495a5e5409
Model: fpadovani/dan-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10 Source: Original Platform
6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.25058469762779817,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.823197078704834,
|
|
"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
|
|
}
|
|
],
|
|
"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": 8213404741632000.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|