696,
|
|
"mean_token_accuracy": 0.19600007981061934,
|
|
"num_tokens": 12501940.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.2739979267120365,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.1818484529852867,
|
|
"num_tokens": 12511566.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.299200105667114,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.19029798060655595,
|
|
"num_tokens": 12519902.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.405635023117066,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.17589733600616456,
|
|
"num_tokens": 12529011.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.315787696838379,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.2656,
|
|
"mean_token_accuracy": 0.1805856019258499,
|
|
"num_tokens": 12538181.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.35498456954956,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.17893521636724471,
|
|
"num_tokens": 12545935.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.29422960281372,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.1820117339491844,
|
|
"num_tokens": 12555586.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.323349094390869,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.18298058658838273,
|
|
"num_tokens": 12564478.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.304536437988281,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.1874542161822319,
|
|
"num_tokens": 12573769.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.286143493652344,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.189128577709198,
|
|
"num_tokens": 12583291.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.273022413253784,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.19136483520269393,
|
|
"num_tokens": 12591828.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.224130153656006,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.18667172342538835,
|
|
"num_tokens": 12600417.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.288603210449219,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19128816276788713,
|
|
"num_tokens": 12609555.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.465093469619751,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.1806751385331154,
|
|
"num_tokens": 12618666.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.46686863899231,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.3224,
|
|
"mean_token_accuracy": 0.1820882961153984,
|
|
"num_tokens": 12627206.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.374486637115479,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.27,
|
|
"mean_token_accuracy": 0.18061840683221816,
|
|
"num_tokens": 12636782.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.309173727035523,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.1896350860595703,
|
|
"num_tokens": 12645895.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.220979022979736,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.1859116241335869,
|
|
"num_tokens": 12655744.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.219499254226685,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.19034142792224884,
|
|
"num_tokens": 12665498.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.347544240951538,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.18442365378141404,
|
|
"num_tokens": 12674218.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.3160968780517575,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.1894842803478241,
|
|
"num_tokens": 12683060.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.311458444595337,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.18776786774396897,
|
|
"num_tokens": 12693145.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.243571090698242,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.17975606322288512,
|
|
"num_tokens": 12701439.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.400462102890015,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.17578370869159698,
|
|
"num_tokens": 12710582.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.386904525756836,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.184463831782341,
|
|
"num_tokens": 12719685.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.32031364440918,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.18566998988389968,
|
|
"num_tokens": 12729632.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.217878770828247,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.1036,
|
|
"mean_token_accuracy": 0.19576410204172134,
|
|
"num_tokens": 12738900.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.214184093475342,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 5.0763,
|
|
"mean_token_accuracy": 0.19970481544733049,
|
|
"num_tokens": 12748195.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.331734228134155,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.18134150207042693,
|
|
"num_tokens": 12757038.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.19258189201355,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.1753,
|
|
"mean_token_accuracy": 0.19638993591070175,
|
|
"num_tokens": 12765871.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.282092189788818,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.1589,
|
|
"mean_token_accuracy": 0.19112114757299423,
|
|
"num_tokens": 12774776.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.372214317321777,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.2495,
|
|
"mean_token_accuracy": 0.18278664201498032,
|
|
"num_tokens": 12783815.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.4111034870147705,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.29,
|
|
"mean_token_accuracy": 0.17568725496530532,
|
|
"num_tokens": 12793690.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.3078378200531,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.18332116156816483,
|
|
"num_tokens": 12802525.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.360084676742554,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.2274,
|
|
"mean_token_accuracy": 0.18500502705574035,
|
|
"num_tokens": 12811246.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.355574703216552,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.1834030732512474,
|
|
"num_tokens": 12820477.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.310442113876343,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.1185,
|
|
"mean_token_accuracy": 0.19551344811916352,
|
|
"num_tokens": 12829544.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.269707918167114,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.1951313778758049,
|
|
"num_tokens": 12839388.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.24746265411377,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.1925328031182289,
|
|
"num_tokens": 12848191.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.24632158279419,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.18232031911611557,
|
|
"num_tokens": 12859239.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.420159435272216,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.18971134573221207,
|
|
"num_tokens": 12868335.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.269492864608765,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.1487,
|
|
"mean_token_accuracy": 0.1872716426849365,
|
|
"num_tokens": 12876939.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.19940676689148,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.1511,
|
|
"mean_token_accuracy": 0.1863880440592766,
|
|
"num_tokens": 12885856.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.435565090179443,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.17623012959957124,
|
|
"num_tokens": 12895451.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.384980773925781,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.18783926218748093,
|
|
"num_tokens": 12904796.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.320826721191406,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.17882730811834335,
|
|
"num_tokens": 12913668.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.3277966499328615,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.1788,
|
|
"mean_token_accuracy": 0.18854000717401503,
|
|
"num_tokens": 12922469.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.193450784683227,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.18770741820335388,
|
|
"num_tokens": 12931070.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.296234560012818,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.2357,
|
|
"mean_token_accuracy": 0.19035572558641434,
|
|
"num_tokens": 12939397.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.422897005081177,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.17893508523702623,
|
|
"num_tokens": 12948951.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.32398829460144,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.1897008717060089,
|
|
"num_tokens": 12958431.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.408656358718872,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.2422,
|
|
"mean_token_accuracy": 0.19711191207170486,
|
|
"num_tokens": 12966521.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.28595757484436,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18485396653413771,
|
|
"num_tokens": 12976458.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.255414915084839,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.19233511239290238,
|
|
"num_tokens": 12985715.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.2574474811553955,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.18003213554620742,
|
|
"num_tokens": 12995640.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.328100156784058,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.18547921776771545,
|
|
"num_tokens": 13004645.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.327472066879272,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.18197911977767944,
|
|
"num_tokens": 13013433.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.399848365783692,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.3034,
|
|
"mean_token_accuracy": 0.18082935661077498,
|
|
"num_tokens": 13023098.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.346718597412109,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.1969370573759079,
|
|
"num_tokens": 13031715.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.270420169830322,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.1948,
|
|
"mean_token_accuracy": 0.18444593250751495,
|
|
"num_tokens": 13040847.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.278219938278198,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.1857482075691223,
|
|
"num_tokens": 13050502.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.30429048538208,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.18868696242570876,
|
|
"num_tokens": 13059729.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.34501051902771,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.2663,
|
|
"mean_token_accuracy": 0.1812531977891922,
|
|
"num_tokens": 13069123.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.319238185882568,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.1846571832895279,
|
|
"num_tokens": 13077777.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.386619281768799,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.17931535094976425,
|
|
"num_tokens": 13086576.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.321637153625488,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.18916917145252227,
|
|
"num_tokens": 13095166.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.322514963150025,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.18322862684726715,
|
|
"num_tokens": 13103692.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.261594581604004,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 5.1294,
|
|
"mean_token_accuracy": 0.18912494629621507,
|
|
"num_tokens": 13111899.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.301736068725586,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.1457,
|
|
"mean_token_accuracy": 0.19724455028772353,
|
|
"num_tokens": 13120345.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.303208208084106,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.1907811388373375,
|
|
"num_tokens": 13129035.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.288313198089599,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.18506258428096772,
|
|
"num_tokens": 13138956.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.338060474395752,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.2023,
|
|
"mean_token_accuracy": 0.18579529523849486,
|
|
"num_tokens": 13148605.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.278689813613892,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.18053558766841887,
|
|
"num_tokens": 13158125.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.243731737136841,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.1900031641125679,
|
|
"num_tokens": 13167404.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.294559335708618,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.1731,
|
|
"mean_token_accuracy": 0.19000328779220582,
|
|
"num_tokens": 13176467.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.217110300064087,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.19307963848114013,
|
|
"num_tokens": 13185201.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.23073673248291,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.19369222819805146,
|
|
"num_tokens": 13194871.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.34356837272644,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.2411,
|
|
"mean_token_accuracy": 0.18253419399261475,
|
|
"num_tokens": 13205006.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.272913312911987,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 5.1738,
|
|
"mean_token_accuracy": 0.18916500508785247,
|
|
"num_tokens": 13214093.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.267279148101807,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.19354642778635026,
|
|
"num_tokens": 13223178.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.257905721664429,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.19590703397989273,
|
|
"num_tokens": 13232357.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.307076072692871,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.181342650949955,
|
|
"num_tokens": 13242538.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.454485702514648,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.3288,
|
|
"mean_token_accuracy": 0.17714773416519164,
|
|
"num_tokens": 13252410.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.3239843368530275,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.2551,
|
|
"mean_token_accuracy": 0.18909587562084199,
|
|
"num_tokens": 13262291.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.291239643096924,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.17985448390245437,
|
|
"num_tokens": 13271952.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.377409601211548,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 5.2516,
|
|
"mean_token_accuracy": 0.18127916753292084,
|
|
"num_tokens": 13281898.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.3245580196380615,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.18747837841510773,
|
|
"num_tokens": 13290205.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.371450138092041,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.264,
|
|
"mean_token_accuracy": 0.17748096883296965,
|
|
"num_tokens": 13299420.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.299730682373047,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.19273400604724883,
|
|
"num_tokens": 13307931.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.288811588287354,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.18483478277921678,
|
|
"num_tokens": 13316646.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.221371078491211,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18441895246505738,
|
|
"num_tokens": 13325564.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.361169385910034,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18220609426498413,
|
|
"num_tokens": 13335396.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.309096097946167,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.18890001624822617,
|
|
"num_tokens": 13344124.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.197010850906372,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.19340737760066987,
|
|
"num_tokens": 13353125.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.3060260772705075,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.18631464689970018,
|
|
"num_tokens": 13361388.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.3180506229400635,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.18138295859098436,
|
|
"num_tokens": 13371061.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.2150026798248295,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.1936565563082695,
|
|
"num_tokens": 13380077.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.37867226600647,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.18226235508918762,
|
|
"num_tokens": 13390091.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.338456916809082,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.19249432682991027,
|
|
"num_tokens": 13399793.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.247054529190064,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19297747313976288,
|
|
"num_tokens": 13408771.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.349658203125,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.3082,
|
|
"mean_token_accuracy": 0.179022678732872,
|
|
"num_tokens": 13417569.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.310270833969116,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.18481265157461166,
|
|
"num_tokens": 13427296.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.387631130218506,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.1780461221933365,
|
|
"num_tokens": 13436489.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.335109424591065,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.1812914326786995,
|
|
"num_tokens": 13445783.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.333179616928101,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.1859467312693596,
|
|
"num_tokens": 13454862.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.3446472644805905,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.18590015321969985,
|
|
"num_tokens": 13463758.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.388862609863281,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.18363479375839234,
|
|
"num_tokens": 13472808.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.257959079742432,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.19224871397018434,
|
|
"num_tokens": 13482550.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.274133014678955,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.2659,
|
|
"mean_token_accuracy": 0.1815333530306816,
|
|
"num_tokens": 13491970.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.294647169113159,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.1917921334505081,
|
|
"num_tokens": 13500699.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.257726860046387,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.18986501544713974,
|
|
"num_tokens": 13509108.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.279509687423706,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 5.1395,
|
|
"mean_token_accuracy": 0.19250394254922867,
|
|
"num_tokens": 13517529.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.177189016342163,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.20139864683151246,
|
|
"num_tokens": 13526379.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.291180562973023,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.17230814099311828,
|
|
"num_tokens": 13535873.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.307261562347412,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.18773140162229537,
|
|
"num_tokens": 13545514.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.291108083724976,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.18375722020864488,
|
|
"num_tokens": 13554226.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.328939390182495,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.1805404931306839,
|
|
"num_tokens": 13563554.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.196860980987549,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.20545026659965515,
|
|
"num_tokens": 13572128.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.334772062301636,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.18795283138751984,
|
|
"num_tokens": 13582285.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.281139945983886,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 5.1325,
|
|
"mean_token_accuracy": 0.1949436455965042,
|
|
"num_tokens": 13590969.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.300789642333984,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.1911582663655281,
|
|
"num_tokens": 13600523.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.322118473052979,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1932110920548439,
|
|
"num_tokens": 13609203.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.232994413375854,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.18712807595729827,
|
|
"num_tokens": 13618175.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.3347086906433105,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.18564439415931702,
|
|
"num_tokens": 13627245.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.450446367263794,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.18550013601779938,
|
|
"num_tokens": 13636910.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.332142734527588,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.18843764215707778,
|
|
"num_tokens": 13646072.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.355451202392578,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18733312636613847,
|
|
"num_tokens": 13655823.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.280789518356324,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.18302804231643677,
|
|
"num_tokens": 13665038.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.395793724060058,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.1843681290745735,
|
|
"num_tokens": 13673925.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.338581800460815,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.18515721708536148,
|
|
"num_tokens": 13682252.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.216605138778687,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.1913221836090088,
|
|
"num_tokens": 13691462.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.4017653465271,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.1839205339550972,
|
|
"num_tokens": 13701370.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.366975736618042,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.18677881509065627,
|
|
"num_tokens": 13709673.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.234641790390015,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.18868394643068315,
|
|
"num_tokens": 13719947.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.3808183670043945,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.18341430723667146,
|
|
"num_tokens": 13728813.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.396779632568359,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.18841298520565034,
|
|
"num_tokens": 13738319.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.248705005645752,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.191838076710701,
|
|
"num_tokens": 13747337.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.271488285064697,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.18855925649404526,
|
|
"num_tokens": 13756050.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.308868312835694,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.1839320629835129,
|
|
"num_tokens": 13765297.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.336758756637574,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.1943068489432335,
|
|
"num_tokens": 13773958.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.285659694671631,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.1855810433626175,
|
|
"num_tokens": 13784037.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.382388496398926,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.19026362299919128,
|
|
"num_tokens": 13793709.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.288311243057251,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.19725475013256072,
|
|
"num_tokens": 13801466.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.331857442855835,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.17607493251562117,
|
|
"num_tokens": 13811903.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.3850696086883545,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.19172122031450273,
|
|
"num_tokens": 13820861.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.385110235214233,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.1790284112095833,
|
|
"num_tokens": 13831049.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.344508504867553,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.2478,
|
|
"mean_token_accuracy": 0.18893121927976608,
|
|
"num_tokens": 13840628.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.25383415222168,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.18811701685190202,
|
|
"num_tokens": 13849424.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.24720778465271,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.19245729148387908,
|
|
"num_tokens": 13859216.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.361807584762573,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1917789936065674,
|
|
"num_tokens": 13867638.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.4235604763031,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.1831221789121628,
|
|
"num_tokens": 13877016.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.312173700332641,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.2891,
|
|
"mean_token_accuracy": 0.17328477948904036,
|
|
"num_tokens": 13887305.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.295931434631347,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.19361737221479416,
|
|
"num_tokens": 13896003.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.282864570617676,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.18436953872442247,
|
|
"num_tokens": 13904964.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.317825841903686,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.18204531371593474,
|
|
"num_tokens": 13915049.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.303839635848999,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.19663185626268387,
|
|
"num_tokens": 13924938.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.43185510635376,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.16907385885715484,
|
|
"num_tokens": 13935050.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.339563465118408,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.19084191918373108,
|
|
"num_tokens": 13943576.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.241533613204956,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.18564321249723434,
|
|
"num_tokens": 13953232.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.343335962295532,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.3758,
|
|
"mean_token_accuracy": 0.17697664722800255,
|
|
"num_tokens": 13962121.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.385099267959594,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.2501,
|
|
"mean_token_accuracy": 0.17955022156238556,
|
|
"num_tokens": 13971681.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.30552110671997,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.19973503351211547,
|
|
"num_tokens": 13980118.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.297439622879028,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.18801899403333663,
|
|
"num_tokens": 13989755.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.222371053695679,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.155,
|
|
"mean_token_accuracy": 0.18301116526126862,
|
|
"num_tokens": 13999289.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.316830015182495,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.2644,
|
|
"mean_token_accuracy": 0.18290550112724305,
|
|
"num_tokens": 14009101.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.377586317062378,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.18653845489025117,
|
|
"num_tokens": 14018197.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.2109386920928955,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.1341,
|
|
"mean_token_accuracy": 0.19235458523035048,
|
|
"num_tokens": 14028108.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.31895809173584,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.1735656425356865,
|
|
"num_tokens": 14038636.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.3375874042510985,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.1839364290237427,
|
|
"num_tokens": 14048502.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.372132015228272,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.3236,
|
|
"mean_token_accuracy": 0.17816595435142518,
|
|
"num_tokens": 14058654.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.328364324569702,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.19192207008600234,
|
|
"num_tokens": 14068614.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.280334568023681,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.1896479234099388,
|
|
"num_tokens": 14077550.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.306500101089478,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.18305613249540328,
|
|
"num_tokens": 14086610.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.260514593124389,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.18237021267414094,
|
|
"num_tokens": 14095795.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.321788883209228,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.1405,
|
|
"mean_token_accuracy": 0.1904669240117073,
|
|
"num_tokens": 14104779.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.297952651977539,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.19697895497083664,
|
|
"num_tokens": 14113299.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.252028608322144,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.2322,
|
|
"mean_token_accuracy": 0.19213329404592513,
|
|
"num_tokens": 14121969.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.353702354431152,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.18738498985767366,
|
|
"num_tokens": 14130850.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.330335378646851,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.18880516290664673,
|
|
"num_tokens": 14140142.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.123462390899658,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.19274820387363434,
|
|
"num_tokens": 14148335.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.360991096496582,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.2553,
|
|
"mean_token_accuracy": 0.1787935361266136,
|
|
"num_tokens": 14157566.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.3845436573028564,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.17988270670175552,
|
|
"num_tokens": 14166037.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.191599130630493,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.19823317974805832,
|
|
"num_tokens": 14174735.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.350530290603638,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 5.2549,
|
|
"mean_token_accuracy": 0.18151563853025438,
|
|
"num_tokens": 14185130.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.4578296661376955,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.18424693793058394,
|
|
"num_tokens": 14194676.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.360512399673462,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18780234456062317,
|
|
"num_tokens": 14204218.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.230155420303345,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.18467172980308533,
|
|
"num_tokens": 14213176.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.373636198043823,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.18102581351995467,
|
|
"num_tokens": 14222490.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.3416601657867435,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17828164547681807,
|
|
"num_tokens": 14231335.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.359674739837646,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.2303,
|
|
"mean_token_accuracy": 0.18459064662456512,
|
|
"num_tokens": 14240583.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.392180061340332,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.2008,
|
|
"mean_token_accuracy": 0.19037179052829742,
|
|
"num_tokens": 14250087.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.374785852432251,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.3015,
|
|
"mean_token_accuracy": 0.17718515545129776,
|
|
"num_tokens": 14261076.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.3138974666595455,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.18958569467067718,
|
|
"num_tokens": 14270234.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.254745769500732,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.18739570677280426,
|
|
"num_tokens": 14279154.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.262589073181152,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.18639917820692062,
|
|
"num_tokens": 14289626.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.267973899841309,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.19295641034841537,
|
|
"num_tokens": 14299647.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.436268663406372,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.179313787817955,
|
|
"num_tokens": 14308944.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.38254828453064,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.2986,
|
|
"mean_token_accuracy": 0.1824707269668579,
|
|
"num_tokens": 14318168.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.289823293685913,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.1992276653647423,
|
|
"num_tokens": 14327249.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.281346654891967,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18996517956256867,
|
|
"num_tokens": 14336055.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.295825099945068,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.19329801350831985,
|
|
"num_tokens": 14344862.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.403456354141236,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.17764141261577607,
|
|
"num_tokens": 14354284.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.354050016403198,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.1875,
|
|
"mean_token_accuracy": 0.18953971862792968,
|
|
"num_tokens": 14363615.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.330633354187012,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.1425,
|
|
"mean_token_accuracy": 0.18493614941835404,
|
|
"num_tokens": 14372805.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.274392747879029,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.2607,
|
|
"mean_token_accuracy": 0.17995638400316238,
|
|
"num_tokens": 14382334.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.328124380111694,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.1736,
|
|
"mean_token_accuracy": 0.18850196301937103,
|
|
"num_tokens": 14391360.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.347755670547485,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.1800881505012512,
|
|
"num_tokens": 14401232.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.426602840423584,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.1826469749212265,
|
|
"num_tokens": 14409773.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.385968399047852,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.18334679454565048,
|
|
"num_tokens": 14419511.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.2667396545410154,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.1925,
|
|
"mean_token_accuracy": 0.19224025309085846,
|
|
"num_tokens": 14428611.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.1868668556213375,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 5.0746,
|
|
"mean_token_accuracy": 0.19552791267633438,
|
|
"num_tokens": 14436721.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.320091581344604,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.2332,
|
|
"mean_token_accuracy": 0.18761514872312546,
|
|
"num_tokens": 14445766.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.244475412368774,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.1005,
|
|
"mean_token_accuracy": 0.18802379816770554,
|
|
"num_tokens": 14453857.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.245399618148804,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19586975872516632,
|
|
"num_tokens": 14462356.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.287431621551514,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.19043235331773758,
|
|
"num_tokens": 14471848.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.263445663452148,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.18838344365358353,
|
|
"num_tokens": 14481128.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.280665159225464,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.19354743063449859,
|
|
"num_tokens": 14490071.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.344894695281982,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.18232745081186294,
|
|
"num_tokens": 14499162.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.327264404296875,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.18955582082271577,
|
|
"num_tokens": 14508525.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.304840087890625,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.1902075305581093,
|
|
"num_tokens": 14516885.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.261585330963134,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.19048814475536346,
|
|
"num_tokens": 14525116.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.250884675979615,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.2641,
|
|
"mean_token_accuracy": 0.1920710727572441,
|
|
"num_tokens": 14534452.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.284350824356079,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19259440004825593,
|
|
"num_tokens": 14544040.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.422929334640503,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18493396043777466,
|
|
"num_tokens": 14553343.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.316207981109619,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.18950279653072358,
|
|
"num_tokens": 14562657.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.242904329299927,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.18897778391838074,
|
|
"num_tokens": 14572167.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.254485607147217,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.18617894649505615,
|
|
"num_tokens": 14580934.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.275124263763428,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19313859790563584,
|
|
"num_tokens": 14589579.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.327301549911499,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.1868191123008728,
|
|
"num_tokens": 14599289.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.343547105789185,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.19341417402029037,
|
|
"num_tokens": 14608322.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.324182224273682,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.2062,
|
|
"mean_token_accuracy": 0.190206441283226,
|
|
"num_tokens": 14617591.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.283283615112305,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.1912426620721817,
|
|
"num_tokens": 14625809.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.375922298431396,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.2284,
|
|
"mean_token_accuracy": 0.18226083368062973,
|
|
"num_tokens": 14635061.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.26524715423584,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.2736,
|
|
"mean_token_accuracy": 0.18430304676294326,
|
|
"num_tokens": 14645104.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.364509105682373,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.18456349819898604,
|
|
"num_tokens": 14653984.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.258089303970337,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.18901885002851487,
|
|
"num_tokens": 14663315.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.215296411514283,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.1944261074066162,
|
|
"num_tokens": 14672608.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.38453106880188,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.19073372185230256,
|
|
"num_tokens": 14682031.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.307742977142334,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18530760258436202,
|
|
"num_tokens": 14691894.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.276402330398559,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.18451732099056245,
|
|
"num_tokens": 14700508.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.397201347351074,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.1825764000415802,
|
|
"num_tokens": 14709241.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.342011737823486,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.18244830667972564,
|
|
"num_tokens": 14719300.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.3934918403625485,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.18987406194210052,
|
|
"num_tokens": 14729717.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.3500213623046875,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.1889166057109833,
|
|
"num_tokens": 14738757.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.0954750061035154,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.18967511951923371,
|
|
"num_tokens": 14747171.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.1857727527618405,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.1838504657149315,
|
|
"num_tokens": 14756064.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.3562424659729,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.1907202944159508,
|
|
"num_tokens": 14765156.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.4175444602966305,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.19196956157684325,
|
|
"num_tokens": 14774059.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.201346492767334,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.115,
|
|
"mean_token_accuracy": 0.19651183634996414,
|
|
"num_tokens": 14783500.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.31565113067627,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.18489293456077577,
|
|
"num_tokens": 14792901.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.413379955291748,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.1820690855383873,
|
|
"num_tokens": 14801619.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.240681743621826,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.1637,
|
|
"mean_token_accuracy": 0.1892152801156044,
|
|
"num_tokens": 14811128.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.2843005657196045,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18780788034200668,
|
|
"num_tokens": 14819772.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.304719734191894,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.19334981739521026,
|
|
"num_tokens": 14828139.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.315226221084595,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.18278479874134063,
|
|
"num_tokens": 14837121.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.302050685882568,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.188950976729393,
|
|
"num_tokens": 14845973.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.295114278793335,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 5.2624,
|
|
"mean_token_accuracy": 0.18287192285060883,
|
|
"num_tokens": 14856072.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.262533712387085,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.1554,
|
|
"mean_token_accuracy": 0.1857127159833908,
|
|
"num_tokens": 14864845.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.317600965499878,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.18602113127708436,
|
|
"num_tokens": 14874170.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.296185922622681,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.19489070773124695,
|
|
"num_tokens": 14882618.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.308361148834228,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.17853918075561523,
|
|
"num_tokens": 14893258.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.336450529098511,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.17795838117599488,
|
|
"num_tokens": 14904424.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.40800838470459,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1789371445775032,
|
|
"num_tokens": 14913935.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.236117124557495,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.1956703245639801,
|
|
"num_tokens": 14923352.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.184804248809814,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 5.0684,
|
|
"mean_token_accuracy": 0.19307749718427658,
|
|
"num_tokens": 14932080.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.289352321624756,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.18349912762641907,
|
|
"num_tokens": 14939747.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.277930116653442,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.18977949172258377,
|
|
"num_tokens": 14948639.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.346895742416382,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.1869726985692978,
|
|
"num_tokens": 14957831.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.384111928939819,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.1735308885574341,
|
|
"num_tokens": 14968732.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.318551921844483,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.19190097600221634,
|
|
"num_tokens": 14978684.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.502088594436645,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18139556646347046,
|
|
"num_tokens": 14988036.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.332143402099609,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.1558,
|
|
"mean_token_accuracy": 0.194850791990757,
|
|
"num_tokens": 14996773.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.29870080947876,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.2494,
|
|
"mean_token_accuracy": 0.18419882506132126,
|
|
"num_tokens": 15005552.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.280312871932983,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19198163002729415,
|
|
"num_tokens": 15014026.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.363230514526367,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.211,
|
|
"mean_token_accuracy": 0.18872150033712387,
|
|
"num_tokens": 15023607.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.294639158248901,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.1872321143746376,
|
|
"num_tokens": 15033102.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.307678127288819,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.191020168364048,
|
|
"num_tokens": 15042506.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.313725519180298,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.19131357371807098,
|
|
"num_tokens": 15052483.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.27556676864624,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.1567,
|
|
"mean_token_accuracy": 0.19765861928462983,
|
|
"num_tokens": 15060769.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.3392613410949705,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.18380562216043472,
|
|
"num_tokens": 15070398.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.349657106399536,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18381480127573013,
|
|
"num_tokens": 15079939.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.3600842475891115,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 5.1668,
|
|
"mean_token_accuracy": 0.19448400437831878,
|
|
"num_tokens": 15089391.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.251515674591064,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.1877202644944191,
|
|
"num_tokens": 15098875.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.311760473251343,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.18449883610010148,
|
|
"num_tokens": 15108359.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.388326025009155,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.17387497872114183,
|
|
"num_tokens": 15117957.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.376242208480835,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.18277179151773454,
|
|
"num_tokens": 15127913.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.3696400165557865,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.18735553920269013,
|
|
"num_tokens": 15137588.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.3270057201385494,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.1827906534075737,
|
|
"num_tokens": 15146147.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.247193956375122,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.19691976755857468,
|
|
"num_tokens": 15156448.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.236945533752442,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.19662522971630098,
|
|
"num_tokens": 15165447.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.32114315032959,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.18877577781677246,
|
|
"num_tokens": 15175046.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.3226992130279545,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.19063031673431396,
|
|
"num_tokens": 15184142.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.261743783950806,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.1447,
|
|
"mean_token_accuracy": 0.18793658018112183,
|
|
"num_tokens": 15194101.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.241338300704956,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.1632,
|
|
"mean_token_accuracy": 0.1834757149219513,
|
|
"num_tokens": 15203083.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.291897964477539,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 5.1542,
|
|
"mean_token_accuracy": 0.19320226311683655,
|
|
"num_tokens": 15210957.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.360385274887085,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.2125,
|
|
"mean_token_accuracy": 0.18672982901334761,
|
|
"num_tokens": 15219144.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.328982257843018,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18534116446971893,
|
|
"num_tokens": 15227633.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.376241874694824,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.1915632367134094,
|
|
"num_tokens": 15235673.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.23722357749939,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.1204,
|
|
"mean_token_accuracy": 0.19583763778209687,
|
|
"num_tokens": 15245164.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.217330074310302,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.1901165008544922,
|
|
"num_tokens": 15254654.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.287178087234497,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.19153740555047988,
|
|
"num_tokens": 15264042.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.319094657897949,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18011727482080458,
|
|
"num_tokens": 15273215.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.276962995529175,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.19372446835041046,
|
|
"num_tokens": 15281441.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.338572978973389,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.18333572298288345,
|
|
"num_tokens": 15290967.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.3263952255249025,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18652485460042953,
|
|
"num_tokens": 15301332.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.389624834060669,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.1886873036623001,
|
|
"num_tokens": 15309547.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.417660903930664,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.245,
|
|
"mean_token_accuracy": 0.18211768120527266,
|
|
"num_tokens": 15318841.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.354889583587647,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.1856311857700348,
|
|
"num_tokens": 15327893.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.211272096633911,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.18985779732465743,
|
|
"num_tokens": 15336320.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.325290536880493,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.2085,
|
|
"mean_token_accuracy": 0.18871812969446183,
|
|
"num_tokens": 15346002.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.269504594802856,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.1908067524433136,
|
|
"num_tokens": 15355670.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.211881399154663,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.0686,
|
|
"mean_token_accuracy": 0.19455941915512084,
|
|
"num_tokens": 15364207.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.260488557815552,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.19283827394247055,
|
|
"num_tokens": 15373021.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.3370285987854,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19300519675016403,
|
|
"num_tokens": 15382023.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.157944536209106,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.1004,
|
|
"mean_token_accuracy": 0.19824046194553374,
|
|
"num_tokens": 15390829.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.320179271697998,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.18232600688934325,
|
|
"num_tokens": 15400415.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.257931232452393,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.18950661569833754,
|
|
"num_tokens": 15408839.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.245182609558105,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.19407836645841597,
|
|
"num_tokens": 15416989.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.273245906829834,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19343802630901336,
|
|
"num_tokens": 15425404.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.206933212280274,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 5.0341,
|
|
"mean_token_accuracy": 0.20115216672420502,
|
|
"num_tokens": 15433672.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.1540303230285645,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 5.0976,
|
|
"mean_token_accuracy": 0.1932443007826805,
|
|
"num_tokens": 15442345.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.235260820388794,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.19401500672101973,
|
|
"num_tokens": 15451891.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.343758869171142,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18704367130994798,
|
|
"num_tokens": 15462192.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.3598902225494385,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.182576522231102,
|
|
"num_tokens": 15471723.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.315639162063599,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.19733315110206603,
|
|
"num_tokens": 15479621.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.274339628219605,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.18573080152273178,
|
|
"num_tokens": 15489180.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.183819150924682,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.1898150399327278,
|
|
"num_tokens": 15498155.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.42573618888855,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.18965250998735428,
|
|
"num_tokens": 15507944.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.2981466293334964,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.1860172912478447,
|
|
"num_tokens": 15516800.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.25133867263794,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.18447698205709456,
|
|
"num_tokens": 15525824.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.3067363739013675,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 5.1804,
|
|
"mean_token_accuracy": 0.19260694533586503,
|
|
"num_tokens": 15534954.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.251150894165039,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20133766233921052,
|
|
"num_tokens": 15543439.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.237839937210083,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.19485290348529816,
|
|
"num_tokens": 15552768.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.35594367980957,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.18608065098524093,
|
|
"num_tokens": 15562193.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.347560262680053,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.19208250790834427,
|
|
"num_tokens": 15571403.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.253741312026977,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.19098494946956635,
|
|
"num_tokens": 15580477.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.242291355133057,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19199638515710832,
|
|
"num_tokens": 15590106.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.384551525115967,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.1891821801662445,
|
|
"num_tokens": 15598939.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.258433818817139,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.18928396254777907,
|
|
"num_tokens": 15607439.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.258288764953614,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.18600573688745498,
|
|
"num_tokens": 15616887.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.27916522026062,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.1435,
|
|
"mean_token_accuracy": 0.19364818334579467,
|
|
"num_tokens": 15626399.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.242170810699463,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.18425308167934418,
|
|
"num_tokens": 15635719.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.2916895866394045,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.19397978931665422,
|
|
"num_tokens": 15644504.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.242740106582642,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.19888446629047393,
|
|
"num_tokens": 15653842.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.276203393936157,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.1843859702348709,
|
|
"num_tokens": 15664235.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.311121940612793,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.19658908993005753,
|
|
"num_tokens": 15673113.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.311741638183594,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.19137491434812545,
|
|
"num_tokens": 15682609.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.231457662582398,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.18539536893367767,
|
|
"num_tokens": 15691414.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.317198991775513,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.18964322805404663,
|
|
"num_tokens": 15700690.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.28790979385376,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 5.0807,
|
|
"mean_token_accuracy": 0.19457218945026397,
|
|
"num_tokens": 15710110.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.256107902526855,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.18826364278793334,
|
|
"num_tokens": 15719182.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.258205127716065,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.1771,
|
|
"mean_token_accuracy": 0.19180652499198914,
|
|
"num_tokens": 15729045.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.24560055732727,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 5.1445,
|
|
"mean_token_accuracy": 0.19240989536046982,
|
|
"num_tokens": 15738312.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.219484615325928,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.19288695603609085,
|
|
"num_tokens": 15747852.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.335433578491211,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19398155361413955,
|
|
"num_tokens": 15757593.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.322363948822021,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.19538125097751619,
|
|
"num_tokens": 15767740.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.239190530776978,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.20100190937519075,
|
|
"num_tokens": 15776306.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.238163805007934,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.1930987611413002,
|
|
"num_tokens": 15784674.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.297255373001098,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.19163012653589248,
|
|
"num_tokens": 15794262.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.283347129821777,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.18070160895586013,
|
|
"num_tokens": 15805853.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.293683576583862,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.19223368018865586,
|
|
"num_tokens": 15815426.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.289098787307739,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19176294207572936,
|
|
"num_tokens": 15825121.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.1976173400878904,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.1959634006023407,
|
|
"num_tokens": 15834649.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.219401264190674,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.18379189521074296,
|
|
"num_tokens": 15844583.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.313754844665527,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.19071279764175414,
|
|
"num_tokens": 15853169.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.2378050804138185,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.19123534709215165,
|
|
"num_tokens": 15862139.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.376718235015869,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.1848651185631752,
|
|
"num_tokens": 15871415.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.185443925857544,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.20612120032310485,
|
|
"num_tokens": 15880581.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.2180744171142575,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.18776457458734513,
|
|
"num_tokens": 15889142.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.246136474609375,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.19433717876672746,
|
|
"num_tokens": 15898058.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.1824267387390135,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.19284000992774963,
|
|
"num_tokens": 15907196.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.234852409362793,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 5.0927,
|
|
"mean_token_accuracy": 0.1937478795647621,
|
|
"num_tokens": 15916291.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.262243700027466,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.18791772276163102,
|
|
"num_tokens": 15924846.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.194462299346924,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.1966923326253891,
|
|
"num_tokens": 15934406.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.302021646499634,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.19082928746938704,
|
|
"num_tokens": 15943481.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.361473083496094,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.18488221615552902,
|
|
"num_tokens": 15952787.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.24317774772644,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.1775,
|
|
"mean_token_accuracy": 0.19052420258522035,
|
|
"num_tokens": 15962295.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.322543287277222,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.19563299417495728,
|
|
"num_tokens": 15971367.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.19252119064331,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19953658282756806,
|
|
"num_tokens": 15981535.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.28391318321228,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.18641686141490937,
|
|
"num_tokens": 15991067.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.215488290786743,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.1963928982615471,
|
|
"num_tokens": 15999310.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.211255645751953,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.19351856261491776,
|
|
"num_tokens": 16008574.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.2873673915863035,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.1901836633682251,
|
|
"num_tokens": 16017208.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.331624221801758,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.18591621071100234,
|
|
"num_tokens": 16027009.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.237117099761963,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.20092488080263138,
|
|
"num_tokens": 16035019.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.221333694458008,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 5.0904,
|
|
"mean_token_accuracy": 0.198664990067482,
|
|
"num_tokens": 16044373.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.257413673400879,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.19224874079227447,
|
|
"num_tokens": 16052888.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.236996507644653,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.1905507206916809,
|
|
"num_tokens": 16062137.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.299497938156128,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.18409110754728317,
|
|
"num_tokens": 16072755.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.306175708770752,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.1622,
|
|
"mean_token_accuracy": 0.1882558822631836,
|
|
"num_tokens": 16081069.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.331820440292359,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.1941478058695793,
|
|
"num_tokens": 16089938.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.21022253036499,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19628458470106125,
|
|
"num_tokens": 16099395.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.175596570968628,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.20078281313180923,
|
|
"num_tokens": 16108196.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.236020612716675,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.19143548905849456,
|
|
"num_tokens": 16118059.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.30237340927124,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.2095,
|
|
"mean_token_accuracy": 0.18966662883758545,
|
|
"num_tokens": 16126981.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.2454451560974125,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 5.0849,
|
|
"mean_token_accuracy": 0.19678558707237243,
|
|
"num_tokens": 16136164.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.283247566223144,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.18060089349746705,
|
|
"num_tokens": 16145739.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.313655376434326,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.18898289054632186,
|
|
"num_tokens": 16155092.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.204944849014282,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.1982123538851738,
|
|
"num_tokens": 16162994.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.27227931022644,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.1113,
|
|
"mean_token_accuracy": 0.19368191957473754,
|
|
"num_tokens": 16171286.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.29538369178772,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.1902650013566017,
|
|
"num_tokens": 16180459.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.280352401733398,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.1910347819328308,
|
|
"num_tokens": 16190103.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.285508012771606,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.19194310158491135,
|
|
"num_tokens": 16199499.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.222455358505249,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.1873357117176056,
|
|
"num_tokens": 16209589.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.171773052215576,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.19819573312997818,
|
|
"num_tokens": 16218499.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.20752968788147,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.1979145109653473,
|
|
"num_tokens": 16227183.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.244198894500732,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.19220415204763414,
|
|
"num_tokens": 16236573.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.285165500640869,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.19057226926088333,
|
|
"num_tokens": 16246399.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.216931533813477,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.18463050872087478,
|
|
"num_tokens": 16254964.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.303437376022339,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.2175,
|
|
"mean_token_accuracy": 0.19016121625900267,
|
|
"num_tokens": 16263579.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.350651025772095,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.1829417511820793,
|
|
"num_tokens": 16273000.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.324179792404175,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.19244228303432465,
|
|
"num_tokens": 16282582.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.201522397994995,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.19175723642110826,
|
|
"num_tokens": 16291153.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.203221988677979,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19804461747407914,
|
|
"num_tokens": 16300527.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.2294846534729,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 5.0197,
|
|
"mean_token_accuracy": 0.2092771887779236,
|
|
"num_tokens": 16309111.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.326550579071045,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18758321106433867,
|
|
"num_tokens": 16318409.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.227953815460205,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.19959003776311873,
|
|
"num_tokens": 16327950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.255214786529541,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.1865760087966919,
|
|
"num_tokens": 16336776.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.3541590690612795,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.2186,
|
|
"mean_token_accuracy": 0.18943388164043426,
|
|
"num_tokens": 16346206.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.288184404373169,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.194120354950428,
|
|
"num_tokens": 16355163.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.276929664611816,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18412055671215058,
|
|
"num_tokens": 16364028.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.255345296859741,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.19027332961559296,
|
|
"num_tokens": 16373669.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.321865844726562,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.1864067181944847,
|
|
"num_tokens": 16383246.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.319370985031128,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.23,
|
|
"mean_token_accuracy": 0.18542566746473313,
|
|
"num_tokens": 16393589.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.220500659942627,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.18315428346395493,
|
|
"num_tokens": 16402734.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.3359418392181395,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.1865530490875244,
|
|
"num_tokens": 16412317.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.311035108566284,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.1744,
|
|
"mean_token_accuracy": 0.1900661453604698,
|
|
"num_tokens": 16421472.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.20952353477478,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 5.0832,
|
|
"mean_token_accuracy": 0.18919856995344161,
|
|
"num_tokens": 16430694.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.282927417755127,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 5.2792,
|
|
"mean_token_accuracy": 0.181670643389225,
|
|
"num_tokens": 16440250.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.255068063735962,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.19686186760663987,
|
|
"num_tokens": 16449294.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.463743400573731,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.17092504799365998,
|
|
"num_tokens": 16459614.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.351200723648072,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.1823495149612427,
|
|
"num_tokens": 16469175.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.213696718215942,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.19510286897420884,
|
|
"num_tokens": 16477818.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.314765119552613,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.1890265390276909,
|
|
"num_tokens": 16487807.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.189211702346801,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.2005615085363388,
|
|
"num_tokens": 16497924.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.30037260055542,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.1715,
|
|
"mean_token_accuracy": 0.1895117536187172,
|
|
"num_tokens": 16508069.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.356766653060913,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.19483387917280198,
|
|
"num_tokens": 16517226.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.25833420753479,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.17950759083032608,
|
|
"num_tokens": 16526997.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.2498777389526365,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.19318631738424302,
|
|
"num_tokens": 16536772.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.23926477432251,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.19715453833341598,
|
|
"num_tokens": 16544901.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.190441751480103,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.106,
|
|
"mean_token_accuracy": 0.19497038722038268,
|
|
"num_tokens": 16553628.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 5.04891709866248,
|
|
"eval_loss": 5.1309638023376465,
|
|
"eval_mean_token_accuracy": 0.20150274327594933,
|
|
"eval_num_tokens": 16553628.0,
|
|
"eval_runtime": 27.7068,
|
|
"eval_samples_per_second": 1362.948,
|
|
"eval_steps_per_second": 170.391,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.284650564193726,
|
|
"epoch": 0.7521717340461076,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004949720091193704,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.19129439890384675,
|
|
"num_tokens": 16561619.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.236381864547729,
|
|
"epoch": 0.7525893752088206,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000494965748847863,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.1949136033654213,
|
|
"num_tokens": 16571316.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.305360794067383,
|
|
"epoch": 0.7530070163715336,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004949594847255905,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.1870893120765686,
|
|
"num_tokens": 16582014.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.26864538192749,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004949532167526625,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.1951904073357582,
|
|
"num_tokens": 16590179.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.282690906524659,
|
|
"epoch": 0.7538422986969596,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004949469449291886,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.2060410797595978,
|
|
"num_tokens": 16598732.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.315931081771851,
|
|
"epoch": 0.7542599398596725,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004949406692552787,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.18190824687480928,
|
|
"num_tokens": 16608844.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.31307282447815,
|
|
"epoch": 0.7546775810223856,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004949343897310426,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.19130521267652512,
|
|
"num_tokens": 16618969.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.309460687637329,
|
|
"epoch": 0.7550952221850986,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004949281063565904,
|
|
"loss": 5.2181,
|
|
"mean_token_accuracy": 0.18992851078510284,
|
|
"num_tokens": 16629081.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.191410732269287,
|
|
"epoch": 0.7555128633478115,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004949218191320319,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20415098816156388,
|
|
"num_tokens": 16637588.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.301031255722046,
|
|
"epoch": 0.7559305045105246,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004949155280574772,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.18461380451917647,
|
|
"num_tokens": 16647763.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.196663284301758,
|
|
"epoch": 0.7563481456732376,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004949092331330365,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.19086116552352905,
|
|
"num_tokens": 16657208.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.267312288284302,
|
|
"epoch": 0.7567657868359505,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00049490293435882,
|
|
"loss": 5.0479,
|
|
"mean_token_accuracy": 0.19404009878635406,
|
|
"num_tokens": 16666375.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.252836084365844,
|
|
"epoch": 0.7571834279986636,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.20120500922203063,
|
|
"num_tokens": 16674847.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.229509449005127,
|
|
"epoch": 0.7576010691613766,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004948903252615006,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.18377767950296403,
|
|
"num_tokens": 16684828.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.327714920043945,
|
|
"epoch": 0.7580187103240895,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004948840149386184,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.18056150674819946,
|
|
"num_tokens": 16694151.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.368087100982666,
|
|
"epoch": 0.7584363514868026,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494877700766402,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.18970449417829513,
|
|
"num_tokens": 16703584.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.225856018066406,
|
|
"epoch": 0.7588539926495156,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004948713827449616,
|
|
"loss": 5.0945,
|
|
"mean_token_accuracy": 0.19073991924524308,
|
|
"num_tokens": 16712593.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.2489885807037355,
|
|
"epoch": 0.7592716338122285,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004948650608744081,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.19166267067193984,
|
|
"num_tokens": 16721848.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.303568649291992,
|
|
"epoch": 0.7596892749749415,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000494858735154852,
|
|
"loss": 5.1778,
|
|
"mean_token_accuracy": 0.19576231390237808,
|
|
"num_tokens": 16730465.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.268704795837403,
|
|
"epoch": 0.7601069161376546,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004948524055864041,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.19145216047763824,
|
|
"num_tokens": 16739518.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.322190666198731,
|
|
"epoch": 0.7605245573003675,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004948460721691752,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18203989714384078,
|
|
"num_tokens": 16749332.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.2628867626190186,
|
|
"epoch": 0.7609421984630805,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004948397349032762,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.20595274567604066,
|
|
"num_tokens": 16757621.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.218843126296997,
|
|
"epoch": 0.7613598396257936,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000494833393788818,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.19500521719455718,
|
|
"num_tokens": 16766382.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.193441390991211,
|
|
"epoch": 0.7617774807885065,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004948270488259117,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19029657989740373,
|
|
"num_tokens": 16774962.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.184526538848877,
|
|
"epoch": 0.7621951219512195,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004948207000146682,
|
|
"loss": 5.0885,
|
|
"mean_token_accuracy": 0.19253478348255157,
|
|
"num_tokens": 16784246.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.260955905914306,
|
|
"epoch": 0.7626127631139326,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004948143473551989,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.1836049288511276,
|
|
"num_tokens": 16793396.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.30218358039856,
|
|
"epoch": 0.7630304042766455,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004948079908476147,
|
|
"loss": 5.1486,
|
|
"mean_token_accuracy": 0.192588971555233,
|
|
"num_tokens": 16801837.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.331125211715698,
|
|
"epoch": 0.7634480454393585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004948016304920271,
|
|
"loss": 5.183,
|
|
"mean_token_accuracy": 0.19275147914886476,
|
|
"num_tokens": 16810332.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.260197448730469,
|
|
"epoch": 0.7638656866020715,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947952662885473,
|
|
"loss": 5.1359,
|
|
"mean_token_accuracy": 0.19549433141946793,
|
|
"num_tokens": 16820278.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.162685585021973,
|
|
"epoch": 0.7642833277647845,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494788898237287,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.19627458304166795,
|
|
"num_tokens": 16828907.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.194856643676758,
|
|
"epoch": 0.7647009689274975,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004947825263383573,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.18765236139297486,
|
|
"num_tokens": 16838579.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.221455717086792,
|
|
"epoch": 0.7651186100902105,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049477615059187,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.19863450527191162,
|
|
"num_tokens": 16847143.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.3156860828399655,
|
|
"epoch": 0.7655362512529235,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004947697709979367,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.19299326092004776,
|
|
"num_tokens": 16855989.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.3172670841217045,
|
|
"epoch": 0.7659538924156365,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004947633875566688,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.19252799600362777,
|
|
"num_tokens": 16864701.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.337530899047851,
|
|
"epoch": 0.7663715335783495,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004947570002681785,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.1833501622080803,
|
|
"num_tokens": 16875032.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.299377059936523,
|
|
"epoch": 0.7667891747410625,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004947506091325772,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.187994647026062,
|
|
"num_tokens": 16884590.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.307699918746948,
|
|
"epoch": 0.7672068159037755,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004947442141499771,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.18981925994157792,
|
|
"num_tokens": 16894257.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.297932529449463,
|
|
"epoch": 0.7676244570664885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004947378153204899,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.19340216666460036,
|
|
"num_tokens": 16904049.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.213099145889283,
|
|
"epoch": 0.7680420982292014,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004947314126442279,
|
|
"loss": 5.0921,
|
|
"mean_token_accuracy": 0.192905293405056,
|
|
"num_tokens": 16913147.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.2790021896362305,
|
|
"epoch": 0.7684597393919145,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494725006121303,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.18875229060649873,
|
|
"num_tokens": 16922142.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.269748210906982,
|
|
"epoch": 0.7688773805546275,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004947185957518273,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.19588406383991241,
|
|
"num_tokens": 16931069.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.246332454681396,
|
|
"epoch": 0.7692950217173404,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004947121815359133,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19074745178222657,
|
|
"num_tokens": 16940172.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.385737133026123,
|
|
"epoch": 0.7697126628800535,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004947057634736729,
|
|
"loss": 5.2617,
|
|
"mean_token_accuracy": 0.18613625764846803,
|
|
"num_tokens": 16951097.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.290096187591553,
|
|
"epoch": 0.7701303040427665,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004946993415652186,
|
|
"loss": 5.1571,
|
|
"mean_token_accuracy": 0.19270050078630446,
|
|
"num_tokens": 16960764.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.209099912643433,
|
|
"epoch": 0.7705479452054794,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000494692915810663,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.1923610597848892,
|
|
"num_tokens": 16969842.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.340341472625733,
|
|
"epoch": 0.7709655863681925,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004946864862101185,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.19927529096603394,
|
|
"num_tokens": 16979070.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.120919322967529,
|
|
"epoch": 0.7713832275309055,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004946800527636975,
|
|
"loss": 5.0648,
|
|
"mean_token_accuracy": 0.19595357328653334,
|
|
"num_tokens": 16988126.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.140116453170776,
|
|
"epoch": 0.7718008686936184,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004946736154715129,
|
|
"loss": 5.0797,
|
|
"mean_token_accuracy": 0.19695620387792587,
|
|
"num_tokens": 16997085.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.2858179092407225,
|
|
"epoch": 0.7722185098563314,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004946671743336771,
|
|
"loss": 5.1579,
|
|
"mean_token_accuracy": 0.1884255200624466,
|
|
"num_tokens": 17005678.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.364119005203247,
|
|
"epoch": 0.7726361510190445,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004946607293503031,
|
|
"loss": 5.0636,
|
|
"mean_token_accuracy": 0.19261190444231033,
|
|
"num_tokens": 17015081.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.245525598526001,
|
|
"epoch": 0.7730537921817574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004946542805215036,
|
|
"loss": 5.1416,
|
|
"mean_token_accuracy": 0.19777034372091293,
|
|
"num_tokens": 17024036.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.278521966934204,
|
|
"epoch": 0.7734714333444704,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004946478278473914,
|
|
"loss": 5.1032,
|
|
"mean_token_accuracy": 0.19373207092285155,
|
|
"num_tokens": 17032120.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.275355339050293,
|
|
"epoch": 0.7738890745071835,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004946413713280797,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.1938307449221611,
|
|
"num_tokens": 17041487.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.2276403427124025,
|
|
"epoch": 0.7743067156698964,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004946349109636814,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.18773230016231537,
|
|
"num_tokens": 17050793.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.275458908081054,
|
|
"epoch": 0.7747243568326094,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004946284467543096,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20014280527830125,
|
|
"num_tokens": 17059536.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.2580150127410885,
|
|
"epoch": 0.7751419979953225,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004946219787000776,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.19805282205343247,
|
|
"num_tokens": 17069075.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.234522724151612,
|
|
"epoch": 0.7755596391580354,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004946155068010984,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.19203932732343673,
|
|
"num_tokens": 17079020.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.281824588775635,
|
|
"epoch": 0.7759772803207484,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004946090310574854,
|
|
"loss": 5.1468,
|
|
"mean_token_accuracy": 0.1919183537364006,
|
|
"num_tokens": 17087905.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.250629615783692,
|
|
"epoch": 0.7763949214834615,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004946025514693519,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.19383215606212617,
|
|
"num_tokens": 17097932.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.253558349609375,
|
|
"epoch": 0.7768125626461744,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945960680368115,
|
|
"loss": 5.1104,
|
|
"mean_token_accuracy": 0.19456967562437058,
|
|
"num_tokens": 17107125.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.311372470855713,
|
|
"epoch": 0.7772302038088874,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004945895807599775,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.18670535385608672,
|
|
"num_tokens": 17116575.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.245980215072632,
|
|
"epoch": 0.7776478449716004,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004945830896389636,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.20212937295436859,
|
|
"num_tokens": 17125422.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.1561438083648685,
|
|
"epoch": 0.7780654861343134,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004945765946738835,
|
|
"loss": 5.0469,
|
|
"mean_token_accuracy": 0.19811525493860244,
|
|
"num_tokens": 17134323.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.170308065414429,
|
|
"epoch": 0.7784831272970264,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004945700958648507,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.20341728180646895,
|
|
"num_tokens": 17143179.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.244274997711182,
|
|
"epoch": 0.7789007684597394,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000494563593211979,
|
|
"loss": 5.0887,
|
|
"mean_token_accuracy": 0.19375640600919725,
|
|
"num_tokens": 17152498.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.239305543899536,
|
|
"epoch": 0.7793184096224524,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004945570867153826,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.18927657902240752,
|
|
"num_tokens": 17161689.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.273555517196655,
|
|
"epoch": 0.7797360507851654,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004945505763751749,
|
|
"loss": 5.1441,
|
|
"mean_token_accuracy": 0.1919786214828491,
|
|
"num_tokens": 17170291.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.317656373977661,
|
|
"epoch": 0.7801536919478784,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004945440621914702,
|
|
"loss": 5.1671,
|
|
"mean_token_accuracy": 0.19348419308662415,
|
|
"num_tokens": 17179712.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.2609655380249025,
|
|
"epoch": 0.7805713331105913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945375441643823,
|
|
"loss": 5.174,
|
|
"mean_token_accuracy": 0.192328542470932,
|
|
"num_tokens": 17188224.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.299058151245117,
|
|
"epoch": 0.7809889742733044,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004945310222940254,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19506229758262633,
|
|
"num_tokens": 17197868.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.241016960144043,
|
|
"epoch": 0.7814066154360174,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004945244965805138,
|
|
"loss": 5.1195,
|
|
"mean_token_accuracy": 0.1913663700222969,
|
|
"num_tokens": 17207576.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.218179702758789,
|
|
"epoch": 0.7818242565987303,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004945179670239616,
|
|
"loss": 5.1256,
|
|
"mean_token_accuracy": 0.18980579525232316,
|
|
"num_tokens": 17217508.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.370937633514404,
|
|
"epoch": 0.7822418977614434,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004945114336244832,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.18452499210834503,
|
|
"num_tokens": 17227890.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.333818960189819,
|
|
"epoch": 0.7826595389241564,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000494504896382193,
|
|
"loss": 5.1465,
|
|
"mean_token_accuracy": 0.19608381241559983,
|
|
"num_tokens": 17237038.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.267381048202514,
|
|
"epoch": 0.7830771800868693,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004944983552972053,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.18515494018793105,
|
|
"num_tokens": 17247653.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.293831014633179,
|
|
"epoch": 0.7834948212495824,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004944918103696347,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.18410503566265107,
|
|
"num_tokens": 17257183.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.312693881988525,
|
|
"epoch": 0.7839124624122954,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004944852615995956,
|
|
"loss": 5.1919,
|
|
"mean_token_accuracy": 0.18909610509872438,
|
|
"num_tokens": 17266315.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.318830728530884,
|
|
"epoch": 0.7843301035750083,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000494478708987203,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.1851031720638275,
|
|
"num_tokens": 17275829.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.4169337272644045,
|
|
"epoch": 0.7847477447377214,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004944721525325713,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.17963435500860214,
|
|
"num_tokens": 17285986.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.2347198009490965,
|
|
"epoch": 0.7851653859004344,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004944655922358154,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.1993911534547806,
|
|
"num_tokens": 17294314.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.12729434967041,
|
|
"epoch": 0.7855830270631473,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004944590280970503,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.1968993991613388,
|
|
"num_tokens": 17303437.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.2858038425445555,
|
|
"epoch": 0.7860006682258603,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004944524601163905,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.18448719531297683,
|
|
"num_tokens": 17313230.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.278919792175293,
|
|
"epoch": 0.7864183093885734,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004944458882939513,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18486365526914597,
|
|
"num_tokens": 17323468.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.130036211013794,
|
|
"epoch": 0.7868359505512863,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004944393126298478,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.20025767236948014,
|
|
"num_tokens": 17332481.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.308260250091553,
|
|
"epoch": 0.7872535917139993,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000494432733124195,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.18895395398139953,
|
|
"num_tokens": 17341550.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.273244428634643,
|
|
"epoch": 0.7876712328767124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000494426149777108,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.1983897492289543,
|
|
"num_tokens": 17350404.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.2244361400604244,
|
|
"epoch": 0.7880888740394253,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000494419562588702,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.19000243693590163,
|
|
"num_tokens": 17360198.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.231658792495727,
|
|
"epoch": 0.7885065152021383,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004944129715590927,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.19901785999536514,
|
|
"num_tokens": 17369681.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.186979579925537,
|
|
"epoch": 0.7889241563648514,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000494406376688395,
|
|
"loss": 5.0852,
|
|
"mean_token_accuracy": 0.19972660690546035,
|
|
"num_tokens": 17378695.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.314598655700683,
|
|
"epoch": 0.7893417975275643,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004943997779767248,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.18282943814992905,
|
|
"num_tokens": 17388161.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.319035291671753,
|
|
"epoch": 0.7897594386902773,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004943931754241972,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.18679031282663344,
|
|
"num_tokens": 17397082.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.203807306289673,
|
|
"epoch": 0.7901770798529903,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000494386569030928,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.19658589959144593,
|
|
"num_tokens": 17405842.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.252545881271362,
|
|
"epoch": 0.7905947210157033,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004943799587970328,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.1925847500562668,
|
|
"num_tokens": 17414639.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.266719675064087,
|
|
"epoch": 0.7910123621784163,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004943733447226275,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.19542211592197417,
|
|
"num_tokens": 17423923.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.138341331481934,
|
|
"epoch": 0.7914300033411293,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004943667268078277,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20514626950025558,
|
|
"num_tokens": 17432309.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.2984966278076175,
|
|
"epoch": 0.7918476445038423,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004943601050527493,
|
|
"loss": 5.2009,
|
|
"mean_token_accuracy": 0.1854607120156288,
|
|
"num_tokens": 17441728.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.343739032745361,
|
|
"epoch": 0.7922652856665553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004943534794575081,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.18469537794589996,
|
|
"num_tokens": 17451168.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.330528974533081,
|
|
"epoch": 0.7926829268292683,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004943468500222203,
|
|
"loss": 5.2315,
|
|
"mean_token_accuracy": 0.19061953872442244,
|
|
"num_tokens": 17461179.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.266789150238037,
|
|
"epoch": 0.7931005679919813,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004943402167470019,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.1966783419251442,
|
|
"num_tokens": 17469710.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.241172504425049,
|
|
"epoch": 0.7935182091546943,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000494333579631969,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19097824692726134,
|
|
"num_tokens": 17479482.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.0443164825439455,
|
|
"epoch": 0.7939358503174073,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004943269386772376,
|
|
"loss": 4.9558,
|
|
"mean_token_accuracy": 0.20915199518203736,
|
|
"num_tokens": 17488458.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.306435489654541,
|
|
"epoch": 0.7943534914801202,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004943202938829243,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.1944829910993576,
|
|
"num_tokens": 17497817.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.214391088485717,
|
|
"epoch": 0.7947711326428333,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004943136452491452,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.19421486407518387,
|
|
"num_tokens": 17506020.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.237166023254394,
|
|
"epoch": 0.7951887738055463,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004943069927760168,
|
|
"loss": 5.1431,
|
|
"mean_token_accuracy": 0.1870472624897957,
|
|
"num_tokens": 17515113.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.283129596710205,
|
|
"epoch": 0.7956064149682592,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004943003364636554,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.198609422147274,
|
|
"num_tokens": 17523473.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.283037567138672,
|
|
"epoch": 0.7960240561309723,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004942936763121777,
|
|
"loss": 5.1631,
|
|
"mean_token_accuracy": 0.18911215513944626,
|
|
"num_tokens": 17532985.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.1913494110107425,
|
|
"epoch": 0.7964416972936853,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004942870123217002,
|
|
"loss": 5.1167,
|
|
"mean_token_accuracy": 0.18947843164205552,
|
|
"num_tokens": 17541859.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.215520143508911,
|
|
"epoch": 0.7968593384563982,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004942803444923398,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.1978566288948059,
|
|
"num_tokens": 17550263.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.3430342197418215,
|
|
"epoch": 0.7972769796191113,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004942736728242127,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.19369956552982331,
|
|
"num_tokens": 17560028.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.302721118927002,
|
|
"epoch": 0.7976946207818243,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004942669973174363,
|
|
"loss": 5.1114,
|
|
"mean_token_accuracy": 0.1931803658604622,
|
|
"num_tokens": 17569082.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.2174601554870605,
|
|
"epoch": 0.7981122619445372,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000494260317972127,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19430044442415237,
|
|
"num_tokens": 17577589.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.087086725234985,
|
|
"epoch": 0.7985299031072502,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004942536347884019,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.2063223659992218,
|
|
"num_tokens": 17586066.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.1341081142425535,
|
|
"epoch": 0.7989475442699633,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004942469477663782,
|
|
"loss": 4.9554,
|
|
"mean_token_accuracy": 0.20437541007995605,
|
|
"num_tokens": 17594328.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.222323274612426,
|
|
"epoch": 0.7993651854326762,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004942402569061726,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.19120361506938935,
|
|
"num_tokens": 17603719.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.381272840499878,
|
|
"epoch": 0.7997828265953892,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004942335622079025,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.19148974865674973,
|
|
"num_tokens": 17613306.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.215620613098144,
|
|
"epoch": 0.8002004677581023,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004942268636716848,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.19395049959421157,
|
|
"num_tokens": 17622756.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.196308517456055,
|
|
"epoch": 0.8006181089208152,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004942201612976372,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.20300968289375304,
|
|
"num_tokens": 17632157.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.196787595748901,
|
|
"epoch": 0.8010357500835282,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004942134550858767,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.2019111067056656,
|
|
"num_tokens": 17641706.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.215884780883789,
|
|
"epoch": 0.8014533912462413,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004942067450365208,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.18573255836963654,
|
|
"num_tokens": 17651572.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.258349895477295,
|
|
"epoch": 0.8018710324089542,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004942000311496871,
|
|
"loss": 5.1543,
|
|
"mean_token_accuracy": 0.19262522161006929,
|
|
"num_tokens": 17661354.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.297380208969116,
|
|
"epoch": 0.8022886735716672,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941933134254928,
|
|
"loss": 5.1173,
|
|
"mean_token_accuracy": 0.1944006398320198,
|
|
"num_tokens": 17670482.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.255826997756958,
|
|
"epoch": 0.8027063147343803,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004941865918640559,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.18901994377374648,
|
|
"num_tokens": 17679429.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.297385931015015,
|
|
"epoch": 0.8031239558970932,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004941798664654937,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18525495380163193,
|
|
"num_tokens": 17688620.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.261661958694458,
|
|
"epoch": 0.8035415970598062,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004941731372299241,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.18994914144277572,
|
|
"num_tokens": 17698493.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.191858768463135,
|
|
"epoch": 0.8039592382225192,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 5.0444,
|
|
"mean_token_accuracy": 0.19941396862268448,
|
|
"num_tokens": 17707408.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.220510578155517,
|
|
"epoch": 0.8043768793852322,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004941596672482343,
|
|
"loss": 5.1254,
|
|
"mean_token_accuracy": 0.19712237119674683,
|
|
"num_tokens": 17716448.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.273178911209106,
|
|
"epoch": 0.8047945205479452,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004941529265023498,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.19830915331840515,
|
|
"num_tokens": 17725287.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.3732161045074465,
|
|
"epoch": 0.8052121617106582,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004941461819199293,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.19137406647205352,
|
|
"num_tokens": 17734674.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.3338597297668455,
|
|
"epoch": 0.8056298028733712,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004941394335010912,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.1871379315853119,
|
|
"num_tokens": 17743589.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.242267227172851,
|
|
"epoch": 0.8060474440360842,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004941326812459535,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.19810663312673568,
|
|
"num_tokens": 17753210.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.324686050415039,
|
|
"epoch": 0.8064650851987972,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941259251546346,
|
|
"loss": 5.0993,
|
|
"mean_token_accuracy": 0.19625033736228942,
|
|
"num_tokens": 17762074.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.360092878341675,
|
|
"epoch": 0.8068827263615101,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004941191652272526,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.18395915031433105,
|
|
"num_tokens": 17771263.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.268192386627197,
|
|
"epoch": 0.8073003675242232,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004941124014639258,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19523436427116395,
|
|
"num_tokens": 17781351.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.219300127029419,
|
|
"epoch": 0.8077180086869362,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004941056338647726,
|
|
"loss": 5.0486,
|
|
"mean_token_accuracy": 0.2020439699292183,
|
|
"num_tokens": 17790343.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.21505708694458,
|
|
"epoch": 0.8081356498496491,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004940988624299116,
|
|
"loss": 5.1281,
|
|
"mean_token_accuracy": 0.1876239076256752,
|
|
"num_tokens": 17799338.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.159978246688842,
|
|
"epoch": 0.8085532910123622,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004940920871594613,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.19193944334983826,
|
|
"num_tokens": 17808852.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.303667068481445,
|
|
"epoch": 0.8089709321750752,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004940853080535403,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.1877689927816391,
|
|
"num_tokens": 17817654.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.266427040100098,
|
|
"epoch": 0.8093885733377881,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940785251122673,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.1913834407925606,
|
|
"num_tokens": 17826640.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.2331428050994875,
|
|
"epoch": 0.8098062145005012,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004940717383357608,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.19399402737617494,
|
|
"num_tokens": 17835493.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.15072922706604,
|
|
"epoch": 0.8102238556632142,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004940649477241401,
|
|
"loss": 5.1065,
|
|
"mean_token_accuracy": 0.19196264296770096,
|
|
"num_tokens": 17845375.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.286759853363037,
|
|
"epoch": 0.8106414968259271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004940581532775237,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20250680446624755,
|
|
"num_tokens": 17854473.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.361585426330566,
|
|
"epoch": 0.8110591379886402,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004940513549960306,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.18932442665100097,
|
|
"num_tokens": 17864242.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.264509153366089,
|
|
"epoch": 0.8114767791513532,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004940445528797798,
|
|
"loss": 5.1532,
|
|
"mean_token_accuracy": 0.1892949566245079,
|
|
"num_tokens": 17873292.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.189016437530517,
|
|
"epoch": 0.8118944203140661,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004940377469288906,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.1957487627863884,
|
|
"num_tokens": 17883601.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.241117000579834,
|
|
"epoch": 0.8123120614767791,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004940309371434819,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.1988212063908577,
|
|
"num_tokens": 17892241.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.30053129196167,
|
|
"epoch": 0.8127297026394922,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004940241235236731,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.1967609107494354,
|
|
"num_tokens": 17901236.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.297317600250244,
|
|
"epoch": 0.8131473438022051,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004940173060695833,
|
|
"loss": 5.1636,
|
|
"mean_token_accuracy": 0.18704858422279358,
|
|
"num_tokens": 17909871.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.109527587890625,
|
|
"epoch": 0.8135649849649181,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004940104847813319,
|
|
"loss": 4.9666,
|
|
"mean_token_accuracy": 0.2048913300037384,
|
|
"num_tokens": 17918158.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.180254507064819,
|
|
"epoch": 0.8139826261276312,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004940036596590384,
|
|
"loss": 5.0734,
|
|
"mean_token_accuracy": 0.1968464434146881,
|
|
"num_tokens": 17927778.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.2881190299987795,
|
|
"epoch": 0.8144002672903441,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004939968307028221,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.19233490526676178,
|
|
"num_tokens": 17936859.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.2676292896270756,
|
|
"epoch": 0.8148179084530571,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004939899979128028,
|
|
"loss": 5.1476,
|
|
"mean_token_accuracy": 0.18997602611780168,
|
|
"num_tokens": 17946477.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.239906692504883,
|
|
"epoch": 0.8152355496157702,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004939831612890999,
|
|
"loss": 5.0964,
|
|
"mean_token_accuracy": 0.1961331143975258,
|
|
"num_tokens": 17956362.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.228900671005249,
|
|
"epoch": 0.8156531907784831,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939763208318332,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.1941460058093071,
|
|
"num_tokens": 17965837.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.312269496917724,
|
|
"epoch": 0.8160708319411961,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004939694765411225,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.18751802444458007,
|
|
"num_tokens": 17974750.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.2949858665466305,
|
|
"epoch": 0.8164884731039092,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004939626284170874,
|
|
"loss": 5.2531,
|
|
"mean_token_accuracy": 0.18865209221839904,
|
|
"num_tokens": 17985106.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.226165246963501,
|
|
"epoch": 0.8169061142666221,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493955776459848,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.19260022640228272,
|
|
"num_tokens": 17995073.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.304164123535156,
|
|
"epoch": 0.8173237554293351,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004939489206695241,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.197147735953331,
|
|
"num_tokens": 18004112.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.28415002822876,
|
|
"epoch": 0.8177413965920481,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004939420610462359,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.1896842449903488,
|
|
"num_tokens": 18013344.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.259722900390625,
|
|
"epoch": 0.8181590377547611,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004939351975901034,
|
|
"loss": 5.0822,
|
|
"mean_token_accuracy": 0.19383978247642517,
|
|
"num_tokens": 18022938.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.213902473449707,
|
|
"epoch": 0.8185766789174741,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004939283303012467,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.19638063609600068,
|
|
"num_tokens": 18031507.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.205690526962281,
|
|
"epoch": 0.8189943200801871,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000493921459179786,
|
|
"loss": 5.1122,
|
|
"mean_token_accuracy": 0.1913120687007904,
|
|
"num_tokens": 18039553.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.221726894378662,
|
|
"epoch": 0.8194119612429,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004939145842258418,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.1963190972805023,
|
|
"num_tokens": 18048550.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.296284818649292,
|
|
"epoch": 0.8198296024056131,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004939077054395341,
|
|
"loss": 5.0962,
|
|
"mean_token_accuracy": 0.1979181319475174,
|
|
"num_tokens": 18057298.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.162118244171142,
|
|
"epoch": 0.8202472435683261,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004939008228209836,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.1951318070292473,
|
|
"num_tokens": 18066740.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.175771713256836,
|
|
"epoch": 0.820664884731039,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004938939363703106,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.19318842142820358,
|
|
"num_tokens": 18076663.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.318018817901612,
|
|
"epoch": 0.8210825258937521,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004938870460876359,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.18922351002693177,
|
|
"num_tokens": 18085037.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.384563207626343,
|
|
"epoch": 0.8215001670564651,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049388015197308,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.18890699744224548,
|
|
"num_tokens": 18094636.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.223188400268555,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004938732540267635,
|
|
"loss": 5.1283,
|
|
"mean_token_accuracy": 0.18941520452499389,
|
|
"num_tokens": 18103083.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.216627311706543,
|
|
"epoch": 0.8223354493818911,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004938663522488072,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.1926014930009842,
|
|
"num_tokens": 18112108.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.386596632003784,
|
|
"epoch": 0.8227530905446041,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004938594466393321,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.19452123641967772,
|
|
"num_tokens": 18121001.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.224433565139771,
|
|
"epoch": 0.823170731707317,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004938525371984588,
|
|
"loss": 5.0303,
|
|
"mean_token_accuracy": 0.20452803373336792,
|
|
"num_tokens": 18129309.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.246949291229248,
|
|
"epoch": 0.8235883728700301,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004938456239263085,
|
|
"loss": 5.2203,
|
|
"mean_token_accuracy": 0.18910325765609742,
|
|
"num_tokens": 18138373.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.308945941925049,
|
|
"epoch": 0.8240060140327431,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004938387068230021,
|
|
"loss": 5.1647,
|
|
"mean_token_accuracy": 0.18817575573921203,
|
|
"num_tokens": 18148038.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.27157506942749,
|
|
"epoch": 0.824423655195456,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004938317858886606,
|
|
"loss": 5.0829,
|
|
"mean_token_accuracy": 0.19335709512233734,
|
|
"num_tokens": 18158132.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.231343030929565,
|
|
"epoch": 0.824841296358169,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004938248611234055,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.19111096411943435,
|
|
"num_tokens": 18167276.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.206383562088012,
|
|
"epoch": 0.8252589375208821,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004938179325273577,
|
|
"loss": 5.1495,
|
|
"mean_token_accuracy": 0.19772316813468932,
|
|
"num_tokens": 18177538.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.3209789276123045,
|
|
"epoch": 0.825676578683595,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004938110001006385,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.19052454978227615,
|
|
"num_tokens": 18187067.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.2642628192901615,
|
|
"epoch": 0.826094219846308,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004938040638433694,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.18694647550582885,
|
|
"num_tokens": 18196710.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.212479782104492,
|
|
"epoch": 0.8265118610090211,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004937971237556719,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.19053595811128615,
|
|
"num_tokens": 18205789.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.1881612777709964,
|
|
"epoch": 0.826929502171734,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004937901798376672,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.19853330105543138,
|
|
"num_tokens": 18214633.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.198566198348999,
|
|
"epoch": 0.827347143334447,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.1407,
|
|
"mean_token_accuracy": 0.19435544610023497,
|
|
"num_tokens": 18225019.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.203691387176514,
|
|
"epoch": 0.8277647844971601,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004937762805112233,
|
|
"loss": 5.0842,
|
|
"mean_token_accuracy": 0.20435549169778824,
|
|
"num_tokens": 18234610.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.222125911712647,
|
|
"epoch": 0.828182425659873,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004937693251030273,
|
|
"loss": 5.1017,
|
|
"mean_token_accuracy": 0.19584225118160248,
|
|
"num_tokens": 18243733.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.170470666885376,
|
|
"epoch": 0.828600066822586,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000493762365865011,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.19895717054605483,
|
|
"num_tokens": 18253105.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.308280277252197,
|
|
"epoch": 0.8290177079852991,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004937554027972961,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.18659522533416747,
|
|
"num_tokens": 18261862.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.334354639053345,
|
|
"epoch": 0.829435349148012,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004937484359000046,
|
|
"loss": 5.2195,
|
|
"mean_token_accuracy": 0.19028422683477403,
|
|
"num_tokens": 18271941.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.2598161697387695,
|
|
"epoch": 0.829852990310725,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004937414651732584,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.19467880874872207,
|
|
"num_tokens": 18281048.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.323976039886475,
|
|
"epoch": 0.830270631473438,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004937344906171795,
|
|
"loss": 5.2334,
|
|
"mean_token_accuracy": 0.18143781125545502,
|
|
"num_tokens": 18290140.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.168869733810425,
|
|
"epoch": 0.830688272636151,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004937275122318902,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.1929491087794304,
|
|
"num_tokens": 18298784.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.275314807891846,
|
|
"epoch": 0.831105913798864,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004937205300175123,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.19509119540452957,
|
|
"num_tokens": 18307750.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.2995954036712645,
|
|
"epoch": 0.831523554961577,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004937135439741682,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19828321933746337,
|
|
"num_tokens": 18317042.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.244739675521851,
|
|
"epoch": 0.83194119612429,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004937065541019806,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.1906749948859215,
|
|
"num_tokens": 18326733.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.3648172378540036,
|
|
"epoch": 0.832358837287003,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004936995604010711,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.1812009334564209,
|
|
"num_tokens": 18336366.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.255705642700195,
|
|
"epoch": 0.832776478449716,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004936925628715628,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.1914728492498398,
|
|
"num_tokens": 18345260.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.322878313064575,
|
|
"epoch": 0.833194119612429,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004936855615135779,
|
|
"loss": 5.1805,
|
|
"mean_token_accuracy": 0.18769506365060806,
|
|
"num_tokens": 18354916.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.315698289871216,
|
|
"epoch": 0.833611760775142,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000493678556327239,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.19391870498657227,
|
|
"num_tokens": 18364012.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.300132942199707,
|
|
"epoch": 0.834029401937855,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004936715473126688,
|
|
"loss": 5.1344,
|
|
"mean_token_accuracy": 0.1849350556731224,
|
|
"num_tokens": 18374685.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.096344947814941,
|
|
"epoch": 0.8344470431005679,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00049366453446999,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.2049587234854698,
|
|
"num_tokens": 18383716.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.142494821548462,
|
|
"epoch": 0.834864684263281,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004936575177993251,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.19872361719608306,
|
|
"num_tokens": 18393071.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.424183464050293,
|
|
"epoch": 0.835282325425994,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004936504973007973,
|
|
"loss": 5.2259,
|
|
"mean_token_accuracy": 0.18933799862861633,
|
|
"num_tokens": 18403593.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.3685239315032955,
|
|
"epoch": 0.8356999665887069,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004936434729745294,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.18411905616521834,
|
|
"num_tokens": 18412016.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.2355184078216555,
|
|
"epoch": 0.83611760775142,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004936364448206442,
|
|
"loss": 5.0537,
|
|
"mean_token_accuracy": 0.19321360886096955,
|
|
"num_tokens": 18421098.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.227397155761719,
|
|
"epoch": 0.836535248914133,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004936294128392649,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.18819456398487092,
|
|
"num_tokens": 18430264.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.332653760910034,
|
|
"epoch": 0.8369528900768459,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004936223770305146,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.1921686962246895,
|
|
"num_tokens": 18439595.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.297098541259766,
|
|
"epoch": 0.837370531239559,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004936153373945165,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.1947207123041153,
|
|
"num_tokens": 18448945.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.288499164581299,
|
|
"epoch": 0.837788172402272,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004936082939313936,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.19456617832183837,
|
|
"num_tokens": 18458623.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.249464321136474,
|
|
"epoch": 0.8382058135649849,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004936012466412695,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.19926332384347917,
|
|
"num_tokens": 18466462.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.2157652378082275,
|
|
"epoch": 0.838623454727698,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004935941955242674,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.18945154994726182,
|
|
"num_tokens": 18475936.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.190078020095825,
|
|
"epoch": 0.839041095890411,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004935871405805109,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.19731518477201462,
|
|
"num_tokens": 18485526.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.2232341289520265,
|
|
"epoch": 0.8394587370531239,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004935800818101232,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.19846357703208922,
|
|
"num_tokens": 18494202.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.347828674316406,
|
|
"epoch": 0.8398763782158369,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004935730192132282,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18958183526992797,
|
|
"num_tokens": 18503502.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.350813388824463,
|
|
"epoch": 0.84029401937855,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004935659527899493,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.1950361981987953,
|
|
"num_tokens": 18512607.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.269353723526001,
|
|
"epoch": 0.8407116605412629,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004935588825404104,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.19499771147966385,
|
|
"num_tokens": 18521875.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.298912239074707,
|
|
"epoch": 0.8411293017039759,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004935518084647351,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.2010849565267563,
|
|
"num_tokens": 18530554.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.277385997772217,
|
|
"epoch": 0.841546942866689,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004935447305630474,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.20428809076547622,
|
|
"num_tokens": 18539037.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.143201160430908,
|
|
"epoch": 0.8419645840294019,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004935376488354711,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.1989608809351921,
|
|
"num_tokens": 18548218.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.296752023696899,
|
|
"epoch": 0.8423822251921149,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004935305632821303,
|
|
"loss": 5.0992,
|
|
"mean_token_accuracy": 0.1943753942847252,
|
|
"num_tokens": 18557968.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.300920295715332,
|
|
"epoch": 0.842799866354828,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004935234739031488,
|
|
"loss": 5.216,
|
|
"mean_token_accuracy": 0.18711352348327637,
|
|
"num_tokens": 18566809.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.256332349777222,
|
|
"epoch": 0.8432175075175409,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004935163806986508,
|
|
"loss": 5.0809,
|
|
"mean_token_accuracy": 0.19128889888525008,
|
|
"num_tokens": 18574419.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.299392127990723,
|
|
"epoch": 0.8436351486802539,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004935092836687607,
|
|
"loss": 5.1346,
|
|
"mean_token_accuracy": 0.19238422960042953,
|
|
"num_tokens": 18584470.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.344189453125,
|
|
"epoch": 0.8440527898429669,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004935021828136025,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19648874551057816,
|
|
"num_tokens": 18593551.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.211934900283813,
|
|
"epoch": 0.8444704310056799,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004934950781333005,
|
|
"loss": 5.1172,
|
|
"mean_token_accuracy": 0.19153958112001418,
|
|
"num_tokens": 18602253.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.244383239746094,
|
|
"epoch": 0.8448880721683929,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004934879696279793,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.18769302368164062,
|
|
"num_tokens": 18611261.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.376082801818848,
|
|
"epoch": 0.8453057133311059,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004934808572977632,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.1848089024424553,
|
|
"num_tokens": 18620508.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.307138156890869,
|
|
"epoch": 0.8457233544938189,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004934737411427765,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.20037644803524018,
|
|
"num_tokens": 18629140.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.1886794090271,
|
|
"epoch": 0.8461409956565319,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004934666211631442,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.20019556134939193,
|
|
"num_tokens": 18637924.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.25268669128418,
|
|
"epoch": 0.8465586368192449,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004934594973589906,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.19955097436904906,
|
|
"num_tokens": 18646193.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.368896007537842,
|
|
"epoch": 0.8469762779819578,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004934523697304406,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.18375039398670195,
|
|
"num_tokens": 18655327.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.293934345245361,
|
|
"epoch": 0.8473939191446709,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004934452382776189,
|
|
"loss": 5.1477,
|
|
"mean_token_accuracy": 0.18675615638494492,
|
|
"num_tokens": 18664633.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.240318775177002,
|
|
"epoch": 0.8478115603073839,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004934381030006504,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.18676041811704636,
|
|
"num_tokens": 18673956.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.238237142562866,
|
|
"epoch": 0.8482292014700968,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00049343096389966,
|
|
"loss": 5.0467,
|
|
"mean_token_accuracy": 0.19457723647356034,
|
|
"num_tokens": 18682257.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.193057298660278,
|
|
"epoch": 0.8486468426328099,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004934238209747724,
|
|
"loss": 5.0388,
|
|
"mean_token_accuracy": 0.19794312119483948,
|
|
"num_tokens": 18691493.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.244580316543579,
|
|
"epoch": 0.8490644837955229,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004934166742261132,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.1974581390619278,
|
|
"num_tokens": 18700309.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.204142093658447,
|
|
"epoch": 0.8494821249582358,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000493409523653807,
|
|
"loss": 5.0857,
|
|
"mean_token_accuracy": 0.19576020985841752,
|
|
"num_tokens": 18709909.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.348386955261231,
|
|
"epoch": 0.8498997661209489,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004934023692579793,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.18125803768634796,
|
|
"num_tokens": 18719270.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.2265712261199955,
|
|
"epoch": 0.8503174072836619,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004933952110387553,
|
|
"loss": 5.0514,
|
|
"mean_token_accuracy": 0.19341590255498886,
|
|
"num_tokens": 18728141.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.239239454269409,
|
|
"epoch": 0.8507350484463748,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 5.0952,
|
|
"mean_token_accuracy": 0.19350501596927644,
|
|
"num_tokens": 18737925.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.255416917800903,
|
|
"epoch": 0.8511526896090879,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004933808831306194,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.19600435346364975,
|
|
"num_tokens": 18746622.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.179063606262207,
|
|
"epoch": 0.8515703307718009,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004933737134419583,
|
|
"loss": 5.0613,
|
|
"mean_token_accuracy": 0.19782729744911193,
|
|
"num_tokens": 18755316.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.176108932495117,
|
|
"epoch": 0.8519879719345138,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004933665399304025,
|
|
"loss": 5.0462,
|
|
"mean_token_accuracy": 0.19505841583013533,
|
|
"num_tokens": 18765264.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.233957576751709,
|
|
"epoch": 0.8524056130972268,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004933593625960777,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.198008631169796,
|
|
"num_tokens": 18774275.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.200260925292969,
|
|
"epoch": 0.8528232542599399,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004933521814391094,
|
|
"loss": 5.0551,
|
|
"mean_token_accuracy": 0.198702871799469,
|
|
"num_tokens": 18782848.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.218249845504761,
|
|
"epoch": 0.8532408954226529,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004933449964596232,
|
|
"loss": 5.1089,
|
|
"mean_token_accuracy": 0.19394540935754775,
|
|
"num_tokens": 18792072.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.3451320171356205,
|
|
"epoch": 0.8536585365853658,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004933378076577451,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.1999950423836708,
|
|
"num_tokens": 18800886.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.236936950683594,
|
|
"epoch": 0.8540761777480789,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004933306150336009,
|
|
"loss": 5.0912,
|
|
"mean_token_accuracy": 0.20164105892181397,
|
|
"num_tokens": 18809673.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.250994777679443,
|
|
"epoch": 0.8544938189107919,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004933234185873164,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.20258415937423707,
|
|
"num_tokens": 18818230.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.211773109436035,
|
|
"epoch": 0.8549114600735048,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004933162183190177,
|
|
"loss": 5.1338,
|
|
"mean_token_accuracy": 0.1945189744234085,
|
|
"num_tokens": 18827600.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.37983283996582,
|
|
"epoch": 0.8553291012362179,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004933090142288308,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1906238839030266,
|
|
"num_tokens": 18837237.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.3497881412506105,
|
|
"epoch": 0.8557467423989309,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004933018063168819,
|
|
"loss": 5.1747,
|
|
"mean_token_accuracy": 0.19596707224845886,
|
|
"num_tokens": 18846859.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.280359506607056,
|
|
"epoch": 0.8561643835616438,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000493294594583297,
|
|
"loss": 5.1059,
|
|
"mean_token_accuracy": 0.1929030016064644,
|
|
"num_tokens": 18856226.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.155808019638061,
|
|
"epoch": 0.8565820247243568,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004932873790282026,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.200956392288208,
|
|
"num_tokens": 18864679.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.241528844833374,
|
|
"epoch": 0.8569996658870699,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004932801596517248,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.18533792495727539,
|
|
"num_tokens": 18874837.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.243050003051758,
|
|
"epoch": 0.8574173070497828,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004932729364539901,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.2024909198284149,
|
|
"num_tokens": 18883669.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.1785496234893795,
|
|
"epoch": 0.8578349482124958,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004932657094351248,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.19862864315509796,
|
|
"num_tokens": 18892199.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.375548553466797,
|
|
"epoch": 0.8582525893752089,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004932584785952555,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.19348810166120528,
|
|
"num_tokens": 18902393.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.2853258609771725,
|
|
"epoch": 0.8586702305379218,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000493251243934509,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.19090647101402283,
|
|
"num_tokens": 18912417.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.3069662094116214,
|
|
"epoch": 0.8590878717006348,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004932440054530116,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.19052484184503554,
|
|
"num_tokens": 18921456.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.2105762481689455,
|
|
"epoch": 0.8595055128633479,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004932367631508903,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.1960864007472992,
|
|
"num_tokens": 18930865.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.230211162567139,
|
|
"epoch": 0.8599231540260608,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004932295170282717,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.1914416015148163,
|
|
"num_tokens": 18940043.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.209995603561401,
|
|
"epoch": 0.8603407951887738,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004932222670852828,
|
|
"loss": 4.9968,
|
|
"mean_token_accuracy": 0.1943082705140114,
|
|
"num_tokens": 18948803.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.2017354488372805,
|
|
"epoch": 0.8607584363514869,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004932150133220504,
|
|
"loss": 5.1025,
|
|
"mean_token_accuracy": 0.19546860903501512,
|
|
"num_tokens": 18958014.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.165151882171631,
|
|
"epoch": 0.8611760775141998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004932077557387015,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.19663773030042647,
|
|
"num_tokens": 18966425.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.19660005569458,
|
|
"epoch": 0.8615937186769128,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004932004943353633,
|
|
"loss": 5.1452,
|
|
"mean_token_accuracy": 0.1869480550289154,
|
|
"num_tokens": 18975445.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.377605724334717,
|
|
"epoch": 0.8620113598396258,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004931932291121627,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19668253511190414,
|
|
"num_tokens": 18984271.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.313975191116333,
|
|
"epoch": 0.8624290010023388,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004931859600692269,
|
|
"loss": 5.1151,
|
|
"mean_token_accuracy": 0.19372533708810807,
|
|
"num_tokens": 18994179.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.196731853485107,
|
|
"epoch": 0.8628466421650518,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004931786872066833,
|
|
"loss": 5.0158,
|
|
"mean_token_accuracy": 0.19707428365945817,
|
|
"num_tokens": 19003313.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.239146041870117,
|
|
"epoch": 0.8632642833277648,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004931714105246592,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19171369969844818,
|
|
"num_tokens": 19013982.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.201680326461792,
|
|
"epoch": 0.8636819244904778,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004931641300232819,
|
|
"loss": 5.0668,
|
|
"mean_token_accuracy": 0.19870493859052657,
|
|
"num_tokens": 19022634.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.211349678039551,
|
|
"epoch": 0.8640995656531908,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004931568457026789,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.19099931567907333,
|
|
"num_tokens": 19031903.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.3132282257080075,
|
|
"epoch": 0.8645172068159038,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004931495575629778,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.19376570582389832,
|
|
"num_tokens": 19040367.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.296181869506836,
|
|
"epoch": 0.8649348479786167,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000493142265604306,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20076291561126708,
|
|
"num_tokens": 19049572.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.29019718170166,
|
|
"epoch": 0.8653524891413298,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004931349698267914,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.1847943753004074,
|
|
"num_tokens": 19059313.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.228671073913574,
|
|
"epoch": 0.8657701303040428,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004931276702305615,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.19198494255542756,
|
|
"num_tokens": 19067941.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.249677133560181,
|
|
"epoch": 0.8661877714667557,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004931203668157441,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.19453371912240983,
|
|
"num_tokens": 19077462.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.262096405029297,
|
|
"epoch": 0.8666054126294688,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004931130595824672,
|
|
"loss": 5.1642,
|
|
"mean_token_accuracy": 0.19705860912799836,
|
|
"num_tokens": 19086669.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.229280614852906,
|
|
"epoch": 0.8670230537921818,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004931057485308587,
|
|
"loss": 5.1279,
|
|
"mean_token_accuracy": 0.1925350546836853,
|
|
"num_tokens": 19095781.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.262217998504639,
|
|
"epoch": 0.8674406949548947,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004930984336610465,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.19263307601213456,
|
|
"num_tokens": 19105106.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.345351076126098,
|
|
"epoch": 0.8678583361176078,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004930911149731587,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.19208741188049316,
|
|
"num_tokens": 19114710.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.273029756546021,
|
|
"epoch": 0.8682759772803208,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004930837924673233,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.2012007027864456,
|
|
"num_tokens": 19123495.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.267076253890991,
|
|
"epoch": 0.8686936184430337,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004930764661436688,
|
|
"loss": 5.1545,
|
|
"mean_token_accuracy": 0.18852797001600266,
|
|
"num_tokens": 19131894.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.334974956512451,
|
|
"epoch": 0.8691112596057468,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004930691360023231,
|
|
"loss": 5.2038,
|
|
"mean_token_accuracy": 0.18459987342357637,
|
|
"num_tokens": 19141213.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.28029842376709,
|
|
"epoch": 0.8695289007684598,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004930618020434147,
|
|
"loss": 5.0678,
|
|
"mean_token_accuracy": 0.19768889099359513,
|
|
"num_tokens": 19150843.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.266949319839478,
|
|
"epoch": 0.8699465419311727,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004930544642670721,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.1998864606022835,
|
|
"num_tokens": 19160198.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.1807776927948,
|
|
"epoch": 0.8703641830938857,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004930471226734235,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.19046980291604995,
|
|
"num_tokens": 19169043.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.231479549407959,
|
|
"epoch": 0.8707818242565988,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004930397772625976,
|
|
"loss": 5.1255,
|
|
"mean_token_accuracy": 0.1895667389035225,
|
|
"num_tokens": 19177976.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.278642797470093,
|
|
"epoch": 0.8711994654193117,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000493032428034723,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.19002075344324112,
|
|
"num_tokens": 19187909.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.2143903255462645,
|
|
"epoch": 0.8716171065820247,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004930250749899282,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.20639198571443557,
|
|
"num_tokens": 19196297.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.2500848293304445,
|
|
"epoch": 0.8720347477447378,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004930177181283422,
|
|
"loss": 5.1713,
|
|
"mean_token_accuracy": 0.1945100963115692,
|
|
"num_tokens": 19205280.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.204897069931031,
|
|
"epoch": 0.8724523889074507,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004930103574500934,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.19966092705726624,
|
|
"num_tokens": 19214789.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.2736598491668705,
|
|
"epoch": 0.8728700300701637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004930029929553109,
|
|
"loss": 5.1109,
|
|
"mean_token_accuracy": 0.19714061170816422,
|
|
"num_tokens": 19224597.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.213609647750855,
|
|
"epoch": 0.8732876712328768,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004929956246441237,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.18928576856851578,
|
|
"num_tokens": 19233716.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.222967720031738,
|
|
"epoch": 0.8737053123955897,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004929882525166608,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.20641841143369674,
|
|
"num_tokens": 19242444.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.20804271697998,
|
|
"epoch": 0.8741229535583027,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004929808765730509,
|
|
"loss": 5.1277,
|
|
"mean_token_accuracy": 0.19357253313064576,
|
|
"num_tokens": 19252380.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.258271265029907,
|
|
"epoch": 0.8745405947210158,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004929734968134235,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.18180986642837524,
|
|
"num_tokens": 19262250.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.302599859237671,
|
|
"epoch": 0.8749582358837287,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004929661132379076,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.18860046267509462,
|
|
"num_tokens": 19272228.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.323856353759766,
|
|
"epoch": 0.8753758770464417,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004929587258466326,
|
|
"loss": 5.1954,
|
|
"mean_token_accuracy": 0.18734628111124038,
|
|
"num_tokens": 19281493.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.338038778305053,
|
|
"epoch": 0.8757935182091547,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004929513346397278,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.18421531319618226,
|
|
"num_tokens": 19292300.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.313906908035278,
|
|
"epoch": 0.8762111593718677,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004929439396173223,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.18565773963928223,
|
|
"num_tokens": 19301516.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.201851177215576,
|
|
"epoch": 0.8766288005345807,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000492936540779546,
|
|
"loss": 4.9956,
|
|
"mean_token_accuracy": 0.20913029164075853,
|
|
"num_tokens": 19311075.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.241045951843262,
|
|
"epoch": 0.8770464416972937,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004929291381265281,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.189761783182621,
|
|
"num_tokens": 19320605.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.243987941741944,
|
|
"epoch": 0.8774640828600067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004929217316583985,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.19928644746541976,
|
|
"num_tokens": 19330604.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.21263108253479,
|
|
"epoch": 0.8778817240227197,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004929143213752865,
|
|
"loss": 5.1633,
|
|
"mean_token_accuracy": 0.19733937233686447,
|
|
"num_tokens": 19340650.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.371497297286988,
|
|
"epoch": 0.8782993651854327,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000492906907277322,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.17760407775640488,
|
|
"num_tokens": 19350431.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.318976926803589,
|
|
"epoch": 0.8787170063481456,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000492899489364635,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.18663914054632186,
|
|
"num_tokens": 19360171.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.238416910171509,
|
|
"epoch": 0.8791346475108587,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004928920676373549,
|
|
"loss": 5.117,
|
|
"mean_token_accuracy": 0.19180480539798736,
|
|
"num_tokens": 19369748.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.2819455623626705,
|
|
"epoch": 0.8795522886735717,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000492884642095612,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.18991636335849763,
|
|
"num_tokens": 19378470.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.253831243515014,
|
|
"epoch": 0.8799699298362846,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004928772127395361,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.1983237236738205,
|
|
"num_tokens": 19387869.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.340179443359375,
|
|
"epoch": 0.8803875709989977,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928697795692575,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.184271876513958,
|
|
"num_tokens": 19396805.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.182686042785645,
|
|
"epoch": 0.8808052121617107,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492862342584906,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.19348762929439545,
|
|
"num_tokens": 19405392.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.325152778625489,
|
|
"epoch": 0.8812228533244236,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000492854901786612,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.19296234846115112,
|
|
"num_tokens": 19413896.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.292904424667358,
|
|
"epoch": 0.8816404944871367,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004928474571745058,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.19237807542085647,
|
|
"num_tokens": 19422136.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.14391016960144,
|
|
"epoch": 0.8820581356498497,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928400087487175,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.19728517383337021,
|
|
"num_tokens": 19431250.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.147278881072998,
|
|
"epoch": 0.8824757768125626,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928325565093777,
|
|
"loss": 5.0427,
|
|
"mean_token_accuracy": 0.19500260949134826,
|
|
"num_tokens": 19439155.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.265140867233276,
|
|
"epoch": 0.8828934179752757,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004928251004566167,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18049997389316558,
|
|
"num_tokens": 19448637.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.3482654094696045,
|
|
"epoch": 0.8833110591379887,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004928176405905653,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.18764340579509736,
|
|
"num_tokens": 19457573.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.251343584060669,
|
|
"epoch": 0.8837287003007016,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004928101769113537,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.20340760797262192,
|
|
"num_tokens": 19466085.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.180642223358154,
|
|
"epoch": 0.8841463414634146,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492802709419113,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.2037220850586891,
|
|
"num_tokens": 19475185.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.26083345413208,
|
|
"epoch": 0.8845639826261277,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004927952381139735,
|
|
"loss": 5.1699,
|
|
"mean_token_accuracy": 0.18603014796972275,
|
|
"num_tokens": 19484387.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.200754451751709,
|
|
"epoch": 0.8849816237888406,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004927877629960663,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.19057920426130295,
|
|
"num_tokens": 19493309.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.269811058044434,
|
|
"epoch": 0.8853992649515536,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004927802840655221,
|
|
"loss": 5.1287,
|
|
"mean_token_accuracy": 0.19439708888530732,
|
|
"num_tokens": 19502284.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.339306306838989,
|
|
"epoch": 0.8858169061142667,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000492772801322472,
|
|
"loss": 5.1376,
|
|
"mean_token_accuracy": 0.19411446750164033,
|
|
"num_tokens": 19512720.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.2461244583129885,
|
|
"epoch": 0.8862345472769796,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004927653147670468,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.2013916179537773,
|
|
"num_tokens": 19521395.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.16604700088501,
|
|
"epoch": 0.8866521884396926,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004927578243993777,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.19396515935659409,
|
|
"num_tokens": 19530855.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.240046072006225,
|
|
"epoch": 0.8870698296024057,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004927503302195957,
|
|
"loss": 5.0518,
|
|
"mean_token_accuracy": 0.19882560074329375,
|
|
"num_tokens": 19540330.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.215531301498413,
|
|
"epoch": 0.8874874707651186,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000492742832227832,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.1946081131696701,
|
|
"num_tokens": 19549639.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.244396591186524,
|
|
"epoch": 0.8879051119278316,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000492735330424218,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.1996217265725136,
|
|
"num_tokens": 19558485.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.306069946289062,
|
|
"epoch": 0.8883227530905446,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000492727824808885,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.1942100167274475,
|
|
"num_tokens": 19566924.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.364131164550781,
|
|
"epoch": 0.8887403942532576,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004927203153819643,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.19472651183605194,
|
|
"num_tokens": 19575901.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.25958743095398,
|
|
"epoch": 0.8891580354159706,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004927128021435875,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.1901501625776291,
|
|
"num_tokens": 19585470.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.289333343505859,
|
|
"epoch": 0.8895756765786836,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492705285093886,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.19389011412858964,
|
|
"num_tokens": 19594775.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.304211235046386,
|
|
"epoch": 0.8899933177413966,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004926977642329913,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.19043017327785491,
|
|
"num_tokens": 19604061.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.206965112686158,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004926902395610353,
|
|
"loss": 5.0574,
|
|
"mean_token_accuracy": 0.20077430158853532,
|
|
"num_tokens": 19613130.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.124741697311402,
|
|
"epoch": 0.8908286000668226,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004926827110781496,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.20327755063772202,
|
|
"num_tokens": 19621951.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.177820444107056,
|
|
"epoch": 0.8912462412295356,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000492675178784466,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.19026484489440917,
|
|
"num_tokens": 19631167.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.3053307056427,
|
|
"epoch": 0.8916638823922486,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004926676426801164,
|
|
"loss": 5.1783,
|
|
"mean_token_accuracy": 0.19123457968235016,
|
|
"num_tokens": 19640548.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.225992441177368,
|
|
"epoch": 0.8920815235549616,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004926601027652328,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.1970062106847763,
|
|
"num_tokens": 19650607.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.165138292312622,
|
|
"epoch": 0.8924991647176745,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000492652559039947,
|
|
"loss": 4.9966,
|
|
"mean_token_accuracy": 0.2015234112739563,
|
|
"num_tokens": 19659845.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.194818210601807,
|
|
"epoch": 0.8929168058803876,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004926450115043912,
|
|
"loss": 5.0789,
|
|
"mean_token_accuracy": 0.19947440475225447,
|
|
"num_tokens": 19668863.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.210253524780273,
|
|
"epoch": 0.8933344470431006,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004926374601586975,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.19982438981533052,
|
|
"num_tokens": 19678335.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.2233171463012695,
|
|
"epoch": 0.8937520882058135,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004926299050029981,
|
|
"loss": 5.0808,
|
|
"mean_token_accuracy": 0.19397748708724977,
|
|
"num_tokens": 19687491.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.124798345565796,
|
|
"epoch": 0.8941697293685266,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004926223460374251,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.20394137799739837,
|
|
"num_tokens": 19696632.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.170961332321167,
|
|
"epoch": 0.8945873705312396,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004926147832621111,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.18890809565782546,
|
|
"num_tokens": 19706275.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.350946235656738,
|
|
"epoch": 0.8950050116939525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004926072166771884,
|
|
"loss": 5.1658,
|
|
"mean_token_accuracy": 0.18675604164600373,
|
|
"num_tokens": 19716016.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.347976732254028,
|
|
"epoch": 0.8954226528566656,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004925996462827895,
|
|
"loss": 5.1013,
|
|
"mean_token_accuracy": 0.19367033690214158,
|
|
"num_tokens": 19725555.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.2164818286895756,
|
|
"epoch": 0.8958402940193786,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004925920720790466,
|
|
"loss": 5.1449,
|
|
"mean_token_accuracy": 0.19570198953151702,
|
|
"num_tokens": 19735184.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.206806325912476,
|
|
"epoch": 0.8962579351820915,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004925844940660928,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.20031583905220032,
|
|
"num_tokens": 19744065.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.23223352432251,
|
|
"epoch": 0.8966755763448045,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004925769122440606,
|
|
"loss": 5.0645,
|
|
"mean_token_accuracy": 0.19948068112134934,
|
|
"num_tokens": 19753251.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.223589324951172,
|
|
"epoch": 0.8970932175075176,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004925693266130824,
|
|
"loss": 5.0183,
|
|
"mean_token_accuracy": 0.20291998535394667,
|
|
"num_tokens": 19761290.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.302721738815308,
|
|
"epoch": 0.8975108586702305,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 5.0997,
|
|
"mean_token_accuracy": 0.19556908011436464,
|
|
"num_tokens": 19769169.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.2339414119720455,
|
|
"epoch": 0.8979284998329435,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004925541439248203,
|
|
"loss": 5.1186,
|
|
"mean_token_accuracy": 0.19987917244434356,
|
|
"num_tokens": 19778118.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.202046823501587,
|
|
"epoch": 0.8983461409956566,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492546546867802,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.19133514016866685,
|
|
"num_tokens": 19787281.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.22608323097229,
|
|
"epoch": 0.8987637821583695,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004925389460023696,
|
|
"loss": 5.0445,
|
|
"mean_token_accuracy": 0.19600608348846435,
|
|
"num_tokens": 19795797.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.289606332778931,
|
|
"epoch": 0.8991814233210825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925313413286559,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19121022373437882,
|
|
"num_tokens": 19804788.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.311471271514892,
|
|
"epoch": 0.8995990644837956,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004925237328467945,
|
|
"loss": 5.1649,
|
|
"mean_token_accuracy": 0.19272789508104324,
|
|
"num_tokens": 19814696.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.316903829574585,
|
|
"epoch": 0.9000167056465085,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004925161205569182,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.19051541090011598,
|
|
"num_tokens": 19824216.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.206996488571167,
|
|
"epoch": 0.9004343468092215,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004925085044591604,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.19773166626691818,
|
|
"num_tokens": 19832272.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.252897596359253,
|
|
"epoch": 0.9008519879719346,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004925008845536544,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.19213270545005798,
|
|
"num_tokens": 19841655.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.209755802154541,
|
|
"epoch": 0.9012696291346475,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004924932608405336,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.20090115517377855,
|
|
"num_tokens": 19851288.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.266305446624756,
|
|
"epoch": 0.9016872702973605,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004924856333199315,
|
|
"loss": 5.1244,
|
|
"mean_token_accuracy": 0.1913056939840317,
|
|
"num_tokens": 19860537.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.304848575592041,
|
|
"epoch": 0.9021049114600735,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004924780019919816,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19724492132663726,
|
|
"num_tokens": 19869618.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.248780965805054,
|
|
"epoch": 0.9025225526227865,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004924703668568174,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.20323309004306794,
|
|
"num_tokens": 19879236.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.204006671905518,
|
|
"epoch": 0.9029401937854995,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004924627279145728,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.19963822960853578,
|
|
"num_tokens": 19887740.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.258492755889892,
|
|
"epoch": 0.9033578349482125,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004924550851653814,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.19848864674568176,
|
|
"num_tokens": 19896024.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.256488466262818,
|
|
"epoch": 0.9037754761109255,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004924474386093769,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.1942973256111145,
|
|
"num_tokens": 19905533.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.1709747314453125,
|
|
"epoch": 0.9041931172736385,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004924397882466933,
|
|
"loss": 4.9772,
|
|
"mean_token_accuracy": 0.20180195122957229,
|
|
"num_tokens": 19913560.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.192577600479126,
|
|
"epoch": 0.9046107584363515,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004924321340774644,
|
|
"loss": 5.0461,
|
|
"mean_token_accuracy": 0.19146844744682312,
|
|
"num_tokens": 19923159.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.125152158737182,
|
|
"epoch": 0.9050283995990644,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004924244761018243,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.2023927837610245,
|
|
"num_tokens": 19931485.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.24166054725647,
|
|
"epoch": 0.9054460407617775,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000492416814319907,
|
|
"loss": 5.1842,
|
|
"mean_token_accuracy": 0.18846316039562225,
|
|
"num_tokens": 19940552.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.260291194915771,
|
|
"epoch": 0.9058636819244905,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004924091487318468,
|
|
"loss": 5.0982,
|
|
"mean_token_accuracy": 0.1973618224263191,
|
|
"num_tokens": 19949334.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.260881805419922,
|
|
"epoch": 0.9062813230872034,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004924014793377776,
|
|
"loss": 5.1362,
|
|
"mean_token_accuracy": 0.19280770570039749,
|
|
"num_tokens": 19958569.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.245477533340454,
|
|
"epoch": 0.9066989642499165,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004923938061378339,
|
|
"loss": 5.1054,
|
|
"mean_token_accuracy": 0.20338567942380906,
|
|
"num_tokens": 19967568.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.281686592102051,
|
|
"epoch": 0.9071166054126295,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004923861291321499,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.202757728099823,
|
|
"num_tokens": 19976466.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.248608493804932,
|
|
"epoch": 0.9075342465753424,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004923784483208601,
|
|
"loss": 5.0318,
|
|
"mean_token_accuracy": 0.2010367915034294,
|
|
"num_tokens": 19986145.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.146245908737183,
|
|
"epoch": 0.9079518877380555,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004923707637040989,
|
|
"loss": 5.0026,
|
|
"mean_token_accuracy": 0.19794430881738662,
|
|
"num_tokens": 19994611.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.211374568939209,
|
|
"epoch": 0.9083695289007685,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004923630752820008,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.18835837841033937,
|
|
"num_tokens": 20004578.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.313225364685058,
|
|
"epoch": 0.9087871700634814,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004923553830547004,
|
|
"loss": 5.1708,
|
|
"mean_token_accuracy": 0.19138211458921434,
|
|
"num_tokens": 20014375.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.207137632369995,
|
|
"epoch": 0.9092048112261945,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004923476870223324,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.1972305342555046,
|
|
"num_tokens": 20023869.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.198520612716675,
|
|
"epoch": 0.9096224523889075,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004923399871850315,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.20006888806819917,
|
|
"num_tokens": 20033465.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.257648563385009,
|
|
"epoch": 0.9100400935516204,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004923322835429326,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.18882854729890824,
|
|
"num_tokens": 20042851.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.264758491516114,
|
|
"epoch": 0.9104577347143334,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004923245760961704,
|
|
"loss": 5.0609,
|
|
"mean_token_accuracy": 0.19790236204862593,
|
|
"num_tokens": 20052765.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.180483007431031,
|
|
"epoch": 0.9108753758770465,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004923168648448799,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.19198423326015474,
|
|
"num_tokens": 20061368.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.206907510757446,
|
|
"epoch": 0.9112930170397594,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004923091497891961,
|
|
"loss": 4.9937,
|
|
"mean_token_accuracy": 0.19722962975502015,
|
|
"num_tokens": 20070408.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.224948120117188,
|
|
"epoch": 0.9117106582024724,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004923014309292541,
|
|
"loss": 5.1412,
|
|
"mean_token_accuracy": 0.18967356532812119,
|
|
"num_tokens": 20080305.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.313349914550781,
|
|
"epoch": 0.9121282993651855,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000492293708265189,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.1885618358850479,
|
|
"num_tokens": 20090715.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.312185764312744,
|
|
"epoch": 0.9125459405278984,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004922859817971359,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.19247750341892242,
|
|
"num_tokens": 20099538.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.237669563293457,
|
|
"epoch": 0.9129635816906114,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004922782515252302,
|
|
"loss": 5.0776,
|
|
"mean_token_accuracy": 0.19177051037549972,
|
|
"num_tokens": 20109177.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.240066337585449,
|
|
"epoch": 0.9133812228533245,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004922705174496072,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.19534749090671538,
|
|
"num_tokens": 20117200.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.186641263961792,
|
|
"epoch": 0.9137988640160374,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004922627795704022,
|
|
"loss": 5.0144,
|
|
"mean_token_accuracy": 0.19756677746772766,
|
|
"num_tokens": 20126069.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.255351400375366,
|
|
"epoch": 0.9142165051787504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004922550378877507,
|
|
"loss": 5.1211,
|
|
"mean_token_accuracy": 0.19087007343769075,
|
|
"num_tokens": 20136763.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.337204837799073,
|
|
"epoch": 0.9146341463414634,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004922472924017882,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.18871946930885314,
|
|
"num_tokens": 20145765.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.2932531356811525,
|
|
"epoch": 0.9150517875041764,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004922395431126506,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.1875919371843338,
|
|
"num_tokens": 20154504.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.257823657989502,
|
|
"epoch": 0.9154694286668894,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004922317900204732,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.19012669026851653,
|
|
"num_tokens": 20163903.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.218070697784424,
|
|
"epoch": 0.9158870698296024,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004922240331253916,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.19441152960062028,
|
|
"num_tokens": 20172910.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.180325841903686,
|
|
"epoch": 0.9163047109923154,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004922162724275421,
|
|
"loss": 5.0167,
|
|
"mean_token_accuracy": 0.2012465238571167,
|
|
"num_tokens": 20182238.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.18865852355957,
|
|
"epoch": 0.9167223521550284,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004922085079270602,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.2020824134349823,
|
|
"num_tokens": 20190673.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.313888502120972,
|
|
"epoch": 0.9171399933177414,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004922007396240819,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.18127480894327164,
|
|
"num_tokens": 20201219.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.260984754562378,
|
|
"epoch": 0.9175576344804544,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004921929675187433,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.19574062377214432,
|
|
"num_tokens": 20210756.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.267330932617187,
|
|
"epoch": 0.9179752756431674,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004921851916111802,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.19784794598817826,
|
|
"num_tokens": 20219959.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.185554504394531,
|
|
"epoch": 0.9183929168058804,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004921774119015289,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.19807119071483612,
|
|
"num_tokens": 20229633.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.091259717941284,
|
|
"epoch": 0.9188105579685933,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004921696283899257,
|
|
"loss": 5.02,
|
|
"mean_token_accuracy": 0.20769816786050796,
|
|
"num_tokens": 20238355.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.251894426345825,
|
|
"epoch": 0.9192281991313064,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004921618410765067,
|
|
"loss": 5.164,
|
|
"mean_token_accuracy": 0.18543900847434996,
|
|
"num_tokens": 20247461.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.360412073135376,
|
|
"epoch": 0.9196458402940194,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004921540499614083,
|
|
"loss": 5.1871,
|
|
"mean_token_accuracy": 0.19539083391427994,
|
|
"num_tokens": 20256505.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.260100698471069,
|
|
"epoch": 0.9200634814567323,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004921462550447669,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19470291435718537,
|
|
"num_tokens": 20266169.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.139707279205322,
|
|
"epoch": 0.9204811226194454,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004921384563267189,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.20562166571617127,
|
|
"num_tokens": 20274620.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.185931539535522,
|
|
"epoch": 0.9208987637821584,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004921306538074008,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.20378299057483673,
|
|
"num_tokens": 20282829.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.188468170166016,
|
|
"epoch": 0.9213164049448713,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004921228474869493,
|
|
"loss": 5.0756,
|
|
"mean_token_accuracy": 0.19281343817710878,
|
|
"num_tokens": 20292510.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.194281053543091,
|
|
"epoch": 0.9217340461075844,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000492115037365501,
|
|
"loss": 5.0508,
|
|
"mean_token_accuracy": 0.1901983931660652,
|
|
"num_tokens": 20302095.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.3502805709838865,
|
|
"epoch": 0.9221516872702974,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004921072234431925,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19120514988899232,
|
|
"num_tokens": 20310505.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.109669542312622,
|
|
"epoch": 0.9225693284330103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000492099405720161,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.1998417094349861,
|
|
"num_tokens": 20319653.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.2052449703216555,
|
|
"epoch": 0.9229869695957233,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004920915841965429,
|
|
"loss": 5.0782,
|
|
"mean_token_accuracy": 0.19663057029247283,
|
|
"num_tokens": 20329156.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.2692626953125,
|
|
"epoch": 0.9234046107584364,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004920837588724753,
|
|
"loss": 5.1411,
|
|
"mean_token_accuracy": 0.1952005445957184,
|
|
"num_tokens": 20338761.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.152078437805176,
|
|
"epoch": 0.9238222519211493,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004920759297480953,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.2031247466802597,
|
|
"num_tokens": 20347080.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.244210433959961,
|
|
"epoch": 0.9242398930838623,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004920680968235397,
|
|
"loss": 5.1112,
|
|
"mean_token_accuracy": 0.18960548639297486,
|
|
"num_tokens": 20355824.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.2096168994903564,
|
|
"epoch": 0.9246575342465754,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004920602600989459,
|
|
"loss": 5.1273,
|
|
"mean_token_accuracy": 0.19506494253873824,
|
|
"num_tokens": 20365406.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.327987337112427,
|
|
"epoch": 0.9250751754092883,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004920524195744509,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.19438378661870956,
|
|
"num_tokens": 20375153.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.283703231811524,
|
|
"epoch": 0.9254928165720013,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004920445752501921,
|
|
"loss": 5.1197,
|
|
"mean_token_accuracy": 0.19402943551540375,
|
|
"num_tokens": 20384402.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.235755729675293,
|
|
"epoch": 0.9259104577347144,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004920367271263066,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.20057592689990997,
|
|
"num_tokens": 20393913.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.120265626907349,
|
|
"epoch": 0.9263280988974273,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004920288752029321,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.2154456079006195,
|
|
"num_tokens": 20402391.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.251606893539429,
|
|
"epoch": 0.9267457400601403,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004920210194802059,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1960636094212532,
|
|
"num_tokens": 20411682.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.187037181854248,
|
|
"epoch": 0.9271633812228534,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004920131599582654,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.19483170360326768,
|
|
"num_tokens": 20421764.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.344834232330323,
|
|
"epoch": 0.9275810223855663,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004920052966372485,
|
|
"loss": 5.1883,
|
|
"mean_token_accuracy": 0.18701663613319397,
|
|
"num_tokens": 20430420.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.310252952575683,
|
|
"epoch": 0.9279986635482793,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004919974295172926,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.1896035060286522,
|
|
"num_tokens": 20440037.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.168285655975342,
|
|
"epoch": 0.9284163047109923,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004919895585985353,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.1997867465019226,
|
|
"num_tokens": 20448307.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.181406164169312,
|
|
"epoch": 0.9288339458737053,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004919816838811149,
|
|
"loss": 5.0114,
|
|
"mean_token_accuracy": 0.20516011863946915,
|
|
"num_tokens": 20456524.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.337266445159912,
|
|
"epoch": 0.9292515870364183,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004919738053651687,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19022679328918457,
|
|
"num_tokens": 20465352.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.267495965957641,
|
|
"epoch": 0.9296692281991313,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000491965923050835,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.20434942990541458,
|
|
"num_tokens": 20474634.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.174790716171264,
|
|
"epoch": 0.9300868693618443,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004919580369382516,
|
|
"loss": 5.0471,
|
|
"mean_token_accuracy": 0.199737286567688,
|
|
"num_tokens": 20483359.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.2164794445037845,
|
|
"epoch": 0.9305045105245573,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004919501470275567,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.19179025888442994,
|
|
"num_tokens": 20494251.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.214709758758545,
|
|
"epoch": 0.9309221516872703,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004919422533188882,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.1997251734137535,
|
|
"num_tokens": 20503277.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.188405466079712,
|
|
"epoch": 0.9313397928499833,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004919343558123845,
|
|
"loss": 5.0582,
|
|
"mean_token_accuracy": 0.19759026914834976,
|
|
"num_tokens": 20513162.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.282330513000488,
|
|
"epoch": 0.9317574340126963,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004919264545081838,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.19210958778858184,
|
|
"num_tokens": 20522438.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.285643529891968,
|
|
"epoch": 0.9321750751754093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004919185494064244,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.19264516830444336,
|
|
"num_tokens": 20531666.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.178625535964966,
|
|
"epoch": 0.9325927163381222,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004919106405072446,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.20066103637218474,
|
|
"num_tokens": 20540593.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.260520696640015,
|
|
"epoch": 0.9330103575008353,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000491902727810783,
|
|
"loss": 5.1831,
|
|
"mean_token_accuracy": 0.18744262754917146,
|
|
"num_tokens": 20550850.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.23972635269165,
|
|
"epoch": 0.9334279986635483,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004918948113171781,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.18880825340747834,
|
|
"num_tokens": 20559954.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.1876668453216555,
|
|
"epoch": 0.9338456398262612,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004918868910265684,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.19822158813476562,
|
|
"num_tokens": 20568750.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.224745655059815,
|
|
"epoch": 0.9342632809889743,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004918789669390927,
|
|
"loss": 5.0322,
|
|
"mean_token_accuracy": 0.19278217554092408,
|
|
"num_tokens": 20578615.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.3025250911712645,
|
|
"epoch": 0.9346809221516873,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004918710390548895,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.19320757538080216,
|
|
"num_tokens": 20587390.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.2235513687133786,
|
|
"epoch": 0.9350985633144002,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004918631073740977,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.1922682762145996,
|
|
"num_tokens": 20597179.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.204394435882568,
|
|
"epoch": 0.9355162044771133,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004918551718968562,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.19775153398513795,
|
|
"num_tokens": 20606074.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.113510417938232,
|
|
"epoch": 0.9359338456398263,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000491847232623304,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.20684831887483596,
|
|
"num_tokens": 20614977.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.171783351898194,
|
|
"epoch": 0.9363514868025392,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004918392895535798,
|
|
"loss": 5.041,
|
|
"mean_token_accuracy": 0.1996773898601532,
|
|
"num_tokens": 20623486.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.256261730194092,
|
|
"epoch": 0.9367691279652522,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000491831342687823,
|
|
"loss": 5.1237,
|
|
"mean_token_accuracy": 0.19405850768089294,
|
|
"num_tokens": 20632780.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.299038457870483,
|
|
"epoch": 0.9371867691279653,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004918233920261723,
|
|
"loss": 5.0795,
|
|
"mean_token_accuracy": 0.19564387202262878,
|
|
"num_tokens": 20642662.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.134138584136963,
|
|
"epoch": 0.9376044102906782,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004918154375687673,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.1907337039709091,
|
|
"num_tokens": 20651612.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.2558274269104,
|
|
"epoch": 0.9380220514533912,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004918074793157472,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.2052842766046524,
|
|
"num_tokens": 20659940.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.320597124099732,
|
|
"epoch": 0.9384396926161043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004917995172672511,
|
|
"loss": 5.0957,
|
|
"mean_token_accuracy": 0.19740411937236785,
|
|
"num_tokens": 20669004.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.151448583602905,
|
|
"epoch": 0.9388573337788172,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004917915514234184,
|
|
"loss": 5.048,
|
|
"mean_token_accuracy": 0.1947203740477562,
|
|
"num_tokens": 20678469.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.2300561428070065,
|
|
"epoch": 0.9392749749415302,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004917835817843887,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.18938689827919006,
|
|
"num_tokens": 20688368.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.278209781646728,
|
|
"epoch": 0.9396926161042433,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004917756083503014,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.1948768049478531,
|
|
"num_tokens": 20698002.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.170444822311401,
|
|
"epoch": 0.9401102572669562,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004917676311212962,
|
|
"loss": 4.9805,
|
|
"mean_token_accuracy": 0.20433486253023148,
|
|
"num_tokens": 20707798.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.191978836059571,
|
|
"epoch": 0.9405278984296692,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004917596500975127,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.19091614335775375,
|
|
"num_tokens": 20716328.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.318720483779908,
|
|
"epoch": 0.9409455395923823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004917516652790907,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.18771746456623079,
|
|
"num_tokens": 20726526.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.334336757659912,
|
|
"epoch": 0.9413631807550952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004917436766661697,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.1918213739991188,
|
|
"num_tokens": 20735086.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.1155815601348875,
|
|
"epoch": 0.9417808219178082,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049173568425889,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.19667697250843047,
|
|
"num_tokens": 20743677.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.195327043533325,
|
|
"epoch": 0.9421984630805212,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004917276880573911,
|
|
"loss": 5.1371,
|
|
"mean_token_accuracy": 0.19365270137786866,
|
|
"num_tokens": 20753351.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.301815176010132,
|
|
"epoch": 0.9426161042432342,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004917196880618132,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.1888377621769905,
|
|
"num_tokens": 20763654.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.420972490310669,
|
|
"epoch": 0.9430337454059472,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004917116842722962,
|
|
"loss": 5.2047,
|
|
"mean_token_accuracy": 0.18214827477931977,
|
|
"num_tokens": 20774424.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.304692554473877,
|
|
"epoch": 0.9434513865686602,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004917036766889804,
|
|
"loss": 5.163,
|
|
"mean_token_accuracy": 0.19471319168806075,
|
|
"num_tokens": 20782975.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.205314254760742,
|
|
"epoch": 0.9438690277313732,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004916956653120058,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.20890066921710967,
|
|
"num_tokens": 20791943.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.257737159729004,
|
|
"epoch": 0.9442866688940862,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.19427275508642197,
|
|
"num_tokens": 20800920.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.201376724243164,
|
|
"epoch": 0.9447043100567992,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004916796311776417,
|
|
"loss": 5.0888,
|
|
"mean_token_accuracy": 0.18870961517095566,
|
|
"num_tokens": 20810284.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.288651418685913,
|
|
"epoch": 0.9451219512195121,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004916716084205328,
|
|
"loss": 5.1404,
|
|
"mean_token_accuracy": 0.18935603648424149,
|
|
"num_tokens": 20819399.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.224337482452393,
|
|
"epoch": 0.9455395923822252,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004916635818703266,
|
|
"loss": 4.967,
|
|
"mean_token_accuracy": 0.2022601321339607,
|
|
"num_tokens": 20827933.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.220342350006104,
|
|
"epoch": 0.9459572335449382,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004916555515271635,
|
|
"loss": 5.0988,
|
|
"mean_token_accuracy": 0.1943625971674919,
|
|
"num_tokens": 20836636.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.260814476013183,
|
|
"epoch": 0.9463748747076511,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004916475173911844,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.20449433326721192,
|
|
"num_tokens": 20845712.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.236303758621216,
|
|
"epoch": 0.9467925158703642,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004916394794625296,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.18921856880187987,
|
|
"num_tokens": 20856874.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.236445903778076,
|
|
"epoch": 0.9472101570330772,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004916314377413399,
|
|
"loss": 5.1536,
|
|
"mean_token_accuracy": 0.18807098269462585,
|
|
"num_tokens": 20866829.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.359128189086914,
|
|
"epoch": 0.9476277981957901,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004916233922277562,
|
|
"loss": 5.2128,
|
|
"mean_token_accuracy": 0.19296897500753402,
|
|
"num_tokens": 20876409.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.323694801330566,
|
|
"epoch": 0.9480454393585032,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004916153429219192,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.18872769176959991,
|
|
"num_tokens": 20886145.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.243799114227295,
|
|
"epoch": 0.9484630805212162,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004916072898239699,
|
|
"loss": 5.0641,
|
|
"mean_token_accuracy": 0.19877122193574906,
|
|
"num_tokens": 20895471.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.274029493331909,
|
|
"epoch": 0.9488807216839291,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004915992329340493,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.19515497237443924,
|
|
"num_tokens": 20904213.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.2413797855377195,
|
|
"epoch": 0.9492983628466422,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004915911722522984,
|
|
"loss": 5.1275,
|
|
"mean_token_accuracy": 0.19965126365423203,
|
|
"num_tokens": 20914028.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.354149436950683,
|
|
"epoch": 0.9497160040093552,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004915831077788583,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.19592286944389342,
|
|
"num_tokens": 20923514.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.278187227249146,
|
|
"epoch": 0.9501336451720681,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004915750395138702,
|
|
"loss": 5.0476,
|
|
"mean_token_accuracy": 0.1942390576004982,
|
|
"num_tokens": 20932072.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.138377380371094,
|
|
"epoch": 0.9505512863347811,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004915669674574754,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.1999897137284279,
|
|
"num_tokens": 20940438.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.256815433502197,
|
|
"epoch": 0.9509689274974942,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004915588916098151,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.19109569638967513,
|
|
"num_tokens": 20949217.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.260021352767945,
|
|
"epoch": 0.9513865686602071,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004915508119710307,
|
|
"loss": 5.0646,
|
|
"mean_token_accuracy": 0.19801012873649598,
|
|
"num_tokens": 20958123.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.1494049549102785,
|
|
"epoch": 0.9518042098229201,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004915427285412636,
|
|
"loss": 4.9657,
|
|
"mean_token_accuracy": 0.19963421076536178,
|
|
"num_tokens": 20966908.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.206936645507812,
|
|
"epoch": 0.9522218509856332,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004915346413206555,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.20151890963315963,
|
|
"num_tokens": 20975241.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.22903881072998,
|
|
"epoch": 0.9526394921483461,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004915265503093478,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.19123898148536683,
|
|
"num_tokens": 20984336.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.1966948986053465,
|
|
"epoch": 0.9530571333110591,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004915184555074824,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.20042452961206436,
|
|
"num_tokens": 20993703.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.252202653884888,
|
|
"epoch": 0.9534747744737722,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004915103569152005,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.19929608404636384,
|
|
"num_tokens": 21002993.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.320909643173218,
|
|
"epoch": 0.9538924156364851,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004915022545326444,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.18557144105434417,
|
|
"num_tokens": 21012380.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.1560979843139645,
|
|
"epoch": 0.9543100567991981,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004914941483599558,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.20174902826547622,
|
|
"num_tokens": 21021585.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.1530389308929445,
|
|
"epoch": 0.9547276979619111,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004914860383972763,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.19964078813791275,
|
|
"num_tokens": 21030461.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.316731595993042,
|
|
"epoch": 0.9551453391246241,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004914779246447483,
|
|
"loss": 5.1916,
|
|
"mean_token_accuracy": 0.19034045040607453,
|
|
"num_tokens": 21039654.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.323159790039062,
|
|
"epoch": 0.9555629802873371,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004914698071025136,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.18595382273197175,
|
|
"num_tokens": 21048564.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.300195598602295,
|
|
"epoch": 0.9559806214500501,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004914616857707143,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.18961497247219086,
|
|
"num_tokens": 21057378.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.224439382553101,
|
|
"epoch": 0.9563982626127631,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004914535606494927,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.20796577781438827,
|
|
"num_tokens": 21066203.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.214624881744385,
|
|
"epoch": 0.9568159037754761,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000491445431738991,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.19385241568088532,
|
|
"num_tokens": 21075432.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.261520004272461,
|
|
"epoch": 0.9572335449381891,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004914372990393515,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.19727037847042084,
|
|
"num_tokens": 21084165.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.152784252166748,
|
|
"epoch": 0.957651186100902,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004914291625507164,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.20346649885177612,
|
|
"num_tokens": 21093075.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.218937397003174,
|
|
"epoch": 0.9580688272636151,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004914210222732284,
|
|
"loss": 5.0449,
|
|
"mean_token_accuracy": 0.1923544779419899,
|
|
"num_tokens": 21101320.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.279229402542114,
|
|
"epoch": 0.9584864684263281,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004914128782070299,
|
|
"loss": 5.1912,
|
|
"mean_token_accuracy": 0.19238204509019852,
|
|
"num_tokens": 21110584.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.211146116256714,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004914047303522636,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.2016417533159256,
|
|
"num_tokens": 21119558.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.207512331008911,
|
|
"epoch": 0.9593217507517541,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004913965787090718,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.1980799302458763,
|
|
"num_tokens": 21129143.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.2786637306213375,
|
|
"epoch": 0.9597393919144671,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004913884232775974,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.19374701976776124,
|
|
"num_tokens": 21139428.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.199481582641601,
|
|
"epoch": 0.96015703307718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004913802640579833,
|
|
"loss": 5.0655,
|
|
"mean_token_accuracy": 0.20119820535182953,
|
|
"num_tokens": 21148489.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.1523597717285154,
|
|
"epoch": 0.9605746742398931,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004913721010503722,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.19520052671432495,
|
|
"num_tokens": 21157419.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.122921371459961,
|
|
"epoch": 0.9609923154026061,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000491363934254907,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.2023424580693245,
|
|
"num_tokens": 21166628.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.185730600357056,
|
|
"epoch": 0.961409956565319,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004913557636717307,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.1961621105670929,
|
|
"num_tokens": 21176335.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.271285629272461,
|
|
"epoch": 0.9618275977280321,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004913475893009864,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.20356837809085845,
|
|
"num_tokens": 21184485.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.305818939208985,
|
|
"epoch": 0.9622452388907451,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000491339411142817,
|
|
"loss": 5.1098,
|
|
"mean_token_accuracy": 0.1950333833694458,
|
|
"num_tokens": 21194216.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.18507866859436,
|
|
"epoch": 0.962662880053458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004913312291973659,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.19253588169813157,
|
|
"num_tokens": 21203902.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.20624737739563,
|
|
"epoch": 0.963080521216171,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004913230434647762,
|
|
"loss": 5.0272,
|
|
"mean_token_accuracy": 0.2101624295115471,
|
|
"num_tokens": 21212618.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.266144752502441,
|
|
"epoch": 0.9634981623788841,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004913148539451912,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.19851963073015214,
|
|
"num_tokens": 21221820.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.1773560523986815,
|
|
"epoch": 0.963915803541597,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004913066606387544,
|
|
"loss": 5.1469,
|
|
"mean_token_accuracy": 0.18888263404369354,
|
|
"num_tokens": 21231085.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.215986490249634,
|
|
"epoch": 0.96433344470431,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000491298463545609,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.1963535025715828,
|
|
"num_tokens": 21240184.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.223777341842651,
|
|
"epoch": 0.9647510858670231,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004912902626658988,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.20060379803180695,
|
|
"num_tokens": 21249085.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.217039728164673,
|
|
"epoch": 0.965168727029736,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004912820579997672,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.20666501224040984,
|
|
"num_tokens": 21258188.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.201117610931396,
|
|
"epoch": 0.965586368192449,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004912738495473577,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.2020363837480545,
|
|
"num_tokens": 21267223.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.204726505279541,
|
|
"epoch": 0.9660040093551621,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004912656373088142,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.20087748914957046,
|
|
"num_tokens": 21276503.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.248251008987427,
|
|
"epoch": 0.9664216505178751,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004912574212842804,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.1960167795419693,
|
|
"num_tokens": 21286775.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.250494861602784,
|
|
"epoch": 0.966839291680588,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004912492014739001,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.20541923195123674,
|
|
"num_tokens": 21295956.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.1827648162841795,
|
|
"epoch": 0.967256932843301,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004912409778778173,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.19221061617136,
|
|
"num_tokens": 21305050.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.0948080062866214,
|
|
"epoch": 0.9676745740060141,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004912327504961758,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.196906778216362,
|
|
"num_tokens": 21313732.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.2102367877960205,
|
|
"epoch": 0.968092215168727,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004912245193291198,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.19872675240039825,
|
|
"num_tokens": 21322526.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.330317831039428,
|
|
"epoch": 0.96850985633144,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004912162843767932,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.18777193427085875,
|
|
"num_tokens": 21332243.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.290076112747192,
|
|
"epoch": 0.9689274974941531,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004912080456393404,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.19114756137132644,
|
|
"num_tokens": 21340827.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.238047361373901,
|
|
"epoch": 0.969345138656866,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004911998031169056,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20302327424287797,
|
|
"num_tokens": 21350506.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.1079185009002686,
|
|
"epoch": 0.969762779819579,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004911915568096328,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.20552604645490646,
|
|
"num_tokens": 21359690.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.253306722640991,
|
|
"epoch": 0.9701804209822921,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004911833067176666,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.18593323677778245,
|
|
"num_tokens": 21368953.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.418764972686768,
|
|
"epoch": 0.970598062145005,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004911750528411515,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.1897052988409996,
|
|
"num_tokens": 21379015.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.212120008468628,
|
|
"epoch": 0.971015703307718,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004911667951802318,
|
|
"loss": 4.9982,
|
|
"mean_token_accuracy": 0.20389384478330613,
|
|
"num_tokens": 21388555.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.146392488479615,
|
|
"epoch": 0.9714333444704311,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004911585337350524,
|
|
"loss": 5.1613,
|
|
"mean_token_accuracy": 0.18404101133346557,
|
|
"num_tokens": 21399011.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.22923526763916,
|
|
"epoch": 0.971850985633144,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004911502685057573,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.19762255996465683,
|
|
"num_tokens": 21408711.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.322312688827514,
|
|
"epoch": 0.972268626795857,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004911419994924918,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.18901695311069489,
|
|
"num_tokens": 21417995.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.203036832809448,
|
|
"epoch": 0.97268626795857,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004911337266954004,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.19022010415792465,
|
|
"num_tokens": 21426550.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.164367580413819,
|
|
"epoch": 0.973103909121283,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004911254501146279,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.20207127183675766,
|
|
"num_tokens": 21435396.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.0929131507873535,
|
|
"epoch": 0.973521550283996,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004911171697503193,
|
|
"loss": 4.9324,
|
|
"mean_token_accuracy": 0.21031402200460433,
|
|
"num_tokens": 21445156.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.159189653396607,
|
|
"epoch": 0.973939191446709,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004911088856026194,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.19453548192977904,
|
|
"num_tokens": 21454924.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.235403156280517,
|
|
"epoch": 0.974356832609422,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004911005976716734,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.20147766321897506,
|
|
"num_tokens": 21465062.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.131636285781861,
|
|
"epoch": 0.974774473772135,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004910923059576264,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.18579394072294236,
|
|
"num_tokens": 21473744.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.230635404586792,
|
|
"epoch": 0.975192114934848,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004910840104606234,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1954369306564331,
|
|
"num_tokens": 21482913.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.258983325958252,
|
|
"epoch": 0.975609756097561,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004910757111808097,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.1843745231628418,
|
|
"num_tokens": 21491551.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.22159514427185,
|
|
"epoch": 0.976027397260274,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004910674081183305,
|
|
"loss": 5.0346,
|
|
"mean_token_accuracy": 0.19817342311143876,
|
|
"num_tokens": 21500389.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.22039532661438,
|
|
"epoch": 0.976445038422987,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004910591012733313,
|
|
"loss": 5.111,
|
|
"mean_token_accuracy": 0.1977502539753914,
|
|
"num_tokens": 21509720.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.2274007320404055,
|
|
"epoch": 0.9768626795857,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004910507906459575,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.19756276905536652,
|
|
"num_tokens": 21519326.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.226836395263672,
|
|
"epoch": 0.977280320748413,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004910424762363545,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.1976720377802849,
|
|
"num_tokens": 21528326.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.215452671051025,
|
|
"epoch": 0.977697961911126,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000491034158044668,
|
|
"loss": 5.0548,
|
|
"mean_token_accuracy": 0.199582277238369,
|
|
"num_tokens": 21536662.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.172195053100586,
|
|
"epoch": 0.9781156030738389,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004910258360710434,
|
|
"loss": 5.0278,
|
|
"mean_token_accuracy": 0.2038472041487694,
|
|
"num_tokens": 21545222.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.24199070930481,
|
|
"epoch": 0.978533244236552,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004910175103156266,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.19624391198158264,
|
|
"num_tokens": 21554051.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.171717643737793,
|
|
"epoch": 0.978950885399265,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004910091807785632,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.2069511115550995,
|
|
"num_tokens": 21562031.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.1460693836212155,
|
|
"epoch": 0.9793685265619779,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004910008474599991,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.21157848984003066,
|
|
"num_tokens": 21570758.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.1400731086730955,
|
|
"epoch": 0.979786167724691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004909925103600801,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.20378078520298004,
|
|
"num_tokens": 21579605.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.289452171325683,
|
|
"epoch": 0.980203808887404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004909841694789523,
|
|
"loss": 5.1556,
|
|
"mean_token_accuracy": 0.18420615345239638,
|
|
"num_tokens": 21588719.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.3434230327606205,
|
|
"epoch": 0.9806214500501169,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004909758248167616,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.18786609619855882,
|
|
"num_tokens": 21598038.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.268276119232178,
|
|
"epoch": 0.98103909121283,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004909674763736542,
|
|
"loss": 5.1406,
|
|
"mean_token_accuracy": 0.18748406916856766,
|
|
"num_tokens": 21607378.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.2020691394805905,
|
|
"epoch": 0.981456732375543,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004909591241497761,
|
|
"loss": 5.0712,
|
|
"mean_token_accuracy": 0.19744382947683334,
|
|
"num_tokens": 21616470.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.272403907775879,
|
|
"epoch": 0.9818743735382559,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004909507681452736,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.18930997252464293,
|
|
"num_tokens": 21626005.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.246461296081543,
|
|
"epoch": 0.9822920147009689,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004909424083602929,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.20637580752372742,
|
|
"num_tokens": 21635620.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.084247064590454,
|
|
"epoch": 0.982709655863682,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004909340447949805,
|
|
"loss": 4.9965,
|
|
"mean_token_accuracy": 0.2055913195014,
|
|
"num_tokens": 21644846.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.129577493667602,
|
|
"epoch": 0.9831272970263949,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004909256774494827,
|
|
"loss": 4.9648,
|
|
"mean_token_accuracy": 0.19818419516086577,
|
|
"num_tokens": 21653275.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.234425020217896,
|
|
"epoch": 0.9835449381891079,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000490917306323946,
|
|
"loss": 5.0995,
|
|
"mean_token_accuracy": 0.20093469470739364,
|
|
"num_tokens": 21661709.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.252344799041748,
|
|
"epoch": 0.983962579351821,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004909089314185169,
|
|
"loss": 5.101,
|
|
"mean_token_accuracy": 0.19146595895290375,
|
|
"num_tokens": 21672409.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.257564687728882,
|
|
"epoch": 0.9843802205145339,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004909005527333421,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.20542110055685042,
|
|
"num_tokens": 21680818.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.236087417602539,
|
|
"epoch": 0.9847978616772469,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004908921702685683,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.20375936329364777,
|
|
"num_tokens": 21689572.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.142813396453858,
|
|
"epoch": 0.98521550283996,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004908837840243421,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.19214267432689666,
|
|
"num_tokens": 21698244.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.223724031448365,
|
|
"epoch": 0.9856331440026729,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004908753940008105,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.2127091482281685,
|
|
"num_tokens": 21706532.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.159911632537842,
|
|
"epoch": 0.9860507851653859,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004908670001981201,
|
|
"loss": 5.0205,
|
|
"mean_token_accuracy": 0.20355266332626343,
|
|
"num_tokens": 21715386.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.180237865447998,
|
|
"epoch": 0.986468426328099,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004908586026164182,
|
|
"loss": 5.0228,
|
|
"mean_token_accuracy": 0.19893961995840073,
|
|
"num_tokens": 21724544.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.314064025878906,
|
|
"epoch": 0.9868860674908119,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004908502012558516,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.1846147820353508,
|
|
"num_tokens": 21734453.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.215813064575196,
|
|
"epoch": 0.9873037086535249,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004908417961165674,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.1935063660144806,
|
|
"num_tokens": 21744243.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.1229248046875,
|
|
"epoch": 0.9877213498162379,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004908333871987126,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.1990435466170311,
|
|
"num_tokens": 21751843.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.199074554443359,
|
|
"epoch": 0.9881389909789509,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004908249745024347,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.1981030821800232,
|
|
"num_tokens": 21760812.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.271065616607666,
|
|
"epoch": 0.9885566321416639,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000490816558027881,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.20252378433942794,
|
|
"num_tokens": 21769460.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.15740180015564,
|
|
"epoch": 0.9889742733043769,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004908081377751985,
|
|
"loss": 4.9841,
|
|
"mean_token_accuracy": 0.2069212093949318,
|
|
"num_tokens": 21778440.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.261011838912964,
|
|
"epoch": 0.9893919144670899,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004907997137445347,
|
|
"loss": 5.1681,
|
|
"mean_token_accuracy": 0.19034019410610198,
|
|
"num_tokens": 21787708.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.185519695281982,
|
|
"epoch": 0.9898095556298029,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004907912859360373,
|
|
"loss": 5.0166,
|
|
"mean_token_accuracy": 0.1997847318649292,
|
|
"num_tokens": 21796517.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.1391078472137455,
|
|
"epoch": 0.9902271967925159,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004907828543498536,
|
|
"loss": 5.0265,
|
|
"mean_token_accuracy": 0.2024710774421692,
|
|
"num_tokens": 21805833.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.2227089405059814,
|
|
"epoch": 0.9906448379552288,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004907744189861313,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.19794497787952423,
|
|
"num_tokens": 21815953.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.237931632995606,
|
|
"epoch": 0.9910624791179419,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.19614858776330948,
|
|
"num_tokens": 21824780.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.17510495185852,
|
|
"epoch": 0.9914801202806549,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004907575369266617,
|
|
"loss": 5.0499,
|
|
"mean_token_accuracy": 0.19313737154006957,
|
|
"num_tokens": 21834514.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.250283336639404,
|
|
"epoch": 0.9918977614433678,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004907490902312099,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20352939665317535,
|
|
"num_tokens": 21844090.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.19174108505249,
|
|
"epoch": 0.9923154026060809,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004907406397588106,
|
|
"loss": 5.0493,
|
|
"mean_token_accuracy": 0.2015935465693474,
|
|
"num_tokens": 21852982.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.221615839004516,
|
|
"epoch": 0.9927330437687939,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004907321855096117,
|
|
"loss": 5.1369,
|
|
"mean_token_accuracy": 0.18960328102111818,
|
|
"num_tokens": 21862734.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.364752626419067,
|
|
"epoch": 0.9931506849315068,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004907237274837613,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.19494061917066574,
|
|
"num_tokens": 21871927.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.1199297428131105,
|
|
"epoch": 0.9935683260942199,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004907152656814072,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.20188662260770798,
|
|
"num_tokens": 21881409.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.221092414855957,
|
|
"epoch": 0.9939859672569329,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004907068001026978,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.2049349531531334,
|
|
"num_tokens": 21890324.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.215235471725464,
|
|
"epoch": 0.9944036084196458,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004906983307477813,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.2050636351108551,
|
|
"num_tokens": 21898352.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.168635559082031,
|
|
"epoch": 0.9948212495823588,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004906898576168057,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.20151031911373138,
|
|
"num_tokens": 21906972.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.253898000717163,
|
|
"epoch": 0.9952388907450719,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004906813807099197,
|
|
"loss": 5.1078,
|
|
"mean_token_accuracy": 0.19511166960000992,
|
|
"num_tokens": 21916304.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.229467058181763,
|
|
"epoch": 0.9956565319077848,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004906729000272714,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.19260700941085815,
|
|
"num_tokens": 21926393.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.276017665863037,
|
|
"epoch": 0.9960741730704978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004906644155690095,
|
|
"loss": 5.043,
|
|
"mean_token_accuracy": 0.19708795547485353,
|
|
"num_tokens": 21935657.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.30380859375,
|
|
"epoch": 0.9964918142332109,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004906559273352823,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.19625190198421477,
|
|
"num_tokens": 21945170.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.218558120727539,
|
|
"epoch": 0.9969094553959238,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004906474353262386,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.19573179632425308,
|
|
"num_tokens": 21954043.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.339192914962768,
|
|
"epoch": 0.9973270965586368,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004906389395420269,
|
|
"loss": 5.2255,
|
|
"mean_token_accuracy": 0.18686571717262268,
|
|
"num_tokens": 21963716.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.413056135177612,
|
|
"epoch": 0.9977447377213499,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000490630439982796,
|
|
"loss": 5.2052,
|
|
"mean_token_accuracy": 0.18740773797035218,
|
|
"num_tokens": 21973059.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.217510223388672,
|
|
"epoch": 0.9981623788840628,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004906219366486947,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.18914537727832795,
|
|
"num_tokens": 21983189.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.200915908813476,
|
|
"epoch": 0.9985800200467758,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004906134295398719,
|
|
"loss": 4.9864,
|
|
"mean_token_accuracy": 0.20520598143339158,
|
|
"num_tokens": 21992124.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.149120664596557,
|
|
"epoch": 0.9989976612094889,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004906049186564764,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.20018115490674973,
|
|
"num_tokens": 22002075.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.185933589935303,
|
|
"epoch": 0.9994153023722018,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004905964039986574,
|
|
"loss": 5.1241,
|
|
"mean_token_accuracy": 0.1803090453147888,
|
|
"num_tokens": 22010831.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.278057432174682,
|
|
"epoch": 0.9998329435349148,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004905878855665637,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.19286288917064667,
|
|
"num_tokens": 22020270.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.303911781311035,
|
|
"epoch": 1.0002505846976277,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004905793633603446,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.1979333996772766,
|
|
"num_tokens": 22030413.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.16483359336853,
|
|
"epoch": 1.0006682258603408,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004905708373801492,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.20012013018131256,
|
|
"num_tokens": 22040420.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.207770442962646,
|
|
"epoch": 1.0010858670230538,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004905623076261269,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.1999570295214653,
|
|
"num_tokens": 22049901.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.2084156513214115,
|
|
"epoch": 1.0015035081857668,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000490553774098427,
|
|
"loss": 4.9804,
|
|
"mean_token_accuracy": 0.19033000320196153,
|
|
"num_tokens": 22058939.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.133357000350952,
|
|
"epoch": 1.0019211493484799,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004905452367971986,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.21050990521907806,
|
|
"num_tokens": 22067553.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.148767614364624,
|
|
"epoch": 1.0023387905111927,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004905366957225916,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.19771587252616882,
|
|
"num_tokens": 22076264.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0023387905111927,
|
|
"eval_entropy": 5.040127530539347,
|
|
"eval_loss": 5.047482967376709,
|
|
"eval_mean_token_accuracy": 0.20809941453667066,
|
|
"eval_num_tokens": 22076264.0,
|
|
"eval_runtime": 27.8658,
|
|
"eval_samples_per_second": 1355.176,
|
|
"eval_steps_per_second": 169.419,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.169580554962158,
|
|
"epoch": 1.0027564316739057,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004905281508747552,
|
|
"loss": 4.8675,
|
|
"mean_token_accuracy": 0.21027906537055968,
|
|
"num_tokens": 22085033.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.161483812332153,
|
|
"epoch": 1.0031740728366187,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004905196022538391,
|
|
"loss": 5.0155,
|
|
"mean_token_accuracy": 0.19453056305646896,
|
|
"num_tokens": 22094619.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.228329372406006,
|
|
"epoch": 1.0035917139993318,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000490511049859993,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.20216394513845443,
|
|
"num_tokens": 22103611.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.27105746269226,
|
|
"epoch": 1.0040093551620448,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004905024936933664,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.1958231121301651,
|
|
"num_tokens": 22112478.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.13277850151062,
|
|
"epoch": 1.0044269963247578,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004904939337541093,
|
|
"loss": 4.8915,
|
|
"mean_token_accuracy": 0.20297117084264754,
|
|
"num_tokens": 22121969.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.204805755615235,
|
|
"epoch": 1.0048446374874707,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004904853700423716,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20368643403053283,
|
|
"num_tokens": 22131241.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.211204957962036,
|
|
"epoch": 1.0052622786501837,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004904768025583031,
|
|
"loss": 4.9736,
|
|
"mean_token_accuracy": 0.20170041024684907,
|
|
"num_tokens": 22140473.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.18708381652832,
|
|
"epoch": 1.0056799198128967,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004904682313020537,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.19304264485836028,
|
|
"num_tokens": 22150071.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.315757369995117,
|
|
"epoch": 1.0060975609756098,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004904596562737737,
|
|
"loss": 5.1198,
|
|
"mean_token_accuracy": 0.19075191915035247,
|
|
"num_tokens": 22159665.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.163830184936524,
|
|
"epoch": 1.0065152021383228,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000490451077473613,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20455554127693176,
|
|
"num_tokens": 22168856.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.133738899230957,
|
|
"epoch": 1.0069328433010358,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004904424949017218,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.1988204911351204,
|
|
"num_tokens": 22177550.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.186951541900635,
|
|
"epoch": 1.0073504844637486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004904339085582504,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.21347827911376954,
|
|
"num_tokens": 22186839.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.282240104675293,
|
|
"epoch": 1.0077681256264617,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004904253184433491,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.19386889189481735,
|
|
"num_tokens": 22196865.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.134208154678345,
|
|
"epoch": 1.0081857667891747,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004904167245571684,
|
|
"loss": 4.9216,
|
|
"mean_token_accuracy": 0.20560819208621978,
|
|
"num_tokens": 22205140.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.072881841659546,
|
|
"epoch": 1.0086034079518877,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004904081268998586,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.20570905208587648,
|
|
"num_tokens": 22214846.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.169860172271728,
|
|
"epoch": 1.0090210491146008,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004903995254715702,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.19393994361162187,
|
|
"num_tokens": 22222984.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.253694105148315,
|
|
"epoch": 1.0094386902773138,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004903909202724539,
|
|
"loss": 5.0041,
|
|
"mean_token_accuracy": 0.1973405286669731,
|
|
"num_tokens": 22231995.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.1990556716918945,
|
|
"epoch": 1.0098563314400266,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004903823113026602,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.21040778309106828,
|
|
"num_tokens": 22240354.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.2165862083435055,
|
|
"epoch": 1.0102739726027397,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00049037369856234,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.19550489634275436,
|
|
"num_tokens": 22249866.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.243975257873535,
|
|
"epoch": 1.0106916137654527,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004903650820516438,
|
|
"loss": 5.0297,
|
|
"mean_token_accuracy": 0.19310591667890548,
|
|
"num_tokens": 22258837.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.196428728103638,
|
|
"epoch": 1.0111092549281657,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004903564617707227,
|
|
"loss": 4.9168,
|
|
"mean_token_accuracy": 0.20485285073518752,
|
|
"num_tokens": 22268035.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.109891319274903,
|
|
"epoch": 1.0115268960908788,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004903478377197275,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.20405521094799042,
|
|
"num_tokens": 22277251.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.001167345046997,
|
|
"epoch": 1.0119445372535918,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004903392098988092,
|
|
"loss": 4.8788,
|
|
"mean_token_accuracy": 0.20342124700546266,
|
|
"num_tokens": 22286269.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.145901727676391,
|
|
"epoch": 1.0123621784163046,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004903305783081188,
|
|
"loss": 4.9023,
|
|
"mean_token_accuracy": 0.20229766219854356,
|
|
"num_tokens": 22294671.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.104437685012817,
|
|
"epoch": 1.0127798195790176,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004903219429478075,
|
|
"loss": 4.9051,
|
|
"mean_token_accuracy": 0.20748473405838014,
|
|
"num_tokens": 22304448.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.224649906158447,
|
|
"epoch": 1.0131974607417307,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004903133038180263,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19456953555345535,
|
|
"num_tokens": 22314425.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.1249021053314205,
|
|
"epoch": 1.0136151019044437,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004903046609189266,
|
|
"loss": 4.8811,
|
|
"mean_token_accuracy": 0.20105402171611786,
|
|
"num_tokens": 22324390.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.1608538150787355,
|
|
"epoch": 1.0140327430671567,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004902960142506597,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.2045635387301445,
|
|
"num_tokens": 22333274.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.1786257266998295,
|
|
"epoch": 1.0144503842298698,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004902873638133768,
|
|
"loss": 4.9867,
|
|
"mean_token_accuracy": 0.20626837015151978,
|
|
"num_tokens": 22342480.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.132463169097901,
|
|
"epoch": 1.0148680253925826,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004902787096072296,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.2083053007721901,
|
|
"num_tokens": 22351105.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.072145700454712,
|
|
"epoch": 1.0152856665552956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004902700516323693,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.21179743558168412,
|
|
"num_tokens": 22360567.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.177220869064331,
|
|
"epoch": 1.0157033077180087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004902613898889477,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.19947971999645234,
|
|
"num_tokens": 22370140.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.127175760269165,
|
|
"epoch": 1.0161209488807217,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004902527243771164,
|
|
"loss": 4.7604,
|
|
"mean_token_accuracy": 0.21180636435747147,
|
|
"num_tokens": 22378676.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.150779676437378,
|
|
"epoch": 1.0165385900434347,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000490244055097027,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.19429712295532225,
|
|
"num_tokens": 22387411.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.177250909805298,
|
|
"epoch": 1.0169562312061478,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004902353820488314,
|
|
"loss": 5.0324,
|
|
"mean_token_accuracy": 0.19497199803590776,
|
|
"num_tokens": 22397023.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.129194545745849,
|
|
"epoch": 1.0173738723688606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004902267052326812,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.2021426558494568,
|
|
"num_tokens": 22406730.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.274524354934693,
|
|
"epoch": 1.0177915135315736,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004902180246487285,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.19656931459903718,
|
|
"num_tokens": 22416920.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.166518926620483,
|
|
"epoch": 1.0182091546942866,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004902093402971254,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19672542363405227,
|
|
"num_tokens": 22426073.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.256448125839233,
|
|
"epoch": 1.0186267958569997,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004902006521780236,
|
|
"loss": 5.0334,
|
|
"mean_token_accuracy": 0.2026686891913414,
|
|
"num_tokens": 22436291.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.068593072891235,
|
|
"epoch": 1.0190444370197127,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004901919602915754,
|
|
"loss": 4.9601,
|
|
"mean_token_accuracy": 0.20481967628002168,
|
|
"num_tokens": 22446053.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.178639125823975,
|
|
"epoch": 1.0194620781824257,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004901832646379328,
|
|
"loss": 4.9274,
|
|
"mean_token_accuracy": 0.20121289789676666,
|
|
"num_tokens": 22455474.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.2100988864898685,
|
|
"epoch": 1.0198797193451385,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004901745652172483,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.20680596679449081,
|
|
"num_tokens": 22464953.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.172916412353516,
|
|
"epoch": 1.0202973605078516,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000490165862029674,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.1944560796022415,
|
|
"num_tokens": 22474076.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.130919408798218,
|
|
"epoch": 1.0207150016705646,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004901571550753622,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.201105098426342,
|
|
"num_tokens": 22483128.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.211022424697876,
|
|
"epoch": 1.0211326428332776,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004901484443544655,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.20136988162994385,
|
|
"num_tokens": 22492239.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.2796038627624515,
|
|
"epoch": 1.0215502839959907,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004901397298671362,
|
|
"loss": 5.1259,
|
|
"mean_token_accuracy": 0.18717017769813538,
|
|
"num_tokens": 22500996.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.226589727401733,
|
|
"epoch": 1.0219679251587037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004901310116135271,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.19812116622924805,
|
|
"num_tokens": 22510524.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.1934960842132565,
|
|
"epoch": 1.0223855663214167,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004901222895937905,
|
|
"loss": 4.9661,
|
|
"mean_token_accuracy": 0.2000878408551216,
|
|
"num_tokens": 22519499.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.102998924255371,
|
|
"epoch": 1.0228032074841296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004901135638080796,
|
|
"loss": 4.8471,
|
|
"mean_token_accuracy": 0.2099151149392128,
|
|
"num_tokens": 22528380.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.2012715339660645,
|
|
"epoch": 1.0232208486468426,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004901048342565465,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.19413138777017594,
|
|
"num_tokens": 22537488.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.20526533126831,
|
|
"epoch": 1.0236384898095556,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004900961009393445,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.20385019332170487,
|
|
"num_tokens": 22547093.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.104848146438599,
|
|
"epoch": 1.0240561309722687,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004900873638566263,
|
|
"loss": 4.8992,
|
|
"mean_token_accuracy": 0.2035337969660759,
|
|
"num_tokens": 22555996.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.170571279525757,
|
|
"epoch": 1.0244737721349817,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000490078623008545,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.1936105325818062,
|
|
"num_tokens": 22565582.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.220041990280151,
|
|
"epoch": 1.0248914132976945,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004900698783952533,
|
|
"loss": 5.0201,
|
|
"mean_token_accuracy": 0.19505415558815004,
|
|
"num_tokens": 22575181.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.267757701873779,
|
|
"epoch": 1.0253090544604075,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004900611300169048,
|
|
"loss": 5.0239,
|
|
"mean_token_accuracy": 0.19922152310609817,
|
|
"num_tokens": 22584799.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.139433813095093,
|
|
"epoch": 1.0257266956231206,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004900523778736521,
|
|
"loss": 4.8303,
|
|
"mean_token_accuracy": 0.2111017256975174,
|
|
"num_tokens": 22593235.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.120855760574341,
|
|
"epoch": 1.0261443367858336,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004900436219656488,
|
|
"loss": 5.0531,
|
|
"mean_token_accuracy": 0.1971993088722229,
|
|
"num_tokens": 22603435.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.1906991481781,
|
|
"epoch": 1.0265619779485466,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000490034862293048,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.19752491116523743,
|
|
"num_tokens": 22612739.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.1834887027740475,
|
|
"epoch": 1.0269796191112597,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004900260988560031,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.19557403326034545,
|
|
"num_tokens": 22622633.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.148898315429688,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004900173316546675,
|
|
"loss": 4.8792,
|
|
"mean_token_accuracy": 0.20551477670669555,
|
|
"num_tokens": 22631428.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.249334478378296,
|
|
"epoch": 1.0278149014366855,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004900085606891947,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.20044250041246414,
|
|
"num_tokens": 22639557.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.207519769668579,
|
|
"epoch": 1.0282325425993986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004899997859597382,
|
|
"loss": 4.9854,
|
|
"mean_token_accuracy": 0.20194839239120482,
|
|
"num_tokens": 22648134.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.122716426849365,
|
|
"epoch": 1.0286501837621116,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004899910074664518,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.20825906693935395,
|
|
"num_tokens": 22657083.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.2278913974761965,
|
|
"epoch": 1.0290678249248246,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004899822252094889,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.20374002158641816,
|
|
"num_tokens": 22666724.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.184357690811157,
|
|
"epoch": 1.0294854660875377,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004899734391890034,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.19929776936769486,
|
|
"num_tokens": 22675955.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.184584522247315,
|
|
"epoch": 1.0299031072502507,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004899646494051491,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.19981490075588226,
|
|
"num_tokens": 22686838.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.269491672515869,
|
|
"epoch": 1.0303207484129635,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004899558558580798,
|
|
"loss": 5.0867,
|
|
"mean_token_accuracy": 0.19477163702249528,
|
|
"num_tokens": 22696257.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.096351575851441,
|
|
"epoch": 1.0307383895756765,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004899470585479495,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.2018014132976532,
|
|
"num_tokens": 22705726.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.156038856506347,
|
|
"epoch": 1.0311560307383896,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004899382574749124,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.19875162541866304,
|
|
"num_tokens": 22714765.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.237843799591064,
|
|
"epoch": 1.0315736719011026,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004899294526391221,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.19588534384965897,
|
|
"num_tokens": 22723423.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.195680475234985,
|
|
"epoch": 1.0319913130638156,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004899206440407332,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.19669269323348998,
|
|
"num_tokens": 22733276.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.1338584423065186,
|
|
"epoch": 1.0324089542265287,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004899118316798996,
|
|
"loss": 4.9623,
|
|
"mean_token_accuracy": 0.20780497193336486,
|
|
"num_tokens": 22742422.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.145673084259033,
|
|
"epoch": 1.0328265953892415,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004899030155567759,
|
|
"loss": 4.9209,
|
|
"mean_token_accuracy": 0.19978038668632508,
|
|
"num_tokens": 22751649.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.14819655418396,
|
|
"epoch": 1.0332442365519545,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000489894195671516,
|
|
"loss": 5.0577,
|
|
"mean_token_accuracy": 0.19188131839036943,
|
|
"num_tokens": 22760411.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.252345848083496,
|
|
"epoch": 1.0336618777146676,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004898853720242747,
|
|
"loss": 5.044,
|
|
"mean_token_accuracy": 0.19762900173664094,
|
|
"num_tokens": 22769289.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.2134363651275635,
|
|
"epoch": 1.0340795188773806,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004898765446152062,
|
|
"loss": 4.9581,
|
|
"mean_token_accuracy": 0.20036045014858245,
|
|
"num_tokens": 22778988.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.176703548431396,
|
|
"epoch": 1.0344971600400936,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004898677134444652,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.19614764750003816,
|
|
"num_tokens": 22788115.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.244096040725708,
|
|
"epoch": 1.0349148012028067,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004898588785122063,
|
|
"loss": 5.045,
|
|
"mean_token_accuracy": 0.20332542657852173,
|
|
"num_tokens": 22797840.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.1602925777435305,
|
|
"epoch": 1.0353324423655195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004898500398185841,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.20884474366903305,
|
|
"num_tokens": 22805947.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.168059778213501,
|
|
"epoch": 1.0357500835282325,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004898411973637532,
|
|
"loss": 4.9775,
|
|
"mean_token_accuracy": 0.20047039836645125,
|
|
"num_tokens": 22816104.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.200162935256958,
|
|
"epoch": 1.0361677246909455,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004898323511478686,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.20200901329517365,
|
|
"num_tokens": 22824994.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.186477613449097,
|
|
"epoch": 1.0365853658536586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004898235011710851,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.19385089129209518,
|
|
"num_tokens": 22834649.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.095633172988892,
|
|
"epoch": 1.0370030070163716,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004898146474335577,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.21230559051036835,
|
|
"num_tokens": 22843060.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.148401212692261,
|
|
"epoch": 1.0374206481790846,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004898057899354412,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.20681700855493546,
|
|
"num_tokens": 22852429.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.120256090164185,
|
|
"epoch": 1.0378382893417974,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000489796928676891,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.2054611250758171,
|
|
"num_tokens": 22861170.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.110870981216431,
|
|
"epoch": 1.0382559305045105,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004897880636580618,
|
|
"loss": 4.9188,
|
|
"mean_token_accuracy": 0.20782249122858049,
|
|
"num_tokens": 22870030.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.111605072021485,
|
|
"epoch": 1.0386735716672235,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000489779194879109,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.20994281023740768,
|
|
"num_tokens": 22878728.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.214935398101806,
|
|
"epoch": 1.0390912128299366,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000489770322340188,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.19354919493198394,
|
|
"num_tokens": 22887625.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.062684822082519,
|
|
"epoch": 1.0395088539926496,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004897614460414539,
|
|
"loss": 4.805,
|
|
"mean_token_accuracy": 0.2110498443245888,
|
|
"num_tokens": 22896791.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.134312391281128,
|
|
"epoch": 1.0399264951553626,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004897525659830623,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.19939010292291642,
|
|
"num_tokens": 22907228.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.0330335140228275,
|
|
"epoch": 1.0403441363180754,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004897436821651683,
|
|
"loss": 4.8197,
|
|
"mean_token_accuracy": 0.21877533346414565,
|
|
"num_tokens": 22915108.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.030098867416382,
|
|
"epoch": 1.0407617774807885,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004897347945879278,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.21331406235694886,
|
|
"num_tokens": 22924092.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.0984215259552,
|
|
"epoch": 1.0411794186435015,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004897259032514963,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.20271498560905457,
|
|
"num_tokens": 22932285.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.2102437019348145,
|
|
"epoch": 1.0415970598062145,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004897170081560292,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.20671599060297013,
|
|
"num_tokens": 22940727.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.205721664428711,
|
|
"epoch": 1.0420147009689276,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004897081093016827,
|
|
"loss": 5.0261,
|
|
"mean_token_accuracy": 0.19765979200601577,
|
|
"num_tokens": 22949678.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.155996799468994,
|
|
"epoch": 1.0424323421316406,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004896992066886121,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.1960259646177292,
|
|
"num_tokens": 22959295.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.179384565353393,
|
|
"epoch": 1.0428499832943534,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004896903003169735,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.20502911508083344,
|
|
"num_tokens": 22968883.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.201585149765014,
|
|
"epoch": 1.0432676244570664,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004896813901869229,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.19676454067230226,
|
|
"num_tokens": 22978199.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.1900026321411135,
|
|
"epoch": 1.0436852656197795,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004896724762986159,
|
|
"loss": 4.9785,
|
|
"mean_token_accuracy": 0.204557004570961,
|
|
"num_tokens": 22987236.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.165955305099487,
|
|
"epoch": 1.0441029067824925,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004896635586522089,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.20499594360589982,
|
|
"num_tokens": 22996293.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.14666337966919,
|
|
"epoch": 1.0445205479452055,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004896546372478581,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.2016330197453499,
|
|
"num_tokens": 23006415.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.1992104053497314,
|
|
"epoch": 1.0449381891079186,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004896457120857192,
|
|
"loss": 5.0383,
|
|
"mean_token_accuracy": 0.19809141457080842,
|
|
"num_tokens": 23015819.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.17161922454834,
|
|
"epoch": 1.0453558302706314,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000489636783165949,
|
|
"loss": 4.8908,
|
|
"mean_token_accuracy": 0.2102263629436493,
|
|
"num_tokens": 23024206.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.228085517883301,
|
|
"epoch": 1.0457734714333444,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004896278504887033,
|
|
"loss": 5.0947,
|
|
"mean_token_accuracy": 0.1936309427022934,
|
|
"num_tokens": 23034003.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.21875147819519,
|
|
"epoch": 1.0461911125960575,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000489618914054139,
|
|
"loss": 5.0276,
|
|
"mean_token_accuracy": 0.19882651120424272,
|
|
"num_tokens": 23043514.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.1769670963287355,
|
|
"epoch": 1.0466087537587705,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000489609973862412,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.19608525633811952,
|
|
"num_tokens": 23053029.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.20466980934143,
|
|
"epoch": 1.0470263949214835,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004896010299136793,
|
|
"loss": 5.0187,
|
|
"mean_token_accuracy": 0.1988625407218933,
|
|
"num_tokens": 23062465.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.14296326637268,
|
|
"epoch": 1.0474440360841966,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004895920822080972,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.2063967302441597,
|
|
"num_tokens": 23071448.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.2012077331542965,
|
|
"epoch": 1.0478616772469094,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004895831307458224,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.1977296620607376,
|
|
"num_tokens": 23081882.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.236787366867065,
|
|
"epoch": 1.0482793184096224,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004895741755270115,
|
|
"loss": 5.0087,
|
|
"mean_token_accuracy": 0.20333647727966309,
|
|
"num_tokens": 23090723.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.0840507507324215,
|
|
"epoch": 1.0486969595723354,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004895652165518215,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21415795981884003,
|
|
"num_tokens": 23099246.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.086436223983765,
|
|
"epoch": 1.0491146007350485,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004895562538204091,
|
|
"loss": 4.9332,
|
|
"mean_token_accuracy": 0.20905129760503768,
|
|
"num_tokens": 23107538.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.183541536331177,
|
|
"epoch": 1.0495322418977615,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004895472873329311,
|
|
"loss": 5.0162,
|
|
"mean_token_accuracy": 0.20389313548803328,
|
|
"num_tokens": 23116996.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.117693519592285,
|
|
"epoch": 1.0499498830604745,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004895383170895447,
|
|
"loss": 4.8888,
|
|
"mean_token_accuracy": 0.2070747897028923,
|
|
"num_tokens": 23126778.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.198449373245239,
|
|
"epoch": 1.0503675242231874,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004895293430904067,
|
|
"loss": 4.9951,
|
|
"mean_token_accuracy": 0.20156582742929458,
|
|
"num_tokens": 23135929.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.150644683837891,
|
|
"epoch": 1.0507851653859004,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004895203653356745,
|
|
"loss": 4.9307,
|
|
"mean_token_accuracy": 0.20446724593639373,
|
|
"num_tokens": 23144369.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.1575178623199465,
|
|
"epoch": 1.0512028065486134,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004895113838255049,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.20366470664739608,
|
|
"num_tokens": 23152813.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.131381559371948,
|
|
"epoch": 1.0516204477113265,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004895023985600555,
|
|
"loss": 4.9579,
|
|
"mean_token_accuracy": 0.19924381673336028,
|
|
"num_tokens": 23161826.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.1752588748931885,
|
|
"epoch": 1.0520380888740395,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004894934095394832,
|
|
"loss": 4.9146,
|
|
"mean_token_accuracy": 0.20176558792591096,
|
|
"num_tokens": 23170757.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.201378583908081,
|
|
"epoch": 1.0524557300367525,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004894844167639458,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.1987537831068039,
|
|
"num_tokens": 23179348.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.161959028244018,
|
|
"epoch": 1.0528733711994653,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004894754202336004,
|
|
"loss": 5.0132,
|
|
"mean_token_accuracy": 0.1949801579117775,
|
|
"num_tokens": 23188643.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.033377742767334,
|
|
"epoch": 1.0532910123621784,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004894664199486047,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.19819177240133284,
|
|
"num_tokens": 23197595.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.175791883468628,
|
|
"epoch": 1.0537086535248914,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004894574159091161,
|
|
"loss": 4.898,
|
|
"mean_token_accuracy": 0.20845069587230683,
|
|
"num_tokens": 23206463.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.228186511993409,
|
|
"epoch": 1.0541262946876044,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004894484081152922,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.19057111740112304,
|
|
"num_tokens": 23215740.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.191231679916382,
|
|
"epoch": 1.0545439358503175,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004894393965672909,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.19950238466262818,
|
|
"num_tokens": 23226046.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.2268517971038815,
|
|
"epoch": 1.0549615770130305,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004894303812652698,
|
|
"loss": 4.9995,
|
|
"mean_token_accuracy": 0.19355977326631546,
|
|
"num_tokens": 23234905.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.0929797172546385,
|
|
"epoch": 1.0553792181757433,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004894213622093867,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.20581526756286622,
|
|
"num_tokens": 23243392.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.1611052513122555,
|
|
"epoch": 1.0557968593384564,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004894123393997997,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.20097920447587966,
|
|
"num_tokens": 23253276.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.077817010879516,
|
|
"epoch": 1.0562145005011694,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004894033128366665,
|
|
"loss": 4.8916,
|
|
"mean_token_accuracy": 0.20813636034727095,
|
|
"num_tokens": 23262336.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.143207693099976,
|
|
"epoch": 1.0566321416638824,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004893942825201453,
|
|
"loss": 5.0021,
|
|
"mean_token_accuracy": 0.199725379049778,
|
|
"num_tokens": 23272103.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.245752000808716,
|
|
"epoch": 1.0570497828265955,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000489385248450394,
|
|
"loss": 5.0615,
|
|
"mean_token_accuracy": 0.2002743437886238,
|
|
"num_tokens": 23281253.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.2179036140441895,
|
|
"epoch": 1.0574674239893085,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000489376210627571,
|
|
"loss": 4.972,
|
|
"mean_token_accuracy": 0.20117961317300798,
|
|
"num_tokens": 23289920.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.1518162250518795,
|
|
"epoch": 1.0578850651520213,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004893671690518343,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.19979559779167175,
|
|
"num_tokens": 23299052.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.176765060424804,
|
|
"epoch": 1.0583027063147343,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004893581237233423,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.20392135232686998,
|
|
"num_tokens": 23307782.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.243820905685425,
|
|
"epoch": 1.0587203474774474,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004893490746422533,
|
|
"loss": 5.0096,
|
|
"mean_token_accuracy": 0.2029566064476967,
|
|
"num_tokens": 23317302.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.147712993621826,
|
|
"epoch": 1.0591379886401604,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004893400218087258,
|
|
"loss": 4.8902,
|
|
"mean_token_accuracy": 0.21001974046230315,
|
|
"num_tokens": 23325899.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.19874677658081,
|
|
"epoch": 1.0595556298028734,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004893309652229183,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.20388401448726653,
|
|
"num_tokens": 23335121.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.180070447921753,
|
|
"epoch": 1.0599732709655865,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004893219048849891,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.1953381896018982,
|
|
"num_tokens": 23345377.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.182038450241089,
|
|
"epoch": 1.0603909121282993,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004893128407950971,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.19701989293098449,
|
|
"num_tokens": 23353963.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.135223150253296,
|
|
"epoch": 1.0608085532910123,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004893037729534007,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.21136902570724486,
|
|
"num_tokens": 23363744.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.162247896194458,
|
|
"epoch": 1.0612261944537253,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004892947013600589,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.20126497596502305,
|
|
"num_tokens": 23372241.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.126316261291504,
|
|
"epoch": 1.0616438356164384,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004892856260152304,
|
|
"loss": 4.9482,
|
|
"mean_token_accuracy": 0.20426203459501266,
|
|
"num_tokens": 23380733.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.222818422317505,
|
|
"epoch": 1.0620614767791514,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000489276546919074,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.1943354457616806,
|
|
"num_tokens": 23389916.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.143852233886719,
|
|
"epoch": 1.0624791179418644,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004892674640717488,
|
|
"loss": 4.9281,
|
|
"mean_token_accuracy": 0.20567619502544404,
|
|
"num_tokens": 23398394.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.2402184963226315,
|
|
"epoch": 1.0628967591045773,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004892583774734138,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.19064523577690123,
|
|
"num_tokens": 23408294.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.154877853393555,
|
|
"epoch": 1.0633144002672903,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004892492871242278,
|
|
"loss": 5.0173,
|
|
"mean_token_accuracy": 0.19271493703126907,
|
|
"num_tokens": 23417301.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.185716199874878,
|
|
"epoch": 1.0637320414300033,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004892401930243504,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.2042860820889473,
|
|
"num_tokens": 23426992.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.145590209960938,
|
|
"epoch": 1.0641496825927164,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004892310951739404,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.2076074466109276,
|
|
"num_tokens": 23435480.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.196811962127685,
|
|
"epoch": 1.0645673237554294,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004892219935731571,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.19965091794729234,
|
|
"num_tokens": 23444436.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.114441728591919,
|
|
"epoch": 1.0649849649181424,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048921288822216,
|
|
"loss": 4.8846,
|
|
"mean_token_accuracy": 0.20941781401634216,
|
|
"num_tokens": 23452913.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.035728788375854,
|
|
"epoch": 1.0654026060808552,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004892037791211086,
|
|
"loss": 4.927,
|
|
"mean_token_accuracy": 0.2055075079202652,
|
|
"num_tokens": 23462078.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.134254360198975,
|
|
"epoch": 1.0658202472435683,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004891946662701621,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.206013286113739,
|
|
"num_tokens": 23470224.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.126784563064575,
|
|
"epoch": 1.0662378884062813,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004891855496694801,
|
|
"loss": 4.9499,
|
|
"mean_token_accuracy": 0.1985659956932068,
|
|
"num_tokens": 23478820.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.206686544418335,
|
|
"epoch": 1.0666555295689943,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004891764293192222,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.1961066633462906,
|
|
"num_tokens": 23488396.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.253154039382935,
|
|
"epoch": 1.0670731707317074,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004891673052195482,
|
|
"loss": 5.0355,
|
|
"mean_token_accuracy": 0.19774702787399293,
|
|
"num_tokens": 23497778.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.296729707717896,
|
|
"epoch": 1.0674908118944204,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004891581773706177,
|
|
"loss": 5.1552,
|
|
"mean_token_accuracy": 0.1900760069489479,
|
|
"num_tokens": 23506637.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.218043994903565,
|
|
"epoch": 1.0679084530571332,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004891490457725906,
|
|
"loss": 5.0379,
|
|
"mean_token_accuracy": 0.19942990094423294,
|
|
"num_tokens": 23515830.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.1818756580352785,
|
|
"epoch": 1.0683260942198463,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004891399104256266,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.20411134958267213,
|
|
"num_tokens": 23525646.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.249075269699096,
|
|
"epoch": 1.0687437353825593,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004891307713298857,
|
|
"loss": 5.0111,
|
|
"mean_token_accuracy": 0.19879214763641356,
|
|
"num_tokens": 23535319.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.150713062286377,
|
|
"epoch": 1.0691613765452723,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000489121628485528,
|
|
"loss": 5.0117,
|
|
"mean_token_accuracy": 0.1978086844086647,
|
|
"num_tokens": 23544275.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.141674470901489,
|
|
"epoch": 1.0695790177079854,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004891124818927133,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.20023730844259263,
|
|
"num_tokens": 23553782.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.100135612487793,
|
|
"epoch": 1.0699966588706984,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004891033315516019,
|
|
"loss": 4.8026,
|
|
"mean_token_accuracy": 0.21267443299293518,
|
|
"num_tokens": 23562718.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.17625880241394,
|
|
"epoch": 1.0704143000334112,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004890941774623541,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.1976195678114891,
|
|
"num_tokens": 23572374.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.121626281738282,
|
|
"epoch": 1.0708319411961242,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004890850196251299,
|
|
"loss": 4.8892,
|
|
"mean_token_accuracy": 0.20726636946201324,
|
|
"num_tokens": 23581227.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.109693765640259,
|
|
"epoch": 1.0712495823588373,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004890758580400898,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2020815595984459,
|
|
"num_tokens": 23591120.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.123488092422486,
|
|
"epoch": 1.0716672235215503,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004890666927073941,
|
|
"loss": 4.9118,
|
|
"mean_token_accuracy": 0.200987546145916,
|
|
"num_tokens": 23599584.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.171791982650757,
|
|
"epoch": 1.0720848646842633,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004890575236272032,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.1995101511478424,
|
|
"num_tokens": 23609479.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.181425142288208,
|
|
"epoch": 1.0725025058469764,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004890483507996778,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.2066161513328552,
|
|
"num_tokens": 23618662.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.2633469581604,
|
|
"epoch": 1.0729201470096892,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004890391742249783,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.19162315130233765,
|
|
"num_tokens": 23628268.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.1647422313690186,
|
|
"epoch": 1.0733377881724022,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004890299939032654,
|
|
"loss": 4.9685,
|
|
"mean_token_accuracy": 0.20322999358177185,
|
|
"num_tokens": 23637538.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.1583905696868895,
|
|
"epoch": 1.0737554293351153,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004890208098346999,
|
|
"loss": 5.093,
|
|
"mean_token_accuracy": 0.19112809300422667,
|
|
"num_tokens": 23647425.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.262768936157227,
|
|
"epoch": 1.0741730704978283,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004890116220194425,
|
|
"loss": 5.1012,
|
|
"mean_token_accuracy": 0.19417205154895784,
|
|
"num_tokens": 23656310.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.192828512191772,
|
|
"epoch": 1.0745907116605413,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000489002430457654,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.20072500109672547,
|
|
"num_tokens": 23664658.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.248310613632202,
|
|
"epoch": 1.0750083528232544,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004889932351494954,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.2046247497200966,
|
|
"num_tokens": 23674396.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.221344089508056,
|
|
"epoch": 1.0754259939859672,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004889840360951277,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.20872651189565658,
|
|
"num_tokens": 23682549.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.135237121582032,
|
|
"epoch": 1.0758436351486802,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004889748332947118,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.20462993681430816,
|
|
"num_tokens": 23692334.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.170808744430542,
|
|
"epoch": 1.0762612763113932,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004889656267484089,
|
|
"loss": 4.9728,
|
|
"mean_token_accuracy": 0.2003317207098007,
|
|
"num_tokens": 23702081.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.2288188457489015,
|
|
"epoch": 1.0766789174741063,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048895641645638,
|
|
"loss": 5.0699,
|
|
"mean_token_accuracy": 0.19660116881132125,
|
|
"num_tokens": 23711019.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.180233001708984,
|
|
"epoch": 1.0770965586368193,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004889472024187867,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.20637753158807753,
|
|
"num_tokens": 23719660.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.1542112827301025,
|
|
"epoch": 1.0775141997995323,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048893798463579,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.19735390841960906,
|
|
"num_tokens": 23728937.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.174329710006714,
|
|
"epoch": 1.0779318409622451,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004889287631075513,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.20844412595033646,
|
|
"num_tokens": 23738530.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.195611524581909,
|
|
"epoch": 1.0783494821249582,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004889195378342322,
|
|
"loss": 5.0016,
|
|
"mean_token_accuracy": 0.2000334620475769,
|
|
"num_tokens": 23748285.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.125119829177857,
|
|
"epoch": 1.0787671232876712,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004889103088159941,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.2008134201169014,
|
|
"num_tokens": 23758312.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.254036998748779,
|
|
"epoch": 1.0791847644503842,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004889010760529986,
|
|
"loss": 5.0671,
|
|
"mean_token_accuracy": 0.1980193793773651,
|
|
"num_tokens": 23767092.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.326939868927002,
|
|
"epoch": 1.0796024056130973,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004888918395454071,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.19739038795232772,
|
|
"num_tokens": 23776257.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.249224376678467,
|
|
"epoch": 1.0800200467758103,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004888825992933817,
|
|
"loss": 5.0439,
|
|
"mean_token_accuracy": 0.19262923896312714,
|
|
"num_tokens": 23785311.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.11654953956604,
|
|
"epoch": 1.0804376879385231,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004888733552970839,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.1992383360862732,
|
|
"num_tokens": 23795050.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.214238834381104,
|
|
"epoch": 1.0808553291012362,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004888641075566755,
|
|
"loss": 5.0611,
|
|
"mean_token_accuracy": 0.1990690752863884,
|
|
"num_tokens": 23803959.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.201442718505859,
|
|
"epoch": 1.0812729702639492,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004888548560723184,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.20271057933568953,
|
|
"num_tokens": 23813568.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.178594398498535,
|
|
"epoch": 1.0816906114266622,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004888456008441748,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.19284995049238204,
|
|
"num_tokens": 23823076.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.07160267829895,
|
|
"epoch": 1.0821082525893753,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004888363418724064,
|
|
"loss": 4.8474,
|
|
"mean_token_accuracy": 0.21805896162986754,
|
|
"num_tokens": 23831624.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.186234712600708,
|
|
"epoch": 1.0825258937520883,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004888270791571756,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.20242290943861008,
|
|
"num_tokens": 23841054.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.163810729980469,
|
|
"epoch": 1.082943534914801,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004888178126986444,
|
|
"loss": 5.0139,
|
|
"mean_token_accuracy": 0.1979166552424431,
|
|
"num_tokens": 23851190.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.181267261505127,
|
|
"epoch": 1.0833611760775141,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004888085424969748,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.21049170941114426,
|
|
"num_tokens": 23859560.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.210985898971558,
|
|
"epoch": 1.0837788172402272,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004887992685523295,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.20190583020448685,
|
|
"num_tokens": 23869103.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.162423515319825,
|
|
"epoch": 1.0841964584029402,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004887899908648706,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.20793181359767915,
|
|
"num_tokens": 23877641.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.164359426498413,
|
|
"epoch": 1.0846140995656532,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004887807094347606,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.20215266793966294,
|
|
"num_tokens": 23886671.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.119530200958252,
|
|
"epoch": 1.0850317407283663,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004887714242621619,
|
|
"loss": 4.9298,
|
|
"mean_token_accuracy": 0.2109586700797081,
|
|
"num_tokens": 23895781.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.2624927997589115,
|
|
"epoch": 1.085449381891079,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004887621353472371,
|
|
"loss": 5.0697,
|
|
"mean_token_accuracy": 0.1970836952328682,
|
|
"num_tokens": 23904478.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.242197561264038,
|
|
"epoch": 1.0858670230537921,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004887528426901488,
|
|
"loss": 4.9739,
|
|
"mean_token_accuracy": 0.19853319078683854,
|
|
"num_tokens": 23913899.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.141314172744751,
|
|
"epoch": 1.0862846642165052,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004887435462910597,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.20020175278186797,
|
|
"num_tokens": 23923583.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.197400522232056,
|
|
"epoch": 1.0867023053792182,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004887342461501326,
|
|
"loss": 5.0075,
|
|
"mean_token_accuracy": 0.1925540715456009,
|
|
"num_tokens": 23932392.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.326419448852539,
|
|
"epoch": 1.0871199465419312,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004887249422675301,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.1848290041089058,
|
|
"num_tokens": 23941480.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.172903347015381,
|
|
"epoch": 1.0875375877046443,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004887156346434154,
|
|
"loss": 5.0,
|
|
"mean_token_accuracy": 0.20673845261335372,
|
|
"num_tokens": 23950720.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.141679382324218,
|
|
"epoch": 1.087955228867357,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004887063232779513,
|
|
"loss": 4.9031,
|
|
"mean_token_accuracy": 0.20663689821958542,
|
|
"num_tokens": 23959441.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.206944608688355,
|
|
"epoch": 1.08837287003007,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004886970081713006,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.20231774151325227,
|
|
"num_tokens": 23968638.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.169567012786866,
|
|
"epoch": 1.0887905111927831,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004886876893236266,
|
|
"loss": 4.9977,
|
|
"mean_token_accuracy": 0.19726155549287797,
|
|
"num_tokens": 23977820.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.104059791564941,
|
|
"epoch": 1.0892081523554962,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004886783667350925,
|
|
"loss": 4.8743,
|
|
"mean_token_accuracy": 0.21075446605682374,
|
|
"num_tokens": 23986674.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.178409242630005,
|
|
"epoch": 1.0896257935182092,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004886690404058613,
|
|
"loss": 5.0009,
|
|
"mean_token_accuracy": 0.20530558824539186,
|
|
"num_tokens": 23995647.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.219105625152588,
|
|
"epoch": 1.0900434346809222,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004886597103360963,
|
|
"loss": 4.9407,
|
|
"mean_token_accuracy": 0.20715427100658418,
|
|
"num_tokens": 24004440.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.24730863571167,
|
|
"epoch": 1.090461075843635,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004886503765259609,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.19461475312709808,
|
|
"num_tokens": 24014632.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.158810997009278,
|
|
"epoch": 1.090878717006348,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004886410389756186,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.20974108576774597,
|
|
"num_tokens": 24024096.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.034177207946778,
|
|
"epoch": 1.0912963581690611,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004886316976852326,
|
|
"loss": 4.943,
|
|
"mean_token_accuracy": 0.20606043934822083,
|
|
"num_tokens": 24033410.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.175591087341308,
|
|
"epoch": 1.0917139993317742,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004886223526549666,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.20546575784683227,
|
|
"num_tokens": 24043110.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.19419264793396,
|
|
"epoch": 1.0921316404944872,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004886130038849843,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.20609234273433685,
|
|
"num_tokens": 24052393.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.232043170928955,
|
|
"epoch": 1.0925492816572002,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004886036513754491,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.1979564294219017,
|
|
"num_tokens": 24061086.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.184473705291748,
|
|
"epoch": 1.092966922819913,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004885942951265251,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.2031309112906456,
|
|
"num_tokens": 24070494.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.156550788879395,
|
|
"epoch": 1.093384563982626,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004885849351383756,
|
|
"loss": 4.8616,
|
|
"mean_token_accuracy": 0.2136886090040207,
|
|
"num_tokens": 24080740.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.12438645362854,
|
|
"epoch": 1.093802205145339,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004885755714111649,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.19929886609315872,
|
|
"num_tokens": 24090372.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.1872323513031,
|
|
"epoch": 1.0942198463080521,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004885662039450565,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.19762236922979354,
|
|
"num_tokens": 24099294.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.19448676109314,
|
|
"epoch": 1.0946374874707652,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004885568327402149,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.20549339205026626,
|
|
"num_tokens": 24108066.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.197881031036377,
|
|
"epoch": 1.0950551286334782,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004885474577968038,
|
|
"loss": 5.0869,
|
|
"mean_token_accuracy": 0.19202090948820114,
|
|
"num_tokens": 24118070.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.273807048797607,
|
|
"epoch": 1.095472769796191,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004885380791149874,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20345836281776428,
|
|
"num_tokens": 24127314.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.201112556457519,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004885286966949298,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.20222124308347703,
|
|
"num_tokens": 24136440.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.143569278717041,
|
|
"epoch": 1.096308052121617,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004885193105367955,
|
|
"loss": 5.0539,
|
|
"mean_token_accuracy": 0.19882403761148454,
|
|
"num_tokens": 24146268.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.1855854988098145,
|
|
"epoch": 1.0967256932843301,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004885099206407486,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.20687180757522583,
|
|
"num_tokens": 24156034.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.233466005325317,
|
|
"epoch": 1.0971433344470432,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004885005270069535,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.2024045169353485,
|
|
"num_tokens": 24165001.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.130460453033447,
|
|
"epoch": 1.0975609756097562,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004884911296355746,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.2046682208776474,
|
|
"num_tokens": 24174490.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.190751647949218,
|
|
"epoch": 1.097978616772469,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004884817285267766,
|
|
"loss": 5.0345,
|
|
"mean_token_accuracy": 0.19710303395986556,
|
|
"num_tokens": 24184471.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.20024003982544,
|
|
"epoch": 1.098396257935182,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004884723236807239,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.20126610845327378,
|
|
"num_tokens": 24193219.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.22159161567688,
|
|
"epoch": 1.098813899097895,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004884629150975814,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.19876063764095306,
|
|
"num_tokens": 24202138.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.132899808883667,
|
|
"epoch": 1.099231540260608,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004884535027775135,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.1982187569141388,
|
|
"num_tokens": 24211689.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.085301733016967,
|
|
"epoch": 1.0996491814233211,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004884440867206851,
|
|
"loss": 4.9129,
|
|
"mean_token_accuracy": 0.2032475396990776,
|
|
"num_tokens": 24221822.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.212867975234985,
|
|
"epoch": 1.1000668225860342,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000488434666927261,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.19549386501312255,
|
|
"num_tokens": 24231504.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.1744537353515625,
|
|
"epoch": 1.100484463748747,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004884252433974062,
|
|
"loss": 4.9641,
|
|
"mean_token_accuracy": 0.19761509597301483,
|
|
"num_tokens": 24240855.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.13556022644043,
|
|
"epoch": 1.10090210491146,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004884158161312856,
|
|
"loss": 4.8875,
|
|
"mean_token_accuracy": 0.21134347319602967,
|
|
"num_tokens": 24249659.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.113099575042725,
|
|
"epoch": 1.101319746074173,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004884063851290642,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.20077899396419524,
|
|
"num_tokens": 24259277.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.164052152633667,
|
|
"epoch": 1.101737387236886,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004883969503909073,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.2017353042960167,
|
|
"num_tokens": 24269744.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.128753232955932,
|
|
"epoch": 1.1021550283995991,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004883875119169798,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20521418154239654,
|
|
"num_tokens": 24278843.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.129987287521362,
|
|
"epoch": 1.1025726695623121,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000488378069707447,
|
|
"loss": 4.8459,
|
|
"mean_token_accuracy": 0.21534471362829208,
|
|
"num_tokens": 24287586.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.127574729919433,
|
|
"epoch": 1.102990310725025,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004883686237624744,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.20345209687948226,
|
|
"num_tokens": 24296318.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.142273044586181,
|
|
"epoch": 1.103407951887738,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004883591740822271,
|
|
"loss": 4.9469,
|
|
"mean_token_accuracy": 0.20400548428297044,
|
|
"num_tokens": 24305901.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.177602243423462,
|
|
"epoch": 1.103825593050451,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004883497206668707,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.2033698320388794,
|
|
"num_tokens": 24315075.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.13605694770813,
|
|
"epoch": 1.104243234213164,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004883402635165705,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.2014315515756607,
|
|
"num_tokens": 24323771.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.190080261230468,
|
|
"epoch": 1.104660875375877,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004883308026314923,
|
|
"loss": 5.067,
|
|
"mean_token_accuracy": 0.19955671280622483,
|
|
"num_tokens": 24334175.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.219483137130737,
|
|
"epoch": 1.1050785165385901,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004883213380118016,
|
|
"loss": 4.9881,
|
|
"mean_token_accuracy": 0.20053200870752336,
|
|
"num_tokens": 24344076.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.172171211242675,
|
|
"epoch": 1.105496157701303,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004883118696576642,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.18882194459438323,
|
|
"num_tokens": 24353333.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.230933332443238,
|
|
"epoch": 1.105913798864016,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004883023975692457,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.19122972190380097,
|
|
"num_tokens": 24362000.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.180014657974243,
|
|
"epoch": 1.106331440026729,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004882929217467118,
|
|
"loss": 4.8783,
|
|
"mean_token_accuracy": 0.20691960752010347,
|
|
"num_tokens": 24370490.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.101082992553711,
|
|
"epoch": 1.106749081189442,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004882834421902287,
|
|
"loss": 4.8896,
|
|
"mean_token_accuracy": 0.21209489703178405,
|
|
"num_tokens": 24378597.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.068929004669189,
|
|
"epoch": 1.107166722352155,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048827395889996226,
|
|
"loss": 4.9167,
|
|
"mean_token_accuracy": 0.2033285140991211,
|
|
"num_tokens": 24387050.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.133096075057983,
|
|
"epoch": 1.107584363514868,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004882644718760784,
|
|
"loss": 4.8922,
|
|
"mean_token_accuracy": 0.21195074766874314,
|
|
"num_tokens": 24395283.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.004158878326416,
|
|
"epoch": 1.108002004677581,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048825498111874325,
|
|
"loss": 4.8525,
|
|
"mean_token_accuracy": 0.20842288434505463,
|
|
"num_tokens": 24404206.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.135065317153931,
|
|
"epoch": 1.108419645840294,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048824548662812294,
|
|
"loss": 4.9051,
|
|
"mean_token_accuracy": 0.20477092564105986,
|
|
"num_tokens": 24414080.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.162567758560181,
|
|
"epoch": 1.108837287003007,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048823598840438384,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.20155803114175797,
|
|
"num_tokens": 24422406.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.159024286270141,
|
|
"epoch": 1.10925492816572,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048822648644769194,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.20203019976615905,
|
|
"num_tokens": 24432159.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.1401063919067385,
|
|
"epoch": 1.109672569328433,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004882169807582138,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.20956576466560364,
|
|
"num_tokens": 24440442.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.159703493118286,
|
|
"epoch": 1.110090210491146,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004882074713361157,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.203843355178833,
|
|
"num_tokens": 24449717.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.15858302116394,
|
|
"epoch": 1.110507851653859,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004881979581815642,
|
|
"loss": 4.8864,
|
|
"mean_token_accuracy": 0.21253306269645691,
|
|
"num_tokens": 24458279.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.085260105133057,
|
|
"epoch": 1.110925492816572,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004881884412947259,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.21036750227212905,
|
|
"num_tokens": 24466096.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.149126386642456,
|
|
"epoch": 1.111343133979285,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048817892067576726,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.1937076061964035,
|
|
"num_tokens": 24474432.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.240054988861084,
|
|
"epoch": 1.111760775141998,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000488169396324855,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.19685342460870742,
|
|
"num_tokens": 24484627.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.1504744529724125,
|
|
"epoch": 1.112178416304711,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048815986824215585,
|
|
"loss": 4.944,
|
|
"mean_token_accuracy": 0.20632336288690567,
|
|
"num_tokens": 24494010.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.131055307388306,
|
|
"epoch": 1.112596057467424,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004881503364278366,
|
|
"loss": 4.8728,
|
|
"mean_token_accuracy": 0.2072224423289299,
|
|
"num_tokens": 24503286.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.076667547225952,
|
|
"epoch": 1.1130136986301369,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004881408008820642,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.2096168354153633,
|
|
"num_tokens": 24512595.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.115263652801514,
|
|
"epoch": 1.11343133979285,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048813126160500555,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.20265370160341262,
|
|
"num_tokens": 24521358.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.274457168579102,
|
|
"epoch": 1.113848980955563,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004881217185968276,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.19628337770700455,
|
|
"num_tokens": 24530233.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.310393667221069,
|
|
"epoch": 1.114266622118276,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004881121718576974,
|
|
"loss": 5.0862,
|
|
"mean_token_accuracy": 0.18637516647577285,
|
|
"num_tokens": 24539645.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.243384790420532,
|
|
"epoch": 1.114684263280989,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048810262138778213,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.19591438323259353,
|
|
"num_tokens": 24549085.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.195956802368164,
|
|
"epoch": 1.115101904443702,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048809306718724886,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.19637491852045058,
|
|
"num_tokens": 24557750.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.188299465179443,
|
|
"epoch": 1.115519545606415,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048808350925626514,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.2018349677324295,
|
|
"num_tokens": 24567281.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.118918943405151,
|
|
"epoch": 1.115937186769128,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048807394759499797,
|
|
"loss": 4.9445,
|
|
"mean_token_accuracy": 0.20531732887029647,
|
|
"num_tokens": 24576548.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.043518447875977,
|
|
"epoch": 1.116354827931841,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004880643822036149,
|
|
"loss": 4.8711,
|
|
"mean_token_accuracy": 0.21077648252248765,
|
|
"num_tokens": 24585528.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.171388339996338,
|
|
"epoch": 1.116772469094554,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048805481308228333,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.20152204632759094,
|
|
"num_tokens": 24594179.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.13182806968689,
|
|
"epoch": 1.117190110257267,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004880452402311709,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.20144240707159042,
|
|
"num_tokens": 24603365.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.174013376235962,
|
|
"epoch": 1.11760775141998,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048803566365044493,
|
|
"loss": 5.0233,
|
|
"mean_token_accuracy": 0.19114116430282593,
|
|
"num_tokens": 24613472.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.226609516143799,
|
|
"epoch": 1.1180253925826928,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004880260833402734,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.2001221925020218,
|
|
"num_tokens": 24623492.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.218543767929077,
|
|
"epoch": 1.1184430337454059,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048801649930082375,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.19790757894515992,
|
|
"num_tokens": 24633245.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.182901668548584,
|
|
"epoch": 1.118860674908119,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000488006911532264,
|
|
"loss": 4.8934,
|
|
"mean_token_accuracy": 0.2092584937810898,
|
|
"num_tokens": 24642652.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.095616149902344,
|
|
"epoch": 1.119278316070832,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004879973200347617,
|
|
"loss": 5.009,
|
|
"mean_token_accuracy": 0.2051973298192024,
|
|
"num_tokens": 24651650.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.195728492736817,
|
|
"epoch": 1.119695957233545,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048798772480848504,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.1953406438231468,
|
|
"num_tokens": 24661356.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.179117012023926,
|
|
"epoch": 1.120113598396258,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048797812585360187,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.2067585438489914,
|
|
"num_tokens": 24670100.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.179187488555908,
|
|
"epoch": 1.120531239558971,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048796852317028024,
|
|
"loss": 5.003,
|
|
"mean_token_accuracy": 0.19608547389507294,
|
|
"num_tokens": 24679437.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.205917310714722,
|
|
"epoch": 1.1209488807216839,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004879589167586882,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.1991334691643715,
|
|
"num_tokens": 24689818.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.210038661956787,
|
|
"epoch": 1.121366521884397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048794930661899414,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.20575864464044571,
|
|
"num_tokens": 24698323.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.1990148544311525,
|
|
"epoch": 1.12178416304711,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048793969275136593,
|
|
"loss": 5.0078,
|
|
"mean_token_accuracy": 0.20010074228048325,
|
|
"num_tokens": 24707447.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.1694653034210205,
|
|
"epoch": 1.122201804209823,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004879300751559722,
|
|
"loss": 4.9073,
|
|
"mean_token_accuracy": 0.21182999312877654,
|
|
"num_tokens": 24716470.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.138053607940674,
|
|
"epoch": 1.122619445372536,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004879204538329812,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.2077472612261772,
|
|
"num_tokens": 24725051.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.245497798919677,
|
|
"epoch": 1.1230370865352488,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004879108287825614,
|
|
"loss": 5.1168,
|
|
"mean_token_accuracy": 0.19481105506420135,
|
|
"num_tokens": 24735303.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.265983581542969,
|
|
"epoch": 1.1234547276979618,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048790120000488115,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.19625573754310607,
|
|
"num_tokens": 24743637.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.158891105651856,
|
|
"epoch": 1.1238723688606749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004878915675001092,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.19919659197330475,
|
|
"num_tokens": 24752424.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.212686491012573,
|
|
"epoch": 1.124290010023388,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004878819312684141,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.1992620497941971,
|
|
"num_tokens": 24762224.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.274323987960815,
|
|
"epoch": 1.124707651186101,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004878722913099645,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.20171975791454316,
|
|
"num_tokens": 24771118.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.201798629760742,
|
|
"epoch": 1.125125292348814,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004878626476249293,
|
|
"loss": 5.0442,
|
|
"mean_token_accuracy": 0.19630365520715715,
|
|
"num_tokens": 24779941.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.123790073394775,
|
|
"epoch": 1.125542933511527,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004878530002134772,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.20277682244777678,
|
|
"num_tokens": 24788650.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.246025085449219,
|
|
"epoch": 1.1259605746742398,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004878433490757771,
|
|
"loss": 5.107,
|
|
"mean_token_accuracy": 0.1920781061053276,
|
|
"num_tokens": 24797953.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.219470548629761,
|
|
"epoch": 1.1263782158369529,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004878336942119979,
|
|
"loss": 4.9667,
|
|
"mean_token_accuracy": 0.2088983654975891,
|
|
"num_tokens": 24807073.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.0711140632629395,
|
|
"epoch": 1.126795856999666,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048782403562230874,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.20147655159235,
|
|
"num_tokens": 24815839.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.189441967010498,
|
|
"epoch": 1.127213498162379,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004878143733068787,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.19571423828601836,
|
|
"num_tokens": 24825496.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.253018617630005,
|
|
"epoch": 1.127631139325092,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004878047072658769,
|
|
"loss": 4.9395,
|
|
"mean_token_accuracy": 0.20792672634124756,
|
|
"num_tokens": 24834527.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.09864068031311,
|
|
"epoch": 1.1280487804878048,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004877950374994725,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.21470311284065247,
|
|
"num_tokens": 24843136.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.228253555297852,
|
|
"epoch": 1.1284664216505178,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004877853640078349,
|
|
"loss": 5.1015,
|
|
"mean_token_accuracy": 0.1951835945248604,
|
|
"num_tokens": 24853304.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.164680814743042,
|
|
"epoch": 1.1288840628132308,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004877756867911333,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.20373250246047975,
|
|
"num_tokens": 24861793.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.159054517745972,
|
|
"epoch": 1.1293017039759439,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004877660058495372,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.20625679492950438,
|
|
"num_tokens": 24871340.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.252390623092651,
|
|
"epoch": 1.129719345138657,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004877563211832161,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19956205189228057,
|
|
"num_tokens": 24880796.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.157743787765503,
|
|
"epoch": 1.13013698630137,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048774663279233947,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.21114081144332886,
|
|
"num_tokens": 24889801.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.190232229232788,
|
|
"epoch": 1.130554627464083,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048773694067707693,
|
|
"loss": 4.9939,
|
|
"mean_token_accuracy": 0.20347868651151657,
|
|
"num_tokens": 24899032.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.214659404754639,
|
|
"epoch": 1.1309722686267958,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048772724483759825,
|
|
"loss": 5.0968,
|
|
"mean_token_accuracy": 0.1981140211224556,
|
|
"num_tokens": 24908792.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.19938097000122,
|
|
"epoch": 1.1313899097895088,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000487717545274073,
|
|
"loss": 5.0152,
|
|
"mean_token_accuracy": 0.20325371474027634,
|
|
"num_tokens": 24918330.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.227181625366211,
|
|
"epoch": 1.1318075509522219,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004877078419866711,
|
|
"loss": 5.0013,
|
|
"mean_token_accuracy": 0.20410169214010238,
|
|
"num_tokens": 24928039.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.212827396392822,
|
|
"epoch": 1.1322251921149349,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048769813497556236,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.19871995598077774,
|
|
"num_tokens": 24937145.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.195865774154663,
|
|
"epoch": 1.132642833277648,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004876884242409168,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.19791145473718644,
|
|
"num_tokens": 24945879.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.100244140625,
|
|
"epoch": 1.1330604744403607,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048767870978290434,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21645372807979585,
|
|
"num_tokens": 24954900.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.286684465408325,
|
|
"epoch": 1.1334781156030738,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004876689916016951,
|
|
"loss": 5.1428,
|
|
"mean_token_accuracy": 0.19452081322669984,
|
|
"num_tokens": 24965015.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.253557825088501,
|
|
"epoch": 1.1338957567657868,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004876592696974591,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.20477031767368317,
|
|
"num_tokens": 24975125.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.163647079467774,
|
|
"epoch": 1.1343133979284998,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004876495440703667,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.19979415982961654,
|
|
"num_tokens": 24983895.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.119611310958862,
|
|
"epoch": 1.1347310390912129,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004876398147205879,
|
|
"loss": 4.9492,
|
|
"mean_token_accuracy": 0.2106444537639618,
|
|
"num_tokens": 24993186.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.158004188537598,
|
|
"epoch": 1.135148680253926,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004876300816482933,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.21135794520378112,
|
|
"num_tokens": 25001785.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.243739128112793,
|
|
"epoch": 1.135566321416639,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004876203448536532,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.20373328626155854,
|
|
"num_tokens": 25010717.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.1449426174163815,
|
|
"epoch": 1.1359839625793517,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004876106043368381,
|
|
"loss": 4.8966,
|
|
"mean_token_accuracy": 0.2063333049416542,
|
|
"num_tokens": 25019438.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.12303524017334,
|
|
"epoch": 1.1364016037420648,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004876008600980183,
|
|
"loss": 4.9525,
|
|
"mean_token_accuracy": 0.19983595311641694,
|
|
"num_tokens": 25028601.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.147025442123413,
|
|
"epoch": 1.1368192449047778,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048759111213736455,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.19687586426734924,
|
|
"num_tokens": 25038046.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.138490438461304,
|
|
"epoch": 1.1372368860674908,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 4.9032,
|
|
"mean_token_accuracy": 0.20973242968320846,
|
|
"num_tokens": 25046712.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.081827640533447,
|
|
"epoch": 1.1376545272302039,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004875716050512379,
|
|
"loss": 4.885,
|
|
"mean_token_accuracy": 0.20888490825891495,
|
|
"num_tokens": 25054918.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.157643461227417,
|
|
"epoch": 1.1380721683929167,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004875618459261065,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.20359669476747513,
|
|
"num_tokens": 25064187.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.24801115989685,
|
|
"epoch": 1.1384898095556297,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048755208307982414,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.200511372089386,
|
|
"num_tokens": 25073700.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.2073126316070555,
|
|
"epoch": 1.1389074507183428,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004875423165125616,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.19598623365163803,
|
|
"num_tokens": 25082974.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.178184223175049,
|
|
"epoch": 1.1393250918810558,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048753254622449006,
|
|
"loss": 4.988,
|
|
"mean_token_accuracy": 0.1999707415699959,
|
|
"num_tokens": 25092450.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.119438695907593,
|
|
"epoch": 1.1397427330437688,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004875227722157804,
|
|
"loss": 4.8981,
|
|
"mean_token_accuracy": 0.20395178496837615,
|
|
"num_tokens": 25102731.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.076331281661988,
|
|
"epoch": 1.1401603742064819,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004875129944866039,
|
|
"loss": 4.8764,
|
|
"mean_token_accuracy": 0.207842880487442,
|
|
"num_tokens": 25111159.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.144111442565918,
|
|
"epoch": 1.140578015369195,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004875032130371316,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.20648204386234284,
|
|
"num_tokens": 25120151.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.142707967758179,
|
|
"epoch": 1.1409956565319077,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004874934278675347,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.20534465461969376,
|
|
"num_tokens": 25128788.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.107631874084473,
|
|
"epoch": 1.1414132976946207,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004874836389779846,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.2037864461541176,
|
|
"num_tokens": 25138149.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.172539710998535,
|
|
"epoch": 1.1418309388573338,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048747384636865267,
|
|
"loss": 4.9767,
|
|
"mean_token_accuracy": 0.19343682676553725,
|
|
"num_tokens": 25147798.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.138930892944336,
|
|
"epoch": 1.1422485800200468,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004874640500397103,
|
|
"loss": 4.8863,
|
|
"mean_token_accuracy": 0.20320495814085007,
|
|
"num_tokens": 25156626.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.175389337539673,
|
|
"epoch": 1.1426662211827598,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004874542499913289,
|
|
"loss": 4.9928,
|
|
"mean_token_accuracy": 0.19642375260591508,
|
|
"num_tokens": 25165846.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.12396273612976,
|
|
"epoch": 1.1430838623454727,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048744444622368015,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.20784615576267243,
|
|
"num_tokens": 25175218.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.2208428382873535,
|
|
"epoch": 1.1435015035081857,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048743463873693576,
|
|
"loss": 5.0311,
|
|
"mean_token_accuracy": 0.19916563481092453,
|
|
"num_tokens": 25185257.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.273836898803711,
|
|
"epoch": 1.1439191446708987,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004874248275312673,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.1926201105117798,
|
|
"num_tokens": 25195348.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.1572037696838375,
|
|
"epoch": 1.1443367858336118,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048741501260684644,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.2076288104057312,
|
|
"num_tokens": 25204810.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.0716104984283445,
|
|
"epoch": 1.1447544269963248,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048740519396384515,
|
|
"loss": 4.8365,
|
|
"mean_token_accuracy": 0.21286435276269913,
|
|
"num_tokens": 25214490.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.07154655456543,
|
|
"epoch": 1.1451720681590378,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048739537160243524,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.21740389466285706,
|
|
"num_tokens": 25222840.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.124548149108887,
|
|
"epoch": 1.1455897093217509,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048738554552278874,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.20677186101675032,
|
|
"num_tokens": 25231056.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.1250114917755125,
|
|
"epoch": 1.1460073504844637,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048737571572507753,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.19861506521701813,
|
|
"num_tokens": 25240445.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.142857789993286,
|
|
"epoch": 1.1464249916471767,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048736588220947384,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.20813391208648682,
|
|
"num_tokens": 25249113.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.135421466827393,
|
|
"epoch": 1.1468426328098897,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048735604497614974,
|
|
"loss": 4.9378,
|
|
"mean_token_accuracy": 0.20647278875112535,
|
|
"num_tokens": 25258202.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.275015830993652,
|
|
"epoch": 1.1472602739726028,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004873462040252775,
|
|
"loss": 5.0426,
|
|
"mean_token_accuracy": 0.1973186269402504,
|
|
"num_tokens": 25268052.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.186558437347412,
|
|
"epoch": 1.1476779151353158,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004873363593570293,
|
|
"loss": 5.0298,
|
|
"mean_token_accuracy": 0.19410761892795564,
|
|
"num_tokens": 25276696.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.09901065826416,
|
|
"epoch": 1.1480955562980286,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004873265109715776,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.207858669757843,
|
|
"num_tokens": 25284920.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.084775638580322,
|
|
"epoch": 1.1485131974607417,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004873166588690947,
|
|
"loss": 4.8854,
|
|
"mean_token_accuracy": 0.2109785035252571,
|
|
"num_tokens": 25293960.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.1927878856658936,
|
|
"epoch": 1.1489308386234547,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004873068030497532,
|
|
"loss": 5.0758,
|
|
"mean_token_accuracy": 0.19657916575670242,
|
|
"num_tokens": 25303948.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.298254442214966,
|
|
"epoch": 1.1493484797861677,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048729694351372545,
|
|
"loss": 5.0694,
|
|
"mean_token_accuracy": 0.2034141942858696,
|
|
"num_tokens": 25313343.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.1492541313171385,
|
|
"epoch": 1.1497661209488808,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004872870802611842,
|
|
"loss": 4.8618,
|
|
"mean_token_accuracy": 0.2067318856716156,
|
|
"num_tokens": 25321664.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.177978086471557,
|
|
"epoch": 1.1501837621115938,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004872772132923021,
|
|
"loss": 5.0244,
|
|
"mean_token_accuracy": 0.2090502381324768,
|
|
"num_tokens": 25331112.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.226603078842163,
|
|
"epoch": 1.1506014032743068,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048726734260725186,
|
|
"loss": 4.9726,
|
|
"mean_token_accuracy": 0.2077540248632431,
|
|
"num_tokens": 25340357.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.193742418289185,
|
|
"epoch": 1.1510190444370196,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004872574682062063,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.20372698158025743,
|
|
"num_tokens": 25349886.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.2048546314239506,
|
|
"epoch": 1.1514366855997327,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004872475900893382,
|
|
"loss": 5.0382,
|
|
"mean_token_accuracy": 0.200131356716156,
|
|
"num_tokens": 25358957.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.133332443237305,
|
|
"epoch": 1.1518543267624457,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004872377082568206,
|
|
"loss": 4.8686,
|
|
"mean_token_accuracy": 0.21120152473449708,
|
|
"num_tokens": 25368237.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.205290651321411,
|
|
"epoch": 1.1522719679251587,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048722782270882643,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.21422120928764343,
|
|
"num_tokens": 25376626.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.114291381835938,
|
|
"epoch": 1.1526896090878718,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004872179334455288,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20702963024377824,
|
|
"num_tokens": 25385824.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.110055780410766,
|
|
"epoch": 1.1531072502505846,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048720804046710074,
|
|
"loss": 4.8924,
|
|
"mean_token_accuracy": 0.2123393937945366,
|
|
"num_tokens": 25394317.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.142131996154785,
|
|
"epoch": 1.1535248914132976,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048719814377371553,
|
|
"loss": 4.9778,
|
|
"mean_token_accuracy": 0.19662246555089952,
|
|
"num_tokens": 25402962.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.136072254180908,
|
|
"epoch": 1.1539425325760106,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004871882433655464,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.2076478362083435,
|
|
"num_tokens": 25411660.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.138869524002075,
|
|
"epoch": 1.1543601737387237,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004871783392427666,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.2050904870033264,
|
|
"num_tokens": 25420377.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.0928856372833256,
|
|
"epoch": 1.1547778149014367,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004871684314055497,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.20411113649606705,
|
|
"num_tokens": 25428811.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.16126503944397,
|
|
"epoch": 1.1551954560641498,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004871585198540689,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.196958290040493,
|
|
"num_tokens": 25438247.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.121724271774292,
|
|
"epoch": 1.1556130972268628,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048714860458849794,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.21387530565261842,
|
|
"num_tokens": 25447122.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.218702983856201,
|
|
"epoch": 1.1560307383895756,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048713868560901013,
|
|
"loss": 5.0711,
|
|
"mean_token_accuracy": 0.19090910404920577,
|
|
"num_tokens": 25455737.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.1803319454193115,
|
|
"epoch": 1.1564483795522886,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004871287629157794,
|
|
"loss": 4.9,
|
|
"mean_token_accuracy": 0.20876794159412385,
|
|
"num_tokens": 25465285.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.166810464859009,
|
|
"epoch": 1.1568660207150017,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004871188365089793,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.20883765518665315,
|
|
"num_tokens": 25474933.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.104287767410279,
|
|
"epoch": 1.1572836618777147,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004871089063887837,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.20794036388397216,
|
|
"num_tokens": 25483279.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.187629079818725,
|
|
"epoch": 1.1577013030404277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048709897255536626,
|
|
"loss": 5.004,
|
|
"mean_token_accuracy": 0.20151136815547943,
|
|
"num_tokens": 25492295.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.2023850440979,
|
|
"epoch": 1.1581189442031405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004870890350089011,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.20169200897216796,
|
|
"num_tokens": 25501397.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.062053966522217,
|
|
"epoch": 1.1585365853658536,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004870790937495621,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.2062204048037529,
|
|
"num_tokens": 25510588.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.235393095016479,
|
|
"epoch": 1.1589542265285666,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048706914877752325,
|
|
"loss": 4.9901,
|
|
"mean_token_accuracy": 0.20219841599464417,
|
|
"num_tokens": 25519531.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.154824829101562,
|
|
"epoch": 1.1593718676912796,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048705920009295867,
|
|
"loss": 4.8935,
|
|
"mean_token_accuracy": 0.20541852563619614,
|
|
"num_tokens": 25529241.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.186248350143432,
|
|
"epoch": 1.1597895088539927,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004870492476960426,
|
|
"loss": 5.016,
|
|
"mean_token_accuracy": 0.19206317216157914,
|
|
"num_tokens": 25538463.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.167735052108765,
|
|
"epoch": 1.1602071500167057,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004870392915869491,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.20156778991222382,
|
|
"num_tokens": 25547481.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.2040567874908445,
|
|
"epoch": 1.1606247911794187,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004870293317658526,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.20362902134656907,
|
|
"num_tokens": 25556083.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.152432250976562,
|
|
"epoch": 1.1610424323421316,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004870193682329275,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.20719525516033171,
|
|
"num_tokens": 25564975.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.019022464752197,
|
|
"epoch": 1.1614600735048446,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048700940098834805,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.2113082990050316,
|
|
"num_tokens": 25574576.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.159143400192261,
|
|
"epoch": 1.1618777146675576,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004869994300322889,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.20774728953838348,
|
|
"num_tokens": 25583485.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.16772494316101,
|
|
"epoch": 1.1622953558302707,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048698945536492454,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.20200437903404236,
|
|
"num_tokens": 25592736.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.198943996429444,
|
|
"epoch": 1.1627129969929837,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004869794769864296,
|
|
"loss": 4.977,
|
|
"mean_token_accuracy": 0.20553614497184752,
|
|
"num_tokens": 25601230.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.218483114242554,
|
|
"epoch": 1.1631306381556965,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004869694948969787,
|
|
"loss": 4.9514,
|
|
"mean_token_accuracy": 0.20510891526937486,
|
|
"num_tokens": 25611139.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.225070285797119,
|
|
"epoch": 1.1635482793184095,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048695950909674666,
|
|
"loss": 5.002,
|
|
"mean_token_accuracy": 0.19451773464679717,
|
|
"num_tokens": 25620255.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.101096773147583,
|
|
"epoch": 1.1639659204811226,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048694951958590835,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.20948225408792495,
|
|
"num_tokens": 25629127.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.133993816375733,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048693952636463854,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.2066566452383995,
|
|
"num_tokens": 25638561.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.094225978851318,
|
|
"epoch": 1.1648012028065486,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048692952943311214,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.19875528961420058,
|
|
"num_tokens": 25647268.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.184319305419922,
|
|
"epoch": 1.1652188439692617,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004869195287915043,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.19910807609558107,
|
|
"num_tokens": 25656804.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.214507675170898,
|
|
"epoch": 1.1656364851319747,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048690952443999,
|
|
"loss": 4.939,
|
|
"mean_token_accuracy": 0.20769357234239577,
|
|
"num_tokens": 25665960.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.304385423660278,
|
|
"epoch": 1.1660541262946875,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048689951637874445,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.18981515914201735,
|
|
"num_tokens": 25676836.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.16274790763855,
|
|
"epoch": 1.1664717674574006,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004868895046079428,
|
|
"loss": 4.8792,
|
|
"mean_token_accuracy": 0.20243281573057176,
|
|
"num_tokens": 25685751.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.10176568031311,
|
|
"epoch": 1.1668894086201136,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004868794891277602,
|
|
"loss": 4.8889,
|
|
"mean_token_accuracy": 0.2062852129340172,
|
|
"num_tokens": 25694948.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.20370192527771,
|
|
"epoch": 1.1673070497828266,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004868694699383722,
|
|
"loss": 5.1107,
|
|
"mean_token_accuracy": 0.2013367608189583,
|
|
"num_tokens": 25704135.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.345385265350342,
|
|
"epoch": 1.1677246909455397,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004868594470399541,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.19421169608831407,
|
|
"num_tokens": 25714300.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.203368663787842,
|
|
"epoch": 1.1681423321082525,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048684942043268137,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.2070540592074394,
|
|
"num_tokens": 25723275.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.215776252746582,
|
|
"epoch": 1.1685599732709655,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048683939011672953,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.19044512659311294,
|
|
"num_tokens": 25732432.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.109826135635376,
|
|
"epoch": 1.1689776144336785,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048682935609227414,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.1989915043115616,
|
|
"num_tokens": 25741001.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.2178901672363285,
|
|
"epoch": 1.1693952555963916,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048681931835949083,
|
|
"loss": 5.0328,
|
|
"mean_token_accuracy": 0.1976896345615387,
|
|
"num_tokens": 25751632.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.198111534118652,
|
|
"epoch": 1.1698128967591046,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004868092769185555,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.19836863428354262,
|
|
"num_tokens": 25760963.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.142030239105225,
|
|
"epoch": 1.1702305379218176,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048679923176964384,
|
|
"loss": 4.9494,
|
|
"mean_token_accuracy": 0.2051076650619507,
|
|
"num_tokens": 25769974.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.185855674743652,
|
|
"epoch": 1.1706481790845307,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004867891829129316,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.2020861253142357,
|
|
"num_tokens": 25778311.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.223141813278199,
|
|
"epoch": 1.1710658202472435,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004867791303485948,
|
|
"loss": 4.9964,
|
|
"mean_token_accuracy": 0.19930825978517533,
|
|
"num_tokens": 25787811.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.20784821510315,
|
|
"epoch": 1.1714834614099565,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004867690740768094,
|
|
"loss": 4.9509,
|
|
"mean_token_accuracy": 0.2062822014093399,
|
|
"num_tokens": 25796651.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.1913830757141115,
|
|
"epoch": 1.1719011025726696,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048675901409775147,
|
|
"loss": 5.0055,
|
|
"mean_token_accuracy": 0.20319464355707167,
|
|
"num_tokens": 25805995.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.193567705154419,
|
|
"epoch": 1.1723187437353826,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048674895041159714,
|
|
"loss": 4.9847,
|
|
"mean_token_accuracy": 0.20811574757099152,
|
|
"num_tokens": 25814833.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.246817541122437,
|
|
"epoch": 1.1727363848980956,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048673888301852247,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20544013530015945,
|
|
"num_tokens": 25823224.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.13305344581604,
|
|
"epoch": 1.1731540260608084,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004867288119187039,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.20710639506578446,
|
|
"num_tokens": 25832583.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.1052168846130375,
|
|
"epoch": 1.1735716672235215,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004867187371123175,
|
|
"loss": 4.986,
|
|
"mean_token_accuracy": 0.2038514420390129,
|
|
"num_tokens": 25841233.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.159973192214966,
|
|
"epoch": 1.1739893083862345,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048670865859953984,
|
|
"loss": 4.916,
|
|
"mean_token_accuracy": 0.2012063130736351,
|
|
"num_tokens": 25849794.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.160331106185913,
|
|
"epoch": 1.1744069495489475,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004866985763805472,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.20307471454143525,
|
|
"num_tokens": 25858629.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.156593275070191,
|
|
"epoch": 1.1748245907116606,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004866884904555162,
|
|
"loss": 4.9812,
|
|
"mean_token_accuracy": 0.20620591789484025,
|
|
"num_tokens": 25868382.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.173895215988159,
|
|
"epoch": 1.1752422318743736,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004866784008246233,
|
|
"loss": 4.9946,
|
|
"mean_token_accuracy": 0.19952823966741562,
|
|
"num_tokens": 25877565.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.2475786209106445,
|
|
"epoch": 1.1756598730370866,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004866683074880453,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.19166408777236937,
|
|
"num_tokens": 25886791.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.2184288024902346,
|
|
"epoch": 1.1760775141997994,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048665821044595884,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.20274678915739058,
|
|
"num_tokens": 25896190.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.100507736206055,
|
|
"epoch": 1.1764951553625125,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004866481096985405,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.20330509096384047,
|
|
"num_tokens": 25904702.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.21715350151062,
|
|
"epoch": 1.1769127965252255,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004866380052459673,
|
|
"loss": 5.0353,
|
|
"mean_token_accuracy": 0.20566550493240357,
|
|
"num_tokens": 25914513.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.088445615768433,
|
|
"epoch": 1.1773304376879385,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004866278970884161,
|
|
"loss": 4.9096,
|
|
"mean_token_accuracy": 0.20272248834371567,
|
|
"num_tokens": 25923436.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.14292540550232,
|
|
"epoch": 1.1777480788506516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048661778522606376,
|
|
"loss": 4.9228,
|
|
"mean_token_accuracy": 0.2077519714832306,
|
|
"num_tokens": 25931883.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.169765615463257,
|
|
"epoch": 1.1781657200133644,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048660766965908736,
|
|
"loss": 4.9941,
|
|
"mean_token_accuracy": 0.19358734786510468,
|
|
"num_tokens": 25942095.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.1053839206695555,
|
|
"epoch": 1.1785833611760774,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048659755038766406,
|
|
"loss": 4.8299,
|
|
"mean_token_accuracy": 0.2170640230178833,
|
|
"num_tokens": 25951265.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.1353813171386715,
|
|
"epoch": 1.1790010023387905,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048658742741197086,
|
|
"loss": 4.9241,
|
|
"mean_token_accuracy": 0.199820576608181,
|
|
"num_tokens": 25960621.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.130825519561768,
|
|
"epoch": 1.1794186435015035,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048657730073218517,
|
|
"loss": 4.9845,
|
|
"mean_token_accuracy": 0.19452319592237471,
|
|
"num_tokens": 25970769.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.2152868747711185,
|
|
"epoch": 1.1798362846642165,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004865671703484841,
|
|
"loss": 5.0872,
|
|
"mean_token_accuracy": 0.1986862078309059,
|
|
"num_tokens": 25980928.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.250247669219971,
|
|
"epoch": 1.1802539258269296,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048655703626104493,
|
|
"loss": 5.0275,
|
|
"mean_token_accuracy": 0.19748563319444656,
|
|
"num_tokens": 25991085.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.114477729797363,
|
|
"epoch": 1.1806715669896426,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048654689847004535,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.21031931191682815,
|
|
"num_tokens": 25999862.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.2166191101074215,
|
|
"epoch": 1.1810892081523554,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004865367569756626,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.20333696901798248,
|
|
"num_tokens": 26009075.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.1617128372192385,
|
|
"epoch": 1.1815068493150684,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048652661177807426,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20697477459907532,
|
|
"num_tokens": 26017822.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.041386413574219,
|
|
"epoch": 1.1819244904777815,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048651646287745803,
|
|
"loss": 4.9036,
|
|
"mean_token_accuracy": 0.20254568457603456,
|
|
"num_tokens": 26026327.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.244654893875122,
|
|
"epoch": 1.1823421316404945,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048650631027399155,
|
|
"loss": 5.0916,
|
|
"mean_token_accuracy": 0.18919677585363387,
|
|
"num_tokens": 26036252.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.283205604553222,
|
|
"epoch": 1.1827597728032075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048649615396785246,
|
|
"loss": 5.0252,
|
|
"mean_token_accuracy": 0.20073236674070358,
|
|
"num_tokens": 26045596.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.1950407981872555,
|
|
"epoch": 1.1831774139659206,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048648599395921863,
|
|
"loss": 4.933,
|
|
"mean_token_accuracy": 0.2103711649775505,
|
|
"num_tokens": 26054824.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.161082553863525,
|
|
"epoch": 1.1835950551286334,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048647583024826786,
|
|
"loss": 4.9377,
|
|
"mean_token_accuracy": 0.1982040971517563,
|
|
"num_tokens": 26064414.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.188171768188477,
|
|
"epoch": 1.1840126962913464,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048646566283517824,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.20044438540935516,
|
|
"num_tokens": 26073597.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.182464361190796,
|
|
"epoch": 1.1844303374540595,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048645549172012756,
|
|
"loss": 4.9487,
|
|
"mean_token_accuracy": 0.20975352376699447,
|
|
"num_tokens": 26082026.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.057018089294433,
|
|
"epoch": 1.1848479786167725,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000486445316903294,
|
|
"loss": 4.8882,
|
|
"mean_token_accuracy": 0.21007515192031861,
|
|
"num_tokens": 26090112.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.1141139507293705,
|
|
"epoch": 1.1852656197794855,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004864351383848556,
|
|
"loss": 4.9078,
|
|
"mean_token_accuracy": 0.2010620579123497,
|
|
"num_tokens": 26098551.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.235504007339477,
|
|
"epoch": 1.1856832609421986,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004864249561649906,
|
|
"loss": 5.0191,
|
|
"mean_token_accuracy": 0.1924814134836197,
|
|
"num_tokens": 26109201.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.224775075912476,
|
|
"epoch": 1.1861009021049114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004864147702438773,
|
|
"loss": 4.974,
|
|
"mean_token_accuracy": 0.20196036696434022,
|
|
"num_tokens": 26119893.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.107402753829956,
|
|
"epoch": 1.1865185432676244,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000486404580621694,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.20614732950925826,
|
|
"num_tokens": 26128341.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.134731912612915,
|
|
"epoch": 1.1869361844303374,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000486394387298619,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.19626276344060897,
|
|
"num_tokens": 26137823.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.192541074752808,
|
|
"epoch": 1.1873538255930505,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048638419027483075,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.2004741072654724,
|
|
"num_tokens": 26147333.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.1548408508300785,
|
|
"epoch": 1.1877714667557635,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004863739895505079,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.20980468690395354,
|
|
"num_tokens": 26156145.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.198816776275635,
|
|
"epoch": 1.1881891079184765,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048636378512582884,
|
|
"loss": 4.8684,
|
|
"mean_token_accuracy": 0.20338238626718522,
|
|
"num_tokens": 26165323.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.147923326492309,
|
|
"epoch": 1.1886067490811894,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048635357700097236,
|
|
"loss": 4.9257,
|
|
"mean_token_accuracy": 0.20748998522758483,
|
|
"num_tokens": 26174549.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 4.985383462905884,
|
|
"epoch": 1.1890243902439024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004863433651761171,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.21116563230752944,
|
|
"num_tokens": 26184012.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.181051349639892,
|
|
"epoch": 1.1894420314066154,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004863331496514418,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.18646551668643951,
|
|
"num_tokens": 26193819.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.129006671905517,
|
|
"epoch": 1.1898596725693285,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048632293042712545,
|
|
"loss": 4.9099,
|
|
"mean_token_accuracy": 0.2062527820467949,
|
|
"num_tokens": 26202209.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.087129402160644,
|
|
"epoch": 1.1902773137320415,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048631270750334674,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.20567490607500077,
|
|
"num_tokens": 26212048.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.237024164199829,
|
|
"epoch": 1.1906949548947545,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048630248088028474,
|
|
"loss": 5.0282,
|
|
"mean_token_accuracy": 0.19961101561784744,
|
|
"num_tokens": 26220877.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.234298276901245,
|
|
"epoch": 1.1911125960574673,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004862922505581185,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.2057940199971199,
|
|
"num_tokens": 26229583.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.241326427459716,
|
|
"epoch": 1.1915302372201804,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000486282016537027,
|
|
"loss": 5.052,
|
|
"mean_token_accuracy": 0.20427430123090745,
|
|
"num_tokens": 26239483.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.1977497100830075,
|
|
"epoch": 1.1919478783828934,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048627177881718954,
|
|
"loss": 5.0207,
|
|
"mean_token_accuracy": 0.19546127915382386,
|
|
"num_tokens": 26248608.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.127264213562012,
|
|
"epoch": 1.1923655195456064,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004862615373987853,
|
|
"loss": 4.8983,
|
|
"mean_token_accuracy": 0.20256271958351135,
|
|
"num_tokens": 26258037.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.24695520401001,
|
|
"epoch": 1.1927831607083195,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004862512922819935,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.18896501809358596,
|
|
"num_tokens": 26267890.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.175356864929199,
|
|
"epoch": 1.1932008018710325,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004862410434669936,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.1990038812160492,
|
|
"num_tokens": 26276963.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.201987361907959,
|
|
"epoch": 1.1936184430337453,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048623079095396496,
|
|
"loss": 4.926,
|
|
"mean_token_accuracy": 0.2005222484469414,
|
|
"num_tokens": 26286667.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.190170335769653,
|
|
"epoch": 1.1940360841964583,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000486220534743087,
|
|
"loss": 4.9342,
|
|
"mean_token_accuracy": 0.20352500528097153,
|
|
"num_tokens": 26295575.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.096679067611694,
|
|
"epoch": 1.1944537253591714,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004862102748345394,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.20471881926059723,
|
|
"num_tokens": 26305813.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.11940631866455,
|
|
"epoch": 1.1948713665218844,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048620001122850164,
|
|
"loss": 4.8828,
|
|
"mean_token_accuracy": 0.21031437814235687,
|
|
"num_tokens": 26314744.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.271763324737549,
|
|
"epoch": 1.1952890076845974,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004861897439251535,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.18897767961025239,
|
|
"num_tokens": 26324469.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.204616355895996,
|
|
"epoch": 1.1957066488473105,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048617947292467473,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.20237270146608352,
|
|
"num_tokens": 26333850.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.114865112304687,
|
|
"epoch": 1.1961242900100233,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048616919822724506,
|
|
"loss": 4.8416,
|
|
"mean_token_accuracy": 0.21607604920864104,
|
|
"num_tokens": 26342327.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.1408744812011715,
|
|
"epoch": 1.1965419311727363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048615891983304436,
|
|
"loss": 5.0325,
|
|
"mean_token_accuracy": 0.20221305042505264,
|
|
"num_tokens": 26351162.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.137059593200684,
|
|
"epoch": 1.1969595723354494,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004861486377422526,
|
|
"loss": 4.9544,
|
|
"mean_token_accuracy": 0.2003741055727005,
|
|
"num_tokens": 26361452.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.185440540313721,
|
|
"epoch": 1.1973772134981624,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004861383519550498,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.21113307178020477,
|
|
"num_tokens": 26370646.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.263523054122925,
|
|
"epoch": 1.1977948546608754,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048612806247161594,
|
|
"loss": 5.1105,
|
|
"mean_token_accuracy": 0.18975039422512055,
|
|
"num_tokens": 26379829.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.186210632324219,
|
|
"epoch": 1.1982124958235885,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004861177692921313,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.19998425096273423,
|
|
"num_tokens": 26389578.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.2332946300506595,
|
|
"epoch": 1.1986301369863013,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048610747241677595,
|
|
"loss": 4.932,
|
|
"mean_token_accuracy": 0.20971637666225434,
|
|
"num_tokens": 26398586.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.183649253845215,
|
|
"epoch": 1.1990477781490143,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004860971718457302,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.2007386326789856,
|
|
"num_tokens": 26407379.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.119349193572998,
|
|
"epoch": 1.1994654193117273,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004860868675791743,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.21587797105312348,
|
|
"num_tokens": 26416489.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.182852029800415,
|
|
"epoch": 1.1998830604744404,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048607655961728876,
|
|
"loss": 4.9818,
|
|
"mean_token_accuracy": 0.19983260035514833,
|
|
"num_tokens": 26424768.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.20806565284729,
|
|
"epoch": 1.2003007016371534,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000486066247960254,
|
|
"loss": 4.9199,
|
|
"mean_token_accuracy": 0.19932166039943694,
|
|
"num_tokens": 26435175.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.070564317703247,
|
|
"epoch": 1.2007183427998664,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048605593260825044,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.2043012872338295,
|
|
"num_tokens": 26443492.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.14607048034668,
|
|
"epoch": 1.2011359839625793,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048604561356145875,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.21427195966243745,
|
|
"num_tokens": 26452239.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.147463321685791,
|
|
"epoch": 1.2015536251252923,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048603529082005955,
|
|
"loss": 5.0522,
|
|
"mean_token_accuracy": 0.20564057379961015,
|
|
"num_tokens": 26461010.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.0993140697479244,
|
|
"epoch": 1.2019712662880053,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048602496438423354,
|
|
"loss": 4.9301,
|
|
"mean_token_accuracy": 0.20684233158826829,
|
|
"num_tokens": 26470762.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.101467227935791,
|
|
"epoch": 1.2023889074507184,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004860146342541616,
|
|
"loss": 4.8815,
|
|
"mean_token_accuracy": 0.21211108416318894,
|
|
"num_tokens": 26479592.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.085744953155517,
|
|
"epoch": 1.2028065486134314,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004860043004300244,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.208307246863842,
|
|
"num_tokens": 26488245.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.1721954345703125,
|
|
"epoch": 1.2032241897761444,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000485993962912003,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.20525965094566345,
|
|
"num_tokens": 26497039.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.156922149658203,
|
|
"epoch": 1.2036418309388572,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004859836217002783,
|
|
"loss": 4.97,
|
|
"mean_token_accuracy": 0.20513388216495515,
|
|
"num_tokens": 26506116.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.112368154525757,
|
|
"epoch": 1.2040594721015703,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004859732767950313,
|
|
"loss": 4.8143,
|
|
"mean_token_accuracy": 0.21666593849658966,
|
|
"num_tokens": 26514309.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.182245302200317,
|
|
"epoch": 1.2044771132642833,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048596292819644315,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.20693174600601197,
|
|
"num_tokens": 26523425.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.180951833724976,
|
|
"epoch": 1.2048947544269963,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000485952575904695,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.20073693096637726,
|
|
"num_tokens": 26532723.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.169610214233399,
|
|
"epoch": 1.2053123955897094,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048594221991996814,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.2023228272795677,
|
|
"num_tokens": 26541933.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.251264524459839,
|
|
"epoch": 1.2057300367524224,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048593186024244373,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.1960674747824669,
|
|
"num_tokens": 26552071.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.256617307662964,
|
|
"epoch": 1.2061476779151352,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004859214968723033,
|
|
"loss": 5.0874,
|
|
"mean_token_accuracy": 0.1978855237364769,
|
|
"num_tokens": 26561470.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.191929960250855,
|
|
"epoch": 1.2065653190778483,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048591112980972813,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.21403641104698182,
|
|
"num_tokens": 26570448.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.2367161273956295,
|
|
"epoch": 1.2069829602405613,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004859007590548997,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.20111777037382125,
|
|
"num_tokens": 26579206.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.150507211685181,
|
|
"epoch": 1.2074006014032743,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048589038460799974,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.2019663095474243,
|
|
"num_tokens": 26587955.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.155042695999145,
|
|
"epoch": 1.2078182425659874,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004858800064692097,
|
|
"loss": 4.9539,
|
|
"mean_token_accuracy": 0.202371346950531,
|
|
"num_tokens": 26597635.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.177419281005859,
|
|
"epoch": 1.2082358837287004,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048586962463871124,
|
|
"loss": 4.907,
|
|
"mean_token_accuracy": 0.21092153936624528,
|
|
"num_tokens": 26606245.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.238356590270996,
|
|
"epoch": 1.2086535248914134,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048585923911668625,
|
|
"loss": 5.013,
|
|
"mean_token_accuracy": 0.19515984505414963,
|
|
"num_tokens": 26614464.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.178532886505127,
|
|
"epoch": 1.2090711660541262,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048584884990331644,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.2051496610045433,
|
|
"num_tokens": 26623436.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.1742331981658936,
|
|
"epoch": 1.2094888072168393,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048583845699878375,
|
|
"loss": 4.9077,
|
|
"mean_token_accuracy": 0.2055835485458374,
|
|
"num_tokens": 26632415.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.111305189132691,
|
|
"epoch": 1.2099064483795523,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004858280604032701,
|
|
"loss": 4.846,
|
|
"mean_token_accuracy": 0.21569220274686812,
|
|
"num_tokens": 26641618.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.2370934009552,
|
|
"epoch": 1.2103240895422653,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048581766011695745,
|
|
"loss": 5.065,
|
|
"mean_token_accuracy": 0.20003195405006408,
|
|
"num_tokens": 26651290.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.185987186431885,
|
|
"epoch": 1.2107417307049784,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048580725614002785,
|
|
"loss": 4.941,
|
|
"mean_token_accuracy": 0.20754511803388595,
|
|
"num_tokens": 26660945.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.172185754776001,
|
|
"epoch": 1.2111593718676912,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048579684847266353,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.2089068904519081,
|
|
"num_tokens": 26670221.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.14262433052063,
|
|
"epoch": 1.2115770130304042,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004857864371150467,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.20941120386123657,
|
|
"num_tokens": 26679074.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.225486946105957,
|
|
"epoch": 1.2119946541931172,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048577602206735943,
|
|
"loss": 5.051,
|
|
"mean_token_accuracy": 0.1984088972210884,
|
|
"num_tokens": 26689124.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.06153564453125,
|
|
"epoch": 1.2124122953558303,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004857656033297843,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.21065133512020112,
|
|
"num_tokens": 26698421.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.161602735519409,
|
|
"epoch": 1.2128299365185433,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048575518090250347,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.20899197161197663,
|
|
"num_tokens": 26706432.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.173313570022583,
|
|
"epoch": 1.2132475776812564,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004857447547856996,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.20769215524196624,
|
|
"num_tokens": 26715224.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.179033422470093,
|
|
"epoch": 1.2136652188439694,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004857343249795552,
|
|
"loss": 4.9502,
|
|
"mean_token_accuracy": 0.20486061722040178,
|
|
"num_tokens": 26724311.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.149508476257324,
|
|
"epoch": 1.2140828600066822,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004857238914842526,
|
|
"loss": 4.9822,
|
|
"mean_token_accuracy": 0.1939324215054512,
|
|
"num_tokens": 26734012.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.1732506275177,
|
|
"epoch": 1.2145005011693952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048571345429997473,
|
|
"loss": 4.8799,
|
|
"mean_token_accuracy": 0.2117844045162201,
|
|
"num_tokens": 26742745.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.135331392288208,
|
|
"epoch": 1.2149181423321083,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048570301342690416,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.21378224492073059,
|
|
"num_tokens": 26751856.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.028673887252808,
|
|
"epoch": 1.2153357834948213,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004856925688652238,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.2136292040348053,
|
|
"num_tokens": 26761359.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.112123823165893,
|
|
"epoch": 1.2157534246575343,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048568212061511634,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.20854734778404235,
|
|
"num_tokens": 26770588.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.222061347961426,
|
|
"epoch": 1.2161710658202471,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048567166867676475,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.2023475781083107,
|
|
"num_tokens": 26780637.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.13651556968689,
|
|
"epoch": 1.2165887069829602,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048566121305035207,
|
|
"loss": 4.9003,
|
|
"mean_token_accuracy": 0.21043167859315873,
|
|
"num_tokens": 26789387.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.188025760650635,
|
|
"epoch": 1.2170063481456732,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048565075373606126,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20440658628940583,
|
|
"num_tokens": 26798677.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.21405258178711,
|
|
"epoch": 1.2174239893083862,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048564029073407545,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.20520322769880295,
|
|
"num_tokens": 26807457.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.198657894134522,
|
|
"epoch": 1.2178416304710993,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004856298240445778,
|
|
"loss": 4.952,
|
|
"mean_token_accuracy": 0.20507543981075288,
|
|
"num_tokens": 26816832.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.118776416778564,
|
|
"epoch": 1.2182592716338123,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004856193536677515,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.20378464311361313,
|
|
"num_tokens": 26826534.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.180170154571533,
|
|
"epoch": 1.2186769127965253,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048560887960377995,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.20114791095256807,
|
|
"num_tokens": 26835981.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.164838790893555,
|
|
"epoch": 1.2190945539592382,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048559840185284647,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.20781095772981645,
|
|
"num_tokens": 26845321.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.135073566436768,
|
|
"epoch": 1.2195121951219512,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048558792041513446,
|
|
"loss": 4.8284,
|
|
"mean_token_accuracy": 0.20998603403568267,
|
|
"num_tokens": 26853866.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.093303155899048,
|
|
"epoch": 1.2199298362846642,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004855774352908273,
|
|
"loss": 4.841,
|
|
"mean_token_accuracy": 0.20932035595178605,
|
|
"num_tokens": 26863581.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.1862140655517575,
|
|
"epoch": 1.2203474774473773,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004855669464801088,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.20711832493543625,
|
|
"num_tokens": 26873481.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.227762126922608,
|
|
"epoch": 1.2207651186100903,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048555645398316237,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.19968123137950897,
|
|
"num_tokens": 26882222.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.205530405044556,
|
|
"epoch": 1.221182759772803,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004855459578001718,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.1995491400361061,
|
|
"num_tokens": 26891305.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.178498888015747,
|
|
"epoch": 1.2216004009355161,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004855354579313208,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.20364181101322174,
|
|
"num_tokens": 26901759.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.218368148803711,
|
|
"epoch": 1.2220180420982292,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004855249543767932,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.19963036924600602,
|
|
"num_tokens": 26911183.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.192747640609741,
|
|
"epoch": 1.2224356832609422,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048551444713677285,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.1953968659043312,
|
|
"num_tokens": 26921185.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.154981517791748,
|
|
"epoch": 1.2228533244236552,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048550393621144374,
|
|
"loss": 4.8211,
|
|
"mean_token_accuracy": 0.21093014776706695,
|
|
"num_tokens": 26930034.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.105802536010742,
|
|
"epoch": 1.2232709655863683,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004854934216009898,
|
|
"loss": 4.8898,
|
|
"mean_token_accuracy": 0.21005679219961165,
|
|
"num_tokens": 26939273.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.125222253799438,
|
|
"epoch": 1.2236886067490813,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004854829033055951,
|
|
"loss": 4.9156,
|
|
"mean_token_accuracy": 0.20484028160572051,
|
|
"num_tokens": 26948924.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.115103101730346,
|
|
"epoch": 1.2241062479117941,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004854723813254439,
|
|
"loss": 4.8273,
|
|
"mean_token_accuracy": 0.20963678658008575,
|
|
"num_tokens": 26957492.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.166096878051758,
|
|
"epoch": 1.2245238890745072,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004854618556607203,
|
|
"loss": 5.0377,
|
|
"mean_token_accuracy": 0.19760544300079347,
|
|
"num_tokens": 26967114.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.290770149230957,
|
|
"epoch": 1.2249415302372202,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048545132631160856,
|
|
"loss": 4.9942,
|
|
"mean_token_accuracy": 0.1987449496984482,
|
|
"num_tokens": 26976661.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.227971982955933,
|
|
"epoch": 1.2253591713999332,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004854407932782931,
|
|
"loss": 5.0161,
|
|
"mean_token_accuracy": 0.20316352993249892,
|
|
"num_tokens": 26986044.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.11852126121521,
|
|
"epoch": 1.2257768125626463,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004854302565609582,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.20548736304044724,
|
|
"num_tokens": 26995166.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.170224046707153,
|
|
"epoch": 1.226194453725359,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048541971615978833,
|
|
"loss": 4.9704,
|
|
"mean_token_accuracy": 0.19872014224529266,
|
|
"num_tokens": 27004245.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.228067350387573,
|
|
"epoch": 1.226612094888072,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00048540917207496806,
|
|
"loss": 5.0647,
|
|
"mean_token_accuracy": 0.19724346250295638,
|
|
"num_tokens": 27013278.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.194910383224487,
|
|
"epoch": 1.2270297360507851,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048539862430668204,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20330731719732284,
|
|
"num_tokens": 27022387.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.1644142150878904,
|
|
"epoch": 1.2274473772134982,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048538807285511474,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.2004190430045128,
|
|
"num_tokens": 27031760.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.20043683052063,
|
|
"epoch": 1.2278650183762112,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048537751772045103,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.21603277027606965,
|
|
"num_tokens": 27040908.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.181299161911011,
|
|
"epoch": 1.2282826595389242,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004853669589028757,
|
|
"loss": 4.9265,
|
|
"mean_token_accuracy": 0.20820981860160828,
|
|
"num_tokens": 27049989.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.098298692703247,
|
|
"epoch": 1.2287003007016373,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004853563964025734,
|
|
"loss": 4.9144,
|
|
"mean_token_accuracy": 0.20996073633432388,
|
|
"num_tokens": 27058706.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.096966505050659,
|
|
"epoch": 1.22911794186435,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048534583021972926,
|
|
"loss": 4.892,
|
|
"mean_token_accuracy": 0.20566961914300919,
|
|
"num_tokens": 27067604.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.153396654129028,
|
|
"epoch": 1.2295355830270631,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004853352603545281,
|
|
"loss": 4.9365,
|
|
"mean_token_accuracy": 0.20968307703733444,
|
|
"num_tokens": 27076489.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.1602373123168945,
|
|
"epoch": 1.2299532241897762,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004853246868071551,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.20618190318346025,
|
|
"num_tokens": 27085750.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.150932931900025,
|
|
"epoch": 1.2303708653524892,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048531410957779533,
|
|
"loss": 4.9084,
|
|
"mean_token_accuracy": 0.20786479860544205,
|
|
"num_tokens": 27095509.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.09764552116394,
|
|
"epoch": 1.2307885065152022,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004853035286666338,
|
|
"loss": 4.9186,
|
|
"mean_token_accuracy": 0.20642659664154053,
|
|
"num_tokens": 27105054.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.199010229110717,
|
|
"epoch": 1.231206147677915,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000485292944073856,
|
|
"loss": 5.0302,
|
|
"mean_token_accuracy": 0.2037755846977234,
|
|
"num_tokens": 27113497.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.2527931213378904,
|
|
"epoch": 1.231623788840628,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000485282355799647,
|
|
"loss": 5.0051,
|
|
"mean_token_accuracy": 0.2051698848605156,
|
|
"num_tokens": 27122718.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.16599817276001,
|
|
"epoch": 1.232041430003341,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048527176384419217,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.20960622280836105,
|
|
"num_tokens": 27132361.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.2240269660949705,
|
|
"epoch": 1.2324590711660541,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048526116820767713,
|
|
"loss": 4.9237,
|
|
"mean_token_accuracy": 0.20689452886581422,
|
|
"num_tokens": 27141430.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.243683576583862,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004852505688902872,
|
|
"loss": 5.0129,
|
|
"mean_token_accuracy": 0.20217214971780778,
|
|
"num_tokens": 27150154.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.149538993835449,
|
|
"epoch": 1.2332943534914802,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004852399658922079,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.20948652625083924,
|
|
"num_tokens": 27159314.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.210212755203247,
|
|
"epoch": 1.2337119946541932,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004852293592136251,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.197274249792099,
|
|
"num_tokens": 27167537.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.248903226852417,
|
|
"epoch": 1.234129635816906,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004852187488547242,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.19964949935674667,
|
|
"num_tokens": 27177037.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.196665191650391,
|
|
"epoch": 1.234547276979619,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048520813481569116,
|
|
"loss": 5.0221,
|
|
"mean_token_accuracy": 0.1987486720085144,
|
|
"num_tokens": 27186498.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.154570627212524,
|
|
"epoch": 1.2349649181423321,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004851975170967116,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.21129745692014695,
|
|
"num_tokens": 27195170.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.167276287078858,
|
|
"epoch": 1.2353825593050451,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004851868956979715,
|
|
"loss": 4.9015,
|
|
"mean_token_accuracy": 0.20844382494688035,
|
|
"num_tokens": 27204756.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 4.999532985687256,
|
|
"epoch": 1.2358002004677582,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004851762706196568,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.20051447302103043,
|
|
"num_tokens": 27213607.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.167258262634277,
|
|
"epoch": 1.236217841630471,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048516564186195353,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.2076592355966568,
|
|
"num_tokens": 27222887.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.231129741668701,
|
|
"epoch": 1.236635482793184,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048515500942504763,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2033357560634613,
|
|
"num_tokens": 27231374.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.2369263648986815,
|
|
"epoch": 1.237053123955897,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048514437330912544,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.19605533480644227,
|
|
"num_tokens": 27239929.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.165923738479615,
|
|
"epoch": 1.23747076511861,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048513373351437294,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.20035431236028672,
|
|
"num_tokens": 27249789.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.170178461074829,
|
|
"epoch": 1.2378884062813231,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048512309004097653,
|
|
"loss": 4.9381,
|
|
"mean_token_accuracy": 0.20190029591321945,
|
|
"num_tokens": 27259773.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.29471230506897,
|
|
"epoch": 1.2383060474440362,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004851124428891226,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.19736886024475098,
|
|
"num_tokens": 27268494.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.220165205001831,
|
|
"epoch": 1.2387236886067492,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004851017920589973,
|
|
"loss": 4.9622,
|
|
"mean_token_accuracy": 0.2003882810473442,
|
|
"num_tokens": 27276914.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.129614210128784,
|
|
"epoch": 1.239141329769462,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004850911375507873,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.20690634250640869,
|
|
"num_tokens": 27286091.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.210960721969604,
|
|
"epoch": 1.239558970932175,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048508047936467907,
|
|
"loss": 4.9972,
|
|
"mean_token_accuracy": 0.2051364302635193,
|
|
"num_tokens": 27295201.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.228882312774658,
|
|
"epoch": 1.239976612094888,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048506981750085914,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.2096265971660614,
|
|
"num_tokens": 27303900.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.159246015548706,
|
|
"epoch": 1.240394253257601,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048505915195951423,
|
|
"loss": 4.9386,
|
|
"mean_token_accuracy": 0.20610670000314713,
|
|
"num_tokens": 27312613.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.145587539672851,
|
|
"epoch": 1.2408118944203141,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048504848274083095,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.20542112737894058,
|
|
"num_tokens": 27322047.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.280626583099365,
|
|
"epoch": 1.241229535583027,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048503780984499625,
|
|
"loss": 5.193,
|
|
"mean_token_accuracy": 0.18792821019887923,
|
|
"num_tokens": 27332163.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.268613195419311,
|
|
"epoch": 1.24164717674574,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004850271332721968,
|
|
"loss": 4.9933,
|
|
"mean_token_accuracy": 0.19999616146087645,
|
|
"num_tokens": 27343838.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.254788970947265,
|
|
"epoch": 1.242064817908453,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004850164530226196,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.2130851849913597,
|
|
"num_tokens": 27352362.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.178209066390991,
|
|
"epoch": 1.242482459071166,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004850057690964515,
|
|
"loss": 5.0498,
|
|
"mean_token_accuracy": 0.19359085857868194,
|
|
"num_tokens": 27361444.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.096546363830567,
|
|
"epoch": 1.242900100233879,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048499508149387973,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.2037036493420601,
|
|
"num_tokens": 27370872.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.145865154266358,
|
|
"epoch": 1.2433177413965921,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048498439021509124,
|
|
"loss": 4.9422,
|
|
"mean_token_accuracy": 0.20644918829202652,
|
|
"num_tokens": 27380628.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.210357427597046,
|
|
"epoch": 1.2437353825593052,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004849736952602732,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.20614794343709947,
|
|
"num_tokens": 27390187.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.2617920398712155,
|
|
"epoch": 1.244153023722018,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000484962996629613,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.19085199534893035,
|
|
"num_tokens": 27400307.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.233146238327026,
|
|
"epoch": 1.244570664884731,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048495229432329775,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.20135580897331237,
|
|
"num_tokens": 27410060.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.219910287857056,
|
|
"epoch": 1.244988306047444,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048494158834151485,
|
|
"loss": 5.011,
|
|
"mean_token_accuracy": 0.1999530240893364,
|
|
"num_tokens": 27419119.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.182317018508911,
|
|
"epoch": 1.245405947210157,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048493087868445176,
|
|
"loss": 4.8978,
|
|
"mean_token_accuracy": 0.21152960360050202,
|
|
"num_tokens": 27428052.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.165277910232544,
|
|
"epoch": 1.24582358837287,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048492016535229594,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2063406303524971,
|
|
"num_tokens": 27436418.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.179647541046142,
|
|
"epoch": 1.246241229535583,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004849094483452349,
|
|
"loss": 5.0616,
|
|
"mean_token_accuracy": 0.20440271347761155,
|
|
"num_tokens": 27445609.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.171057796478271,
|
|
"epoch": 1.246658870698296,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004848987276634564,
|
|
"loss": 5.0225,
|
|
"mean_token_accuracy": 0.2003096967935562,
|
|
"num_tokens": 27456250.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.197917842864991,
|
|
"epoch": 1.247076511861009,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048488800330714795,
|
|
"loss": 4.9383,
|
|
"mean_token_accuracy": 0.19898485094308854,
|
|
"num_tokens": 27466134.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.154957008361817,
|
|
"epoch": 1.247494153023722,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048487727527649733,
|
|
"loss": 4.9505,
|
|
"mean_token_accuracy": 0.20494175255298613,
|
|
"num_tokens": 27476097.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.1492591381073,
|
|
"epoch": 1.247911794186435,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048486654357169246,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.2057437241077423,
|
|
"num_tokens": 27485850.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.199787569046021,
|
|
"epoch": 1.248329435349148,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004848558081929211,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.20572056770324706,
|
|
"num_tokens": 27494169.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.152124214172363,
|
|
"epoch": 1.2487470765118611,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004848450691403712,
|
|
"loss": 4.9615,
|
|
"mean_token_accuracy": 0.20099812746047974,
|
|
"num_tokens": 27502599.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.055132341384888,
|
|
"epoch": 1.249164717674574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004848343264142307,
|
|
"loss": 4.7231,
|
|
"mean_token_accuracy": 0.22839573323726653,
|
|
"num_tokens": 27511278.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.195808172225952,
|
|
"epoch": 1.249582358837287,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004848235800146879,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.19828079342842103,
|
|
"num_tokens": 27521040.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.190809535980224,
|
|
"epoch": 1.25,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004848128299419306,
|
|
"loss": 4.9781,
|
|
"mean_token_accuracy": 0.1986464723944664,
|
|
"num_tokens": 27530893.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.187432146072387,
|
|
"epoch": 1.250417641162713,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048480207619614726,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.2017314299941063,
|
|
"num_tokens": 27540401.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.081004905700683,
|
|
"epoch": 1.250835282325426,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000484791318777526,
|
|
"loss": 4.7966,
|
|
"mean_token_accuracy": 0.21301444619894028,
|
|
"num_tokens": 27549951.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.165010023117065,
|
|
"epoch": 1.2512529234881389,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048478055768625517,
|
|
"loss": 4.9409,
|
|
"mean_token_accuracy": 0.2008342146873474,
|
|
"num_tokens": 27559170.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.0890114307403564,
|
|
"epoch": 1.251670564650852,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048476979292252323,
|
|
"loss": 4.7998,
|
|
"mean_token_accuracy": 0.21791396141052247,
|
|
"num_tokens": 27567094.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.144490766525268,
|
|
"epoch": 1.252088205813565,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004847590244865185,
|
|
"loss": 4.9308,
|
|
"mean_token_accuracy": 0.20808619409799575,
|
|
"num_tokens": 27575141.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.185410737991333,
|
|
"epoch": 1.252505846976278,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048474825237842964,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20510129630565643,
|
|
"num_tokens": 27584094.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.240324258804321,
|
|
"epoch": 1.252923488138991,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000484737476598445,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.1942172572016716,
|
|
"num_tokens": 27593157.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.252923488138991,
|
|
"eval_entropy": 4.972418664143616,
|
|
"eval_loss": 4.976927280426025,
|
|
"eval_mean_token_accuracy": 0.2142851393337637,
|
|
"eval_num_tokens": 27593157.0,
|
|
"eval_runtime": 27.6167,
|
|
"eval_samples_per_second": 1367.399,
|
|
"eval_steps_per_second": 170.948,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"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": 4.0887597735936e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|