30090 lines
827 KiB
JSON
30090 lines
827 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.252923488138991,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.742122554779053,
|
|
"epoch": 0.000417641162712997,
|
|
"grad_norm": 5.59375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.7426,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 8702.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742121601104737,
|
|
"epoch": 0.000835282325425994,
|
|
"grad_norm": 4.9375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7359,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 17355.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742114067077637,
|
|
"epoch": 0.001252923488138991,
|
|
"grad_norm": 5.1875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7158,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 25975.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742129802703857,
|
|
"epoch": 0.001670564650851988,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.6794,
|
|
"mean_token_accuracy": 0.00029278567526489494,
|
|
"num_tokens": 35099.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742053031921387,
|
|
"epoch": 0.002088205813564985,
|
|
"grad_norm": 4.875,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.5829,
|
|
"mean_token_accuracy": 0.002680328907445073,
|
|
"num_tokens": 44526.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741730117797852,
|
|
"epoch": 0.002505846976277982,
|
|
"grad_norm": 4.5,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.4495,
|
|
"mean_token_accuracy": 0.025214007031172513,
|
|
"num_tokens": 53856.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740700435638427,
|
|
"epoch": 0.002923488138990979,
|
|
"grad_norm": 3.3125,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3326,
|
|
"mean_token_accuracy": 0.04184841923415661,
|
|
"num_tokens": 63583.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.737869358062744,
|
|
"epoch": 0.003341129301703976,
|
|
"grad_norm": 2.796875,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.1371,
|
|
"mean_token_accuracy": 0.04405288808047771,
|
|
"num_tokens": 71894.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.73253116607666,
|
|
"epoch": 0.003758770464416973,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0595,
|
|
"mean_token_accuracy": 0.04489131569862366,
|
|
"num_tokens": 81234.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.726473808288574,
|
|
"epoch": 0.00417641162712997,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.9743,
|
|
"mean_token_accuracy": 0.04135479014366865,
|
|
"num_tokens": 90759.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.72225399017334,
|
|
"epoch": 0.004594052789842967,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9276,
|
|
"mean_token_accuracy": 0.042906027659773825,
|
|
"num_tokens": 100765.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.71838436126709,
|
|
"epoch": 0.005011693952555964,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.8575,
|
|
"mean_token_accuracy": 0.04668322093784809,
|
|
"num_tokens": 110317.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.714269351959228,
|
|
"epoch": 0.005429335115268961,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.7809,
|
|
"mean_token_accuracy": 0.04387491997331381,
|
|
"num_tokens": 119665.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.711958026885986,
|
|
"epoch": 0.005846976277981958,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.7164,
|
|
"mean_token_accuracy": 0.04178145974874496,
|
|
"num_tokens": 128083.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.710527801513672,
|
|
"epoch": 0.006264617440694955,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.6655,
|
|
"mean_token_accuracy": 0.04346162974834442,
|
|
"num_tokens": 137168.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.705409908294678,
|
|
"epoch": 0.006682258603407952,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.5644,
|
|
"mean_token_accuracy": 0.04724513851106167,
|
|
"num_tokens": 146023.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.697060108184814,
|
|
"epoch": 0.007099899766120949,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.539,
|
|
"mean_token_accuracy": 0.043902423605322836,
|
|
"num_tokens": 154392.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.686701488494872,
|
|
"epoch": 0.007517540928833946,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.4266,
|
|
"mean_token_accuracy": 0.04443326331675053,
|
|
"num_tokens": 163673.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.679195785522461,
|
|
"epoch": 0.007935182091546943,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.3917,
|
|
"mean_token_accuracy": 0.04754145070910454,
|
|
"num_tokens": 172879.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.668279361724853,
|
|
"epoch": 0.00835282325425994,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.311,
|
|
"mean_token_accuracy": 0.05805562548339367,
|
|
"num_tokens": 183378.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.64778175354004,
|
|
"epoch": 0.008770464416972937,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.1882,
|
|
"mean_token_accuracy": 0.058023329451680185,
|
|
"num_tokens": 192255.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.609379386901855,
|
|
"epoch": 0.009188105579685933,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.0856,
|
|
"mean_token_accuracy": 0.05645543336868286,
|
|
"num_tokens": 202118.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.552488803863525,
|
|
"epoch": 0.00960574674239893,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.9239,
|
|
"mean_token_accuracy": 0.05940695628523827,
|
|
"num_tokens": 210536.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.494095134735108,
|
|
"epoch": 0.010023387905111928,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.8123,
|
|
"mean_token_accuracy": 0.05913706123828888,
|
|
"num_tokens": 219577.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.45734453201294,
|
|
"epoch": 0.010441029067824925,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.7051,
|
|
"mean_token_accuracy": 0.057156120985746385,
|
|
"num_tokens": 227676.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.395902347564697,
|
|
"epoch": 0.010858670230537921,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.5495,
|
|
"mean_token_accuracy": 0.06603703089058399,
|
|
"num_tokens": 236692.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.323854541778564,
|
|
"epoch": 0.011276311393250919,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.5097,
|
|
"mean_token_accuracy": 0.05694400519132614,
|
|
"num_tokens": 246143.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.26358995437622,
|
|
"epoch": 0.011693952555963916,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.3347,
|
|
"mean_token_accuracy": 0.06364477723836899,
|
|
"num_tokens": 255263.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.139849853515624,
|
|
"epoch": 0.012111593718676913,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.2469,
|
|
"mean_token_accuracy": 0.06181924939155579,
|
|
"num_tokens": 264219.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.00226879119873,
|
|
"epoch": 0.01252923488138991,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.1372,
|
|
"mean_token_accuracy": 0.06256255879998207,
|
|
"num_tokens": 274819.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 9.904099082946777,
|
|
"epoch": 0.012946876044102907,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.0018,
|
|
"mean_token_accuracy": 0.06529068276286125,
|
|
"num_tokens": 284382.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.72164478302002,
|
|
"epoch": 0.013364517206815904,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.9077,
|
|
"mean_token_accuracy": 0.06376104950904846,
|
|
"num_tokens": 294457.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.5483229637146,
|
|
"epoch": 0.013782158369528901,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.7723,
|
|
"mean_token_accuracy": 0.0630855705589056,
|
|
"num_tokens": 303788.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.329432392120362,
|
|
"epoch": 0.014199799532241897,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.7114,
|
|
"mean_token_accuracy": 0.0626518715173006,
|
|
"num_tokens": 312815.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.140421104431152,
|
|
"epoch": 0.014617440694954895,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6501,
|
|
"mean_token_accuracy": 0.06696275398135185,
|
|
"num_tokens": 323599.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.923584079742431,
|
|
"epoch": 0.015035081857667892,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.5714,
|
|
"mean_token_accuracy": 0.06868262700736523,
|
|
"num_tokens": 332788.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.773529720306396,
|
|
"epoch": 0.01545272302038089,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.557,
|
|
"mean_token_accuracy": 0.06944454908370971,
|
|
"num_tokens": 342528.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.585641288757325,
|
|
"epoch": 0.015870364183093885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.4513,
|
|
"mean_token_accuracy": 0.07589564621448516,
|
|
"num_tokens": 350404.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.316099929809571,
|
|
"epoch": 0.016288005345806884,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.3716,
|
|
"mean_token_accuracy": 0.0725555706769228,
|
|
"num_tokens": 360806.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.30558967590332,
|
|
"epoch": 0.01670564650851988,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.3737,
|
|
"mean_token_accuracy": 0.07712265998125076,
|
|
"num_tokens": 370236.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.26392936706543,
|
|
"epoch": 0.017123287671232876,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.3407,
|
|
"mean_token_accuracy": 0.07612420171499253,
|
|
"num_tokens": 380409.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.188503170013428,
|
|
"epoch": 0.017540928833945875,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.2554,
|
|
"mean_token_accuracy": 0.0819562017917633,
|
|
"num_tokens": 389797.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.090349197387695,
|
|
"epoch": 0.01795856999665887,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1638,
|
|
"mean_token_accuracy": 0.08251158446073532,
|
|
"num_tokens": 398867.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.969277334213257,
|
|
"epoch": 0.018376211159371866,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.3557,
|
|
"mean_token_accuracy": 0.07762790322303773,
|
|
"num_tokens": 409921.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.04366888999939,
|
|
"epoch": 0.018793852322084866,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.16,
|
|
"mean_token_accuracy": 0.08810438439249993,
|
|
"num_tokens": 418962.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.852949237823486,
|
|
"epoch": 0.01921149348479786,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1777,
|
|
"mean_token_accuracy": 0.08824707269668579,
|
|
"num_tokens": 428111.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.989979887008667,
|
|
"epoch": 0.01962913464751086,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.2081,
|
|
"mean_token_accuracy": 0.08595793023705482,
|
|
"num_tokens": 437370.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.886132049560547,
|
|
"epoch": 0.020046775810223856,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.0847,
|
|
"mean_token_accuracy": 0.08573980554938317,
|
|
"num_tokens": 446687.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.9483672142028805,
|
|
"epoch": 0.020464416972936852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.2439,
|
|
"mean_token_accuracy": 0.07872043699026107,
|
|
"num_tokens": 455306.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.801475906372071,
|
|
"epoch": 0.02088205813564985,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.1467,
|
|
"mean_token_accuracy": 0.08012107759714127,
|
|
"num_tokens": 465491.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.833319616317749,
|
|
"epoch": 0.021299699298362847,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.1415,
|
|
"mean_token_accuracy": 0.08490735366940498,
|
|
"num_tokens": 475782.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.83586573600769,
|
|
"epoch": 0.021717340461075842,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.1472,
|
|
"mean_token_accuracy": 0.08664263188838958,
|
|
"num_tokens": 484901.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.776985597610474,
|
|
"epoch": 0.02213498162378884,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.072,
|
|
"mean_token_accuracy": 0.08647527918219566,
|
|
"num_tokens": 493742.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.73929386138916,
|
|
"epoch": 0.022552622786501837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.0923,
|
|
"mean_token_accuracy": 0.08229703679680825,
|
|
"num_tokens": 502959.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.730380439758301,
|
|
"epoch": 0.022970263949214833,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0222,
|
|
"mean_token_accuracy": 0.08907360509037972,
|
|
"num_tokens": 512003.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.7105358123779295,
|
|
"epoch": 0.023387905111927832,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.1147,
|
|
"mean_token_accuracy": 0.0869998462498188,
|
|
"num_tokens": 520680.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.667366695404053,
|
|
"epoch": 0.023805546274640828,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.0402,
|
|
"mean_token_accuracy": 0.08833886310458183,
|
|
"num_tokens": 529001.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.6311241626739506,
|
|
"epoch": 0.024223187437353827,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.0129,
|
|
"mean_token_accuracy": 0.0985827162861824,
|
|
"num_tokens": 537309.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.624583101272583,
|
|
"epoch": 0.024640828600066823,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9437,
|
|
"mean_token_accuracy": 0.09322682172060012,
|
|
"num_tokens": 546436.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.56837830543518,
|
|
"epoch": 0.02505846976277982,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.0198,
|
|
"mean_token_accuracy": 0.09756411463022233,
|
|
"num_tokens": 555634.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.483178758621216,
|
|
"epoch": 0.025476110925492818,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8692,
|
|
"mean_token_accuracy": 0.09527311623096466,
|
|
"num_tokens": 564781.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.586818838119507,
|
|
"epoch": 0.025893752088205813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.0743,
|
|
"mean_token_accuracy": 0.0929844930768013,
|
|
"num_tokens": 575130.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.626620864868164,
|
|
"epoch": 0.02631139325091881,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.0136,
|
|
"mean_token_accuracy": 0.08612743467092514,
|
|
"num_tokens": 584030.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.515700101852417,
|
|
"epoch": 0.026729034413631808,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.9211,
|
|
"mean_token_accuracy": 0.09688968062400818,
|
|
"num_tokens": 593079.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.4722246646881105,
|
|
"epoch": 0.027146675576344804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8694,
|
|
"mean_token_accuracy": 0.10736346021294593,
|
|
"num_tokens": 601830.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.49754638671875,
|
|
"epoch": 0.027564316739057803,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.8304,
|
|
"mean_token_accuracy": 0.09651741534471511,
|
|
"num_tokens": 610296.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.4197306632995605,
|
|
"epoch": 0.0279819579017708,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8731,
|
|
"mean_token_accuracy": 0.09373932555317879,
|
|
"num_tokens": 619762.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.420308685302734,
|
|
"epoch": 0.028399599064483794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.8909,
|
|
"mean_token_accuracy": 0.09487934783101082,
|
|
"num_tokens": 629271.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.52911901473999,
|
|
"epoch": 0.028817240227196794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.9938,
|
|
"mean_token_accuracy": 0.08758045360445976,
|
|
"num_tokens": 638425.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.482238721847534,
|
|
"epoch": 0.02923488138990979,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.9674,
|
|
"mean_token_accuracy": 0.09015953838825226,
|
|
"num_tokens": 647322.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.503779792785645,
|
|
"epoch": 0.029652522552622785,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.9697,
|
|
"mean_token_accuracy": 0.08973397910594941,
|
|
"num_tokens": 656511.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.481411170959473,
|
|
"epoch": 0.030070163715335784,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8918,
|
|
"mean_token_accuracy": 0.0935517430305481,
|
|
"num_tokens": 667039.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.378106498718262,
|
|
"epoch": 0.03048780487804878,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.766,
|
|
"mean_token_accuracy": 0.0998542919754982,
|
|
"num_tokens": 676065.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.464444732666015,
|
|
"epoch": 0.03090544604076178,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9181,
|
|
"mean_token_accuracy": 0.09695194140076638,
|
|
"num_tokens": 684344.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.335521030426025,
|
|
"epoch": 0.03132308720347477,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.873,
|
|
"mean_token_accuracy": 0.09614600911736489,
|
|
"num_tokens": 692839.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.4365702152252195,
|
|
"epoch": 0.03174072836618777,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.845,
|
|
"mean_token_accuracy": 0.09973672106862068,
|
|
"num_tokens": 702689.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.325565671920776,
|
|
"epoch": 0.03215836952890077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.8415,
|
|
"mean_token_accuracy": 0.0916935682296753,
|
|
"num_tokens": 711579.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.428183269500733,
|
|
"epoch": 0.03257601069161377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.7867,
|
|
"mean_token_accuracy": 0.09845689535140992,
|
|
"num_tokens": 720469.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.209290266036987,
|
|
"epoch": 0.03299365185432676,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7604,
|
|
"mean_token_accuracy": 0.09956807419657707,
|
|
"num_tokens": 730326.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.355399799346924,
|
|
"epoch": 0.03341129301703976,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7572,
|
|
"mean_token_accuracy": 0.10625478997826576,
|
|
"num_tokens": 738992.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.229115772247314,
|
|
"epoch": 0.03382893417975276,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.8151,
|
|
"mean_token_accuracy": 0.09731377884745598,
|
|
"num_tokens": 748387.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.369128704071045,
|
|
"epoch": 0.03424657534246575,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7356,
|
|
"mean_token_accuracy": 0.10202734097838402,
|
|
"num_tokens": 757712.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.201074743270874,
|
|
"epoch": 0.03466421650517875,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7106,
|
|
"mean_token_accuracy": 0.09947160556912422,
|
|
"num_tokens": 766626.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.218473052978515,
|
|
"epoch": 0.03508185766789175,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.6622,
|
|
"mean_token_accuracy": 0.10467798709869384,
|
|
"num_tokens": 775942.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.319445276260376,
|
|
"epoch": 0.03549949883060474,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.743,
|
|
"mean_token_accuracy": 0.10339497774839401,
|
|
"num_tokens": 784680.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.324266147613526,
|
|
"epoch": 0.03591713999331774,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8274,
|
|
"mean_token_accuracy": 0.09892603307962418,
|
|
"num_tokens": 794107.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.254756164550781,
|
|
"epoch": 0.03633478115603074,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.796,
|
|
"mean_token_accuracy": 0.10009015426039695,
|
|
"num_tokens": 803584.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.310313606262207,
|
|
"epoch": 0.03675242231874373,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7773,
|
|
"mean_token_accuracy": 0.10064135193824768,
|
|
"num_tokens": 812460.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.196012496948242,
|
|
"epoch": 0.03717006348145673,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7503,
|
|
"mean_token_accuracy": 0.10141536369919776,
|
|
"num_tokens": 821946.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.204004621505737,
|
|
"epoch": 0.03758770464416973,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.6911,
|
|
"mean_token_accuracy": 0.09515870362520218,
|
|
"num_tokens": 831781.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.2210071086883545,
|
|
"epoch": 0.03800534580688272,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.6405,
|
|
"mean_token_accuracy": 0.10319173634052277,
|
|
"num_tokens": 840903.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.1188592433929445,
|
|
"epoch": 0.03842298696959572,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.1028764121234417,
|
|
"num_tokens": 850545.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.177313804626465,
|
|
"epoch": 0.03884062813230872,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.726,
|
|
"mean_token_accuracy": 0.10074673295021057,
|
|
"num_tokens": 860606.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.329133081436157,
|
|
"epoch": 0.03925826929502172,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7694,
|
|
"mean_token_accuracy": 0.10264237001538276,
|
|
"num_tokens": 868767.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.103873348236084,
|
|
"epoch": 0.03967591045773471,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6409,
|
|
"mean_token_accuracy": 0.1013137087225914,
|
|
"num_tokens": 877820.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.212535333633423,
|
|
"epoch": 0.04009355162044771,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7729,
|
|
"mean_token_accuracy": 0.09580215588212013,
|
|
"num_tokens": 887035.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.261131954193115,
|
|
"epoch": 0.04051119278316071,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.7436,
|
|
"mean_token_accuracy": 0.10203550904989242,
|
|
"num_tokens": 896249.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.094175338745117,
|
|
"epoch": 0.040928833945873704,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6564,
|
|
"mean_token_accuracy": 0.09608230963349343,
|
|
"num_tokens": 905307.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.0745786190032955,
|
|
"epoch": 0.0413464751085867,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6378,
|
|
"mean_token_accuracy": 0.10336728692054749,
|
|
"num_tokens": 914587.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.122777318954467,
|
|
"epoch": 0.0417641162712997,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.5584,
|
|
"mean_token_accuracy": 0.11078567281365395,
|
|
"num_tokens": 923361.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.154393339157105,
|
|
"epoch": 0.042181757434012694,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.6615,
|
|
"mean_token_accuracy": 0.10329530760645866,
|
|
"num_tokens": 931698.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.1185431480407715,
|
|
"epoch": 0.04259939859672569,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6228,
|
|
"mean_token_accuracy": 0.1053171068429947,
|
|
"num_tokens": 940141.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.98853235244751,
|
|
"epoch": 0.04301703975943869,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5873,
|
|
"mean_token_accuracy": 0.10950357466936111,
|
|
"num_tokens": 948926.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.208238315582276,
|
|
"epoch": 0.043434680922151685,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6677,
|
|
"mean_token_accuracy": 0.10224388837814331,
|
|
"num_tokens": 957995.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.085497188568115,
|
|
"epoch": 0.043852322084864684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6741,
|
|
"mean_token_accuracy": 0.10617537721991539,
|
|
"num_tokens": 968004.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.1213349342346195,
|
|
"epoch": 0.04426996324757768,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6951,
|
|
"mean_token_accuracy": 0.10752663984894753,
|
|
"num_tokens": 977931.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.977365303039551,
|
|
"epoch": 0.044687604410290675,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6561,
|
|
"mean_token_accuracy": 0.10034975931048393,
|
|
"num_tokens": 986904.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.063871145248413,
|
|
"epoch": 0.045105245573003674,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6027,
|
|
"mean_token_accuracy": 0.10650393143296241,
|
|
"num_tokens": 997482.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.0778279304504395,
|
|
"epoch": 0.045522886735716674,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6128,
|
|
"mean_token_accuracy": 0.10725649818778038,
|
|
"num_tokens": 1007196.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.058020162582397,
|
|
"epoch": 0.045940527898429666,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.7021,
|
|
"mean_token_accuracy": 0.10655904859304428,
|
|
"num_tokens": 1016435.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.029399967193603,
|
|
"epoch": 0.046358169061142665,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.5814,
|
|
"mean_token_accuracy": 0.10815284475684166,
|
|
"num_tokens": 1026299.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.969214200973511,
|
|
"epoch": 0.046775810223855664,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5411,
|
|
"mean_token_accuracy": 0.11086997389793396,
|
|
"num_tokens": 1034672.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.929189205169678,
|
|
"epoch": 0.04719345138656866,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5294,
|
|
"mean_token_accuracy": 0.11677401661872863,
|
|
"num_tokens": 1042786.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.0000075340271,
|
|
"epoch": 0.047611092549281656,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.5073,
|
|
"mean_token_accuracy": 0.11181584969162942,
|
|
"num_tokens": 1052709.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.024741125106812,
|
|
"epoch": 0.048028733711994655,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5826,
|
|
"mean_token_accuracy": 0.10405817180871964,
|
|
"num_tokens": 1061880.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.037390232086182,
|
|
"epoch": 0.048446374874707654,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5537,
|
|
"mean_token_accuracy": 0.10765022113919258,
|
|
"num_tokens": 1071234.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.0248270511627195,
|
|
"epoch": 0.048864016037420646,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.10200266987085342,
|
|
"num_tokens": 1081252.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.906812763214111,
|
|
"epoch": 0.049281657200133645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5343,
|
|
"mean_token_accuracy": 0.10761479586362839,
|
|
"num_tokens": 1090642.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.004644918441772,
|
|
"epoch": 0.049699298362846644,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.1107115812599659,
|
|
"num_tokens": 1099918.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.037489223480224,
|
|
"epoch": 0.05011693952555964,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.5498,
|
|
"mean_token_accuracy": 0.10938952788710594,
|
|
"num_tokens": 1109521.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.80020923614502,
|
|
"epoch": 0.050534580688272636,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.4223,
|
|
"mean_token_accuracy": 0.12316331788897514,
|
|
"num_tokens": 1118140.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.91481761932373,
|
|
"epoch": 0.050952221850985635,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.5787,
|
|
"mean_token_accuracy": 0.10839839428663253,
|
|
"num_tokens": 1127591.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.027100372314453,
|
|
"epoch": 0.05136986301369863,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.5591,
|
|
"mean_token_accuracy": 0.1044753447175026,
|
|
"num_tokens": 1136223.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.935626745223999,
|
|
"epoch": 0.051787504176411626,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4368,
|
|
"mean_token_accuracy": 0.11771413609385491,
|
|
"num_tokens": 1146367.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.7960490703582765,
|
|
"epoch": 0.052205145339124626,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.11227771192789078,
|
|
"num_tokens": 1156230.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.978573226928711,
|
|
"epoch": 0.05262278650183762,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.5624,
|
|
"mean_token_accuracy": 0.10628528222441673,
|
|
"num_tokens": 1166106.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.914755392074585,
|
|
"epoch": 0.05304042766455062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5656,
|
|
"mean_token_accuracy": 0.11575563699007034,
|
|
"num_tokens": 1174887.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.908324193954468,
|
|
"epoch": 0.053458068827263616,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5233,
|
|
"mean_token_accuracy": 0.12051590755581856,
|
|
"num_tokens": 1184027.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.857800912857056,
|
|
"epoch": 0.053875709989976615,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4713,
|
|
"mean_token_accuracy": 0.1128120668232441,
|
|
"num_tokens": 1194632.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.883691072463989,
|
|
"epoch": 0.05429335115268961,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.4153,
|
|
"mean_token_accuracy": 0.12454415932297706,
|
|
"num_tokens": 1204601.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.806664991378784,
|
|
"epoch": 0.05471099231540261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6042,
|
|
"mean_token_accuracy": 0.11112436130642891,
|
|
"num_tokens": 1213288.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.8806665420532225,
|
|
"epoch": 0.055128633478115606,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5376,
|
|
"mean_token_accuracy": 0.11152591183781624,
|
|
"num_tokens": 1222768.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.910279750823975,
|
|
"epoch": 0.0555462746408286,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5191,
|
|
"mean_token_accuracy": 0.1134497992694378,
|
|
"num_tokens": 1232421.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.828466987609863,
|
|
"epoch": 0.0559639158035416,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.3929,
|
|
"mean_token_accuracy": 0.12303503230214119,
|
|
"num_tokens": 1241230.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.886627149581909,
|
|
"epoch": 0.056381556966254597,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5597,
|
|
"mean_token_accuracy": 0.11267556771636009,
|
|
"num_tokens": 1250879.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.886648941040039,
|
|
"epoch": 0.05679919812896759,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4169,
|
|
"mean_token_accuracy": 0.12256434261798858,
|
|
"num_tokens": 1259073.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.741843509674072,
|
|
"epoch": 0.05721683929168059,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4493,
|
|
"mean_token_accuracy": 0.11314508318901062,
|
|
"num_tokens": 1269174.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.916187334060669,
|
|
"epoch": 0.05763448045439359,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6023,
|
|
"mean_token_accuracy": 0.11100954487919808,
|
|
"num_tokens": 1279366.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.768966245651245,
|
|
"epoch": 0.05805212161710658,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4105,
|
|
"mean_token_accuracy": 0.11207879930734635,
|
|
"num_tokens": 1288879.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.743048238754272,
|
|
"epoch": 0.05846976277981958,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.3024,
|
|
"mean_token_accuracy": 0.11753646731376648,
|
|
"num_tokens": 1298098.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.770110464096069,
|
|
"epoch": 0.05888740394253258,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4606,
|
|
"mean_token_accuracy": 0.11356354281306266,
|
|
"num_tokens": 1306960.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.854166841506958,
|
|
"epoch": 0.05930504510524557,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5218,
|
|
"mean_token_accuracy": 0.11107228845357894,
|
|
"num_tokens": 1317252.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.823494577407837,
|
|
"epoch": 0.05972268626795857,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.427,
|
|
"mean_token_accuracy": 0.11604731008410454,
|
|
"num_tokens": 1326712.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.788588237762451,
|
|
"epoch": 0.06014032743067157,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4856,
|
|
"mean_token_accuracy": 0.11697607561945915,
|
|
"num_tokens": 1336205.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.823712778091431,
|
|
"epoch": 0.06055796859338457,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4533,
|
|
"mean_token_accuracy": 0.1154071107506752,
|
|
"num_tokens": 1345347.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.788979196548462,
|
|
"epoch": 0.06097560975609756,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.11326988786458969,
|
|
"num_tokens": 1354267.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.707552146911621,
|
|
"epoch": 0.06139325091881056,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.4253,
|
|
"mean_token_accuracy": 0.10984169691801071,
|
|
"num_tokens": 1363949.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.847339773178101,
|
|
"epoch": 0.06181089208152356,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.46,
|
|
"mean_token_accuracy": 0.11028305515646934,
|
|
"num_tokens": 1374405.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.574991655349732,
|
|
"epoch": 0.06222853324423655,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.3733,
|
|
"mean_token_accuracy": 0.12012771666049957,
|
|
"num_tokens": 1384156.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.7866004467010494,
|
|
"epoch": 0.06264617440694954,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.3843,
|
|
"mean_token_accuracy": 0.12277914807200432,
|
|
"num_tokens": 1393896.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.672963714599609,
|
|
"epoch": 0.06306381556966255,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.2705,
|
|
"mean_token_accuracy": 0.1256583385169506,
|
|
"num_tokens": 1403842.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.712489080429077,
|
|
"epoch": 0.06348145673237554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.3878,
|
|
"mean_token_accuracy": 0.12302643731236458,
|
|
"num_tokens": 1412644.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.6753857135772705,
|
|
"epoch": 0.06389909789508853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.3293,
|
|
"mean_token_accuracy": 0.12695508673787118,
|
|
"num_tokens": 1421815.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.762657022476196,
|
|
"epoch": 0.06431673905780154,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4556,
|
|
"mean_token_accuracy": 0.11635951921343804,
|
|
"num_tokens": 1431572.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.64413104057312,
|
|
"epoch": 0.06473438022051453,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.3452,
|
|
"mean_token_accuracy": 0.12333026081323624,
|
|
"num_tokens": 1440609.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.771637105941773,
|
|
"epoch": 0.06515202138322754,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4553,
|
|
"mean_token_accuracy": 0.12362872958183288,
|
|
"num_tokens": 1451193.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.616492509841919,
|
|
"epoch": 0.06556966254594053,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.263,
|
|
"mean_token_accuracy": 0.12763497680425645,
|
|
"num_tokens": 1459772.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.700885200500489,
|
|
"epoch": 0.06598730370865352,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3668,
|
|
"mean_token_accuracy": 0.1201256386935711,
|
|
"num_tokens": 1469251.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.637189674377441,
|
|
"epoch": 0.06640494487136653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.486,
|
|
"mean_token_accuracy": 0.11636328250169754,
|
|
"num_tokens": 1478090.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.766718864440918,
|
|
"epoch": 0.06682258603407952,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.3289,
|
|
"mean_token_accuracy": 0.11908229663968087,
|
|
"num_tokens": 1488231.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.748629426956176,
|
|
"epoch": 0.06724022719679251,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4014,
|
|
"mean_token_accuracy": 0.12175856158137321,
|
|
"num_tokens": 1496904.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.523228120803833,
|
|
"epoch": 0.06765786835950552,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.334,
|
|
"mean_token_accuracy": 0.12687446549534798,
|
|
"num_tokens": 1506006.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.733132934570312,
|
|
"epoch": 0.06807550952221851,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.2813,
|
|
"mean_token_accuracy": 0.12203963398933411,
|
|
"num_tokens": 1515826.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.6297523975372314,
|
|
"epoch": 0.0684931506849315,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3552,
|
|
"mean_token_accuracy": 0.11122297570109367,
|
|
"num_tokens": 1525001.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.583107852935791,
|
|
"epoch": 0.06891079184764451,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.3229,
|
|
"mean_token_accuracy": 0.11932475045323372,
|
|
"num_tokens": 1533647.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.6441779136657715,
|
|
"epoch": 0.0693284330103575,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.3445,
|
|
"mean_token_accuracy": 0.11783274039626121,
|
|
"num_tokens": 1542461.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.660567283630371,
|
|
"epoch": 0.0697460741730705,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.2262,
|
|
"mean_token_accuracy": 0.1264207936823368,
|
|
"num_tokens": 1552249.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.576170206069946,
|
|
"epoch": 0.0701637153357835,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.3921,
|
|
"mean_token_accuracy": 0.12855046465992928,
|
|
"num_tokens": 1561570.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.734837198257447,
|
|
"epoch": 0.07058135649849649,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4302,
|
|
"mean_token_accuracy": 0.11865505427122117,
|
|
"num_tokens": 1572263.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.5386943340301515,
|
|
"epoch": 0.07099899766120948,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.2651,
|
|
"mean_token_accuracy": 0.12368358746170997,
|
|
"num_tokens": 1580828.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.6218860149383545,
|
|
"epoch": 0.07141663882392249,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.2414,
|
|
"mean_token_accuracy": 0.11890774369239807,
|
|
"num_tokens": 1589858.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.687988328933716,
|
|
"epoch": 0.07183427998663548,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.3765,
|
|
"mean_token_accuracy": 0.12400484904646873,
|
|
"num_tokens": 1598822.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.580365896224976,
|
|
"epoch": 0.07225192114934847,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.2517,
|
|
"mean_token_accuracy": 0.1287302441895008,
|
|
"num_tokens": 1607508.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.569807338714599,
|
|
"epoch": 0.07266956231206148,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.2682,
|
|
"mean_token_accuracy": 0.1310380905866623,
|
|
"num_tokens": 1616986.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.714363670349121,
|
|
"epoch": 0.07308720347477447,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3465,
|
|
"mean_token_accuracy": 0.12610832080245019,
|
|
"num_tokens": 1626940.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.540983772277832,
|
|
"epoch": 0.07350484463748747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.3218,
|
|
"mean_token_accuracy": 0.12229821383953095,
|
|
"num_tokens": 1636249.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.62174711227417,
|
|
"epoch": 0.07392248580020047,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3601,
|
|
"mean_token_accuracy": 0.12111141234636306,
|
|
"num_tokens": 1645943.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.664224576950073,
|
|
"epoch": 0.07434012696291346,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.402,
|
|
"mean_token_accuracy": 0.12018121778964996,
|
|
"num_tokens": 1655119.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.53070068359375,
|
|
"epoch": 0.07475776812562646,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.3106,
|
|
"mean_token_accuracy": 0.124847911298275,
|
|
"num_tokens": 1663635.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.53735842704773,
|
|
"epoch": 0.07517540928833946,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.1585,
|
|
"mean_token_accuracy": 0.13482338264584542,
|
|
"num_tokens": 1672360.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.471534395217896,
|
|
"epoch": 0.07559305045105245,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.2349,
|
|
"mean_token_accuracy": 0.1260572887957096,
|
|
"num_tokens": 1681750.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.578565979003907,
|
|
"epoch": 0.07601069161376545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2329,
|
|
"mean_token_accuracy": 0.13175752609968186,
|
|
"num_tokens": 1690434.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.559924745559693,
|
|
"epoch": 0.07642833277647845,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2595,
|
|
"mean_token_accuracy": 0.12138056978583336,
|
|
"num_tokens": 1699982.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.432953596115112,
|
|
"epoch": 0.07684597393919144,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.187,
|
|
"mean_token_accuracy": 0.12513865381479264,
|
|
"num_tokens": 1709251.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.492142963409424,
|
|
"epoch": 0.07726361510190444,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.2698,
|
|
"mean_token_accuracy": 0.1200482964515686,
|
|
"num_tokens": 1718556.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.459371662139892,
|
|
"epoch": 0.07768125626461744,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.236,
|
|
"mean_token_accuracy": 0.1269206404685974,
|
|
"num_tokens": 1728265.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.594856071472168,
|
|
"epoch": 0.07809889742733044,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.2492,
|
|
"mean_token_accuracy": 0.12795129865407945,
|
|
"num_tokens": 1737537.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.351608943939209,
|
|
"epoch": 0.07851653859004344,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.1095,
|
|
"mean_token_accuracy": 0.12889909520745277,
|
|
"num_tokens": 1747357.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.573435544967651,
|
|
"epoch": 0.07893417975275643,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3365,
|
|
"mean_token_accuracy": 0.11498595103621483,
|
|
"num_tokens": 1757462.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.536618280410766,
|
|
"epoch": 0.07935182091546943,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.175,
|
|
"mean_token_accuracy": 0.13465738147497178,
|
|
"num_tokens": 1766127.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.49476056098938,
|
|
"epoch": 0.07976946207818243,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2778,
|
|
"mean_token_accuracy": 0.12881955578923227,
|
|
"num_tokens": 1775106.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.541385173797607,
|
|
"epoch": 0.08018710324089542,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.2576,
|
|
"mean_token_accuracy": 0.13110605105757714,
|
|
"num_tokens": 1785626.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.4958192825317385,
|
|
"epoch": 0.08060474440360842,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.2885,
|
|
"mean_token_accuracy": 0.12439391762018204,
|
|
"num_tokens": 1795064.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.43884506225586,
|
|
"epoch": 0.08102238556632142,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.2553,
|
|
"mean_token_accuracy": 0.12753869816660882,
|
|
"num_tokens": 1804429.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.597222757339478,
|
|
"epoch": 0.08144002672903441,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.2732,
|
|
"mean_token_accuracy": 0.12425616905093192,
|
|
"num_tokens": 1813542.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.474799776077271,
|
|
"epoch": 0.08185766789174741,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.1995,
|
|
"mean_token_accuracy": 0.12659965306520463,
|
|
"num_tokens": 1824172.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.40195951461792,
|
|
"epoch": 0.08227530905446041,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.2122,
|
|
"mean_token_accuracy": 0.12306850850582123,
|
|
"num_tokens": 1832989.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.536772537231445,
|
|
"epoch": 0.0826929502171734,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.1649,
|
|
"mean_token_accuracy": 0.1325046107172966,
|
|
"num_tokens": 1842345.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.416742944717408,
|
|
"epoch": 0.0831105913798864,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2391,
|
|
"mean_token_accuracy": 0.12276924774050713,
|
|
"num_tokens": 1851952.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.37835545539856,
|
|
"epoch": 0.0835282325425994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2235,
|
|
"mean_token_accuracy": 0.12877754718065262,
|
|
"num_tokens": 1861029.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.685376405715942,
|
|
"epoch": 0.0839458737053124,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999987395534,
|
|
"loss": 6.296,
|
|
"mean_token_accuracy": 0.13085904866456985,
|
|
"num_tokens": 1869650.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.526375818252563,
|
|
"epoch": 0.08436351486802539,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999936189888,
|
|
"loss": 6.35,
|
|
"mean_token_accuracy": 0.13077539652585984,
|
|
"num_tokens": 1879078.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.410852146148682,
|
|
"epoch": 0.0847811560307384,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999845595285,
|
|
"loss": 6.1781,
|
|
"mean_token_accuracy": 0.12249526754021645,
|
|
"num_tokens": 1888596.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.411129570007324,
|
|
"epoch": 0.08519879719345139,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999999715611727,
|
|
"loss": 6.1918,
|
|
"mean_token_accuracy": 0.13483786955475807,
|
|
"num_tokens": 1897342.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.401776599884033,
|
|
"epoch": 0.08561643835616438,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999546239215,
|
|
"loss": 6.1331,
|
|
"mean_token_accuracy": 0.13173556253314017,
|
|
"num_tokens": 1905685.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.575545740127564,
|
|
"epoch": 0.08603407951887738,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999337477753,
|
|
"loss": 6.3381,
|
|
"mean_token_accuracy": 0.11911348029971122,
|
|
"num_tokens": 1915195.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.471239280700684,
|
|
"epoch": 0.08645172068159038,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999999089327344,
|
|
"loss": 6.3375,
|
|
"mean_token_accuracy": 0.11769160553812981,
|
|
"num_tokens": 1925156.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.4332513332366945,
|
|
"epoch": 0.08686936184430337,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999998801787993,
|
|
"loss": 6.2073,
|
|
"mean_token_accuracy": 0.1246685691177845,
|
|
"num_tokens": 1934521.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.542106246948242,
|
|
"epoch": 0.08728700300701638,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999998474859704,
|
|
"loss": 6.1181,
|
|
"mean_token_accuracy": 0.12874981313943862,
|
|
"num_tokens": 1944160.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.339631366729736,
|
|
"epoch": 0.08770464416972937,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999998108542483,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.13465228974819182,
|
|
"num_tokens": 1953022.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.239454984664917,
|
|
"epoch": 0.08812228533244236,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997702836339,
|
|
"loss": 6.0884,
|
|
"mean_token_accuracy": 0.12914091050624849,
|
|
"num_tokens": 1961544.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.530628108978272,
|
|
"epoch": 0.08853992649515537,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999997257741274,
|
|
"loss": 6.199,
|
|
"mean_token_accuracy": 0.1303819626569748,
|
|
"num_tokens": 1970319.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.2712071418762205,
|
|
"epoch": 0.08895756765786836,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049999967732573,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.13570455610752105,
|
|
"num_tokens": 1979582.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.4226930141448975,
|
|
"epoch": 0.08937520882058135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999996249384425,
|
|
"loss": 6.2109,
|
|
"mean_token_accuracy": 0.12984167486429216,
|
|
"num_tokens": 1988422.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.30324649810791,
|
|
"epoch": 0.08979284998329436,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999995686122657,
|
|
"loss": 6.1043,
|
|
"mean_token_accuracy": 0.13544947057962417,
|
|
"num_tokens": 1998125.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.3886956691741945,
|
|
"epoch": 0.09021049114600735,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999995083472006,
|
|
"loss": 6.0843,
|
|
"mean_token_accuracy": 0.13154266104102136,
|
|
"num_tokens": 2006993.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.239620876312256,
|
|
"epoch": 0.09062813230872034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999994441432481,
|
|
"loss": 6.1494,
|
|
"mean_token_accuracy": 0.1386062189936638,
|
|
"num_tokens": 2016901.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.429760503768921,
|
|
"epoch": 0.09104577347143335,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999993760004097,
|
|
"loss": 6.1803,
|
|
"mean_token_accuracy": 0.1347517654299736,
|
|
"num_tokens": 2026397.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.428375577926635,
|
|
"epoch": 0.09146341463414634,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999993039186864,
|
|
"loss": 6.143,
|
|
"mean_token_accuracy": 0.12609727829694747,
|
|
"num_tokens": 2035241.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.35336651802063,
|
|
"epoch": 0.09188105579685933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999992278980794,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.13159844800829887,
|
|
"num_tokens": 2044559.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.362043714523315,
|
|
"epoch": 0.09229869695957234,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999991479385901,
|
|
"loss": 6.1496,
|
|
"mean_token_accuracy": 0.1316295139491558,
|
|
"num_tokens": 2055368.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.2911652565002445,
|
|
"epoch": 0.09271633812228533,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999990640402198,
|
|
"loss": 6.0811,
|
|
"mean_token_accuracy": 0.13263901248574256,
|
|
"num_tokens": 2064405.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.407223510742187,
|
|
"epoch": 0.09313397928499834,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999989762029701,
|
|
"loss": 6.1391,
|
|
"mean_token_accuracy": 0.13383666202425956,
|
|
"num_tokens": 2073341.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.365416622161865,
|
|
"epoch": 0.09355162044771133,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999988844268425,
|
|
"loss": 6.2715,
|
|
"mean_token_accuracy": 0.1288045458495617,
|
|
"num_tokens": 2081701.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.401083040237427,
|
|
"epoch": 0.09396926161042432,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999987887118387,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.13317954689264297,
|
|
"num_tokens": 2090662.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.307847595214843,
|
|
"epoch": 0.09438690277313733,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999986890579602,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.12922341972589493,
|
|
"num_tokens": 2100351.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.389047288894654,
|
|
"epoch": 0.09480454393585032,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999985854652087,
|
|
"loss": 6.1506,
|
|
"mean_token_accuracy": 0.13551958799362182,
|
|
"num_tokens": 2108776.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.26150426864624,
|
|
"epoch": 0.09522218509856331,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999984779335862,
|
|
"loss": 6.1954,
|
|
"mean_token_accuracy": 0.14278710186481475,
|
|
"num_tokens": 2117235.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.395204067230225,
|
|
"epoch": 0.09563982626127632,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999983664630945,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.13623337671160698,
|
|
"num_tokens": 2126482.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.3989664077758786,
|
|
"epoch": 0.09605746742398931,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999982510537357,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.13455943241715432,
|
|
"num_tokens": 2135949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.277780437469483,
|
|
"epoch": 0.0964751085867023,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999981317055116,
|
|
"loss": 6.1089,
|
|
"mean_token_accuracy": 0.13122595921158792,
|
|
"num_tokens": 2144887.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.3384411334991455,
|
|
"epoch": 0.09689274974941531,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999980084184244,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.1300405539572239,
|
|
"num_tokens": 2153159.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.365826511383057,
|
|
"epoch": 0.0973103909121283,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999978811924762,
|
|
"loss": 6.1517,
|
|
"mean_token_accuracy": 0.1322521060705185,
|
|
"num_tokens": 2162408.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.431914615631103,
|
|
"epoch": 0.09772803207484129,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999977500276693,
|
|
"loss": 6.0947,
|
|
"mean_token_accuracy": 0.13279680758714676,
|
|
"num_tokens": 2171407.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.156321907043457,
|
|
"epoch": 0.0981456732375543,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999976149240058,
|
|
"loss": 5.9727,
|
|
"mean_token_accuracy": 0.1389105349779129,
|
|
"num_tokens": 2180281.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.37581090927124,
|
|
"epoch": 0.09856331440026729,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999974758814884,
|
|
"loss": 6.1001,
|
|
"mean_token_accuracy": 0.13524875566363334,
|
|
"num_tokens": 2188901.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.332090520858765,
|
|
"epoch": 0.09898095556298028,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999973329001193,
|
|
"loss": 6.2314,
|
|
"mean_token_accuracy": 0.12800901457667352,
|
|
"num_tokens": 2199284.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.2976422786712645,
|
|
"epoch": 0.09939859672569329,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999971859799009,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.13661887347698212,
|
|
"num_tokens": 2208013.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.394473075866699,
|
|
"epoch": 0.09981623788840628,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999970351208361,
|
|
"loss": 6.0996,
|
|
"mean_token_accuracy": 0.13562223240733146,
|
|
"num_tokens": 2217444.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.087979173660278,
|
|
"epoch": 0.10023387905111927,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999968803229275,
|
|
"loss": 6.0029,
|
|
"mean_token_accuracy": 0.1400437444448471,
|
|
"num_tokens": 2226596.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.317812299728393,
|
|
"epoch": 0.10065152021383228,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999967215861775,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.12716382518410682,
|
|
"num_tokens": 2235441.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.3419664859771725,
|
|
"epoch": 0.10106916137654527,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499996558910589,
|
|
"loss": 6.1267,
|
|
"mean_token_accuracy": 0.12739901766180992,
|
|
"num_tokens": 2244783.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.319285345077515,
|
|
"epoch": 0.10148680253925826,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499996392296165,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.13457274362444877,
|
|
"num_tokens": 2254484.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.156066513061523,
|
|
"epoch": 0.10190444370197127,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999962217429083,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.14332070723176002,
|
|
"num_tokens": 2263394.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.1780284404754635,
|
|
"epoch": 0.10232208486468426,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999960472508219,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.13802936673164368,
|
|
"num_tokens": 2272826.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.242110347747802,
|
|
"epoch": 0.10273972602739725,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499995868819909,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.14013530537486077,
|
|
"num_tokens": 2282169.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.300645256042481,
|
|
"epoch": 0.10315736719011026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999956864501725,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.13503486216068267,
|
|
"num_tokens": 2291432.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.316603946685791,
|
|
"epoch": 0.10357500835282325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999955001416156,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.1410436287522316,
|
|
"num_tokens": 2300576.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.175787353515625,
|
|
"epoch": 0.10399264951553625,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999953098942417,
|
|
"loss": 6.1101,
|
|
"mean_token_accuracy": 0.13297224342823027,
|
|
"num_tokens": 2310790.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.3335785388946535,
|
|
"epoch": 0.10441029067824925,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999951157080541,
|
|
"loss": 6.0415,
|
|
"mean_token_accuracy": 0.1348338879644871,
|
|
"num_tokens": 2319831.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.1294896602630615,
|
|
"epoch": 0.10482793184096224,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999949175830561,
|
|
"loss": 5.8914,
|
|
"mean_token_accuracy": 0.14019689410924913,
|
|
"num_tokens": 2329474.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.3479657649993895,
|
|
"epoch": 0.10524557300367524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999947155192514,
|
|
"loss": 6.1823,
|
|
"mean_token_accuracy": 0.1338234931230545,
|
|
"num_tokens": 2338179.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.144778203964234,
|
|
"epoch": 0.10566321416638824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999945095166433,
|
|
"loss": 5.9713,
|
|
"mean_token_accuracy": 0.13504180908203126,
|
|
"num_tokens": 2346899.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.26592984199524,
|
|
"epoch": 0.10608085532910123,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999942995752354,
|
|
"loss": 6.118,
|
|
"mean_token_accuracy": 0.12911219522356987,
|
|
"num_tokens": 2356077.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.347704839706421,
|
|
"epoch": 0.10649849649181423,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999940856950315,
|
|
"loss": 6.0588,
|
|
"mean_token_accuracy": 0.1411923922598362,
|
|
"num_tokens": 2365224.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.158240222930909,
|
|
"epoch": 0.10691613765452723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999938678760354,
|
|
"loss": 5.9556,
|
|
"mean_token_accuracy": 0.1429154209792614,
|
|
"num_tokens": 2375187.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.348350143432617,
|
|
"epoch": 0.10733377881724022,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999936461182507,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.13689570799469947,
|
|
"num_tokens": 2383460.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.20832200050354,
|
|
"epoch": 0.10775141997995323,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999934204216814,
|
|
"loss": 6.0613,
|
|
"mean_token_accuracy": 0.13686455488204957,
|
|
"num_tokens": 2392701.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.254377174377441,
|
|
"epoch": 0.10816906114266622,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999931907863315,
|
|
"loss": 5.9995,
|
|
"mean_token_accuracy": 0.13979897350072862,
|
|
"num_tokens": 2401516.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.236419677734375,
|
|
"epoch": 0.10858670230537922,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499992957212205,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.14022000283002853,
|
|
"num_tokens": 2410799.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.272280979156494,
|
|
"epoch": 0.10900434346809222,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999927196993059,
|
|
"loss": 5.947,
|
|
"mean_token_accuracy": 0.14832693412899972,
|
|
"num_tokens": 2419431.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.114010667800903,
|
|
"epoch": 0.10942198463080521,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999924782476384,
|
|
"loss": 5.9768,
|
|
"mean_token_accuracy": 0.14567074179649353,
|
|
"num_tokens": 2427848.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.1843818664550785,
|
|
"epoch": 0.1098396257935182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999922328572068,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.14341116473078727,
|
|
"num_tokens": 2437960.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.290063714981079,
|
|
"epoch": 0.11025726695623121,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999919835280154,
|
|
"loss": 6.063,
|
|
"mean_token_accuracy": 0.14577179551124572,
|
|
"num_tokens": 2445835.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.189918756484985,
|
|
"epoch": 0.1106749081189442,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999917302600684,
|
|
"loss": 5.956,
|
|
"mean_token_accuracy": 0.13776196390390397,
|
|
"num_tokens": 2454556.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.167909431457519,
|
|
"epoch": 0.1110925492816572,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999914730533704,
|
|
"loss": 6.0471,
|
|
"mean_token_accuracy": 0.1329791449010372,
|
|
"num_tokens": 2465301.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.278769207000733,
|
|
"epoch": 0.1115101904443702,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999912119079258,
|
|
"loss": 6.0267,
|
|
"mean_token_accuracy": 0.13931921273469924,
|
|
"num_tokens": 2474085.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.241355133056641,
|
|
"epoch": 0.1119278316070832,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999909468237393,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.14178281426429748,
|
|
"num_tokens": 2482439.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.11001501083374,
|
|
"epoch": 0.11234547276979619,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999906778008153,
|
|
"loss": 6.0129,
|
|
"mean_token_accuracy": 0.14232075661420823,
|
|
"num_tokens": 2491877.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.363374376296997,
|
|
"epoch": 0.11276311393250919,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999904048391588,
|
|
"loss": 6.0974,
|
|
"mean_token_accuracy": 0.14235304296016693,
|
|
"num_tokens": 2501669.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.059836149215698,
|
|
"epoch": 0.11318075509522219,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999901279387743,
|
|
"loss": 5.9852,
|
|
"mean_token_accuracy": 0.13875525668263436,
|
|
"num_tokens": 2511612.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.278777408599853,
|
|
"epoch": 0.11359839625793518,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999898470996669,
|
|
"loss": 5.9083,
|
|
"mean_token_accuracy": 0.14018528833985328,
|
|
"num_tokens": 2520791.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.085299110412597,
|
|
"epoch": 0.11401603742064818,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999895623218415,
|
|
"loss": 5.9904,
|
|
"mean_token_accuracy": 0.1424546256661415,
|
|
"num_tokens": 2529834.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.2312211990356445,
|
|
"epoch": 0.11443367858336118,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999892736053027,
|
|
"loss": 5.9862,
|
|
"mean_token_accuracy": 0.14232583120465278,
|
|
"num_tokens": 2539053.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.0757904052734375,
|
|
"epoch": 0.11485131974607417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999889809500561,
|
|
"loss": 6.012,
|
|
"mean_token_accuracy": 0.14125642478466033,
|
|
"num_tokens": 2549475.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.2677689552307125,
|
|
"epoch": 0.11526896090878717,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999886843561065,
|
|
"loss": 6.0769,
|
|
"mean_token_accuracy": 0.14093926027417183,
|
|
"num_tokens": 2558718.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.167285919189453,
|
|
"epoch": 0.11568660207150017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999883838234592,
|
|
"loss": 5.9037,
|
|
"mean_token_accuracy": 0.14511679708957673,
|
|
"num_tokens": 2567454.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.093648147583008,
|
|
"epoch": 0.11610424323421316,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999880793521194,
|
|
"loss": 5.82,
|
|
"mean_token_accuracy": 0.14054204970598222,
|
|
"num_tokens": 2575989.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.19893708229065,
|
|
"epoch": 0.11652188439692616,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999877709420924,
|
|
"loss": 6.0154,
|
|
"mean_token_accuracy": 0.1437713012099266,
|
|
"num_tokens": 2585240.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.164418172836304,
|
|
"epoch": 0.11693952555963916,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999874585933837,
|
|
"loss": 6.0533,
|
|
"mean_token_accuracy": 0.13939456194639205,
|
|
"num_tokens": 2593286.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.257520866394043,
|
|
"epoch": 0.11735716672235215,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999871423059987,
|
|
"loss": 6.0063,
|
|
"mean_token_accuracy": 0.14244570657610894,
|
|
"num_tokens": 2602992.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.109090948104859,
|
|
"epoch": 0.11777480788506516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499986822079943,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.1422979399561882,
|
|
"num_tokens": 2611469.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.140593338012695,
|
|
"epoch": 0.11819244904777815,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999864979152221,
|
|
"loss": 5.8956,
|
|
"mean_token_accuracy": 0.1449924021959305,
|
|
"num_tokens": 2621456.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.058706188201905,
|
|
"epoch": 0.11861009021049114,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999861698118417,
|
|
"loss": 5.893,
|
|
"mean_token_accuracy": 0.13982913196086882,
|
|
"num_tokens": 2630355.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.172034072875976,
|
|
"epoch": 0.11902773137320415,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999858377698076,
|
|
"loss": 5.9123,
|
|
"mean_token_accuracy": 0.14697495326399804,
|
|
"num_tokens": 2639508.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.0646039009094235,
|
|
"epoch": 0.11944537253591714,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999855017891256,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.15053340196609497,
|
|
"num_tokens": 2648056.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.182350111007691,
|
|
"epoch": 0.11986301369863013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999851618698017,
|
|
"loss": 6.0378,
|
|
"mean_token_accuracy": 0.13799886107444764,
|
|
"num_tokens": 2657731.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.104360628128052,
|
|
"epoch": 0.12028065486134314,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004999848180118416,
|
|
"loss": 5.878,
|
|
"mean_token_accuracy": 0.14412474036216735,
|
|
"num_tokens": 2666424.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 5.992441177368164,
|
|
"epoch": 0.12069829602405613,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999844702152516,
|
|
"loss": 5.793,
|
|
"mean_token_accuracy": 0.1518073007464409,
|
|
"num_tokens": 2674646.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.237054443359375,
|
|
"epoch": 0.12111593718676913,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999841184800374,
|
|
"loss": 5.9863,
|
|
"mean_token_accuracy": 0.14161835610866547,
|
|
"num_tokens": 2683295.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.116791200637818,
|
|
"epoch": 0.12153357834948213,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999837628062055,
|
|
"loss": 5.8928,
|
|
"mean_token_accuracy": 0.14603603705763818,
|
|
"num_tokens": 2692220.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.111183929443359,
|
|
"epoch": 0.12195121951219512,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999834031937621,
|
|
"loss": 6.0896,
|
|
"mean_token_accuracy": 0.13455943539738655,
|
|
"num_tokens": 2702095.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.3252228736877445,
|
|
"epoch": 0.12236886067490813,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999830396427133,
|
|
"loss": 6.0157,
|
|
"mean_token_accuracy": 0.1376993291079998,
|
|
"num_tokens": 2711440.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.169790554046631,
|
|
"epoch": 0.12278650183762112,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999826721530657,
|
|
"loss": 6.001,
|
|
"mean_token_accuracy": 0.14647723585367203,
|
|
"num_tokens": 2720564.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.193677091598511,
|
|
"epoch": 0.12320414300033411,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999823007248255,
|
|
"loss": 5.8517,
|
|
"mean_token_accuracy": 0.13836075663566588,
|
|
"num_tokens": 2729442.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.122766494750977,
|
|
"epoch": 0.12362178416304712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999819253579992,
|
|
"loss": 5.9647,
|
|
"mean_token_accuracy": 0.1364038832485676,
|
|
"num_tokens": 2738683.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.1442817687988285,
|
|
"epoch": 0.12403942532576011,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999815460525938,
|
|
"loss": 5.9333,
|
|
"mean_token_accuracy": 0.14273701012134551,
|
|
"num_tokens": 2747888.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.067212295532227,
|
|
"epoch": 0.1244570664884731,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999811628086155,
|
|
"loss": 5.7995,
|
|
"mean_token_accuracy": 0.14842113852500916,
|
|
"num_tokens": 2756667.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.137423133850097,
|
|
"epoch": 0.1248747076511861,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499980775626071,
|
|
"loss": 5.978,
|
|
"mean_token_accuracy": 0.14387312531471252,
|
|
"num_tokens": 2765116.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 5.987923860549927,
|
|
"epoch": 0.12529234881389908,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999803845049674,
|
|
"loss": 5.8348,
|
|
"mean_token_accuracy": 0.148624786734581,
|
|
"num_tokens": 2774259.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.0781763076782225,
|
|
"epoch": 0.1257099899766121,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999799894453112,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.14260915145277978,
|
|
"num_tokens": 2782988.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.074441432952881,
|
|
"epoch": 0.1261276311393251,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999795904471095,
|
|
"loss": 5.8764,
|
|
"mean_token_accuracy": 0.1461164064705372,
|
|
"num_tokens": 2791409.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.199710178375244,
|
|
"epoch": 0.12654527230203808,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999791875103694,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.143809075653553,
|
|
"num_tokens": 2800644.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.061881637573242,
|
|
"epoch": 0.12696291346475108,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999787806350977,
|
|
"loss": 5.8425,
|
|
"mean_token_accuracy": 0.14784278273582457,
|
|
"num_tokens": 2809838.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.122160530090332,
|
|
"epoch": 0.1273805546274641,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999783698213016,
|
|
"loss": 5.9717,
|
|
"mean_token_accuracy": 0.1433075912296772,
|
|
"num_tokens": 2818972.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.13506383895874,
|
|
"epoch": 0.12779819579017707,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999779550689885,
|
|
"loss": 5.8962,
|
|
"mean_token_accuracy": 0.1441321402788162,
|
|
"num_tokens": 2827733.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.1400655746459964,
|
|
"epoch": 0.12821583695289007,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999775363781654,
|
|
"loss": 5.9921,
|
|
"mean_token_accuracy": 0.14137880951166154,
|
|
"num_tokens": 2837300.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.183238124847412,
|
|
"epoch": 0.12863347811560308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999771137488395,
|
|
"loss": 5.8972,
|
|
"mean_token_accuracy": 0.14587430506944657,
|
|
"num_tokens": 2846076.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.954459524154663,
|
|
"epoch": 0.12905111927831608,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999766871810188,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.14452776312828064,
|
|
"num_tokens": 2855523.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.148645496368408,
|
|
"epoch": 0.12946876044102906,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999762566747101,
|
|
"loss": 5.9546,
|
|
"mean_token_accuracy": 0.14385624825954438,
|
|
"num_tokens": 2864277.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.116501188278198,
|
|
"epoch": 0.12988640160374207,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999758222299214,
|
|
"loss": 5.9374,
|
|
"mean_token_accuracy": 0.14204028993844986,
|
|
"num_tokens": 2873561.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.12092695236206,
|
|
"epoch": 0.13030404276645507,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999753838466601,
|
|
"loss": 5.8148,
|
|
"mean_token_accuracy": 0.1522620737552643,
|
|
"num_tokens": 2882449.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.0730757236480715,
|
|
"epoch": 0.13072168392916805,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999749415249338,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.15969083160161973,
|
|
"num_tokens": 2890862.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 5.995173978805542,
|
|
"epoch": 0.13113932509188106,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999744952647505,
|
|
"loss": 5.8679,
|
|
"mean_token_accuracy": 0.15128796994686128,
|
|
"num_tokens": 2899611.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.126881837844849,
|
|
"epoch": 0.13155696625459407,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999740450661176,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.14792831093072892,
|
|
"num_tokens": 2908111.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.092712545394898,
|
|
"epoch": 0.13197460741730704,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999735909290436,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.1501033529639244,
|
|
"num_tokens": 2917194.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.04348578453064,
|
|
"epoch": 0.13239224858002005,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999731328535358,
|
|
"loss": 5.8566,
|
|
"mean_token_accuracy": 0.14753102511167526,
|
|
"num_tokens": 2926684.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.9717113971710205,
|
|
"epoch": 0.13280988974273306,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999726708396026,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14780840948224067,
|
|
"num_tokens": 2936094.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.083980226516724,
|
|
"epoch": 0.13322753090544603,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499972204887252,
|
|
"loss": 5.8373,
|
|
"mean_token_accuracy": 0.14772946015000343,
|
|
"num_tokens": 2944389.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.005502843856812,
|
|
"epoch": 0.13364517206815904,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999717349964922,
|
|
"loss": 5.8579,
|
|
"mean_token_accuracy": 0.14418584555387498,
|
|
"num_tokens": 2954466.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.135638904571533,
|
|
"epoch": 0.13406281323087205,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999712611673313,
|
|
"loss": 6.0455,
|
|
"mean_token_accuracy": 0.13582754135131836,
|
|
"num_tokens": 2965403.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.272896146774292,
|
|
"epoch": 0.13448045439358502,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999707833997777,
|
|
"loss": 6.044,
|
|
"mean_token_accuracy": 0.14214518070220947,
|
|
"num_tokens": 2975896.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.984560871124268,
|
|
"epoch": 0.13489809555629803,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999703016938398,
|
|
"loss": 5.8884,
|
|
"mean_token_accuracy": 0.15345285460352898,
|
|
"num_tokens": 2984937.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 5.952976226806641,
|
|
"epoch": 0.13531573671901104,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499969816049526,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.14834006428718566,
|
|
"num_tokens": 2994052.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.1258875846862795,
|
|
"epoch": 0.13573337788172402,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999693264668446,
|
|
"loss": 5.7352,
|
|
"mean_token_accuracy": 0.1505567364394665,
|
|
"num_tokens": 3003274.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.0712028503417965,
|
|
"epoch": 0.13615101904443702,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999688329458045,
|
|
"loss": 5.84,
|
|
"mean_token_accuracy": 0.15118275731801986,
|
|
"num_tokens": 3011440.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.008664512634278,
|
|
"epoch": 0.13656866020715003,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999683354864141,
|
|
"loss": 5.9329,
|
|
"mean_token_accuracy": 0.14488905742764474,
|
|
"num_tokens": 3021032.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.072646713256836,
|
|
"epoch": 0.136986301369863,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999678340886823,
|
|
"loss": 5.9002,
|
|
"mean_token_accuracy": 0.1485132485628128,
|
|
"num_tokens": 3030160.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.0518828392028805,
|
|
"epoch": 0.137403942532576,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999673287526176,
|
|
"loss": 5.9321,
|
|
"mean_token_accuracy": 0.1511251837015152,
|
|
"num_tokens": 3039098.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.145869588851928,
|
|
"epoch": 0.13782158369528902,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999668194782291,
|
|
"loss": 5.8652,
|
|
"mean_token_accuracy": 0.14529599547386168,
|
|
"num_tokens": 3048679.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.002886247634888,
|
|
"epoch": 0.138239224858002,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999663062655257,
|
|
"loss": 5.7778,
|
|
"mean_token_accuracy": 0.15449400395154952,
|
|
"num_tokens": 3057613.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.0733765125274655,
|
|
"epoch": 0.138656866020715,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999657891145162,
|
|
"loss": 5.9725,
|
|
"mean_token_accuracy": 0.14817949309945105,
|
|
"num_tokens": 3066291.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.028089237213135,
|
|
"epoch": 0.139074507183428,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999652680252099,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.14239186346530913,
|
|
"num_tokens": 3075897.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.171479940414429,
|
|
"epoch": 0.139492148346141,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999647429976157,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.14334002286195754,
|
|
"num_tokens": 3085193.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.060310125350952,
|
|
"epoch": 0.139909789508854,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999642140317429,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.14457208216190337,
|
|
"num_tokens": 3094335.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.0583384990692135,
|
|
"epoch": 0.140327430671567,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999636811276007,
|
|
"loss": 5.9671,
|
|
"mean_token_accuracy": 0.14252406731247902,
|
|
"num_tokens": 3103964.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.042476081848145,
|
|
"epoch": 0.14074507183427998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999631442851986,
|
|
"loss": 5.8487,
|
|
"mean_token_accuracy": 0.14683347940444946,
|
|
"num_tokens": 3113321.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.0762725353240965,
|
|
"epoch": 0.14116271299699298,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999626035045458,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.14716964587569237,
|
|
"num_tokens": 3122467.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.074911594390869,
|
|
"epoch": 0.141580354159706,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999620587856519,
|
|
"loss": 5.8106,
|
|
"mean_token_accuracy": 0.1543986439704895,
|
|
"num_tokens": 3131239.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 5.974051237106323,
|
|
"epoch": 0.14199799532241897,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999615101285262,
|
|
"loss": 5.9463,
|
|
"mean_token_accuracy": 0.14293202459812165,
|
|
"num_tokens": 3140568.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.088217878341675,
|
|
"epoch": 0.14241563648513197,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999609575331786,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.14690518230199814,
|
|
"num_tokens": 3151227.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.073013973236084,
|
|
"epoch": 0.14283327764784498,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999604009996186,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.1575349062681198,
|
|
"num_tokens": 3159865.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.97011547088623,
|
|
"epoch": 0.14325091881055796,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499959840527856,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.1552349552512169,
|
|
"num_tokens": 3169832.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.988092088699341,
|
|
"epoch": 0.14366855997327097,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999592761179007,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.14358080923557281,
|
|
"num_tokens": 3180357.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.048899412155151,
|
|
"epoch": 0.14408620113598397,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999587077697624,
|
|
"loss": 5.8213,
|
|
"mean_token_accuracy": 0.15338835269212722,
|
|
"num_tokens": 3189663.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.034728240966797,
|
|
"epoch": 0.14450384229869695,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999581354834512,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.1513874851167202,
|
|
"num_tokens": 3199578.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.077489566802979,
|
|
"epoch": 0.14492148346140996,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499957559258977,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.15805275589227677,
|
|
"num_tokens": 3208839.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.081794166564942,
|
|
"epoch": 0.14533912462412296,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049995697909635,
|
|
"loss": 5.8594,
|
|
"mean_token_accuracy": 0.15180393382906915,
|
|
"num_tokens": 3217449.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 5.9614564895629885,
|
|
"epoch": 0.14575676578683594,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999563949955803,
|
|
"loss": 5.7557,
|
|
"mean_token_accuracy": 0.1466016449034214,
|
|
"num_tokens": 3226561.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.04267988204956,
|
|
"epoch": 0.14617440694954895,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499955806956678,
|
|
"loss": 5.8522,
|
|
"mean_token_accuracy": 0.15752413123846054,
|
|
"num_tokens": 3235400.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.0401026725769045,
|
|
"epoch": 0.14659204811226195,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999552149796536,
|
|
"loss": 5.9144,
|
|
"mean_token_accuracy": 0.14410170838236808,
|
|
"num_tokens": 3244862.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 5.979519271850586,
|
|
"epoch": 0.14700968927497493,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999546190645175,
|
|
"loss": 5.8129,
|
|
"mean_token_accuracy": 0.1537217117846012,
|
|
"num_tokens": 3254370.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.0241940975189205,
|
|
"epoch": 0.14742733043768794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999540192112799,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.15348097831010818,
|
|
"num_tokens": 3264079.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.9918759822845455,
|
|
"epoch": 0.14784497160040094,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999534154199514,
|
|
"loss": 5.8969,
|
|
"mean_token_accuracy": 0.15254206955432892,
|
|
"num_tokens": 3273315.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 5.959523487091064,
|
|
"epoch": 0.14826261276311392,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999528076905426,
|
|
"loss": 5.7799,
|
|
"mean_token_accuracy": 0.1521797373890877,
|
|
"num_tokens": 3282045.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.010910081863403,
|
|
"epoch": 0.14868025392582693,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999521960230641,
|
|
"loss": 5.8839,
|
|
"mean_token_accuracy": 0.1504328355193138,
|
|
"num_tokens": 3291596.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.929302835464478,
|
|
"epoch": 0.14909789508853993,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999515804175268,
|
|
"loss": 5.7192,
|
|
"mean_token_accuracy": 0.15593315809965133,
|
|
"num_tokens": 3300407.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.025093269348145,
|
|
"epoch": 0.1495155362512529,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499950960873941,
|
|
"loss": 5.7526,
|
|
"mean_token_accuracy": 0.15117358267307282,
|
|
"num_tokens": 3309848.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.93266453742981,
|
|
"epoch": 0.14993317741396592,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999503373923182,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.1462218925356865,
|
|
"num_tokens": 3319031.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.971647119522094,
|
|
"epoch": 0.15035081857667892,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999497099726687,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.1453866645693779,
|
|
"num_tokens": 3327918.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.944482469558716,
|
|
"epoch": 0.1507684597393919,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999490786150039,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.14495486468076707,
|
|
"num_tokens": 3337071.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.112966394424438,
|
|
"epoch": 0.1511861009021049,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999484433193348,
|
|
"loss": 5.8881,
|
|
"mean_token_accuracy": 0.1472978837788105,
|
|
"num_tokens": 3346334.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.038641357421875,
|
|
"epoch": 0.15160374206481791,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999478040856722,
|
|
"loss": 5.8042,
|
|
"mean_token_accuracy": 0.14679064601659775,
|
|
"num_tokens": 3354932.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.838101720809936,
|
|
"epoch": 0.1520213832275309,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999471609140276,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.151202093064785,
|
|
"num_tokens": 3364345.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.046137475967408,
|
|
"epoch": 0.1524390243902439,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999465138044122,
|
|
"loss": 5.837,
|
|
"mean_token_accuracy": 0.14820541590452194,
|
|
"num_tokens": 3372918.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.906940031051636,
|
|
"epoch": 0.1528566655529569,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999458627568373,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.15286548137664796,
|
|
"num_tokens": 3381815.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.9043457984924315,
|
|
"epoch": 0.15327430671566988,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999452077713144,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.1523844078183174,
|
|
"num_tokens": 3391057.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.079875421524048,
|
|
"epoch": 0.1536919478783829,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999445488478547,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.14450442418456078,
|
|
"num_tokens": 3401254.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.981129789352417,
|
|
"epoch": 0.1541095890410959,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00049994388598647,
|
|
"loss": 5.8614,
|
|
"mean_token_accuracy": 0.14819915741682052,
|
|
"num_tokens": 3411031.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 5.982936429977417,
|
|
"epoch": 0.15452723020380887,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999432191871719,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.15687229484319687,
|
|
"num_tokens": 3420154.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.114473152160644,
|
|
"epoch": 0.15494487136652188,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004999425484499718,
|
|
"loss": 5.8862,
|
|
"mean_token_accuracy": 0.15098146200180054,
|
|
"num_tokens": 3429285.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.987294626235962,
|
|
"epoch": 0.1553625125292349,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999418737748817,
|
|
"loss": 5.8558,
|
|
"mean_token_accuracy": 0.14990614205598832,
|
|
"num_tokens": 3438065.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.067724609375,
|
|
"epoch": 0.15578015369194786,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999411951619134,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.14882780537009238,
|
|
"num_tokens": 3447534.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.009346771240234,
|
|
"epoch": 0.15619779485466087,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999405126110786,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.15343883335590364,
|
|
"num_tokens": 3456435.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.931367492675781,
|
|
"epoch": 0.15661543601737388,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999398261223895,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.154514442384243,
|
|
"num_tokens": 3464982.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.091391706466675,
|
|
"epoch": 0.15703307718008688,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999391356958579,
|
|
"loss": 5.9261,
|
|
"mean_token_accuracy": 0.14851265177130699,
|
|
"num_tokens": 3474585.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 5.937274599075318,
|
|
"epoch": 0.15745071834279986,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499938441331496,
|
|
"loss": 5.7652,
|
|
"mean_token_accuracy": 0.15298966467380523,
|
|
"num_tokens": 3483164.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.942174434661865,
|
|
"epoch": 0.15786835950551287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999377430293159,
|
|
"loss": 5.7712,
|
|
"mean_token_accuracy": 0.14635431468486787,
|
|
"num_tokens": 3492984.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.909766054153442,
|
|
"epoch": 0.15828600066822587,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004999370407893299,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.16215786188840867,
|
|
"num_tokens": 3500356.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.018685245513916,
|
|
"epoch": 0.15870364183093885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999363346115501,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.15466036051511764,
|
|
"num_tokens": 3509792.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.9935344696044925,
|
|
"epoch": 0.15912128299365186,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999356244959893,
|
|
"loss": 5.7378,
|
|
"mean_token_accuracy": 0.149660687148571,
|
|
"num_tokens": 3519340.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.8559294700622555,
|
|
"epoch": 0.15953892415636486,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999349104426594,
|
|
"loss": 5.7346,
|
|
"mean_token_accuracy": 0.15643487572669984,
|
|
"num_tokens": 3528846.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.969501399993897,
|
|
"epoch": 0.15995656531907784,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999341924515732,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.15309956967830657,
|
|
"num_tokens": 3537766.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.955421113967896,
|
|
"epoch": 0.16037420648179085,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999334705227431,
|
|
"loss": 5.796,
|
|
"mean_token_accuracy": 0.1499815657734871,
|
|
"num_tokens": 3546724.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.901809024810791,
|
|
"epoch": 0.16079184764450385,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499932744656182,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.16025683730840684,
|
|
"num_tokens": 3555599.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.8585106372833256,
|
|
"epoch": 0.16120948880721683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999320148519024,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.15616288557648658,
|
|
"num_tokens": 3564754.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.821812677383423,
|
|
"epoch": 0.16162712996992984,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999312811099171,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.16239829510450363,
|
|
"num_tokens": 3573166.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.954546213150024,
|
|
"epoch": 0.16204477113264285,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999305434302391,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.1504362255334854,
|
|
"num_tokens": 3581602.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.977283334732055,
|
|
"epoch": 0.16246241229535582,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499929801812881,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.16076785027980806,
|
|
"num_tokens": 3590946.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 5.840662717819214,
|
|
"epoch": 0.16288005345806883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999290562578561,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.15856219083070755,
|
|
"num_tokens": 3599888.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.941868877410888,
|
|
"epoch": 0.16329769462078184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999283067651773,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.16239314377307892,
|
|
"num_tokens": 3609773.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.869628143310547,
|
|
"epoch": 0.16371533578349481,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999275533348577,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.1552025258541107,
|
|
"num_tokens": 3618820.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.990446376800537,
|
|
"epoch": 0.16413297694620782,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999267959669106,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.1533038690686226,
|
|
"num_tokens": 3629010.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.895765590667724,
|
|
"epoch": 0.16455061810892083,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999260346613491,
|
|
"loss": 5.747,
|
|
"mean_token_accuracy": 0.15518127232789994,
|
|
"num_tokens": 3636915.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.916001415252685,
|
|
"epoch": 0.1649682592716338,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999252694181867,
|
|
"loss": 5.7295,
|
|
"mean_token_accuracy": 0.1585697278380394,
|
|
"num_tokens": 3646011.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.943479585647583,
|
|
"epoch": 0.1653859004343468,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999245002374367,
|
|
"loss": 5.7033,
|
|
"mean_token_accuracy": 0.16055430471897125,
|
|
"num_tokens": 3655059.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.9830348014831545,
|
|
"epoch": 0.16580354159705982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999237271191125,
|
|
"loss": 5.7979,
|
|
"mean_token_accuracy": 0.15375116169452668,
|
|
"num_tokens": 3664553.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.9315876960754395,
|
|
"epoch": 0.1662211827597728,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999229500632279,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.1533743694424629,
|
|
"num_tokens": 3673604.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.930443811416626,
|
|
"epoch": 0.1666388239224858,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999221690697961,
|
|
"loss": 5.7126,
|
|
"mean_token_accuracy": 0.1625876694917679,
|
|
"num_tokens": 3682634.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.919408082962036,
|
|
"epoch": 0.1670564650851988,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999213841388312,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.15079522579908372,
|
|
"num_tokens": 3691961.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.88884482383728,
|
|
"epoch": 0.16747410624791179,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999205952703466,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.1490720458328724,
|
|
"num_tokens": 3701412.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.956575727462768,
|
|
"epoch": 0.1678917474106248,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999198024643563,
|
|
"loss": 5.7988,
|
|
"mean_token_accuracy": 0.15698140263557434,
|
|
"num_tokens": 3710449.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.961668586730957,
|
|
"epoch": 0.1683093885733378,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999190057208741,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.14847119450569152,
|
|
"num_tokens": 3718654.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.898903131484985,
|
|
"epoch": 0.16872702973605078,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499918205039914,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.15195512697100638,
|
|
"num_tokens": 3728660.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.887713956832886,
|
|
"epoch": 0.16914467089876378,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999174004214899,
|
|
"loss": 5.7612,
|
|
"mean_token_accuracy": 0.1582832634449005,
|
|
"num_tokens": 3738085.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.943373489379883,
|
|
"epoch": 0.1695623120614768,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999165918656161,
|
|
"loss": 5.698,
|
|
"mean_token_accuracy": 0.15785950943827629,
|
|
"num_tokens": 3747727.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.963870048522949,
|
|
"epoch": 0.16997995322418977,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999157793723065,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15320221334695816,
|
|
"num_tokens": 3757864.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.827042865753174,
|
|
"epoch": 0.17039759438690277,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999149629415755,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.16073038354516028,
|
|
"num_tokens": 3766843.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.94908447265625,
|
|
"epoch": 0.17081523554961578,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999141425734374,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.1535307839512825,
|
|
"num_tokens": 3776171.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.944053077697754,
|
|
"epoch": 0.17123287671232876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999133182679064,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.16170434057712554,
|
|
"num_tokens": 3785545.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.784623289108277,
|
|
"epoch": 0.17165051787504176,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999124900249971,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.15819989293813705,
|
|
"num_tokens": 3794110.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.945992040634155,
|
|
"epoch": 0.17206815903775477,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004999116578447239,
|
|
"loss": 5.8108,
|
|
"mean_token_accuracy": 0.15511984676122664,
|
|
"num_tokens": 3803727.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.9064085483551025,
|
|
"epoch": 0.17248580020046775,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999108217271015,
|
|
"loss": 5.7648,
|
|
"mean_token_accuracy": 0.1535521849989891,
|
|
"num_tokens": 3812904.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.095454597473145,
|
|
"epoch": 0.17290344136318075,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999099816721444,
|
|
"loss": 5.851,
|
|
"mean_token_accuracy": 0.15227640569210052,
|
|
"num_tokens": 3822009.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.841128206253051,
|
|
"epoch": 0.17332108252589376,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999091376798673,
|
|
"loss": 5.7599,
|
|
"mean_token_accuracy": 0.15635585486888887,
|
|
"num_tokens": 3830877.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.060049676895142,
|
|
"epoch": 0.17373872368860674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999082897502849,
|
|
"loss": 5.8234,
|
|
"mean_token_accuracy": 0.1512978546321392,
|
|
"num_tokens": 3839876.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.048352336883545,
|
|
"epoch": 0.17415636485131974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999074378834123,
|
|
"loss": 5.8174,
|
|
"mean_token_accuracy": 0.16038154661655427,
|
|
"num_tokens": 3848769.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.854233169555664,
|
|
"epoch": 0.17457400601403275,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999065820792644,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.15877358615398407,
|
|
"num_tokens": 3857676.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.918405389785766,
|
|
"epoch": 0.17499164717674573,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999057223378559,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.15598385334014891,
|
|
"num_tokens": 3867098.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.797727441787719,
|
|
"epoch": 0.17540928833945874,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499904858659202,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.1513415813446045,
|
|
"num_tokens": 3876247.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.859252500534057,
|
|
"epoch": 0.17582692950217174,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999039910433179,
|
|
"loss": 5.7278,
|
|
"mean_token_accuracy": 0.16455016881227494,
|
|
"num_tokens": 3885747.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.052870464324951,
|
|
"epoch": 0.17624457066488472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999031194902187,
|
|
"loss": 5.8473,
|
|
"mean_token_accuracy": 0.15237005054950714,
|
|
"num_tokens": 3896077.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.972765064239502,
|
|
"epoch": 0.17666221182759773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999022439999198,
|
|
"loss": 5.8471,
|
|
"mean_token_accuracy": 0.14567215442657472,
|
|
"num_tokens": 3906323.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.924546098709106,
|
|
"epoch": 0.17707985299031073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999013645724362,
|
|
"loss": 5.744,
|
|
"mean_token_accuracy": 0.15510283634066582,
|
|
"num_tokens": 3915510.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.93877215385437,
|
|
"epoch": 0.1774974941530237,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999004812077836,
|
|
"loss": 5.8143,
|
|
"mean_token_accuracy": 0.1571462519466877,
|
|
"num_tokens": 3924799.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.834187316894531,
|
|
"epoch": 0.17791513531573672,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004998995939059773,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.15311417132616043,
|
|
"num_tokens": 3933675.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.885807180404663,
|
|
"epoch": 0.17833277647844972,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499898702667033,
|
|
"loss": 5.6939,
|
|
"mean_token_accuracy": 0.15966519266366958,
|
|
"num_tokens": 3942086.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.9234106063842775,
|
|
"epoch": 0.1787504176411627,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004998978074909661,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15536481142044067,
|
|
"num_tokens": 3950626.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.733146715164184,
|
|
"epoch": 0.1791680588038757,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998969083777925,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.17237166315317154,
|
|
"num_tokens": 3959006.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.853768444061279,
|
|
"epoch": 0.1795856999665887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998960053275277,
|
|
"loss": 5.7,
|
|
"mean_token_accuracy": 0.16328830420970916,
|
|
"num_tokens": 3968177.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.902877569198608,
|
|
"epoch": 0.1800033411293017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998950983401875,
|
|
"loss": 5.6651,
|
|
"mean_token_accuracy": 0.15961136817932128,
|
|
"num_tokens": 3977052.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.8690708637237545,
|
|
"epoch": 0.1804209822920147,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998941874157882,
|
|
"loss": 5.6858,
|
|
"mean_token_accuracy": 0.15438530892133712,
|
|
"num_tokens": 3985101.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.850992012023926,
|
|
"epoch": 0.1808386234547277,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998932725543453,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.15906111001968384,
|
|
"num_tokens": 3992936.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.916439151763916,
|
|
"epoch": 0.18125626461744068,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998923537558749,
|
|
"loss": 5.7801,
|
|
"mean_token_accuracy": 0.1568411409854889,
|
|
"num_tokens": 4001702.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.8718656539917,
|
|
"epoch": 0.1816739057801537,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998914310203932,
|
|
"loss": 5.7721,
|
|
"mean_token_accuracy": 0.157361763715744,
|
|
"num_tokens": 4011639.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.805581378936767,
|
|
"epoch": 0.1820915469428667,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998905043479163,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.16170865297317505,
|
|
"num_tokens": 4021420.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.7755042552948,
|
|
"epoch": 0.18250918810557967,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998895737384605,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.15489371567964555,
|
|
"num_tokens": 4030869.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.772803878784179,
|
|
"epoch": 0.18292682926829268,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998886391920418,
|
|
"loss": 5.5327,
|
|
"mean_token_accuracy": 0.1654495880007744,
|
|
"num_tokens": 4039573.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.7726646900177006,
|
|
"epoch": 0.18334447043100568,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998877007086769,
|
|
"loss": 5.6365,
|
|
"mean_token_accuracy": 0.16419821083545685,
|
|
"num_tokens": 4048684.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.77266206741333,
|
|
"epoch": 0.18376211159371866,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004998867582883821,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.152945114672184,
|
|
"num_tokens": 4057968.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.963563871383667,
|
|
"epoch": 0.18417975275643167,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998858119311739,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.15852373093366623,
|
|
"num_tokens": 4068057.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.830620002746582,
|
|
"epoch": 0.18459739391914468,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998848616370689,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.16643038839101792,
|
|
"num_tokens": 4077141.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.784256935119629,
|
|
"epoch": 0.18501503508185768,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998839074060837,
|
|
"loss": 5.6668,
|
|
"mean_token_accuracy": 0.15795958489179612,
|
|
"num_tokens": 4085227.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.864757537841797,
|
|
"epoch": 0.18543267624457066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499882949238235,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.1627066969871521,
|
|
"num_tokens": 4093674.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.904892301559448,
|
|
"epoch": 0.18585031740728367,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998819871335396,
|
|
"loss": 5.7977,
|
|
"mean_token_accuracy": 0.15320228040218353,
|
|
"num_tokens": 4103466.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.9529468536376955,
|
|
"epoch": 0.18626795856999667,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998810210920142,
|
|
"loss": 5.6308,
|
|
"mean_token_accuracy": 0.15609087347984313,
|
|
"num_tokens": 4111833.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.831648969650269,
|
|
"epoch": 0.18668559973270965,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998800511136759,
|
|
"loss": 5.696,
|
|
"mean_token_accuracy": 0.15844447761774064,
|
|
"num_tokens": 4121546.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.88375301361084,
|
|
"epoch": 0.18710324089542266,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998790771985417,
|
|
"loss": 5.6594,
|
|
"mean_token_accuracy": 0.16582350432872772,
|
|
"num_tokens": 4130408.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.788675308227539,
|
|
"epoch": 0.18752088205813566,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998780993466284,
|
|
"loss": 5.7884,
|
|
"mean_token_accuracy": 0.15529951304197312,
|
|
"num_tokens": 4139793.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.9381426811218265,
|
|
"epoch": 0.18793852322084864,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998771175579534,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.1638265699148178,
|
|
"num_tokens": 4148192.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.749383401870728,
|
|
"epoch": 0.18835616438356165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998761318325337,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.1587271884083748,
|
|
"num_tokens": 4157960.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.599839687347412,
|
|
"epoch": 0.18877380554627465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998751421703868,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.17087434977293015,
|
|
"num_tokens": 4166356.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.921038627624512,
|
|
"epoch": 0.18919144670898763,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998741485715297,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.1493260845541954,
|
|
"num_tokens": 4176139.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.862062454223633,
|
|
"epoch": 0.18960908787170064,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049987315103598,
|
|
"loss": 5.6537,
|
|
"mean_token_accuracy": 0.1571880027651787,
|
|
"num_tokens": 4185583.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.7853264808654785,
|
|
"epoch": 0.19002672903441364,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998721495637551,
|
|
"loss": 5.7499,
|
|
"mean_token_accuracy": 0.15288184583187103,
|
|
"num_tokens": 4194275.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.86413426399231,
|
|
"epoch": 0.19044437019712662,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998711441548726,
|
|
"loss": 5.6825,
|
|
"mean_token_accuracy": 0.16003127843141557,
|
|
"num_tokens": 4203424.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.735157155990601,
|
|
"epoch": 0.19086201135983963,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998701348093499,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.16366421282291413,
|
|
"num_tokens": 4212452.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.897738647460938,
|
|
"epoch": 0.19127965252255263,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499869121527205,
|
|
"loss": 5.7611,
|
|
"mean_token_accuracy": 0.15444075167179108,
|
|
"num_tokens": 4221639.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.865130138397217,
|
|
"epoch": 0.1916972936852656,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998681043084553,
|
|
"loss": 5.6302,
|
|
"mean_token_accuracy": 0.1672831192612648,
|
|
"num_tokens": 4231362.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.815743017196655,
|
|
"epoch": 0.19211493484797862,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998670831531188,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.15458433628082274,
|
|
"num_tokens": 4241035.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.94687819480896,
|
|
"epoch": 0.19253257601069163,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998660580612135,
|
|
"loss": 5.6458,
|
|
"mean_token_accuracy": 0.1604814574122429,
|
|
"num_tokens": 4250275.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.761688947677612,
|
|
"epoch": 0.1929502171734046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998650290327569,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.15605543106794356,
|
|
"num_tokens": 4259952.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.860372161865234,
|
|
"epoch": 0.1933678583361176,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998639960677675,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.16590958833694458,
|
|
"num_tokens": 4269985.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.8047374248504635,
|
|
"epoch": 0.19378549949883062,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998629591662631,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.16162675321102143,
|
|
"num_tokens": 4278317.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.785900402069092,
|
|
"epoch": 0.1942031406615436,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499861918328262,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.16352908909320832,
|
|
"num_tokens": 4286633.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.809439373016358,
|
|
"epoch": 0.1946207818242566,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998608735537822,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.16824746429920195,
|
|
"num_tokens": 4295696.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.761776733398437,
|
|
"epoch": 0.1950384229869696,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998598248428423,
|
|
"loss": 5.6942,
|
|
"mean_token_accuracy": 0.16295794695615767,
|
|
"num_tokens": 4305139.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.801323413848877,
|
|
"epoch": 0.19545606414968258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998587721954604,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.16570183932781218,
|
|
"num_tokens": 4314029.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.803794860839844,
|
|
"epoch": 0.1958737053123956,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998577156116551,
|
|
"loss": 5.7027,
|
|
"mean_token_accuracy": 0.15905870646238326,
|
|
"num_tokens": 4323667.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.898095417022705,
|
|
"epoch": 0.1962913464751086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998566550914448,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.1614445775747299,
|
|
"num_tokens": 4333456.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.882632923126221,
|
|
"epoch": 0.19670898763782158,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998555906348481,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.15647562146186828,
|
|
"num_tokens": 4342527.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.8123023986816404,
|
|
"epoch": 0.19712662880053458,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998545222418836,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.15761913359165192,
|
|
"num_tokens": 4351294.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.791871070861816,
|
|
"epoch": 0.1975442699632476,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998534499125701,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.1602482318878174,
|
|
"num_tokens": 4361596.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.866342163085937,
|
|
"epoch": 0.19796191112596057,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998523736469263,
|
|
"loss": 5.6464,
|
|
"mean_token_accuracy": 0.16265444308519364,
|
|
"num_tokens": 4370917.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.719123411178589,
|
|
"epoch": 0.19837955228867357,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499851293444971,
|
|
"loss": 5.6783,
|
|
"mean_token_accuracy": 0.1592626839876175,
|
|
"num_tokens": 4380244.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.787483501434326,
|
|
"epoch": 0.19879719345138658,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998502093067231,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.15903472751379014,
|
|
"num_tokens": 4389852.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.896140050888062,
|
|
"epoch": 0.19921483461409956,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998491212322017,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.1548086531460285,
|
|
"num_tokens": 4399743.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.879378080368042,
|
|
"epoch": 0.19963247577681256,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998480292214258,
|
|
"loss": 5.6432,
|
|
"mean_token_accuracy": 0.15781110972166063,
|
|
"num_tokens": 4408661.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.790725517272949,
|
|
"epoch": 0.20005011693952557,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998469332744144,
|
|
"loss": 5.6009,
|
|
"mean_token_accuracy": 0.16551696062088012,
|
|
"num_tokens": 4417671.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.77877402305603,
|
|
"epoch": 0.20046775810223855,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998458333911869,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.1598905384540558,
|
|
"num_tokens": 4426850.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.955265283584595,
|
|
"epoch": 0.20088539926495155,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998447295717624,
|
|
"loss": 5.7931,
|
|
"mean_token_accuracy": 0.15605985820293428,
|
|
"num_tokens": 4435769.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.819901657104492,
|
|
"epoch": 0.20130304042766456,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998436218161602,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.16049996465444566,
|
|
"num_tokens": 4445521.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.86675992012024,
|
|
"epoch": 0.20172068159037754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998425101243999,
|
|
"loss": 5.7061,
|
|
"mean_token_accuracy": 0.15795376002788544,
|
|
"num_tokens": 4454674.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.996614456176758,
|
|
"epoch": 0.20213832275309054,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998413944965007,
|
|
"loss": 5.7236,
|
|
"mean_token_accuracy": 0.1618449531495571,
|
|
"num_tokens": 4464035.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.7577736377716064,
|
|
"epoch": 0.20255596391580355,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998402749324823,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.163533054292202,
|
|
"num_tokens": 4472055.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.785602712631226,
|
|
"epoch": 0.20297360507851653,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998391514323642,
|
|
"loss": 5.6749,
|
|
"mean_token_accuracy": 0.1660549208521843,
|
|
"num_tokens": 4480669.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.895810174942016,
|
|
"epoch": 0.20339124624122953,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998380239961661,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.1660724997520447,
|
|
"num_tokens": 4489481.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.792815732955932,
|
|
"epoch": 0.20380888740394254,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998368926239078,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1635495975613594,
|
|
"num_tokens": 4497508.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.710590028762818,
|
|
"epoch": 0.20422652856665552,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499835757315609,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.16281557828187943,
|
|
"num_tokens": 4506373.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.8337420463562015,
|
|
"epoch": 0.20464416972936852,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998346180712898,
|
|
"loss": 5.6954,
|
|
"mean_token_accuracy": 0.1564403623342514,
|
|
"num_tokens": 4516283.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.770689964294434,
|
|
"epoch": 0.20506181089208153,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998334748909698,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.1744811698794365,
|
|
"num_tokens": 4524276.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.7850175380706785,
|
|
"epoch": 0.2054794520547945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998323277746694,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.15986775159835814,
|
|
"num_tokens": 4532951.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.787815380096435,
|
|
"epoch": 0.20589709321750752,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004998311767224081,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16870736479759216,
|
|
"num_tokens": 4542229.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.749476480484009,
|
|
"epoch": 0.20631473438022052,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998300217342067,
|
|
"loss": 5.5336,
|
|
"mean_token_accuracy": 0.16806766539812087,
|
|
"num_tokens": 4551126.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.787161350250244,
|
|
"epoch": 0.2067323755429335,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004998288628100851,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.1591607302427292,
|
|
"num_tokens": 4560628.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.809577608108521,
|
|
"epoch": 0.2071500167056465,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998276999500636,
|
|
"loss": 5.6891,
|
|
"mean_token_accuracy": 0.16426692605018617,
|
|
"num_tokens": 4570184.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.848023366928101,
|
|
"epoch": 0.2075676578683595,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998265331541627,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.16781152188777923,
|
|
"num_tokens": 4580357.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.827300310134888,
|
|
"epoch": 0.2079852990310725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998253624224026,
|
|
"loss": 5.7448,
|
|
"mean_token_accuracy": 0.1515749141573906,
|
|
"num_tokens": 4589965.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.801667642593384,
|
|
"epoch": 0.2084029401937855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499824187754804,
|
|
"loss": 5.5621,
|
|
"mean_token_accuracy": 0.1672935664653778,
|
|
"num_tokens": 4598753.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.7748055934906,
|
|
"epoch": 0.2088205813564985,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998230091513872,
|
|
"loss": 5.6224,
|
|
"mean_token_accuracy": 0.16568318605422974,
|
|
"num_tokens": 4608698.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.810699701309204,
|
|
"epoch": 0.20923822251921148,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998218266121731,
|
|
"loss": 5.7281,
|
|
"mean_token_accuracy": 0.16196652129292488,
|
|
"num_tokens": 4618137.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.762399625778198,
|
|
"epoch": 0.2096558636819245,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998206401371823,
|
|
"loss": 5.5543,
|
|
"mean_token_accuracy": 0.16459099799394608,
|
|
"num_tokens": 4627468.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.700483942031861,
|
|
"epoch": 0.2100735048446375,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998194497264357,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.17145939618349076,
|
|
"num_tokens": 4636659.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.712591743469238,
|
|
"epoch": 0.21049114600735047,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998182553799538,
|
|
"loss": 5.5657,
|
|
"mean_token_accuracy": 0.1616992771625519,
|
|
"num_tokens": 4644969.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.8478742122650145,
|
|
"epoch": 0.21090878717006348,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998170570977579,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15977111607789993,
|
|
"num_tokens": 4653930.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.778926277160645,
|
|
"epoch": 0.21132642833277648,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998158548798687,
|
|
"loss": 5.5438,
|
|
"mean_token_accuracy": 0.16683215498924256,
|
|
"num_tokens": 4663146.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.731309604644776,
|
|
"epoch": 0.21174406949548946,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998146487263074,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15984612554311753,
|
|
"num_tokens": 4671874.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.6937836647033695,
|
|
"epoch": 0.21216171065820247,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998134386370951,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.1655649721622467,
|
|
"num_tokens": 4680811.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.822449207305908,
|
|
"epoch": 0.21257935182091547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998122246122529,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.1640414848923683,
|
|
"num_tokens": 4689977.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.72489562034607,
|
|
"epoch": 0.21299699298362845,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998110066518021,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.1763449266552925,
|
|
"num_tokens": 4698479.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.640039730072021,
|
|
"epoch": 0.21341463414634146,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499809784755764,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.161933995783329,
|
|
"num_tokens": 4707575.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.783615350723267,
|
|
"epoch": 0.21383227530905446,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049980855892416,
|
|
"loss": 5.6148,
|
|
"mean_token_accuracy": 0.1656864881515503,
|
|
"num_tokens": 4717015.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.783946561813354,
|
|
"epoch": 0.21424991647176747,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004998073291570116,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.15882773846387863,
|
|
"num_tokens": 4726466.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.801740312576294,
|
|
"epoch": 0.21466755763448045,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998060954543404,
|
|
"loss": 5.6929,
|
|
"mean_token_accuracy": 0.16479280441999436,
|
|
"num_tokens": 4736497.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.713510656356812,
|
|
"epoch": 0.21508519879719346,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998048578161678,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.1654522955417633,
|
|
"num_tokens": 4745693.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.744898414611816,
|
|
"epoch": 0.21550283995990646,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998036162425155,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.1734490066766739,
|
|
"num_tokens": 4754274.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.825760412216186,
|
|
"epoch": 0.21592048112261944,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998023707334055,
|
|
"loss": 5.76,
|
|
"mean_token_accuracy": 0.15564341247081756,
|
|
"num_tokens": 4765607.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.813382291793824,
|
|
"epoch": 0.21633812228533245,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998011212888592,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.16956669241189956,
|
|
"num_tokens": 4775291.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.656440782546997,
|
|
"epoch": 0.21675576344804545,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997998679088988,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.1743773937225342,
|
|
"num_tokens": 4783859.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.670311164855957,
|
|
"epoch": 0.21717340461075843,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997986105935461,
|
|
"loss": 5.5265,
|
|
"mean_token_accuracy": 0.16651082336902617,
|
|
"num_tokens": 4792891.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.757329988479614,
|
|
"epoch": 0.21759104577347144,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997973493428231,
|
|
"loss": 5.606,
|
|
"mean_token_accuracy": 0.16225490868091583,
|
|
"num_tokens": 4801551.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.799970865249634,
|
|
"epoch": 0.21800868693618444,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997960841567519,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.16481925845146178,
|
|
"num_tokens": 4810430.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.712379360198975,
|
|
"epoch": 0.21842632809889742,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997948150353548,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.1724429875612259,
|
|
"num_tokens": 4819156.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.778680372238159,
|
|
"epoch": 0.21884396926161043,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997935419786537,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.16232399195432662,
|
|
"num_tokens": 4827724.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.7654613018035885,
|
|
"epoch": 0.21926161042432343,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997922649866712,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.17342215925455093,
|
|
"num_tokens": 4836954.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.770890951156616,
|
|
"epoch": 0.2196792515870364,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997909840594294,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.16099561005830765,
|
|
"num_tokens": 4847504.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.784782838821411,
|
|
"epoch": 0.22009689274974942,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997896991969509,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.17029968053102493,
|
|
"num_tokens": 4856105.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.7090918064117435,
|
|
"epoch": 0.22051453391246242,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997884103992581,
|
|
"loss": 5.5947,
|
|
"mean_token_accuracy": 0.16394108533859253,
|
|
"num_tokens": 4866118.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.75405969619751,
|
|
"epoch": 0.2209321750751754,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997871176663736,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.16301430761814117,
|
|
"num_tokens": 4875242.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.890598392486572,
|
|
"epoch": 0.2213498162378884,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997858209983201,
|
|
"loss": 5.6817,
|
|
"mean_token_accuracy": 0.16772009283304215,
|
|
"num_tokens": 4884726.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.734208250045777,
|
|
"epoch": 0.22176745740060141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997845203951202,
|
|
"loss": 5.6117,
|
|
"mean_token_accuracy": 0.16239058673381807,
|
|
"num_tokens": 4893178.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.790639019012451,
|
|
"epoch": 0.2221850985633144,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997832158567967,
|
|
"loss": 5.7144,
|
|
"mean_token_accuracy": 0.16555942147970198,
|
|
"num_tokens": 4903126.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.7078839302062985,
|
|
"epoch": 0.2226027397260274,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997819073833724,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.17669259011745453,
|
|
"num_tokens": 4912069.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.6767395496368405,
|
|
"epoch": 0.2230203808887404,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997805949748702,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16776227653026582,
|
|
"num_tokens": 4921014.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.594740676879883,
|
|
"epoch": 0.22343802205145338,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997792786313132,
|
|
"loss": 5.5565,
|
|
"mean_token_accuracy": 0.16906140074133874,
|
|
"num_tokens": 4930382.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.7800782203674315,
|
|
"epoch": 0.2238556632141664,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997779583527243,
|
|
"loss": 5.6108,
|
|
"mean_token_accuracy": 0.15652296096086502,
|
|
"num_tokens": 4939672.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.809805393218994,
|
|
"epoch": 0.2242733043768794,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997766341391268,
|
|
"loss": 5.6483,
|
|
"mean_token_accuracy": 0.15791001468896865,
|
|
"num_tokens": 4949186.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.787170314788819,
|
|
"epoch": 0.22469094553959237,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997753059905437,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.1618640184402466,
|
|
"num_tokens": 4958155.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.640371799468994,
|
|
"epoch": 0.22510858670230538,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997739739069981,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.17097348123788833,
|
|
"num_tokens": 4966524.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.768008184432984,
|
|
"epoch": 0.22552622786501839,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997726378885138,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.16756032705307006,
|
|
"num_tokens": 4976066.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.716037225723267,
|
|
"epoch": 0.22594386902773136,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997712979351137,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.17585382759571075,
|
|
"num_tokens": 4984957.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.6190448760986325,
|
|
"epoch": 0.22636151019044437,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997699540468216,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.17340092957019806,
|
|
"num_tokens": 4994430.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.646725225448608,
|
|
"epoch": 0.22677915135315738,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997686062236609,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.1680037721991539,
|
|
"num_tokens": 5003893.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.751096105575561,
|
|
"epoch": 0.22719679251587035,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997672544656553,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.16746485978364944,
|
|
"num_tokens": 5014083.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.6994177341461185,
|
|
"epoch": 0.22761443367858336,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997658987728283,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1704857677221298,
|
|
"num_tokens": 5023025.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.653778743743897,
|
|
"epoch": 0.22803207484129637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997645391452035,
|
|
"loss": 5.5722,
|
|
"mean_token_accuracy": 0.1677939623594284,
|
|
"num_tokens": 5032620.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.802613639831543,
|
|
"epoch": 0.22844971600400935,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499763175582805,
|
|
"loss": 5.5867,
|
|
"mean_token_accuracy": 0.16344683468341828,
|
|
"num_tokens": 5041773.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.8078845024108885,
|
|
"epoch": 0.22886735716672235,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997618080856566,
|
|
"loss": 5.6512,
|
|
"mean_token_accuracy": 0.15850055813789368,
|
|
"num_tokens": 5051450.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.704273319244384,
|
|
"epoch": 0.22928499832943536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997604366537823,
|
|
"loss": 5.6019,
|
|
"mean_token_accuracy": 0.16153014898300172,
|
|
"num_tokens": 5061172.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.68063178062439,
|
|
"epoch": 0.22970263949214834,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997590612872058,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.17272624373435974,
|
|
"num_tokens": 5071161.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.735128879547119,
|
|
"epoch": 0.23012028065486134,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997576819859515,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.1705945312976837,
|
|
"num_tokens": 5080884.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.698446464538574,
|
|
"epoch": 0.23053792181757435,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997562987500434,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.16551766842603682,
|
|
"num_tokens": 5090164.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.622687101364136,
|
|
"epoch": 0.23095556298028733,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997549115795058,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.1630670577287674,
|
|
"num_tokens": 5098700.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.801355028152466,
|
|
"epoch": 0.23137320414300033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499753520474363,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.15362178534269333,
|
|
"num_tokens": 5107713.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.88943395614624,
|
|
"epoch": 0.23179084530571334,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004997521254346391,
|
|
"loss": 5.7254,
|
|
"mean_token_accuracy": 0.15206045657396317,
|
|
"num_tokens": 5117532.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.686231327056885,
|
|
"epoch": 0.23220848646842632,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997507264603589,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.16964103877544404,
|
|
"num_tokens": 5126891.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.638346815109253,
|
|
"epoch": 0.23262612763113932,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997493235515466,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.1693371891975403,
|
|
"num_tokens": 5135608.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.718230295181274,
|
|
"epoch": 0.23304376879385233,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004997479167082269,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.16581456810235978,
|
|
"num_tokens": 5145055.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.780206775665283,
|
|
"epoch": 0.2334614099565653,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997465059304243,
|
|
"loss": 5.5928,
|
|
"mean_token_accuracy": 0.16677365899086,
|
|
"num_tokens": 5154742.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.755462265014648,
|
|
"epoch": 0.23387905111927831,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997450912181637,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.1658760577440262,
|
|
"num_tokens": 5163876.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.690133333206177,
|
|
"epoch": 0.23429669228199132,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004997436725714696,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.16277918666601182,
|
|
"num_tokens": 5173614.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.723607540130615,
|
|
"epoch": 0.2347143334447043,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997422499903671,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.17018153071403502,
|
|
"num_tokens": 5182061.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.859146022796631,
|
|
"epoch": 0.2351319746074173,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499740823474881,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.15502672716975213,
|
|
"num_tokens": 5191661.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.838399457931518,
|
|
"epoch": 0.2355496157701303,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997393930250363,
|
|
"loss": 5.668,
|
|
"mean_token_accuracy": 0.15951003283262252,
|
|
"num_tokens": 5200624.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.732665061950684,
|
|
"epoch": 0.2359672569328433,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499737958640858,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.16468401551246642,
|
|
"num_tokens": 5209741.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.711571788787841,
|
|
"epoch": 0.2363848980955563,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997365203223711,
|
|
"loss": 5.5124,
|
|
"mean_token_accuracy": 0.17061730325222016,
|
|
"num_tokens": 5218877.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.721763801574707,
|
|
"epoch": 0.2368025392582693,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499735078069601,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.15691242963075638,
|
|
"num_tokens": 5229153.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.712396860122681,
|
|
"epoch": 0.23722018042098228,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004997336318825728,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.16605440974235536,
|
|
"num_tokens": 5238561.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.745545673370361,
|
|
"epoch": 0.23763782158369529,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004997321817613119,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.16150942146778108,
|
|
"num_tokens": 5248135.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.727228450775146,
|
|
"epoch": 0.2380554627464083,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997307277058436,
|
|
"loss": 5.5193,
|
|
"mean_token_accuracy": 0.1711078479886055,
|
|
"num_tokens": 5257286.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.73480453491211,
|
|
"epoch": 0.23847310390912127,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997292697161935,
|
|
"loss": 5.7028,
|
|
"mean_token_accuracy": 0.1597718745470047,
|
|
"num_tokens": 5266595.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.738870573043823,
|
|
"epoch": 0.23889074507183428,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499727807792387,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.16441358774900436,
|
|
"num_tokens": 5275651.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.6004722118377686,
|
|
"epoch": 0.23930838623454728,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997263419344495,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.17445990592241287,
|
|
"num_tokens": 5284596.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.684853649139404,
|
|
"epoch": 0.23972602739726026,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997248721424071,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.16735316216945648,
|
|
"num_tokens": 5292410.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.689931201934814,
|
|
"epoch": 0.24014366855997327,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997233984162853,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.17355552911758423,
|
|
"num_tokens": 5301124.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.752901887893676,
|
|
"epoch": 0.24056130972268627,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997219207561099,
|
|
"loss": 5.5634,
|
|
"mean_token_accuracy": 0.16944514065980912,
|
|
"num_tokens": 5310571.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.711241912841797,
|
|
"epoch": 0.24097895088539925,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997204391619068,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16994390040636062,
|
|
"num_tokens": 5319746.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.681296682357788,
|
|
"epoch": 0.24139659204811226,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997189536337018,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.16615889891982077,
|
|
"num_tokens": 5329734.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.638192129135132,
|
|
"epoch": 0.24181423321082526,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997174641715211,
|
|
"loss": 5.4221,
|
|
"mean_token_accuracy": 0.174007411301136,
|
|
"num_tokens": 5338405.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.7107789516448975,
|
|
"epoch": 0.24223187437353827,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997159707753906,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.16282730400562287,
|
|
"num_tokens": 5348179.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.830678081512451,
|
|
"epoch": 0.24264951553625125,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997144734453367,
|
|
"loss": 5.6737,
|
|
"mean_token_accuracy": 0.15729831159114838,
|
|
"num_tokens": 5358035.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.681098127365113,
|
|
"epoch": 0.24306715669896425,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997129721813853,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.17312878519296646,
|
|
"num_tokens": 5366713.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.59452486038208,
|
|
"epoch": 0.24348479786167726,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997114669835629,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.17589147090911866,
|
|
"num_tokens": 5375245.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.598801755905152,
|
|
"epoch": 0.24390243902439024,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997099578518959,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.17066216617822647,
|
|
"num_tokens": 5384097.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.769566297531128,
|
|
"epoch": 0.24432008018710324,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997084447864105,
|
|
"loss": 5.6232,
|
|
"mean_token_accuracy": 0.15925524681806563,
|
|
"num_tokens": 5393611.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.702077054977417,
|
|
"epoch": 0.24473772134981625,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004997069277871333,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.16924689710140228,
|
|
"num_tokens": 5402332.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.572508668899536,
|
|
"epoch": 0.24515536251252923,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997054068540908,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.1812253177165985,
|
|
"num_tokens": 5411415.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.762411594390869,
|
|
"epoch": 0.24557300367524224,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997038819873098,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.17928455621004105,
|
|
"num_tokens": 5419742.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.63980073928833,
|
|
"epoch": 0.24599064483795524,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997023531868167,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.17695468217134475,
|
|
"num_tokens": 5428689.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.7062506675720215,
|
|
"epoch": 0.24640828600066822,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004997008204526386,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.159965880215168,
|
|
"num_tokens": 5438096.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.713601589202881,
|
|
"epoch": 0.24682592716338123,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996992837848021,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.16694851964712143,
|
|
"num_tokens": 5446726.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.689603424072265,
|
|
"epoch": 0.24724356832609423,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996977431833342,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.164705727994442,
|
|
"num_tokens": 5456275.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.7204803943634035,
|
|
"epoch": 0.2476612094888072,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996961986482618,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.17396539449691772,
|
|
"num_tokens": 5466135.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.666129779815674,
|
|
"epoch": 0.24807885065152022,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996946501796119,
|
|
"loss": 5.445,
|
|
"mean_token_accuracy": 0.1775720924139023,
|
|
"num_tokens": 5474882.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.536153888702392,
|
|
"epoch": 0.24849649181423322,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996930977774118,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.17584052830934524,
|
|
"num_tokens": 5484856.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.7396951675415036,
|
|
"epoch": 0.2489141329769462,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996915414416885,
|
|
"loss": 5.5855,
|
|
"mean_token_accuracy": 0.16176697015762329,
|
|
"num_tokens": 5493840.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.690059757232666,
|
|
"epoch": 0.2493317741396592,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996899811724693,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.1691231533885002,
|
|
"num_tokens": 5502655.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.6382838726043705,
|
|
"epoch": 0.2497494153023722,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996884169697816,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.17606000751256942,
|
|
"num_tokens": 5511640.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.601326131820679,
|
|
"epoch": 0.2501670564650852,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996868488336526,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.1702730119228363,
|
|
"num_tokens": 5520704.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.68818998336792,
|
|
"epoch": 0.25058469762779817,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996852767641099,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.16632438600063323,
|
|
"num_tokens": 5531090.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.25058469762779817,
|
|
"eval_entropy": 5.435018019059077,
|
|
"eval_loss": 5.5041375160217285,
|
|
"eval_mean_token_accuracy": 0.17884081382335204,
|
|
"eval_num_tokens": 5531090.0,
|
|
"eval_runtime": 45.7906,
|
|
"eval_samples_per_second": 824.689,
|
|
"eval_steps_per_second": 103.1,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.701263189315796,
|
|
"epoch": 0.2510023387905112,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996837007611811,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.1650678113102913,
|
|
"num_tokens": 5539905.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.780577039718628,
|
|
"epoch": 0.2514199799532242,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996821208248935,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.1613453820347786,
|
|
"num_tokens": 5549052.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.770159578323364,
|
|
"epoch": 0.25183762111593716,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996805369552749,
|
|
"loss": 5.6166,
|
|
"mean_token_accuracy": 0.16313306540250777,
|
|
"num_tokens": 5558156.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.691643190383911,
|
|
"epoch": 0.2522552622786502,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004996789491523532,
|
|
"loss": 5.5177,
|
|
"mean_token_accuracy": 0.1727276027202606,
|
|
"num_tokens": 5567367.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.689290523529053,
|
|
"epoch": 0.2526729034413632,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004996773574161559,
|
|
"loss": 5.613,
|
|
"mean_token_accuracy": 0.1634739249944687,
|
|
"num_tokens": 5576883.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.735215950012207,
|
|
"epoch": 0.25309054460407615,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996757617467112,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.16875770837068557,
|
|
"num_tokens": 5586050.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.781308889389038,
|
|
"epoch": 0.2535081857667892,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996741621440466,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.16329652369022368,
|
|
"num_tokens": 5595933.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.716435384750366,
|
|
"epoch": 0.25392582692950216,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996725586081906,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.16573665738105775,
|
|
"num_tokens": 5604832.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.676588869094848,
|
|
"epoch": 0.25434346809221514,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996709511391709,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.16873539686203004,
|
|
"num_tokens": 5614077.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.658464765548706,
|
|
"epoch": 0.2547611092549282,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996693397370158,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.17220488786697388,
|
|
"num_tokens": 5622971.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.5848020076751705,
|
|
"epoch": 0.25517875041764115,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996677244017534,
|
|
"loss": 5.4154,
|
|
"mean_token_accuracy": 0.17932918518781663,
|
|
"num_tokens": 5631356.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.64474573135376,
|
|
"epoch": 0.25559639158035413,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996661051334121,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.1699503093957901,
|
|
"num_tokens": 5641095.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.645469522476196,
|
|
"epoch": 0.25601403274306717,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996644819320201,
|
|
"loss": 5.4605,
|
|
"mean_token_accuracy": 0.1748073071241379,
|
|
"num_tokens": 5651311.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.704125118255615,
|
|
"epoch": 0.25643167390578014,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996628547976061,
|
|
"loss": 5.4973,
|
|
"mean_token_accuracy": 0.173713319003582,
|
|
"num_tokens": 5659957.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.599669027328491,
|
|
"epoch": 0.2568493150684932,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996612237301983,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.16966650635004044,
|
|
"num_tokens": 5668876.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.591058588027954,
|
|
"epoch": 0.25726695623120616,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996595887298254,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.1702518045902252,
|
|
"num_tokens": 5677809.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.600033569335937,
|
|
"epoch": 0.25768459739391913,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499657949796516,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.1776470348238945,
|
|
"num_tokens": 5687055.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.57922329902649,
|
|
"epoch": 0.25810223855663217,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996563069302986,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.17120731472969056,
|
|
"num_tokens": 5696394.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.701501893997192,
|
|
"epoch": 0.25851987971934515,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996546601312023,
|
|
"loss": 5.5305,
|
|
"mean_token_accuracy": 0.17498694807291032,
|
|
"num_tokens": 5704372.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.607770776748657,
|
|
"epoch": 0.2589375208820581,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004996530093992558,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17966010719537734,
|
|
"num_tokens": 5713535.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.569789981842041,
|
|
"epoch": 0.25935516204477116,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996513547344877,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.17471472620964051,
|
|
"num_tokens": 5722559.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.640872287750244,
|
|
"epoch": 0.25977280320748414,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996496961369274,
|
|
"loss": 5.5028,
|
|
"mean_token_accuracy": 0.1675395280122757,
|
|
"num_tokens": 5731765.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.562532901763916,
|
|
"epoch": 0.2601904443701971,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996480336066037,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.18473481386899948,
|
|
"num_tokens": 5739989.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.575654935836792,
|
|
"epoch": 0.26060808553291015,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004996463671435458,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.17603574693202972,
|
|
"num_tokens": 5748461.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.696073913574219,
|
|
"epoch": 0.26102572669562313,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996446967477829,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.17175565510988236,
|
|
"num_tokens": 5757495.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.760733699798584,
|
|
"epoch": 0.2614433678583361,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996430224193441,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.16298272460699081,
|
|
"num_tokens": 5767951.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.7048746109008786,
|
|
"epoch": 0.26186100902104914,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996413441582589,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.17121414095163345,
|
|
"num_tokens": 5777021.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.621953725814819,
|
|
"epoch": 0.2622786501837621,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996396619645564,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.17355370968580247,
|
|
"num_tokens": 5785794.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.62881326675415,
|
|
"epoch": 0.2626962913464751,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996379758382662,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.17763975858688355,
|
|
"num_tokens": 5794480.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.504114103317261,
|
|
"epoch": 0.26311393250918813,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499636285779418,
|
|
"loss": 5.3339,
|
|
"mean_token_accuracy": 0.18272120505571365,
|
|
"num_tokens": 5802341.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.616283178329468,
|
|
"epoch": 0.2635315736719011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996345917880412,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.1707792580127716,
|
|
"num_tokens": 5811365.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.590710544586182,
|
|
"epoch": 0.2639492148346141,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996328938641654,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.18022541850805282,
|
|
"num_tokens": 5819957.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.6348718166351315,
|
|
"epoch": 0.2643668559973271,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996311920078204,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.17249127775430678,
|
|
"num_tokens": 5828378.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.701619005203247,
|
|
"epoch": 0.2647844971600401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004996294862190361,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.1653009533882141,
|
|
"num_tokens": 5837310.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.640773677825928,
|
|
"epoch": 0.2652021383227531,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499627776497842,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.17431499511003495,
|
|
"num_tokens": 5845945.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.565975904464722,
|
|
"epoch": 0.2656197794854661,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996260628442686,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.16953630596399308,
|
|
"num_tokens": 5855954.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.73816499710083,
|
|
"epoch": 0.2660374206481791,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004996243452583454,
|
|
"loss": 5.5884,
|
|
"mean_token_accuracy": 0.15719056725502015,
|
|
"num_tokens": 5865327.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.765272760391236,
|
|
"epoch": 0.26645506181089207,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996226237401028,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.17207725644111632,
|
|
"num_tokens": 5873959.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.617573165893555,
|
|
"epoch": 0.2668727029736051,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996208982895706,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.17430177181959153,
|
|
"num_tokens": 5882566.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.6079028129577635,
|
|
"epoch": 0.2672903441363181,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996191689067794,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.171030256152153,
|
|
"num_tokens": 5891407.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.680180215835572,
|
|
"epoch": 0.26770798529903106,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996174355917591,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.1772758662700653,
|
|
"num_tokens": 5900123.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.59296555519104,
|
|
"epoch": 0.2681256264617441,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996156983445404,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.17191927433013915,
|
|
"num_tokens": 5909043.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.644886541366577,
|
|
"epoch": 0.26854326762445707,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996139571651534,
|
|
"loss": 5.5085,
|
|
"mean_token_accuracy": 0.17081481367349624,
|
|
"num_tokens": 5918728.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.700129461288452,
|
|
"epoch": 0.26896090878717005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996122120536288,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.1704002872109413,
|
|
"num_tokens": 5927281.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.654440546035767,
|
|
"epoch": 0.2693785499498831,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996104630099969,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18245238363742827,
|
|
"num_tokens": 5935696.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.487210369110107,
|
|
"epoch": 0.26979619111259606,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996087100342885,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.17293272614479066,
|
|
"num_tokens": 5944858.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.786357736587524,
|
|
"epoch": 0.27021383227530904,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996069531265345,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.1659095987677574,
|
|
"num_tokens": 5954243.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.619866609573364,
|
|
"epoch": 0.2706314734380221,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996051922867653,
|
|
"loss": 5.4607,
|
|
"mean_token_accuracy": 0.1738550290465355,
|
|
"num_tokens": 5963318.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.562462186813354,
|
|
"epoch": 0.27104911460073505,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996034275150118,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.18603187501430513,
|
|
"num_tokens": 5971487.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.563692235946656,
|
|
"epoch": 0.27146675576344803,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499601658811305,
|
|
"loss": 5.4388,
|
|
"mean_token_accuracy": 0.18158252984285356,
|
|
"num_tokens": 5979981.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.720085859298706,
|
|
"epoch": 0.27188439692616106,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995998861756758,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1740057200193405,
|
|
"num_tokens": 5989427.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.600606250762939,
|
|
"epoch": 0.27230203808887404,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995981096081552,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.17140828669071198,
|
|
"num_tokens": 5999434.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.588597822189331,
|
|
"epoch": 0.272719679251587,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995963291087744,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.1686915397644043,
|
|
"num_tokens": 6008963.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.639681959152222,
|
|
"epoch": 0.27313732041430006,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004995945446775645,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.16593142300844194,
|
|
"num_tokens": 6017693.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.689112806320191,
|
|
"epoch": 0.27355496157701303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995927563145566,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.1642194002866745,
|
|
"num_tokens": 6027943.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.699401807785034,
|
|
"epoch": 0.273972602739726,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995909640197825,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.17256641536951065,
|
|
"num_tokens": 6036750.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.606420516967773,
|
|
"epoch": 0.27439024390243905,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995891677932729,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.1757910281419754,
|
|
"num_tokens": 6045722.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.575706672668457,
|
|
"epoch": 0.274807885065152,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995873676350597,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.1688882127404213,
|
|
"num_tokens": 6055001.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.714236783981323,
|
|
"epoch": 0.275225526227865,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995855635451743,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.16770867705345155,
|
|
"num_tokens": 6063420.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.56790246963501,
|
|
"epoch": 0.27564316739057804,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995837555236484,
|
|
"loss": 5.4715,
|
|
"mean_token_accuracy": 0.1717872366309166,
|
|
"num_tokens": 6073075.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.686523342132569,
|
|
"epoch": 0.276060808553291,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995819435705133,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.16897699981927872,
|
|
"num_tokens": 6083035.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.562081241607666,
|
|
"epoch": 0.276478449716004,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995801276858011,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.17127932012081146,
|
|
"num_tokens": 6090980.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.583674812316895,
|
|
"epoch": 0.276896090878717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995783078695434,
|
|
"loss": 5.4192,
|
|
"mean_token_accuracy": 0.1810470089316368,
|
|
"num_tokens": 6099402.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.670659017562866,
|
|
"epoch": 0.27731373204143,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499576484121772,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.17860162109136582,
|
|
"num_tokens": 6109251.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.685530805587769,
|
|
"epoch": 0.277731373204143,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995746564425191,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.16376227289438247,
|
|
"num_tokens": 6119005.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.680942440032959,
|
|
"epoch": 0.278149014366856,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004995728248318163,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.17641908675432205,
|
|
"num_tokens": 6127566.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.582499313354492,
|
|
"epoch": 0.278566655529569,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995709892896961,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.1744324892759323,
|
|
"num_tokens": 6137189.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.691714143753051,
|
|
"epoch": 0.278984296692282,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995691498161903,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.1700959786772728,
|
|
"num_tokens": 6147038.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.683166360855102,
|
|
"epoch": 0.279401937854995,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004995673064113313,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.17305740118026733,
|
|
"num_tokens": 6155770.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.587224531173706,
|
|
"epoch": 0.279819579017708,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995654590751513,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.17449014633893967,
|
|
"num_tokens": 6164030.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.572806549072266,
|
|
"epoch": 0.28023722018042097,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995636078076825,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.17433962225914001,
|
|
"num_tokens": 6173046.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.666071510314941,
|
|
"epoch": 0.280654861343134,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995617526089575,
|
|
"loss": 5.4332,
|
|
"mean_token_accuracy": 0.179418683052063,
|
|
"num_tokens": 6182193.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.60524845123291,
|
|
"epoch": 0.281072502505847,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995598934790087,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.17807191610336304,
|
|
"num_tokens": 6190791.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.6347860336303714,
|
|
"epoch": 0.28149014366855996,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995580304178687,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.16796986013650894,
|
|
"num_tokens": 6199245.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.605140256881714,
|
|
"epoch": 0.281907784831273,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995561634255701,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.17431096434593202,
|
|
"num_tokens": 6208420.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.610596609115601,
|
|
"epoch": 0.28232542599398597,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995542925021455,
|
|
"loss": 5.5092,
|
|
"mean_token_accuracy": 0.1715408131480217,
|
|
"num_tokens": 6217059.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.581323337554932,
|
|
"epoch": 0.28274306715669895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995524176476277,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.17685751914978026,
|
|
"num_tokens": 6225955.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.584299468994141,
|
|
"epoch": 0.283160708319412,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995505388620497,
|
|
"loss": 5.4535,
|
|
"mean_token_accuracy": 0.17205138504505157,
|
|
"num_tokens": 6235989.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.671328830718994,
|
|
"epoch": 0.28357834948212496,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499548656145444,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.16483559012413024,
|
|
"num_tokens": 6244821.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.658933019638061,
|
|
"epoch": 0.28399599064483794,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004995467694978439,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.16611048877239226,
|
|
"num_tokens": 6254157.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.750556373596192,
|
|
"epoch": 0.28441363180755097,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995448789192823,
|
|
"loss": 5.5468,
|
|
"mean_token_accuracy": 0.17158015072345734,
|
|
"num_tokens": 6263807.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.580238723754883,
|
|
"epoch": 0.28483127297026395,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995429844097922,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.17550105154514312,
|
|
"num_tokens": 6273075.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.660174798965454,
|
|
"epoch": 0.2852489141329769,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995410859694071,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.17570087164640427,
|
|
"num_tokens": 6282079.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.564072990417481,
|
|
"epoch": 0.28566655529568996,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995391835981599,
|
|
"loss": 5.4799,
|
|
"mean_token_accuracy": 0.1690463125705719,
|
|
"num_tokens": 6291957.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.637568235397339,
|
|
"epoch": 0.28608419645840294,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499537277296084,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.16970505118370055,
|
|
"num_tokens": 6301144.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.621378087997437,
|
|
"epoch": 0.2865018376211159,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995353670632127,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.17622729688882827,
|
|
"num_tokens": 6310654.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.651818752288818,
|
|
"epoch": 0.28691947878382895,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995334528995797,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.1763767495751381,
|
|
"num_tokens": 6319562.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.61013503074646,
|
|
"epoch": 0.28733711994654193,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004995315348052182,
|
|
"loss": 5.4635,
|
|
"mean_token_accuracy": 0.17209085673093796,
|
|
"num_tokens": 6329056.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.562315130233765,
|
|
"epoch": 0.2877547611092549,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499529612780162,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.1756098523736,
|
|
"num_tokens": 6337857.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.648341941833496,
|
|
"epoch": 0.28817240227196794,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995276868244446,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1731391057372093,
|
|
"num_tokens": 6346876.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.526121950149536,
|
|
"epoch": 0.2885900434346809,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995257569380998,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.1779223069548607,
|
|
"num_tokens": 6356200.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.66925311088562,
|
|
"epoch": 0.2890076845973939,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004995238231211614,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.17246579229831696,
|
|
"num_tokens": 6365761.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.6093944072723385,
|
|
"epoch": 0.28942532576010693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004995218853736631,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1674227923154831,
|
|
"num_tokens": 6375326.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.691514873504639,
|
|
"epoch": 0.2898429669228199,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995199436956391,
|
|
"loss": 5.5508,
|
|
"mean_token_accuracy": 0.17709466367959975,
|
|
"num_tokens": 6384662.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.5763490200042725,
|
|
"epoch": 0.2902606080855329,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004995179980871231,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.17378984689712523,
|
|
"num_tokens": 6393576.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.612979507446289,
|
|
"epoch": 0.2906782492482459,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995160485481493,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.1743532732129097,
|
|
"num_tokens": 6402436.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.647745513916016,
|
|
"epoch": 0.2910958904109589,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499514095078752,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.1738475278019905,
|
|
"num_tokens": 6411471.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.667367744445801,
|
|
"epoch": 0.2915135315736719,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499512137678965,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.16805141121149064,
|
|
"num_tokens": 6421355.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.580398082733154,
|
|
"epoch": 0.2919311727363849,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995101763488229,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.1668199583888054,
|
|
"num_tokens": 6430579.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.577182912826538,
|
|
"epoch": 0.2923488138990979,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995082110883599,
|
|
"loss": 5.4551,
|
|
"mean_token_accuracy": 0.1728660747408867,
|
|
"num_tokens": 6439939.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.515458440780639,
|
|
"epoch": 0.29276645506181087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995062418976104,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.17504774332046508,
|
|
"num_tokens": 6448598.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.620071649551392,
|
|
"epoch": 0.2931840962245239,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995042687766089,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.1640665978193283,
|
|
"num_tokens": 6457647.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.542760372161865,
|
|
"epoch": 0.2936017373872369,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995022917253899,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.1857729509472847,
|
|
"num_tokens": 6466391.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.564976930618286,
|
|
"epoch": 0.29401937854994986,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995003107439882,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.1815667122602463,
|
|
"num_tokens": 6475252.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.613153648376465,
|
|
"epoch": 0.2944370197126629,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994983258324383,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.17397726625204085,
|
|
"num_tokens": 6484959.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.652011346817017,
|
|
"epoch": 0.2948546608753759,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004994963369907748,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.17536231279373168,
|
|
"num_tokens": 6495221.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.596998786926269,
|
|
"epoch": 0.29527230203808885,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994943442190328,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.1758079096674919,
|
|
"num_tokens": 6504390.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.49628758430481,
|
|
"epoch": 0.2956899432008019,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994923475172471,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.17681221067905425,
|
|
"num_tokens": 6514105.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.497510385513306,
|
|
"epoch": 0.29610758436351486,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.1738963931798935,
|
|
"num_tokens": 6523673.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.567109155654907,
|
|
"epoch": 0.29652522552622784,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994883423236843,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.18165491968393327,
|
|
"num_tokens": 6532158.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.618200397491455,
|
|
"epoch": 0.2969428666889409,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004994863338319775,
|
|
"loss": 5.4994,
|
|
"mean_token_accuracy": 0.16905129104852676,
|
|
"num_tokens": 6541580.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.614306402206421,
|
|
"epoch": 0.29736050785165385,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004994843214103672,
|
|
"loss": 5.4248,
|
|
"mean_token_accuracy": 0.17545585483312606,
|
|
"num_tokens": 6550298.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.739443969726563,
|
|
"epoch": 0.29777814901436683,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004994823050588886,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.17042788714170456,
|
|
"num_tokens": 6560774.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.604328870773315,
|
|
"epoch": 0.29819579017707987,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499480284777577,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.17681997120380402,
|
|
"num_tokens": 6568946.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.623058176040649,
|
|
"epoch": 0.29861343133979285,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994782605664677,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.1736734241247177,
|
|
"num_tokens": 6579798.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.587291431427002,
|
|
"epoch": 0.2990310725025058,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994762324255965,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.17470444291830062,
|
|
"num_tokens": 6589309.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.675253868103027,
|
|
"epoch": 0.29944871366521886,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994742003549986,
|
|
"loss": 5.5437,
|
|
"mean_token_accuracy": 0.16898644268512725,
|
|
"num_tokens": 6598835.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.6550679206848145,
|
|
"epoch": 0.29986635482793184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994721643547095,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.1754730075597763,
|
|
"num_tokens": 6608167.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.511614847183227,
|
|
"epoch": 0.3002839959906448,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499470124424765,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.18357801884412767,
|
|
"num_tokens": 6616904.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.507685136795044,
|
|
"epoch": 0.30070163715335785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994680805652008,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.17928119003772736,
|
|
"num_tokens": 6625841.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.5269406795501705,
|
|
"epoch": 0.3011192783160708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994660327760527,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.18719015121459961,
|
|
"num_tokens": 6633755.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.544970369338989,
|
|
"epoch": 0.3015369194787838,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994639810573565,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.1831843376159668,
|
|
"num_tokens": 6642372.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.626782369613648,
|
|
"epoch": 0.30195456064149684,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499461925409148,
|
|
"loss": 5.4002,
|
|
"mean_token_accuracy": 0.18004399687051773,
|
|
"num_tokens": 6652271.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.643217420578003,
|
|
"epoch": 0.3023722018042098,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004994598658314634,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.16798514425754546,
|
|
"num_tokens": 6661463.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.589829206466675,
|
|
"epoch": 0.3027898429669228,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004994578023243386,
|
|
"loss": 5.4099,
|
|
"mean_token_accuracy": 0.17615225911140442,
|
|
"num_tokens": 6671423.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.581682109832764,
|
|
"epoch": 0.30320748412963583,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994557348878098,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.1665767788887024,
|
|
"num_tokens": 6680218.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.519573068618774,
|
|
"epoch": 0.3036251252923488,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994536635219133,
|
|
"loss": 5.4024,
|
|
"mean_token_accuracy": 0.17173747718334198,
|
|
"num_tokens": 6689117.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.585209655761719,
|
|
"epoch": 0.3040427664550618,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994515882266852,
|
|
"loss": 5.4655,
|
|
"mean_token_accuracy": 0.17823539227247237,
|
|
"num_tokens": 6698024.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.65181794166565,
|
|
"epoch": 0.3044604076177748,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994495090021618,
|
|
"loss": 5.5942,
|
|
"mean_token_accuracy": 0.1686693847179413,
|
|
"num_tokens": 6706253.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.648300361633301,
|
|
"epoch": 0.3048780487804878,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994474258483796,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.17750954627990723,
|
|
"num_tokens": 6716440.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.619204807281494,
|
|
"epoch": 0.3052956899432008,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994453387653751,
|
|
"loss": 5.3662,
|
|
"mean_token_accuracy": 0.17830655425786973,
|
|
"num_tokens": 6725263.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.542618083953857,
|
|
"epoch": 0.3057133311059138,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994432477531847,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.17351234704256058,
|
|
"num_tokens": 6735023.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.61643500328064,
|
|
"epoch": 0.3061309722686268,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004994411528118452,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.1697386994957924,
|
|
"num_tokens": 6744659.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.551114273071289,
|
|
"epoch": 0.30654861343133977,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994390539413931,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.1664675086736679,
|
|
"num_tokens": 6753844.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.598834800720215,
|
|
"epoch": 0.3069662545940528,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994369511418652,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.17445214986801147,
|
|
"num_tokens": 6762574.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.6650525569915775,
|
|
"epoch": 0.3073838957567658,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994348444132983,
|
|
"loss": 5.5809,
|
|
"mean_token_accuracy": 0.17015109211206436,
|
|
"num_tokens": 6772991.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.548781204223633,
|
|
"epoch": 0.30780153691947876,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004994327337557293,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.17374803274869918,
|
|
"num_tokens": 6781380.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.564214038848877,
|
|
"epoch": 0.3082191780821918,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004994306191691952,
|
|
"loss": 5.4297,
|
|
"mean_token_accuracy": 0.17173753976821898,
|
|
"num_tokens": 6791125.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.718353986740112,
|
|
"epoch": 0.30863681924490477,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004994285006537329,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.17240104228258132,
|
|
"num_tokens": 6801038.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.48997654914856,
|
|
"epoch": 0.30905446040761775,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994263782093796,
|
|
"loss": 5.3667,
|
|
"mean_token_accuracy": 0.17592186182737352,
|
|
"num_tokens": 6810049.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.526648473739624,
|
|
"epoch": 0.3094721015703308,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994242518361723,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.17937501668930053,
|
|
"num_tokens": 6819375.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.6430739402771,
|
|
"epoch": 0.30988974273304376,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004994221215341484,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.17287019789218902,
|
|
"num_tokens": 6828872.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.544311571121216,
|
|
"epoch": 0.31030738389575674,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004994199873033452,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.1801329791545868,
|
|
"num_tokens": 6838698.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.492436122894287,
|
|
"epoch": 0.3107250250584698,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994178491437999,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.18416499048471452,
|
|
"num_tokens": 6848147.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.596598291397095,
|
|
"epoch": 0.31114266622118275,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994157070555501,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.17777412086725236,
|
|
"num_tokens": 6857777.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.618748950958252,
|
|
"epoch": 0.31156030738389573,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994135610386331,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.17851509898900986,
|
|
"num_tokens": 6866340.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.623656368255615,
|
|
"epoch": 0.31197794854660876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994114110930867,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.18082705289125442,
|
|
"num_tokens": 6875670.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.6321512222290036,
|
|
"epoch": 0.31239558970932174,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004994092572189483,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.17251480966806412,
|
|
"num_tokens": 6885722.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.589204740524292,
|
|
"epoch": 0.3128132308720348,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004994070994162558,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17485132813453674,
|
|
"num_tokens": 6894267.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.648172521591187,
|
|
"epoch": 0.31323087203474775,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994049376850471,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16601836010813714,
|
|
"num_tokens": 6904488.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.583740615844727,
|
|
"epoch": 0.31364851319746073,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994027720253596,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.1724591687321663,
|
|
"num_tokens": 6913329.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.544614505767822,
|
|
"epoch": 0.31406615436017377,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994006024372315,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.1843334659934044,
|
|
"num_tokens": 6921722.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.602997827529907,
|
|
"epoch": 0.31448379552288674,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993984289207007,
|
|
"loss": 5.4567,
|
|
"mean_token_accuracy": 0.17751626223325728,
|
|
"num_tokens": 6931183.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.635328531265259,
|
|
"epoch": 0.3149014366855997,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993962514758054,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.17839431315660476,
|
|
"num_tokens": 6939813.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.642183876037597,
|
|
"epoch": 0.31531907784831276,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004993940701025836,
|
|
"loss": 5.5787,
|
|
"mean_token_accuracy": 0.1723739504814148,
|
|
"num_tokens": 6950227.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.620023775100708,
|
|
"epoch": 0.31573671901102573,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993918848010734,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17621598690748214,
|
|
"num_tokens": 6959971.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.537133884429932,
|
|
"epoch": 0.3161543601737387,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993896955713133,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.1891302391886711,
|
|
"num_tokens": 6968557.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.552752256393433,
|
|
"epoch": 0.31657200133645175,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993875024133414,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.17565442025661468,
|
|
"num_tokens": 6978058.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.566929817199707,
|
|
"epoch": 0.3169896424991647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993853053271962,
|
|
"loss": 5.451,
|
|
"mean_token_accuracy": 0.17600191235542298,
|
|
"num_tokens": 6986549.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.570564937591553,
|
|
"epoch": 0.3174072836618777,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004993831043129161,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.1723635047674179,
|
|
"num_tokens": 6995907.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.569065189361572,
|
|
"epoch": 0.31782492482459074,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004993808993705397,
|
|
"loss": 5.3498,
|
|
"mean_token_accuracy": 0.1742982655763626,
|
|
"num_tokens": 7006195.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.447622632980346,
|
|
"epoch": 0.3182425659873037,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993786905001055,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.17850562781095505,
|
|
"num_tokens": 7015223.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.57822813987732,
|
|
"epoch": 0.3186602071500167,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993764777016524,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17754828035831452,
|
|
"num_tokens": 7024191.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.438897752761841,
|
|
"epoch": 0.31907784831272973,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993742609752188,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.17499469965696335,
|
|
"num_tokens": 7032947.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.548297119140625,
|
|
"epoch": 0.3194954894754427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993720403208438,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.18875021934509278,
|
|
"num_tokens": 7041422.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.603101539611816,
|
|
"epoch": 0.3199131306381557,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499369815738566,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.16446553170681,
|
|
"num_tokens": 7051051.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.542109632492066,
|
|
"epoch": 0.3203307718008687,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993675872284248,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17837198227643966,
|
|
"num_tokens": 7060116.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.634469318389892,
|
|
"epoch": 0.3207484129635817,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993653547904586,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.17458738535642623,
|
|
"num_tokens": 7068759.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.415265274047852,
|
|
"epoch": 0.3211660541262947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499363118424707,
|
|
"loss": 5.3133,
|
|
"mean_token_accuracy": 0.1825884237885475,
|
|
"num_tokens": 7078321.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.624850416183472,
|
|
"epoch": 0.3215836952890077,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993608781312088,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.178279247879982,
|
|
"num_tokens": 7088126.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.579383516311646,
|
|
"epoch": 0.3220013364517207,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993586339100035,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.17236804068088532,
|
|
"num_tokens": 7096948.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.429286098480224,
|
|
"epoch": 0.32241897761443367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004993563857611301,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.18273018449544906,
|
|
"num_tokens": 7106867.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.467058324813843,
|
|
"epoch": 0.3228366187771467,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993541336846283,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.17537071853876113,
|
|
"num_tokens": 7115971.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.578650236129761,
|
|
"epoch": 0.3232542599398597,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993518776805372,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.18472694903612136,
|
|
"num_tokens": 7124659.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.605439043045044,
|
|
"epoch": 0.32367190110257266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993496177488965,
|
|
"loss": 5.6036,
|
|
"mean_token_accuracy": 0.16980562806129457,
|
|
"num_tokens": 7133456.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.511414003372193,
|
|
"epoch": 0.3240895422652857,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993473538897457,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.17757457196712495,
|
|
"num_tokens": 7142649.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.648666000366211,
|
|
"epoch": 0.32450718342799867,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993450861031243,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17098803967237472,
|
|
"num_tokens": 7153151.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.503868484497071,
|
|
"epoch": 0.32492482459071165,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993428143890722,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.1792224019765854,
|
|
"num_tokens": 7161638.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.519910860061645,
|
|
"epoch": 0.3253424657534247,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004993405387476291,
|
|
"loss": 5.3676,
|
|
"mean_token_accuracy": 0.180894111096859,
|
|
"num_tokens": 7170832.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.567269706726075,
|
|
"epoch": 0.32576010691613766,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004993382591788349,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.18134671151638032,
|
|
"num_tokens": 7180025.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.553269243240356,
|
|
"epoch": 0.32617774807885064,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993359756827293,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.17944396585226058,
|
|
"num_tokens": 7189287.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.601120281219482,
|
|
"epoch": 0.32659538924156367,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004993336882593524,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.1689503476023674,
|
|
"num_tokens": 7198438.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.528104448318482,
|
|
"epoch": 0.32701303040427665,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993313969087444,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.1743347465991974,
|
|
"num_tokens": 7208006.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.602669095993042,
|
|
"epoch": 0.32743067156698963,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993291016309452,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.17532382905483246,
|
|
"num_tokens": 7216975.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.513580417633056,
|
|
"epoch": 0.32784831272970266,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499326802425995,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.17284868955612182,
|
|
"num_tokens": 7225664.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.578778839111328,
|
|
"epoch": 0.32826595389241564,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993244992939342,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.17680099755525588,
|
|
"num_tokens": 7234780.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.590681791305542,
|
|
"epoch": 0.3286835950551286,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499322192234803,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.18491931557655333,
|
|
"num_tokens": 7242648.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.542868185043335,
|
|
"epoch": 0.32910123621784165,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993198812486418,
|
|
"loss": 5.4138,
|
|
"mean_token_accuracy": 0.18120619356632234,
|
|
"num_tokens": 7251856.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.669962549209595,
|
|
"epoch": 0.32951887738055463,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499317566335491,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.17906445413827896,
|
|
"num_tokens": 7260552.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.527570629119873,
|
|
"epoch": 0.3299365185432676,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004993152474953913,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.17863740175962448,
|
|
"num_tokens": 7270328.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.501397800445557,
|
|
"epoch": 0.33035415970598064,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993129247283831,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.18057112395763397,
|
|
"num_tokens": 7279797.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.573873615264892,
|
|
"epoch": 0.3307718008686936,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993105980345071,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.17486949414014816,
|
|
"num_tokens": 7290205.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.548024415969849,
|
|
"epoch": 0.3311894420314066,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993082674138042,
|
|
"loss": 5.4016,
|
|
"mean_token_accuracy": 0.18294740617275237,
|
|
"num_tokens": 7298544.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.442582082748413,
|
|
"epoch": 0.33160708319411963,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499305932866315,
|
|
"loss": 5.3753,
|
|
"mean_token_accuracy": 0.18276675790548325,
|
|
"num_tokens": 7307662.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.542536497116089,
|
|
"epoch": 0.3320247243568326,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004993035943920805,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.17841993570327758,
|
|
"num_tokens": 7317085.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.643019580841065,
|
|
"epoch": 0.3324423655195456,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993012519911416,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.1812269002199173,
|
|
"num_tokens": 7326190.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.5581700801849365,
|
|
"epoch": 0.3328600066822586,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992989056635392,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.18142253309488296,
|
|
"num_tokens": 7336143.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.557201528549195,
|
|
"epoch": 0.3332776478449716,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992965554093146,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.1773979902267456,
|
|
"num_tokens": 7346024.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.588890838623047,
|
|
"epoch": 0.3336952890076846,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992942012285086,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.1687189981341362,
|
|
"num_tokens": 7355477.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.5849528312683105,
|
|
"epoch": 0.3341129301703976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992918431211629,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.1911688417196274,
|
|
"num_tokens": 7364720.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.504607343673706,
|
|
"epoch": 0.3345305713331106,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992894810873183,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.18405580669641494,
|
|
"num_tokens": 7373793.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.550771713256836,
|
|
"epoch": 0.33494821249582357,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004992871151270165,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.1778610572218895,
|
|
"num_tokens": 7383886.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.655559968948364,
|
|
"epoch": 0.3353658536585366,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004992847452402986,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.1737416908144951,
|
|
"num_tokens": 7393617.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.571028566360473,
|
|
"epoch": 0.3357834948212496,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992823714272064,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1906258374452591,
|
|
"num_tokens": 7401949.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.399551343917847,
|
|
"epoch": 0.33620113598396256,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992799936877813,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.18554448932409287,
|
|
"num_tokens": 7410180.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.669768762588501,
|
|
"epoch": 0.3366187771466756,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004992776120220649,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.16831523180007935,
|
|
"num_tokens": 7420506.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.654279279708862,
|
|
"epoch": 0.3370364183093886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992752264300989,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.1782596752047539,
|
|
"num_tokens": 7429644.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.593759536743164,
|
|
"epoch": 0.33745405947210155,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992728369119252,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.17445121109485626,
|
|
"num_tokens": 7439129.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.529770135879517,
|
|
"epoch": 0.3378717006348146,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992704434675855,
|
|
"loss": 5.4463,
|
|
"mean_token_accuracy": 0.16825538277626037,
|
|
"num_tokens": 7449355.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.601033926010132,
|
|
"epoch": 0.33828934179752757,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004992680460971218,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1750248908996582,
|
|
"num_tokens": 7458763.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.5343467712402346,
|
|
"epoch": 0.33870698296024054,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992656448005758,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.18176914155483245,
|
|
"num_tokens": 7467697.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.548629426956177,
|
|
"epoch": 0.3391246241229536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992632395779899,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.1769605129957199,
|
|
"num_tokens": 7476728.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.527476406097412,
|
|
"epoch": 0.33954226528566656,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004992608304294061,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.1807983100414276,
|
|
"num_tokens": 7486794.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.648890638351441,
|
|
"epoch": 0.33995990644837953,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992584173548664,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.17890453785657884,
|
|
"num_tokens": 7496286.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.540819454193115,
|
|
"epoch": 0.34037754761109257,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992560003544131,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.1823621667921543,
|
|
"num_tokens": 7505670.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.524999904632568,
|
|
"epoch": 0.34079518877380555,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004992535794280887,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.17998970299959183,
|
|
"num_tokens": 7514702.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.573918151855469,
|
|
"epoch": 0.3412128299365185,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992511545759354,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.1779135674238205,
|
|
"num_tokens": 7523705.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.477626943588257,
|
|
"epoch": 0.34163047109923156,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992487257979958,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18465856313705445,
|
|
"num_tokens": 7532491.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.512922763824463,
|
|
"epoch": 0.34204811226194454,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004992462930943123,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.17840403020381929,
|
|
"num_tokens": 7540761.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.6294543743133545,
|
|
"epoch": 0.3424657534246575,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992438564649275,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.17790439277887343,
|
|
"num_tokens": 7550897.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.4592883586883545,
|
|
"epoch": 0.34288339458737055,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992414159098841,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.17544154673814774,
|
|
"num_tokens": 7559982.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.524592304229737,
|
|
"epoch": 0.3433010357500835,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992389714292247,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.17102374136447906,
|
|
"num_tokens": 7569358.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.565312910079956,
|
|
"epoch": 0.3437186769127965,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992365230229922,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.173369462788105,
|
|
"num_tokens": 7578437.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.4965414047241214,
|
|
"epoch": 0.34413631807550954,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992340706912295,
|
|
"loss": 5.3223,
|
|
"mean_token_accuracy": 0.18511273562908173,
|
|
"num_tokens": 7587528.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.589574480056763,
|
|
"epoch": 0.3445539592382225,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004992316144339794,
|
|
"loss": 5.3593,
|
|
"mean_token_accuracy": 0.1848417639732361,
|
|
"num_tokens": 7595991.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.51519889831543,
|
|
"epoch": 0.3449716004009355,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004992291542512852,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.18367814123630524,
|
|
"num_tokens": 7604538.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.524887561798096,
|
|
"epoch": 0.34538924156364853,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004992266901431895,
|
|
"loss": 5.3594,
|
|
"mean_token_accuracy": 0.1797987386584282,
|
|
"num_tokens": 7613853.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.478319311141968,
|
|
"epoch": 0.3458068827263615,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004992242221097358,
|
|
"loss": 5.2927,
|
|
"mean_token_accuracy": 0.1872032940387726,
|
|
"num_tokens": 7623538.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.511484241485595,
|
|
"epoch": 0.3462245238890745,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992217501509672,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.1825394406914711,
|
|
"num_tokens": 7632121.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.602395820617676,
|
|
"epoch": 0.3466421650517875,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499219274266927,
|
|
"loss": 5.4051,
|
|
"mean_token_accuracy": 0.1751413092017174,
|
|
"num_tokens": 7640779.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.487886953353882,
|
|
"epoch": 0.3470598062145005,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992167944576584,
|
|
"loss": 5.3108,
|
|
"mean_token_accuracy": 0.17689754217863082,
|
|
"num_tokens": 7649138.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.451353406906128,
|
|
"epoch": 0.3474774473772135,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499214310723205,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.1837406873703003,
|
|
"num_tokens": 7658510.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.49662823677063,
|
|
"epoch": 0.3478950885399265,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992118230636102,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.18834259063005448,
|
|
"num_tokens": 7666946.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.512709474563598,
|
|
"epoch": 0.3483127297026395,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992093314789176,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.1844685673713684,
|
|
"num_tokens": 7675572.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.409683656692505,
|
|
"epoch": 0.34873037086535247,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004992068359691707,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.1820487394928932,
|
|
"num_tokens": 7684719.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.430762386322021,
|
|
"epoch": 0.3491480120280655,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992043365344132,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.17550996094942092,
|
|
"num_tokens": 7694370.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.593293333053589,
|
|
"epoch": 0.3495656531907785,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004992018331746891,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1738266259431839,
|
|
"num_tokens": 7703572.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.579589700698852,
|
|
"epoch": 0.34998329435349146,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991993258900418,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.18230030536651612,
|
|
"num_tokens": 7712732.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.567245578765869,
|
|
"epoch": 0.3504009355162045,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004991968146805156,
|
|
"loss": 5.469,
|
|
"mean_token_accuracy": 0.17016618698835373,
|
|
"num_tokens": 7722213.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.586042642593384,
|
|
"epoch": 0.35081857667891747,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004991942995461542,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.17417784184217452,
|
|
"num_tokens": 7732228.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.545481777191162,
|
|
"epoch": 0.35123621784163045,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004991917804870018,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.17282902151346208,
|
|
"num_tokens": 7741662.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.571476173400879,
|
|
"epoch": 0.3516538590043435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991892575031024,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.18452260494232178,
|
|
"num_tokens": 7749608.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.485206890106201,
|
|
"epoch": 0.35207150016705646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991867305945001,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.17790669053792954,
|
|
"num_tokens": 7758387.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.433868741989135,
|
|
"epoch": 0.35248914132976944,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991841997612394,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.17614639103412627,
|
|
"num_tokens": 7768103.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.48126449584961,
|
|
"epoch": 0.3529067824924825,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991816650033643,
|
|
"loss": 5.233,
|
|
"mean_token_accuracy": 0.18586599677801133,
|
|
"num_tokens": 7776826.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.478780460357666,
|
|
"epoch": 0.35332442365519545,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991791263209194,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.17375344932079315,
|
|
"num_tokens": 7785866.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.607062244415284,
|
|
"epoch": 0.35374206481790843,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004991765837139491,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.1705208495259285,
|
|
"num_tokens": 7795140.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.4969398975372314,
|
|
"epoch": 0.35415970598062146,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991740371824977,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.18425862342119217,
|
|
"num_tokens": 7804256.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.484107542037964,
|
|
"epoch": 0.35457734714333444,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049917148672661,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.18591732233762742,
|
|
"num_tokens": 7812295.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.597751331329346,
|
|
"epoch": 0.3549949883060474,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004991689323463306,
|
|
"loss": 5.3691,
|
|
"mean_token_accuracy": 0.1824835479259491,
|
|
"num_tokens": 7821208.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.499298477172852,
|
|
"epoch": 0.35541262946876045,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004991663740417042,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1770219698548317,
|
|
"num_tokens": 7830542.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.423828172683716,
|
|
"epoch": 0.35583027063147343,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991638118127757,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.18910087496042252,
|
|
"num_tokens": 7839469.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.571734666824341,
|
|
"epoch": 0.3562479117941864,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004991612456595896,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.1752399519085884,
|
|
"num_tokens": 7849350.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.493672275543213,
|
|
"epoch": 0.35666555295689945,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991586755821913,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.18433552831411362,
|
|
"num_tokens": 7858882.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.481722164154053,
|
|
"epoch": 0.3570831941196124,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991561015806254,
|
|
"loss": 5.3898,
|
|
"mean_token_accuracy": 0.1779269754886627,
|
|
"num_tokens": 7868704.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.612700986862182,
|
|
"epoch": 0.3575008352823254,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004991535236549372,
|
|
"loss": 5.4024,
|
|
"mean_token_accuracy": 0.1754518121480942,
|
|
"num_tokens": 7878103.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.37280764579773,
|
|
"epoch": 0.35791847644503844,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004991509418051718,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19291636049747468,
|
|
"num_tokens": 7887228.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.498071479797363,
|
|
"epoch": 0.3583361176077514,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991483560313743,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.17669123709201812,
|
|
"num_tokens": 7897205.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.4981996536254885,
|
|
"epoch": 0.3587537587704644,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00049914576633359,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.18551304191350937,
|
|
"num_tokens": 7906336.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.440997743606568,
|
|
"epoch": 0.3591713999331774,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004991431727118643,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.17580654919147493,
|
|
"num_tokens": 7914773.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.467397689819336,
|
|
"epoch": 0.3595890410958904,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991405751662426,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.18639442771673204,
|
|
"num_tokens": 7922759.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.485037755966187,
|
|
"epoch": 0.3600066822586034,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004991379736967703,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.18302679061889648,
|
|
"num_tokens": 7932199.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.428512048721314,
|
|
"epoch": 0.3604243234213164,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991353683034929,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.18623681366443634,
|
|
"num_tokens": 7941045.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.493168306350708,
|
|
"epoch": 0.3608419645840294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004991327589864563,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.19039287716150283,
|
|
"num_tokens": 7949339.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.488691711425782,
|
|
"epoch": 0.3612596057467424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991301457457057,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.18072604089975358,
|
|
"num_tokens": 7958182.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.510261535644531,
|
|
"epoch": 0.3616772469094554,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991275285812873,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.18515653908252716,
|
|
"num_tokens": 7966711.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.407047462463379,
|
|
"epoch": 0.3620948880721684,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991249074932466,
|
|
"loss": 5.226,
|
|
"mean_token_accuracy": 0.18636159896850585,
|
|
"num_tokens": 7974864.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.485093259811402,
|
|
"epoch": 0.36251252923488136,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004991222824816296,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.17070340663194655,
|
|
"num_tokens": 7984812.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.510895109176635,
|
|
"epoch": 0.3629301703975944,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991196535464824,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.17756010890007018,
|
|
"num_tokens": 7994862.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.519192886352539,
|
|
"epoch": 0.3633478115603074,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991170206878508,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.17955076843500137,
|
|
"num_tokens": 8003943.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.489389324188233,
|
|
"epoch": 0.36376545272302035,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499114383905781,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.18052455335855483,
|
|
"num_tokens": 8012841.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.4510892868042,
|
|
"epoch": 0.3641830938857334,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991117432003192,
|
|
"loss": 5.2826,
|
|
"mean_token_accuracy": 0.18153723031282426,
|
|
"num_tokens": 8021766.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.5102602481842045,
|
|
"epoch": 0.36460073504844637,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004991090985715116,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.1822043165564537,
|
|
"num_tokens": 8030491.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.442203187942505,
|
|
"epoch": 0.36501837621115935,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004991064500194043,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.18632659167051316,
|
|
"num_tokens": 8039325.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.487106895446777,
|
|
"epoch": 0.3654360173738724,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991037975440439,
|
|
"loss": 5.3648,
|
|
"mean_token_accuracy": 0.18059566766023635,
|
|
"num_tokens": 8048673.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.651902198791504,
|
|
"epoch": 0.36585365853658536,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004991011411454769,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.17421940341591835,
|
|
"num_tokens": 8057934.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.448347330093384,
|
|
"epoch": 0.36627129969929834,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990984808237495,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18487884253263473,
|
|
"num_tokens": 8066923.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.462883567810058,
|
|
"epoch": 0.36668894086201137,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990958165789086,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.1760290041565895,
|
|
"num_tokens": 8076263.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.514085721969605,
|
|
"epoch": 0.36710658202472435,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004990931484110005,
|
|
"loss": 5.4095,
|
|
"mean_token_accuracy": 0.1810617759823799,
|
|
"num_tokens": 8085741.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.486966371536255,
|
|
"epoch": 0.3675242231874373,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990904763200722,
|
|
"loss": 5.3771,
|
|
"mean_token_accuracy": 0.178292016685009,
|
|
"num_tokens": 8094646.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.475282049179077,
|
|
"epoch": 0.36794186435015036,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004990878003061705,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.177623650431633,
|
|
"num_tokens": 8103215.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.467202425003052,
|
|
"epoch": 0.36835950551286334,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990851203693419,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.18833307027816773,
|
|
"num_tokens": 8112381.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.486483478546143,
|
|
"epoch": 0.3687771466755763,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990824365096336,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.1806489571928978,
|
|
"num_tokens": 8121139.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.561320209503174,
|
|
"epoch": 0.36919478783828935,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990797487270926,
|
|
"loss": 5.4055,
|
|
"mean_token_accuracy": 0.18097275197505952,
|
|
"num_tokens": 8130011.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.4849504947662355,
|
|
"epoch": 0.36961242900100233,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004990770570217659,
|
|
"loss": 5.3462,
|
|
"mean_token_accuracy": 0.18215416222810746,
|
|
"num_tokens": 8138757.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.463592290878296,
|
|
"epoch": 0.37003007016371536,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990743613937005,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.18118430972099303,
|
|
"num_tokens": 8147862.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.491280555725098,
|
|
"epoch": 0.37044771132642834,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004990716618429436,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.1887040838599205,
|
|
"num_tokens": 8156754.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.466277074813843,
|
|
"epoch": 0.3708653524891413,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004990689583695428,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.18729740530252456,
|
|
"num_tokens": 8165647.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.428556489944458,
|
|
"epoch": 0.37128299365185435,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499066250973545,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.18351357579231262,
|
|
"num_tokens": 8174811.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.435256910324097,
|
|
"epoch": 0.37170063481456733,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990635396549978,
|
|
"loss": 5.2514,
|
|
"mean_token_accuracy": 0.19050270766019822,
|
|
"num_tokens": 8184270.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.578146076202392,
|
|
"epoch": 0.3721182759772803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004990608244139486,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17651860117912294,
|
|
"num_tokens": 8193209.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.605398416519165,
|
|
"epoch": 0.37253591713999334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499058105250445,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17623425722122193,
|
|
"num_tokens": 8202502.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.56442608833313,
|
|
"epoch": 0.3729535583027063,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004990553821645346,
|
|
"loss": 5.427,
|
|
"mean_token_accuracy": 0.17833691239356994,
|
|
"num_tokens": 8212226.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.532606315612793,
|
|
"epoch": 0.3733711994654193,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499052655156265,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.17988564670085908,
|
|
"num_tokens": 8220729.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.487145471572876,
|
|
"epoch": 0.37378884062813234,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004990499242256839,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18228236883878707,
|
|
"num_tokens": 8230385.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.559069967269897,
|
|
"epoch": 0.3742064817908453,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004990471893728394,
|
|
"loss": 5.3262,
|
|
"mean_token_accuracy": 0.18018670082092286,
|
|
"num_tokens": 8240057.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.324749755859375,
|
|
"epoch": 0.3746241229535583,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000499044450597779,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.1948035776615143,
|
|
"num_tokens": 8249903.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.474420166015625,
|
|
"epoch": 0.3750417641162713,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990417079005508,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.18153468817472457,
|
|
"num_tokens": 8259334.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.384976768493653,
|
|
"epoch": 0.3754594052789843,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499038961281203,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.19038648456335067,
|
|
"num_tokens": 8268543.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.525278043746948,
|
|
"epoch": 0.3758770464416973,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990362107397834,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.18458831012248994,
|
|
"num_tokens": 8278257.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.512914323806763,
|
|
"epoch": 0.3762946876044103,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990334562763401,
|
|
"loss": 5.2567,
|
|
"mean_token_accuracy": 0.19528784602880478,
|
|
"num_tokens": 8287506.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.434405660629272,
|
|
"epoch": 0.3767123287671233,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990306978909216,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.19175124168395996,
|
|
"num_tokens": 8295803.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.4258969783782955,
|
|
"epoch": 0.3771299699298363,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990279355835761,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.1786240041255951,
|
|
"num_tokens": 8305344.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.55896520614624,
|
|
"epoch": 0.3775476110925493,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004990251693543519,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.17490887641906738,
|
|
"num_tokens": 8315226.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.575095748901367,
|
|
"epoch": 0.3779652522552623,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004990223992032975,
|
|
"loss": 5.3775,
|
|
"mean_token_accuracy": 0.17822618186473846,
|
|
"num_tokens": 8324614.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.371170139312744,
|
|
"epoch": 0.37838289341797526,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004990196251304612,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.18501548767089843,
|
|
"num_tokens": 8334014.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.452558135986328,
|
|
"epoch": 0.3788005345806883,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499016847135892,
|
|
"loss": 5.2613,
|
|
"mean_token_accuracy": 0.1895100936293602,
|
|
"num_tokens": 8343038.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.53317608833313,
|
|
"epoch": 0.3792181757434013,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499014065219638,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.17636892199516296,
|
|
"num_tokens": 8353170.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.456049823760987,
|
|
"epoch": 0.37963581690611425,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990112793817481,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.19051716327667237,
|
|
"num_tokens": 8362240.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.4160411834716795,
|
|
"epoch": 0.3800534580688273,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004990084896222713,
|
|
"loss": 5.2783,
|
|
"mean_token_accuracy": 0.18670295178890228,
|
|
"num_tokens": 8370723.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.404092025756836,
|
|
"epoch": 0.38047109923154027,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004990056959412562,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.1899563893675804,
|
|
"num_tokens": 8379282.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.432742595672607,
|
|
"epoch": 0.38088874039425324,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004990028983387517,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.19815326035022734,
|
|
"num_tokens": 8387918.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.567809247970581,
|
|
"epoch": 0.3813063815569663,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990000968148068,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.17480838000774385,
|
|
"num_tokens": 8397755.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.5175190448760985,
|
|
"epoch": 0.38172402271967926,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004989972913694707,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.17644692361354827,
|
|
"num_tokens": 8408229.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.441759347915649,
|
|
"epoch": 0.38214166388239224,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989944820027923,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.17874940633773803,
|
|
"num_tokens": 8417039.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.417681932449341,
|
|
"epoch": 0.38255930504510527,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989916687148209,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.18702251017093657,
|
|
"num_tokens": 8426656.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.533075571060181,
|
|
"epoch": 0.38297694620781825,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989888515056057,
|
|
"loss": 5.267,
|
|
"mean_token_accuracy": 0.18273862898349763,
|
|
"num_tokens": 8435254.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.374875497817993,
|
|
"epoch": 0.3833945873705312,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498986030375196,
|
|
"loss": 5.1947,
|
|
"mean_token_accuracy": 0.18701607435941697,
|
|
"num_tokens": 8444594.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.345734453201294,
|
|
"epoch": 0.38381222853324426,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989832053236413,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.1889701634645462,
|
|
"num_tokens": 8453737.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.496078252792358,
|
|
"epoch": 0.38422986969595724,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498980376350991,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18156538754701615,
|
|
"num_tokens": 8463033.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.508194017410278,
|
|
"epoch": 0.3846475108586702,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989775434572945,
|
|
"loss": 5.3063,
|
|
"mean_token_accuracy": 0.17999700754880904,
|
|
"num_tokens": 8472875.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.5385175228118895,
|
|
"epoch": 0.38506515202138325,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004989747066426015,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.17085468024015427,
|
|
"num_tokens": 8482281.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.502962446212768,
|
|
"epoch": 0.38548279318409623,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004989718659069618,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.18520839661359786,
|
|
"num_tokens": 8490871.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.437960529327393,
|
|
"epoch": 0.3859004343468092,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000498969021250425,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.1898990362882614,
|
|
"num_tokens": 8499765.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.38298659324646,
|
|
"epoch": 0.38631807550952224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989661726730407,
|
|
"loss": 5.2825,
|
|
"mean_token_accuracy": 0.18729780614376068,
|
|
"num_tokens": 8508163.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.498678398132324,
|
|
"epoch": 0.3867357166722352,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989633201748591,
|
|
"loss": 5.3476,
|
|
"mean_token_accuracy": 0.1796739086508751,
|
|
"num_tokens": 8517791.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.476361989974976,
|
|
"epoch": 0.3871533578349482,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004989604637559299,
|
|
"loss": 5.2706,
|
|
"mean_token_accuracy": 0.1868073597550392,
|
|
"num_tokens": 8526051.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.493523216247558,
|
|
"epoch": 0.38757099899766123,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989576034163033,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.17812628000974656,
|
|
"num_tokens": 8536102.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.487749004364014,
|
|
"epoch": 0.3879886401603742,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004989547391560293,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.17128999531269073,
|
|
"num_tokens": 8544566.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.517955350875854,
|
|
"epoch": 0.3884062813230872,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000498951870975158,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17243936210870742,
|
|
"num_tokens": 8555397.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.521270132064819,
|
|
"epoch": 0.3888239224858002,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989489988737395,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.186031574010849,
|
|
"num_tokens": 8564184.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.612167549133301,
|
|
"epoch": 0.3892415636485132,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989461228518243,
|
|
"loss": 5.3263,
|
|
"mean_token_accuracy": 0.18221308887004853,
|
|
"num_tokens": 8572967.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.474199867248535,
|
|
"epoch": 0.3896592048112262,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004989432429094627,
|
|
"loss": 5.3105,
|
|
"mean_token_accuracy": 0.18588981926441192,
|
|
"num_tokens": 8581946.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.408122158050537,
|
|
"epoch": 0.3900768459739392,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004989403590467049,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.19287759214639663,
|
|
"num_tokens": 8590528.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.42282018661499,
|
|
"epoch": 0.3904944871366522,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004989374712636017,
|
|
"loss": 5.2163,
|
|
"mean_token_accuracy": 0.188861246407032,
|
|
"num_tokens": 8600399.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.484813785552978,
|
|
"epoch": 0.39091212829936517,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989345795602036,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.18671162724494933,
|
|
"num_tokens": 8609620.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.41406741142273,
|
|
"epoch": 0.3913297694620782,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989316839365609,
|
|
"loss": 5.3121,
|
|
"mean_token_accuracy": 0.18761529624462128,
|
|
"num_tokens": 8618077.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.373091411590576,
|
|
"epoch": 0.3917474106247912,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989287843927246,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18883857280015945,
|
|
"num_tokens": 8626672.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.42592487335205,
|
|
"epoch": 0.39216505178750416,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004989258809287455,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.1877009853720665,
|
|
"num_tokens": 8635997.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.49935212135315,
|
|
"epoch": 0.3925826929502172,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989229735446743,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.17100426703691482,
|
|
"num_tokens": 8645296.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.515685272216797,
|
|
"epoch": 0.39300033411293017,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004989200622405619,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.17950820028781891,
|
|
"num_tokens": 8654772.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.4163219928741455,
|
|
"epoch": 0.39341797527564315,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004989171470164592,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.1816800579428673,
|
|
"num_tokens": 8664279.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.476864528656006,
|
|
"epoch": 0.3938356164383562,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004989142278724173,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.17603901475667955,
|
|
"num_tokens": 8673405.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.490294027328491,
|
|
"epoch": 0.39425325760106916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004989113048084874,
|
|
"loss": 5.3073,
|
|
"mean_token_accuracy": 0.1824507713317871,
|
|
"num_tokens": 8682254.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.45321569442749,
|
|
"epoch": 0.39467089876378214,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004989083778247206,
|
|
"loss": 5.2041,
|
|
"mean_token_accuracy": 0.1958479955792427,
|
|
"num_tokens": 8690751.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.516774129867554,
|
|
"epoch": 0.3950885399264952,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000498905446921168,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.1741472974419594,
|
|
"num_tokens": 8700485.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.4783166408538815,
|
|
"epoch": 0.39550618108920815,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004989025120978812,
|
|
"loss": 5.3031,
|
|
"mean_token_accuracy": 0.17581946849823,
|
|
"num_tokens": 8709650.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.425529527664184,
|
|
"epoch": 0.39592382225192113,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988995733549113,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.18366322964429854,
|
|
"num_tokens": 8719090.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.426125860214233,
|
|
"epoch": 0.39634146341463417,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004988966306923099,
|
|
"loss": 5.4147,
|
|
"mean_token_accuracy": 0.18398146331310272,
|
|
"num_tokens": 8728563.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.576057195663452,
|
|
"epoch": 0.39675910457734714,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988936841101284,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.1861005201935768,
|
|
"num_tokens": 8737587.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.541537809371948,
|
|
"epoch": 0.3971767457400601,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988907336084186,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.18668136298656463,
|
|
"num_tokens": 8747377.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.566713142395019,
|
|
"epoch": 0.39759438690277316,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988877791872319,
|
|
"loss": 5.3374,
|
|
"mean_token_accuracy": 0.18346888571977615,
|
|
"num_tokens": 8756471.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.406263446807861,
|
|
"epoch": 0.39801202806548613,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988848208466202,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.18126556873321534,
|
|
"num_tokens": 8765445.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.578355693817139,
|
|
"epoch": 0.3984296692281991,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004988818585866351,
|
|
"loss": 5.3813,
|
|
"mean_token_accuracy": 0.18272889852523805,
|
|
"num_tokens": 8774946.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.536053323745728,
|
|
"epoch": 0.39884731039091215,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988788924073288,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.17975222170352936,
|
|
"num_tokens": 8783652.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.3968977451324465,
|
|
"epoch": 0.3992649515536251,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988759223087528,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19014027565717698,
|
|
"num_tokens": 8792633.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.366938066482544,
|
|
"epoch": 0.3996825927163381,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988729482909595,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.18786804527044296,
|
|
"num_tokens": 8802376.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.423903322219848,
|
|
"epoch": 0.40010023387905114,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004988699703540006,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.1882595971226692,
|
|
"num_tokens": 8812122.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.41010046005249,
|
|
"epoch": 0.4005178750417641,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988669884979284,
|
|
"loss": 5.2057,
|
|
"mean_token_accuracy": 0.1879386231303215,
|
|
"num_tokens": 8821111.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.447687149047852,
|
|
"epoch": 0.4009355162044771,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988640027227951,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.18124178498983384,
|
|
"num_tokens": 8830354.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.403280639648438,
|
|
"epoch": 0.4013531573671901,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000498861013028653,
|
|
"loss": 5.2161,
|
|
"mean_token_accuracy": 0.1910982608795166,
|
|
"num_tokens": 8839500.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.484344387054444,
|
|
"epoch": 0.4017707985299031,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004988580194155544,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.1856370285153389,
|
|
"num_tokens": 8849632.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.5780744552612305,
|
|
"epoch": 0.4021884396926161,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988550218835517,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.17849408388137816,
|
|
"num_tokens": 8858383.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.385653781890869,
|
|
"epoch": 0.4026060808553291,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004988520204326975,
|
|
"loss": 5.1983,
|
|
"mean_token_accuracy": 0.19090892970561982,
|
|
"num_tokens": 8866755.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.454571104049682,
|
|
"epoch": 0.4030237220180421,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004988490150630441,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.17596109658479692,
|
|
"num_tokens": 8876896.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.548031997680664,
|
|
"epoch": 0.4034413631807551,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004988460057746443,
|
|
"loss": 5.334,
|
|
"mean_token_accuracy": 0.18507929295301437,
|
|
"num_tokens": 8886029.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.5046196460723875,
|
|
"epoch": 0.4038590043434681,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988429925675507,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.18310321122407913,
|
|
"num_tokens": 8895396.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.496002531051635,
|
|
"epoch": 0.4042766455061811,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004988399754418161,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.19374214261770248,
|
|
"num_tokens": 8904125.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.4126872539520265,
|
|
"epoch": 0.40469428666889407,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988369543974932,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.1803189903497696,
|
|
"num_tokens": 8913011.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.402322721481323,
|
|
"epoch": 0.4051119278316071,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004988339294346351,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.18455570340156555,
|
|
"num_tokens": 8921596.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.496550750732422,
|
|
"epoch": 0.4055295689943201,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988309005532946,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.18543683290481566,
|
|
"num_tokens": 8931267.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.358983516693115,
|
|
"epoch": 0.40594721015703306,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004988278677535247,
|
|
"loss": 5.1291,
|
|
"mean_token_accuracy": 0.19053051471710206,
|
|
"num_tokens": 8940082.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.505894899368286,
|
|
"epoch": 0.4063648513197461,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004988248310353788,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.1844634771347046,
|
|
"num_tokens": 8949838.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.494176912307739,
|
|
"epoch": 0.40678249248245907,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988217903989095,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.1894363820552826,
|
|
"num_tokens": 8958510.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.51385908126831,
|
|
"epoch": 0.40720013364517205,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004988187458441704,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18134814202785493,
|
|
"num_tokens": 8968372.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.3543768405914305,
|
|
"epoch": 0.4076177748078851,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004988156973712149,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.19353510141372682,
|
|
"num_tokens": 8977121.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.433396863937378,
|
|
"epoch": 0.40803541597059806,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004988126449800961,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.18651665449142457,
|
|
"num_tokens": 8986643.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.452758121490478,
|
|
"epoch": 0.40845305713331104,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988095886708676,
|
|
"loss": 5.1491,
|
|
"mean_token_accuracy": 0.19153372049331666,
|
|
"num_tokens": 8994925.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.3938392162322994,
|
|
"epoch": 0.40887069829602407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004988065284435828,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.18742894232273102,
|
|
"num_tokens": 9003844.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.459982872009277,
|
|
"epoch": 0.40928833945873705,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004988034642982954,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.1847367376089096,
|
|
"num_tokens": 9013351.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.510900974273682,
|
|
"epoch": 0.40970598062145,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004988003962350589,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.1836380034685135,
|
|
"num_tokens": 9023488.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.4314319610595705,
|
|
"epoch": 0.41012362178416306,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498797324253927,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.1866202875971794,
|
|
"num_tokens": 9033018.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.427098226547241,
|
|
"epoch": 0.41054126294687604,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987942483549537,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18624649941921234,
|
|
"num_tokens": 9041572.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.573683738708496,
|
|
"epoch": 0.410958904109589,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987911685381926,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.17627662271261216,
|
|
"num_tokens": 9051505.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.479363441467285,
|
|
"epoch": 0.41137654527230205,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987880848036977,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.18796220421791077,
|
|
"num_tokens": 9061168.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.3330975532531735,
|
|
"epoch": 0.41179418643501503,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004987849971515232,
|
|
"loss": 5.1533,
|
|
"mean_token_accuracy": 0.18812801390886308,
|
|
"num_tokens": 9069776.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.484102582931518,
|
|
"epoch": 0.412211827597728,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987819055817227,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.18646983206272125,
|
|
"num_tokens": 9078995.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.394393873214722,
|
|
"epoch": 0.41262946876044104,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987788100943507,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.19072956889867781,
|
|
"num_tokens": 9088291.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.4095031261444095,
|
|
"epoch": 0.413047109923154,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004987757106894613,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.18989295959472657,
|
|
"num_tokens": 9097013.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.435576009750366,
|
|
"epoch": 0.413464751085867,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004987726073671086,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.17917950749397277,
|
|
"num_tokens": 9106909.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.417089748382568,
|
|
"epoch": 0.41388239224858003,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004987695001273471,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.1776151493191719,
|
|
"num_tokens": 9116056.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.45604944229126,
|
|
"epoch": 0.414300033411293,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987663889702313,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.18915201723575592,
|
|
"num_tokens": 9124968.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.457709074020386,
|
|
"epoch": 0.414717674574006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004987632738958155,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.19009630084037782,
|
|
"num_tokens": 9134423.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.541339588165283,
|
|
"epoch": 0.415135315736719,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004987601549041541,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.1850879430770874,
|
|
"num_tokens": 9144179.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.420493459701538,
|
|
"epoch": 0.415552956899432,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004987570319953018,
|
|
"loss": 5.3669,
|
|
"mean_token_accuracy": 0.18252476155757905,
|
|
"num_tokens": 9154045.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.308528327941895,
|
|
"epoch": 0.415970598062145,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987539051693134,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.19155644923448562,
|
|
"num_tokens": 9162922.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.401633548736572,
|
|
"epoch": 0.416388239224858,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987507744262436,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.18865952342748643,
|
|
"num_tokens": 9172327.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.382492542266846,
|
|
"epoch": 0.416805880387571,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987476397661472,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.19583573937416077,
|
|
"num_tokens": 9180830.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.490254497528076,
|
|
"epoch": 0.41722352155028397,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004987445011890789,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.18453311920166016,
|
|
"num_tokens": 9190787.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.508502006530762,
|
|
"epoch": 0.417641162712997,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498741358695094,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.18619910329580308,
|
|
"num_tokens": 9199554.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.374854564666748,
|
|
"epoch": 0.41805880387571,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498738212284247,
|
|
"loss": 5.2194,
|
|
"mean_token_accuracy": 0.18740950971841813,
|
|
"num_tokens": 9209309.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.488752555847168,
|
|
"epoch": 0.41847644503842296,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004987350619565934,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.1809329703450203,
|
|
"num_tokens": 9218529.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.462771558761597,
|
|
"epoch": 0.418894086201136,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004987319077121884,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19021305441856384,
|
|
"num_tokens": 9226924.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.348441743850708,
|
|
"epoch": 0.419311727363849,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004987287495510869,
|
|
"loss": 5.2795,
|
|
"mean_token_accuracy": 0.17676490694284439,
|
|
"num_tokens": 9237602.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.500708532333374,
|
|
"epoch": 0.41972936852656195,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987255874733444,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.18865429162979125,
|
|
"num_tokens": 9246209.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.421678066253662,
|
|
"epoch": 0.420147009689275,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004987224214790161,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.18645316511392593,
|
|
"num_tokens": 9255464.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.35802845954895,
|
|
"epoch": 0.42056465085198796,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987192515681575,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.1853409081697464,
|
|
"num_tokens": 9265520.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.481031227111816,
|
|
"epoch": 0.42098229201470094,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004987160777408243,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.1859673097729683,
|
|
"num_tokens": 9274916.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.484265422821045,
|
|
"epoch": 0.421399933177414,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004987128999970717,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.17960992455482483,
|
|
"num_tokens": 9284684.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.4706159114837645,
|
|
"epoch": 0.42181757434012696,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004987097183369555,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.1874099686741829,
|
|
"num_tokens": 9294020.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.45339674949646,
|
|
"epoch": 0.42223521550283993,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004987065327605315,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.18615740090608596,
|
|
"num_tokens": 9303730.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.468004512786865,
|
|
"epoch": 0.42265285666555297,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004987033432678553,
|
|
"loss": 5.2454,
|
|
"mean_token_accuracy": 0.18701883554458618,
|
|
"num_tokens": 9312851.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.352798128128052,
|
|
"epoch": 0.42307049782826595,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004987001498589828,
|
|
"loss": 5.1149,
|
|
"mean_token_accuracy": 0.1964243084192276,
|
|
"num_tokens": 9321143.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.454397535324096,
|
|
"epoch": 0.4234881389909789,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049869695253397,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.1905997335910797,
|
|
"num_tokens": 9329843.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.540484428405762,
|
|
"epoch": 0.42390578015369196,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004986937512928727,
|
|
"loss": 5.3858,
|
|
"mean_token_accuracy": 0.17478944063186647,
|
|
"num_tokens": 9339549.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.48171215057373,
|
|
"epoch": 0.42432342131640494,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000498690546135747,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.18295445591211318,
|
|
"num_tokens": 9348220.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.44566707611084,
|
|
"epoch": 0.4247410624791179,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986873370626491,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.1865879163146019,
|
|
"num_tokens": 9357440.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.469370603561401,
|
|
"epoch": 0.42515870364183095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498684124073635,
|
|
"loss": 5.2668,
|
|
"mean_token_accuracy": 0.18817803263664246,
|
|
"num_tokens": 9366457.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.437319898605347,
|
|
"epoch": 0.4255763448045439,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004986809071687612,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.18234614580869674,
|
|
"num_tokens": 9375432.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.428205251693726,
|
|
"epoch": 0.4259939859672569,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986776863480838,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.18737971186637878,
|
|
"num_tokens": 9383353.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.512642192840576,
|
|
"epoch": 0.42641162712996994,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004986744616116593,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.1873912274837494,
|
|
"num_tokens": 9393012.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.437117862701416,
|
|
"epoch": 0.4268292682926829,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498671232959544,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.191709765791893,
|
|
"num_tokens": 9401394.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.370872163772583,
|
|
"epoch": 0.42724690945539595,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004986680003917947,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.18689843267202377,
|
|
"num_tokens": 9410310.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.393358850479126,
|
|
"epoch": 0.42766455061810893,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004986647639084677,
|
|
"loss": 5.1861,
|
|
"mean_token_accuracy": 0.19294835776090621,
|
|
"num_tokens": 9418625.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.455751991271972,
|
|
"epoch": 0.4280821917808219,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049866152350962,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.18329329937696456,
|
|
"num_tokens": 9428722.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.482298088073731,
|
|
"epoch": 0.42849983294353494,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986582791953078,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.18959519267082214,
|
|
"num_tokens": 9438447.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.418071269989014,
|
|
"epoch": 0.4289174741062479,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986550309655884,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.18700263798236846,
|
|
"num_tokens": 9447457.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.475923204421997,
|
|
"epoch": 0.4293351152689609,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986517788205184,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.1782189592719078,
|
|
"num_tokens": 9456837.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.547563076019287,
|
|
"epoch": 0.42975275643167393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986485227601548,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.17853771895170212,
|
|
"num_tokens": 9465733.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.43075156211853,
|
|
"epoch": 0.4301703975943869,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986452627845547,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.1913004770874977,
|
|
"num_tokens": 9473978.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.379370880126953,
|
|
"epoch": 0.4305880387570999,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000498641998893775,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18594589680433274,
|
|
"num_tokens": 9482914.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.438448047637939,
|
|
"epoch": 0.4310056799198129,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004986387310878728,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.19495287388563157,
|
|
"num_tokens": 9492060.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.466447591781616,
|
|
"epoch": 0.4314233210825259,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004986354593669056,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.1829022854566574,
|
|
"num_tokens": 9501186.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.484063053131104,
|
|
"epoch": 0.4318409622452389,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004986321837309304,
|
|
"loss": 5.2933,
|
|
"mean_token_accuracy": 0.18105715066194533,
|
|
"num_tokens": 9509727.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.478100299835205,
|
|
"epoch": 0.4322586034079519,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004986289041800046,
|
|
"loss": 5.237,
|
|
"mean_token_accuracy": 0.18081933557987212,
|
|
"num_tokens": 9519203.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.443422412872314,
|
|
"epoch": 0.4326762445706649,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004986256207141857,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.18555376678705215,
|
|
"num_tokens": 9529277.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.4498817920684814,
|
|
"epoch": 0.43309388573337787,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004986223333335311,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.1830058738589287,
|
|
"num_tokens": 9538215.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.301967334747315,
|
|
"epoch": 0.4335115268960909,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004986190420380985,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.1891431137919426,
|
|
"num_tokens": 9547570.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.2756694793701175,
|
|
"epoch": 0.4339291680588039,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004986157468279453,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19198305606842042,
|
|
"num_tokens": 9556383.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.383520793914795,
|
|
"epoch": 0.43434680922151686,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004986124477031293,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.18692761212587355,
|
|
"num_tokens": 9566793.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.489547538757324,
|
|
"epoch": 0.4347644503842299,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004986091446637083,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.18457262217998505,
|
|
"num_tokens": 9576079.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.438872385025024,
|
|
"epoch": 0.4351820915469429,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00049860583770974,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.18729605972766877,
|
|
"num_tokens": 9586318.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.373680973052979,
|
|
"epoch": 0.43559973270965585,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004986025268412823,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.1897333726286888,
|
|
"num_tokens": 9594453.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.303825521469117,
|
|
"epoch": 0.4360173738723689,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985992120583933,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.19857619404792787,
|
|
"num_tokens": 9603677.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.422148132324219,
|
|
"epoch": 0.43643501503508186,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498595893361131,
|
|
"loss": 5.2916,
|
|
"mean_token_accuracy": 0.18710941970348358,
|
|
"num_tokens": 9612353.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.506691551208496,
|
|
"epoch": 0.43685265619779484,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004985925707495533,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.18843815475702286,
|
|
"num_tokens": 9621607.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.44722580909729,
|
|
"epoch": 0.4372702973605079,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004985892442237186,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.1900441288948059,
|
|
"num_tokens": 9630155.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.399506902694702,
|
|
"epoch": 0.43768793852322085,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004985859137836851,
|
|
"loss": 5.218,
|
|
"mean_token_accuracy": 0.18862127661705017,
|
|
"num_tokens": 9639418.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.438596439361572,
|
|
"epoch": 0.43810557968593383,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985825794295109,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.18817966133356095,
|
|
"num_tokens": 9648030.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.414564228057861,
|
|
"epoch": 0.43852322084864687,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985792411612546,
|
|
"loss": 5.221,
|
|
"mean_token_accuracy": 0.18779697865247727,
|
|
"num_tokens": 9657746.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.388850307464599,
|
|
"epoch": 0.43894086201135984,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985758989789746,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.19324512630701066,
|
|
"num_tokens": 9667840.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.486927175521851,
|
|
"epoch": 0.4393585031740728,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004985725528827293,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18287472426891327,
|
|
"num_tokens": 9677595.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.330494594573975,
|
|
"epoch": 0.43977614433678586,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985692028725774,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.19438521265983583,
|
|
"num_tokens": 9685515.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.343545579910279,
|
|
"epoch": 0.44019378549949884,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004985658489485774,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.1855165183544159,
|
|
"num_tokens": 9694238.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.490376043319702,
|
|
"epoch": 0.4406114266622118,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985624911107882,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.18229396641254425,
|
|
"num_tokens": 9703388.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.453785371780396,
|
|
"epoch": 0.44102906782492485,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004985591293592685,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.18630390614271164,
|
|
"num_tokens": 9713085.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.477219820022583,
|
|
"epoch": 0.4414467089876378,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004985557636940771,
|
|
"loss": 5.2545,
|
|
"mean_token_accuracy": 0.18936343640089034,
|
|
"num_tokens": 9721733.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.489253044128418,
|
|
"epoch": 0.4418643501503508,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498552394115273,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.18463747203350067,
|
|
"num_tokens": 9731478.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.4287919998168945,
|
|
"epoch": 0.44228199131306384,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985490206229151,
|
|
"loss": 5.268,
|
|
"mean_token_accuracy": 0.18442467004060745,
|
|
"num_tokens": 9742058.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.340026950836181,
|
|
"epoch": 0.4426996324757768,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004985456432170626,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.18886782228946686,
|
|
"num_tokens": 9751034.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.395762872695923,
|
|
"epoch": 0.4431172736384898,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004985422618977744,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.18440112471580505,
|
|
"num_tokens": 9760692.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.432795906066895,
|
|
"epoch": 0.44353491480120283,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049853887666511,
|
|
"loss": 5.1569,
|
|
"mean_token_accuracy": 0.18824788480997084,
|
|
"num_tokens": 9769759.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.376852655410767,
|
|
"epoch": 0.4439525559639158,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985354875191283,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.19364855140447618,
|
|
"num_tokens": 9778597.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.2799968242645265,
|
|
"epoch": 0.4443701971266288,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004985320944598889,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.2005080282688141,
|
|
"num_tokens": 9787259.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.418052053451538,
|
|
"epoch": 0.4447878382893418,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985286974874512,
|
|
"loss": 5.3293,
|
|
"mean_token_accuracy": 0.18076300323009492,
|
|
"num_tokens": 9796297.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.460309982299805,
|
|
"epoch": 0.4452054794520548,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985252966018745,
|
|
"loss": 5.1262,
|
|
"mean_token_accuracy": 0.20076993554830552,
|
|
"num_tokens": 9805217.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.400050354003906,
|
|
"epoch": 0.4456231206147678,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004985218918032184,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.18437316864728928,
|
|
"num_tokens": 9814788.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.306721639633179,
|
|
"epoch": 0.4460407617774808,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004985184830915426,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.18621596246957778,
|
|
"num_tokens": 9823238.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.397016334533691,
|
|
"epoch": 0.4464584029401938,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004985150704669067,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.1887279123067856,
|
|
"num_tokens": 9832619.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.4020778179168705,
|
|
"epoch": 0.44687604410290677,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004985116539293704,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.19023136645555497,
|
|
"num_tokens": 9841505.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.439421319961548,
|
|
"epoch": 0.4472936852656198,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004985082334789936,
|
|
"loss": 5.2556,
|
|
"mean_token_accuracy": 0.18449438065290452,
|
|
"num_tokens": 9851062.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.3722827434539795,
|
|
"epoch": 0.4477113264283328,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004985048091158361,
|
|
"loss": 5.1143,
|
|
"mean_token_accuracy": 0.18671787679195403,
|
|
"num_tokens": 9860080.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.377421188354492,
|
|
"epoch": 0.44812896759104576,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004985013808399578,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.1794202744960785,
|
|
"num_tokens": 9870968.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.3914794921875,
|
|
"epoch": 0.4485466087537588,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004984979486514189,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.20115971118211745,
|
|
"num_tokens": 9879243.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.391350984573364,
|
|
"epoch": 0.44896424991647177,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004984945125502795,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.19181129783391954,
|
|
"num_tokens": 9889203.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.410650396347046,
|
|
"epoch": 0.44938189107918475,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004984910725365994,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.19484663009643555,
|
|
"num_tokens": 9898989.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.385343742370606,
|
|
"epoch": 0.4497995322418978,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004984876286104392,
|
|
"loss": 5.1857,
|
|
"mean_token_accuracy": 0.19111303240060806,
|
|
"num_tokens": 9908030.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.515639925003052,
|
|
"epoch": 0.45021717340461076,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984841807718591,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.18028317391872406,
|
|
"num_tokens": 9917331.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.442778778076172,
|
|
"epoch": 0.45063481456732374,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984807290209193,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.19573354125022888,
|
|
"num_tokens": 9925418.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.4272825717926025,
|
|
"epoch": 0.45105245573003677,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984772733576803,
|
|
"loss": 5.2878,
|
|
"mean_token_accuracy": 0.17937994450330735,
|
|
"num_tokens": 9934525.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.421660232543945,
|
|
"epoch": 0.45147009689274975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984738137822028,
|
|
"loss": 5.3251,
|
|
"mean_token_accuracy": 0.18079611659049988,
|
|
"num_tokens": 9944087.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.493865871429444,
|
|
"epoch": 0.45188773805546273,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498470350294547,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.19009149372577666,
|
|
"num_tokens": 9953005.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.445831775665283,
|
|
"epoch": 0.45230537921817576,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984668828947739,
|
|
"loss": 5.1957,
|
|
"mean_token_accuracy": 0.18674670457839965,
|
|
"num_tokens": 9961963.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.354967498779297,
|
|
"epoch": 0.45272302038088874,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984634115829439,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.1852552056312561,
|
|
"num_tokens": 9970654.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.432764148712158,
|
|
"epoch": 0.4531406615436017,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498459936359118,
|
|
"loss": 5.2775,
|
|
"mean_token_accuracy": 0.18723644316196442,
|
|
"num_tokens": 9979625.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.433414268493652,
|
|
"epoch": 0.45355830270631475,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004984564572233568,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.19804619997739792,
|
|
"num_tokens": 9988584.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.314892339706421,
|
|
"epoch": 0.45397594386902773,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004984529741757216,
|
|
"loss": 5.1175,
|
|
"mean_token_accuracy": 0.19850447922945022,
|
|
"num_tokens": 9997315.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.330080842971801,
|
|
"epoch": 0.4543935850317407,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004984494872162728,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.18722862750291824,
|
|
"num_tokens": 10006431.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.435089254379273,
|
|
"epoch": 0.45481122619445374,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498445996345072,
|
|
"loss": 5.2344,
|
|
"mean_token_accuracy": 0.19351187199354172,
|
|
"num_tokens": 10015960.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.407324361801147,
|
|
"epoch": 0.4552288673571667,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004984425015621799,
|
|
"loss": 5.1885,
|
|
"mean_token_accuracy": 0.19092332422733307,
|
|
"num_tokens": 10025948.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.432583522796631,
|
|
"epoch": 0.4556465085198797,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000498439002867658,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.1858166828751564,
|
|
"num_tokens": 10034358.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.421167230606079,
|
|
"epoch": 0.45606414968259273,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004984355002615673,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.18035876601934434,
|
|
"num_tokens": 10044887.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.349170207977295,
|
|
"epoch": 0.4564817908453057,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004984319937439693,
|
|
"loss": 5.1712,
|
|
"mean_token_accuracy": 0.1863957315683365,
|
|
"num_tokens": 10054026.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.409258699417114,
|
|
"epoch": 0.4568994320080187,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004984284833149252,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1844397231936455,
|
|
"num_tokens": 10063089.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.588518762588501,
|
|
"epoch": 0.4573170731707317,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004984249689744966,
|
|
"loss": 5.3104,
|
|
"mean_token_accuracy": 0.1768183022737503,
|
|
"num_tokens": 10073816.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.40412712097168,
|
|
"epoch": 0.4577347143334447,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000498421450722745,
|
|
"loss": 5.2455,
|
|
"mean_token_accuracy": 0.189549458026886,
|
|
"num_tokens": 10082407.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.391772985458374,
|
|
"epoch": 0.4581523554961577,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000498417928559732,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.18563029915094376,
|
|
"num_tokens": 10091423.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.433389282226562,
|
|
"epoch": 0.4585699966588707,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984144024855191,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18567567467689514,
|
|
"num_tokens": 10101381.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.424247074127197,
|
|
"epoch": 0.4589876378215837,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004984108725001683,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.18847638964653016,
|
|
"num_tokens": 10111000.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.465272045135498,
|
|
"epoch": 0.45940527898429667,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004984073386037413,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.18563397377729415,
|
|
"num_tokens": 10120380.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.40173716545105,
|
|
"epoch": 0.4598229201470097,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004984038007962997,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.18884543776512147,
|
|
"num_tokens": 10129236.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.479322004318237,
|
|
"epoch": 0.4602405613097227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984002590779059,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.18686946481466293,
|
|
"num_tokens": 10138851.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.427707624435425,
|
|
"epoch": 0.46065820247243566,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004983967134486215,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.1890336573123932,
|
|
"num_tokens": 10148030.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.394572162628174,
|
|
"epoch": 0.4610758436351487,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983931639085088,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.19900597482919694,
|
|
"num_tokens": 10156362.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.4444725036621096,
|
|
"epoch": 0.4614934847978617,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004983896104576298,
|
|
"loss": 5.255,
|
|
"mean_token_accuracy": 0.1866983264684677,
|
|
"num_tokens": 10165603.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.396441125869751,
|
|
"epoch": 0.46191112596057465,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000498386053096047,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18723201602697373,
|
|
"num_tokens": 10175577.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.396557235717774,
|
|
"epoch": 0.4623287671232877,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983824918238221,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.19485459923744203,
|
|
"num_tokens": 10184736.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.470610809326172,
|
|
"epoch": 0.46274640828600067,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498378926641018,
|
|
"loss": 5.2521,
|
|
"mean_token_accuracy": 0.19185058474540712,
|
|
"num_tokens": 10194154.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.423891258239746,
|
|
"epoch": 0.46316404944871364,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983753575476969,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.18525027632713317,
|
|
"num_tokens": 10203773.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.381209850311279,
|
|
"epoch": 0.4635816906114267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004983717845439212,
|
|
"loss": 5.2654,
|
|
"mean_token_accuracy": 0.18513274788856507,
|
|
"num_tokens": 10212260.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.422849082946778,
|
|
"epoch": 0.46399933177413966,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004983682076297536,
|
|
"loss": 5.3042,
|
|
"mean_token_accuracy": 0.18700378984212876,
|
|
"num_tokens": 10221042.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.414604806900025,
|
|
"epoch": 0.46441697293685263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983646268052567,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.18983226120471955,
|
|
"num_tokens": 10230336.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.450517988204956,
|
|
"epoch": 0.46483461409956567,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004983610420704931,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.18141137361526488,
|
|
"num_tokens": 10241655.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.348510074615478,
|
|
"epoch": 0.46525225526227865,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983574534255256,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.18565696328878403,
|
|
"num_tokens": 10250926.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.3349449634552,
|
|
"epoch": 0.4656698964249916,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498353860870417,
|
|
"loss": 5.2191,
|
|
"mean_token_accuracy": 0.18590866774320602,
|
|
"num_tokens": 10260034.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.482433462142945,
|
|
"epoch": 0.46608753758770466,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983502644052303,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.1779246985912323,
|
|
"num_tokens": 10269170.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.5078449726104735,
|
|
"epoch": 0.46650517875041764,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004983466640300282,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.18893269151449205,
|
|
"num_tokens": 10278385.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.4656421661376955,
|
|
"epoch": 0.4669228199131306,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004983430597448741,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19075634181499482,
|
|
"num_tokens": 10287678.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.403865623474121,
|
|
"epoch": 0.46734046107584365,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004983394515498308,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.18925031572580336,
|
|
"num_tokens": 10296579.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.437282562255859,
|
|
"epoch": 0.46775810223855663,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004983358394449616,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1898487016558647,
|
|
"num_tokens": 10305812.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.448018407821655,
|
|
"epoch": 0.4681757434012696,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004983322234303297,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.18164938688278198,
|
|
"num_tokens": 10314735.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.4351646423339846,
|
|
"epoch": 0.46859338456398264,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004983286035059984,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.18386204689741134,
|
|
"num_tokens": 10323415.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.418152618408203,
|
|
"epoch": 0.4690110257266956,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983249796720311,
|
|
"loss": 5.2145,
|
|
"mean_token_accuracy": 0.1970824718475342,
|
|
"num_tokens": 10331670.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.456290531158447,
|
|
"epoch": 0.4694286668894086,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004983213519284912,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.1823984920978546,
|
|
"num_tokens": 10340609.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.348497343063355,
|
|
"epoch": 0.46984630805212163,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004983177202754421,
|
|
"loss": 5.0314,
|
|
"mean_token_accuracy": 0.2066277638077736,
|
|
"num_tokens": 10349035.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.330918788909912,
|
|
"epoch": 0.4702639492148346,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004983140847129476,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.19656471014022828,
|
|
"num_tokens": 10358005.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.360467433929443,
|
|
"epoch": 0.4706815903775476,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983104452410713,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.18540138155221939,
|
|
"num_tokens": 10366791.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.40042724609375,
|
|
"epoch": 0.4710992315402606,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004983068018598768,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.1813494935631752,
|
|
"num_tokens": 10376485.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.396445274353027,
|
|
"epoch": 0.4715168727029736,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000498303154569428,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.19248452484607698,
|
|
"num_tokens": 10385962.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.391742277145386,
|
|
"epoch": 0.4719345138656866,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004982995033697887,
|
|
"loss": 5.2076,
|
|
"mean_token_accuracy": 0.19472643584012986,
|
|
"num_tokens": 10394314.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.394843530654907,
|
|
"epoch": 0.4723521550283996,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982958482610226,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.1960946276783943,
|
|
"num_tokens": 10403733.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.353224611282348,
|
|
"epoch": 0.4727697961911126,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000498292189243194,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17926349639892578,
|
|
"num_tokens": 10413979.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.4293018817901615,
|
|
"epoch": 0.47318743735382557,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000498288526316367,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.19092903882265091,
|
|
"num_tokens": 10422630.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.391359853744507,
|
|
"epoch": 0.4736050785165386,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982848594806054,
|
|
"loss": 5.1785,
|
|
"mean_token_accuracy": 0.19484773129224778,
|
|
"num_tokens": 10431422.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.439520025253296,
|
|
"epoch": 0.4740227196792516,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982811887359736,
|
|
"loss": 5.2962,
|
|
"mean_token_accuracy": 0.1824900820851326,
|
|
"num_tokens": 10440953.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.3710533618927006,
|
|
"epoch": 0.47444036084196456,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982775140825359,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.1896195650100708,
|
|
"num_tokens": 10449331.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.394535493850708,
|
|
"epoch": 0.4748580020046776,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004982738355203565,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19098381251096724,
|
|
"num_tokens": 10458021.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.43800573348999,
|
|
"epoch": 0.47527564316739057,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004982701530494998,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.19253524988889695,
|
|
"num_tokens": 10466743.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.374477672576904,
|
|
"epoch": 0.47569328433010355,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982664666700304,
|
|
"loss": 5.2137,
|
|
"mean_token_accuracy": 0.18603936731815338,
|
|
"num_tokens": 10475537.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.513244009017944,
|
|
"epoch": 0.4761109254928166,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004982627763820128,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.1832273319363594,
|
|
"num_tokens": 10485257.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.525562906265259,
|
|
"epoch": 0.47652856665552956,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004982590821855115,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1894189313054085,
|
|
"num_tokens": 10494449.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.402962779998779,
|
|
"epoch": 0.47694620781824254,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004982553840805912,
|
|
"loss": 5.2778,
|
|
"mean_token_accuracy": 0.1898958593606949,
|
|
"num_tokens": 10504216.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.4967145919799805,
|
|
"epoch": 0.4773638489809556,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982516820673167,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1894870176911354,
|
|
"num_tokens": 10512676.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.364314126968384,
|
|
"epoch": 0.47778149014366855,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982479761457528,
|
|
"loss": 5.1251,
|
|
"mean_token_accuracy": 0.1935805857181549,
|
|
"num_tokens": 10521587.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.404315710067749,
|
|
"epoch": 0.47819913130638153,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982442663159643,
|
|
"loss": 5.2866,
|
|
"mean_token_accuracy": 0.18175797611474992,
|
|
"num_tokens": 10530043.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.368263149261475,
|
|
"epoch": 0.47861677246909456,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004982405525780162,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.19503370821475982,
|
|
"num_tokens": 10539491.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.354542064666748,
|
|
"epoch": 0.47903441363180754,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004982368349319736,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.18833290040493011,
|
|
"num_tokens": 10547893.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.469902372360229,
|
|
"epoch": 0.4794520547945205,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004982331133779014,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.17868206202983855,
|
|
"num_tokens": 10557597.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.465248727798462,
|
|
"epoch": 0.47986969595723356,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982293879158649,
|
|
"loss": 5.2167,
|
|
"mean_token_accuracy": 0.1897121325135231,
|
|
"num_tokens": 10566349.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.403199195861816,
|
|
"epoch": 0.48028733711994653,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004982256585459293,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.18665742874145508,
|
|
"num_tokens": 10574897.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.447471380233765,
|
|
"epoch": 0.4807049782826595,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004982219252681597,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.18940539360046388,
|
|
"num_tokens": 10583233.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.332688522338867,
|
|
"epoch": 0.48112261944537255,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004982181880826218,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.1920537531375885,
|
|
"num_tokens": 10592202.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.337571334838867,
|
|
"epoch": 0.4815402606080855,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004982144469893807,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.19041890501976014,
|
|
"num_tokens": 10601221.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.455085945129395,
|
|
"epoch": 0.4819579017707985,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000498210701988502,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.18375370800495147,
|
|
"num_tokens": 10610983.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.457437992095947,
|
|
"epoch": 0.48237554293351154,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004982069530800514,
|
|
"loss": 5.3049,
|
|
"mean_token_accuracy": 0.18623082041740419,
|
|
"num_tokens": 10619378.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.470373058319092,
|
|
"epoch": 0.4827931840962245,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004982032002640943,
|
|
"loss": 5.1988,
|
|
"mean_token_accuracy": 0.19191256910562515,
|
|
"num_tokens": 10628288.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.457940578460693,
|
|
"epoch": 0.48321082525893755,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981994435406965,
|
|
"loss": 5.3574,
|
|
"mean_token_accuracy": 0.17868073433637618,
|
|
"num_tokens": 10639433.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.347267723083496,
|
|
"epoch": 0.4836284664216505,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981956829099239,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.18723085671663284,
|
|
"num_tokens": 10649654.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.403138923645019,
|
|
"epoch": 0.4840461075843635,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981919183718422,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18621639013290406,
|
|
"num_tokens": 10658620.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.3692464351654055,
|
|
"epoch": 0.48446374874707654,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004981881499265173,
|
|
"loss": 5.1033,
|
|
"mean_token_accuracy": 0.19129590839147567,
|
|
"num_tokens": 10667942.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.305265188217163,
|
|
"epoch": 0.4848813899097895,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004981843775740151,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.18814138174057007,
|
|
"num_tokens": 10676895.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.496080636978149,
|
|
"epoch": 0.4852990310725025,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981806013144017,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.18187302947044373,
|
|
"num_tokens": 10685986.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.4939916133880615,
|
|
"epoch": 0.48571667223521553,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981768211477434,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.19719823598861694,
|
|
"num_tokens": 10694430.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.368886184692383,
|
|
"epoch": 0.4861343133979285,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000498173037074106,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19116412997245788,
|
|
"num_tokens": 10702997.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.374971628189087,
|
|
"epoch": 0.4865519545606415,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004981692490935561,
|
|
"loss": 5.3167,
|
|
"mean_token_accuracy": 0.18619992285966874,
|
|
"num_tokens": 10711652.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.4620719909667965,
|
|
"epoch": 0.4869695957233545,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004981654572061597,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.18306376338005065,
|
|
"num_tokens": 10721749.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.36485071182251,
|
|
"epoch": 0.4873872368860675,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004981616614119836,
|
|
"loss": 5.229,
|
|
"mean_token_accuracy": 0.18836989849805832,
|
|
"num_tokens": 10729678.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.4476886749267575,
|
|
"epoch": 0.4878048780487805,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004981578617110938,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.18365153819322586,
|
|
"num_tokens": 10740276.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.3470542430877686,
|
|
"epoch": 0.4882225192114935,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004981540581035571,
|
|
"loss": 5.2722,
|
|
"mean_token_accuracy": 0.18048646599054335,
|
|
"num_tokens": 10749249.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.426681041717529,
|
|
"epoch": 0.4886401603742065,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00049815025058944,
|
|
"loss": 5.1276,
|
|
"mean_token_accuracy": 0.19819484800100326,
|
|
"num_tokens": 10758888.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.296361207962036,
|
|
"epoch": 0.48905780153691947,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981464391688092,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.19552705734968184,
|
|
"num_tokens": 10768156.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.347362995147705,
|
|
"epoch": 0.4894754426996325,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981426238417312,
|
|
"loss": 5.1635,
|
|
"mean_token_accuracy": 0.20008436739444732,
|
|
"num_tokens": 10776762.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.441961288452148,
|
|
"epoch": 0.4898930838623455,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004981388046082731,
|
|
"loss": 5.2665,
|
|
"mean_token_accuracy": 0.17891191840171813,
|
|
"num_tokens": 10785495.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.368473482131958,
|
|
"epoch": 0.49031072502505846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004981349814685016,
|
|
"loss": 5.1282,
|
|
"mean_token_accuracy": 0.191314297914505,
|
|
"num_tokens": 10794400.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.359164381027222,
|
|
"epoch": 0.4907283661877715,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004981311544224838,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.19437927901744842,
|
|
"num_tokens": 10803138.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.462613439559936,
|
|
"epoch": 0.49114600735048447,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004981273234702864,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.18240292370319366,
|
|
"num_tokens": 10813583.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.348620653152466,
|
|
"epoch": 0.49156364851319745,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004981234886119767,
|
|
"loss": 5.1446,
|
|
"mean_token_accuracy": 0.19907235205173493,
|
|
"num_tokens": 10822532.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.289391088485718,
|
|
"epoch": 0.4919812896759105,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981196498476217,
|
|
"loss": 5.2331,
|
|
"mean_token_accuracy": 0.19357739835977555,
|
|
"num_tokens": 10832256.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.422555160522461,
|
|
"epoch": 0.49239893083862346,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004981158071772887,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.1932843953371048,
|
|
"num_tokens": 10840909.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.400418472290039,
|
|
"epoch": 0.49281657200133644,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004981119606010449,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.19052398800849915,
|
|
"num_tokens": 10849931.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.398821496963501,
|
|
"epoch": 0.4932342131640495,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004981081101189577,
|
|
"loss": 5.2242,
|
|
"mean_token_accuracy": 0.190839883685112,
|
|
"num_tokens": 10859518.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.397838973999024,
|
|
"epoch": 0.49365185432676245,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004981042557310945,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.18702766299247742,
|
|
"num_tokens": 10868567.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.270372676849365,
|
|
"epoch": 0.49406949548947543,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004981003974375227,
|
|
"loss": 5.0597,
|
|
"mean_token_accuracy": 0.19807375967502594,
|
|
"num_tokens": 10877463.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.339721965789795,
|
|
"epoch": 0.49448713665218846,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004980965352383099,
|
|
"loss": 5.1939,
|
|
"mean_token_accuracy": 0.1899080440402031,
|
|
"num_tokens": 10886228.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.493758630752564,
|
|
"epoch": 0.49490477781490144,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980926691335238,
|
|
"loss": 5.2877,
|
|
"mean_token_accuracy": 0.18432832062244414,
|
|
"num_tokens": 10895415.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.414480495452881,
|
|
"epoch": 0.4953224189776144,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004980887991232318,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.1809064745903015,
|
|
"num_tokens": 10904146.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.369438552856446,
|
|
"epoch": 0.49574006014032745,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000498084925207502,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.19040572196245192,
|
|
"num_tokens": 10914027.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.367545557022095,
|
|
"epoch": 0.49615770130304043,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000498081047386402,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.19287265688180924,
|
|
"num_tokens": 10923065.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.493957376480102,
|
|
"epoch": 0.4965753424657534,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004980771656599998,
|
|
"loss": 5.3274,
|
|
"mean_token_accuracy": 0.17854325026273726,
|
|
"num_tokens": 10932752.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.504323673248291,
|
|
"epoch": 0.49699298362846644,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980732800283633,
|
|
"loss": 5.2632,
|
|
"mean_token_accuracy": 0.1884702205657959,
|
|
"num_tokens": 10942536.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.376228141784668,
|
|
"epoch": 0.4974106247911794,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980693904915604,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.18781334161758423,
|
|
"num_tokens": 10952258.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.376414632797241,
|
|
"epoch": 0.4978282659538924,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980654970496595,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.18580455482006072,
|
|
"num_tokens": 10961590.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.405714321136474,
|
|
"epoch": 0.49824590711660544,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004980615997027284,
|
|
"loss": 5.184,
|
|
"mean_token_accuracy": 0.19644657373428345,
|
|
"num_tokens": 10971380.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.374588346481323,
|
|
"epoch": 0.4986635482793184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980576984508356,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.1910658985376358,
|
|
"num_tokens": 10979510.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.364955043792724,
|
|
"epoch": 0.4990811894420314,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004980537932940492,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.18778235465288162,
|
|
"num_tokens": 10988921.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.428235054016113,
|
|
"epoch": 0.4994988306047444,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004980498842324377,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.19132654815912248,
|
|
"num_tokens": 10998644.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.309868288040161,
|
|
"epoch": 0.4999164717674574,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004980459712660694,
|
|
"loss": 5.0925,
|
|
"mean_token_accuracy": 0.19584756791591645,
|
|
"num_tokens": 11006975.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.3369608402252195,
|
|
"epoch": 0.5003341129301704,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004980420543950131,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.1886674866080284,
|
|
"num_tokens": 11016011.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.51916651725769,
|
|
"epoch": 0.5007517540928834,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004980381336193371,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.17856939733028412,
|
|
"num_tokens": 11025600.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.369285678863525,
|
|
"epoch": 0.5011693952555963,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004980342089391099,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.19820183664560317,
|
|
"num_tokens": 11034747.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5011693952555963,
|
|
"eval_entropy": 5.074534042486067,
|
|
"eval_loss": 5.171754360198975,
|
|
"eval_mean_token_accuracy": 0.20148191507373087,
|
|
"eval_num_tokens": 11034747.0,
|
|
"eval_runtime": 45.7091,
|
|
"eval_samples_per_second": 826.159,
|
|
"eval_steps_per_second": 103.284,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.371310901641846,
|
|
"epoch": 0.5015870364183094,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004980302803544006,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.18710723221302034,
|
|
"num_tokens": 11043461.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.4246784210205075,
|
|
"epoch": 0.5020046775810224,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004980263478652778,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.18661852926015854,
|
|
"num_tokens": 11053632.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.363954353332519,
|
|
"epoch": 0.5024223187437353,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004980224114718102,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.18672070056200027,
|
|
"num_tokens": 11062620.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.358308601379394,
|
|
"epoch": 0.5028399599064484,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004980184711740669,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.1908510982990265,
|
|
"num_tokens": 11071105.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.405192756652832,
|
|
"epoch": 0.5032576010691614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004980145269721168,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20309916585683824,
|
|
"num_tokens": 11079926.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.370731210708618,
|
|
"epoch": 0.5036752422318743,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000498010578866029,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.18998298197984695,
|
|
"num_tokens": 11089395.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.367911863327026,
|
|
"epoch": 0.5040928833945874,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004980066268558726,
|
|
"loss": 5.1974,
|
|
"mean_token_accuracy": 0.20166174769401551,
|
|
"num_tokens": 11098464.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.467078399658203,
|
|
"epoch": 0.5045105245573004,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004980026709417167,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.18537590950727462,
|
|
"num_tokens": 11107861.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.362668657302857,
|
|
"epoch": 0.5049281657200133,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979987111236306,
|
|
"loss": 5.1342,
|
|
"mean_token_accuracy": 0.1961098313331604,
|
|
"num_tokens": 11116453.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.306366348266602,
|
|
"epoch": 0.5053458068827263,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979947474016837,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.19458985030651094,
|
|
"num_tokens": 11125166.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.50698447227478,
|
|
"epoch": 0.5057634480454394,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004979907797759453,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.18648483902215957,
|
|
"num_tokens": 11134560.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.459315967559815,
|
|
"epoch": 0.5061810892081523,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004979868082464849,
|
|
"loss": 5.1595,
|
|
"mean_token_accuracy": 0.199700328707695,
|
|
"num_tokens": 11143994.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.329993534088135,
|
|
"epoch": 0.5065987303708653,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004979828328133719,
|
|
"loss": 5.1814,
|
|
"mean_token_accuracy": 0.1865094408392906,
|
|
"num_tokens": 11152234.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.330966806411743,
|
|
"epoch": 0.5070163715335784,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004979788534766762,
|
|
"loss": 5.0477,
|
|
"mean_token_accuracy": 0.20409696847200393,
|
|
"num_tokens": 11161334.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.2545277118682865,
|
|
"epoch": 0.5074340126962913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004979748702364672,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.1898155018687248,
|
|
"num_tokens": 11170510.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.291109323501587,
|
|
"epoch": 0.5078516538590043,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979708830928147,
|
|
"loss": 5.1224,
|
|
"mean_token_accuracy": 0.20186497122049332,
|
|
"num_tokens": 11179378.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.44141731262207,
|
|
"epoch": 0.5082692950217174,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004979668920457884,
|
|
"loss": 5.2786,
|
|
"mean_token_accuracy": 0.18256962150335312,
|
|
"num_tokens": 11189534.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.358128690719605,
|
|
"epoch": 0.5086869361844303,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004979628970954584,
|
|
"loss": 5.1227,
|
|
"mean_token_accuracy": 0.1995835319161415,
|
|
"num_tokens": 11197827.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.311423206329346,
|
|
"epoch": 0.5091045773471433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979588982418944,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.1948838397860527,
|
|
"num_tokens": 11206759.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.343368148803711,
|
|
"epoch": 0.5095222185098564,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979548954851666,
|
|
"loss": 5.0642,
|
|
"mean_token_accuracy": 0.19709432274103164,
|
|
"num_tokens": 11216021.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.383245038986206,
|
|
"epoch": 0.5099398596725693,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497950888825345,
|
|
"loss": 5.1963,
|
|
"mean_token_accuracy": 0.18956346809864044,
|
|
"num_tokens": 11224936.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.307970476150513,
|
|
"epoch": 0.5103575008352823,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979468782624996,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.19218112230300904,
|
|
"num_tokens": 11233905.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.355756139755249,
|
|
"epoch": 0.5107751419979953,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004979428637967009,
|
|
"loss": 5.1319,
|
|
"mean_token_accuracy": 0.19714314490556717,
|
|
"num_tokens": 11242470.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.346217107772827,
|
|
"epoch": 0.5111927831607083,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004979388454280189,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1902886748313904,
|
|
"num_tokens": 11251861.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.40616626739502,
|
|
"epoch": 0.5116104243234213,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000497934823156524,
|
|
"loss": 5.1816,
|
|
"mean_token_accuracy": 0.18871729224920272,
|
|
"num_tokens": 11260830.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.354992914199829,
|
|
"epoch": 0.5120280654861343,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004979307969822869,
|
|
"loss": 5.1701,
|
|
"mean_token_accuracy": 0.19636960774660112,
|
|
"num_tokens": 11269906.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.423812389373779,
|
|
"epoch": 0.5124457066488474,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979267669053776,
|
|
"loss": 5.2386,
|
|
"mean_token_accuracy": 0.1922266736626625,
|
|
"num_tokens": 11279471.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.498798847198486,
|
|
"epoch": 0.5128633478115603,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004979227329258671,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.1858723059296608,
|
|
"num_tokens": 11288586.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.368722343444825,
|
|
"epoch": 0.5132809889742733,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004979186950438256,
|
|
"loss": 5.2838,
|
|
"mean_token_accuracy": 0.1882128655910492,
|
|
"num_tokens": 11297768.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.330961847305298,
|
|
"epoch": 0.5136986301369864,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004979146532593243,
|
|
"loss": 5.1373,
|
|
"mean_token_accuracy": 0.19379662573337555,
|
|
"num_tokens": 11307096.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.291053676605225,
|
|
"epoch": 0.5141162712996993,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004979106075724334,
|
|
"loss": 5.0147,
|
|
"mean_token_accuracy": 0.20165223777294158,
|
|
"num_tokens": 11315518.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.3389616966247555,
|
|
"epoch": 0.5145339124624123,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004979065579832242,
|
|
"loss": 5.0772,
|
|
"mean_token_accuracy": 0.1999486044049263,
|
|
"num_tokens": 11324232.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.364621829986572,
|
|
"epoch": 0.5149515536251253,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004979025044917673,
|
|
"loss": 5.2064,
|
|
"mean_token_accuracy": 0.18995740860700608,
|
|
"num_tokens": 11332923.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.351355361938476,
|
|
"epoch": 0.5153691947878383,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004978984470981339,
|
|
"loss": 5.2016,
|
|
"mean_token_accuracy": 0.18982303142547607,
|
|
"num_tokens": 11342350.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.323089170455932,
|
|
"epoch": 0.5157868359505513,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978943858023946,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19940741807222367,
|
|
"num_tokens": 11350982.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.339259433746338,
|
|
"epoch": 0.5162044771132643,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497890320604621,
|
|
"loss": 5.1882,
|
|
"mean_token_accuracy": 0.19151103794574736,
|
|
"num_tokens": 11360637.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.326295328140259,
|
|
"epoch": 0.5166221182759773,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000497886251504884,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.19761618971824646,
|
|
"num_tokens": 11368783.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.263182878494263,
|
|
"epoch": 0.5170397594386903,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004978821785032549,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.20286861807107925,
|
|
"num_tokens": 11378359.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.298379039764404,
|
|
"epoch": 0.5174574006014033,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004978781015998048,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.1864807888865471,
|
|
"num_tokens": 11387235.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.45116868019104,
|
|
"epoch": 0.5178750417641163,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004978740207946056,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.18897955417633056,
|
|
"num_tokens": 11396400.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.4217616558074955,
|
|
"epoch": 0.5182926829268293,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004978699360877281,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.1933171421289444,
|
|
"num_tokens": 11405589.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.340744686126709,
|
|
"epoch": 0.5187103240895423,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004978658474792442,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.18833179026842117,
|
|
"num_tokens": 11414983.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.379719352722168,
|
|
"epoch": 0.5191279652522552,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004978617549692253,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.19461302161216737,
|
|
"num_tokens": 11423172.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.427470254898071,
|
|
"epoch": 0.5195456064149683,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004978576585577432,
|
|
"loss": 5.1597,
|
|
"mean_token_accuracy": 0.1955975577235222,
|
|
"num_tokens": 11432758.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.307151174545288,
|
|
"epoch": 0.5199632475776813,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978535582448695,
|
|
"loss": 5.1429,
|
|
"mean_token_accuracy": 0.19425086826086044,
|
|
"num_tokens": 11441754.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.338606548309326,
|
|
"epoch": 0.5203808887403942,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004978494540306761,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19322633743286133,
|
|
"num_tokens": 11451176.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.401440668106079,
|
|
"epoch": 0.5207985299031073,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004978453459152346,
|
|
"loss": 5.2799,
|
|
"mean_token_accuracy": 0.1845268800854683,
|
|
"num_tokens": 11461353.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.4003277778625485,
|
|
"epoch": 0.5212161710658203,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978412338986172,
|
|
"loss": 5.2226,
|
|
"mean_token_accuracy": 0.19184250235557557,
|
|
"num_tokens": 11470103.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.411133718490601,
|
|
"epoch": 0.5216338122285332,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004978371179808958,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.20293542742729187,
|
|
"num_tokens": 11480348.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.3573017597198485,
|
|
"epoch": 0.5220514533912463,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004978329981621424,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.1941980689764023,
|
|
"num_tokens": 11490836.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.289730644226074,
|
|
"epoch": 0.5224690945539593,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000497828874442429,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.201852186024189,
|
|
"num_tokens": 11500344.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.409614372253418,
|
|
"epoch": 0.5228867357166722,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000497824746821828,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.1962419107556343,
|
|
"num_tokens": 11509624.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.372205305099487,
|
|
"epoch": 0.5233043768793852,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004978206153004117,
|
|
"loss": 5.2345,
|
|
"mean_token_accuracy": 0.18493836969137192,
|
|
"num_tokens": 11519915.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.3526781558990475,
|
|
"epoch": 0.5237220180420983,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004978164798782523,
|
|
"loss": 5.0358,
|
|
"mean_token_accuracy": 0.19962794780731202,
|
|
"num_tokens": 11528918.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.339715623855591,
|
|
"epoch": 0.5241396592048112,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978123405554221,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.18854066729545593,
|
|
"num_tokens": 11537396.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.441776371002197,
|
|
"epoch": 0.5245573003675242,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004978081973319938,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.17991774082183837,
|
|
"num_tokens": 11547196.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.424055194854736,
|
|
"epoch": 0.5249749415302373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004978040502080398,
|
|
"loss": 5.1772,
|
|
"mean_token_accuracy": 0.18890680372714996,
|
|
"num_tokens": 11556126.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.408015203475952,
|
|
"epoch": 0.5253925826929502,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004977998991836327,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.19184066653251647,
|
|
"num_tokens": 11565622.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.2802653312683105,
|
|
"epoch": 0.5258102238556632,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004977957442588451,
|
|
"loss": 5.0929,
|
|
"mean_token_accuracy": 0.18885134607553483,
|
|
"num_tokens": 11576052.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.3731475353240965,
|
|
"epoch": 0.5262278650183763,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004977915854337498,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.18309632390737535,
|
|
"num_tokens": 11585907.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.333365726470947,
|
|
"epoch": 0.5266455061810892,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004977874227084197,
|
|
"loss": 5.1102,
|
|
"mean_token_accuracy": 0.1893043637275696,
|
|
"num_tokens": 11594802.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.349949836730957,
|
|
"epoch": 0.5270631473438022,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004977832560829277,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.1998143494129181,
|
|
"num_tokens": 11604026.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.352085113525391,
|
|
"epoch": 0.5274807885065153,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004977790855573464,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.18360945135354995,
|
|
"num_tokens": 11614209.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.347003936767578,
|
|
"epoch": 0.5278984296692282,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977749111317492,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.1972319170832634,
|
|
"num_tokens": 11622492.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.3417829990386965,
|
|
"epoch": 0.5283160708319412,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497770732806209,
|
|
"loss": 5.1183,
|
|
"mean_token_accuracy": 0.19714829325675964,
|
|
"num_tokens": 11631106.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.3663414478302,
|
|
"epoch": 0.5287337119946542,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497766550580799,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.2007100448012352,
|
|
"num_tokens": 11639748.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.344409227371216,
|
|
"epoch": 0.5291513531573672,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977623644555923,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.1919018194079399,
|
|
"num_tokens": 11648524.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.366573190689087,
|
|
"epoch": 0.5295689943200802,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004977581744306624,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.1894583910703659,
|
|
"num_tokens": 11658439.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.345481109619141,
|
|
"epoch": 0.5299866354827932,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977539805060824,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.19623524695634842,
|
|
"num_tokens": 11666319.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.30642032623291,
|
|
"epoch": 0.5304042766455062,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977497826819259,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.1939917355775833,
|
|
"num_tokens": 11675506.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.3404871940612795,
|
|
"epoch": 0.5308219178082192,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004977455809582664,
|
|
"loss": 5.1551,
|
|
"mean_token_accuracy": 0.19206639677286147,
|
|
"num_tokens": 11685613.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.352160787582397,
|
|
"epoch": 0.5312395589709322,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004977413753351772,
|
|
"loss": 5.1894,
|
|
"mean_token_accuracy": 0.18840061128139496,
|
|
"num_tokens": 11694896.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.48978853225708,
|
|
"epoch": 0.5316572001336451,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004977371658127323,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.18616707772016525,
|
|
"num_tokens": 11703599.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.325676488876343,
|
|
"epoch": 0.5320748412963582,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004977329523910051,
|
|
"loss": 5.096,
|
|
"mean_token_accuracy": 0.20794474184513093,
|
|
"num_tokens": 11712155.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.369633388519287,
|
|
"epoch": 0.5324924824590712,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004977287350700695,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19570441097021102,
|
|
"num_tokens": 11721224.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.307780075073242,
|
|
"epoch": 0.5329101236217841,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977245138499993,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20322698950767518,
|
|
"num_tokens": 11729733.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.349961423873902,
|
|
"epoch": 0.5333277647844972,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004977202887308684,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.18604572862386703,
|
|
"num_tokens": 11738840.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.420208501815796,
|
|
"epoch": 0.5337454059472102,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004977160597127507,
|
|
"loss": 5.2287,
|
|
"mean_token_accuracy": 0.19101801067590712,
|
|
"num_tokens": 11748632.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.307418441772461,
|
|
"epoch": 0.5341630471099231,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977118267957204,
|
|
"loss": 5.0367,
|
|
"mean_token_accuracy": 0.19861231446266175,
|
|
"num_tokens": 11756707.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.350621461868286,
|
|
"epoch": 0.5345806882726362,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977075899798513,
|
|
"loss": 5.1968,
|
|
"mean_token_accuracy": 0.1886812999844551,
|
|
"num_tokens": 11765346.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.388677597045898,
|
|
"epoch": 0.5349983294353492,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000497703349265218,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.19622065573930741,
|
|
"num_tokens": 11773663.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.393760013580322,
|
|
"epoch": 0.5354159705980621,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976991046518943,
|
|
"loss": 5.2367,
|
|
"mean_token_accuracy": 0.18964672535657884,
|
|
"num_tokens": 11783782.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.402032566070557,
|
|
"epoch": 0.5358336117607752,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004976948561399549,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.1915680319070816,
|
|
"num_tokens": 11792241.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.384722518920898,
|
|
"epoch": 0.5362512529234882,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976906037294738,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.18948673605918884,
|
|
"num_tokens": 11801576.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.341787433624267,
|
|
"epoch": 0.5366688940862011,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004976863474205257,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.2000510111451149,
|
|
"num_tokens": 11810710.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.414744234085083,
|
|
"epoch": 0.5370865352489141,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004976820872131851,
|
|
"loss": 5.2375,
|
|
"mean_token_accuracy": 0.1876342236995697,
|
|
"num_tokens": 11820099.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.361027622222901,
|
|
"epoch": 0.5375041764116272,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004976778231075266,
|
|
"loss": 5.0838,
|
|
"mean_token_accuracy": 0.19711955189704894,
|
|
"num_tokens": 11828846.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.298186874389648,
|
|
"epoch": 0.5379218175743401,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004976735551036245,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.19465531706809996,
|
|
"num_tokens": 11837935.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.332701063156128,
|
|
"epoch": 0.5383394587370531,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000497669283201554,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.1943788394331932,
|
|
"num_tokens": 11846984.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.295116186141968,
|
|
"epoch": 0.5387570998997662,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976650074013895,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.1988813489675522,
|
|
"num_tokens": 11856114.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.3103714942932125,
|
|
"epoch": 0.5391747410624791,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004976607277032061,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.19245218485593796,
|
|
"num_tokens": 11866623.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.345043039321899,
|
|
"epoch": 0.5395923822251921,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976564441070788,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19719077944755553,
|
|
"num_tokens": 11876445.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.388862466812133,
|
|
"epoch": 0.5400100233879052,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004976521566130823,
|
|
"loss": 5.1867,
|
|
"mean_token_accuracy": 0.18925078511238097,
|
|
"num_tokens": 11885411.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.4106419563293455,
|
|
"epoch": 0.5404276645506181,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004976478652212918,
|
|
"loss": 5.1739,
|
|
"mean_token_accuracy": 0.19863243848085405,
|
|
"num_tokens": 11894803.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.321146154403687,
|
|
"epoch": 0.5408453057133311,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976435699317824,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.19962106496095658,
|
|
"num_tokens": 11904299.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.29001898765564,
|
|
"epoch": 0.5412629468760441,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004976392707446293,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.19826269745826722,
|
|
"num_tokens": 11914197.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.3684563636779785,
|
|
"epoch": 0.5416805880387571,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004976349676599078,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.19499578326940536,
|
|
"num_tokens": 11923610.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.355332469940185,
|
|
"epoch": 0.5420982292014701,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004976306606776932,
|
|
"loss": 5.1041,
|
|
"mean_token_accuracy": 0.20078449547290803,
|
|
"num_tokens": 11932896.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.397964572906494,
|
|
"epoch": 0.5425158703641831,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976263497980609,
|
|
"loss": 5.1966,
|
|
"mean_token_accuracy": 0.19083174020051957,
|
|
"num_tokens": 11941343.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.322998714447022,
|
|
"epoch": 0.5429335115268961,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004976220350210864,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19521888345479965,
|
|
"num_tokens": 11950412.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.3088782787322994,
|
|
"epoch": 0.5433511526896091,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004976177163468451,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.20229381024837495,
|
|
"num_tokens": 11959021.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.385486364364624,
|
|
"epoch": 0.5437687938523221,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976133937754128,
|
|
"loss": 5.1841,
|
|
"mean_token_accuracy": 0.19089934080839158,
|
|
"num_tokens": 11968725.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.338533687591553,
|
|
"epoch": 0.544186435015035,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004976090673068651,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.19223623126745223,
|
|
"num_tokens": 11977775.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.396485805511475,
|
|
"epoch": 0.5446040761777481,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004976047369412778,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.1863601803779602,
|
|
"num_tokens": 11988010.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.267076730728149,
|
|
"epoch": 0.5450217173404611,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004976004026787266,
|
|
"loss": 5.0859,
|
|
"mean_token_accuracy": 0.19687168300151825,
|
|
"num_tokens": 11997284.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.407790803909302,
|
|
"epoch": 0.545439358503174,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975960645192873,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.19141084253787993,
|
|
"num_tokens": 12005516.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.387099313735962,
|
|
"epoch": 0.5458569996658871,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004975917224630359,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.19781887382268906,
|
|
"num_tokens": 12014236.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.349125146865845,
|
|
"epoch": 0.5462746408286001,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975873765100487,
|
|
"loss": 5.1573,
|
|
"mean_token_accuracy": 0.19421713799238205,
|
|
"num_tokens": 12022201.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.347995471954346,
|
|
"epoch": 0.546692281991313,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004975830266604013,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.18418316543102264,
|
|
"num_tokens": 12032421.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.455700492858886,
|
|
"epoch": 0.5471099231540261,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004975786729141702,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.19091300070285797,
|
|
"num_tokens": 12041443.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.339406156539917,
|
|
"epoch": 0.5475275643167391,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004975743152714314,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.19153235256671905,
|
|
"num_tokens": 12050753.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.377761030197144,
|
|
"epoch": 0.547945205479452,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004975699537322616,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.18913163989782333,
|
|
"num_tokens": 12059886.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.355277633666992,
|
|
"epoch": 0.5483628466421651,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975655882967366,
|
|
"loss": 5.1418,
|
|
"mean_token_accuracy": 0.1900908187031746,
|
|
"num_tokens": 12068695.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.32841649055481,
|
|
"epoch": 0.5487804878048781,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004975612189649331,
|
|
"loss": 5.0752,
|
|
"mean_token_accuracy": 0.19925803542137147,
|
|
"num_tokens": 12077552.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.470986318588257,
|
|
"epoch": 0.549198128967591,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975568457369276,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19376844614744188,
|
|
"num_tokens": 12085994.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.365000152587891,
|
|
"epoch": 0.549615770130304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004975524686127966,
|
|
"loss": 5.0889,
|
|
"mean_token_accuracy": 0.1935693308711052,
|
|
"num_tokens": 12095342.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.292310285568237,
|
|
"epoch": 0.5500334112930171,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004975480875926168,
|
|
"loss": 5.1515,
|
|
"mean_token_accuracy": 0.19415584355592727,
|
|
"num_tokens": 12104578.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.195289564132691,
|
|
"epoch": 0.55045105245573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004975437026764648,
|
|
"loss": 4.9743,
|
|
"mean_token_accuracy": 0.20345960557460785,
|
|
"num_tokens": 12113614.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.406784105300903,
|
|
"epoch": 0.550868693618443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004975393138644175,
|
|
"loss": 5.2625,
|
|
"mean_token_accuracy": 0.19465185403823854,
|
|
"num_tokens": 12123328.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.393036937713623,
|
|
"epoch": 0.5512863347811561,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004975349211565515,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.19463902413845063,
|
|
"num_tokens": 12133011.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.441806507110596,
|
|
"epoch": 0.551703975943869,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000497530524552944,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.1859285220503807,
|
|
"num_tokens": 12142398.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.4156862735748295,
|
|
"epoch": 0.552121617106582,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004975261240536716,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.1768987938761711,
|
|
"num_tokens": 12152210.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.3214953422546385,
|
|
"epoch": 0.5525392582692951,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004975217196588117,
|
|
"loss": 5.1156,
|
|
"mean_token_accuracy": 0.19948102086782454,
|
|
"num_tokens": 12162083.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.449624109268188,
|
|
"epoch": 0.552956899432008,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004975173113684413,
|
|
"loss": 5.2123,
|
|
"mean_token_accuracy": 0.18549382388591767,
|
|
"num_tokens": 12172024.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.50048828125,
|
|
"epoch": 0.553374540594721,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004975128991826374,
|
|
"loss": 5.318,
|
|
"mean_token_accuracy": 0.18137646913528443,
|
|
"num_tokens": 12181474.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.4226806640625,
|
|
"epoch": 0.553792181757434,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004975084831014774,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.19145766794681549,
|
|
"num_tokens": 12190622.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.364470386505127,
|
|
"epoch": 0.554209822920147,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004975040631250386,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.18950837701559067,
|
|
"num_tokens": 12199282.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.346656370162964,
|
|
"epoch": 0.55462746408286,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974996392533983,
|
|
"loss": 5.1296,
|
|
"mean_token_accuracy": 0.19598551839590073,
|
|
"num_tokens": 12208536.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.377294445037842,
|
|
"epoch": 0.555045105245573,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000497495211486634,
|
|
"loss": 5.1829,
|
|
"mean_token_accuracy": 0.1942179575562477,
|
|
"num_tokens": 12217716.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.290253400802612,
|
|
"epoch": 0.555462746408286,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004974907798248232,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.2022324874997139,
|
|
"num_tokens": 12226214.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.296945953369141,
|
|
"epoch": 0.555880387570999,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974863442680434,
|
|
"loss": 5.0398,
|
|
"mean_token_accuracy": 0.19773054420948027,
|
|
"num_tokens": 12235005.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.283091354370117,
|
|
"epoch": 0.556298028733712,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974819048163725,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.1941853165626526,
|
|
"num_tokens": 12243085.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.460150146484375,
|
|
"epoch": 0.556715669896425,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497477461469888,
|
|
"loss": 5.2421,
|
|
"mean_token_accuracy": 0.18839055746793748,
|
|
"num_tokens": 12252826.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.4285454750061035,
|
|
"epoch": 0.557133311059138,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974730142286677,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1895604521036148,
|
|
"num_tokens": 12261166.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.319204521179199,
|
|
"epoch": 0.557550952221851,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004974685630927895,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.1969272181391716,
|
|
"num_tokens": 12270695.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.448785209655762,
|
|
"epoch": 0.557968593384564,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004974641080623314,
|
|
"loss": 5.2896,
|
|
"mean_token_accuracy": 0.18632653653621672,
|
|
"num_tokens": 12280486.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.433121919631958,
|
|
"epoch": 0.558386234547277,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004974596491373711,
|
|
"loss": 5.1274,
|
|
"mean_token_accuracy": 0.19442566186189653,
|
|
"num_tokens": 12289246.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.168073034286499,
|
|
"epoch": 0.55880387570999,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004974551863179871,
|
|
"loss": 5.0963,
|
|
"mean_token_accuracy": 0.19665029197931289,
|
|
"num_tokens": 12297562.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.388290691375732,
|
|
"epoch": 0.5592215168727029,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004974507196042572,
|
|
"loss": 5.1942,
|
|
"mean_token_accuracy": 0.18809617012739183,
|
|
"num_tokens": 12307647.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.482595014572143,
|
|
"epoch": 0.559639158035416,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004974462489962597,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.1878604143857956,
|
|
"num_tokens": 12317840.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.337702131271362,
|
|
"epoch": 0.560056799198129,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004974417744940729,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.19751934111118316,
|
|
"num_tokens": 12327340.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.265525245666504,
|
|
"epoch": 0.5604744403608419,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000497437296097775,
|
|
"loss": 5.1408,
|
|
"mean_token_accuracy": 0.1950373589992523,
|
|
"num_tokens": 12336269.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.467349004745484,
|
|
"epoch": 0.560892081523555,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004974328138074445,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.18728578388690947,
|
|
"num_tokens": 12345197.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.397080135345459,
|
|
"epoch": 0.561309722686268,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004974283276231599,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.18496414124965668,
|
|
"num_tokens": 12355312.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.352804136276245,
|
|
"epoch": 0.5617273638489809,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004974238375449996,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.19194717109203338,
|
|
"num_tokens": 12364354.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.426503467559814,
|
|
"epoch": 0.562145005011694,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974193435730424,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.1853985846042633,
|
|
"num_tokens": 12373512.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.371908187866211,
|
|
"epoch": 0.562562646174407,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004974148457073668,
|
|
"loss": 5.2387,
|
|
"mean_token_accuracy": 0.1899238035082817,
|
|
"num_tokens": 12383087.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.328854513168335,
|
|
"epoch": 0.5629802873371199,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004974103439480517,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.20298333317041398,
|
|
"num_tokens": 12392097.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.341432666778564,
|
|
"epoch": 0.563397928499833,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004974058382951757,
|
|
"loss": 5.1352,
|
|
"mean_token_accuracy": 0.1985837325453758,
|
|
"num_tokens": 12401806.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.3904945850372314,
|
|
"epoch": 0.563815569662546,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004974013287488177,
|
|
"loss": 5.1499,
|
|
"mean_token_accuracy": 0.18843519389629365,
|
|
"num_tokens": 12412111.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.291284847259521,
|
|
"epoch": 0.5642332108252589,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004973968153090569,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.20206182301044465,
|
|
"num_tokens": 12421451.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.19704794883728,
|
|
"epoch": 0.5646508519879719,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004973922979759722,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.20033052265644075,
|
|
"num_tokens": 12430535.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.366093635559082,
|
|
"epoch": 0.565068493150685,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973877767496424,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.18773623257875444,
|
|
"num_tokens": 12439727.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.330592632293701,
|
|
"epoch": 0.5654861343133979,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004973832516301472,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.1990250378847122,
|
|
"num_tokens": 12448889.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.280762243270874,
|
|
"epoch": 0.5659037754761109,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004973787226175652,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.19861100614070892,
|
|
"num_tokens": 12457529.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.326727724075317,
|
|
"epoch": 0.566321416638824,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004973741897119761,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.1926957532763481,
|
|
"num_tokens": 12466379.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.317066383361817,
|
|
"epoch": 0.5667390578015369,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973696529134592,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.19899345487356185,
|
|
"num_tokens": 12475317.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.381332015991211,
|
|
"epoch": 0.5671566989642499,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973651122220938,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.18579948097467422,
|
|
"num_tokens": 12483882.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.4720409393310545,
|
|
"epoch": 0.567574340126963,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973605676379595,
|
|
"loss": 5.1997,
|
|
"mean_token_accuracy": 0.1925591856241226,
|
|
"num_tokens": 12493782.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.290466785430908,
|
|
"epoch": 0.5679919812896759,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004973560191611357,
|
|
"loss": 5.0002,
|
|
"mean_token_accuracy": 0.20428299456834792,
|
|
"num_tokens": 12501940.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.290628671646118,
|
|
"epoch": 0.5684096224523889,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004973514667917021,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.19120573848485947,
|
|
"num_tokens": 12511566.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.350892734527588,
|
|
"epoch": 0.5688272636151019,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004973469105297386,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.19574938267469405,
|
|
"num_tokens": 12519902.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.426688575744629,
|
|
"epoch": 0.5692449047778149,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004973423503753247,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.1862822949886322,
|
|
"num_tokens": 12529011.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.383047246932984,
|
|
"epoch": 0.5696625459405279,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004973377863285403,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.18973727524280548,
|
|
"num_tokens": 12538181.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.372748517990113,
|
|
"epoch": 0.5700801871032409,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004973332183894653,
|
|
"loss": 5.1263,
|
|
"mean_token_accuracy": 0.1965460568666458,
|
|
"num_tokens": 12545935.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.322467803955078,
|
|
"epoch": 0.5704978282659539,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004973286465581798,
|
|
"loss": 5.1455,
|
|
"mean_token_accuracy": 0.19253342747688293,
|
|
"num_tokens": 12555586.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.346379041671753,
|
|
"epoch": 0.5709154694286669,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004973240708347637,
|
|
"loss": 5.144,
|
|
"mean_token_accuracy": 0.19310083389282226,
|
|
"num_tokens": 12564478.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.321989631652832,
|
|
"epoch": 0.5713331105913799,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973194912192971,
|
|
"loss": 5.0836,
|
|
"mean_token_accuracy": 0.19851395040750502,
|
|
"num_tokens": 12573769.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.293387603759766,
|
|
"epoch": 0.5717507517540928,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004973149077118602,
|
|
"loss": 5.1118,
|
|
"mean_token_accuracy": 0.20072826743125916,
|
|
"num_tokens": 12583291.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.296703433990478,
|
|
"epoch": 0.5721683929168059,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004973103203125333,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20669862180948256,
|
|
"num_tokens": 12591828.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.359651756286621,
|
|
"epoch": 0.5725860340795189,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004973057290213965,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.19550466686487197,
|
|
"num_tokens": 12600417.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.296748542785645,
|
|
"epoch": 0.5730036752422318,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004973011338385304,
|
|
"loss": 5.1191,
|
|
"mean_token_accuracy": 0.1996015191078186,
|
|
"num_tokens": 12609555.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.479836130142212,
|
|
"epoch": 0.5734213164049449,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972965347640154,
|
|
"loss": 5.2229,
|
|
"mean_token_accuracy": 0.19145398288965226,
|
|
"num_tokens": 12618666.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.483303022384644,
|
|
"epoch": 0.5738389575676579,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497291931797932,
|
|
"loss": 5.2405,
|
|
"mean_token_accuracy": 0.19066340774297713,
|
|
"num_tokens": 12627206.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.4183789730072025,
|
|
"epoch": 0.5742565987303708,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004972873249403608,
|
|
"loss": 5.1817,
|
|
"mean_token_accuracy": 0.1946453332901001,
|
|
"num_tokens": 12636782.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.373637866973877,
|
|
"epoch": 0.5746742398930839,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972827141913822,
|
|
"loss": 5.0985,
|
|
"mean_token_accuracy": 0.2005917802453041,
|
|
"num_tokens": 12645895.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.292585992813111,
|
|
"epoch": 0.5750918810557969,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004972780995510773,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.1963945597410202,
|
|
"num_tokens": 12655744.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.22461838722229,
|
|
"epoch": 0.5755095222185098,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004972734810195266,
|
|
"loss": 5.1222,
|
|
"mean_token_accuracy": 0.19921172857284547,
|
|
"num_tokens": 12665498.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.363934135437011,
|
|
"epoch": 0.5759271633812229,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972688585968112,
|
|
"loss": 5.0981,
|
|
"mean_token_accuracy": 0.19758863300085067,
|
|
"num_tokens": 12674218.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.377480697631836,
|
|
"epoch": 0.5763448045439359,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004972642322830118,
|
|
"loss": 5.2035,
|
|
"mean_token_accuracy": 0.19689171463251115,
|
|
"num_tokens": 12683060.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.319082641601563,
|
|
"epoch": 0.5767624457066488,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972596020782096,
|
|
"loss": 5.1409,
|
|
"mean_token_accuracy": 0.19724392890930176,
|
|
"num_tokens": 12693145.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.263584899902344,
|
|
"epoch": 0.5771800868693618,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004972549679824853,
|
|
"loss": 5.1076,
|
|
"mean_token_accuracy": 0.19264092296361923,
|
|
"num_tokens": 12701439.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.387259006500244,
|
|
"epoch": 0.5775977280320749,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972503299959204,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18422734141349792,
|
|
"num_tokens": 12710582.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.392769384384155,
|
|
"epoch": 0.5780153691947878,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000497245688118596,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.1991504356265068,
|
|
"num_tokens": 12719685.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.326436996459961,
|
|
"epoch": 0.5784330103575008,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972410423505932,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1956579267978668,
|
|
"num_tokens": 12729632.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.257115268707276,
|
|
"epoch": 0.5788506515202139,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004972363926919935,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.20584451258182526,
|
|
"num_tokens": 12738900.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.234428453445434,
|
|
"epoch": 0.5792682926829268,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004972317391428782,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.2092110425233841,
|
|
"num_tokens": 12748195.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.386837911605835,
|
|
"epoch": 0.5796859338456398,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004972270817033288,
|
|
"loss": 5.1366,
|
|
"mean_token_accuracy": 0.19250407069921494,
|
|
"num_tokens": 12757038.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.294331216812134,
|
|
"epoch": 0.5801035750083529,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004972224203734269,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.20248115062713623,
|
|
"num_tokens": 12765871.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.321333217620849,
|
|
"epoch": 0.5805212161710658,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000497217755153254,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.19954693764448167,
|
|
"num_tokens": 12774776.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.378604602813721,
|
|
"epoch": 0.5809388573337788,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004972130860428918,
|
|
"loss": 5.1611,
|
|
"mean_token_accuracy": 0.19467803537845613,
|
|
"num_tokens": 12783815.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.431467008590698,
|
|
"epoch": 0.5813564984964918,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004972084130424222,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.18621581941843032,
|
|
"num_tokens": 12793690.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.292046070098877,
|
|
"epoch": 0.5817741396592048,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004972037361519267,
|
|
"loss": 5.151,
|
|
"mean_token_accuracy": 0.1941456377506256,
|
|
"num_tokens": 12802525.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.385690546035766,
|
|
"epoch": 0.5821917808219178,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004971990553714874,
|
|
"loss": 5.1252,
|
|
"mean_token_accuracy": 0.1924806609749794,
|
|
"num_tokens": 12811246.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.361019563674927,
|
|
"epoch": 0.5826094219846308,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971943707011861,
|
|
"loss": 5.1619,
|
|
"mean_token_accuracy": 0.19383280277252196,
|
|
"num_tokens": 12820477.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.307391262054443,
|
|
"epoch": 0.5830270631473438,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000497189682141105,
|
|
"loss": 5.0248,
|
|
"mean_token_accuracy": 0.20165422707796096,
|
|
"num_tokens": 12829544.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.38154444694519,
|
|
"epoch": 0.5834447043100568,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004971849896913259,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.20376940071582794,
|
|
"num_tokens": 12839388.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.305687189102173,
|
|
"epoch": 0.5838623454727698,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971802933519312,
|
|
"loss": 5.0194,
|
|
"mean_token_accuracy": 0.2048604443669319,
|
|
"num_tokens": 12848191.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.2804811000823975,
|
|
"epoch": 0.5842799866354828,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004971755931230031,
|
|
"loss": 5.1865,
|
|
"mean_token_accuracy": 0.19613789916038513,
|
|
"num_tokens": 12859239.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.361107730865479,
|
|
"epoch": 0.5846976277981958,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004971708890046236,
|
|
"loss": 5.2246,
|
|
"mean_token_accuracy": 0.19486147165298462,
|
|
"num_tokens": 12868335.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.319368600845337,
|
|
"epoch": 0.5851152689609088,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971661809968755,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.19932467639446258,
|
|
"num_tokens": 12876939.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.237836313247681,
|
|
"epoch": 0.5855329101236217,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004971614690998409,
|
|
"loss": 5.057,
|
|
"mean_token_accuracy": 0.20067977011203766,
|
|
"num_tokens": 12885856.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.429441452026367,
|
|
"epoch": 0.5859505512863348,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004971567533136024,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.18448419123888016,
|
|
"num_tokens": 12895451.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.433368682861328,
|
|
"epoch": 0.5863681924490478,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971520336382424,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.19419241547584534,
|
|
"num_tokens": 12904796.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.337957429885864,
|
|
"epoch": 0.5867858336117607,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971473100738437,
|
|
"loss": 5.2554,
|
|
"mean_token_accuracy": 0.19285500198602676,
|
|
"num_tokens": 12913668.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.3801453590393065,
|
|
"epoch": 0.5872034747744738,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497142582620489,
|
|
"loss": 5.0768,
|
|
"mean_token_accuracy": 0.19855692386627197,
|
|
"num_tokens": 12922469.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.260585451126099,
|
|
"epoch": 0.5876211159371868,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971378512782609,
|
|
"loss": 5.0905,
|
|
"mean_token_accuracy": 0.19931782335042952,
|
|
"num_tokens": 12931070.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.296568965911865,
|
|
"epoch": 0.5880387570998997,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004971331160472424,
|
|
"loss": 5.153,
|
|
"mean_token_accuracy": 0.196849125623703,
|
|
"num_tokens": 12939397.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.395985412597656,
|
|
"epoch": 0.5884563982626128,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004971283769275163,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.1901712790131569,
|
|
"num_tokens": 12948951.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.33565673828125,
|
|
"epoch": 0.5888740394253258,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971236339191656,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.1993100419640541,
|
|
"num_tokens": 12958431.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.402555990219116,
|
|
"epoch": 0.5892916805880387,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004971188870222734,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.2008296802639961,
|
|
"num_tokens": 12966521.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.282171106338501,
|
|
"epoch": 0.5897093217507517,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004971141362369226,
|
|
"loss": 5.12,
|
|
"mean_token_accuracy": 0.197982756793499,
|
|
"num_tokens": 12976458.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.289409875869751,
|
|
"epoch": 0.5901269629134648,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004971093815631965,
|
|
"loss": 5.0951,
|
|
"mean_token_accuracy": 0.19220995157957077,
|
|
"num_tokens": 12985715.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.274262237548828,
|
|
"epoch": 0.5905446040761777,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004971046230011783,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.1918730169534683,
|
|
"num_tokens": 12995640.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.3513427734375,
|
|
"epoch": 0.5909622452388907,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970998605509514,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20095302611589433,
|
|
"num_tokens": 13004645.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.314946794509888,
|
|
"epoch": 0.5913798864016038,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000497095094212599,
|
|
"loss": 5.1464,
|
|
"mean_token_accuracy": 0.19299272298812867,
|
|
"num_tokens": 13013433.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.433899736404419,
|
|
"epoch": 0.5917975275643167,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004970903239862047,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.18795922845602037,
|
|
"num_tokens": 13023098.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.372664165496826,
|
|
"epoch": 0.5922151687270297,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004970855498718519,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.2051659867167473,
|
|
"num_tokens": 13031715.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.292305326461792,
|
|
"epoch": 0.5926328098897428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004970807718696243,
|
|
"loss": 5.0896,
|
|
"mean_token_accuracy": 0.19841336756944655,
|
|
"num_tokens": 13040847.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.34084119796753,
|
|
"epoch": 0.5930504510524557,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004970759899796055,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.19473594427108765,
|
|
"num_tokens": 13050502.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.388140296936035,
|
|
"epoch": 0.5934680922151687,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970712042018791,
|
|
"loss": 5.0788,
|
|
"mean_token_accuracy": 0.19840793460607528,
|
|
"num_tokens": 13059729.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.349490642547607,
|
|
"epoch": 0.5938857333778818,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004970664145365289,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.19124558120965957,
|
|
"num_tokens": 13069123.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.311074113845825,
|
|
"epoch": 0.5943033745405947,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000497061620983639,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.19660508632659912,
|
|
"num_tokens": 13077777.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.394503593444824,
|
|
"epoch": 0.5947210157033077,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004970568235432931,
|
|
"loss": 5.2301,
|
|
"mean_token_accuracy": 0.1882762148976326,
|
|
"num_tokens": 13086576.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.338584089279175,
|
|
"epoch": 0.5951386568660207,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970520222155751,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.19548357427120208,
|
|
"num_tokens": 13095166.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.3513439178466795,
|
|
"epoch": 0.5955562980287337,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004970472170005692,
|
|
"loss": 5.1278,
|
|
"mean_token_accuracy": 0.19135345816612243,
|
|
"num_tokens": 13103692.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.306836557388306,
|
|
"epoch": 0.5959739391914467,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004970424078983596,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.19749976247549056,
|
|
"num_tokens": 13111899.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.333582401275635,
|
|
"epoch": 0.5963915803541597,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004970375949090302,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.20347608178853988,
|
|
"num_tokens": 13120345.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.277674341201783,
|
|
"epoch": 0.5968092215168727,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970327780326655,
|
|
"loss": 5.0687,
|
|
"mean_token_accuracy": 0.2032480373978615,
|
|
"num_tokens": 13129035.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.328729104995728,
|
|
"epoch": 0.5972268626795857,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004970279572693498,
|
|
"loss": 5.1267,
|
|
"mean_token_accuracy": 0.1966870456933975,
|
|
"num_tokens": 13138956.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.394966554641724,
|
|
"epoch": 0.5976445038422987,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004970231326191674,
|
|
"loss": 5.1161,
|
|
"mean_token_accuracy": 0.19748767763376235,
|
|
"num_tokens": 13148605.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.325041103363037,
|
|
"epoch": 0.5980621450050116,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004970183040822029,
|
|
"loss": 5.1568,
|
|
"mean_token_accuracy": 0.18915382474660875,
|
|
"num_tokens": 13158125.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.253943204879761,
|
|
"epoch": 0.5984797861677247,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004970134716585407,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.20492862910032272,
|
|
"num_tokens": 13167404.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.31074070930481,
|
|
"epoch": 0.5988974273304377,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004970086353482654,
|
|
"loss": 5.09,
|
|
"mean_token_accuracy": 0.19220914393663407,
|
|
"num_tokens": 13176467.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.27944130897522,
|
|
"epoch": 0.5993150684931506,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004970037951514617,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.19955122619867324,
|
|
"num_tokens": 13185201.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.324817180633545,
|
|
"epoch": 0.5997327096558637,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969989510682143,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.20281673967838287,
|
|
"num_tokens": 13194871.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.3310469627380375,
|
|
"epoch": 0.6001503508185767,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004969941030986082,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.19500688463449478,
|
|
"num_tokens": 13205006.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.2916566848754885,
|
|
"epoch": 0.6005679919812896,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496989251242728,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.19780711084604263,
|
|
"num_tokens": 13214093.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.3135199546813965,
|
|
"epoch": 0.6009856331440027,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969843955006588,
|
|
"loss": 5.1028,
|
|
"mean_token_accuracy": 0.2031728908419609,
|
|
"num_tokens": 13223178.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.313259220123291,
|
|
"epoch": 0.6014032743067157,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004969795358724855,
|
|
"loss": 5.0425,
|
|
"mean_token_accuracy": 0.20272548794746398,
|
|
"num_tokens": 13232357.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.319094610214234,
|
|
"epoch": 0.6018209154694286,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004969746723582932,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.18483280539512634,
|
|
"num_tokens": 13242538.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.423026514053345,
|
|
"epoch": 0.6022385566321417,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969698049581672,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.18862584084272385,
|
|
"num_tokens": 13252410.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.386341953277588,
|
|
"epoch": 0.6026561977948547,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004969649336721924,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.19739165306091308,
|
|
"num_tokens": 13262291.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.302865266799927,
|
|
"epoch": 0.6030738389575676,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004969600585004544,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.18964814841747285,
|
|
"num_tokens": 13271952.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.385211515426636,
|
|
"epoch": 0.6034914801202806,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969551794430383,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.19001296311616897,
|
|
"num_tokens": 13281898.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.382339334487915,
|
|
"epoch": 0.6039091212829937,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004969502965000297,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19508667588233947,
|
|
"num_tokens": 13290205.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.414503002166748,
|
|
"epoch": 0.6043267624457066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000496945409671514,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.18842467069625854,
|
|
"num_tokens": 13299420.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.287105655670166,
|
|
"epoch": 0.6047444036084196,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969405189575768,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.2015368476510048,
|
|
"num_tokens": 13307931.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.3633325576782225,
|
|
"epoch": 0.6051620447711327,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004969356243583036,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.19404988288879393,
|
|
"num_tokens": 13316646.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.301310014724732,
|
|
"epoch": 0.6055796859338456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004969307258737802,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.19736787378787995,
|
|
"num_tokens": 13325564.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.317345809936524,
|
|
"epoch": 0.6059973270965586,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004969258235040921,
|
|
"loss": 5.1351,
|
|
"mean_token_accuracy": 0.19347794204950333,
|
|
"num_tokens": 13335396.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.291594123840332,
|
|
"epoch": 0.6064149682592717,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004969209172493255,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.1981159895658493,
|
|
"num_tokens": 13344124.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.24299168586731,
|
|
"epoch": 0.6068326094219846,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004969160071095661,
|
|
"loss": 4.9991,
|
|
"mean_token_accuracy": 0.20052360445261003,
|
|
"num_tokens": 13353125.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.2948503494262695,
|
|
"epoch": 0.6072502505846976,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969110930848999,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.20314514636993408,
|
|
"num_tokens": 13361388.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.345920753479004,
|
|
"epoch": 0.6076678917474106,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004969061751754129,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.18771567940711975,
|
|
"num_tokens": 13371061.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.298269557952881,
|
|
"epoch": 0.6080855329101236,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004969012533811911,
|
|
"loss": 4.975,
|
|
"mean_token_accuracy": 0.19975163042545319,
|
|
"num_tokens": 13380077.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.3957642078399655,
|
|
"epoch": 0.6085031740728366,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004968963277023208,
|
|
"loss": 5.1718,
|
|
"mean_token_accuracy": 0.191219325363636,
|
|
"num_tokens": 13390091.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.345768117904663,
|
|
"epoch": 0.6089208152355496,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004968913981388882,
|
|
"loss": 5.0108,
|
|
"mean_token_accuracy": 0.20293781608343125,
|
|
"num_tokens": 13399793.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.337620067596435,
|
|
"epoch": 0.6093384563982626,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004968864646909797,
|
|
"loss": 5.1293,
|
|
"mean_token_accuracy": 0.19611043781042098,
|
|
"num_tokens": 13408771.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.358864879608154,
|
|
"epoch": 0.6097560975609756,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968815273586814,
|
|
"loss": 5.2177,
|
|
"mean_token_accuracy": 0.18658999502658843,
|
|
"num_tokens": 13417569.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.293046569824218,
|
|
"epoch": 0.6101737387236886,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004968765861420799,
|
|
"loss": 5.0878,
|
|
"mean_token_accuracy": 0.2041165366768837,
|
|
"num_tokens": 13427296.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.432798719406128,
|
|
"epoch": 0.6105913798864016,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004968716410412617,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.18836065977811814,
|
|
"num_tokens": 13436489.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.34585132598877,
|
|
"epoch": 0.6110090210491146,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004968666920563134,
|
|
"loss": 5.1625,
|
|
"mean_token_accuracy": 0.19824957698583603,
|
|
"num_tokens": 13445783.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.379728841781616,
|
|
"epoch": 0.6114266622118276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004968617391873216,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.18964212238788605,
|
|
"num_tokens": 13454862.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.34812297821045,
|
|
"epoch": 0.6118443033745405,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968567824343729,
|
|
"loss": 5.1588,
|
|
"mean_token_accuracy": 0.19582237154245377,
|
|
"num_tokens": 13463758.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.379159736633301,
|
|
"epoch": 0.6122619445372536,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004968518217975542,
|
|
"loss": 5.168,
|
|
"mean_token_accuracy": 0.19349175840616226,
|
|
"num_tokens": 13472808.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.31771764755249,
|
|
"epoch": 0.6126795856999666,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968468572769524,
|
|
"loss": 5.0884,
|
|
"mean_token_accuracy": 0.20151603668928147,
|
|
"num_tokens": 13482550.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.357081460952759,
|
|
"epoch": 0.6130972268626795,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004968418888726543,
|
|
"loss": 5.1766,
|
|
"mean_token_accuracy": 0.19466602951288223,
|
|
"num_tokens": 13491970.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.294427967071533,
|
|
"epoch": 0.6135148680253926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004968369165847469,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.2018074259161949,
|
|
"num_tokens": 13500699.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.283569812774658,
|
|
"epoch": 0.6139325091881056,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968319404133173,
|
|
"loss": 5.0066,
|
|
"mean_token_accuracy": 0.20503169000148774,
|
|
"num_tokens": 13509108.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.259005880355835,
|
|
"epoch": 0.6143501503508185,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004968269603584525,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.20261374413967131,
|
|
"num_tokens": 13517529.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.180866336822509,
|
|
"epoch": 0.6147677915135316,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004968219764202397,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.21324941217899324,
|
|
"num_tokens": 13526379.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.391942548751831,
|
|
"epoch": 0.6151854326762446,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004968169885987663,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.18173944652080537,
|
|
"num_tokens": 13535873.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.365327215194702,
|
|
"epoch": 0.6156030738389575,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004968119968941193,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.19876305013895035,
|
|
"num_tokens": 13545514.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.251443099975586,
|
|
"epoch": 0.6160207150016705,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004968070013063866,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.1928595632314682,
|
|
"num_tokens": 13554226.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.3155303478240965,
|
|
"epoch": 0.6164383561643836,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004968020018356552,
|
|
"loss": 5.1402,
|
|
"mean_token_accuracy": 0.19376360028982162,
|
|
"num_tokens": 13563554.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.2465372562408445,
|
|
"epoch": 0.6168559973270965,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004967969984820128,
|
|
"loss": 4.9293,
|
|
"mean_token_accuracy": 0.20616493821144105,
|
|
"num_tokens": 13572128.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.3716052055358885,
|
|
"epoch": 0.6172736384898095,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004967919912455469,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.20025199204683303,
|
|
"num_tokens": 13582285.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.299549198150634,
|
|
"epoch": 0.6176912796525226,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967869801263454,
|
|
"loss": 5.0403,
|
|
"mean_token_accuracy": 0.20231725424528121,
|
|
"num_tokens": 13590969.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.357057332992554,
|
|
"epoch": 0.6181089208152355,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967819651244957,
|
|
"loss": 5.129,
|
|
"mean_token_accuracy": 0.20152340084314346,
|
|
"num_tokens": 13600523.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.311819648742675,
|
|
"epoch": 0.6185265619779485,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004967769462400857,
|
|
"loss": 5.0677,
|
|
"mean_token_accuracy": 0.20277047902345657,
|
|
"num_tokens": 13609203.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.269484519958496,
|
|
"epoch": 0.6189442031406616,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967719234732033,
|
|
"loss": 5.0979,
|
|
"mean_token_accuracy": 0.197970649600029,
|
|
"num_tokens": 13618175.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.374366664886475,
|
|
"epoch": 0.6193618443033745,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004967668968239365,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19711214452981948,
|
|
"num_tokens": 13627245.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.4815150737762455,
|
|
"epoch": 0.6197794854660875,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004967618662923732,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1910698965191841,
|
|
"num_tokens": 13636910.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.357352352142334,
|
|
"epoch": 0.6201971266288006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004967568318786016,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.20097007751464843,
|
|
"num_tokens": 13646072.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.357939100265503,
|
|
"epoch": 0.6206147677915135,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004967517935827097,
|
|
"loss": 5.1555,
|
|
"mean_token_accuracy": 0.19580046683549882,
|
|
"num_tokens": 13655823.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.315997886657715,
|
|
"epoch": 0.6210324089542265,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004967467514047856,
|
|
"loss": 5.1688,
|
|
"mean_token_accuracy": 0.19353338778018953,
|
|
"num_tokens": 13665038.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.419570684432983,
|
|
"epoch": 0.6214500501169395,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967417053449178,
|
|
"loss": 5.166,
|
|
"mean_token_accuracy": 0.19620077311992645,
|
|
"num_tokens": 13673925.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.320555591583252,
|
|
"epoch": 0.6218676912796525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967366554031945,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19400883466005325,
|
|
"num_tokens": 13682252.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.284979343414307,
|
|
"epoch": 0.6222853324423655,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004967316015797042,
|
|
"loss": 5.1,
|
|
"mean_token_accuracy": 0.19885452836751938,
|
|
"num_tokens": 13691462.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.4202024936676025,
|
|
"epoch": 0.6227029736050785,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004967265438745352,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.18782111257314682,
|
|
"num_tokens": 13701370.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.403611135482788,
|
|
"epoch": 0.6231206147677915,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004967214822877763,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.19804510921239854,
|
|
"num_tokens": 13709673.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.29628472328186,
|
|
"epoch": 0.6235382559305045,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004967164168195159,
|
|
"loss": 5.1677,
|
|
"mean_token_accuracy": 0.19853689074516295,
|
|
"num_tokens": 13719947.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.347589588165283,
|
|
"epoch": 0.6239558970932175,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004967113474698428,
|
|
"loss": 5.1844,
|
|
"mean_token_accuracy": 0.18847784399986267,
|
|
"num_tokens": 13728813.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.394614267349243,
|
|
"epoch": 0.6243735382559304,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004967062742388456,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20129719972610474,
|
|
"num_tokens": 13738319.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.198353385925293,
|
|
"epoch": 0.6247911794186435,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004967011971266132,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.19858871400356293,
|
|
"num_tokens": 13747337.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.309659767150879,
|
|
"epoch": 0.6252088205813565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004966961161332346,
|
|
"loss": 5.0157,
|
|
"mean_token_accuracy": 0.20277777165174485,
|
|
"num_tokens": 13756050.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.37460880279541,
|
|
"epoch": 0.6256264617440696,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004966910312587985,
|
|
"loss": 5.1308,
|
|
"mean_token_accuracy": 0.197844460606575,
|
|
"num_tokens": 13765297.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.3622293949127195,
|
|
"epoch": 0.6260441029067825,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004966859425033941,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.2088264837861061,
|
|
"num_tokens": 13773958.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.303714418411255,
|
|
"epoch": 0.6264617440694955,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004966808498671104,
|
|
"loss": 5.1703,
|
|
"mean_token_accuracy": 0.19533663988113403,
|
|
"num_tokens": 13784037.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.376762199401855,
|
|
"epoch": 0.6268793852322085,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004966757533500367,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.1953112006187439,
|
|
"num_tokens": 13793709.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.3261706829071045,
|
|
"epoch": 0.6272970263949215,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000496670652952262,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.21007993966341018,
|
|
"num_tokens": 13801466.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.32651948928833,
|
|
"epoch": 0.6277146675576345,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004966655486738757,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.18720995038747787,
|
|
"num_tokens": 13811903.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.433754396438599,
|
|
"epoch": 0.6281323087203475,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004966604405149672,
|
|
"loss": 5.1709,
|
|
"mean_token_accuracy": 0.20043850988149642,
|
|
"num_tokens": 13820861.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.392036819458008,
|
|
"epoch": 0.6285499498830605,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004966553284756257,
|
|
"loss": 5.2362,
|
|
"mean_token_accuracy": 0.19158738553524018,
|
|
"num_tokens": 13831049.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.354241466522216,
|
|
"epoch": 0.6289675910457735,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004966502125559411,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.19620001316070557,
|
|
"num_tokens": 13840628.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.272139596939087,
|
|
"epoch": 0.6293852322084865,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004966450927560026,
|
|
"loss": 5.0094,
|
|
"mean_token_accuracy": 0.1958682805299759,
|
|
"num_tokens": 13849424.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.258982229232788,
|
|
"epoch": 0.6298028733711994,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966399690759,
|
|
"loss": 5.0669,
|
|
"mean_token_accuracy": 0.19829782098531723,
|
|
"num_tokens": 13859216.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.403354930877685,
|
|
"epoch": 0.6302205145339125,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496634841515723,
|
|
"loss": 5.1915,
|
|
"mean_token_accuracy": 0.19932115226984023,
|
|
"num_tokens": 13867638.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.456949853897095,
|
|
"epoch": 0.6306381556966255,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004966297100755613,
|
|
"loss": 5.1996,
|
|
"mean_token_accuracy": 0.19038033336400986,
|
|
"num_tokens": 13877016.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.3104642868042,
|
|
"epoch": 0.6310557968593384,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004966245747555047,
|
|
"loss": 5.1941,
|
|
"mean_token_accuracy": 0.18951427042484284,
|
|
"num_tokens": 13887305.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.326711940765381,
|
|
"epoch": 0.6314734380220515,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004966194355556432,
|
|
"loss": 5.0338,
|
|
"mean_token_accuracy": 0.2035259947180748,
|
|
"num_tokens": 13896003.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.270294618606568,
|
|
"epoch": 0.6318910791847645,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004966142924760666,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.19187588095664979,
|
|
"num_tokens": 13904964.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.350745820999146,
|
|
"epoch": 0.6323087203474774,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004966091455168652,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.19344709813594818,
|
|
"num_tokens": 13915049.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.3415679931640625,
|
|
"epoch": 0.6327263615101905,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004966039946781289,
|
|
"loss": 5.0745,
|
|
"mean_token_accuracy": 0.20321254134178163,
|
|
"num_tokens": 13924938.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.46542592048645,
|
|
"epoch": 0.6331440026729035,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000496598839959948,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.18086140006780624,
|
|
"num_tokens": 13935050.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.379476737976074,
|
|
"epoch": 0.6335616438356164,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004965936813624126,
|
|
"loss": 5.0946,
|
|
"mean_token_accuracy": 0.20454391837120056,
|
|
"num_tokens": 13943576.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.311718225479126,
|
|
"epoch": 0.6339792849983295,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000496588518885613,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.1998242199420929,
|
|
"num_tokens": 13953232.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.4081847190856935,
|
|
"epoch": 0.6343969261610425,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004965833525296397,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18928366228938104,
|
|
"num_tokens": 13962121.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.393481349945068,
|
|
"epoch": 0.6348145673237554,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965781822945831,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.1911754310131073,
|
|
"num_tokens": 13971681.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.315832090377808,
|
|
"epoch": 0.6352322084864684,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004965730081805338,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.2094218224287033,
|
|
"num_tokens": 13980118.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.334166717529297,
|
|
"epoch": 0.6356498496491815,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004965678301875821,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.20157801359891891,
|
|
"num_tokens": 13989755.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.318079471588135,
|
|
"epoch": 0.6360674908118944,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496562648315819,
|
|
"loss": 5.0698,
|
|
"mean_token_accuracy": 0.1943339601159096,
|
|
"num_tokens": 13999289.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.3282873153686525,
|
|
"epoch": 0.6364851319746074,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496557462565335,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19684980511665345,
|
|
"num_tokens": 14009101.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.327979850769043,
|
|
"epoch": 0.6369027731373205,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004965522729362209,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.2018255189061165,
|
|
"num_tokens": 14018197.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.308821296691894,
|
|
"epoch": 0.6373204143000334,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004965470794285676,
|
|
"loss": 5.0466,
|
|
"mean_token_accuracy": 0.2008366510272026,
|
|
"num_tokens": 14028108.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.3702045440673825,
|
|
"epoch": 0.6377380554627464,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000496541882042466,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.18684548139572144,
|
|
"num_tokens": 14038636.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.353422212600708,
|
|
"epoch": 0.6381556966254595,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004965366807780071,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18714100420475005,
|
|
"num_tokens": 14048502.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.41514744758606,
|
|
"epoch": 0.6385733377881724,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004965314756352818,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.18882432579994202,
|
|
"num_tokens": 14058654.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.353787565231324,
|
|
"epoch": 0.6389909789508854,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965262666143816,
|
|
"loss": 5.0527,
|
|
"mean_token_accuracy": 0.20317932814359665,
|
|
"num_tokens": 14068614.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.292949438095093,
|
|
"epoch": 0.6394086201135984,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965210537153973,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.2023366928100586,
|
|
"num_tokens": 14077550.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.358682489395141,
|
|
"epoch": 0.6398262612763114,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004965158369384204,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.18797807693481444,
|
|
"num_tokens": 14086610.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.3093830108642575,
|
|
"epoch": 0.6402439024390244,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000496510616283542,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.19520796239376068,
|
|
"num_tokens": 14095795.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.272781753540039,
|
|
"epoch": 0.6406615436017374,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004965053917508537,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.2024879649281502,
|
|
"num_tokens": 14104779.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.340172624588012,
|
|
"epoch": 0.6410791847644504,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004965001633404469,
|
|
"loss": 4.9651,
|
|
"mean_token_accuracy": 0.20671241134405136,
|
|
"num_tokens": 14113299.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.318248844146728,
|
|
"epoch": 0.6414968259271634,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004964949310524131,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20106455981731414,
|
|
"num_tokens": 14121969.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.368939352035523,
|
|
"epoch": 0.6419144670898764,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964896948868439,
|
|
"loss": 5.0603,
|
|
"mean_token_accuracy": 0.19724276512861252,
|
|
"num_tokens": 14130850.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.350848960876465,
|
|
"epoch": 0.6423321082525894,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004964844548438311,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.19854483902454376,
|
|
"num_tokens": 14140142.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.162275314331055,
|
|
"epoch": 0.6427497494153024,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004964792109234662,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.20520005226135254,
|
|
"num_tokens": 14148335.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.367498826980591,
|
|
"epoch": 0.6431673905780154,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004964739631258411,
|
|
"loss": 5.1529,
|
|
"mean_token_accuracy": 0.18786907494068145,
|
|
"num_tokens": 14157566.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.3978753089904785,
|
|
"epoch": 0.6435850317407283,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964687114510478,
|
|
"loss": 5.1594,
|
|
"mean_token_accuracy": 0.19214931577444078,
|
|
"num_tokens": 14166037.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.302136421203613,
|
|
"epoch": 0.6440026729034414,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000496463455899178,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20371997505426406,
|
|
"num_tokens": 14174735.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.379946994781494,
|
|
"epoch": 0.6444203140661544,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004964581964703239,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19014421999454498,
|
|
"num_tokens": 14185130.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.438870763778686,
|
|
"epoch": 0.6448379552288673,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004964529331645776,
|
|
"loss": 5.1591,
|
|
"mean_token_accuracy": 0.1921945184469223,
|
|
"num_tokens": 14194676.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.372873687744141,
|
|
"epoch": 0.6452555963915804,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000496447665982031,
|
|
"loss": 5.132,
|
|
"mean_token_accuracy": 0.19571897983551026,
|
|
"num_tokens": 14204218.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.264962291717529,
|
|
"epoch": 0.6456732375542934,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964423949227765,
|
|
"loss": 5.167,
|
|
"mean_token_accuracy": 0.1954248696565628,
|
|
"num_tokens": 14213176.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.371309280395508,
|
|
"epoch": 0.6460908787170063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004964371199869062,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.193475341796875,
|
|
"num_tokens": 14222490.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.364813280105591,
|
|
"epoch": 0.6465085198797194,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004964318411745127,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1889796882867813,
|
|
"num_tokens": 14231335.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.377953100204468,
|
|
"epoch": 0.6469261610424324,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004964265584856883,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.19608911573886872,
|
|
"num_tokens": 14240583.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.430382823944091,
|
|
"epoch": 0.6473438022051453,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004964212719205254,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.1984202280640602,
|
|
"num_tokens": 14250087.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.395354986190796,
|
|
"epoch": 0.6477614433678583,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004964159814791167,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.18818021863698958,
|
|
"num_tokens": 14261076.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.3157330513000485,
|
|
"epoch": 0.6481790845305714,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004964106871615547,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.2005872830748558,
|
|
"num_tokens": 14270234.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.2813966274261475,
|
|
"epoch": 0.6485967256932843,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000496405388967932,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.1967516139149666,
|
|
"num_tokens": 14279154.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.312413454055786,
|
|
"epoch": 0.6490143668559973,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004964000868983416,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.19537826180458068,
|
|
"num_tokens": 14289626.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.304482364654541,
|
|
"epoch": 0.6494320080187104,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004963947809528761,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.20509156435728074,
|
|
"num_tokens": 14299647.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.430705785751343,
|
|
"epoch": 0.6498496491814233,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963894711316285,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18813633769750596,
|
|
"num_tokens": 14308944.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.372679138183594,
|
|
"epoch": 0.6502672903441363,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.19386800080537797,
|
|
"num_tokens": 14318168.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.326407337188721,
|
|
"epoch": 0.6506849315068494,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004963788398621587,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20723003000020981,
|
|
"num_tokens": 14327249.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.316002655029297,
|
|
"epoch": 0.6511025726695623,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004963735184141227,
|
|
"loss": 5.1099,
|
|
"mean_token_accuracy": 0.1961625933647156,
|
|
"num_tokens": 14336055.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.294028282165527,
|
|
"epoch": 0.6515202138322753,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004963681930906768,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.2043228343129158,
|
|
"num_tokens": 14344862.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.431717872619629,
|
|
"epoch": 0.6519378549949884,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004963628638919141,
|
|
"loss": 5.2721,
|
|
"mean_token_accuracy": 0.1862041935324669,
|
|
"num_tokens": 14354284.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.37448558807373,
|
|
"epoch": 0.6523554961577013,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004963575308179281,
|
|
"loss": 5.0978,
|
|
"mean_token_accuracy": 0.19853051155805587,
|
|
"num_tokens": 14363615.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.324336338043213,
|
|
"epoch": 0.6527731373204143,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004963521938688122,
|
|
"loss": 5.0446,
|
|
"mean_token_accuracy": 0.19110076427459716,
|
|
"num_tokens": 14372805.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.346999025344848,
|
|
"epoch": 0.6531907784831273,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004963468530446596,
|
|
"loss": 5.1459,
|
|
"mean_token_accuracy": 0.19429202228784562,
|
|
"num_tokens": 14382334.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.38353853225708,
|
|
"epoch": 0.6536084196458403,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004963415083455639,
|
|
"loss": 5.0901,
|
|
"mean_token_accuracy": 0.1968158721923828,
|
|
"num_tokens": 14391360.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.4134129047393795,
|
|
"epoch": 0.6540260608085533,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004963361597716186,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.18921163976192473,
|
|
"num_tokens": 14401232.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.4066259384155275,
|
|
"epoch": 0.6544437019712663,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004963308073229175,
|
|
"loss": 5.1209,
|
|
"mean_token_accuracy": 0.19198620170354844,
|
|
"num_tokens": 14409773.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.351168966293335,
|
|
"epoch": 0.6548613431339793,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004963254509995542,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19272187501192092,
|
|
"num_tokens": 14419511.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.312403964996338,
|
|
"epoch": 0.6552789842966923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004963200908016224,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.19612731635570527,
|
|
"num_tokens": 14428611.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.261601066589355,
|
|
"epoch": 0.6556966254594053,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496314726729216,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.20782947838306426,
|
|
"num_tokens": 14436721.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.343482589721679,
|
|
"epoch": 0.6561142666221182,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004963093587824289,
|
|
"loss": 5.1393,
|
|
"mean_token_accuracy": 0.1950383886694908,
|
|
"num_tokens": 14445766.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.208344841003418,
|
|
"epoch": 0.6565319077848313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004963039869613551,
|
|
"loss": 5.0105,
|
|
"mean_token_accuracy": 0.19755252897739412,
|
|
"num_tokens": 14453857.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.26979923248291,
|
|
"epoch": 0.6569495489475443,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004962986112660887,
|
|
"loss": 5.152,
|
|
"mean_token_accuracy": 0.1985751837491989,
|
|
"num_tokens": 14462356.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.339071416854859,
|
|
"epoch": 0.6573671901102572,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004962932316967237,
|
|
"loss": 5.0637,
|
|
"mean_token_accuracy": 0.2032722756266594,
|
|
"num_tokens": 14471848.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.294857120513916,
|
|
"epoch": 0.6577848312729703,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004962878482533544,
|
|
"loss": 5.1159,
|
|
"mean_token_accuracy": 0.19989920854568483,
|
|
"num_tokens": 14481128.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.296504545211792,
|
|
"epoch": 0.6582024724356833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004962824609360748,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.20626104176044463,
|
|
"num_tokens": 14490071.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.406992387771607,
|
|
"epoch": 0.6586201135983962,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962770697449794,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.19094453752040863,
|
|
"num_tokens": 14499162.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.343120908737182,
|
|
"epoch": 0.6590377547611093,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004962716746801625,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.19562383443117143,
|
|
"num_tokens": 14508525.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.342346143722534,
|
|
"epoch": 0.6594553959238223,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962662757417187,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20063686966896058,
|
|
"num_tokens": 14516885.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.298411321640015,
|
|
"epoch": 0.6598730370865352,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004962608729297424,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.20002715289592743,
|
|
"num_tokens": 14525116.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.290652847290039,
|
|
"epoch": 0.6602906782492483,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004962554662443281,
|
|
"loss": 5.1654,
|
|
"mean_token_accuracy": 0.20551083385944366,
|
|
"num_tokens": 14534452.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.30949444770813,
|
|
"epoch": 0.6607083194119613,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004962500556855706,
|
|
"loss": 5.0337,
|
|
"mean_token_accuracy": 0.20393030643463134,
|
|
"num_tokens": 14544040.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.41433801651001,
|
|
"epoch": 0.6611259605746742,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004962446412535645,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.19545911699533464,
|
|
"num_tokens": 14553343.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.338744258880615,
|
|
"epoch": 0.6615436017373872,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004962392229484046,
|
|
"loss": 5.0806,
|
|
"mean_token_accuracy": 0.20066311508417128,
|
|
"num_tokens": 14562657.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.306552171707153,
|
|
"epoch": 0.6619612429001003,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000496233800770186,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.20089496970176696,
|
|
"num_tokens": 14572167.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.306908464431762,
|
|
"epoch": 0.6623788840628132,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004962283747190033,
|
|
"loss": 5.0757,
|
|
"mean_token_accuracy": 0.19629357010126114,
|
|
"num_tokens": 14580934.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.300098562240601,
|
|
"epoch": 0.6627965252255262,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004962229447949515,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.2060925304889679,
|
|
"num_tokens": 14589579.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.387610197067261,
|
|
"epoch": 0.6632141663882393,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004962175109981259,
|
|
"loss": 5.1396,
|
|
"mean_token_accuracy": 0.19479325115680696,
|
|
"num_tokens": 14599289.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.351546382904052,
|
|
"epoch": 0.6636318075509522,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004962120733286215,
|
|
"loss": 5.0977,
|
|
"mean_token_accuracy": 0.20407487004995345,
|
|
"num_tokens": 14608322.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.334446716308594,
|
|
"epoch": 0.6640494487136652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004962066317865334,
|
|
"loss": 5.1145,
|
|
"mean_token_accuracy": 0.20266272574663163,
|
|
"num_tokens": 14617591.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.289065504074097,
|
|
"epoch": 0.6644670898763783,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000496201186371957,
|
|
"loss": 5.0594,
|
|
"mean_token_accuracy": 0.19937008172273635,
|
|
"num_tokens": 14625809.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.39598331451416,
|
|
"epoch": 0.6648847310390912,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004961957370849875,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.1908267319202423,
|
|
"num_tokens": 14635061.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.31296935081482,
|
|
"epoch": 0.6653023722018042,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004961902839257205,
|
|
"loss": 5.1758,
|
|
"mean_token_accuracy": 0.1925966426730156,
|
|
"num_tokens": 14645104.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.3807408809661865,
|
|
"epoch": 0.6657200133645172,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004961848268942513,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.19549504071474075,
|
|
"num_tokens": 14653984.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.339137125015259,
|
|
"epoch": 0.6661376545272302,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004961793659906754,
|
|
"loss": 5.1066,
|
|
"mean_token_accuracy": 0.19128828048706054,
|
|
"num_tokens": 14663315.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.291628837585449,
|
|
"epoch": 0.6665552956899432,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004961739012150885,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.19822268635034562,
|
|
"num_tokens": 14672608.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.366587400436401,
|
|
"epoch": 0.6669729368526562,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004961684325675862,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.20482892394065857,
|
|
"num_tokens": 14682031.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.324712896347046,
|
|
"epoch": 0.6673905780153692,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004961629600482643,
|
|
"loss": 5.1401,
|
|
"mean_token_accuracy": 0.19599850922822953,
|
|
"num_tokens": 14691894.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.299334716796875,
|
|
"epoch": 0.6678082191780822,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004961574836572186,
|
|
"loss": 5.0919,
|
|
"mean_token_accuracy": 0.19348276257514954,
|
|
"num_tokens": 14700508.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.4263256072998045,
|
|
"epoch": 0.6682258603407952,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961520033945448,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19804321080446244,
|
|
"num_tokens": 14709241.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.433790922164917,
|
|
"epoch": 0.6686435015035082,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004961465192603391,
|
|
"loss": 5.1433,
|
|
"mean_token_accuracy": 0.19273824989795685,
|
|
"num_tokens": 14719300.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.404751873016357,
|
|
"epoch": 0.6690611426662212,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961410312546974,
|
|
"loss": 5.1904,
|
|
"mean_token_accuracy": 0.20090636610984802,
|
|
"num_tokens": 14729717.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.379194641113282,
|
|
"epoch": 0.6694787838289342,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004961355393777158,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.2006773829460144,
|
|
"num_tokens": 14738757.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.160495090484619,
|
|
"epoch": 0.6698964249916471,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004961300436294902,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.20169602036476136,
|
|
"num_tokens": 14747171.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.247114276885986,
|
|
"epoch": 0.6703140661543602,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004961245440101171,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.19286514371633529,
|
|
"num_tokens": 14756064.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.409082841873169,
|
|
"epoch": 0.6707317073170732,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004961190405196928,
|
|
"loss": 5.0287,
|
|
"mean_token_accuracy": 0.20715447813272475,
|
|
"num_tokens": 14765156.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.414972352981567,
|
|
"epoch": 0.6711493484797861,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004961135331583135,
|
|
"loss": 5.1106,
|
|
"mean_token_accuracy": 0.20417901426553725,
|
|
"num_tokens": 14774059.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.253400278091431,
|
|
"epoch": 0.6715669896424992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004961080219260755,
|
|
"loss": 5.0153,
|
|
"mean_token_accuracy": 0.20877986401319504,
|
|
"num_tokens": 14783500.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.350839900970459,
|
|
"epoch": 0.6719846308052122,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004961025068230757,
|
|
"loss": 5.137,
|
|
"mean_token_accuracy": 0.19133350551128386,
|
|
"num_tokens": 14792901.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.37168779373169,
|
|
"epoch": 0.6724022719679251,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960969878494103,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.19221657067537307,
|
|
"num_tokens": 14801619.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.277453231811523,
|
|
"epoch": 0.6728199131306382,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960914650051758,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.1990262433886528,
|
|
"num_tokens": 14811128.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.317573738098145,
|
|
"epoch": 0.6732375542933512,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004960859382904691,
|
|
"loss": 5.1228,
|
|
"mean_token_accuracy": 0.1939890444278717,
|
|
"num_tokens": 14819772.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.313987350463867,
|
|
"epoch": 0.6736551954560641,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000496080407705387,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.2040141701698303,
|
|
"num_tokens": 14828139.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.330444955825806,
|
|
"epoch": 0.6740728366187771,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004960748732500263,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.19583479315042496,
|
|
"num_tokens": 14837121.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.3272114276885985,
|
|
"epoch": 0.6744904777814902,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004960693349244838,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.19898477494716643,
|
|
"num_tokens": 14845973.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.338535165786743,
|
|
"epoch": 0.6749081189442031,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004960637927288566,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.19188700169324874,
|
|
"num_tokens": 14856072.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.297983646392822,
|
|
"epoch": 0.6753257601069161,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004960582466632414,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.20269555002450942,
|
|
"num_tokens": 14864845.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.368402290344238,
|
|
"epoch": 0.6757434012696292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004960526967277356,
|
|
"loss": 5.081,
|
|
"mean_token_accuracy": 0.20204036682844162,
|
|
"num_tokens": 14874170.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.339005422592163,
|
|
"epoch": 0.6761610424323421,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004960471429224363,
|
|
"loss": 5.0102,
|
|
"mean_token_accuracy": 0.2044421300292015,
|
|
"num_tokens": 14882618.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.336379814147949,
|
|
"epoch": 0.6765786835950551,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960415852474406,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.19564032107591628,
|
|
"num_tokens": 14893258.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.3359650611877445,
|
|
"epoch": 0.6769963247577682,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000496036023702846,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.1839256390929222,
|
|
"num_tokens": 14904424.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.393545436859131,
|
|
"epoch": 0.6774139659204811,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004960304582887497,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.18990901708602906,
|
|
"num_tokens": 14913935.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.25920729637146,
|
|
"epoch": 0.6778316070831941,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004960248890052493,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.20592834651470185,
|
|
"num_tokens": 14923352.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.280186748504638,
|
|
"epoch": 0.6782492482459072,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000496019315852442,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.20654631406068802,
|
|
"num_tokens": 14932080.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.302289962768555,
|
|
"epoch": 0.6786668894086201,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004960137388304255,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.19200025945901872,
|
|
"num_tokens": 14939747.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.302951192855835,
|
|
"epoch": 0.6790845305713331,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004960081579392975,
|
|
"loss": 5.1234,
|
|
"mean_token_accuracy": 0.1983903869986534,
|
|
"num_tokens": 14948639.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.366544437408447,
|
|
"epoch": 0.6795021717340461,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004960025731791558,
|
|
"loss": 5.07,
|
|
"mean_token_accuracy": 0.2011776402592659,
|
|
"num_tokens": 14957831.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.4015264987945555,
|
|
"epoch": 0.6799198128967591,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004959969845500979,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.18743169903755189,
|
|
"num_tokens": 14968732.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.303138732910156,
|
|
"epoch": 0.6803374540594721,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004959913920522218,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.202997125685215,
|
|
"num_tokens": 14978684.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.540664577484131,
|
|
"epoch": 0.6807550952221851,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004959857956856254,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.19166718423366547,
|
|
"num_tokens": 14988036.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.362942552566528,
|
|
"epoch": 0.6811727363848981,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004959801954504067,
|
|
"loss": 5.0679,
|
|
"mean_token_accuracy": 0.2075038433074951,
|
|
"num_tokens": 14996773.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.297462224960327,
|
|
"epoch": 0.6815903775476111,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004959745913466635,
|
|
"loss": 5.1378,
|
|
"mean_token_accuracy": 0.1957137554883957,
|
|
"num_tokens": 15005552.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.3333393096923825,
|
|
"epoch": 0.6820080187103241,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004959689833744942,
|
|
"loss": 5.0566,
|
|
"mean_token_accuracy": 0.20576381534337998,
|
|
"num_tokens": 15014026.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.382020044326782,
|
|
"epoch": 0.682425659873037,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004959633715339969,
|
|
"loss": 5.1301,
|
|
"mean_token_accuracy": 0.19739755094051362,
|
|
"num_tokens": 15023607.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.34213080406189,
|
|
"epoch": 0.6828433010357501,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004959577558252698,
|
|
"loss": 5.1131,
|
|
"mean_token_accuracy": 0.19693882018327713,
|
|
"num_tokens": 15033102.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.309530210494995,
|
|
"epoch": 0.6832609421984631,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004959521362484112,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.19837612509727479,
|
|
"num_tokens": 15042506.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.2551594257354735,
|
|
"epoch": 0.683678583361176,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004959465128035195,
|
|
"loss": 5.0483,
|
|
"mean_token_accuracy": 0.20119027942419052,
|
|
"num_tokens": 15052483.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.342989110946656,
|
|
"epoch": 0.6840962245238891,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004959408854906932,
|
|
"loss": 5.0465,
|
|
"mean_token_accuracy": 0.20539987534284593,
|
|
"num_tokens": 15060769.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.419846057891846,
|
|
"epoch": 0.6845138656866021,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959352543100306,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.19296460449695588,
|
|
"num_tokens": 15070398.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.338227844238281,
|
|
"epoch": 0.684931506849315,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004959296192616305,
|
|
"loss": 5.2056,
|
|
"mean_token_accuracy": 0.19881249219179153,
|
|
"num_tokens": 15079939.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.381723165512085,
|
|
"epoch": 0.6853491480120281,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004959239803455916,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.2024775892496109,
|
|
"num_tokens": 15089391.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.278679370880127,
|
|
"epoch": 0.6857667891747411,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004959183375620123,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.19703567326068877,
|
|
"num_tokens": 15098875.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.336717414855957,
|
|
"epoch": 0.686184430337454,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004959126909109918,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.19052750319242479,
|
|
"num_tokens": 15108359.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.388481855392456,
|
|
"epoch": 0.686602071500167,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004959070403926286,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.1880239501595497,
|
|
"num_tokens": 15117957.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.372163963317871,
|
|
"epoch": 0.6870197126628801,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004959013860070217,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.20073024034500123,
|
|
"num_tokens": 15127913.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.383512878417969,
|
|
"epoch": 0.687437353825593,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004958957277542701,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.19352732747793197,
|
|
"num_tokens": 15137588.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.337337779998779,
|
|
"epoch": 0.687854994988306,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004958900656344731,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.19708040058612825,
|
|
"num_tokens": 15146147.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.286891460418701,
|
|
"epoch": 0.6882726361510191,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004958843996477296,
|
|
"loss": 5.0524,
|
|
"mean_token_accuracy": 0.20437600314617158,
|
|
"num_tokens": 15156448.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.33973798751831,
|
|
"epoch": 0.688690277313732,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004958787297941386,
|
|
"loss": 5.0549,
|
|
"mean_token_accuracy": 0.20773497372865676,
|
|
"num_tokens": 15165447.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.349364185333252,
|
|
"epoch": 0.689107918476445,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004958730560737998,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20047943890094758,
|
|
"num_tokens": 15175046.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.3166008472442625,
|
|
"epoch": 0.6895255596391581,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004958673784868121,
|
|
"loss": 5.0368,
|
|
"mean_token_accuracy": 0.1975402981042862,
|
|
"num_tokens": 15184142.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.266688299179077,
|
|
"epoch": 0.689943200801871,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004958616970332752,
|
|
"loss": 5.0567,
|
|
"mean_token_accuracy": 0.19528615474700928,
|
|
"num_tokens": 15194101.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.3019262790679935,
|
|
"epoch": 0.690360841964584,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958560117132884,
|
|
"loss": 5.0525,
|
|
"mean_token_accuracy": 0.19740259051322936,
|
|
"num_tokens": 15203083.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.367357587814331,
|
|
"epoch": 0.6907784831272971,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004958503225269513,
|
|
"loss": 5.0674,
|
|
"mean_token_accuracy": 0.2002798467874527,
|
|
"num_tokens": 15210957.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.38237829208374,
|
|
"epoch": 0.69119612429001,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958446294743633,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.19218998402357101,
|
|
"num_tokens": 15219144.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.324297523498535,
|
|
"epoch": 0.691613765452723,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958389325556245,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.1977696806192398,
|
|
"num_tokens": 15227633.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.375818824768066,
|
|
"epoch": 0.692031406615436,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004958332317708341,
|
|
"loss": 5.0801,
|
|
"mean_token_accuracy": 0.20032769143581391,
|
|
"num_tokens": 15235673.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.285147666931152,
|
|
"epoch": 0.692449047778149,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004958275271200924,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.2006660982966423,
|
|
"num_tokens": 15245164.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.253752183914185,
|
|
"epoch": 0.692866688940862,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004958218186034988,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.1984976813197136,
|
|
"num_tokens": 15254654.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.308433866500854,
|
|
"epoch": 0.693284330103575,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004958161062211537,
|
|
"loss": 4.9598,
|
|
"mean_token_accuracy": 0.20424797236919404,
|
|
"num_tokens": 15264042.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.3810821056365965,
|
|
"epoch": 0.693701971266288,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004958103899731566,
|
|
"loss": 5.2496,
|
|
"mean_token_accuracy": 0.1898939147591591,
|
|
"num_tokens": 15273215.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.337585878372193,
|
|
"epoch": 0.694119612429001,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004958046698596081,
|
|
"loss": 5.0106,
|
|
"mean_token_accuracy": 0.1990499749779701,
|
|
"num_tokens": 15281441.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.368911170959473,
|
|
"epoch": 0.694537253591714,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004957989458806079,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.19374166280031205,
|
|
"num_tokens": 15290967.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.3219091415405275,
|
|
"epoch": 0.694954894754427,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004957932180362564,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.19824674874544143,
|
|
"num_tokens": 15301332.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.395729112625122,
|
|
"epoch": 0.69537253591714,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004957874863266538,
|
|
"loss": 5.1233,
|
|
"mean_token_accuracy": 0.2019718274474144,
|
|
"num_tokens": 15309547.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.4256011009216305,
|
|
"epoch": 0.695790177079853,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004957817507519006,
|
|
"loss": 5.1599,
|
|
"mean_token_accuracy": 0.1930350750684738,
|
|
"num_tokens": 15318841.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.398059320449829,
|
|
"epoch": 0.696207818242566,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004957760113120971,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.1951725348830223,
|
|
"num_tokens": 15327893.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.273368263244629,
|
|
"epoch": 0.696625459405279,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004957702680073437,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.20006659477949143,
|
|
"num_tokens": 15336320.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.321401119232178,
|
|
"epoch": 0.697043100567992,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004957645208377411,
|
|
"loss": 5.1249,
|
|
"mean_token_accuracy": 0.1987346738576889,
|
|
"num_tokens": 15346002.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.292619514465332,
|
|
"epoch": 0.6974607417307049,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004957587698033898,
|
|
"loss": 5.062,
|
|
"mean_token_accuracy": 0.1989813193678856,
|
|
"num_tokens": 15355670.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.291586446762085,
|
|
"epoch": 0.697878382893418,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004957530149043905,
|
|
"loss": 5.0008,
|
|
"mean_token_accuracy": 0.20562281906604768,
|
|
"num_tokens": 15364207.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.276925897598266,
|
|
"epoch": 0.698296024056131,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004957472561408438,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.20109020918607712,
|
|
"num_tokens": 15373021.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.301882743835449,
|
|
"epoch": 0.6987136652188439,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004957414935128509,
|
|
"loss": 5.0908,
|
|
"mean_token_accuracy": 0.20604297369718552,
|
|
"num_tokens": 15382023.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.257896900177002,
|
|
"epoch": 0.699131306381557,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004957357270205123,
|
|
"loss": 5.0054,
|
|
"mean_token_accuracy": 0.20505329221487045,
|
|
"num_tokens": 15390829.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.361479187011719,
|
|
"epoch": 0.69954894754427,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004957299566639292,
|
|
"loss": 5.0755,
|
|
"mean_token_accuracy": 0.1926500529050827,
|
|
"num_tokens": 15400415.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.291661596298217,
|
|
"epoch": 0.6999665887069829,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957241824432025,
|
|
"loss": 5.1142,
|
|
"mean_token_accuracy": 0.20200859755277634,
|
|
"num_tokens": 15408839.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.26589183807373,
|
|
"epoch": 0.700384229869696,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004957184043584333,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.20620953887701035,
|
|
"num_tokens": 15416989.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.233847808837891,
|
|
"epoch": 0.700801871032409,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004957126224097227,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20701220780611038,
|
|
"num_tokens": 15425404.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.2213235855102536,
|
|
"epoch": 0.7012195121951219,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000495706836597172,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.21381697803735733,
|
|
"num_tokens": 15433672.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.2221287250518795,
|
|
"epoch": 0.7016371533578349,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004957010469208825,
|
|
"loss": 5.0289,
|
|
"mean_token_accuracy": 0.2010230988264084,
|
|
"num_tokens": 15442345.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.312219476699829,
|
|
"epoch": 0.702054794520548,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004956952533809554,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.20898640006780625,
|
|
"num_tokens": 15451891.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.392408037185669,
|
|
"epoch": 0.7024724356832609,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004956894559774923,
|
|
"loss": 5.131,
|
|
"mean_token_accuracy": 0.19439685493707656,
|
|
"num_tokens": 15462192.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.357154607772827,
|
|
"epoch": 0.7028900768459739,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004956836547105947,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.19382841289043426,
|
|
"num_tokens": 15471723.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.34092378616333,
|
|
"epoch": 0.703307718008687,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004956778495803641,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.20461504757404328,
|
|
"num_tokens": 15479621.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.350914239883423,
|
|
"epoch": 0.7037253591713999,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000495672040586902,
|
|
"loss": 5.0853,
|
|
"mean_token_accuracy": 0.20011101216077803,
|
|
"num_tokens": 15489180.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.258227586746216,
|
|
"epoch": 0.7041430003341129,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004956662277303103,
|
|
"loss": 5.0424,
|
|
"mean_token_accuracy": 0.20534710288047792,
|
|
"num_tokens": 15498155.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.441788864135742,
|
|
"epoch": 0.704560641496826,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004956604110106905,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.1984770879149437,
|
|
"num_tokens": 15507944.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.29026780128479,
|
|
"epoch": 0.7049782826595389,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004956545904281447,
|
|
"loss": 5.1069,
|
|
"mean_token_accuracy": 0.1954318568110466,
|
|
"num_tokens": 15516800.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.3028112888336185,
|
|
"epoch": 0.7053959238222519,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004956487659827748,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.1971202999353409,
|
|
"num_tokens": 15525824.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.334076070785523,
|
|
"epoch": 0.705813564984965,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004956429376746825,
|
|
"loss": 5.0762,
|
|
"mean_token_accuracy": 0.20262415558099747,
|
|
"num_tokens": 15534954.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.266501331329346,
|
|
"epoch": 0.7062312061476779,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004956371055039701,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.2070791408419609,
|
|
"num_tokens": 15543439.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.30676007270813,
|
|
"epoch": 0.7066488473103909,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004956312694707395,
|
|
"loss": 5.0125,
|
|
"mean_token_accuracy": 0.2009556323289871,
|
|
"num_tokens": 15552768.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.37309455871582,
|
|
"epoch": 0.7070664884731039,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000495625429575093,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.19696727842092515,
|
|
"num_tokens": 15562193.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.312422847747802,
|
|
"epoch": 0.7074841296358169,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956195858171327,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.20370602011680602,
|
|
"num_tokens": 15571403.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.281801366806031,
|
|
"epoch": 0.7079017707985299,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004956137381969611,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.20224549174308776,
|
|
"num_tokens": 15580477.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.280908727645874,
|
|
"epoch": 0.7083194119612429,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004956078867146805,
|
|
"loss": 5.1202,
|
|
"mean_token_accuracy": 0.20028530657291413,
|
|
"num_tokens": 15590106.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.394092607498169,
|
|
"epoch": 0.7087370531239559,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004956020313703933,
|
|
"loss": 5.1055,
|
|
"mean_token_accuracy": 0.19786422401666642,
|
|
"num_tokens": 15598939.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.3496955871582035,
|
|
"epoch": 0.7091546942866689,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955961721642018,
|
|
"loss": 5.0606,
|
|
"mean_token_accuracy": 0.19913401156663896,
|
|
"num_tokens": 15607439.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.244808340072632,
|
|
"epoch": 0.7095723354493819,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000495590309096209,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.20154862105846405,
|
|
"num_tokens": 15616887.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.2764912128448485,
|
|
"epoch": 0.7099899766120948,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004955844421665171,
|
|
"loss": 5.0356,
|
|
"mean_token_accuracy": 0.20259701162576677,
|
|
"num_tokens": 15626399.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.260780668258667,
|
|
"epoch": 0.7104076177748079,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004955785713752292,
|
|
"loss": 5.074,
|
|
"mean_token_accuracy": 0.20007085502147676,
|
|
"num_tokens": 15635719.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.319685697555542,
|
|
"epoch": 0.7108252589375209,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004955726967224479,
|
|
"loss": 5.0475,
|
|
"mean_token_accuracy": 0.20726848840713502,
|
|
"num_tokens": 15644504.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.277904796600342,
|
|
"epoch": 0.7112429001002338,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000495566818208276,
|
|
"loss": 5.0003,
|
|
"mean_token_accuracy": 0.20440294444561005,
|
|
"num_tokens": 15653842.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.293590545654297,
|
|
"epoch": 0.7116605412629469,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004955609358328163,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.1918836146593094,
|
|
"num_tokens": 15664235.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.333241891860962,
|
|
"epoch": 0.7120781824256599,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955550495961722,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.20445387065410614,
|
|
"num_tokens": 15673113.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.3686319351196286,
|
|
"epoch": 0.7124958235883728,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004955491594984462,
|
|
"loss": 5.116,
|
|
"mean_token_accuracy": 0.19903599768877028,
|
|
"num_tokens": 15682609.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.256578207015991,
|
|
"epoch": 0.7129134647510859,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004955432655397419,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19227395504713057,
|
|
"num_tokens": 15691414.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.3290627002716064,
|
|
"epoch": 0.7133311059137989,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004955373677201621,
|
|
"loss": 5.0676,
|
|
"mean_token_accuracy": 0.20009913742542268,
|
|
"num_tokens": 15700690.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.308279657363892,
|
|
"epoch": 0.7137487470765118,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004955314660398105,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.20043952465057374,
|
|
"num_tokens": 15710110.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.322026920318604,
|
|
"epoch": 0.7141663882392248,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004955255604987899,
|
|
"loss": 5.0336,
|
|
"mean_token_accuracy": 0.19411475956439972,
|
|
"num_tokens": 15719182.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.317400312423706,
|
|
"epoch": 0.7145840294019379,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495519651097204,
|
|
"loss": 5.0732,
|
|
"mean_token_accuracy": 0.2080293208360672,
|
|
"num_tokens": 15729045.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.288547134399414,
|
|
"epoch": 0.7150016705646508,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004955137378351561,
|
|
"loss": 5.0581,
|
|
"mean_token_accuracy": 0.20035295188426971,
|
|
"num_tokens": 15738312.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.2256094455719,
|
|
"epoch": 0.7154193117273638,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004955078207127498,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.1990751177072525,
|
|
"num_tokens": 15747852.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.342038154602051,
|
|
"epoch": 0.7158369528900769,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004955018997300886,
|
|
"loss": 5.0771,
|
|
"mean_token_accuracy": 0.19786131531000137,
|
|
"num_tokens": 15757593.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.328027820587158,
|
|
"epoch": 0.7162545940527898,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004954959748872764,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.2041265606880188,
|
|
"num_tokens": 15767740.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.290323162078858,
|
|
"epoch": 0.7166722352155028,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954900461844167,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.21241872161626815,
|
|
"num_tokens": 15776306.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.259528541564942,
|
|
"epoch": 0.7170898763782159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004954841136216132,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.20325778871774675,
|
|
"num_tokens": 15784674.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.368355178833008,
|
|
"epoch": 0.7175075175409288,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954781771989701,
|
|
"loss": 5.0535,
|
|
"mean_token_accuracy": 0.19906822293996812,
|
|
"num_tokens": 15794262.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.328971195220947,
|
|
"epoch": 0.7179251587036418,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.000495472236916591,
|
|
"loss": 5.1221,
|
|
"mean_token_accuracy": 0.1943685680627823,
|
|
"num_tokens": 15805853.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.285169887542724,
|
|
"epoch": 0.7183427998663549,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954662927745799,
|
|
"loss": 5.0972,
|
|
"mean_token_accuracy": 0.20210544019937515,
|
|
"num_tokens": 15815426.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.319616794586182,
|
|
"epoch": 0.7187604410290678,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004954603447730411,
|
|
"loss": 5.0754,
|
|
"mean_token_accuracy": 0.1994279369711876,
|
|
"num_tokens": 15825121.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.306467533111572,
|
|
"epoch": 0.7191780821917808,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004954543929120786,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.2056216225028038,
|
|
"num_tokens": 15834649.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.238444805145264,
|
|
"epoch": 0.7195957233544938,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954484371917967,
|
|
"loss": 5.0835,
|
|
"mean_token_accuracy": 0.19457235485315322,
|
|
"num_tokens": 15844583.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.291723251342773,
|
|
"epoch": 0.7200133645172068,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954424776122993,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.20075231790542603,
|
|
"num_tokens": 15853169.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.299955654144287,
|
|
"epoch": 0.7204310056799198,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004954365141736913,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.20153999477624893,
|
|
"num_tokens": 15862139.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.421988391876221,
|
|
"epoch": 0.7208486468426328,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004954305468760765,
|
|
"loss": 5.1398,
|
|
"mean_token_accuracy": 0.1914064422249794,
|
|
"num_tokens": 15871415.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.25295729637146,
|
|
"epoch": 0.7212662880053458,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004954245757195598,
|
|
"loss": 4.9547,
|
|
"mean_token_accuracy": 0.2131354257464409,
|
|
"num_tokens": 15880581.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.270177364349365,
|
|
"epoch": 0.7216839291680588,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004954186007042454,
|
|
"loss": 5.0285,
|
|
"mean_token_accuracy": 0.20069338530302047,
|
|
"num_tokens": 15889142.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.263737487792969,
|
|
"epoch": 0.7221015703307718,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004954126218302382,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.207366181910038,
|
|
"num_tokens": 15898058.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.2450182914733885,
|
|
"epoch": 0.7225192114934847,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004954066390976427,
|
|
"loss": 4.9611,
|
|
"mean_token_accuracy": 0.20488033145666124,
|
|
"num_tokens": 15907196.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.2933323860168455,
|
|
"epoch": 0.7229368526561978,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004954006525065639,
|
|
"loss": 5.0257,
|
|
"mean_token_accuracy": 0.20379539132118224,
|
|
"num_tokens": 15916291.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.309026575088501,
|
|
"epoch": 0.7233544938189108,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004953946620571061,
|
|
"loss": 5.0267,
|
|
"mean_token_accuracy": 0.19797522127628325,
|
|
"num_tokens": 15924846.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.20244665145874,
|
|
"epoch": 0.7237721349816237,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004953886677493746,
|
|
"loss": 4.9993,
|
|
"mean_token_accuracy": 0.2082879737019539,
|
|
"num_tokens": 15934406.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.315201759338379,
|
|
"epoch": 0.7241897761443368,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004953826695834741,
|
|
"loss": 5.0095,
|
|
"mean_token_accuracy": 0.20294035524129866,
|
|
"num_tokens": 15943481.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.408049058914185,
|
|
"epoch": 0.7246074173070498,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953766675595098,
|
|
"loss": 5.16,
|
|
"mean_token_accuracy": 0.19902303963899612,
|
|
"num_tokens": 15952787.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.271516370773315,
|
|
"epoch": 0.7250250584697627,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004953706616775866,
|
|
"loss": 5.089,
|
|
"mean_token_accuracy": 0.19395713806152343,
|
|
"num_tokens": 15962295.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.3628943920135494,
|
|
"epoch": 0.7254426996324758,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004953646519378097,
|
|
"loss": 5.2168,
|
|
"mean_token_accuracy": 0.20312317460775375,
|
|
"num_tokens": 15971367.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.233772420883179,
|
|
"epoch": 0.7258603407951888,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004953586383402844,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.2040407955646515,
|
|
"num_tokens": 15981535.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.309322690963745,
|
|
"epoch": 0.7262779819579017,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004953526208851157,
|
|
"loss": 5.1434,
|
|
"mean_token_accuracy": 0.19534515589475632,
|
|
"num_tokens": 15991067.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.26609058380127,
|
|
"epoch": 0.7266956231206148,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004953465995724092,
|
|
"loss": 4.9459,
|
|
"mean_token_accuracy": 0.2124885931611061,
|
|
"num_tokens": 15999310.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.244246482849121,
|
|
"epoch": 0.7271132642833278,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004953405744022705,
|
|
"loss": 4.9689,
|
|
"mean_token_accuracy": 0.1995558962225914,
|
|
"num_tokens": 16008574.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.287505388259888,
|
|
"epoch": 0.7275309054460407,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953345453748045,
|
|
"loss": 5.0259,
|
|
"mean_token_accuracy": 0.20503512322902678,
|
|
"num_tokens": 16017208.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.357419490814209,
|
|
"epoch": 0.7279485466087537,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004953285124901171,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.19681234508752823,
|
|
"num_tokens": 16027009.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.3083242893219,
|
|
"epoch": 0.7283661877714668,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000495322475748314,
|
|
"loss": 5.0184,
|
|
"mean_token_accuracy": 0.20988769233226776,
|
|
"num_tokens": 16035019.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.2568888664245605,
|
|
"epoch": 0.7287838289341797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004953164351495007,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.2123623177409172,
|
|
"num_tokens": 16044373.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.292593002319336,
|
|
"epoch": 0.7292014700968927,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004953103906937831,
|
|
"loss": 5.0473,
|
|
"mean_token_accuracy": 0.20019331574440002,
|
|
"num_tokens": 16052888.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.2805887222290036,
|
|
"epoch": 0.7296191112596058,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004953043423812669,
|
|
"loss": 5.0159,
|
|
"mean_token_accuracy": 0.20051151067018508,
|
|
"num_tokens": 16062137.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.329266881942749,
|
|
"epoch": 0.7300367524223187,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004952982902120579,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.1829935371875763,
|
|
"num_tokens": 16072755.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.3109759330749515,
|
|
"epoch": 0.7304543935850317,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004952922341862622,
|
|
"loss": 5.0781,
|
|
"mean_token_accuracy": 0.1956650897860527,
|
|
"num_tokens": 16081069.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.355233144760132,
|
|
"epoch": 0.7308720347477448,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952861743039858,
|
|
"loss": 5.1024,
|
|
"mean_token_accuracy": 0.20134016871452332,
|
|
"num_tokens": 16089938.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.252851676940918,
|
|
"epoch": 0.7312896759104577,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004952801105653347,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.2069542333483696,
|
|
"num_tokens": 16099395.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.250736808776855,
|
|
"epoch": 0.7317073170731707,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004952740429704152,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.21120189130306244,
|
|
"num_tokens": 16108196.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.327375268936157,
|
|
"epoch": 0.7321249582358837,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004952679715193334,
|
|
"loss": 5.0731,
|
|
"mean_token_accuracy": 0.20398153811693193,
|
|
"num_tokens": 16118059.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.3151367664337155,
|
|
"epoch": 0.7325425993985967,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004952618962121956,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20365259945392608,
|
|
"num_tokens": 16126981.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.249662256240844,
|
|
"epoch": 0.7329602405613097,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004952558170491082,
|
|
"loss": 4.9817,
|
|
"mean_token_accuracy": 0.21323874592781067,
|
|
"num_tokens": 16136164.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.330404901504517,
|
|
"epoch": 0.7333778817240227,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952497340301776,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.1954864650964737,
|
|
"num_tokens": 16145739.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.3741007328033445,
|
|
"epoch": 0.7337955228867357,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004952436471555103,
|
|
"loss": 5.0783,
|
|
"mean_token_accuracy": 0.19891777485609055,
|
|
"num_tokens": 16155092.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.229849004745484,
|
|
"epoch": 0.7342131640494487,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004952375564252128,
|
|
"loss": 4.9645,
|
|
"mean_token_accuracy": 0.2107301875948906,
|
|
"num_tokens": 16162994.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.260258340835572,
|
|
"epoch": 0.7346308052121617,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004952314618393919,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.20456575602293015,
|
|
"num_tokens": 16171286.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.285358095169068,
|
|
"epoch": 0.7350484463748747,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000495225363398154,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.1976119711995125,
|
|
"num_tokens": 16180459.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.322805547714234,
|
|
"epoch": 0.7354660875375877,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004952192611016061,
|
|
"loss": 5.0854,
|
|
"mean_token_accuracy": 0.20227680802345277,
|
|
"num_tokens": 16190103.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.328626108169556,
|
|
"epoch": 0.7358837287003007,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000495213154949855,
|
|
"loss": 5.0227,
|
|
"mean_token_accuracy": 0.19959045797586442,
|
|
"num_tokens": 16199499.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.262804746627808,
|
|
"epoch": 0.7363013698630136,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004952070449430075,
|
|
"loss": 5.092,
|
|
"mean_token_accuracy": 0.19372017979621886,
|
|
"num_tokens": 16209589.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.222028541564941,
|
|
"epoch": 0.7367190110257267,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004952009310811706,
|
|
"loss": 4.9435,
|
|
"mean_token_accuracy": 0.20576345324516296,
|
|
"num_tokens": 16218499.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.240480899810791,
|
|
"epoch": 0.7371366521884397,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951948133644514,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.21034753173589707,
|
|
"num_tokens": 16227183.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.297750949859619,
|
|
"epoch": 0.7375542933511526,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000495188691792957,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.2009079486131668,
|
|
"num_tokens": 16236573.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.318086242675781,
|
|
"epoch": 0.7379719345138657,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004951825663667943,
|
|
"loss": 5.0294,
|
|
"mean_token_accuracy": 0.20320519655942917,
|
|
"num_tokens": 16246399.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.293214130401611,
|
|
"epoch": 0.7383895756765787,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000495176437086071,
|
|
"loss": 5.0999,
|
|
"mean_token_accuracy": 0.19551804214715957,
|
|
"num_tokens": 16254964.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.3588892936706545,
|
|
"epoch": 0.7388072168392917,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000495170303950894,
|
|
"loss": 5.1136,
|
|
"mean_token_accuracy": 0.2047969341278076,
|
|
"num_tokens": 16263579.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.375021457672119,
|
|
"epoch": 0.7392248580020047,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004951641669613708,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19406411647796631,
|
|
"num_tokens": 16273000.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.339499664306641,
|
|
"epoch": 0.7396424991647177,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004951580261176088,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.20513754487037658,
|
|
"num_tokens": 16282582.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.276492881774902,
|
|
"epoch": 0.7400601403274307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004951518814197156,
|
|
"loss": 4.989,
|
|
"mean_token_accuracy": 0.20123317688703538,
|
|
"num_tokens": 16291153.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.238758754730225,
|
|
"epoch": 0.7404777814901436,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004951457328677989,
|
|
"loss": 5.0333,
|
|
"mean_token_accuracy": 0.20677470713853835,
|
|
"num_tokens": 16300527.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.261174201965332,
|
|
"epoch": 0.7408954226528567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004951395804619659,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.21674227565526963,
|
|
"num_tokens": 16309111.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.386971473693848,
|
|
"epoch": 0.7413130638155697,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004951334242023247,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19671186804771423,
|
|
"num_tokens": 16318409.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.30442180633545,
|
|
"epoch": 0.7417307049782826,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004951272640889828,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20902032107114793,
|
|
"num_tokens": 16327950.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.327867126464843,
|
|
"epoch": 0.7421483461409957,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004951211001220484,
|
|
"loss": 5.0932,
|
|
"mean_token_accuracy": 0.1947564512491226,
|
|
"num_tokens": 16336776.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.330788564682007,
|
|
"epoch": 0.7425659873037087,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000495114932301629,
|
|
"loss": 5.0973,
|
|
"mean_token_accuracy": 0.20303537249565123,
|
|
"num_tokens": 16346206.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.281230020523071,
|
|
"epoch": 0.7429836284664216,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004951087606278328,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.20319949090480804,
|
|
"num_tokens": 16355163.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.327037143707275,
|
|
"epoch": 0.7434012696291347,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004951025851007678,
|
|
"loss": 5.0909,
|
|
"mean_token_accuracy": 0.19471413791179656,
|
|
"num_tokens": 16364028.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.3012348175048825,
|
|
"epoch": 0.7438189107918477,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950964057205421,
|
|
"loss": 5.0179,
|
|
"mean_token_accuracy": 0.19897612780332566,
|
|
"num_tokens": 16373669.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.3665741920471195,
|
|
"epoch": 0.7442365519545606,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000495090222487264,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.19930920898914337,
|
|
"num_tokens": 16383246.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.32965579032898,
|
|
"epoch": 0.7446541931172737,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004950840354010415,
|
|
"loss": 5.1316,
|
|
"mean_token_accuracy": 0.19587484747171402,
|
|
"num_tokens": 16393589.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.268144273757935,
|
|
"epoch": 0.7450718342799867,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004950778444619831,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.19518257230520247,
|
|
"num_tokens": 16402734.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.376037168502807,
|
|
"epoch": 0.7454894754426996,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000495071649670197,
|
|
"loss": 5.1598,
|
|
"mean_token_accuracy": 0.19054750055074693,
|
|
"num_tokens": 16412317.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.322746133804321,
|
|
"epoch": 0.7459071166054126,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000495065451025792,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.20200826078653336,
|
|
"num_tokens": 16421472.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.2680981159210205,
|
|
"epoch": 0.7463247577681257,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004950592485288761,
|
|
"loss": 4.9969,
|
|
"mean_token_accuracy": 0.20153672248125076,
|
|
"num_tokens": 16430694.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.332237768173218,
|
|
"epoch": 0.7467423989308386,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950530421795584,
|
|
"loss": 5.1832,
|
|
"mean_token_accuracy": 0.19030925035476684,
|
|
"num_tokens": 16440250.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.28470630645752,
|
|
"epoch": 0.7471600400935516,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004950468319779472,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.20592001080513,
|
|
"num_tokens": 16449294.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.481476163864135,
|
|
"epoch": 0.7475776812562647,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004950406179241515,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18400996774435044,
|
|
"num_tokens": 16459614.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.376629734039307,
|
|
"epoch": 0.7479953224189776,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004950344000182798,
|
|
"loss": 5.1312,
|
|
"mean_token_accuracy": 0.19200930148363113,
|
|
"num_tokens": 16469175.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.250803518295288,
|
|
"epoch": 0.7484129635816906,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004950281782604411,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.20726359337568284,
|
|
"num_tokens": 16477818.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.3442065715789795,
|
|
"epoch": 0.7488306047444037,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004950219526507442,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.20067232251167297,
|
|
"num_tokens": 16487807.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.24239501953125,
|
|
"epoch": 0.7492482459071166,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004950157231892983,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.20650298446416854,
|
|
"num_tokens": 16497924.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.310427856445313,
|
|
"epoch": 0.7496658870698296,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004950094898762123,
|
|
"loss": 5.0689,
|
|
"mean_token_accuracy": 0.19899906665086747,
|
|
"num_tokens": 16508069.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.367056941986084,
|
|
"epoch": 0.7500835282325427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950032527115954,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.1984042629599571,
|
|
"num_tokens": 16517226.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.288536071777344,
|
|
"epoch": 0.7505011693952556,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004949970116955566,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.1917812705039978,
|
|
"num_tokens": 16526997.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.315144824981689,
|
|
"epoch": 0.7509188105579686,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004949907668282054,
|
|
"loss": 5.006,
|
|
"mean_token_accuracy": 0.2027788445353508,
|
|
"num_tokens": 16536772.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.232349443435669,
|
|
"epoch": 0.7513364517206816,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000494984518109651,
|
|
"loss": 4.9227,
|
|
"mean_token_accuracy": 0.21390523612499238,
|
|
"num_tokens": 16544901.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.2355247974395756,
|
|
"epoch": 0.7517540928833946,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004949782655400028,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.21016237437725066,
|
|
"num_tokens": 16553628.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7517540928833946,
|
|
"eval_entropy": 5.042980490385337,
|
|
"eval_loss": 5.0131916999816895,
|
|
"eval_mean_token_accuracy": 0.21371608528450015,
|
|
"eval_num_tokens": 16553628.0,
|
|
"eval_runtime": 45.5808,
|
|
"eval_samples_per_second": 828.484,
|
|
"eval_steps_per_second": 103.574,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.328627681732177,
|
|
"epoch": 0.7521717340461076,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949720091193704,
|
|
"loss": 5.085,
|
|
"mean_token_accuracy": 0.20136228054761887,
|
|
"num_tokens": 16561619.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.275867986679077,
|
|
"epoch": 0.7525893752088206,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000494965748847863,
|
|
"loss": 5.0715,
|
|
"mean_token_accuracy": 0.20350001901388168,
|
|
"num_tokens": 16571316.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.3689199924469,
|
|
"epoch": 0.7530070163715336,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004949594847255905,
|
|
"loss": 5.1521,
|
|
"mean_token_accuracy": 0.20123015493154525,
|
|
"num_tokens": 16582014.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.273039674758911,
|
|
"epoch": 0.7534246575342466,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004949532167526625,
|
|
"loss": 5.0376,
|
|
"mean_token_accuracy": 0.20891620516777037,
|
|
"num_tokens": 16590179.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.300007343292236,
|
|
"epoch": 0.7538422986969596,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004949469449291886,
|
|
"loss": 4.9501,
|
|
"mean_token_accuracy": 0.2107928514480591,
|
|
"num_tokens": 16598732.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.335094785690307,
|
|
"epoch": 0.7542599398596725,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004949406692552787,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.19825499653816223,
|
|
"num_tokens": 16608844.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.325690031051636,
|
|
"epoch": 0.7546775810223856,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004949343897310426,
|
|
"loss": 5.0883,
|
|
"mean_token_accuracy": 0.20014682561159133,
|
|
"num_tokens": 16618969.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.3566525936126705,
|
|
"epoch": 0.7550952221850986,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004949281063565904,
|
|
"loss": 5.1053,
|
|
"mean_token_accuracy": 0.19824974089860917,
|
|
"num_tokens": 16629081.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.228001308441162,
|
|
"epoch": 0.7555128633478115,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004949218191320319,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.21619396805763244,
|
|
"num_tokens": 16637588.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.304362392425537,
|
|
"epoch": 0.7559305045105246,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004949155280574772,
|
|
"loss": 5.0654,
|
|
"mean_token_accuracy": 0.19863190352916718,
|
|
"num_tokens": 16647763.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.231770944595337,
|
|
"epoch": 0.7563481456732376,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004949092331330365,
|
|
"loss": 4.9834,
|
|
"mean_token_accuracy": 0.2045108810067177,
|
|
"num_tokens": 16657208.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.300762367248535,
|
|
"epoch": 0.7567657868359505,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049490293435882,
|
|
"loss": 4.945,
|
|
"mean_token_accuracy": 0.2033146858215332,
|
|
"num_tokens": 16666375.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.316979932785034,
|
|
"epoch": 0.7571834279986636,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004948966317349379,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.20570386499166488,
|
|
"num_tokens": 16674847.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.2400044918060305,
|
|
"epoch": 0.7576010691613766,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004948903252615006,
|
|
"loss": 5.1073,
|
|
"mean_token_accuracy": 0.19229450225830078,
|
|
"num_tokens": 16684828.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.348769283294677,
|
|
"epoch": 0.7580187103240895,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004948840149386184,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.19501926600933076,
|
|
"num_tokens": 16694151.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.411171913146973,
|
|
"epoch": 0.7584363514868026,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000494877700766402,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.1986489087343216,
|
|
"num_tokens": 16703584.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.272515439987183,
|
|
"epoch": 0.7588539926495156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004948713827449616,
|
|
"loss": 5.0088,
|
|
"mean_token_accuracy": 0.20575342327356339,
|
|
"num_tokens": 16712593.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.243364429473877,
|
|
"epoch": 0.7592716338122285,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004948650608744081,
|
|
"loss": 4.9875,
|
|
"mean_token_accuracy": 0.19874690026044844,
|
|
"num_tokens": 16721848.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.301230573654175,
|
|
"epoch": 0.7596892749749415,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000494858735154852,
|
|
"loss": 5.0778,
|
|
"mean_token_accuracy": 0.20661334544420243,
|
|
"num_tokens": 16730465.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.342642879486084,
|
|
"epoch": 0.7601069161376546,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948524055864041,
|
|
"loss": 5.0575,
|
|
"mean_token_accuracy": 0.1983390912413597,
|
|
"num_tokens": 16739518.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.373666191101075,
|
|
"epoch": 0.7605245573003675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004948460721691752,
|
|
"loss": 5.1387,
|
|
"mean_token_accuracy": 0.19277205914258957,
|
|
"num_tokens": 16749332.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.326131820678711,
|
|
"epoch": 0.7609421984630805,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004948397349032762,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.21733313500881196,
|
|
"num_tokens": 16757621.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.256700658798218,
|
|
"epoch": 0.7613598396257936,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000494833393788818,
|
|
"loss": 4.9866,
|
|
"mean_token_accuracy": 0.20941648334264756,
|
|
"num_tokens": 16766382.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.233947658538819,
|
|
"epoch": 0.7617774807885065,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004948270488259117,
|
|
"loss": 4.9936,
|
|
"mean_token_accuracy": 0.20447325855493545,
|
|
"num_tokens": 16774962.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.278624200820923,
|
|
"epoch": 0.7621951219512195,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004948207000146682,
|
|
"loss": 4.9935,
|
|
"mean_token_accuracy": 0.2010357826948166,
|
|
"num_tokens": 16784246.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.265715503692627,
|
|
"epoch": 0.7626127631139326,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004948143473551989,
|
|
"loss": 5.0895,
|
|
"mean_token_accuracy": 0.19274531900882722,
|
|
"num_tokens": 16793396.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.337631273269653,
|
|
"epoch": 0.7630304042766455,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004948079908476147,
|
|
"loss": 5.0359,
|
|
"mean_token_accuracy": 0.2026448056101799,
|
|
"num_tokens": 16801837.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.4140543937683105,
|
|
"epoch": 0.7634480454393585,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004948016304920271,
|
|
"loss": 5.082,
|
|
"mean_token_accuracy": 0.20373877733945847,
|
|
"num_tokens": 16810332.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.275704765319825,
|
|
"epoch": 0.7638656866020715,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004947952662885473,
|
|
"loss": 5.0373,
|
|
"mean_token_accuracy": 0.20458294749259948,
|
|
"num_tokens": 16820278.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.207873153686523,
|
|
"epoch": 0.7642833277647845,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494788898237287,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.20767840296030043,
|
|
"num_tokens": 16828907.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.269165945053101,
|
|
"epoch": 0.7647009689274975,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004947825263383573,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.19670089483261108,
|
|
"num_tokens": 16838579.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.249943780899048,
|
|
"epoch": 0.7651186100902105,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00049477615059187,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.20545322597026824,
|
|
"num_tokens": 16847143.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.3339742660522464,
|
|
"epoch": 0.7655362512529235,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004947697709979367,
|
|
"loss": 4.9987,
|
|
"mean_token_accuracy": 0.20467438846826552,
|
|
"num_tokens": 16855989.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.339896965026855,
|
|
"epoch": 0.7659538924156365,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004947633875566688,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.1983796015381813,
|
|
"num_tokens": 16864701.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.351294136047363,
|
|
"epoch": 0.7663715335783495,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004947570002681785,
|
|
"loss": 5.1031,
|
|
"mean_token_accuracy": 0.19619534462690352,
|
|
"num_tokens": 16875032.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.336219120025635,
|
|
"epoch": 0.7667891747410625,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004947506091325772,
|
|
"loss": 5.1507,
|
|
"mean_token_accuracy": 0.19627355188131332,
|
|
"num_tokens": 16884590.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.279163885116577,
|
|
"epoch": 0.7672068159037755,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004947442141499771,
|
|
"loss": 4.9763,
|
|
"mean_token_accuracy": 0.20216863304376603,
|
|
"num_tokens": 16894257.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.329294347763062,
|
|
"epoch": 0.7676244570664885,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004947378153204899,
|
|
"loss": 5.1035,
|
|
"mean_token_accuracy": 0.20266560316085816,
|
|
"num_tokens": 16904049.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.261391973495483,
|
|
"epoch": 0.7680420982292014,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004947314126442279,
|
|
"loss": 4.9923,
|
|
"mean_token_accuracy": 0.2057476595044136,
|
|
"num_tokens": 16913147.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.258284664154052,
|
|
"epoch": 0.7684597393919145,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000494725006121303,
|
|
"loss": 5.0251,
|
|
"mean_token_accuracy": 0.19961391985416413,
|
|
"num_tokens": 16922142.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.313911437988281,
|
|
"epoch": 0.7688773805546275,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004947185957518273,
|
|
"loss": 5.0719,
|
|
"mean_token_accuracy": 0.20551112294197083,
|
|
"num_tokens": 16931069.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.2711810111999515,
|
|
"epoch": 0.7692950217173404,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004947121815359133,
|
|
"loss": 5.1345,
|
|
"mean_token_accuracy": 0.20068963915109633,
|
|
"num_tokens": 16940172.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.318318605422974,
|
|
"epoch": 0.7697126628800535,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004947057634736729,
|
|
"loss": 5.1519,
|
|
"mean_token_accuracy": 0.19864448457956313,
|
|
"num_tokens": 16951097.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.405415344238281,
|
|
"epoch": 0.7701303040427665,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004946993415652186,
|
|
"loss": 5.072,
|
|
"mean_token_accuracy": 0.1988403931260109,
|
|
"num_tokens": 16960764.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.263200807571411,
|
|
"epoch": 0.7705479452054794,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494692915810663,
|
|
"loss": 5.1129,
|
|
"mean_token_accuracy": 0.20223597437143326,
|
|
"num_tokens": 16969842.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.289483737945557,
|
|
"epoch": 0.7709655863681925,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946864862101185,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.21281166076660157,
|
|
"num_tokens": 16979070.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.163484859466553,
|
|
"epoch": 0.7713832275309055,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004946800527636975,
|
|
"loss": 4.9519,
|
|
"mean_token_accuracy": 0.2051929846405983,
|
|
"num_tokens": 16988126.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.188770818710327,
|
|
"epoch": 0.7718008686936184,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004946736154715129,
|
|
"loss": 4.9665,
|
|
"mean_token_accuracy": 0.20784328728914261,
|
|
"num_tokens": 16997085.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.314389944076538,
|
|
"epoch": 0.7722185098563314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004946671743336771,
|
|
"loss": 5.0484,
|
|
"mean_token_accuracy": 0.20061145722866058,
|
|
"num_tokens": 17005678.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.364008665084839,
|
|
"epoch": 0.7726361510190445,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004946607293503031,
|
|
"loss": 4.9632,
|
|
"mean_token_accuracy": 0.20176951438188553,
|
|
"num_tokens": 17015081.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.2835992813110355,
|
|
"epoch": 0.7730537921817574,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004946542805215036,
|
|
"loss": 5.0517,
|
|
"mean_token_accuracy": 0.20822138488292694,
|
|
"num_tokens": 17024036.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.311074066162109,
|
|
"epoch": 0.7734714333444704,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004946478278473914,
|
|
"loss": 5.0149,
|
|
"mean_token_accuracy": 0.20927557945251465,
|
|
"num_tokens": 17032120.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.311744022369385,
|
|
"epoch": 0.7738890745071835,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004946413713280797,
|
|
"loss": 5.0145,
|
|
"mean_token_accuracy": 0.20164657086133958,
|
|
"num_tokens": 17041487.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.273798084259033,
|
|
"epoch": 0.7743067156698964,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004946349109636814,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.1993025615811348,
|
|
"num_tokens": 17050793.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.3039326667785645,
|
|
"epoch": 0.7747243568326094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004946284467543096,
|
|
"loss": 5.0084,
|
|
"mean_token_accuracy": 0.20892512202262878,
|
|
"num_tokens": 17059536.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.320153331756591,
|
|
"epoch": 0.7751419979953225,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004946219787000776,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.20443508625030518,
|
|
"num_tokens": 17069075.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.293126201629638,
|
|
"epoch": 0.7755596391580354,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004946155068010984,
|
|
"loss": 5.0516,
|
|
"mean_token_accuracy": 0.20636919736862183,
|
|
"num_tokens": 17079020.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.26950969696045,
|
|
"epoch": 0.7759772803207484,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004946090310574854,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.2017408311367035,
|
|
"num_tokens": 17087905.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.278450965881348,
|
|
"epoch": 0.7763949214834615,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004946025514693519,
|
|
"loss": 5.0393,
|
|
"mean_token_accuracy": 0.20421561896800994,
|
|
"num_tokens": 17097932.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.279170083999634,
|
|
"epoch": 0.7768125626461744,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004945960680368115,
|
|
"loss": 5.0236,
|
|
"mean_token_accuracy": 0.20093638002872466,
|
|
"num_tokens": 17107125.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.340269947052002,
|
|
"epoch": 0.7772302038088874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004945895807599775,
|
|
"loss": 5.0528,
|
|
"mean_token_accuracy": 0.19782705008983612,
|
|
"num_tokens": 17116575.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.283654308319091,
|
|
"epoch": 0.7776478449716004,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945830896389636,
|
|
"loss": 4.9725,
|
|
"mean_token_accuracy": 0.21084398478269578,
|
|
"num_tokens": 17125422.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.2341485023498535,
|
|
"epoch": 0.7780654861343134,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004945765946738835,
|
|
"loss": 4.9446,
|
|
"mean_token_accuracy": 0.20786211639642715,
|
|
"num_tokens": 17134323.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.20372428894043,
|
|
"epoch": 0.7784831272970264,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004945700958648507,
|
|
"loss": 4.9488,
|
|
"mean_token_accuracy": 0.2108437016606331,
|
|
"num_tokens": 17143179.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.260954999923706,
|
|
"epoch": 0.7789007684597394,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000494563593211979,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20529664307832718,
|
|
"num_tokens": 17152498.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.292381858825683,
|
|
"epoch": 0.7793184096224524,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004945570867153826,
|
|
"loss": 5.0414,
|
|
"mean_token_accuracy": 0.19694066494703294,
|
|
"num_tokens": 17161689.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.322631740570069,
|
|
"epoch": 0.7797360507851654,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004945505763751749,
|
|
"loss": 5.0481,
|
|
"mean_token_accuracy": 0.2006200760602951,
|
|
"num_tokens": 17170291.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.323950529098511,
|
|
"epoch": 0.7801536919478784,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004945440621914702,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.20223954170942307,
|
|
"num_tokens": 17179712.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.283712434768677,
|
|
"epoch": 0.7805713331105913,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945375441643823,
|
|
"loss": 5.0681,
|
|
"mean_token_accuracy": 0.20636019706726075,
|
|
"num_tokens": 17188224.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.345323705673218,
|
|
"epoch": 0.7809889742733044,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004945310222940254,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2045991227030754,
|
|
"num_tokens": 17197868.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.326085758209229,
|
|
"epoch": 0.7814066154360174,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004945244965805138,
|
|
"loss": 5.0263,
|
|
"mean_token_accuracy": 0.20145805180072784,
|
|
"num_tokens": 17207576.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.248692512512207,
|
|
"epoch": 0.7818242565987303,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004945179670239616,
|
|
"loss": 5.0343,
|
|
"mean_token_accuracy": 0.20002631545066835,
|
|
"num_tokens": 17217508.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.386681270599365,
|
|
"epoch": 0.7822418977614434,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004945114336244832,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.19634187072515488,
|
|
"num_tokens": 17227890.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.369872093200684,
|
|
"epoch": 0.7826595389241564,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000494504896382193,
|
|
"loss": 5.0279,
|
|
"mean_token_accuracy": 0.2058451294898987,
|
|
"num_tokens": 17237038.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.289510917663574,
|
|
"epoch": 0.7830771800868693,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004944983552972053,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.19624403715133668,
|
|
"num_tokens": 17247653.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.302428817749023,
|
|
"epoch": 0.7834948212495824,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944918103696347,
|
|
"loss": 5.1212,
|
|
"mean_token_accuracy": 0.19456664621829986,
|
|
"num_tokens": 17257183.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.350917005538941,
|
|
"epoch": 0.7839124624122954,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004944852615995956,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.19733911156654357,
|
|
"num_tokens": 17266315.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.3644421100616455,
|
|
"epoch": 0.7843301035750083,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000494478708987203,
|
|
"loss": 5.0847,
|
|
"mean_token_accuracy": 0.1959547221660614,
|
|
"num_tokens": 17275829.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.398329448699951,
|
|
"epoch": 0.7847477447377214,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004944721525325713,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.18853181898593901,
|
|
"num_tokens": 17285986.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.274197912216186,
|
|
"epoch": 0.7851653859004344,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004944655922358154,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.20977804213762283,
|
|
"num_tokens": 17294314.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.239909934997558,
|
|
"epoch": 0.7855830270631473,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944590280970503,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.20857228338718414,
|
|
"num_tokens": 17303437.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.348685026168823,
|
|
"epoch": 0.7860006682258603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004944524601163905,
|
|
"loss": 5.08,
|
|
"mean_token_accuracy": 0.19719846844673156,
|
|
"num_tokens": 17313230.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.309378576278687,
|
|
"epoch": 0.7864183093885734,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004944458882939513,
|
|
"loss": 5.0316,
|
|
"mean_token_accuracy": 0.1990100160241127,
|
|
"num_tokens": 17323468.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.212638711929321,
|
|
"epoch": 0.7868359505512863,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004944393126298478,
|
|
"loss": 4.9252,
|
|
"mean_token_accuracy": 0.20892719328403472,
|
|
"num_tokens": 17332481.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.361672210693359,
|
|
"epoch": 0.7872535917139993,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000494432733124195,
|
|
"loss": 5.0214,
|
|
"mean_token_accuracy": 0.20264473408460618,
|
|
"num_tokens": 17341550.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.290366840362549,
|
|
"epoch": 0.7876712328767124,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000494426149777108,
|
|
"loss": 4.9859,
|
|
"mean_token_accuracy": 0.20967596024274826,
|
|
"num_tokens": 17350404.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.26309118270874,
|
|
"epoch": 0.7880888740394253,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494419562588702,
|
|
"loss": 4.9863,
|
|
"mean_token_accuracy": 0.20126352459192276,
|
|
"num_tokens": 17360198.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.335349988937378,
|
|
"epoch": 0.7885065152021383,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004944129715590927,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.20855500400066376,
|
|
"num_tokens": 17369681.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.248564863204956,
|
|
"epoch": 0.7889241563648514,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000494406376688395,
|
|
"loss": 4.996,
|
|
"mean_token_accuracy": 0.2115302413702011,
|
|
"num_tokens": 17378695.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.293895292282104,
|
|
"epoch": 0.7893417975275643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943997779767248,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.1902354344725609,
|
|
"num_tokens": 17388161.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.343603515625,
|
|
"epoch": 0.7897594386902773,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004943931754241972,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.1994435429573059,
|
|
"num_tokens": 17397082.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.286892509460449,
|
|
"epoch": 0.7901770798529903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000494386569030928,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.20848157554864882,
|
|
"num_tokens": 17405842.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.297520685195923,
|
|
"epoch": 0.7905947210157033,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004943799587970328,
|
|
"loss": 5.0714,
|
|
"mean_token_accuracy": 0.19690555930137635,
|
|
"num_tokens": 17414639.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.253600645065307,
|
|
"epoch": 0.7910123621784163,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004943733447226275,
|
|
"loss": 5.0558,
|
|
"mean_token_accuracy": 0.2077075019478798,
|
|
"num_tokens": 17423923.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.198218917846679,
|
|
"epoch": 0.7914300033411293,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004943667268078277,
|
|
"loss": 4.9103,
|
|
"mean_token_accuracy": 0.2168076142668724,
|
|
"num_tokens": 17432309.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.322853755950928,
|
|
"epoch": 0.7918476445038423,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943601050527493,
|
|
"loss": 5.0926,
|
|
"mean_token_accuracy": 0.1972428724169731,
|
|
"num_tokens": 17441728.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.367465972900391,
|
|
"epoch": 0.7922652856665553,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004943534794575081,
|
|
"loss": 5.1049,
|
|
"mean_token_accuracy": 0.19958454072475434,
|
|
"num_tokens": 17451168.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.383996105194091,
|
|
"epoch": 0.7926829268292683,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004943468500222203,
|
|
"loss": 5.1179,
|
|
"mean_token_accuracy": 0.20060024857521058,
|
|
"num_tokens": 17461179.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.308714151382446,
|
|
"epoch": 0.7931005679919813,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004943402167470019,
|
|
"loss": 4.9997,
|
|
"mean_token_accuracy": 0.20039448291063308,
|
|
"num_tokens": 17469710.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.269232273101807,
|
|
"epoch": 0.7935182091546943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000494333579631969,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.20108631551265715,
|
|
"num_tokens": 17479482.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.121825313568115,
|
|
"epoch": 0.7939358503174073,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004943269386772376,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.21769867539405824,
|
|
"num_tokens": 17488458.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.365880870819092,
|
|
"epoch": 0.7943534914801202,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004943202938829243,
|
|
"loss": 5.0536,
|
|
"mean_token_accuracy": 0.2024788439273834,
|
|
"num_tokens": 17497817.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.264668750762939,
|
|
"epoch": 0.7947711326428333,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004943136452491452,
|
|
"loss": 4.9462,
|
|
"mean_token_accuracy": 0.20621895045042038,
|
|
"num_tokens": 17506020.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.277979326248169,
|
|
"epoch": 0.7951887738055463,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004943069927760168,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.19332547187805177,
|
|
"num_tokens": 17515113.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.343518877029419,
|
|
"epoch": 0.7956064149682592,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004943003364636554,
|
|
"loss": 5.0326,
|
|
"mean_token_accuracy": 0.20723738074302672,
|
|
"num_tokens": 17523473.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.339873266220093,
|
|
"epoch": 0.7960240561309723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942936763121777,
|
|
"loss": 5.0521,
|
|
"mean_token_accuracy": 0.19817662239074707,
|
|
"num_tokens": 17532985.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.2334998607635494,
|
|
"epoch": 0.7964416972936853,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004942870123217002,
|
|
"loss": 5.0081,
|
|
"mean_token_accuracy": 0.20495658814907075,
|
|
"num_tokens": 17541859.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.275954341888427,
|
|
"epoch": 0.7968593384563982,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004942803444923398,
|
|
"loss": 5.0107,
|
|
"mean_token_accuracy": 0.20691990107297897,
|
|
"num_tokens": 17550263.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.35688853263855,
|
|
"epoch": 0.7972769796191113,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942736728242127,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.2087086781859398,
|
|
"num_tokens": 17560028.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.323987722396851,
|
|
"epoch": 0.7976946207818243,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004942669973174363,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.2048540383577347,
|
|
"num_tokens": 17569082.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.2496294498443605,
|
|
"epoch": 0.7981122619445372,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000494260317972127,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.206503427028656,
|
|
"num_tokens": 17577589.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.180022144317627,
|
|
"epoch": 0.7985299031072502,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942536347884019,
|
|
"loss": 4.8421,
|
|
"mean_token_accuracy": 0.2192721277475357,
|
|
"num_tokens": 17586066.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.194910621643066,
|
|
"epoch": 0.7989475442699633,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942469477663782,
|
|
"loss": 4.8678,
|
|
"mean_token_accuracy": 0.21410966217517852,
|
|
"num_tokens": 17594328.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.339822101593017,
|
|
"epoch": 0.7993651854326762,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004942402569061726,
|
|
"loss": 5.0879,
|
|
"mean_token_accuracy": 0.20207907855510712,
|
|
"num_tokens": 17603719.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.403347110748291,
|
|
"epoch": 0.7997828265953892,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004942335622079025,
|
|
"loss": 5.1397,
|
|
"mean_token_accuracy": 0.19575755745172502,
|
|
"num_tokens": 17613306.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.2789653778076175,
|
|
"epoch": 0.8002004677581023,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942268636716848,
|
|
"loss": 4.9967,
|
|
"mean_token_accuracy": 0.20045470893383027,
|
|
"num_tokens": 17622756.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.224092292785644,
|
|
"epoch": 0.8006181089208152,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004942201612976372,
|
|
"loss": 5.0171,
|
|
"mean_token_accuracy": 0.21207732409238816,
|
|
"num_tokens": 17632157.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.263051986694336,
|
|
"epoch": 0.8010357500835282,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004942134550858767,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.2130012959241867,
|
|
"num_tokens": 17641706.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.288396835327148,
|
|
"epoch": 0.8014533912462413,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004942067450365208,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.2000431939959526,
|
|
"num_tokens": 17651572.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.308429479598999,
|
|
"epoch": 0.8018710324089542,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004942000311496871,
|
|
"loss": 5.0622,
|
|
"mean_token_accuracy": 0.20260873138904573,
|
|
"num_tokens": 17661354.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.295257234573365,
|
|
"epoch": 0.8022886735716672,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004941933134254928,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.20456148833036422,
|
|
"num_tokens": 17670482.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.307756137847901,
|
|
"epoch": 0.8027063147343803,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941865918640559,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.1957583472132683,
|
|
"num_tokens": 17679429.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.341779804229736,
|
|
"epoch": 0.8031239558970932,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941798664654937,
|
|
"loss": 5.1363,
|
|
"mean_token_accuracy": 0.19351305067539215,
|
|
"num_tokens": 17688620.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.293888664245605,
|
|
"epoch": 0.8035415970598062,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004941731372299241,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.20158742219209672,
|
|
"num_tokens": 17698493.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.249817943572998,
|
|
"epoch": 0.8039592382225192,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004941664041574651,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.21297183334827424,
|
|
"num_tokens": 17707408.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.2815269947052,
|
|
"epoch": 0.8043768793852322,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941596672482343,
|
|
"loss": 5.0151,
|
|
"mean_token_accuracy": 0.2105283558368683,
|
|
"num_tokens": 17716448.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.2984757900238035,
|
|
"epoch": 0.8047945205479452,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004941529265023498,
|
|
"loss": 5.0619,
|
|
"mean_token_accuracy": 0.2112373799085617,
|
|
"num_tokens": 17725287.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.343301820755005,
|
|
"epoch": 0.8052121617106582,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004941461819199293,
|
|
"loss": 5.0793,
|
|
"mean_token_accuracy": 0.20268040746450425,
|
|
"num_tokens": 17734674.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.377449798583984,
|
|
"epoch": 0.8056298028733712,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004941394335010912,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.20087917745113373,
|
|
"num_tokens": 17743589.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.329857015609742,
|
|
"epoch": 0.8060474440360842,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004941326812459535,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.20657789707183838,
|
|
"num_tokens": 17753210.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.32722806930542,
|
|
"epoch": 0.8064650851987972,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004941259251546346,
|
|
"loss": 4.999,
|
|
"mean_token_accuracy": 0.20269202440977097,
|
|
"num_tokens": 17762074.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.368362665176392,
|
|
"epoch": 0.8068827263615101,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004941191652272526,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.1902139440178871,
|
|
"num_tokens": 17771263.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.301179981231689,
|
|
"epoch": 0.8073003675242232,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004941124014639258,
|
|
"loss": 4.984,
|
|
"mean_token_accuracy": 0.20613858997821807,
|
|
"num_tokens": 17781351.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.273010778427124,
|
|
"epoch": 0.8077180086869362,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004941056338647726,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.21401092708110808,
|
|
"num_tokens": 17790343.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.27913122177124,
|
|
"epoch": 0.8081356498496491,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004940988624299116,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.20028326511383057,
|
|
"num_tokens": 17799338.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.2721569538116455,
|
|
"epoch": 0.8085532910123622,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004940920871594613,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.20145072937011718,
|
|
"num_tokens": 17808852.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.301829099655151,
|
|
"epoch": 0.8089709321750752,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004940853080535403,
|
|
"loss": 5.0258,
|
|
"mean_token_accuracy": 0.20637283325195313,
|
|
"num_tokens": 17817654.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.269134616851806,
|
|
"epoch": 0.8093885733377881,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940785251122673,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.2048156350851059,
|
|
"num_tokens": 17826640.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.27788290977478,
|
|
"epoch": 0.8098062145005012,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004940717383357608,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.20859374701976777,
|
|
"num_tokens": 17835493.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.236548519134521,
|
|
"epoch": 0.8102238556632142,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004940649477241401,
|
|
"loss": 5.0052,
|
|
"mean_token_accuracy": 0.20643193274736404,
|
|
"num_tokens": 17845375.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.303682613372803,
|
|
"epoch": 0.8106414968259271,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004940581532775237,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.21037209928035736,
|
|
"num_tokens": 17854473.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.3612508296966555,
|
|
"epoch": 0.8110591379886402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004940513549960306,
|
|
"loss": 5.0456,
|
|
"mean_token_accuracy": 0.20334742814302445,
|
|
"num_tokens": 17864242.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.359550714492798,
|
|
"epoch": 0.8114767791513532,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004940445528797798,
|
|
"loss": 5.0639,
|
|
"mean_token_accuracy": 0.20069871693849564,
|
|
"num_tokens": 17873292.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.244348955154419,
|
|
"epoch": 0.8118944203140661,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940377469288906,
|
|
"loss": 4.9679,
|
|
"mean_token_accuracy": 0.2037941873073578,
|
|
"num_tokens": 17883601.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.304574012756348,
|
|
"epoch": 0.8123120614767791,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004940309371434819,
|
|
"loss": 5.0463,
|
|
"mean_token_accuracy": 0.2009972795844078,
|
|
"num_tokens": 17892241.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.332890319824219,
|
|
"epoch": 0.8127297026394922,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940241235236731,
|
|
"loss": 5.0703,
|
|
"mean_token_accuracy": 0.2082612082362175,
|
|
"num_tokens": 17901236.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.284566497802734,
|
|
"epoch": 0.8131473438022051,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004940173060695833,
|
|
"loss": 5.0607,
|
|
"mean_token_accuracy": 0.19371364414691924,
|
|
"num_tokens": 17909871.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.161655616760254,
|
|
"epoch": 0.8135649849649181,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004940104847813319,
|
|
"loss": 4.8685,
|
|
"mean_token_accuracy": 0.2147802010178566,
|
|
"num_tokens": 17918158.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.214431238174439,
|
|
"epoch": 0.8139826261276312,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004940036596590384,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.2067795515060425,
|
|
"num_tokens": 17927778.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.292331123352051,
|
|
"epoch": 0.8144002672903441,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004939968307028221,
|
|
"loss": 4.9961,
|
|
"mean_token_accuracy": 0.20510769933462142,
|
|
"num_tokens": 17936859.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.253911447525025,
|
|
"epoch": 0.8148179084530571,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004939899979128028,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.20255742967128754,
|
|
"num_tokens": 17946477.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.300867128372192,
|
|
"epoch": 0.8152355496157702,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004939831612890999,
|
|
"loss": 5.0005,
|
|
"mean_token_accuracy": 0.2051709532737732,
|
|
"num_tokens": 17956362.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.262574815750122,
|
|
"epoch": 0.8156531907784831,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004939763208318332,
|
|
"loss": 5.0121,
|
|
"mean_token_accuracy": 0.2053813010454178,
|
|
"num_tokens": 17965837.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.282008409500122,
|
|
"epoch": 0.8160708319411961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004939694765411225,
|
|
"loss": 5.0954,
|
|
"mean_token_accuracy": 0.19501988142728804,
|
|
"num_tokens": 17974750.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.332566833496093,
|
|
"epoch": 0.8164884731039092,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939626284170874,
|
|
"loss": 5.1651,
|
|
"mean_token_accuracy": 0.19189069271087647,
|
|
"num_tokens": 17985106.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.303172779083252,
|
|
"epoch": 0.8169061142666221,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493955776459848,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.20358987003564835,
|
|
"num_tokens": 17995073.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.299810791015625,
|
|
"epoch": 0.8173237554293351,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004939489206695241,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.21079401522874833,
|
|
"num_tokens": 18004112.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.285667276382446,
|
|
"epoch": 0.8177413965920481,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004939420610462359,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20583859086036682,
|
|
"num_tokens": 18013344.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.294785690307617,
|
|
"epoch": 0.8181590377547611,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004939351975901034,
|
|
"loss": 4.9855,
|
|
"mean_token_accuracy": 0.20558829456567765,
|
|
"num_tokens": 18022938.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.269521999359131,
|
|
"epoch": 0.8185766789174741,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004939283303012467,
|
|
"loss": 4.9719,
|
|
"mean_token_accuracy": 0.20116849839687348,
|
|
"num_tokens": 18031507.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.217773962020874,
|
|
"epoch": 0.8189943200801871,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000493921459179786,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.20494818240404128,
|
|
"num_tokens": 18039553.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.260326766967774,
|
|
"epoch": 0.8194119612429,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004939145842258418,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.20717705339193343,
|
|
"num_tokens": 18048550.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.3044679164886475,
|
|
"epoch": 0.8198296024056131,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004939077054395341,
|
|
"loss": 4.9971,
|
|
"mean_token_accuracy": 0.20472484081983566,
|
|
"num_tokens": 18057298.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.189090919494629,
|
|
"epoch": 0.8202472435683261,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004939008228209836,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.20839583575725557,
|
|
"num_tokens": 18066740.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.266100692749023,
|
|
"epoch": 0.820664884731039,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004938939363703106,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.20083184391260148,
|
|
"num_tokens": 18076663.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.3550303936004635,
|
|
"epoch": 0.8210825258937521,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004938870460876359,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.19616746455430983,
|
|
"num_tokens": 18085037.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.40608024597168,
|
|
"epoch": 0.8215001670564651,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00049388015197308,
|
|
"loss": 5.1213,
|
|
"mean_token_accuracy": 0.19837906062602997,
|
|
"num_tokens": 18094636.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.305377244949341,
|
|
"epoch": 0.821917808219178,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938732540267635,
|
|
"loss": 5.0361,
|
|
"mean_token_accuracy": 0.20277401208877563,
|
|
"num_tokens": 18103083.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.238370275497436,
|
|
"epoch": 0.8223354493818911,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004938663522488072,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.20113914161920549,
|
|
"num_tokens": 18112108.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.414588165283203,
|
|
"epoch": 0.8227530905446041,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004938594466393321,
|
|
"loss": 5.0773,
|
|
"mean_token_accuracy": 0.2010812059044838,
|
|
"num_tokens": 18121001.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.2940467357635494,
|
|
"epoch": 0.823170731707317,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004938525371984588,
|
|
"loss": 4.9379,
|
|
"mean_token_accuracy": 0.2100592702627182,
|
|
"num_tokens": 18129309.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.306638145446778,
|
|
"epoch": 0.8235883728700301,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004938456239263085,
|
|
"loss": 5.1097,
|
|
"mean_token_accuracy": 0.19680015593767167,
|
|
"num_tokens": 18138373.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.347333383560181,
|
|
"epoch": 0.8240060140327431,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004938387068230021,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.19877478927373887,
|
|
"num_tokens": 18148038.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.313597536087036,
|
|
"epoch": 0.824423655195456,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938317858886606,
|
|
"loss": 4.9788,
|
|
"mean_token_accuracy": 0.20435064882040024,
|
|
"num_tokens": 18158132.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.259231090545654,
|
|
"epoch": 0.824841296358169,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004938248611234055,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.2057383880019188,
|
|
"num_tokens": 18167276.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.2493713855743405,
|
|
"epoch": 0.8252589375208821,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004938179325273577,
|
|
"loss": 5.0584,
|
|
"mean_token_accuracy": 0.20667851716279984,
|
|
"num_tokens": 18177538.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.3181962966918945,
|
|
"epoch": 0.825676578683595,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004938110001006385,
|
|
"loss": 5.0485,
|
|
"mean_token_accuracy": 0.20177048891782762,
|
|
"num_tokens": 18187067.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.246301317214966,
|
|
"epoch": 0.826094219846308,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004938040638433694,
|
|
"loss": 5.0192,
|
|
"mean_token_accuracy": 0.19615020155906676,
|
|
"num_tokens": 18196710.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.254277181625366,
|
|
"epoch": 0.8265118610090211,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004937971237556719,
|
|
"loss": 5.022,
|
|
"mean_token_accuracy": 0.2020798683166504,
|
|
"num_tokens": 18205789.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.280001068115235,
|
|
"epoch": 0.826929502171734,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004937901798376672,
|
|
"loss": 4.8769,
|
|
"mean_token_accuracy": 0.2114336222410202,
|
|
"num_tokens": 18214633.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.295221185684204,
|
|
"epoch": 0.827347143334447,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004937832320894772,
|
|
"loss": 5.0375,
|
|
"mean_token_accuracy": 0.2016205221414566,
|
|
"num_tokens": 18225019.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.186416053771973,
|
|
"epoch": 0.8277647844971601,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004937762805112233,
|
|
"loss": 4.9747,
|
|
"mean_token_accuracy": 0.2126376897096634,
|
|
"num_tokens": 18234610.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.265705490112305,
|
|
"epoch": 0.828182425659873,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004937693251030273,
|
|
"loss": 4.9924,
|
|
"mean_token_accuracy": 0.20449338406324385,
|
|
"num_tokens": 18243733.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.295730209350586,
|
|
"epoch": 0.828600066822586,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000493762365865011,
|
|
"loss": 4.9985,
|
|
"mean_token_accuracy": 0.20857708752155305,
|
|
"num_tokens": 18253105.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.3593605041503904,
|
|
"epoch": 0.8290177079852991,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937554027972961,
|
|
"loss": 5.083,
|
|
"mean_token_accuracy": 0.1967705011367798,
|
|
"num_tokens": 18261862.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.334206819534302,
|
|
"epoch": 0.829435349148012,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004937484359000046,
|
|
"loss": 5.1134,
|
|
"mean_token_accuracy": 0.20386075377464294,
|
|
"num_tokens": 18271941.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.234013938903809,
|
|
"epoch": 0.829852990310725,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937414651732584,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.21173980534076692,
|
|
"num_tokens": 18281048.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.3753643989562985,
|
|
"epoch": 0.830270631473438,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004937344906171795,
|
|
"loss": 5.1421,
|
|
"mean_token_accuracy": 0.19821691811084746,
|
|
"num_tokens": 18290140.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.212609672546387,
|
|
"epoch": 0.830688272636151,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004937275122318902,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.19909176975488663,
|
|
"num_tokens": 18298784.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.291703367233277,
|
|
"epoch": 0.831105913798864,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937205300175123,
|
|
"loss": 5.0369,
|
|
"mean_token_accuracy": 0.20625924915075303,
|
|
"num_tokens": 18307750.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.320566177368164,
|
|
"epoch": 0.831523554961577,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004937135439741682,
|
|
"loss": 5.008,
|
|
"mean_token_accuracy": 0.20745422393083573,
|
|
"num_tokens": 18317042.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.266500568389892,
|
|
"epoch": 0.83194119612429,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004937065541019806,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.20151247382164,
|
|
"num_tokens": 18326733.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.389435911178589,
|
|
"epoch": 0.832358837287003,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004936995604010711,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.19566041976213455,
|
|
"num_tokens": 18336366.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.3185296058654785,
|
|
"epoch": 0.832776478449716,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004936925628715628,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.20051100254058837,
|
|
"num_tokens": 18345260.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.316124010086059,
|
|
"epoch": 0.833194119612429,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936855615135779,
|
|
"loss": 5.0922,
|
|
"mean_token_accuracy": 0.20094930678606032,
|
|
"num_tokens": 18354916.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.294518566131591,
|
|
"epoch": 0.833611760775142,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493678556327239,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.20490070432424545,
|
|
"num_tokens": 18364012.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.295546817779541,
|
|
"epoch": 0.834029401937855,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004936715473126688,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.19984930753707886,
|
|
"num_tokens": 18374685.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.185560274124145,
|
|
"epoch": 0.8344470431005679,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.00049366453446999,
|
|
"loss": 4.8772,
|
|
"mean_token_accuracy": 0.21436823904514313,
|
|
"num_tokens": 18383716.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.2336760520935055,
|
|
"epoch": 0.834864684263281,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004936575177993251,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.20930355340242385,
|
|
"num_tokens": 18393071.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.402569675445557,
|
|
"epoch": 0.835282325425994,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004936504973007973,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.20065169930458068,
|
|
"num_tokens": 18403593.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.38895697593689,
|
|
"epoch": 0.8356999665887069,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004936434729745294,
|
|
"loss": 5.1364,
|
|
"mean_token_accuracy": 0.19206025302410126,
|
|
"num_tokens": 18412016.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.276046943664551,
|
|
"epoch": 0.83611760775142,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004936364448206442,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.20763250142335893,
|
|
"num_tokens": 18421098.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.265837717056274,
|
|
"epoch": 0.836535248914133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004936294128392649,
|
|
"loss": 5.0421,
|
|
"mean_token_accuracy": 0.19949822276830673,
|
|
"num_tokens": 18430264.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.382352352142334,
|
|
"epoch": 0.8369528900768459,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004936223770305146,
|
|
"loss": 5.0936,
|
|
"mean_token_accuracy": 0.20505709201097488,
|
|
"num_tokens": 18439595.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.29772539138794,
|
|
"epoch": 0.837370531239559,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004936153373945165,
|
|
"loss": 5.0112,
|
|
"mean_token_accuracy": 0.20335680097341538,
|
|
"num_tokens": 18448945.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.275892734527588,
|
|
"epoch": 0.837788172402272,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004936082939313936,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.20817580074071884,
|
|
"num_tokens": 18458623.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.302818965911865,
|
|
"epoch": 0.8382058135649849,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004936012466412695,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.20688553899526596,
|
|
"num_tokens": 18466462.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.321800661087036,
|
|
"epoch": 0.838623454727698,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004935941955242674,
|
|
"loss": 5.033,
|
|
"mean_token_accuracy": 0.2010161578655243,
|
|
"num_tokens": 18475936.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.253032112121582,
|
|
"epoch": 0.839041095890411,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935871405805109,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.2042238309979439,
|
|
"num_tokens": 18485526.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.251066589355469,
|
|
"epoch": 0.8394587370531239,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004935800818101232,
|
|
"loss": 4.9669,
|
|
"mean_token_accuracy": 0.21049756705760955,
|
|
"num_tokens": 18494202.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.3914501667022705,
|
|
"epoch": 0.8398763782158369,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004935730192132282,
|
|
"loss": 5.1315,
|
|
"mean_token_accuracy": 0.199594122171402,
|
|
"num_tokens": 18503502.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.361604022979736,
|
|
"epoch": 0.84029401937855,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004935659527899493,
|
|
"loss": 5.0586,
|
|
"mean_token_accuracy": 0.2059072345495224,
|
|
"num_tokens": 18512607.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.306092596054077,
|
|
"epoch": 0.8407116605412629,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004935588825404104,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.206988425552845,
|
|
"num_tokens": 18521875.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.3057904720306395,
|
|
"epoch": 0.8411293017039759,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004935518084647351,
|
|
"loss": 5.0569,
|
|
"mean_token_accuracy": 0.2059520587325096,
|
|
"num_tokens": 18530554.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.334392023086548,
|
|
"epoch": 0.841546942866689,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004935447305630474,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.21342624276876448,
|
|
"num_tokens": 18539037.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.212561178207397,
|
|
"epoch": 0.8419645840294019,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004935376488354711,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.20939378440380096,
|
|
"num_tokens": 18548218.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.3200713157653805,
|
|
"epoch": 0.8423822251921149,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004935305632821303,
|
|
"loss": 5.0014,
|
|
"mean_token_accuracy": 0.20581123381853103,
|
|
"num_tokens": 18557968.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.335072946548462,
|
|
"epoch": 0.842799866354828,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004935234739031488,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.197623610496521,
|
|
"num_tokens": 18566809.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.341650819778442,
|
|
"epoch": 0.8432175075175409,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004935163806986508,
|
|
"loss": 4.9887,
|
|
"mean_token_accuracy": 0.1985984191298485,
|
|
"num_tokens": 18574419.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.287086105346679,
|
|
"epoch": 0.8436351486802539,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004935092836687607,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.20586064606904983,
|
|
"num_tokens": 18584470.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.293055438995362,
|
|
"epoch": 0.8440527898429669,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004935021828136025,
|
|
"loss": 5.0222,
|
|
"mean_token_accuracy": 0.20671310275793076,
|
|
"num_tokens": 18593551.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.313801908493042,
|
|
"epoch": 0.8444704310056799,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004934950781333005,
|
|
"loss": 4.9984,
|
|
"mean_token_accuracy": 0.20686371773481368,
|
|
"num_tokens": 18602253.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.303022193908691,
|
|
"epoch": 0.8448880721683929,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004934879696279793,
|
|
"loss": 5.0629,
|
|
"mean_token_accuracy": 0.1979691281914711,
|
|
"num_tokens": 18611261.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.37919774055481,
|
|
"epoch": 0.8453057133311059,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004934808572977632,
|
|
"loss": 5.1292,
|
|
"mean_token_accuracy": 0.19424993097782134,
|
|
"num_tokens": 18620508.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.3805327892303465,
|
|
"epoch": 0.8457233544938189,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004934737411427765,
|
|
"loss": 5.0497,
|
|
"mean_token_accuracy": 0.20973548740148545,
|
|
"num_tokens": 18629140.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.255376720428467,
|
|
"epoch": 0.8461409956565319,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004934666211631442,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20868595093488693,
|
|
"num_tokens": 18637924.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.249253511428833,
|
|
"epoch": 0.8465586368192449,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004934594973589906,
|
|
"loss": 4.9575,
|
|
"mean_token_accuracy": 0.20524512529373168,
|
|
"num_tokens": 18646193.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.404231595993042,
|
|
"epoch": 0.8469762779819578,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004934523697304406,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.1946185350418091,
|
|
"num_tokens": 18655327.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.319961214065552,
|
|
"epoch": 0.8473939191446709,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004934452382776189,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.19827838540077208,
|
|
"num_tokens": 18664633.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.313873195648194,
|
|
"epoch": 0.8478115603073839,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004934381030006504,
|
|
"loss": 5.0505,
|
|
"mean_token_accuracy": 0.19499401450157167,
|
|
"num_tokens": 18673956.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.296115493774414,
|
|
"epoch": 0.8482292014700968,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00049343096389966,
|
|
"loss": 4.9424,
|
|
"mean_token_accuracy": 0.2113516628742218,
|
|
"num_tokens": 18682257.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.247281503677368,
|
|
"epoch": 0.8486468426328099,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004934238209747724,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.21227099299430846,
|
|
"num_tokens": 18691493.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.278650283813477,
|
|
"epoch": 0.8490644837955229,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004934166742261132,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.21012082397937776,
|
|
"num_tokens": 18700309.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.251601314544677,
|
|
"epoch": 0.8494821249582358,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000493409523653807,
|
|
"loss": 4.9756,
|
|
"mean_token_accuracy": 0.20372741520404816,
|
|
"num_tokens": 18709909.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.394166803359985,
|
|
"epoch": 0.8498997661209489,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004934023692579793,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.1942512258887291,
|
|
"num_tokens": 18719270.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.266862154006958,
|
|
"epoch": 0.8503174072836619,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933952110387553,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.20405737161636353,
|
|
"num_tokens": 18728141.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.28151650428772,
|
|
"epoch": 0.8507350484463748,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004933880489962602,
|
|
"loss": 5.0053,
|
|
"mean_token_accuracy": 0.20471728295087815,
|
|
"num_tokens": 18737925.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.305218267440796,
|
|
"epoch": 0.8511526896090879,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004933808831306194,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.20414305329322815,
|
|
"num_tokens": 18746622.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.29584059715271,
|
|
"epoch": 0.8515703307718009,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004933737134419583,
|
|
"loss": 4.9568,
|
|
"mean_token_accuracy": 0.20452301502227782,
|
|
"num_tokens": 18755316.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.258632612228394,
|
|
"epoch": 0.8519879719345138,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933665399304025,
|
|
"loss": 4.9484,
|
|
"mean_token_accuracy": 0.208237661421299,
|
|
"num_tokens": 18765264.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.237370777130127,
|
|
"epoch": 0.8524056130972268,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004933593625960777,
|
|
"loss": 4.965,
|
|
"mean_token_accuracy": 0.20784535259008408,
|
|
"num_tokens": 18774275.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.290697240829468,
|
|
"epoch": 0.8528232542599399,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004933521814391094,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.20709307491779327,
|
|
"num_tokens": 18782848.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.239592599868774,
|
|
"epoch": 0.8532408954226529,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004933449964596232,
|
|
"loss": 5.0124,
|
|
"mean_token_accuracy": 0.20847624838352202,
|
|
"num_tokens": 18792072.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.318029546737671,
|
|
"epoch": 0.8536585365853658,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004933378076577451,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.2082846611738205,
|
|
"num_tokens": 18800886.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.273925304412842,
|
|
"epoch": 0.8540761777480789,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004933306150336009,
|
|
"loss": 4.9897,
|
|
"mean_token_accuracy": 0.21183057874441147,
|
|
"num_tokens": 18809673.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.275402164459228,
|
|
"epoch": 0.8544938189107919,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004933234185873164,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.21424993574619294,
|
|
"num_tokens": 18818230.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.301094436645508,
|
|
"epoch": 0.8549114600735048,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004933162183190177,
|
|
"loss": 5.0413,
|
|
"mean_token_accuracy": 0.20516440868377686,
|
|
"num_tokens": 18827600.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.421688222885132,
|
|
"epoch": 0.8553291012362179,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004933090142288308,
|
|
"loss": 5.1153,
|
|
"mean_token_accuracy": 0.19783318936824798,
|
|
"num_tokens": 18837237.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.330673313140869,
|
|
"epoch": 0.8557467423989309,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004933018063168819,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.20791014432907104,
|
|
"num_tokens": 18846859.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.3161280155181885,
|
|
"epoch": 0.8561643835616438,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000493294594583297,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.2050260752439499,
|
|
"num_tokens": 18856226.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.230455636978149,
|
|
"epoch": 0.8565820247243568,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004932873790282026,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.20871823728084565,
|
|
"num_tokens": 18864679.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.305653667449951,
|
|
"epoch": 0.8569996658870699,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004932801596517248,
|
|
"loss": 5.0683,
|
|
"mean_token_accuracy": 0.1987113833427429,
|
|
"num_tokens": 18874837.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.326244163513183,
|
|
"epoch": 0.8574173070497828,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004932729364539901,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.21527738869190216,
|
|
"num_tokens": 18883669.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.2176577091217045,
|
|
"epoch": 0.8578349482124958,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004932657094351248,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.21127166599035263,
|
|
"num_tokens": 18892199.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.323324060440063,
|
|
"epoch": 0.8582525893752089,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932584785952555,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.20386639088392258,
|
|
"num_tokens": 18902393.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.379483222961426,
|
|
"epoch": 0.8586702305379218,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493251243934509,
|
|
"loss": 5.1094,
|
|
"mean_token_accuracy": 0.20026783645153046,
|
|
"num_tokens": 18912417.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.3742118835449215,
|
|
"epoch": 0.8590878717006348,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004932440054530116,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.20298342108726503,
|
|
"num_tokens": 18921456.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.252741003036499,
|
|
"epoch": 0.8595055128633479,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004932367631508903,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.20776328295469285,
|
|
"num_tokens": 18930865.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.279796552658081,
|
|
"epoch": 0.8599231540260608,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004932295170282717,
|
|
"loss": 4.9411,
|
|
"mean_token_accuracy": 0.2069946363568306,
|
|
"num_tokens": 18940043.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.218703699111939,
|
|
"epoch": 0.8603407951887738,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004932222670852828,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.2113702565431595,
|
|
"num_tokens": 18948803.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.283490133285523,
|
|
"epoch": 0.8607584363514869,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932150133220504,
|
|
"loss": 5.0028,
|
|
"mean_token_accuracy": 0.20119367092847823,
|
|
"num_tokens": 18958014.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.272213554382324,
|
|
"epoch": 0.8611760775141998,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004932077557387015,
|
|
"loss": 4.9916,
|
|
"mean_token_accuracy": 0.20666328817605972,
|
|
"num_tokens": 18966425.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.233971834182739,
|
|
"epoch": 0.8615937186769128,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004932004943353633,
|
|
"loss": 5.0598,
|
|
"mean_token_accuracy": 0.19889507740736007,
|
|
"num_tokens": 18975445.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.3610106945037845,
|
|
"epoch": 0.8620113598396258,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004931932291121627,
|
|
"loss": 5.0675,
|
|
"mean_token_accuracy": 0.20659312307834626,
|
|
"num_tokens": 18984271.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.29894609451294,
|
|
"epoch": 0.8624290010023388,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004931859600692269,
|
|
"loss": 5.0077,
|
|
"mean_token_accuracy": 0.2019526705145836,
|
|
"num_tokens": 18994179.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.252616357803345,
|
|
"epoch": 0.8628466421650518,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004931786872066833,
|
|
"loss": 4.914,
|
|
"mean_token_accuracy": 0.21181457340717316,
|
|
"num_tokens": 19003313.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.294435453414917,
|
|
"epoch": 0.8632642833277648,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931714105246592,
|
|
"loss": 5.0747,
|
|
"mean_token_accuracy": 0.20050304979085923,
|
|
"num_tokens": 19013982.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.259725761413574,
|
|
"epoch": 0.8636819244904778,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004931641300232819,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.20617287009954452,
|
|
"num_tokens": 19022634.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.312937784194946,
|
|
"epoch": 0.8640995656531908,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931568457026789,
|
|
"loss": 5.0585,
|
|
"mean_token_accuracy": 0.2004276007413864,
|
|
"num_tokens": 19031903.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.326122379302978,
|
|
"epoch": 0.8645172068159038,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004931495575629778,
|
|
"loss": 5.014,
|
|
"mean_token_accuracy": 0.2050051510334015,
|
|
"num_tokens": 19040367.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.304536581039429,
|
|
"epoch": 0.8649348479786167,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000493142265604306,
|
|
"loss": 4.976,
|
|
"mean_token_accuracy": 0.21539195924997329,
|
|
"num_tokens": 19049572.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.329609346389771,
|
|
"epoch": 0.8653524891413298,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004931349698267914,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.19756895005702974,
|
|
"num_tokens": 19059313.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.290513610839843,
|
|
"epoch": 0.8657701303040428,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004931276702305615,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.2028427764773369,
|
|
"num_tokens": 19067941.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.289610958099365,
|
|
"epoch": 0.8661877714667557,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004931203668157441,
|
|
"loss": 4.9619,
|
|
"mean_token_accuracy": 0.20647017806768417,
|
|
"num_tokens": 19077462.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.279487133026123,
|
|
"epoch": 0.8666054126294688,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004931130595824672,
|
|
"loss": 5.0506,
|
|
"mean_token_accuracy": 0.20754966288805007,
|
|
"num_tokens": 19086669.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.275893068313598,
|
|
"epoch": 0.8670230537921818,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004931057485308587,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.2036629468202591,
|
|
"num_tokens": 19095781.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.320440626144409,
|
|
"epoch": 0.8674406949548947,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004930984336610465,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.20856657326221467,
|
|
"num_tokens": 19105106.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.376770305633545,
|
|
"epoch": 0.8678583361176078,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004930911149731587,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.20458581447601318,
|
|
"num_tokens": 19114710.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.322228050231933,
|
|
"epoch": 0.8682759772803208,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004930837924673233,
|
|
"loss": 5.0418,
|
|
"mean_token_accuracy": 0.21001044511795045,
|
|
"num_tokens": 19123495.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.32572979927063,
|
|
"epoch": 0.8686936184430337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004930764661436688,
|
|
"loss": 5.0433,
|
|
"mean_token_accuracy": 0.202639901638031,
|
|
"num_tokens": 19131894.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.361495113372802,
|
|
"epoch": 0.8691112596057468,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004930691360023231,
|
|
"loss": 5.098,
|
|
"mean_token_accuracy": 0.19560072273015977,
|
|
"num_tokens": 19141213.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.327635860443115,
|
|
"epoch": 0.8695289007684598,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004930618020434147,
|
|
"loss": 4.9955,
|
|
"mean_token_accuracy": 0.2053014948964119,
|
|
"num_tokens": 19150843.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.272561502456665,
|
|
"epoch": 0.8699465419311727,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930544642670721,
|
|
"loss": 4.9787,
|
|
"mean_token_accuracy": 0.21014084964990615,
|
|
"num_tokens": 19160198.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.26478271484375,
|
|
"epoch": 0.8703641830938857,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004930471226734235,
|
|
"loss": 4.9893,
|
|
"mean_token_accuracy": 0.2024066373705864,
|
|
"num_tokens": 19169043.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.307534837722779,
|
|
"epoch": 0.8707818242565988,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004930397772625976,
|
|
"loss": 5.027,
|
|
"mean_token_accuracy": 0.204340161383152,
|
|
"num_tokens": 19177976.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.295533180236816,
|
|
"epoch": 0.8711994654193117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000493032428034723,
|
|
"loss": 5.1137,
|
|
"mean_token_accuracy": 0.1977749466896057,
|
|
"num_tokens": 19187909.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.241855907440185,
|
|
"epoch": 0.8716171065820247,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004930250749899282,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.21657078862190246,
|
|
"num_tokens": 19196297.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.324614191055298,
|
|
"epoch": 0.8720347477447378,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004930177181283422,
|
|
"loss": 5.0595,
|
|
"mean_token_accuracy": 0.2065043956041336,
|
|
"num_tokens": 19205280.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.224476051330567,
|
|
"epoch": 0.8724523889074507,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004930103574500934,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.20982642769813536,
|
|
"num_tokens": 19214789.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.312243509292602,
|
|
"epoch": 0.8728700300701637,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004930029929553109,
|
|
"loss": 5.0185,
|
|
"mean_token_accuracy": 0.20623940974473953,
|
|
"num_tokens": 19224597.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.299521780014038,
|
|
"epoch": 0.8732876712328768,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929956246441237,
|
|
"loss": 4.9712,
|
|
"mean_token_accuracy": 0.20611770451068878,
|
|
"num_tokens": 19233716.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.2492045879364015,
|
|
"epoch": 0.8737053123955897,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004929882525166608,
|
|
"loss": 4.8858,
|
|
"mean_token_accuracy": 0.2150235429406166,
|
|
"num_tokens": 19242444.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.276464891433716,
|
|
"epoch": 0.8741229535583027,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004929808765730509,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.20595028549432753,
|
|
"num_tokens": 19252380.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.33533205986023,
|
|
"epoch": 0.8745405947210158,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004929734968134235,
|
|
"loss": 5.1008,
|
|
"mean_token_accuracy": 0.199392868578434,
|
|
"num_tokens": 19262250.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.367617988586426,
|
|
"epoch": 0.8749582358837287,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004929661132379076,
|
|
"loss": 5.1127,
|
|
"mean_token_accuracy": 0.19977856874465943,
|
|
"num_tokens": 19272228.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.338474559783935,
|
|
"epoch": 0.8753758770464417,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004929587258466326,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.20023833066225052,
|
|
"num_tokens": 19281493.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.388702392578125,
|
|
"epoch": 0.8757935182091547,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004929513346397278,
|
|
"loss": 5.0903,
|
|
"mean_token_accuracy": 0.19686453342437743,
|
|
"num_tokens": 19292300.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.373995161056518,
|
|
"epoch": 0.8762111593718677,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004929439396173223,
|
|
"loss": 5.0573,
|
|
"mean_token_accuracy": 0.19610776007175446,
|
|
"num_tokens": 19301516.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.252033662796021,
|
|
"epoch": 0.8766288005345807,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492936540779546,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.21123408675193786,
|
|
"num_tokens": 19311075.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.260432195663452,
|
|
"epoch": 0.8770464416972937,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004929291381265281,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.20350782573223114,
|
|
"num_tokens": 19320605.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.274372720718384,
|
|
"epoch": 0.8774640828600067,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004929217316583985,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.21216148436069487,
|
|
"num_tokens": 19330604.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.289424991607666,
|
|
"epoch": 0.8778817240227197,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004929143213752865,
|
|
"loss": 5.0601,
|
|
"mean_token_accuracy": 0.2045086592435837,
|
|
"num_tokens": 19340650.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.377853012084961,
|
|
"epoch": 0.8782993651854327,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492906907277322,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.18965041190385817,
|
|
"num_tokens": 19350431.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.3663732528686525,
|
|
"epoch": 0.8787170063481456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000492899489364635,
|
|
"loss": 5.0631,
|
|
"mean_token_accuracy": 0.20302023291587828,
|
|
"num_tokens": 19360171.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.34380259513855,
|
|
"epoch": 0.8791346475108587,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004928920676373549,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.20387198477983476,
|
|
"num_tokens": 19369748.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.315323114395142,
|
|
"epoch": 0.8795522886735717,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492884642095612,
|
|
"loss": 5.063,
|
|
"mean_token_accuracy": 0.19860274344682693,
|
|
"num_tokens": 19378470.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.240320634841919,
|
|
"epoch": 0.8799699298362846,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004928772127395361,
|
|
"loss": 4.9694,
|
|
"mean_token_accuracy": 0.20913950800895692,
|
|
"num_tokens": 19387869.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.363303852081299,
|
|
"epoch": 0.8803875709989977,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004928697795692575,
|
|
"loss": 5.1096,
|
|
"mean_token_accuracy": 0.20102762281894684,
|
|
"num_tokens": 19396805.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.26795072555542,
|
|
"epoch": 0.8808052121617107,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000492862342584906,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.2059139922261238,
|
|
"num_tokens": 19405392.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.38167290687561,
|
|
"epoch": 0.8812228533244236,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000492854901786612,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20350367724895477,
|
|
"num_tokens": 19413896.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.3298125743865965,
|
|
"epoch": 0.8816404944871367,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004928474571745058,
|
|
"loss": 4.9731,
|
|
"mean_token_accuracy": 0.20981867611408234,
|
|
"num_tokens": 19422136.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.201847410202026,
|
|
"epoch": 0.8820581356498497,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004928400087487175,
|
|
"loss": 4.8576,
|
|
"mean_token_accuracy": 0.20926002115011216,
|
|
"num_tokens": 19431250.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.2413330078125,
|
|
"epoch": 0.8824757768125626,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004928325565093777,
|
|
"loss": 4.9247,
|
|
"mean_token_accuracy": 0.20986948162317276,
|
|
"num_tokens": 19439155.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.321356296539307,
|
|
"epoch": 0.8828934179752757,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004928251004566167,
|
|
"loss": 5.0882,
|
|
"mean_token_accuracy": 0.19206874519586564,
|
|
"num_tokens": 19448637.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.403696155548095,
|
|
"epoch": 0.8833110591379887,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004928176405905653,
|
|
"loss": 5.0891,
|
|
"mean_token_accuracy": 0.19659219384193422,
|
|
"num_tokens": 19457573.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.278180503845215,
|
|
"epoch": 0.8837287003007016,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004928101769113537,
|
|
"loss": 4.9429,
|
|
"mean_token_accuracy": 0.21089721769094466,
|
|
"num_tokens": 19466085.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.201364946365357,
|
|
"epoch": 0.8841463414634146,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000492802709419113,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.21619755029678345,
|
|
"num_tokens": 19475185.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.3189562320709225,
|
|
"epoch": 0.8845639826261277,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004927952381139735,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.19414522051811217,
|
|
"num_tokens": 19484387.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.239376497268677,
|
|
"epoch": 0.8849816237888406,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004927877629960663,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.20380643606185914,
|
|
"num_tokens": 19493309.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.285148239135742,
|
|
"epoch": 0.8853992649515536,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004927802840655221,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.2021192342042923,
|
|
"num_tokens": 19502284.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.387592887878418,
|
|
"epoch": 0.8858169061142667,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492772801322472,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.2028966322541237,
|
|
"num_tokens": 19512720.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.320599317550659,
|
|
"epoch": 0.8862345472769796,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004927653147670468,
|
|
"loss": 4.9786,
|
|
"mean_token_accuracy": 0.20816096663475037,
|
|
"num_tokens": 19521395.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.222299337387085,
|
|
"epoch": 0.8866521884396926,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004927578243993777,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.20712675303220748,
|
|
"num_tokens": 19530855.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.2567637920379635,
|
|
"epoch": 0.8870698296024057,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004927503302195957,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.21275728493928908,
|
|
"num_tokens": 19540330.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.290124893188477,
|
|
"epoch": 0.8874874707651186,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000492742832227832,
|
|
"loss": 4.9654,
|
|
"mean_token_accuracy": 0.20247079730033873,
|
|
"num_tokens": 19549639.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.301794004440308,
|
|
"epoch": 0.8879051119278316,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000492735330424218,
|
|
"loss": 5.0588,
|
|
"mean_token_accuracy": 0.21230444610118865,
|
|
"num_tokens": 19558485.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.351099252700806,
|
|
"epoch": 0.8883227530905446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000492727824808885,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.20544956177473067,
|
|
"num_tokens": 19566924.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.369914150238037,
|
|
"epoch": 0.8887403942532576,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004927203153819643,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.20210351645946503,
|
|
"num_tokens": 19575901.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.301700115203857,
|
|
"epoch": 0.8891580354159706,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004927128021435875,
|
|
"loss": 5.047,
|
|
"mean_token_accuracy": 0.20331940799951553,
|
|
"num_tokens": 19585470.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.320741796493531,
|
|
"epoch": 0.8895756765786836,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000492705285093886,
|
|
"loss": 5.0556,
|
|
"mean_token_accuracy": 0.2021444946527481,
|
|
"num_tokens": 19594775.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.349822759628296,
|
|
"epoch": 0.8899933177413966,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926977642329913,
|
|
"loss": 5.0156,
|
|
"mean_token_accuracy": 0.20540826469659806,
|
|
"num_tokens": 19604061.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.253830337524414,
|
|
"epoch": 0.8904109589041096,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926902395610353,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.2116168662905693,
|
|
"num_tokens": 19613130.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.232883310317993,
|
|
"epoch": 0.8908286000668226,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004926827110781496,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.2094137966632843,
|
|
"num_tokens": 19621951.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.2585282802581785,
|
|
"epoch": 0.8912462412295356,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000492675178784466,
|
|
"loss": 4.9605,
|
|
"mean_token_accuracy": 0.2010581001639366,
|
|
"num_tokens": 19631167.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.310780811309814,
|
|
"epoch": 0.8916638823922486,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004926676426801164,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.19809516966342927,
|
|
"num_tokens": 19640548.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.297132444381714,
|
|
"epoch": 0.8920815235549616,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004926601027652328,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.20372147858142853,
|
|
"num_tokens": 19650607.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.225397253036499,
|
|
"epoch": 0.8924991647176745,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.000492652559039947,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.21761897057294846,
|
|
"num_tokens": 19659845.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.222863054275512,
|
|
"epoch": 0.8929168058803876,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004926450115043912,
|
|
"loss": 4.9608,
|
|
"mean_token_accuracy": 0.21084788143634797,
|
|
"num_tokens": 19668863.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.296765232086182,
|
|
"epoch": 0.8933344470431006,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004926374601586975,
|
|
"loss": 4.9749,
|
|
"mean_token_accuracy": 0.20998479127883912,
|
|
"num_tokens": 19678335.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.300933742523194,
|
|
"epoch": 0.8937520882058135,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004926299050029981,
|
|
"loss": 4.9802,
|
|
"mean_token_accuracy": 0.20377939641475679,
|
|
"num_tokens": 19687491.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.192112159729004,
|
|
"epoch": 0.8941697293685266,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004926223460374251,
|
|
"loss": 4.8834,
|
|
"mean_token_accuracy": 0.21372992545366287,
|
|
"num_tokens": 19696632.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.217490482330322,
|
|
"epoch": 0.8945873705312396,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004926147832621111,
|
|
"loss": 5.029,
|
|
"mean_token_accuracy": 0.20426514595746995,
|
|
"num_tokens": 19706275.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.352607536315918,
|
|
"epoch": 0.8950050116939525,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004926072166771884,
|
|
"loss": 5.0455,
|
|
"mean_token_accuracy": 0.19862300753593445,
|
|
"num_tokens": 19716016.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.3861438751220705,
|
|
"epoch": 0.8954226528566656,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004925996462827895,
|
|
"loss": 5.0079,
|
|
"mean_token_accuracy": 0.20271613150835038,
|
|
"num_tokens": 19725555.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.33118052482605,
|
|
"epoch": 0.8958402940193786,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004925920720790466,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.20407730787992479,
|
|
"num_tokens": 19735184.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.247045040130615,
|
|
"epoch": 0.8962579351820915,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925844940660928,
|
|
"loss": 4.9647,
|
|
"mean_token_accuracy": 0.20765860378742218,
|
|
"num_tokens": 19744065.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.250415182113647,
|
|
"epoch": 0.8966755763448045,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004925769122440606,
|
|
"loss": 4.9738,
|
|
"mean_token_accuracy": 0.21167444586753845,
|
|
"num_tokens": 19753251.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.250483751296997,
|
|
"epoch": 0.8970932175075176,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004925693266130824,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.21825634092092513,
|
|
"num_tokens": 19761290.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.341028022766113,
|
|
"epoch": 0.8975108586702305,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004925617371732914,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.20666397213935853,
|
|
"num_tokens": 19769169.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.289629793167114,
|
|
"epoch": 0.8979284998329435,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925541439248203,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.2061848148703575,
|
|
"num_tokens": 19778118.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.267689228057861,
|
|
"epoch": 0.8983461409956566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000492546546867802,
|
|
"loss": 5.0708,
|
|
"mean_token_accuracy": 0.20078818798065184,
|
|
"num_tokens": 19787281.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.268228435516358,
|
|
"epoch": 0.8987637821583695,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004925389460023696,
|
|
"loss": 4.9463,
|
|
"mean_token_accuracy": 0.2077861711382866,
|
|
"num_tokens": 19795797.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.34446382522583,
|
|
"epoch": 0.8991814233210825,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925313413286559,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.19944023489952087,
|
|
"num_tokens": 19804788.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.328783130645752,
|
|
"epoch": 0.8995990644837956,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004925237328467945,
|
|
"loss": 5.053,
|
|
"mean_token_accuracy": 0.20478852093219757,
|
|
"num_tokens": 19814696.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.352157258987427,
|
|
"epoch": 0.9000167056465085,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004925161205569182,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.19836931228637694,
|
|
"num_tokens": 19824216.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.2622819423675535,
|
|
"epoch": 0.9004343468092215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004925085044591604,
|
|
"loss": 4.9676,
|
|
"mean_token_accuracy": 0.21081067770719528,
|
|
"num_tokens": 19832272.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.336883020401001,
|
|
"epoch": 0.9008519879719346,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004925008845536544,
|
|
"loss": 5.0741,
|
|
"mean_token_accuracy": 0.2030440405011177,
|
|
"num_tokens": 19841655.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.264914321899414,
|
|
"epoch": 0.9012696291346475,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004924932608405336,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.2056529477238655,
|
|
"num_tokens": 19851288.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.27549467086792,
|
|
"epoch": 0.9016872702973605,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004924856333199315,
|
|
"loss": 5.0237,
|
|
"mean_token_accuracy": 0.20438656061887742,
|
|
"num_tokens": 19860537.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.337455081939697,
|
|
"epoch": 0.9021049114600735,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924780019919816,
|
|
"loss": 5.0612,
|
|
"mean_token_accuracy": 0.20651496052742005,
|
|
"num_tokens": 19869618.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.265950679779053,
|
|
"epoch": 0.9025225526227865,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004924703668568174,
|
|
"loss": 4.942,
|
|
"mean_token_accuracy": 0.2128925234079361,
|
|
"num_tokens": 19879236.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.280300426483154,
|
|
"epoch": 0.9029401937854995,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924627279145728,
|
|
"loss": 4.9823,
|
|
"mean_token_accuracy": 0.20672302991151809,
|
|
"num_tokens": 19887740.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.300790739059448,
|
|
"epoch": 0.9033578349482125,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004924550851653814,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.21413167268037797,
|
|
"num_tokens": 19896024.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.337387990951538,
|
|
"epoch": 0.9037754761109255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004924474386093769,
|
|
"loss": 4.9796,
|
|
"mean_token_accuracy": 0.21044441759586335,
|
|
"num_tokens": 19905533.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.210439777374267,
|
|
"epoch": 0.9041931172736385,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004924397882466933,
|
|
"loss": 4.8861,
|
|
"mean_token_accuracy": 0.21574046611785888,
|
|
"num_tokens": 19913560.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.2439226627349855,
|
|
"epoch": 0.9046107584363515,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004924321340774644,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.2089828684926033,
|
|
"num_tokens": 19923159.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.189917278289795,
|
|
"epoch": 0.9050283995990644,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004924244761018243,
|
|
"loss": 4.8214,
|
|
"mean_token_accuracy": 0.2135223165154457,
|
|
"num_tokens": 19931485.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.287079524993897,
|
|
"epoch": 0.9054460407617775,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000492416814319907,
|
|
"loss": 5.0692,
|
|
"mean_token_accuracy": 0.20601470917463302,
|
|
"num_tokens": 19940552.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.29929518699646,
|
|
"epoch": 0.9058636819244905,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004924091487318468,
|
|
"loss": 5.0037,
|
|
"mean_token_accuracy": 0.20899098217487336,
|
|
"num_tokens": 19949334.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.317359113693238,
|
|
"epoch": 0.9062813230872034,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924014793377776,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.20224995911121368,
|
|
"num_tokens": 19958569.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.307737970352173,
|
|
"epoch": 0.9066989642499165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004923938061378339,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.2164480671286583,
|
|
"num_tokens": 19967568.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.376305866241455,
|
|
"epoch": 0.9071166054126295,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004923861291321499,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.20867286175489425,
|
|
"num_tokens": 19976466.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.310326337814331,
|
|
"epoch": 0.9075342465753424,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004923784483208601,
|
|
"loss": 4.9392,
|
|
"mean_token_accuracy": 0.21381379216909407,
|
|
"num_tokens": 19986145.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.167883014678955,
|
|
"epoch": 0.9079518877380555,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923707637040989,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.21275967061519624,
|
|
"num_tokens": 19994611.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.225242042541504,
|
|
"epoch": 0.9083695289007685,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004923630752820008,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.2013227418065071,
|
|
"num_tokens": 20004578.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.379642343521118,
|
|
"epoch": 0.9087871700634814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004923553830547004,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.20085204839706422,
|
|
"num_tokens": 20014375.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.231244850158691,
|
|
"epoch": 0.9092048112261945,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004923476870223324,
|
|
"loss": 4.9194,
|
|
"mean_token_accuracy": 0.20915978848934175,
|
|
"num_tokens": 20023869.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.230802536010742,
|
|
"epoch": 0.9096224523889075,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004923399871850315,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.21218640357255936,
|
|
"num_tokens": 20033465.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.321956539154053,
|
|
"epoch": 0.9100400935516204,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004923322835429326,
|
|
"loss": 5.0365,
|
|
"mean_token_accuracy": 0.19897611290216446,
|
|
"num_tokens": 20042851.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.3265519618988035,
|
|
"epoch": 0.9104577347143334,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923245760961704,
|
|
"loss": 4.9489,
|
|
"mean_token_accuracy": 0.2093171328306198,
|
|
"num_tokens": 20052765.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.236003351211548,
|
|
"epoch": 0.9108753758770465,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923168648448799,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.20981592684984207,
|
|
"num_tokens": 20061368.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.2109270095825195,
|
|
"epoch": 0.9112930170397594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004923091497891961,
|
|
"loss": 4.8971,
|
|
"mean_token_accuracy": 0.20371938794851302,
|
|
"num_tokens": 20070408.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.273788738250732,
|
|
"epoch": 0.9117106582024724,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004923014309292541,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.1982407957315445,
|
|
"num_tokens": 20080305.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.347381114959717,
|
|
"epoch": 0.9121282993651855,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492293708265189,
|
|
"loss": 5.1018,
|
|
"mean_token_accuracy": 0.19891208857297898,
|
|
"num_tokens": 20090715.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.317757272720337,
|
|
"epoch": 0.9125459405278984,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004922859817971359,
|
|
"loss": 5.0454,
|
|
"mean_token_accuracy": 0.20527127832174302,
|
|
"num_tokens": 20099538.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.2591578483581545,
|
|
"epoch": 0.9129635816906114,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004922782515252302,
|
|
"loss": 4.995,
|
|
"mean_token_accuracy": 0.20378221124410628,
|
|
"num_tokens": 20109177.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.342626237869263,
|
|
"epoch": 0.9133812228533245,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922705174496072,
|
|
"loss": 5.0362,
|
|
"mean_token_accuracy": 0.20373914688825606,
|
|
"num_tokens": 20117200.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.283761072158813,
|
|
"epoch": 0.9137988640160374,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004922627795704022,
|
|
"loss": 4.9198,
|
|
"mean_token_accuracy": 0.2127875030040741,
|
|
"num_tokens": 20126069.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.313186359405518,
|
|
"epoch": 0.9142165051787504,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004922550378877507,
|
|
"loss": 5.0235,
|
|
"mean_token_accuracy": 0.20618784427642822,
|
|
"num_tokens": 20136763.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.343409061431885,
|
|
"epoch": 0.9146341463414634,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004922472924017882,
|
|
"loss": 5.0624,
|
|
"mean_token_accuracy": 0.20051228553056716,
|
|
"num_tokens": 20145765.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.330703926086426,
|
|
"epoch": 0.9150517875041764,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922395431126506,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.20489881038665772,
|
|
"num_tokens": 20154504.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.280119132995606,
|
|
"epoch": 0.9154694286668894,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004922317900204732,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.20063123106956482,
|
|
"num_tokens": 20163903.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.29094820022583,
|
|
"epoch": 0.9158870698296024,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004922240331253916,
|
|
"loss": 4.9393,
|
|
"mean_token_accuracy": 0.21172392517328262,
|
|
"num_tokens": 20172910.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.256262540817261,
|
|
"epoch": 0.9163047109923154,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004922162724275421,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.2108933448791504,
|
|
"num_tokens": 20182238.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.252716398239135,
|
|
"epoch": 0.9167223521550284,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004922085079270602,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.20766966342926024,
|
|
"num_tokens": 20190673.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.306190252304077,
|
|
"epoch": 0.9171399933177414,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004922007396240819,
|
|
"loss": 5.1116,
|
|
"mean_token_accuracy": 0.19755789637565613,
|
|
"num_tokens": 20201219.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.303773069381714,
|
|
"epoch": 0.9175576344804544,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004921929675187433,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.20875435769557954,
|
|
"num_tokens": 20210756.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.326369047164917,
|
|
"epoch": 0.9179752756431674,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004921851916111802,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.2071087345480919,
|
|
"num_tokens": 20219959.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.271667957305908,
|
|
"epoch": 0.9183929168058804,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004921774119015289,
|
|
"loss": 4.9322,
|
|
"mean_token_accuracy": 0.20586028099060058,
|
|
"num_tokens": 20229633.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.199474811553955,
|
|
"epoch": 0.9188105579685933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004921696283899257,
|
|
"loss": 4.917,
|
|
"mean_token_accuracy": 0.2173251211643219,
|
|
"num_tokens": 20238355.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.32249264717102,
|
|
"epoch": 0.9192281991313064,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004921618410765067,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.19583073258399963,
|
|
"num_tokens": 20247461.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.348478078842163,
|
|
"epoch": 0.9196458402940194,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004921540499614083,
|
|
"loss": 5.069,
|
|
"mean_token_accuracy": 0.207705295085907,
|
|
"num_tokens": 20256505.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.288292598724365,
|
|
"epoch": 0.9200634814567323,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004921462550447669,
|
|
"loss": 4.9755,
|
|
"mean_token_accuracy": 0.20665141940116882,
|
|
"num_tokens": 20266169.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.19335241317749,
|
|
"epoch": 0.9204811226194454,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004921384563267189,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.21625247299671174,
|
|
"num_tokens": 20274620.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.274489450454712,
|
|
"epoch": 0.9208987637821584,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004921306538074008,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.20840287506580352,
|
|
"num_tokens": 20282829.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.234308338165283,
|
|
"epoch": 0.9213164049448713,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921228474869493,
|
|
"loss": 4.9744,
|
|
"mean_token_accuracy": 0.20824021100997925,
|
|
"num_tokens": 20292510.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.225999641418457,
|
|
"epoch": 0.9217340461075844,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000492115037365501,
|
|
"loss": 4.9453,
|
|
"mean_token_accuracy": 0.20515142381191254,
|
|
"num_tokens": 20302095.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.350071144104004,
|
|
"epoch": 0.9221516872702974,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004921072234431925,
|
|
"loss": 5.0103,
|
|
"mean_token_accuracy": 0.2087814375758171,
|
|
"num_tokens": 20310505.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.236289739608765,
|
|
"epoch": 0.9225693284330103,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000492099405720161,
|
|
"loss": 4.8911,
|
|
"mean_token_accuracy": 0.2151905208826065,
|
|
"num_tokens": 20319653.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.2699360847473145,
|
|
"epoch": 0.9229869695957233,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920915841965429,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.2085288554430008,
|
|
"num_tokens": 20329156.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.287440013885498,
|
|
"epoch": 0.9234046107584364,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004920837588724753,
|
|
"loss": 5.0504,
|
|
"mean_token_accuracy": 0.2025542750954628,
|
|
"num_tokens": 20338761.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.23920841217041,
|
|
"epoch": 0.9238222519211493,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004920759297480953,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.2100648120045662,
|
|
"num_tokens": 20347080.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.325594425201416,
|
|
"epoch": 0.9242398930838623,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920680968235397,
|
|
"loss": 5.0067,
|
|
"mean_token_accuracy": 0.20340287834405898,
|
|
"num_tokens": 20355824.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.267500591278076,
|
|
"epoch": 0.9246575342465754,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920602600989459,
|
|
"loss": 5.0091,
|
|
"mean_token_accuracy": 0.20724878907203675,
|
|
"num_tokens": 20365406.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.3728578090667725,
|
|
"epoch": 0.9250751754092883,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004920524195744509,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.20342708230018616,
|
|
"num_tokens": 20375153.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.334122371673584,
|
|
"epoch": 0.9254928165720013,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004920445752501921,
|
|
"loss": 5.0038,
|
|
"mean_token_accuracy": 0.21258741170167922,
|
|
"num_tokens": 20384402.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.309116458892822,
|
|
"epoch": 0.9259104577347144,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004920367271263066,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.2119446188211441,
|
|
"num_tokens": 20393913.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.170202255249023,
|
|
"epoch": 0.9263280988974273,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004920288752029321,
|
|
"loss": 4.8435,
|
|
"mean_token_accuracy": 0.2275947719812393,
|
|
"num_tokens": 20402391.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.335839366912841,
|
|
"epoch": 0.9267457400601403,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920210194802059,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.2070319399237633,
|
|
"num_tokens": 20411682.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.252764081954956,
|
|
"epoch": 0.9271633812228534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004920131599582654,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.20783103853464127,
|
|
"num_tokens": 20421764.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.364587736129761,
|
|
"epoch": 0.9275810223855663,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004920052966372485,
|
|
"loss": 5.0918,
|
|
"mean_token_accuracy": 0.19600590467453002,
|
|
"num_tokens": 20430420.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.343398904800415,
|
|
"epoch": 0.9279986635482793,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004919974295172926,
|
|
"loss": 5.0299,
|
|
"mean_token_accuracy": 0.20487948954105378,
|
|
"num_tokens": 20440037.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.217753887176514,
|
|
"epoch": 0.9284163047109923,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004919895585985353,
|
|
"loss": 4.935,
|
|
"mean_token_accuracy": 0.2131136640906334,
|
|
"num_tokens": 20448307.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.236877536773681,
|
|
"epoch": 0.9288339458737053,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004919816838811149,
|
|
"loss": 4.9169,
|
|
"mean_token_accuracy": 0.2137738883495331,
|
|
"num_tokens": 20456524.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.363579177856446,
|
|
"epoch": 0.9292515870364183,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004919738053651687,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20072562694549562,
|
|
"num_tokens": 20465352.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.347170686721801,
|
|
"epoch": 0.9296692281991313,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000491965923050835,
|
|
"loss": 4.9065,
|
|
"mean_token_accuracy": 0.21797690838575362,
|
|
"num_tokens": 20474634.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.274740743637085,
|
|
"epoch": 0.9300868693618443,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004919580369382516,
|
|
"loss": 4.9441,
|
|
"mean_token_accuracy": 0.20745591670274735,
|
|
"num_tokens": 20483359.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.298547172546387,
|
|
"epoch": 0.9305045105245573,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004919501470275567,
|
|
"loss": 5.0736,
|
|
"mean_token_accuracy": 0.20330417305231094,
|
|
"num_tokens": 20494251.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.233838176727295,
|
|
"epoch": 0.9309221516872703,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004919422533188882,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.21014939695596696,
|
|
"num_tokens": 20503277.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.22549467086792,
|
|
"epoch": 0.9313397928499833,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919343558123845,
|
|
"loss": 4.9874,
|
|
"mean_token_accuracy": 0.2057997390627861,
|
|
"num_tokens": 20513162.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.338308715820313,
|
|
"epoch": 0.9317574340126963,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004919264545081838,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20400698930025102,
|
|
"num_tokens": 20522438.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.311813592910767,
|
|
"epoch": 0.9321750751754093,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004919185494064244,
|
|
"loss": 5.0137,
|
|
"mean_token_accuracy": 0.19955204129219056,
|
|
"num_tokens": 20531666.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.275125026702881,
|
|
"epoch": 0.9325927163381222,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004919106405072446,
|
|
"loss": 4.9981,
|
|
"mean_token_accuracy": 0.21183069199323654,
|
|
"num_tokens": 20540593.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.313379383087158,
|
|
"epoch": 0.9330103575008353,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000491902727810783,
|
|
"loss": 5.0876,
|
|
"mean_token_accuracy": 0.19825908541679382,
|
|
"num_tokens": 20550850.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.285665512084961,
|
|
"epoch": 0.9334279986635483,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004918948113171781,
|
|
"loss": 4.9638,
|
|
"mean_token_accuracy": 0.20133431404829025,
|
|
"num_tokens": 20559954.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.294297695159912,
|
|
"epoch": 0.9338456398262612,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004918868910265684,
|
|
"loss": 4.9686,
|
|
"mean_token_accuracy": 0.20562165528535842,
|
|
"num_tokens": 20568750.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.31992883682251,
|
|
"epoch": 0.9342632809889743,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004918789669390927,
|
|
"loss": 4.9333,
|
|
"mean_token_accuracy": 0.20625250339508056,
|
|
"num_tokens": 20578615.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.355983924865723,
|
|
"epoch": 0.9346809221516873,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004918710390548895,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.2034828171133995,
|
|
"num_tokens": 20587390.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.303935718536377,
|
|
"epoch": 0.9350985633144002,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004918631073740977,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.20325606912374497,
|
|
"num_tokens": 20597179.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.281005001068115,
|
|
"epoch": 0.9355162044771133,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918551718968562,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.2086229369044304,
|
|
"num_tokens": 20606074.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.174286317825318,
|
|
"epoch": 0.9359338456398263,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000491847232623304,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.2200875461101532,
|
|
"num_tokens": 20614977.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.245162105560302,
|
|
"epoch": 0.9363514868025392,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004918392895535798,
|
|
"loss": 4.9533,
|
|
"mean_token_accuracy": 0.20189266800880432,
|
|
"num_tokens": 20623486.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.321696329116821,
|
|
"epoch": 0.9367691279652522,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000491831342687823,
|
|
"loss": 5.012,
|
|
"mean_token_accuracy": 0.2082706168293953,
|
|
"num_tokens": 20632780.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.345497417449951,
|
|
"epoch": 0.9371867691279653,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004918233920261723,
|
|
"loss": 4.9675,
|
|
"mean_token_accuracy": 0.20917925536632537,
|
|
"num_tokens": 20642662.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.189872217178345,
|
|
"epoch": 0.9376044102906782,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004918154375687673,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.20507752746343613,
|
|
"num_tokens": 20651612.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.339445638656616,
|
|
"epoch": 0.9380220514533912,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004918074793157472,
|
|
"loss": 4.9765,
|
|
"mean_token_accuracy": 0.21197497397661208,
|
|
"num_tokens": 20659940.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.398441314697266,
|
|
"epoch": 0.9384396926161043,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004917995172672511,
|
|
"loss": 4.9926,
|
|
"mean_token_accuracy": 0.20385115146636962,
|
|
"num_tokens": 20669004.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.24006929397583,
|
|
"epoch": 0.9388573337788172,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004917915514234184,
|
|
"loss": 4.9375,
|
|
"mean_token_accuracy": 0.20403863489627838,
|
|
"num_tokens": 20678469.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.269977664947509,
|
|
"epoch": 0.9392749749415302,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004917835817843887,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.2044987991452217,
|
|
"num_tokens": 20688368.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.312200975418091,
|
|
"epoch": 0.9396926161042433,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004917756083503014,
|
|
"loss": 5.0253,
|
|
"mean_token_accuracy": 0.20118874162435532,
|
|
"num_tokens": 20698002.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.259361410140992,
|
|
"epoch": 0.9401102572669562,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004917676311212962,
|
|
"loss": 4.8757,
|
|
"mean_token_accuracy": 0.21805861294269563,
|
|
"num_tokens": 20707798.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.292035436630249,
|
|
"epoch": 0.9405278984296692,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004917596500975127,
|
|
"loss": 5.0605,
|
|
"mean_token_accuracy": 0.20286330580711365,
|
|
"num_tokens": 20716328.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.3365460395812985,
|
|
"epoch": 0.9409455395923823,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004917516652790907,
|
|
"loss": 5.0313,
|
|
"mean_token_accuracy": 0.19615522027015686,
|
|
"num_tokens": 20726526.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.3934227466583256,
|
|
"epoch": 0.9413631807550952,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917436766661697,
|
|
"loss": 5.0219,
|
|
"mean_token_accuracy": 0.2018624171614647,
|
|
"num_tokens": 20735086.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.200656414031982,
|
|
"epoch": 0.9417808219178082,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049173568425889,
|
|
"loss": 4.9083,
|
|
"mean_token_accuracy": 0.2102491408586502,
|
|
"num_tokens": 20743677.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.306549787521362,
|
|
"epoch": 0.9421984630805212,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004917276880573911,
|
|
"loss": 5.0327,
|
|
"mean_token_accuracy": 0.20566902160644532,
|
|
"num_tokens": 20753351.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.342454719543457,
|
|
"epoch": 0.9426161042432342,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004917196880618132,
|
|
"loss": 5.0667,
|
|
"mean_token_accuracy": 0.20327116400003434,
|
|
"num_tokens": 20763654.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.409023809432983,
|
|
"epoch": 0.9430337454059472,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004917116842722962,
|
|
"loss": 5.0831,
|
|
"mean_token_accuracy": 0.1948322206735611,
|
|
"num_tokens": 20774424.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.374111366271973,
|
|
"epoch": 0.9434513865686602,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004917036766889804,
|
|
"loss": 5.0422,
|
|
"mean_token_accuracy": 0.20762633085250853,
|
|
"num_tokens": 20782975.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.296127700805664,
|
|
"epoch": 0.9438690277313732,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004916956653120058,
|
|
"loss": 4.8807,
|
|
"mean_token_accuracy": 0.22276984453201293,
|
|
"num_tokens": 20791943.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.313929653167724,
|
|
"epoch": 0.9442866688940862,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004916876501415129,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.20826699882745742,
|
|
"num_tokens": 20800920.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.26575345993042,
|
|
"epoch": 0.9447043100567992,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004916796311776417,
|
|
"loss": 4.9705,
|
|
"mean_token_accuracy": 0.20526081025600434,
|
|
"num_tokens": 20810284.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.347360754013062,
|
|
"epoch": 0.9451219512195121,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916716084205328,
|
|
"loss": 5.0238,
|
|
"mean_token_accuracy": 0.20144737362861634,
|
|
"num_tokens": 20819399.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.270338106155395,
|
|
"epoch": 0.9455395923822252,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004916635818703266,
|
|
"loss": 4.8587,
|
|
"mean_token_accuracy": 0.21626204252243042,
|
|
"num_tokens": 20827933.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.270012283325196,
|
|
"epoch": 0.9459572335449382,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004916555515271635,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.2057144582271576,
|
|
"num_tokens": 20836636.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.277413082122803,
|
|
"epoch": 0.9463748747076511,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004916475173911844,
|
|
"loss": 4.9444,
|
|
"mean_token_accuracy": 0.21231750398874283,
|
|
"num_tokens": 20845712.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.339170217514038,
|
|
"epoch": 0.9467925158703642,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916394794625296,
|
|
"loss": 4.9979,
|
|
"mean_token_accuracy": 0.20167570412158967,
|
|
"num_tokens": 20856874.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.331341171264649,
|
|
"epoch": 0.9472101570330772,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004916314377413399,
|
|
"loss": 5.0329,
|
|
"mean_token_accuracy": 0.2027890592813492,
|
|
"num_tokens": 20866829.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.3872312068939205,
|
|
"epoch": 0.9476277981957901,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004916233922277562,
|
|
"loss": 5.125,
|
|
"mean_token_accuracy": 0.20333950370550155,
|
|
"num_tokens": 20876409.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.347262620925903,
|
|
"epoch": 0.9480454393585032,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004916153429219192,
|
|
"loss": 5.038,
|
|
"mean_token_accuracy": 0.20568130910396576,
|
|
"num_tokens": 20886145.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.26878776550293,
|
|
"epoch": 0.9484630805212162,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004916072898239699,
|
|
"loss": 4.9682,
|
|
"mean_token_accuracy": 0.21085396111011506,
|
|
"num_tokens": 20895471.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.295267391204834,
|
|
"epoch": 0.9488807216839291,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004915992329340493,
|
|
"loss": 4.9474,
|
|
"mean_token_accuracy": 0.20530525892972945,
|
|
"num_tokens": 20904213.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.29747257232666,
|
|
"epoch": 0.9492983628466422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004915911722522984,
|
|
"loss": 5.0335,
|
|
"mean_token_accuracy": 0.21358608603477477,
|
|
"num_tokens": 20914028.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.370604372024536,
|
|
"epoch": 0.9497160040093552,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004915831077788583,
|
|
"loss": 5.0749,
|
|
"mean_token_accuracy": 0.2074764460325241,
|
|
"num_tokens": 20923514.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.303053951263427,
|
|
"epoch": 0.9501336451720681,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004915750395138702,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.2089749827980995,
|
|
"num_tokens": 20932072.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.199862337112426,
|
|
"epoch": 0.9505512863347811,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004915669674574754,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.21068890690803527,
|
|
"num_tokens": 20940438.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.287867498397827,
|
|
"epoch": 0.9509689274974942,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004915588916098151,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.20705017745494841,
|
|
"num_tokens": 20949217.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.31136302947998,
|
|
"epoch": 0.9513865686602071,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004915508119710307,
|
|
"loss": 4.9714,
|
|
"mean_token_accuracy": 0.21213664561510087,
|
|
"num_tokens": 20958123.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.2451191425323485,
|
|
"epoch": 0.9518042098229201,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004915427285412636,
|
|
"loss": 4.856,
|
|
"mean_token_accuracy": 0.21094325184822083,
|
|
"num_tokens": 20966908.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.2829122066497805,
|
|
"epoch": 0.9522218509856332,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004915346413206555,
|
|
"loss": 4.9753,
|
|
"mean_token_accuracy": 0.2136373221874237,
|
|
"num_tokens": 20975241.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.284571981430053,
|
|
"epoch": 0.9526394921483461,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915265503093478,
|
|
"loss": 4.9892,
|
|
"mean_token_accuracy": 0.20635112076997758,
|
|
"num_tokens": 20984336.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.277150630950928,
|
|
"epoch": 0.9530571333110591,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004915184555074824,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.21265217959880828,
|
|
"num_tokens": 20993703.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.28307089805603,
|
|
"epoch": 0.9534747744737722,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004915103569152005,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.21520542353391647,
|
|
"num_tokens": 21002993.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.378454065322876,
|
|
"epoch": 0.9538924156364851,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004915022545326444,
|
|
"loss": 5.0813,
|
|
"mean_token_accuracy": 0.19823065102100373,
|
|
"num_tokens": 21012380.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.261223888397216,
|
|
"epoch": 0.9543100567991981,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004914941483599558,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.20924108177423478,
|
|
"num_tokens": 21021585.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.224903583526611,
|
|
"epoch": 0.9547276979619111,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004914860383972763,
|
|
"loss": 4.9732,
|
|
"mean_token_accuracy": 0.214534130692482,
|
|
"num_tokens": 21030461.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.363995933532715,
|
|
"epoch": 0.9551453391246241,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004914779246447483,
|
|
"loss": 5.0906,
|
|
"mean_token_accuracy": 0.198251348733902,
|
|
"num_tokens": 21039654.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.316459321975708,
|
|
"epoch": 0.9555629802873371,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004914698071025136,
|
|
"loss": 5.0656,
|
|
"mean_token_accuracy": 0.2009978711605072,
|
|
"num_tokens": 21048564.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.322699165344238,
|
|
"epoch": 0.9559806214500501,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004914616857707143,
|
|
"loss": 5.0203,
|
|
"mean_token_accuracy": 0.20229019224643707,
|
|
"num_tokens": 21057378.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.288770246505737,
|
|
"epoch": 0.9563982626127631,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914535606494927,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.2173044800758362,
|
|
"num_tokens": 21066203.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.2841465950012205,
|
|
"epoch": 0.9568159037754761,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000491445431738991,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.2069260761141777,
|
|
"num_tokens": 21075432.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.3534728527069095,
|
|
"epoch": 0.9572335449381891,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004914372990393515,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.20837677121162415,
|
|
"num_tokens": 21084165.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.233235931396484,
|
|
"epoch": 0.957651186100902,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004914291625507164,
|
|
"loss": 4.9045,
|
|
"mean_token_accuracy": 0.21746279746294023,
|
|
"num_tokens": 21093075.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.287274789810181,
|
|
"epoch": 0.9580688272636151,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004914210222732284,
|
|
"loss": 4.94,
|
|
"mean_token_accuracy": 0.20684575140476227,
|
|
"num_tokens": 21101320.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.340948581695557,
|
|
"epoch": 0.9584864684263281,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004914128782070299,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.2028108924627304,
|
|
"num_tokens": 21110584.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.250833797454834,
|
|
"epoch": 0.958904109589041,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004914047303522636,
|
|
"loss": 4.8831,
|
|
"mean_token_accuracy": 0.2092112809419632,
|
|
"num_tokens": 21119558.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.240352535247803,
|
|
"epoch": 0.9593217507517541,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004913965787090718,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.21071923077106475,
|
|
"num_tokens": 21129143.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.289736938476563,
|
|
"epoch": 0.9597393919144671,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913884232775974,
|
|
"loss": 5.0374,
|
|
"mean_token_accuracy": 0.20636197477579116,
|
|
"num_tokens": 21139428.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.27970142364502,
|
|
"epoch": 0.96015703307718,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913802640579833,
|
|
"loss": 4.9668,
|
|
"mean_token_accuracy": 0.21000314503908157,
|
|
"num_tokens": 21148489.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.2396503448486325,
|
|
"epoch": 0.9605746742398931,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913721010503722,
|
|
"loss": 4.8712,
|
|
"mean_token_accuracy": 0.2121509477496147,
|
|
"num_tokens": 21157419.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.233207702636719,
|
|
"epoch": 0.9609923154026061,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000491363934254907,
|
|
"loss": 4.8969,
|
|
"mean_token_accuracy": 0.20998494178056717,
|
|
"num_tokens": 21166628.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.285282707214355,
|
|
"epoch": 0.961409956565319,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004913557636717307,
|
|
"loss": 4.9774,
|
|
"mean_token_accuracy": 0.20113057494163514,
|
|
"num_tokens": 21176335.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.3234803676605225,
|
|
"epoch": 0.9618275977280321,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004913475893009864,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.21436670273542405,
|
|
"num_tokens": 21184485.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.377234935760498,
|
|
"epoch": 0.9622452388907451,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000491339411142817,
|
|
"loss": 5.0058,
|
|
"mean_token_accuracy": 0.2069265589118004,
|
|
"num_tokens": 21194216.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.277431058883667,
|
|
"epoch": 0.962662880053458,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004913312291973659,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.19919504970312119,
|
|
"num_tokens": 21203902.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.24494161605835,
|
|
"epoch": 0.963080521216171,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004913230434647762,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.2198522984981537,
|
|
"num_tokens": 21212618.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.298515176773071,
|
|
"epoch": 0.9634981623788841,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004913148539451912,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.20470901429653168,
|
|
"num_tokens": 21221820.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.252080965042114,
|
|
"epoch": 0.963915803541597,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004913066606387544,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.20308583825826645,
|
|
"num_tokens": 21231085.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.238254404067993,
|
|
"epoch": 0.96433344470431,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000491298463545609,
|
|
"loss": 4.9585,
|
|
"mean_token_accuracy": 0.2077096402645111,
|
|
"num_tokens": 21240184.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.290735673904419,
|
|
"epoch": 0.9647510858670231,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004912902626658988,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.2127323254942894,
|
|
"num_tokens": 21249085.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.284249877929687,
|
|
"epoch": 0.965168727029736,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004912820579997672,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21872651875019072,
|
|
"num_tokens": 21258188.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.236255693435669,
|
|
"epoch": 0.965586368192449,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004912738495473577,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.21281397938728333,
|
|
"num_tokens": 21267223.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.314878034591675,
|
|
"epoch": 0.9660040093551621,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004912656373088142,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.21394867449998856,
|
|
"num_tokens": 21276503.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.302453184127808,
|
|
"epoch": 0.9664216505178751,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004912574212842804,
|
|
"loss": 5.0291,
|
|
"mean_token_accuracy": 0.20277022570371628,
|
|
"num_tokens": 21286775.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.25169792175293,
|
|
"epoch": 0.966839291680588,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004912492014739001,
|
|
"loss": 4.9238,
|
|
"mean_token_accuracy": 0.21492058485746385,
|
|
"num_tokens": 21295956.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.276896953582764,
|
|
"epoch": 0.967256932843301,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004912409778778173,
|
|
"loss": 4.9464,
|
|
"mean_token_accuracy": 0.2050861358642578,
|
|
"num_tokens": 21305050.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.20089201927185,
|
|
"epoch": 0.9676745740060141,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004912327504961758,
|
|
"loss": 4.8865,
|
|
"mean_token_accuracy": 0.20798760056495666,
|
|
"num_tokens": 21313732.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.225341558456421,
|
|
"epoch": 0.968092215168727,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004912245193291198,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21240306347608567,
|
|
"num_tokens": 21322526.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.376803827285767,
|
|
"epoch": 0.96850985633144,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004912162843767932,
|
|
"loss": 5.0565,
|
|
"mean_token_accuracy": 0.19928446114063264,
|
|
"num_tokens": 21332243.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.3471533298492435,
|
|
"epoch": 0.9689274974941531,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004912080456393404,
|
|
"loss": 4.9799,
|
|
"mean_token_accuracy": 0.20539722591638565,
|
|
"num_tokens": 21340827.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.311161661148072,
|
|
"epoch": 0.969345138656866,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004911998031169056,
|
|
"loss": 4.9303,
|
|
"mean_token_accuracy": 0.21907938420772552,
|
|
"num_tokens": 21350506.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.244030284881592,
|
|
"epoch": 0.969762779819579,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004911915568096328,
|
|
"loss": 4.8673,
|
|
"mean_token_accuracy": 0.21808142364025115,
|
|
"num_tokens": 21359690.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.345354986190796,
|
|
"epoch": 0.9701804209822921,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004911833067176666,
|
|
"loss": 5.0339,
|
|
"mean_token_accuracy": 0.19799952507019042,
|
|
"num_tokens": 21368953.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.449045181274414,
|
|
"epoch": 0.970598062145005,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004911750528411515,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.1986107662320137,
|
|
"num_tokens": 21379015.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.237863445281983,
|
|
"epoch": 0.971015703307718,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004911667951802318,
|
|
"loss": 4.9102,
|
|
"mean_token_accuracy": 0.2116827115416527,
|
|
"num_tokens": 21388555.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.2393883228302,
|
|
"epoch": 0.9714333444704311,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004911585337350524,
|
|
"loss": 5.0513,
|
|
"mean_token_accuracy": 0.1984583854675293,
|
|
"num_tokens": 21399011.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.333369302749634,
|
|
"epoch": 0.971850985633144,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911502685057573,
|
|
"loss": 4.9949,
|
|
"mean_token_accuracy": 0.20397056192159652,
|
|
"num_tokens": 21408711.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.3743212699890135,
|
|
"epoch": 0.972268626795857,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004911419994924918,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.20577232837677,
|
|
"num_tokens": 21417995.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.31250524520874,
|
|
"epoch": 0.97268626795857,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004911337266954004,
|
|
"loss": 5.0099,
|
|
"mean_token_accuracy": 0.19857528805732727,
|
|
"num_tokens": 21426550.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.228099155426025,
|
|
"epoch": 0.973103909121283,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004911254501146279,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21550876945257186,
|
|
"num_tokens": 21435396.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.2208034038543705,
|
|
"epoch": 0.973521550283996,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004911171697503193,
|
|
"loss": 4.8282,
|
|
"mean_token_accuracy": 0.21877573132514955,
|
|
"num_tokens": 21445156.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.258206081390381,
|
|
"epoch": 0.973939191446709,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004911088856026194,
|
|
"loss": 5.0411,
|
|
"mean_token_accuracy": 0.20361632704734803,
|
|
"num_tokens": 21454924.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.298038005828857,
|
|
"epoch": 0.974356832609422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004911005976716734,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.2093232810497284,
|
|
"num_tokens": 21465062.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.254428672790527,
|
|
"epoch": 0.974774473772135,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004910923059576264,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.20237172693014144,
|
|
"num_tokens": 21473744.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.229976749420166,
|
|
"epoch": 0.975192114934848,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004910840104606234,
|
|
"loss": 4.9562,
|
|
"mean_token_accuracy": 0.21244654059410095,
|
|
"num_tokens": 21482913.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.313730716705322,
|
|
"epoch": 0.975609756097561,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004910757111808097,
|
|
"loss": 5.0596,
|
|
"mean_token_accuracy": 0.20069590210914612,
|
|
"num_tokens": 21491551.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.300209474563599,
|
|
"epoch": 0.976027397260274,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004910674081183305,
|
|
"loss": 4.9403,
|
|
"mean_token_accuracy": 0.20909209847450255,
|
|
"num_tokens": 21500389.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.3261474609375,
|
|
"epoch": 0.976445038422987,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004910591012733313,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.2048298016190529,
|
|
"num_tokens": 21509720.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.292244863510132,
|
|
"epoch": 0.9768626795857,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004910507906459575,
|
|
"loss": 5.0123,
|
|
"mean_token_accuracy": 0.20616686344146729,
|
|
"num_tokens": 21519326.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.290464067459107,
|
|
"epoch": 0.977280320748413,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004910424762363545,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.20929498523473739,
|
|
"num_tokens": 21528326.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.309686231613159,
|
|
"epoch": 0.977697961911126,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000491034158044668,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.21281250864267348,
|
|
"num_tokens": 21536662.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.226805353164673,
|
|
"epoch": 0.9781156030738389,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004910258360710434,
|
|
"loss": 4.9244,
|
|
"mean_token_accuracy": 0.21122912764549256,
|
|
"num_tokens": 21545222.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.279647588729858,
|
|
"epoch": 0.978533244236552,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910175103156266,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.2151697412133217,
|
|
"num_tokens": 21554051.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.237771368026733,
|
|
"epoch": 0.978950885399265,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004910091807785632,
|
|
"loss": 4.9112,
|
|
"mean_token_accuracy": 0.21219869405031205,
|
|
"num_tokens": 21562031.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.241698312759399,
|
|
"epoch": 0.9793685265619779,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004910008474599991,
|
|
"loss": 4.8556,
|
|
"mean_token_accuracy": 0.2162618577480316,
|
|
"num_tokens": 21570758.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.274776554107666,
|
|
"epoch": 0.979786167724691,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004909925103600801,
|
|
"loss": 4.9495,
|
|
"mean_token_accuracy": 0.2146730199456215,
|
|
"num_tokens": 21579605.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.3157305240631105,
|
|
"epoch": 0.980203808887404,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909841694789523,
|
|
"loss": 5.0396,
|
|
"mean_token_accuracy": 0.19625861793756486,
|
|
"num_tokens": 21588719.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.431564569473267,
|
|
"epoch": 0.9806214500501169,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004909758248167616,
|
|
"loss": 5.0871,
|
|
"mean_token_accuracy": 0.19370762407779693,
|
|
"num_tokens": 21598038.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.344277000427246,
|
|
"epoch": 0.98103909121283,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004909674763736542,
|
|
"loss": 5.0392,
|
|
"mean_token_accuracy": 0.2021482467651367,
|
|
"num_tokens": 21607378.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.27409553527832,
|
|
"epoch": 0.981456732375543,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004909591241497761,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.212735678255558,
|
|
"num_tokens": 21616470.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.384966707229614,
|
|
"epoch": 0.9818743735382559,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004909507681452736,
|
|
"loss": 5.0143,
|
|
"mean_token_accuracy": 0.2016165778040886,
|
|
"num_tokens": 21626005.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.293928766250611,
|
|
"epoch": 0.9822920147009689,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004909424083602929,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.2216232255101204,
|
|
"num_tokens": 21635620.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.2013486385345455,
|
|
"epoch": 0.982709655863682,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004909340447949805,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.21165000200271605,
|
|
"num_tokens": 21644846.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.235617303848267,
|
|
"epoch": 0.9831272970263949,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004909256774494827,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.2114097148180008,
|
|
"num_tokens": 21653275.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.316766023635864,
|
|
"epoch": 0.9835449381891079,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000490917306323946,
|
|
"loss": 4.9978,
|
|
"mean_token_accuracy": 0.20615476965904236,
|
|
"num_tokens": 21661709.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.299030113220215,
|
|
"epoch": 0.983962579351821,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004909089314185169,
|
|
"loss": 5.0057,
|
|
"mean_token_accuracy": 0.20231498181819915,
|
|
"num_tokens": 21672409.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.350260782241821,
|
|
"epoch": 0.9843802205145339,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004909005527333421,
|
|
"loss": 4.8681,
|
|
"mean_token_accuracy": 0.21751368790864944,
|
|
"num_tokens": 21680818.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.34231858253479,
|
|
"epoch": 0.9847978616772469,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004908921702685683,
|
|
"loss": 5.0109,
|
|
"mean_token_accuracy": 0.21705520302057266,
|
|
"num_tokens": 21689572.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.252370309829712,
|
|
"epoch": 0.98521550283996,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004908837840243421,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.2052754506468773,
|
|
"num_tokens": 21698244.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.271486711502075,
|
|
"epoch": 0.9856331440026729,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004908753940008105,
|
|
"loss": 4.8701,
|
|
"mean_token_accuracy": 0.22707632631063462,
|
|
"num_tokens": 21706532.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.231799507141114,
|
|
"epoch": 0.9860507851653859,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004908670001981201,
|
|
"loss": 4.9218,
|
|
"mean_token_accuracy": 0.2163535788655281,
|
|
"num_tokens": 21715386.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.214222192764282,
|
|
"epoch": 0.986468426328099,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908586026164182,
|
|
"loss": 4.9239,
|
|
"mean_token_accuracy": 0.2111831098794937,
|
|
"num_tokens": 21724544.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.391922235488892,
|
|
"epoch": 0.9868860674908119,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004908502012558516,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.20145853161811828,
|
|
"num_tokens": 21734453.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.297837114334106,
|
|
"epoch": 0.9873037086535249,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004908417961165674,
|
|
"loss": 4.9419,
|
|
"mean_token_accuracy": 0.20611570179462432,
|
|
"num_tokens": 21744243.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.217907047271728,
|
|
"epoch": 0.9877213498162379,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004908333871987126,
|
|
"loss": 4.8819,
|
|
"mean_token_accuracy": 0.21511097252368927,
|
|
"num_tokens": 21751843.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.223396492004395,
|
|
"epoch": 0.9881389909789509,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004908249745024347,
|
|
"loss": 4.8919,
|
|
"mean_token_accuracy": 0.20840270072221756,
|
|
"num_tokens": 21760812.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.29658260345459,
|
|
"epoch": 0.9885566321416639,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000490816558027881,
|
|
"loss": 4.8963,
|
|
"mean_token_accuracy": 0.21393621563911439,
|
|
"num_tokens": 21769460.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.258234977722168,
|
|
"epoch": 0.9889742733043769,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004908081377751985,
|
|
"loss": 4.8801,
|
|
"mean_token_accuracy": 0.21869006603956223,
|
|
"num_tokens": 21778440.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.308716583251953,
|
|
"epoch": 0.9893919144670899,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004907997137445347,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.2028886541724205,
|
|
"num_tokens": 21787708.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.260091066360474,
|
|
"epoch": 0.9898095556298029,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004907912859360373,
|
|
"loss": 4.9062,
|
|
"mean_token_accuracy": 0.21266570687294006,
|
|
"num_tokens": 21796517.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.25144853591919,
|
|
"epoch": 0.9902271967925159,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004907828543498536,
|
|
"loss": 4.909,
|
|
"mean_token_accuracy": 0.21517527401447295,
|
|
"num_tokens": 21805833.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.279707288742065,
|
|
"epoch": 0.9906448379552288,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004907744189861313,
|
|
"loss": 4.9564,
|
|
"mean_token_accuracy": 0.21202875375747682,
|
|
"num_tokens": 21815953.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.342713499069214,
|
|
"epoch": 0.9910624791179419,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000490765979845018,
|
|
"loss": 4.9477,
|
|
"mean_token_accuracy": 0.20468706786632537,
|
|
"num_tokens": 21824780.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.2657012939453125,
|
|
"epoch": 0.9914801202806549,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004907575369266617,
|
|
"loss": 4.9497,
|
|
"mean_token_accuracy": 0.2018110543489456,
|
|
"num_tokens": 21834514.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.292583084106445,
|
|
"epoch": 0.9918977614433678,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004907490902312099,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.21520423740148545,
|
|
"num_tokens": 21844090.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.276777553558349,
|
|
"epoch": 0.9923154026060809,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004907406397588106,
|
|
"loss": 4.9531,
|
|
"mean_token_accuracy": 0.21337115317583083,
|
|
"num_tokens": 21852982.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.287903308868408,
|
|
"epoch": 0.9927330437687939,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004907321855096117,
|
|
"loss": 5.0397,
|
|
"mean_token_accuracy": 0.2024641141295433,
|
|
"num_tokens": 21862734.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.415623140335083,
|
|
"epoch": 0.9931506849315068,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004907237274837613,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.2056353360414505,
|
|
"num_tokens": 21871927.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.238947629928589,
|
|
"epoch": 0.9935683260942199,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004907152656814072,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.2155211627483368,
|
|
"num_tokens": 21881409.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.262485122680664,
|
|
"epoch": 0.9939859672569329,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004907068001026978,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.2158389762043953,
|
|
"num_tokens": 21890324.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.252199411392212,
|
|
"epoch": 0.9944036084196458,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004906983307477813,
|
|
"loss": 4.8822,
|
|
"mean_token_accuracy": 0.21921912729740142,
|
|
"num_tokens": 21898352.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.291586446762085,
|
|
"epoch": 0.9948212495823588,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004906898576168057,
|
|
"loss": 4.9176,
|
|
"mean_token_accuracy": 0.21006711274385453,
|
|
"num_tokens": 21906972.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.335603713989258,
|
|
"epoch": 0.9952388907450719,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004906813807099197,
|
|
"loss": 5.0027,
|
|
"mean_token_accuracy": 0.21121777594089508,
|
|
"num_tokens": 21916304.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.288942432403564,
|
|
"epoch": 0.9956565319077848,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004906729000272714,
|
|
"loss": 5.0039,
|
|
"mean_token_accuracy": 0.20206081569194795,
|
|
"num_tokens": 21926393.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.320159101486206,
|
|
"epoch": 0.9960741730704978,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004906644155690095,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.2059588372707367,
|
|
"num_tokens": 21935657.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.317689752578735,
|
|
"epoch": 0.9964918142332109,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004906559273352823,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.2049526169896126,
|
|
"num_tokens": 21945170.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.320736217498779,
|
|
"epoch": 0.9969094553959238,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004906474353262386,
|
|
"loss": 4.9999,
|
|
"mean_token_accuracy": 0.2098765030503273,
|
|
"num_tokens": 21954043.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.377010488510132,
|
|
"epoch": 0.9973270965586368,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906389395420269,
|
|
"loss": 5.1193,
|
|
"mean_token_accuracy": 0.2001539021730423,
|
|
"num_tokens": 21963716.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.437428045272827,
|
|
"epoch": 0.9977447377213499,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000490630439982796,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.2011202484369278,
|
|
"num_tokens": 21973059.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.320317029953003,
|
|
"epoch": 0.9981623788840628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004906219366486947,
|
|
"loss": 5.0064,
|
|
"mean_token_accuracy": 0.1961218908429146,
|
|
"num_tokens": 21983189.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.219368410110474,
|
|
"epoch": 0.9985800200467758,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004906134295398719,
|
|
"loss": 4.8837,
|
|
"mean_token_accuracy": 0.219818677008152,
|
|
"num_tokens": 21992124.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.215649175643921,
|
|
"epoch": 0.9989976612094889,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004906049186564764,
|
|
"loss": 4.9051,
|
|
"mean_token_accuracy": 0.20576963126659392,
|
|
"num_tokens": 22002075.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.3437916278839115,
|
|
"epoch": 0.9994153023722018,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004905964039986574,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.19821561723947526,
|
|
"num_tokens": 22010831.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.320625638961792,
|
|
"epoch": 0.9998329435349148,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004905878855665637,
|
|
"loss": 4.9794,
|
|
"mean_token_accuracy": 0.20407988280057907,
|
|
"num_tokens": 22020270.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.327650737762451,
|
|
"epoch": 1.0002505846976277,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004905793633603446,
|
|
"loss": 4.9131,
|
|
"mean_token_accuracy": 0.21265690326690673,
|
|
"num_tokens": 22030413.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.280015134811402,
|
|
"epoch": 1.0006682258603408,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004905708373801492,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.21518293917179107,
|
|
"num_tokens": 22040420.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.365551280975342,
|
|
"epoch": 1.0010858670230538,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004905623076261269,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.20414592921733857,
|
|
"num_tokens": 22049901.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.2825493812561035,
|
|
"epoch": 1.0015035081857668,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000490553774098427,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.20693850815296172,
|
|
"num_tokens": 22058939.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.217721748352051,
|
|
"epoch": 1.0019211493484799,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004905452367971986,
|
|
"loss": 4.7918,
|
|
"mean_token_accuracy": 0.2233424335718155,
|
|
"num_tokens": 22067553.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.259334373474121,
|
|
"epoch": 1.0023387905111927,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004905366957225916,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.20890826135873794,
|
|
"num_tokens": 22076264.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0023387905111927,
|
|
"eval_entropy": 5.056694016570738,
|
|
"eval_loss": 4.924590110778809,
|
|
"eval_mean_token_accuracy": 0.22129064991050695,
|
|
"eval_num_tokens": 22076264.0,
|
|
"eval_runtime": 45.8139,
|
|
"eval_samples_per_second": 824.27,
|
|
"eval_steps_per_second": 103.047,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.246809005737305,
|
|
"epoch": 1.0027564316739057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004905281508747552,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.2205996483564377,
|
|
"num_tokens": 22085033.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.265406513214112,
|
|
"epoch": 1.0031740728366187,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004905196022538391,
|
|
"loss": 4.9132,
|
|
"mean_token_accuracy": 0.20308529138565062,
|
|
"num_tokens": 22094619.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.307168054580688,
|
|
"epoch": 1.0035917139993318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490511049859993,
|
|
"loss": 4.9331,
|
|
"mean_token_accuracy": 0.21664617359638214,
|
|
"num_tokens": 22103611.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.39004430770874,
|
|
"epoch": 1.0040093551620448,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004905024936933664,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.2079549804329872,
|
|
"num_tokens": 22112478.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.270122480392456,
|
|
"epoch": 1.0044269963247578,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004904939337541093,
|
|
"loss": 4.7898,
|
|
"mean_token_accuracy": 0.21323963850736619,
|
|
"num_tokens": 22121969.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.29180154800415,
|
|
"epoch": 1.0048446374874707,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004904853700423716,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.21474773287773133,
|
|
"num_tokens": 22131241.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.248391008377075,
|
|
"epoch": 1.0052622786501837,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004904768025583031,
|
|
"loss": 4.8711,
|
|
"mean_token_accuracy": 0.21420881152153015,
|
|
"num_tokens": 22140473.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.315644025802612,
|
|
"epoch": 1.0056799198128967,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004904682313020537,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.2080448731780052,
|
|
"num_tokens": 22150071.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.391983270645142,
|
|
"epoch": 1.0060975609756098,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004904596562737737,
|
|
"loss": 5.0138,
|
|
"mean_token_accuracy": 0.20491338819265364,
|
|
"num_tokens": 22159665.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.257573843002319,
|
|
"epoch": 1.0065152021383228,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000490451077473613,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21317777931690216,
|
|
"num_tokens": 22168856.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.2508502960205075,
|
|
"epoch": 1.0069328433010358,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004904424949017218,
|
|
"loss": 4.8923,
|
|
"mean_token_accuracy": 0.21343611627817155,
|
|
"num_tokens": 22177550.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.281982278823852,
|
|
"epoch": 1.0073504844637486,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004904339085582504,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.22298264354467393,
|
|
"num_tokens": 22186839.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.374949216842651,
|
|
"epoch": 1.0077681256264617,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004904253184433491,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.21002558916807174,
|
|
"num_tokens": 22196865.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.2034296035766605,
|
|
"epoch": 1.0081857667891747,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004904167245571684,
|
|
"loss": 4.8315,
|
|
"mean_token_accuracy": 0.21533747911453247,
|
|
"num_tokens": 22205140.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.21571159362793,
|
|
"epoch": 1.0086034079518877,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004904081268998586,
|
|
"loss": 4.8156,
|
|
"mean_token_accuracy": 0.2168579950928688,
|
|
"num_tokens": 22214846.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.353195095062256,
|
|
"epoch": 1.0090210491146008,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004903995254715702,
|
|
"loss": 4.9406,
|
|
"mean_token_accuracy": 0.2021574929356575,
|
|
"num_tokens": 22222984.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.326009511947632,
|
|
"epoch": 1.0094386902773138,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903909202724539,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.21061499267816544,
|
|
"num_tokens": 22231995.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.285386419296264,
|
|
"epoch": 1.0098563314400266,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903823113026602,
|
|
"loss": 4.8709,
|
|
"mean_token_accuracy": 0.22359912991523742,
|
|
"num_tokens": 22240354.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.300979804992676,
|
|
"epoch": 1.0102739726027397,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00049037369856234,
|
|
"loss": 4.9421,
|
|
"mean_token_accuracy": 0.20800324082374572,
|
|
"num_tokens": 22249866.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.326562738418579,
|
|
"epoch": 1.0106916137654527,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004903650820516438,
|
|
"loss": 4.928,
|
|
"mean_token_accuracy": 0.20360100418329238,
|
|
"num_tokens": 22258837.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.305313777923584,
|
|
"epoch": 1.0111092549281657,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004903564617707227,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.22058717757463456,
|
|
"num_tokens": 22268035.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.235574579238891,
|
|
"epoch": 1.0115268960908788,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903478377197275,
|
|
"loss": 4.7793,
|
|
"mean_token_accuracy": 0.21906282901763915,
|
|
"num_tokens": 22277251.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.179210138320923,
|
|
"epoch": 1.0119445372535918,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004903392098988092,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.21609960347414017,
|
|
"num_tokens": 22286269.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.229155969619751,
|
|
"epoch": 1.0123621784163046,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004903305783081188,
|
|
"loss": 4.8107,
|
|
"mean_token_accuracy": 0.21513462513685228,
|
|
"num_tokens": 22294671.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.208030080795288,
|
|
"epoch": 1.0127798195790176,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004903219429478075,
|
|
"loss": 4.8008,
|
|
"mean_token_accuracy": 0.22222669124603273,
|
|
"num_tokens": 22304448.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.308165407180786,
|
|
"epoch": 1.0131974607417307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004903133038180263,
|
|
"loss": 5.0045,
|
|
"mean_token_accuracy": 0.20136084109544755,
|
|
"num_tokens": 22314425.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.256166791915893,
|
|
"epoch": 1.0136151019044437,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004903046609189266,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.21119165867567063,
|
|
"num_tokens": 22324390.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.207523345947266,
|
|
"epoch": 1.0140327430671567,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004902960142506597,
|
|
"loss": 4.8309,
|
|
"mean_token_accuracy": 0.2127667561173439,
|
|
"num_tokens": 22333274.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.235506772994995,
|
|
"epoch": 1.0144503842298698,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004902873638133768,
|
|
"loss": 4.876,
|
|
"mean_token_accuracy": 0.22109102010726928,
|
|
"num_tokens": 22342480.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.243493556976318,
|
|
"epoch": 1.0148680253925826,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004902787096072296,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.21722892671823502,
|
|
"num_tokens": 22351105.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.2132933139801025,
|
|
"epoch": 1.0152856665552956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004902700516323693,
|
|
"loss": 4.8463,
|
|
"mean_token_accuracy": 0.21939685940742493,
|
|
"num_tokens": 22360567.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.3150389194488525,
|
|
"epoch": 1.0157033077180087,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004902613898889477,
|
|
"loss": 4.9052,
|
|
"mean_token_accuracy": 0.21238097846508025,
|
|
"num_tokens": 22370140.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.221841478347779,
|
|
"epoch": 1.0161209488807217,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004902527243771164,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.22859495431184768,
|
|
"num_tokens": 22378676.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.227549600601196,
|
|
"epoch": 1.0165385900434347,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000490244055097027,
|
|
"loss": 4.8631,
|
|
"mean_token_accuracy": 0.20926012247800826,
|
|
"num_tokens": 22387411.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.316168975830078,
|
|
"epoch": 1.0169562312061478,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004902353820488314,
|
|
"loss": 4.9433,
|
|
"mean_token_accuracy": 0.20667811036109923,
|
|
"num_tokens": 22397023.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.267161083221436,
|
|
"epoch": 1.0173738723688606,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004902267052326812,
|
|
"loss": 4.8381,
|
|
"mean_token_accuracy": 0.2157186061143875,
|
|
"num_tokens": 22406730.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.357573318481445,
|
|
"epoch": 1.0177915135315736,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004902180246487285,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.20715391486883164,
|
|
"num_tokens": 22416920.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.253149557113647,
|
|
"epoch": 1.0182091546942866,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004902093402971254,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.21363817304372787,
|
|
"num_tokens": 22426073.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.325179719924927,
|
|
"epoch": 1.0186267958569997,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004902006521780236,
|
|
"loss": 4.9294,
|
|
"mean_token_accuracy": 0.21335553228855134,
|
|
"num_tokens": 22436291.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.159155321121216,
|
|
"epoch": 1.0190444370197127,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004901919602915754,
|
|
"loss": 4.8734,
|
|
"mean_token_accuracy": 0.20914125591516494,
|
|
"num_tokens": 22446053.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.296555280685425,
|
|
"epoch": 1.0194620781824257,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004901832646379328,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.20908380895853043,
|
|
"num_tokens": 22455474.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.273329591751098,
|
|
"epoch": 1.0198797193451385,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004901745652172483,
|
|
"loss": 4.854,
|
|
"mean_token_accuracy": 0.22174932658672333,
|
|
"num_tokens": 22464953.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.2175013542175295,
|
|
"epoch": 1.0202973605078516,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000490165862029674,
|
|
"loss": 4.7924,
|
|
"mean_token_accuracy": 0.21431187987327577,
|
|
"num_tokens": 22474076.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.252267122268677,
|
|
"epoch": 1.0207150016705646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004901571550753622,
|
|
"loss": 4.8501,
|
|
"mean_token_accuracy": 0.21205525547266008,
|
|
"num_tokens": 22483128.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.385244464874267,
|
|
"epoch": 1.0211326428332776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004901484443544655,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.20639538019895554,
|
|
"num_tokens": 22492239.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.3584372997283936,
|
|
"epoch": 1.0215502839959907,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004901397298671362,
|
|
"loss": 5.0232,
|
|
"mean_token_accuracy": 0.2036021888256073,
|
|
"num_tokens": 22500996.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.302613687515259,
|
|
"epoch": 1.0219679251587037,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004901310116135271,
|
|
"loss": 4.8664,
|
|
"mean_token_accuracy": 0.21133332550525666,
|
|
"num_tokens": 22510524.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.289977359771728,
|
|
"epoch": 1.0223855663214167,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004901222895937905,
|
|
"loss": 4.8637,
|
|
"mean_token_accuracy": 0.21150947660207747,
|
|
"num_tokens": 22519499.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.228893566131592,
|
|
"epoch": 1.0228032074841296,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004901135638080796,
|
|
"loss": 4.7641,
|
|
"mean_token_accuracy": 0.21870095431804656,
|
|
"num_tokens": 22528380.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.3199084281921385,
|
|
"epoch": 1.0232208486468426,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004901048342565465,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20651179999113084,
|
|
"num_tokens": 22537488.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.243310499191284,
|
|
"epoch": 1.0236384898095556,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004900961009393445,
|
|
"loss": 4.9107,
|
|
"mean_token_accuracy": 0.21264176517724992,
|
|
"num_tokens": 22547093.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.175053215026855,
|
|
"epoch": 1.0240561309722687,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004900873638566263,
|
|
"loss": 4.7953,
|
|
"mean_token_accuracy": 0.21935492902994155,
|
|
"num_tokens": 22555996.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.254518175125122,
|
|
"epoch": 1.0244737721349817,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000490078623008545,
|
|
"loss": 4.9049,
|
|
"mean_token_accuracy": 0.20648833066225053,
|
|
"num_tokens": 22565582.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.277912187576294,
|
|
"epoch": 1.0248914132976945,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004900698783952533,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.2035459727048874,
|
|
"num_tokens": 22575181.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.347463226318359,
|
|
"epoch": 1.0253090544604075,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004900611300169048,
|
|
"loss": 4.9358,
|
|
"mean_token_accuracy": 0.20913406908512117,
|
|
"num_tokens": 22584799.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.262407445907593,
|
|
"epoch": 1.0257266956231206,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900523778736521,
|
|
"loss": 4.7415,
|
|
"mean_token_accuracy": 0.22797274440526963,
|
|
"num_tokens": 22593235.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.255698585510254,
|
|
"epoch": 1.0261443367858336,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004900436219656488,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.2087998792529106,
|
|
"num_tokens": 22603435.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.282780742645263,
|
|
"epoch": 1.0265619779485466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000490034862293048,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.20927974730730056,
|
|
"num_tokens": 22612739.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.296806192398071,
|
|
"epoch": 1.0269796191112597,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004900260988560031,
|
|
"loss": 4.9419,
|
|
"mean_token_accuracy": 0.2125260427594185,
|
|
"num_tokens": 22622633.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.234863424301148,
|
|
"epoch": 1.0273972602739727,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004900173316546675,
|
|
"loss": 4.7751,
|
|
"mean_token_accuracy": 0.22701316922903061,
|
|
"num_tokens": 22631428.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.374781131744385,
|
|
"epoch": 1.0278149014366855,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004900085606891947,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.212162284553051,
|
|
"num_tokens": 22639557.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.344132947921753,
|
|
"epoch": 1.0282325425993986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899997859597382,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.21700177043676377,
|
|
"num_tokens": 22648134.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.224088382720947,
|
|
"epoch": 1.0286501837621116,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004899910074664518,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.2239394813776016,
|
|
"num_tokens": 22657083.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.240394115447998,
|
|
"epoch": 1.0290678249248246,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004899822252094889,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20932259410619736,
|
|
"num_tokens": 22666724.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.272408151626587,
|
|
"epoch": 1.0294854660875377,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004899734391890034,
|
|
"loss": 4.9051,
|
|
"mean_token_accuracy": 0.21296626925468445,
|
|
"num_tokens": 22675955.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.324677133560181,
|
|
"epoch": 1.0299031072502507,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004899646494051491,
|
|
"loss": 4.9026,
|
|
"mean_token_accuracy": 0.2088274136185646,
|
|
"num_tokens": 22686838.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.355966091156006,
|
|
"epoch": 1.0303207484129635,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004899558558580798,
|
|
"loss": 4.9852,
|
|
"mean_token_accuracy": 0.20080111026763917,
|
|
"num_tokens": 22696257.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.203815746307373,
|
|
"epoch": 1.0307383895756765,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004899470585479495,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.21742138266563416,
|
|
"num_tokens": 22705726.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.2529621601104735,
|
|
"epoch": 1.0311560307383896,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004899382574749124,
|
|
"loss": 4.9037,
|
|
"mean_token_accuracy": 0.21096795946359634,
|
|
"num_tokens": 22714765.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.35432538986206,
|
|
"epoch": 1.0315736719011026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004899294526391221,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.20978816598653793,
|
|
"num_tokens": 22723423.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.307466316223144,
|
|
"epoch": 1.0319913130638156,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004899206440407332,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.20794116854667663,
|
|
"num_tokens": 22733276.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.274510908126831,
|
|
"epoch": 1.0324089542265287,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004899118316798996,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.21883702427148818,
|
|
"num_tokens": 22742422.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.236082124710083,
|
|
"epoch": 1.0328265953892415,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004899030155567759,
|
|
"loss": 4.8181,
|
|
"mean_token_accuracy": 0.20870425105094909,
|
|
"num_tokens": 22751649.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.2808863639831545,
|
|
"epoch": 1.0332442365519545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000489894195671516,
|
|
"loss": 4.9448,
|
|
"mean_token_accuracy": 0.20261846631765365,
|
|
"num_tokens": 22760411.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.374655485153198,
|
|
"epoch": 1.0336618777146676,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004898853720242747,
|
|
"loss": 4.9473,
|
|
"mean_token_accuracy": 0.21155185699462892,
|
|
"num_tokens": 22769289.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.283149671554566,
|
|
"epoch": 1.0340795188773806,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004898765446152062,
|
|
"loss": 4.8594,
|
|
"mean_token_accuracy": 0.21647396087646484,
|
|
"num_tokens": 22778988.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.329295110702515,
|
|
"epoch": 1.0344971600400936,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898677134444652,
|
|
"loss": 4.9815,
|
|
"mean_token_accuracy": 0.21008906364440919,
|
|
"num_tokens": 22788115.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.303075647354126,
|
|
"epoch": 1.0349148012028067,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004898588785122063,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.21420614868402482,
|
|
"num_tokens": 22797840.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.232848644256592,
|
|
"epoch": 1.0353324423655195,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004898500398185841,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.2235892027616501,
|
|
"num_tokens": 22805947.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.303641319274902,
|
|
"epoch": 1.0357500835282325,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004898411973637532,
|
|
"loss": 4.8753,
|
|
"mean_token_accuracy": 0.20754227340221404,
|
|
"num_tokens": 22816104.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.275610828399659,
|
|
"epoch": 1.0361677246909455,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004898323511478686,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.21395995765924453,
|
|
"num_tokens": 22824994.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.343665933609008,
|
|
"epoch": 1.0365853658536586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004898235011710851,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.20883876979351043,
|
|
"num_tokens": 22834649.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.247687244415284,
|
|
"epoch": 1.0370030070163716,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004898146474335577,
|
|
"loss": 4.7689,
|
|
"mean_token_accuracy": 0.22501306235790253,
|
|
"num_tokens": 22843060.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.258506345748901,
|
|
"epoch": 1.0374206481790846,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004898057899354412,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.22048294246196748,
|
|
"num_tokens": 22852429.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.219359827041626,
|
|
"epoch": 1.0378382893417974,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000489796928676891,
|
|
"loss": 4.834,
|
|
"mean_token_accuracy": 0.21665908992290497,
|
|
"num_tokens": 22861170.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.200287818908691,
|
|
"epoch": 1.0382559305045105,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004897880636580618,
|
|
"loss": 4.8222,
|
|
"mean_token_accuracy": 0.21934612840414047,
|
|
"num_tokens": 22870030.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.232861423492432,
|
|
"epoch": 1.0386735716672235,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489779194879109,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21988009959459304,
|
|
"num_tokens": 22878728.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.330334281921386,
|
|
"epoch": 1.0390912128299366,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000489770322340188,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.20863900631666182,
|
|
"num_tokens": 22887625.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.189791822433472,
|
|
"epoch": 1.0395088539926496,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004897614460414539,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.22721462547779084,
|
|
"num_tokens": 22896791.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.247493600845337,
|
|
"epoch": 1.0399264951553626,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004897525659830623,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.21134709119796752,
|
|
"num_tokens": 22907228.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.182691240310669,
|
|
"epoch": 1.0403441363180754,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004897436821651683,
|
|
"loss": 4.7175,
|
|
"mean_token_accuracy": 0.2239181101322174,
|
|
"num_tokens": 22915108.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.139223575592041,
|
|
"epoch": 1.0407617774807885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004897347945879278,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.22129716873168945,
|
|
"num_tokens": 22924092.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.172150325775147,
|
|
"epoch": 1.0411794186435015,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004897259032514963,
|
|
"loss": 4.8,
|
|
"mean_token_accuracy": 0.21257222294807435,
|
|
"num_tokens": 22932285.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.261834239959716,
|
|
"epoch": 1.0415970598062145,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004897170081560292,
|
|
"loss": 4.8449,
|
|
"mean_token_accuracy": 0.217219477891922,
|
|
"num_tokens": 22940727.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.314929342269897,
|
|
"epoch": 1.0420147009689276,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004897081093016827,
|
|
"loss": 4.9283,
|
|
"mean_token_accuracy": 0.20554616749286653,
|
|
"num_tokens": 22949678.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.26433310508728,
|
|
"epoch": 1.0424323421316406,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004896992066886121,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.20889280140399932,
|
|
"num_tokens": 22959295.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.305531978607178,
|
|
"epoch": 1.0428499832943534,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004896903003169735,
|
|
"loss": 4.8615,
|
|
"mean_token_accuracy": 0.21151233315467835,
|
|
"num_tokens": 22968883.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.2837104320526125,
|
|
"epoch": 1.0432676244570664,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004896813901869229,
|
|
"loss": 4.911,
|
|
"mean_token_accuracy": 0.2054387077689171,
|
|
"num_tokens": 22978199.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.268492221832275,
|
|
"epoch": 1.0436852656197795,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004896724762986159,
|
|
"loss": 4.8732,
|
|
"mean_token_accuracy": 0.2163829892873764,
|
|
"num_tokens": 22987236.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.289384365081787,
|
|
"epoch": 1.0441029067824925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004896635586522089,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.21869356334209442,
|
|
"num_tokens": 22996293.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.285279178619385,
|
|
"epoch": 1.0445205479452055,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004896546372478581,
|
|
"loss": 4.9288,
|
|
"mean_token_accuracy": 0.2129640981554985,
|
|
"num_tokens": 23006415.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.28571081161499,
|
|
"epoch": 1.0449381891079186,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896457120857192,
|
|
"loss": 4.9266,
|
|
"mean_token_accuracy": 0.2084796756505966,
|
|
"num_tokens": 23015819.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.261923885345459,
|
|
"epoch": 1.0453558302706314,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000489636783165949,
|
|
"loss": 4.7985,
|
|
"mean_token_accuracy": 0.21745622307062148,
|
|
"num_tokens": 23024206.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.334952640533447,
|
|
"epoch": 1.0457734714333444,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004896278504887033,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.20604425966739653,
|
|
"num_tokens": 23034003.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.306336879730225,
|
|
"epoch": 1.0461911125960575,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489618914054139,
|
|
"loss": 4.9268,
|
|
"mean_token_accuracy": 0.21041675359010698,
|
|
"num_tokens": 23043514.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.303295612335205,
|
|
"epoch": 1.0466087537587705,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000489609973862412,
|
|
"loss": 4.865,
|
|
"mean_token_accuracy": 0.20901357531547546,
|
|
"num_tokens": 23053029.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.323730373382569,
|
|
"epoch": 1.0470263949214835,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004896010299136793,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.2130068987607956,
|
|
"num_tokens": 23062465.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.244287014007568,
|
|
"epoch": 1.0474440360841966,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004895920822080972,
|
|
"loss": 4.8441,
|
|
"mean_token_accuracy": 0.21172131448984147,
|
|
"num_tokens": 23071448.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.316421937942505,
|
|
"epoch": 1.0478616772469094,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895831307458224,
|
|
"loss": 4.9336,
|
|
"mean_token_accuracy": 0.20748321563005448,
|
|
"num_tokens": 23081882.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.3214373111724855,
|
|
"epoch": 1.0482793184096224,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004895741755270115,
|
|
"loss": 4.91,
|
|
"mean_token_accuracy": 0.2157897934317589,
|
|
"num_tokens": 23090723.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.218851232528687,
|
|
"epoch": 1.0486969595723354,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004895652165518215,
|
|
"loss": 4.7531,
|
|
"mean_token_accuracy": 0.22482918351888656,
|
|
"num_tokens": 23099246.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.215344333648682,
|
|
"epoch": 1.0491146007350485,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004895562538204091,
|
|
"loss": 4.8294,
|
|
"mean_token_accuracy": 0.22352291494607926,
|
|
"num_tokens": 23107538.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.252891778945923,
|
|
"epoch": 1.0495322418977615,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004895472873329311,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.21693438291549683,
|
|
"num_tokens": 23116996.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.233146619796753,
|
|
"epoch": 1.0499498830604745,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004895383170895447,
|
|
"loss": 4.8149,
|
|
"mean_token_accuracy": 0.21810064911842347,
|
|
"num_tokens": 23126778.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.293397378921509,
|
|
"epoch": 1.0503675242231874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004895293430904067,
|
|
"loss": 4.8877,
|
|
"mean_token_accuracy": 0.21864828765392302,
|
|
"num_tokens": 23135929.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.202874994277954,
|
|
"epoch": 1.0507851653859004,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004895203653356745,
|
|
"loss": 4.826,
|
|
"mean_token_accuracy": 0.21563326120376586,
|
|
"num_tokens": 23144369.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.269008016586303,
|
|
"epoch": 1.0512028065486134,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004895113838255049,
|
|
"loss": 4.8407,
|
|
"mean_token_accuracy": 0.21469895392656327,
|
|
"num_tokens": 23152813.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.2409507751464846,
|
|
"epoch": 1.0516204477113265,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004895023985600555,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.20796194076538085,
|
|
"num_tokens": 23161826.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.242619180679322,
|
|
"epoch": 1.0520380888740395,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004894934095394832,
|
|
"loss": 4.8281,
|
|
"mean_token_accuracy": 0.21420652717351912,
|
|
"num_tokens": 23170757.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.280904388427734,
|
|
"epoch": 1.0524557300367525,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004894844167639458,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.21356096267700195,
|
|
"num_tokens": 23179348.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.275903177261353,
|
|
"epoch": 1.0528733711994653,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004894754202336004,
|
|
"loss": 4.9098,
|
|
"mean_token_accuracy": 0.2077879637479782,
|
|
"num_tokens": 23188643.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.1799873352050785,
|
|
"epoch": 1.0532910123621784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004894664199486047,
|
|
"loss": 4.8041,
|
|
"mean_token_accuracy": 0.21431031972169876,
|
|
"num_tokens": 23197595.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.274394798278808,
|
|
"epoch": 1.0537086535248914,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894574159091161,
|
|
"loss": 4.802,
|
|
"mean_token_accuracy": 0.22180366963148118,
|
|
"num_tokens": 23206463.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.304717302322388,
|
|
"epoch": 1.0541262946876044,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004894484081152922,
|
|
"loss": 4.9534,
|
|
"mean_token_accuracy": 0.20685575604438783,
|
|
"num_tokens": 23215740.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.271686220169068,
|
|
"epoch": 1.0545439358503175,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004894393965672909,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.21370041370391846,
|
|
"num_tokens": 23226046.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.325798606872558,
|
|
"epoch": 1.0549615770130305,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004894303812652698,
|
|
"loss": 4.8862,
|
|
"mean_token_accuracy": 0.20680003464221955,
|
|
"num_tokens": 23234905.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.219187164306641,
|
|
"epoch": 1.0553792181757433,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004894213622093867,
|
|
"loss": 4.7777,
|
|
"mean_token_accuracy": 0.2163815751671791,
|
|
"num_tokens": 23243392.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.264422988891601,
|
|
"epoch": 1.0557968593384564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004894123393997997,
|
|
"loss": 4.8334,
|
|
"mean_token_accuracy": 0.21219051778316497,
|
|
"num_tokens": 23253276.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.220353031158448,
|
|
"epoch": 1.0562145005011694,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004894033128366665,
|
|
"loss": 4.8119,
|
|
"mean_token_accuracy": 0.2194204017519951,
|
|
"num_tokens": 23262336.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.262905836105347,
|
|
"epoch": 1.0566321416638824,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004893942825201453,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.21300832480192183,
|
|
"num_tokens": 23272103.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.3164060592651365,
|
|
"epoch": 1.0570497828265955,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000489385248450394,
|
|
"loss": 4.9674,
|
|
"mean_token_accuracy": 0.20830277502536773,
|
|
"num_tokens": 23281253.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.272291755676269,
|
|
"epoch": 1.0574674239893085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000489376210627571,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.21539395451545715,
|
|
"num_tokens": 23289920.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.272904777526856,
|
|
"epoch": 1.0578850651520213,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004893671690518343,
|
|
"loss": 4.9025,
|
|
"mean_token_accuracy": 0.21367832124233246,
|
|
"num_tokens": 23299052.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.314483165740967,
|
|
"epoch": 1.0583027063147343,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004893581237233423,
|
|
"loss": 4.9351,
|
|
"mean_token_accuracy": 0.2174665719270706,
|
|
"num_tokens": 23307782.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.343705844879151,
|
|
"epoch": 1.0587203474774474,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004893490746422533,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.20708404183387757,
|
|
"num_tokens": 23317302.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.249320936203003,
|
|
"epoch": 1.0591379886401604,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004893400218087258,
|
|
"loss": 4.8001,
|
|
"mean_token_accuracy": 0.21396278738975524,
|
|
"num_tokens": 23325899.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.288690233230591,
|
|
"epoch": 1.0595556298028734,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004893309652229183,
|
|
"loss": 4.8677,
|
|
"mean_token_accuracy": 0.21665596663951875,
|
|
"num_tokens": 23335121.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.306689119338989,
|
|
"epoch": 1.0599732709655865,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004893219048849891,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.21091147661209106,
|
|
"num_tokens": 23345377.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.302104330062866,
|
|
"epoch": 1.0603909121282993,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004893128407950971,
|
|
"loss": 4.9264,
|
|
"mean_token_accuracy": 0.2062322601675987,
|
|
"num_tokens": 23353963.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.2655562400817875,
|
|
"epoch": 1.0608085532910123,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004893037729534007,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.2237083911895752,
|
|
"num_tokens": 23363744.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.25923867225647,
|
|
"epoch": 1.0612261944537253,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004892947013600589,
|
|
"loss": 4.8298,
|
|
"mean_token_accuracy": 0.21450933665037156,
|
|
"num_tokens": 23372241.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.270337820053101,
|
|
"epoch": 1.0616438356164384,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004892856260152304,
|
|
"loss": 4.8592,
|
|
"mean_token_accuracy": 0.21690657883882522,
|
|
"num_tokens": 23380733.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.331677007675171,
|
|
"epoch": 1.0620614767791514,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000489276546919074,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.2083763912320137,
|
|
"num_tokens": 23389916.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.235184526443481,
|
|
"epoch": 1.0624791179418644,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004892674640717488,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.22123125940561295,
|
|
"num_tokens": 23398394.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.31439847946167,
|
|
"epoch": 1.0628967591045773,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004892583774734138,
|
|
"loss": 4.962,
|
|
"mean_token_accuracy": 0.20556977540254592,
|
|
"num_tokens": 23408294.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.271951341629029,
|
|
"epoch": 1.0633144002672903,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004892492871242278,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.209499591588974,
|
|
"num_tokens": 23417301.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.315945291519165,
|
|
"epoch": 1.0637320414300033,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004892401930243504,
|
|
"loss": 4.8946,
|
|
"mean_token_accuracy": 0.2094876676797867,
|
|
"num_tokens": 23426992.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.257646799087524,
|
|
"epoch": 1.0641496825927164,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892310951739404,
|
|
"loss": 4.857,
|
|
"mean_token_accuracy": 0.2149661213159561,
|
|
"num_tokens": 23435480.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.28791766166687,
|
|
"epoch": 1.0645673237554294,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004892219935731571,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.21583802700042726,
|
|
"num_tokens": 23444436.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.256935977935791,
|
|
"epoch": 1.0649849649181424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048921288822216,
|
|
"loss": 4.7818,
|
|
"mean_token_accuracy": 0.22258649170398712,
|
|
"num_tokens": 23452913.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.157002735137939,
|
|
"epoch": 1.0654026060808552,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004892037791211086,
|
|
"loss": 4.845,
|
|
"mean_token_accuracy": 0.21187103539705276,
|
|
"num_tokens": 23462078.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.21531343460083,
|
|
"epoch": 1.0658202472435683,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004891946662701621,
|
|
"loss": 4.8361,
|
|
"mean_token_accuracy": 0.21349118053913116,
|
|
"num_tokens": 23470224.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.275239038467407,
|
|
"epoch": 1.0662378884062813,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004891855496694801,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.2095652386546135,
|
|
"num_tokens": 23478820.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.363530063629151,
|
|
"epoch": 1.0666555295689943,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004891764293192222,
|
|
"loss": 4.9449,
|
|
"mean_token_accuracy": 0.21117118000984192,
|
|
"num_tokens": 23488396.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.345733690261841,
|
|
"epoch": 1.0670731707317074,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004891673052195482,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.21150419116020203,
|
|
"num_tokens": 23497778.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.346113681793213,
|
|
"epoch": 1.0674908118944204,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004891581773706177,
|
|
"loss": 5.0496,
|
|
"mean_token_accuracy": 0.19934436827898025,
|
|
"num_tokens": 23506637.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.276606655120849,
|
|
"epoch": 1.0679084530571332,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004891490457725906,
|
|
"loss": 4.9412,
|
|
"mean_token_accuracy": 0.2122051790356636,
|
|
"num_tokens": 23515830.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.299188566207886,
|
|
"epoch": 1.0683260942198463,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004891399104256266,
|
|
"loss": 4.8984,
|
|
"mean_token_accuracy": 0.20973681658506393,
|
|
"num_tokens": 23525646.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.340732192993164,
|
|
"epoch": 1.0687437353825593,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004891307713298857,
|
|
"loss": 4.9202,
|
|
"mean_token_accuracy": 0.210468028485775,
|
|
"num_tokens": 23535319.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.2757823944091795,
|
|
"epoch": 1.0691613765452723,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000489121628485528,
|
|
"loss": 4.9253,
|
|
"mean_token_accuracy": 0.20886609852313995,
|
|
"num_tokens": 23544275.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.274276638031006,
|
|
"epoch": 1.0695790177079854,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004891124818927133,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.21344413459300995,
|
|
"num_tokens": 23553782.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.23857102394104,
|
|
"epoch": 1.0699966588706984,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004891033315516019,
|
|
"loss": 4.7062,
|
|
"mean_token_accuracy": 0.22099323719739913,
|
|
"num_tokens": 23562718.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.310618925094604,
|
|
"epoch": 1.0704143000334112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004890941774623541,
|
|
"loss": 4.9004,
|
|
"mean_token_accuracy": 0.2124182775616646,
|
|
"num_tokens": 23572374.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.238804149627685,
|
|
"epoch": 1.0708319411961242,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004890850196251299,
|
|
"loss": 4.8036,
|
|
"mean_token_accuracy": 0.21885028928518296,
|
|
"num_tokens": 23581227.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.2372599124908445,
|
|
"epoch": 1.0712495823588373,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004890758580400898,
|
|
"loss": 4.8264,
|
|
"mean_token_accuracy": 0.2182935208082199,
|
|
"num_tokens": 23591120.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.247696876525879,
|
|
"epoch": 1.0716672235215503,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004890666927073941,
|
|
"loss": 4.8356,
|
|
"mean_token_accuracy": 0.21578808426856994,
|
|
"num_tokens": 23599584.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.283841180801391,
|
|
"epoch": 1.0720848646842633,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004890575236272032,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.2147333800792694,
|
|
"num_tokens": 23609479.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.290532827377319,
|
|
"epoch": 1.0725025058469764,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004890483507996778,
|
|
"loss": 4.8531,
|
|
"mean_token_accuracy": 0.21915708035230635,
|
|
"num_tokens": 23618662.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.340745449066162,
|
|
"epoch": 1.0729201470096892,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004890391742249783,
|
|
"loss": 4.971,
|
|
"mean_token_accuracy": 0.20816505700349808,
|
|
"num_tokens": 23628268.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.3096489906311035,
|
|
"epoch": 1.0733377881724022,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004890299939032654,
|
|
"loss": 4.878,
|
|
"mean_token_accuracy": 0.21064930707216262,
|
|
"num_tokens": 23637538.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.294584941864014,
|
|
"epoch": 1.0737554293351153,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004890208098346999,
|
|
"loss": 4.9905,
|
|
"mean_token_accuracy": 0.2008451759815216,
|
|
"num_tokens": 23647425.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.325083684921265,
|
|
"epoch": 1.0741730704978283,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004890116220194425,
|
|
"loss": 4.9906,
|
|
"mean_token_accuracy": 0.207221382856369,
|
|
"num_tokens": 23656310.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.327293539047242,
|
|
"epoch": 1.0745907116605413,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000489002430457654,
|
|
"loss": 4.8964,
|
|
"mean_token_accuracy": 0.2117558717727661,
|
|
"num_tokens": 23664658.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.355808401107788,
|
|
"epoch": 1.0750083528232544,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004889932351494954,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.2197593405842781,
|
|
"num_tokens": 23674396.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.309822845458984,
|
|
"epoch": 1.0754259939859672,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004889840360951277,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.22368940711021423,
|
|
"num_tokens": 23682549.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.274024629592896,
|
|
"epoch": 1.0758436351486802,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004889748332947118,
|
|
"loss": 4.8806,
|
|
"mean_token_accuracy": 0.2104768618941307,
|
|
"num_tokens": 23692334.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.28533296585083,
|
|
"epoch": 1.0762612763113932,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004889656267484089,
|
|
"loss": 4.8694,
|
|
"mean_token_accuracy": 0.2119373455643654,
|
|
"num_tokens": 23702081.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.337715911865234,
|
|
"epoch": 1.0766789174741063,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048895641645638,
|
|
"loss": 4.9457,
|
|
"mean_token_accuracy": 0.2102488249540329,
|
|
"num_tokens": 23711019.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.328818941116333,
|
|
"epoch": 1.0770965586368193,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004889472024187867,
|
|
"loss": 4.8482,
|
|
"mean_token_accuracy": 0.2179038181900978,
|
|
"num_tokens": 23719660.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.287744188308716,
|
|
"epoch": 1.0775141997995323,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048893798463579,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.21076500713825225,
|
|
"num_tokens": 23728937.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.229873561859131,
|
|
"epoch": 1.0779318409622451,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004889287631075513,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.21785372048616408,
|
|
"num_tokens": 23738530.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.285984516143799,
|
|
"epoch": 1.0783494821249582,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004889195378342322,
|
|
"loss": 4.9134,
|
|
"mean_token_accuracy": 0.2135392501950264,
|
|
"num_tokens": 23748285.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.273105049133301,
|
|
"epoch": 1.0787671232876712,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004889103088159941,
|
|
"loss": 4.8626,
|
|
"mean_token_accuracy": 0.20783385634422302,
|
|
"num_tokens": 23758312.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.358125638961792,
|
|
"epoch": 1.0791847644503842,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004889010760529986,
|
|
"loss": 4.9717,
|
|
"mean_token_accuracy": 0.2055422842502594,
|
|
"num_tokens": 23767092.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.3877147197723385,
|
|
"epoch": 1.0796024056130973,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888918395454071,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.20713424533605576,
|
|
"num_tokens": 23776257.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.356147146224975,
|
|
"epoch": 1.0800200467758103,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004888825992933817,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.1992855653166771,
|
|
"num_tokens": 23785311.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.225370836257935,
|
|
"epoch": 1.0804376879385231,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004888733552970839,
|
|
"loss": 4.8841,
|
|
"mean_token_accuracy": 0.21173476278781891,
|
|
"num_tokens": 23795050.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.3725183486938475,
|
|
"epoch": 1.0808553291012362,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004888641075566755,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.21569675207138062,
|
|
"num_tokens": 23803959.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.332688236236573,
|
|
"epoch": 1.0812729702639492,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888548560723184,
|
|
"loss": 4.83,
|
|
"mean_token_accuracy": 0.2111940860748291,
|
|
"num_tokens": 23813568.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.295133924484253,
|
|
"epoch": 1.0816906114266622,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888456008441748,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.20616151094436647,
|
|
"num_tokens": 23823076.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.203731870651245,
|
|
"epoch": 1.0821082525893753,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004888363418724064,
|
|
"loss": 4.7713,
|
|
"mean_token_accuracy": 0.2262434706091881,
|
|
"num_tokens": 23831624.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.294639253616333,
|
|
"epoch": 1.0825258937520883,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004888270791571756,
|
|
"loss": 4.9136,
|
|
"mean_token_accuracy": 0.2109811410307884,
|
|
"num_tokens": 23841054.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.299885845184326,
|
|
"epoch": 1.082943534914801,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004888178126986444,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.2062146082520485,
|
|
"num_tokens": 23851190.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.316627931594849,
|
|
"epoch": 1.0833611760775141,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004888085424969748,
|
|
"loss": 4.8979,
|
|
"mean_token_accuracy": 0.22755252569913864,
|
|
"num_tokens": 23859560.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.2599893569946286,
|
|
"epoch": 1.0837788172402272,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004887992685523295,
|
|
"loss": 4.8823,
|
|
"mean_token_accuracy": 0.21547191590070724,
|
|
"num_tokens": 23869103.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.218966007232666,
|
|
"epoch": 1.0841964584029402,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004887899908648706,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.21841607838869095,
|
|
"num_tokens": 23877641.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.298699808120728,
|
|
"epoch": 1.0846140995656532,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004887807094347606,
|
|
"loss": 4.9222,
|
|
"mean_token_accuracy": 0.21484084725379943,
|
|
"num_tokens": 23886671.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.2424522876739506,
|
|
"epoch": 1.0850317407283663,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004887714242621619,
|
|
"loss": 4.8364,
|
|
"mean_token_accuracy": 0.22110432833433152,
|
|
"num_tokens": 23895781.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.30145525932312,
|
|
"epoch": 1.085449381891079,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004887621353472371,
|
|
"loss": 4.9733,
|
|
"mean_token_accuracy": 0.21105241328477858,
|
|
"num_tokens": 23904478.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.3344789981842045,
|
|
"epoch": 1.0858670230537921,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004887528426901488,
|
|
"loss": 4.8693,
|
|
"mean_token_accuracy": 0.20795080959796905,
|
|
"num_tokens": 23913899.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.26324691772461,
|
|
"epoch": 1.0862846642165052,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004887435462910597,
|
|
"loss": 4.9518,
|
|
"mean_token_accuracy": 0.20975328832864762,
|
|
"num_tokens": 23923583.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.3348548412323,
|
|
"epoch": 1.0867023053792182,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004887342461501326,
|
|
"loss": 4.9273,
|
|
"mean_token_accuracy": 0.207862688601017,
|
|
"num_tokens": 23932392.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.399308824539185,
|
|
"epoch": 1.0871199465419312,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004887249422675301,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.19642797559499742,
|
|
"num_tokens": 23941480.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.2896442890167235,
|
|
"epoch": 1.0875375877046443,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004887156346434154,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.2117832988500595,
|
|
"num_tokens": 23950720.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.267007303237915,
|
|
"epoch": 1.087955228867357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004887063232779513,
|
|
"loss": 4.8225,
|
|
"mean_token_accuracy": 0.21915109306573868,
|
|
"num_tokens": 23959441.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.298937273025513,
|
|
"epoch": 1.08837287003007,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004886970081713006,
|
|
"loss": 4.8493,
|
|
"mean_token_accuracy": 0.21189857870340348,
|
|
"num_tokens": 23968638.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.27697720527649,
|
|
"epoch": 1.0887905111927831,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004886876893236266,
|
|
"loss": 4.9001,
|
|
"mean_token_accuracy": 0.2122112914919853,
|
|
"num_tokens": 23977820.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.243701410293579,
|
|
"epoch": 1.0892081523554962,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004886783667350925,
|
|
"loss": 4.7878,
|
|
"mean_token_accuracy": 0.22236406803131104,
|
|
"num_tokens": 23986674.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.272480440139771,
|
|
"epoch": 1.0896257935182092,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004886690404058613,
|
|
"loss": 4.9057,
|
|
"mean_token_accuracy": 0.2160531237721443,
|
|
"num_tokens": 23995647.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.335162258148193,
|
|
"epoch": 1.0900434346809222,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004886597103360963,
|
|
"loss": 4.8477,
|
|
"mean_token_accuracy": 0.2172822579741478,
|
|
"num_tokens": 24004440.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.344361305236816,
|
|
"epoch": 1.090461075843635,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004886503765259609,
|
|
"loss": 4.978,
|
|
"mean_token_accuracy": 0.20818854123353958,
|
|
"num_tokens": 24014632.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.296687602996826,
|
|
"epoch": 1.090878717006348,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004886410389756186,
|
|
"loss": 4.812,
|
|
"mean_token_accuracy": 0.21960192620754243,
|
|
"num_tokens": 24024096.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.219444513320923,
|
|
"epoch": 1.0912963581690611,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004886316976852326,
|
|
"loss": 4.8433,
|
|
"mean_token_accuracy": 0.21302777230739595,
|
|
"num_tokens": 24033410.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.256748867034912,
|
|
"epoch": 1.0917139993317742,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004886223526549666,
|
|
"loss": 4.9053,
|
|
"mean_token_accuracy": 0.21537299305200577,
|
|
"num_tokens": 24043110.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.29110279083252,
|
|
"epoch": 1.0921316404944872,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004886130038849843,
|
|
"loss": 4.8956,
|
|
"mean_token_accuracy": 0.21182889640331268,
|
|
"num_tokens": 24052393.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.354882287979126,
|
|
"epoch": 1.0925492816572002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004886036513754491,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.21071390211582183,
|
|
"num_tokens": 24061086.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.302862691879272,
|
|
"epoch": 1.092966922819913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004885942951265251,
|
|
"loss": 4.9287,
|
|
"mean_token_accuracy": 0.20985956788063048,
|
|
"num_tokens": 24070494.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.242587947845459,
|
|
"epoch": 1.093384563982626,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004885849351383756,
|
|
"loss": 4.7881,
|
|
"mean_token_accuracy": 0.220012104511261,
|
|
"num_tokens": 24080740.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.250574970245362,
|
|
"epoch": 1.093802205145339,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004885755714111649,
|
|
"loss": 4.8505,
|
|
"mean_token_accuracy": 0.2137792408466339,
|
|
"num_tokens": 24090372.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.280078983306884,
|
|
"epoch": 1.0942198463080521,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004885662039450565,
|
|
"loss": 4.9007,
|
|
"mean_token_accuracy": 0.21208566576242446,
|
|
"num_tokens": 24099294.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.299003791809082,
|
|
"epoch": 1.0946374874707652,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004885568327402149,
|
|
"loss": 4.8742,
|
|
"mean_token_accuracy": 0.21682745665311814,
|
|
"num_tokens": 24108066.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.308969354629516,
|
|
"epoch": 1.0950551286334782,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004885474577968038,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.2048403337597847,
|
|
"num_tokens": 24118070.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.349172067642212,
|
|
"epoch": 1.095472769796191,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004885380791149874,
|
|
"loss": 4.9309,
|
|
"mean_token_accuracy": 0.21517109572887422,
|
|
"num_tokens": 24127314.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.329885482788086,
|
|
"epoch": 1.095890410958904,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004885286966949298,
|
|
"loss": 4.9529,
|
|
"mean_token_accuracy": 0.21105244904756545,
|
|
"num_tokens": 24136440.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.280307149887085,
|
|
"epoch": 1.096308052121617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004885193105367955,
|
|
"loss": 4.9656,
|
|
"mean_token_accuracy": 0.20456818491220474,
|
|
"num_tokens": 24146268.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.309845209121704,
|
|
"epoch": 1.0967256932843301,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004885099206407486,
|
|
"loss": 4.8661,
|
|
"mean_token_accuracy": 0.22280244827270507,
|
|
"num_tokens": 24156034.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.3573150634765625,
|
|
"epoch": 1.0971433344470432,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004885005270069535,
|
|
"loss": 4.8874,
|
|
"mean_token_accuracy": 0.2113825261592865,
|
|
"num_tokens": 24165001.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.217966890335083,
|
|
"epoch": 1.0975609756097562,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004884911296355746,
|
|
"loss": 4.8279,
|
|
"mean_token_accuracy": 0.21781458407640458,
|
|
"num_tokens": 24174490.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.296054124832153,
|
|
"epoch": 1.097978616772469,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004884817285267766,
|
|
"loss": 4.9515,
|
|
"mean_token_accuracy": 0.20683279931545256,
|
|
"num_tokens": 24184471.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.325363731384277,
|
|
"epoch": 1.098396257935182,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004884723236807239,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.21301867812871933,
|
|
"num_tokens": 24193219.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.344966793060303,
|
|
"epoch": 1.098813899097895,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004884629150975814,
|
|
"loss": 4.9325,
|
|
"mean_token_accuracy": 0.210093691945076,
|
|
"num_tokens": 24202138.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.26617317199707,
|
|
"epoch": 1.099231540260608,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004884535027775135,
|
|
"loss": 4.8629,
|
|
"mean_token_accuracy": 0.21267833858728408,
|
|
"num_tokens": 24211689.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.209694671630859,
|
|
"epoch": 1.0996491814233211,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004884440867206851,
|
|
"loss": 4.8159,
|
|
"mean_token_accuracy": 0.21995905339717864,
|
|
"num_tokens": 24221822.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.306625127792358,
|
|
"epoch": 1.1000668225860342,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000488434666927261,
|
|
"loss": 4.9577,
|
|
"mean_token_accuracy": 0.20468082278966904,
|
|
"num_tokens": 24231504.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.289003229141235,
|
|
"epoch": 1.100484463748747,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004884252433974062,
|
|
"loss": 4.8682,
|
|
"mean_token_accuracy": 0.20972338914871216,
|
|
"num_tokens": 24240855.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.248393917083741,
|
|
"epoch": 1.10090210491146,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004884158161312856,
|
|
"loss": 4.7806,
|
|
"mean_token_accuracy": 0.22080374956130983,
|
|
"num_tokens": 24249659.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.231697082519531,
|
|
"epoch": 1.101319746074173,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004884063851290642,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.21091266572475434,
|
|
"num_tokens": 24259277.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.247213554382324,
|
|
"epoch": 1.101737387236886,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004883969503909073,
|
|
"loss": 4.9181,
|
|
"mean_token_accuracy": 0.20889114886522292,
|
|
"num_tokens": 24269744.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.263672685623169,
|
|
"epoch": 1.1021550283995991,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883875119169798,
|
|
"loss": 4.8268,
|
|
"mean_token_accuracy": 0.21963981539011002,
|
|
"num_tokens": 24278843.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.215049505233765,
|
|
"epoch": 1.1025726695623121,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000488378069707447,
|
|
"loss": 4.7704,
|
|
"mean_token_accuracy": 0.23093816936016082,
|
|
"num_tokens": 24287586.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.241842269897461,
|
|
"epoch": 1.102990310725025,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004883686237624744,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.21372128427028655,
|
|
"num_tokens": 24296318.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.275514125823975,
|
|
"epoch": 1.103407951887738,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004883591740822271,
|
|
"loss": 4.8707,
|
|
"mean_token_accuracy": 0.21349561214447021,
|
|
"num_tokens": 24305901.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.279876661300659,
|
|
"epoch": 1.103825593050451,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004883497206668707,
|
|
"loss": 4.8277,
|
|
"mean_token_accuracy": 0.2161480411887169,
|
|
"num_tokens": 24315075.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.287496328353882,
|
|
"epoch": 1.104243234213164,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004883402635165705,
|
|
"loss": 4.8996,
|
|
"mean_token_accuracy": 0.21491537392139434,
|
|
"num_tokens": 24323771.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.308077335357666,
|
|
"epoch": 1.104660875375877,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004883308026314923,
|
|
"loss": 4.9836,
|
|
"mean_token_accuracy": 0.20897426307201386,
|
|
"num_tokens": 24334175.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.346924543380737,
|
|
"epoch": 1.1050785165385901,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004883213380118016,
|
|
"loss": 4.884,
|
|
"mean_token_accuracy": 0.21414946317672728,
|
|
"num_tokens": 24344076.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.319311809539795,
|
|
"epoch": 1.105496157701303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004883118696576642,
|
|
"loss": 4.9513,
|
|
"mean_token_accuracy": 0.20323739498853682,
|
|
"num_tokens": 24353333.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.345140790939331,
|
|
"epoch": 1.105913798864016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004883023975692457,
|
|
"loss": 4.9316,
|
|
"mean_token_accuracy": 0.19883385598659514,
|
|
"num_tokens": 24362000.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.288261270523071,
|
|
"epoch": 1.106331440026729,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004882929217467118,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.21625980436801912,
|
|
"num_tokens": 24370490.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.234595012664795,
|
|
"epoch": 1.106749081189442,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004882834421902287,
|
|
"loss": 4.7968,
|
|
"mean_token_accuracy": 0.22402080595493318,
|
|
"num_tokens": 24378597.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.210676383972168,
|
|
"epoch": 1.107166722352155,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048827395889996226,
|
|
"loss": 4.8343,
|
|
"mean_token_accuracy": 0.2184252470731735,
|
|
"num_tokens": 24387050.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.267589282989502,
|
|
"epoch": 1.107584363514868,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004882644718760784,
|
|
"loss": 4.7957,
|
|
"mean_token_accuracy": 0.22348345220088958,
|
|
"num_tokens": 24395283.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.165054178237915,
|
|
"epoch": 1.108002004677581,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048825498111874325,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.22134947776794434,
|
|
"num_tokens": 24404206.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.244530296325683,
|
|
"epoch": 1.108419645840294,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.00048824548662812294,
|
|
"loss": 4.8049,
|
|
"mean_token_accuracy": 0.2146410882472992,
|
|
"num_tokens": 24414080.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.308543062210083,
|
|
"epoch": 1.108837287003007,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048823598840438384,
|
|
"loss": 4.8953,
|
|
"mean_token_accuracy": 0.21301015764474868,
|
|
"num_tokens": 24422406.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.288754987716675,
|
|
"epoch": 1.10925492816572,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048822648644769194,
|
|
"loss": 4.8796,
|
|
"mean_token_accuracy": 0.2084352046251297,
|
|
"num_tokens": 24432159.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.273263740539551,
|
|
"epoch": 1.109672569328433,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004882169807582138,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.21557990312576295,
|
|
"num_tokens": 24440442.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.287055778503418,
|
|
"epoch": 1.110090210491146,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004882074713361157,
|
|
"loss": 4.8735,
|
|
"mean_token_accuracy": 0.21588267683982848,
|
|
"num_tokens": 24449717.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.254686641693115,
|
|
"epoch": 1.110507851653859,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004881979581815642,
|
|
"loss": 4.8053,
|
|
"mean_token_accuracy": 0.22107547670602798,
|
|
"num_tokens": 24458279.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.24847936630249,
|
|
"epoch": 1.110925492816572,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004881884412947259,
|
|
"loss": 4.7765,
|
|
"mean_token_accuracy": 0.22044652551412583,
|
|
"num_tokens": 24466096.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.324870157241821,
|
|
"epoch": 1.111343133979285,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048817892067576726,
|
|
"loss": 4.9458,
|
|
"mean_token_accuracy": 0.20834062695503236,
|
|
"num_tokens": 24474432.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.375838661193848,
|
|
"epoch": 1.111760775141998,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000488169396324855,
|
|
"loss": 4.9692,
|
|
"mean_token_accuracy": 0.2107497811317444,
|
|
"num_tokens": 24484627.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.278687953948975,
|
|
"epoch": 1.112178416304711,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048815986824215585,
|
|
"loss": 4.8612,
|
|
"mean_token_accuracy": 0.2141796663403511,
|
|
"num_tokens": 24494010.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.238835287094116,
|
|
"epoch": 1.112596057467424,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004881503364278366,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.22009282410144806,
|
|
"num_tokens": 24503286.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.173361682891846,
|
|
"epoch": 1.1130136986301369,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004881408008820642,
|
|
"loss": 4.7588,
|
|
"mean_token_accuracy": 0.22442252933979034,
|
|
"num_tokens": 24512595.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.293496179580688,
|
|
"epoch": 1.11343133979285,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048813126160500555,
|
|
"loss": 4.8401,
|
|
"mean_token_accuracy": 0.2113596111536026,
|
|
"num_tokens": 24521358.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.41713318824768,
|
|
"epoch": 1.113848980955563,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004881217185968276,
|
|
"loss": 4.993,
|
|
"mean_token_accuracy": 0.21133463382720946,
|
|
"num_tokens": 24530233.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.409033679962159,
|
|
"epoch": 1.114266622118276,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004881121718576974,
|
|
"loss": 4.9811,
|
|
"mean_token_accuracy": 0.1954956293106079,
|
|
"num_tokens": 24539645.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.31529278755188,
|
|
"epoch": 1.114684263280989,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048810262138778213,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.2072860687971115,
|
|
"num_tokens": 24549085.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.353154087066651,
|
|
"epoch": 1.115101904443702,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048809306718724886,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.207663793861866,
|
|
"num_tokens": 24557750.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.361567831039428,
|
|
"epoch": 1.115519545606415,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00048808350925626514,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.21261006146669387,
|
|
"num_tokens": 24567281.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.248485565185547,
|
|
"epoch": 1.115937186769128,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048807394759499797,
|
|
"loss": 4.8457,
|
|
"mean_token_accuracy": 0.21442843228578568,
|
|
"num_tokens": 24576548.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.20340666770935,
|
|
"epoch": 1.116354827931841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004880643822036149,
|
|
"loss": 4.7775,
|
|
"mean_token_accuracy": 0.2225051552057266,
|
|
"num_tokens": 24585528.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.265936183929443,
|
|
"epoch": 1.116772469094554,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048805481308228333,
|
|
"loss": 4.8731,
|
|
"mean_token_accuracy": 0.2130543917417526,
|
|
"num_tokens": 24594179.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.2870190143585205,
|
|
"epoch": 1.117190110257267,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004880452402311709,
|
|
"loss": 4.9277,
|
|
"mean_token_accuracy": 0.21559205353260041,
|
|
"num_tokens": 24603365.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.298516511917114,
|
|
"epoch": 1.11760775141998,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00048803566365044493,
|
|
"loss": 4.9284,
|
|
"mean_token_accuracy": 0.20634755492210388,
|
|
"num_tokens": 24613472.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.306252384185791,
|
|
"epoch": 1.1180253925826928,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004880260833402734,
|
|
"loss": 4.8945,
|
|
"mean_token_accuracy": 0.2109985038638115,
|
|
"num_tokens": 24623492.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.350619745254517,
|
|
"epoch": 1.1184430337454059,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048801649930082375,
|
|
"loss": 4.963,
|
|
"mean_token_accuracy": 0.20846630036830902,
|
|
"num_tokens": 24633245.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.32208285331726,
|
|
"epoch": 1.118860674908119,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000488006911532264,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.22022706717252732,
|
|
"num_tokens": 24642652.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.244876718521118,
|
|
"epoch": 1.119278316070832,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004879973200347617,
|
|
"loss": 4.9276,
|
|
"mean_token_accuracy": 0.20962270647287368,
|
|
"num_tokens": 24651650.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.302092170715332,
|
|
"epoch": 1.119695957233545,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.00048798772480848504,
|
|
"loss": 4.9196,
|
|
"mean_token_accuracy": 0.21212091594934462,
|
|
"num_tokens": 24661356.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.239861679077149,
|
|
"epoch": 1.120113598396258,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048797812585360187,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.21514668315649033,
|
|
"num_tokens": 24670100.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.291288566589356,
|
|
"epoch": 1.120531239558971,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048796852317028024,
|
|
"loss": 4.897,
|
|
"mean_token_accuracy": 0.2144634649157524,
|
|
"num_tokens": 24679437.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.339767503738403,
|
|
"epoch": 1.1209488807216839,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004879589167586882,
|
|
"loss": 4.8643,
|
|
"mean_token_accuracy": 0.2130082741379738,
|
|
"num_tokens": 24689818.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.35367169380188,
|
|
"epoch": 1.121366521884397,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048794930661899414,
|
|
"loss": 4.9177,
|
|
"mean_token_accuracy": 0.21489592343568803,
|
|
"num_tokens": 24698323.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.338282918930053,
|
|
"epoch": 1.12178416304711,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048793969275136593,
|
|
"loss": 4.9323,
|
|
"mean_token_accuracy": 0.2109528586268425,
|
|
"num_tokens": 24707447.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.28376955986023,
|
|
"epoch": 1.122201804209823,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004879300751559722,
|
|
"loss": 4.8278,
|
|
"mean_token_accuracy": 0.2172815814614296,
|
|
"num_tokens": 24716470.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.291512584686279,
|
|
"epoch": 1.122619445372536,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004879204538329812,
|
|
"loss": 4.8293,
|
|
"mean_token_accuracy": 0.21512616723775863,
|
|
"num_tokens": 24725051.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.3568384647369385,
|
|
"epoch": 1.1230370865352488,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004879108287825614,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.20120859444141387,
|
|
"num_tokens": 24735303.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.326174116134643,
|
|
"epoch": 1.1234547276979618,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048790120000488115,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.21230633705854415,
|
|
"num_tokens": 24743637.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.312710762023926,
|
|
"epoch": 1.1238723688606749,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004878915675001092,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.21179048120975494,
|
|
"num_tokens": 24752424.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.3614856719970705,
|
|
"epoch": 1.124290010023388,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004878819312684141,
|
|
"loss": 4.9255,
|
|
"mean_token_accuracy": 0.20959601700305938,
|
|
"num_tokens": 24762224.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.348032140731812,
|
|
"epoch": 1.124707651186101,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004878722913099645,
|
|
"loss": 4.8997,
|
|
"mean_token_accuracy": 0.21544939577579497,
|
|
"num_tokens": 24771118.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.3021481990814205,
|
|
"epoch": 1.125125292348814,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004878626476249293,
|
|
"loss": 4.9353,
|
|
"mean_token_accuracy": 0.2121492385864258,
|
|
"num_tokens": 24779941.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.308758640289307,
|
|
"epoch": 1.125542933511527,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004878530002134772,
|
|
"loss": 4.8852,
|
|
"mean_token_accuracy": 0.21347497552633285,
|
|
"num_tokens": 24788650.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.400888824462891,
|
|
"epoch": 1.1259605746742398,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004878433490757771,
|
|
"loss": 5.005,
|
|
"mean_token_accuracy": 0.20322306752204894,
|
|
"num_tokens": 24797953.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.357196950912476,
|
|
"epoch": 1.1263782158369529,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004878336942119979,
|
|
"loss": 4.8674,
|
|
"mean_token_accuracy": 0.22296086251735686,
|
|
"num_tokens": 24807073.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.2120765209197994,
|
|
"epoch": 1.126795856999666,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048782403562230874,
|
|
"loss": 4.8261,
|
|
"mean_token_accuracy": 0.2128051996231079,
|
|
"num_tokens": 24815839.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.253981351852417,
|
|
"epoch": 1.127213498162379,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004878143733068787,
|
|
"loss": 5.0089,
|
|
"mean_token_accuracy": 0.20382945090532303,
|
|
"num_tokens": 24825496.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.314820957183838,
|
|
"epoch": 1.127631139325092,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004878047072658769,
|
|
"loss": 4.842,
|
|
"mean_token_accuracy": 0.216281196475029,
|
|
"num_tokens": 24834527.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.255876064300537,
|
|
"epoch": 1.1280487804878048,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004877950374994725,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.226950204372406,
|
|
"num_tokens": 24843136.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.367184972763061,
|
|
"epoch": 1.1284664216505178,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004877853640078349,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.20357572734355928,
|
|
"num_tokens": 24853304.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.237215042114258,
|
|
"epoch": 1.1288840628132308,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004877756867911333,
|
|
"loss": 4.8163,
|
|
"mean_token_accuracy": 0.2220786228775978,
|
|
"num_tokens": 24861793.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.286478710174561,
|
|
"epoch": 1.1293017039759439,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004877660058495372,
|
|
"loss": 4.8729,
|
|
"mean_token_accuracy": 0.21528170853853226,
|
|
"num_tokens": 24871340.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.37237958908081,
|
|
"epoch": 1.129719345138657,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004877563211832161,
|
|
"loss": 4.9493,
|
|
"mean_token_accuracy": 0.21095248609781264,
|
|
"num_tokens": 24880796.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.24170560836792,
|
|
"epoch": 1.13013698630137,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048774663279233947,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.22240207046270372,
|
|
"num_tokens": 24889801.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.307558870315551,
|
|
"epoch": 1.130554627464083,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048773694067707693,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.2117237001657486,
|
|
"num_tokens": 24899032.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.355996036529541,
|
|
"epoch": 1.1309722686267958,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048772724483759825,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.2129591479897499,
|
|
"num_tokens": 24908792.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.327474451065063,
|
|
"epoch": 1.1313899097895088,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000487717545274073,
|
|
"loss": 4.9017,
|
|
"mean_token_accuracy": 0.21812181025743485,
|
|
"num_tokens": 24918330.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.3583149909973145,
|
|
"epoch": 1.1318075509522219,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004877078419866711,
|
|
"loss": 4.9075,
|
|
"mean_token_accuracy": 0.21812282204627992,
|
|
"num_tokens": 24928039.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.32003960609436,
|
|
"epoch": 1.1322251921149349,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048769813497556236,
|
|
"loss": 5.0001,
|
|
"mean_token_accuracy": 0.2054269567131996,
|
|
"num_tokens": 24937145.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.311992979049682,
|
|
"epoch": 1.132642833277648,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004876884242409168,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.20897700935602187,
|
|
"num_tokens": 24945879.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.256800699234009,
|
|
"epoch": 1.1330604744403607,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048767870978290434,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.22672015726566314,
|
|
"num_tokens": 24954900.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.370893144607544,
|
|
"epoch": 1.1334781156030738,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004876689916016951,
|
|
"loss": 5.0319,
|
|
"mean_token_accuracy": 0.2040715143084526,
|
|
"num_tokens": 24965015.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.338613653182984,
|
|
"epoch": 1.1338957567657868,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004876592696974591,
|
|
"loss": 4.8604,
|
|
"mean_token_accuracy": 0.2147621899843216,
|
|
"num_tokens": 24975125.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.305952024459839,
|
|
"epoch": 1.1343133979284998,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004876495440703667,
|
|
"loss": 4.9425,
|
|
"mean_token_accuracy": 0.2016499698162079,
|
|
"num_tokens": 24983895.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.263954782485962,
|
|
"epoch": 1.1347310390912129,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004876398147205879,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.22257362455129623,
|
|
"num_tokens": 24993186.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.277096700668335,
|
|
"epoch": 1.135148680253926,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004876300816482933,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.2224116548895836,
|
|
"num_tokens": 25001785.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.347155237197876,
|
|
"epoch": 1.135566321416639,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004876203448536532,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.21788772493600844,
|
|
"num_tokens": 25010717.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.295159578323364,
|
|
"epoch": 1.1359839625793517,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004876106043368381,
|
|
"loss": 4.806,
|
|
"mean_token_accuracy": 0.21501536071300506,
|
|
"num_tokens": 25019438.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.254235935211182,
|
|
"epoch": 1.1364016037420648,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004876008600980183,
|
|
"loss": 4.8607,
|
|
"mean_token_accuracy": 0.21165283471345903,
|
|
"num_tokens": 25028601.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.258656311035156,
|
|
"epoch": 1.1368192449047778,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048759111213736455,
|
|
"loss": 4.8929,
|
|
"mean_token_accuracy": 0.21360308974981307,
|
|
"num_tokens": 25038046.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.272345542907715,
|
|
"epoch": 1.1372368860674908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004875813604550476,
|
|
"loss": 4.8122,
|
|
"mean_token_accuracy": 0.21677210181951523,
|
|
"num_tokens": 25046712.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.237390756607056,
|
|
"epoch": 1.1376545272302039,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004875716050512379,
|
|
"loss": 4.7856,
|
|
"mean_token_accuracy": 0.22365109771490096,
|
|
"num_tokens": 25054918.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.251475143432617,
|
|
"epoch": 1.1380721683929167,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004875618459261065,
|
|
"loss": 4.8585,
|
|
"mean_token_accuracy": 0.20908747613430023,
|
|
"num_tokens": 25064187.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.3185296058654785,
|
|
"epoch": 1.1384898095556297,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048755208307982414,
|
|
"loss": 4.8659,
|
|
"mean_token_accuracy": 0.2168547511100769,
|
|
"num_tokens": 25073700.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.346991109848022,
|
|
"epoch": 1.1389074507183428,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004875423165125616,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.2092817932367325,
|
|
"num_tokens": 25082974.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.330929851531982,
|
|
"epoch": 1.1393250918810558,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048753254622449006,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.2088674232363701,
|
|
"num_tokens": 25092450.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.254373693466187,
|
|
"epoch": 1.1397427330437688,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004875227722157804,
|
|
"loss": 4.8044,
|
|
"mean_token_accuracy": 0.2167067751288414,
|
|
"num_tokens": 25102731.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.21466817855835,
|
|
"epoch": 1.1401603742064819,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004875129944866039,
|
|
"loss": 4.7846,
|
|
"mean_token_accuracy": 0.22452840805053711,
|
|
"num_tokens": 25111159.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.26133246421814,
|
|
"epoch": 1.140578015369195,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004875032130371316,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.22307331413030623,
|
|
"num_tokens": 25120151.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.286589860916138,
|
|
"epoch": 1.1409956565319077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004874934278675347,
|
|
"loss": 4.8579,
|
|
"mean_token_accuracy": 0.2169698417186737,
|
|
"num_tokens": 25128788.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.255595731735229,
|
|
"epoch": 1.1414132976946207,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004874836389779846,
|
|
"loss": 4.8154,
|
|
"mean_token_accuracy": 0.21314146518707275,
|
|
"num_tokens": 25138149.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.2830733299255375,
|
|
"epoch": 1.1418309388573338,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048747384636865267,
|
|
"loss": 4.8748,
|
|
"mean_token_accuracy": 0.20735131651163102,
|
|
"num_tokens": 25147798.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.220418405532837,
|
|
"epoch": 1.1422485800200468,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004874640500397103,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.20990932434797288,
|
|
"num_tokens": 25156626.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.288068199157715,
|
|
"epoch": 1.1426662211827598,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004874542499913289,
|
|
"loss": 4.8755,
|
|
"mean_token_accuracy": 0.21849137991666795,
|
|
"num_tokens": 25165846.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.238394165039063,
|
|
"epoch": 1.1430838623454727,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048744444622368015,
|
|
"loss": 4.8351,
|
|
"mean_token_accuracy": 0.21690909564495087,
|
|
"num_tokens": 25175218.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.325964403152466,
|
|
"epoch": 1.1435015035081857,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.00048743463873693576,
|
|
"loss": 4.9536,
|
|
"mean_token_accuracy": 0.2123661831021309,
|
|
"num_tokens": 25185257.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.397424697875977,
|
|
"epoch": 1.1439191446708987,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004874248275312673,
|
|
"loss": 4.9803,
|
|
"mean_token_accuracy": 0.20287563949823378,
|
|
"num_tokens": 25195348.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.300476026535034,
|
|
"epoch": 1.1443367858336118,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048741501260684644,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.21636418998241425,
|
|
"num_tokens": 25204810.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.222959661483765,
|
|
"epoch": 1.1447544269963248,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048740519396384515,
|
|
"loss": 4.7476,
|
|
"mean_token_accuracy": 0.22459547966718674,
|
|
"num_tokens": 25214490.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.1869542598724365,
|
|
"epoch": 1.1451720681590378,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048739537160243524,
|
|
"loss": 4.7862,
|
|
"mean_token_accuracy": 0.2268478035926819,
|
|
"num_tokens": 25222840.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.290386390686035,
|
|
"epoch": 1.1455897093217509,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048738554552278874,
|
|
"loss": 4.7725,
|
|
"mean_token_accuracy": 0.2144513964653015,
|
|
"num_tokens": 25231056.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.311003160476685,
|
|
"epoch": 1.1460073504844637,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048737571572507753,
|
|
"loss": 4.8602,
|
|
"mean_token_accuracy": 0.20823847651481628,
|
|
"num_tokens": 25240445.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.2657286643981935,
|
|
"epoch": 1.1464249916471767,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048736588220947384,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.21907963901758193,
|
|
"num_tokens": 25249113.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.240375423431397,
|
|
"epoch": 1.1468426328098897,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048735604497614974,
|
|
"loss": 4.8514,
|
|
"mean_token_accuracy": 0.21787066608667374,
|
|
"num_tokens": 25258202.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.408869838714599,
|
|
"epoch": 1.1472602739726028,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004873462040252775,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.2081083133816719,
|
|
"num_tokens": 25268052.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.330584526062012,
|
|
"epoch": 1.1476779151353158,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004873363593570293,
|
|
"loss": 4.9223,
|
|
"mean_token_accuracy": 0.21000739932060242,
|
|
"num_tokens": 25276696.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.230520343780517,
|
|
"epoch": 1.1480955562980286,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004873265109715776,
|
|
"loss": 4.8243,
|
|
"mean_token_accuracy": 0.215564127266407,
|
|
"num_tokens": 25284920.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.236227750778198,
|
|
"epoch": 1.1485131974607417,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004873166588690947,
|
|
"loss": 4.7962,
|
|
"mean_token_accuracy": 0.22844958901405335,
|
|
"num_tokens": 25293960.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.335511016845703,
|
|
"epoch": 1.1489308386234547,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004873068030497532,
|
|
"loss": 4.982,
|
|
"mean_token_accuracy": 0.20452963560819626,
|
|
"num_tokens": 25303948.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.366847515106201,
|
|
"epoch": 1.1493484797861677,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048729694351372545,
|
|
"loss": 4.9687,
|
|
"mean_token_accuracy": 0.2122664839029312,
|
|
"num_tokens": 25313343.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.312794494628906,
|
|
"epoch": 1.1497661209488808,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004872870802611842,
|
|
"loss": 4.7885,
|
|
"mean_token_accuracy": 0.21724634021520614,
|
|
"num_tokens": 25321664.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.31779637336731,
|
|
"epoch": 1.1501837621115938,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004872772132923021,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.21834651678800582,
|
|
"num_tokens": 25331112.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.340660667419433,
|
|
"epoch": 1.1506014032743068,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048726734260725186,
|
|
"loss": 4.8781,
|
|
"mean_token_accuracy": 0.21803223341703415,
|
|
"num_tokens": 25340357.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.306051921844483,
|
|
"epoch": 1.1510190444370196,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004872574682062063,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.21451245993375778,
|
|
"num_tokens": 25349886.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.343042516708374,
|
|
"epoch": 1.1514366855997327,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004872475900893382,
|
|
"loss": 4.9364,
|
|
"mean_token_accuracy": 0.21684686988592147,
|
|
"num_tokens": 25358957.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.260214185714721,
|
|
"epoch": 1.1518543267624457,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004872377082568206,
|
|
"loss": 4.7724,
|
|
"mean_token_accuracy": 0.2199736163020134,
|
|
"num_tokens": 25368237.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.304642820358277,
|
|
"epoch": 1.1522719679251587,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048722782270882643,
|
|
"loss": 4.824,
|
|
"mean_token_accuracy": 0.21889438331127167,
|
|
"num_tokens": 25376626.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.228048276901245,
|
|
"epoch": 1.1526896090878718,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004872179334455288,
|
|
"loss": 4.8171,
|
|
"mean_token_accuracy": 0.21464346051216127,
|
|
"num_tokens": 25385824.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.226820755004883,
|
|
"epoch": 1.1531072502505846,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048720804046710074,
|
|
"loss": 4.7959,
|
|
"mean_token_accuracy": 0.22037454396486283,
|
|
"num_tokens": 25394317.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.262857961654663,
|
|
"epoch": 1.1535248914132976,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048719814377371553,
|
|
"loss": 4.8752,
|
|
"mean_token_accuracy": 0.2087165266275406,
|
|
"num_tokens": 25402962.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.254965829849243,
|
|
"epoch": 1.1539425325760106,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004871882433655464,
|
|
"loss": 4.773,
|
|
"mean_token_accuracy": 0.22089720964431764,
|
|
"num_tokens": 25411660.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.2793981552124025,
|
|
"epoch": 1.1543601737387237,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004871783392427666,
|
|
"loss": 4.8458,
|
|
"mean_token_accuracy": 0.22077429294586182,
|
|
"num_tokens": 25420377.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.214014053344727,
|
|
"epoch": 1.1547778149014367,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004871684314055497,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.2173460453748703,
|
|
"num_tokens": 25428811.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.310364007949829,
|
|
"epoch": 1.1551954560641498,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004871585198540689,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.21073182225227355,
|
|
"num_tokens": 25438247.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.239340019226074,
|
|
"epoch": 1.1556130972268628,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048714860458849794,
|
|
"loss": 4.7929,
|
|
"mean_token_accuracy": 0.22644001990556717,
|
|
"num_tokens": 25447122.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.326520109176636,
|
|
"epoch": 1.1560307383895756,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048713868560901013,
|
|
"loss": 4.9784,
|
|
"mean_token_accuracy": 0.2041818305850029,
|
|
"num_tokens": 25455737.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.299466514587403,
|
|
"epoch": 1.1564483795522886,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004871287629157794,
|
|
"loss": 4.8208,
|
|
"mean_token_accuracy": 0.22329221069812774,
|
|
"num_tokens": 25465285.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.300172519683838,
|
|
"epoch": 1.1568660207150017,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004871188365089793,
|
|
"loss": 4.859,
|
|
"mean_token_accuracy": 0.22035358846187592,
|
|
"num_tokens": 25474933.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.220467281341553,
|
|
"epoch": 1.1572836618777147,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004871089063887837,
|
|
"loss": 4.8741,
|
|
"mean_token_accuracy": 0.214975243806839,
|
|
"num_tokens": 25483279.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.291132068634033,
|
|
"epoch": 1.1577013030404277,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048709897255536626,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.21430132985115052,
|
|
"num_tokens": 25492295.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.342033004760742,
|
|
"epoch": 1.1581189442031405,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004870890350089011,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.21129416078329086,
|
|
"num_tokens": 25501397.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.218774127960205,
|
|
"epoch": 1.1585365853658536,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004870790937495621,
|
|
"loss": 4.8206,
|
|
"mean_token_accuracy": 0.21797821372747422,
|
|
"num_tokens": 25510588.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.359376668930054,
|
|
"epoch": 1.1589542265285666,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048706914877752325,
|
|
"loss": 4.8943,
|
|
"mean_token_accuracy": 0.21436829417943953,
|
|
"num_tokens": 25519531.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.270188713073731,
|
|
"epoch": 1.1593718676912796,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048705920009295867,
|
|
"loss": 4.8172,
|
|
"mean_token_accuracy": 0.21490209698677062,
|
|
"num_tokens": 25529241.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.297169637680054,
|
|
"epoch": 1.1597895088539927,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004870492476960426,
|
|
"loss": 4.9263,
|
|
"mean_token_accuracy": 0.20956378132104875,
|
|
"num_tokens": 25538463.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.27384729385376,
|
|
"epoch": 1.1602071500167057,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004870392915869491,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.2140885427594185,
|
|
"num_tokens": 25547481.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.321070003509521,
|
|
"epoch": 1.1606247911794187,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004870293317658526,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.2263233482837677,
|
|
"num_tokens": 25556083.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.305483627319336,
|
|
"epoch": 1.1610424323421316,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004870193682329275,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.21651659905910492,
|
|
"num_tokens": 25564975.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.1812526226043705,
|
|
"epoch": 1.1614600735048446,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048700940098834805,
|
|
"loss": 4.6915,
|
|
"mean_token_accuracy": 0.22576250433921813,
|
|
"num_tokens": 25574576.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.28244686126709,
|
|
"epoch": 1.1618777146675576,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004869994300322889,
|
|
"loss": 4.8437,
|
|
"mean_token_accuracy": 0.22024205029010774,
|
|
"num_tokens": 25583485.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.302479791641235,
|
|
"epoch": 1.1622953558302707,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048698945536492454,
|
|
"loss": 4.8777,
|
|
"mean_token_accuracy": 0.2092752069234848,
|
|
"num_tokens": 25592736.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.306464290618896,
|
|
"epoch": 1.1627129969929837,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004869794769864296,
|
|
"loss": 4.889,
|
|
"mean_token_accuracy": 0.21997833102941514,
|
|
"num_tokens": 25601230.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.291229724884033,
|
|
"epoch": 1.1631306381556965,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004869694948969787,
|
|
"loss": 4.866,
|
|
"mean_token_accuracy": 0.22094489485025406,
|
|
"num_tokens": 25611139.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.33829255104065,
|
|
"epoch": 1.1635482793184095,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048695950909674666,
|
|
"loss": 4.9115,
|
|
"mean_token_accuracy": 0.20500550419092178,
|
|
"num_tokens": 25620255.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.262288236618042,
|
|
"epoch": 1.1639659204811226,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048694951958590835,
|
|
"loss": 4.7776,
|
|
"mean_token_accuracy": 0.22528681308031082,
|
|
"num_tokens": 25629127.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.2347527027130125,
|
|
"epoch": 1.1643835616438356,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048693952636463854,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.21933797597885132,
|
|
"num_tokens": 25638561.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.2616376876831055,
|
|
"epoch": 1.1648012028065486,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048692952943311214,
|
|
"loss": 4.837,
|
|
"mean_token_accuracy": 0.21445476561784743,
|
|
"num_tokens": 25647268.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.364459466934204,
|
|
"epoch": 1.1652188439692617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004869195287915043,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.20588933825492858,
|
|
"num_tokens": 25656804.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.251067686080932,
|
|
"epoch": 1.1656364851319747,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048690952443999,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.21925395131111144,
|
|
"num_tokens": 25665960.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.38764762878418,
|
|
"epoch": 1.1660541262946875,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048689951637874445,
|
|
"loss": 5.0583,
|
|
"mean_token_accuracy": 0.204960797727108,
|
|
"num_tokens": 25676836.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.2788561344146725,
|
|
"epoch": 1.1664717674574006,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004868895046079428,
|
|
"loss": 4.7937,
|
|
"mean_token_accuracy": 0.21251301914453508,
|
|
"num_tokens": 25685751.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.237187480926513,
|
|
"epoch": 1.1668894086201136,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004868794891277602,
|
|
"loss": 4.8084,
|
|
"mean_token_accuracy": 0.2190708950161934,
|
|
"num_tokens": 25694948.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.3689666271209715,
|
|
"epoch": 1.1673070497828266,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004868694699383722,
|
|
"loss": 5.0128,
|
|
"mean_token_accuracy": 0.20762406885623932,
|
|
"num_tokens": 25704135.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.436590003967285,
|
|
"epoch": 1.1677246909455397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004868594470399541,
|
|
"loss": 5.007,
|
|
"mean_token_accuracy": 0.2094082534313202,
|
|
"num_tokens": 25714300.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.270674371719361,
|
|
"epoch": 1.1681423321082525,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048684942043268137,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.21670733392238617,
|
|
"num_tokens": 25723275.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.340898227691651,
|
|
"epoch": 1.1685599732709655,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00048683939011672953,
|
|
"loss": 5.0488,
|
|
"mean_token_accuracy": 0.20089862048625945,
|
|
"num_tokens": 25732432.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.260267543792724,
|
|
"epoch": 1.1689776144336785,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048682935609227414,
|
|
"loss": 4.8411,
|
|
"mean_token_accuracy": 0.21325727105140685,
|
|
"num_tokens": 25741001.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.354995012283325,
|
|
"epoch": 1.1693952555963916,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048681931835949083,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.20827681422233582,
|
|
"num_tokens": 25751632.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.3226298809051515,
|
|
"epoch": 1.1698128967591046,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004868092769185555,
|
|
"loss": 4.8944,
|
|
"mean_token_accuracy": 0.21107469946146012,
|
|
"num_tokens": 25760963.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.249393320083618,
|
|
"epoch": 1.1702305379218176,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048679923176964384,
|
|
"loss": 4.8506,
|
|
"mean_token_accuracy": 0.21791949719190598,
|
|
"num_tokens": 25769974.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.2887732028961185,
|
|
"epoch": 1.1706481790845307,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004867891829129316,
|
|
"loss": 4.8688,
|
|
"mean_token_accuracy": 0.21354460716247559,
|
|
"num_tokens": 25778311.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.359960889816284,
|
|
"epoch": 1.1710658202472435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867791303485948,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.21040723025798796,
|
|
"num_tokens": 25787811.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.307669401168823,
|
|
"epoch": 1.1714834614099565,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004867690740768094,
|
|
"loss": 4.8653,
|
|
"mean_token_accuracy": 0.2202005311846733,
|
|
"num_tokens": 25796651.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.300128221511841,
|
|
"epoch": 1.1719011025726696,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048675901409775147,
|
|
"loss": 4.929,
|
|
"mean_token_accuracy": 0.21232935041189194,
|
|
"num_tokens": 25805995.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.332314920425415,
|
|
"epoch": 1.1723187437353826,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048674895041159714,
|
|
"loss": 4.9046,
|
|
"mean_token_accuracy": 0.2141195461153984,
|
|
"num_tokens": 25814833.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.337783098220825,
|
|
"epoch": 1.1727363848980956,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048673888301852247,
|
|
"loss": 4.9862,
|
|
"mean_token_accuracy": 0.21480366587638855,
|
|
"num_tokens": 25823224.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.239027309417724,
|
|
"epoch": 1.1731540260608084,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004867288119187039,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.22379774898290633,
|
|
"num_tokens": 25832583.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.286594343185425,
|
|
"epoch": 1.1735716672235215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004867187371123175,
|
|
"loss": 4.8967,
|
|
"mean_token_accuracy": 0.21071151942014693,
|
|
"num_tokens": 25841233.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.275851821899414,
|
|
"epoch": 1.1739893083862345,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048670865859953984,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.21494330912828447,
|
|
"num_tokens": 25849794.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.279708385467529,
|
|
"epoch": 1.1744069495489475,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004866985763805472,
|
|
"loss": 4.784,
|
|
"mean_token_accuracy": 0.21513072401285172,
|
|
"num_tokens": 25858629.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.317321538925171,
|
|
"epoch": 1.1748245907116606,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004866884904555162,
|
|
"loss": 4.8985,
|
|
"mean_token_accuracy": 0.21351731270551683,
|
|
"num_tokens": 25868382.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.316340923309326,
|
|
"epoch": 1.1752422318743736,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004866784008246233,
|
|
"loss": 4.8881,
|
|
"mean_token_accuracy": 0.21199864894151688,
|
|
"num_tokens": 25877565.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.3823902130126955,
|
|
"epoch": 1.1756598730370866,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004866683074880453,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.1993249848484993,
|
|
"num_tokens": 25886791.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.308034992218017,
|
|
"epoch": 1.1760775141997994,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048665821044595884,
|
|
"loss": 4.863,
|
|
"mean_token_accuracy": 0.21241417676210403,
|
|
"num_tokens": 25896190.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.258593988418579,
|
|
"epoch": 1.1764951553625125,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004866481096985405,
|
|
"loss": 4.8061,
|
|
"mean_token_accuracy": 0.21635949462652207,
|
|
"num_tokens": 25904702.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.380900478363037,
|
|
"epoch": 1.1769127965252255,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004866380052459673,
|
|
"loss": 4.9618,
|
|
"mean_token_accuracy": 0.21529793441295625,
|
|
"num_tokens": 25914513.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.233208656311035,
|
|
"epoch": 1.1773304376879385,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004866278970884161,
|
|
"loss": 4.8307,
|
|
"mean_token_accuracy": 0.21113640815019608,
|
|
"num_tokens": 25923436.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.277005434036255,
|
|
"epoch": 1.1777480788506516,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048661778522606376,
|
|
"loss": 4.847,
|
|
"mean_token_accuracy": 0.216677750647068,
|
|
"num_tokens": 25931883.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.359256362915039,
|
|
"epoch": 1.1781657200133644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048660766965908736,
|
|
"loss": 4.9206,
|
|
"mean_token_accuracy": 0.20923472046852112,
|
|
"num_tokens": 25942095.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.266597414016724,
|
|
"epoch": 1.1785833611760774,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048659755038766406,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22945853769779206,
|
|
"num_tokens": 25951265.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.270097064971924,
|
|
"epoch": 1.1790010023387905,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048658742741197086,
|
|
"loss": 4.8595,
|
|
"mean_token_accuracy": 0.2136015921831131,
|
|
"num_tokens": 25960621.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.279816675186157,
|
|
"epoch": 1.1794186435015035,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048657730073218517,
|
|
"loss": 4.9116,
|
|
"mean_token_accuracy": 0.20688603669404984,
|
|
"num_tokens": 25970769.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.322383785247803,
|
|
"epoch": 1.1798362846642165,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004865671703484841,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.20970679819583893,
|
|
"num_tokens": 25980928.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.317748165130615,
|
|
"epoch": 1.1802539258269296,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048655703626104493,
|
|
"loss": 4.9271,
|
|
"mean_token_accuracy": 0.2089887961745262,
|
|
"num_tokens": 25991085.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.263252115249633,
|
|
"epoch": 1.1806715669896426,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048654689847004535,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.21276907175779342,
|
|
"num_tokens": 25999862.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.375521564483643,
|
|
"epoch": 1.1810892081523554,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004865367569756626,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.21259890645742416,
|
|
"num_tokens": 26009075.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.3167399883270265,
|
|
"epoch": 1.1815068493150684,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048652661177807426,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.21735656261444092,
|
|
"num_tokens": 26017822.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.197692394256592,
|
|
"epoch": 1.1819244904777815,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048651646287745803,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.21580744087696074,
|
|
"num_tokens": 26026327.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.334139442443847,
|
|
"epoch": 1.1823421316404945,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048650631027399155,
|
|
"loss": 4.997,
|
|
"mean_token_accuracy": 0.20143674612045287,
|
|
"num_tokens": 26036252.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.385194158554077,
|
|
"epoch": 1.1827597728032075,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048649615396785246,
|
|
"loss": 4.9565,
|
|
"mean_token_accuracy": 0.20766499042510986,
|
|
"num_tokens": 26045596.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.33499846458435,
|
|
"epoch": 1.1831774139659206,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048648599395921863,
|
|
"loss": 4.843,
|
|
"mean_token_accuracy": 0.21937379688024522,
|
|
"num_tokens": 26054824.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.318455362319947,
|
|
"epoch": 1.1835950551286334,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048647583024826786,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.20799652934074403,
|
|
"num_tokens": 26064414.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.319556665420532,
|
|
"epoch": 1.1840126962913464,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048646566283517824,
|
|
"loss": 4.8803,
|
|
"mean_token_accuracy": 0.21460512429475784,
|
|
"num_tokens": 26073597.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.3037676334381105,
|
|
"epoch": 1.1844303374540595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048645549172012756,
|
|
"loss": 4.8547,
|
|
"mean_token_accuracy": 0.2137479677796364,
|
|
"num_tokens": 26082026.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.22292537689209,
|
|
"epoch": 1.1848479786167725,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000486445316903294,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.21975057274103166,
|
|
"num_tokens": 26090112.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.244842290878296,
|
|
"epoch": 1.1852656197794855,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004864351383848556,
|
|
"loss": 4.8147,
|
|
"mean_token_accuracy": 0.21224441528320312,
|
|
"num_tokens": 26098551.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.345350074768066,
|
|
"epoch": 1.1856832609421986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004864249561649906,
|
|
"loss": 4.9286,
|
|
"mean_token_accuracy": 0.2116273283958435,
|
|
"num_tokens": 26109201.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.325102663040161,
|
|
"epoch": 1.1861009021049114,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004864147702438773,
|
|
"loss": 4.8866,
|
|
"mean_token_accuracy": 0.2113925889134407,
|
|
"num_tokens": 26119893.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.273728227615356,
|
|
"epoch": 1.1865185432676244,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000486404580621694,
|
|
"loss": 4.8483,
|
|
"mean_token_accuracy": 0.2194788247346878,
|
|
"num_tokens": 26128341.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.321913814544677,
|
|
"epoch": 1.1869361844303374,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000486394387298619,
|
|
"loss": 4.8851,
|
|
"mean_token_accuracy": 0.20443363338708878,
|
|
"num_tokens": 26137823.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.341306972503662,
|
|
"epoch": 1.1873538255930505,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048638419027483075,
|
|
"loss": 4.9091,
|
|
"mean_token_accuracy": 0.21508204638957978,
|
|
"num_tokens": 26147333.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.262877750396728,
|
|
"epoch": 1.1877714667557635,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004863739895505079,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.2188376858830452,
|
|
"num_tokens": 26156145.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.29925537109375,
|
|
"epoch": 1.1881891079184765,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048636378512582884,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.21502636075019838,
|
|
"num_tokens": 26165323.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.2859429836273195,
|
|
"epoch": 1.1886067490811894,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048635357700097236,
|
|
"loss": 4.8439,
|
|
"mean_token_accuracy": 0.2193395659327507,
|
|
"num_tokens": 26174549.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.179352188110352,
|
|
"epoch": 1.1890243902439024,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004863433651761171,
|
|
"loss": 4.7419,
|
|
"mean_token_accuracy": 0.2244386300444603,
|
|
"num_tokens": 26184012.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.32244176864624,
|
|
"epoch": 1.1894420314066154,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004863331496514418,
|
|
"loss": 4.9442,
|
|
"mean_token_accuracy": 0.19358464181423188,
|
|
"num_tokens": 26193819.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.222387742996216,
|
|
"epoch": 1.1898596725693285,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048632293042712545,
|
|
"loss": 4.8283,
|
|
"mean_token_accuracy": 0.21450960338115693,
|
|
"num_tokens": 26202209.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.2218691349029545,
|
|
"epoch": 1.1902773137320415,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048631270750334674,
|
|
"loss": 4.8262,
|
|
"mean_token_accuracy": 0.21674735546112062,
|
|
"num_tokens": 26212048.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.3557123184204105,
|
|
"epoch": 1.1906949548947545,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048630248088028474,
|
|
"loss": 4.9523,
|
|
"mean_token_accuracy": 0.21151799708604813,
|
|
"num_tokens": 26220877.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.386314010620117,
|
|
"epoch": 1.1911125960574673,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004862922505581185,
|
|
"loss": 4.8804,
|
|
"mean_token_accuracy": 0.21514079123735427,
|
|
"num_tokens": 26229583.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.332051753997803,
|
|
"epoch": 1.1915302372201804,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000486282016537027,
|
|
"loss": 4.98,
|
|
"mean_token_accuracy": 0.21363709568977357,
|
|
"num_tokens": 26239483.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.284231853485108,
|
|
"epoch": 1.1919478783828934,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048627177881718954,
|
|
"loss": 4.9104,
|
|
"mean_token_accuracy": 0.2070065274834633,
|
|
"num_tokens": 26248608.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.239997529983521,
|
|
"epoch": 1.1923655195456064,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004862615373987853,
|
|
"loss": 4.821,
|
|
"mean_token_accuracy": 0.2165408179163933,
|
|
"num_tokens": 26258037.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.370838451385498,
|
|
"epoch": 1.1927831607083195,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004862512922819935,
|
|
"loss": 5.0576,
|
|
"mean_token_accuracy": 0.1969443753361702,
|
|
"num_tokens": 26267890.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.290849113464356,
|
|
"epoch": 1.1932008018710325,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004862410434669936,
|
|
"loss": 4.8617,
|
|
"mean_token_accuracy": 0.21404768526554108,
|
|
"num_tokens": 26276963.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.263153123855591,
|
|
"epoch": 1.1936184430337453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048623079095396496,
|
|
"loss": 4.8456,
|
|
"mean_token_accuracy": 0.20937862247228622,
|
|
"num_tokens": 26286667.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.312361049652099,
|
|
"epoch": 1.1940360841964583,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000486220534743087,
|
|
"loss": 4.833,
|
|
"mean_token_accuracy": 0.21266380101442336,
|
|
"num_tokens": 26295575.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.278595638275147,
|
|
"epoch": 1.1944537253591714,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004862102748345394,
|
|
"loss": 4.8526,
|
|
"mean_token_accuracy": 0.21584392040967942,
|
|
"num_tokens": 26305813.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.237206649780274,
|
|
"epoch": 1.1948713665218844,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048620001122850164,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.22068473547697068,
|
|
"num_tokens": 26314744.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.381536912918091,
|
|
"epoch": 1.1952890076845974,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004861897439251535,
|
|
"loss": 4.9931,
|
|
"mean_token_accuracy": 0.20787703841924668,
|
|
"num_tokens": 26324469.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.348711538314819,
|
|
"epoch": 1.1957066488473105,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048617947292467473,
|
|
"loss": 4.8762,
|
|
"mean_token_accuracy": 0.21416390985250472,
|
|
"num_tokens": 26333850.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.240645790100098,
|
|
"epoch": 1.1961242900100233,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048616919822724506,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.22519317269325256,
|
|
"num_tokens": 26342327.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.293298816680908,
|
|
"epoch": 1.1965419311727363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048615891983304436,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.21542782336473465,
|
|
"num_tokens": 26351162.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.29336462020874,
|
|
"epoch": 1.1969595723354494,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004861486377422526,
|
|
"loss": 4.8638,
|
|
"mean_token_accuracy": 0.21124514192342758,
|
|
"num_tokens": 26361452.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.249883079528809,
|
|
"epoch": 1.1973772134981624,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004861383519550498,
|
|
"loss": 4.8328,
|
|
"mean_token_accuracy": 0.2201031655073166,
|
|
"num_tokens": 26370646.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.354554319381714,
|
|
"epoch": 1.1977948546608754,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00048612806247161594,
|
|
"loss": 5.0115,
|
|
"mean_token_accuracy": 0.20260423868894578,
|
|
"num_tokens": 26379829.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.306061220169068,
|
|
"epoch": 1.1982124958235885,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004861177692921313,
|
|
"loss": 4.9405,
|
|
"mean_token_accuracy": 0.20972613692283631,
|
|
"num_tokens": 26389578.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.31884617805481,
|
|
"epoch": 1.1986301369863013,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048610747241677595,
|
|
"loss": 4.8432,
|
|
"mean_token_accuracy": 0.21577268093824387,
|
|
"num_tokens": 26398586.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.288777017593384,
|
|
"epoch": 1.1990477781490143,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004860971718457302,
|
|
"loss": 4.8857,
|
|
"mean_token_accuracy": 0.21273362934589385,
|
|
"num_tokens": 26407379.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.222073268890381,
|
|
"epoch": 1.1994654193117273,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004860868675791743,
|
|
"loss": 4.752,
|
|
"mean_token_accuracy": 0.22450169175863266,
|
|
"num_tokens": 26416489.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.322600317001343,
|
|
"epoch": 1.1998830604744404,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048607655961728876,
|
|
"loss": 4.8947,
|
|
"mean_token_accuracy": 0.21046234518289567,
|
|
"num_tokens": 26424768.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.306586456298828,
|
|
"epoch": 1.2003007016371534,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000486066247960254,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.20874216705560683,
|
|
"num_tokens": 26435175.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.226129865646362,
|
|
"epoch": 1.2007183427998664,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048605593260825044,
|
|
"loss": 4.7768,
|
|
"mean_token_accuracy": 0.21988315880298615,
|
|
"num_tokens": 26443492.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.331259775161743,
|
|
"epoch": 1.2011359839625793,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048604561356145875,
|
|
"loss": 4.8157,
|
|
"mean_token_accuracy": 0.2181943729519844,
|
|
"num_tokens": 26452239.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.267340469360351,
|
|
"epoch": 1.2015536251252923,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048603529082005955,
|
|
"loss": 4.9663,
|
|
"mean_token_accuracy": 0.2122291088104248,
|
|
"num_tokens": 26461010.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.233697843551636,
|
|
"epoch": 1.2019712662880053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048602496438423354,
|
|
"loss": 4.8326,
|
|
"mean_token_accuracy": 0.21397516131401062,
|
|
"num_tokens": 26470762.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.254516458511352,
|
|
"epoch": 1.2023889074507184,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004860146342541616,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.2227164775133133,
|
|
"num_tokens": 26479592.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.2286559581756595,
|
|
"epoch": 1.2028065486134314,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004860043004300244,
|
|
"loss": 4.7891,
|
|
"mean_token_accuracy": 0.2198523461818695,
|
|
"num_tokens": 26488245.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.329161262512207,
|
|
"epoch": 1.2032241897761444,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000485993962912003,
|
|
"loss": 4.8537,
|
|
"mean_token_accuracy": 0.21521327793598174,
|
|
"num_tokens": 26497039.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.269559621810913,
|
|
"epoch": 1.2036418309388572,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004859836217002783,
|
|
"loss": 4.8868,
|
|
"mean_token_accuracy": 0.21336199194192887,
|
|
"num_tokens": 26506116.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.2657799243927,
|
|
"epoch": 1.2040594721015703,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004859732767950313,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.2276120290160179,
|
|
"num_tokens": 26514309.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.3064085960388185,
|
|
"epoch": 1.2044771132642833,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048596292819644315,
|
|
"loss": 4.8667,
|
|
"mean_token_accuracy": 0.22201981544494628,
|
|
"num_tokens": 26523425.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.367256021499633,
|
|
"epoch": 1.2048947544269963,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000485952575904695,
|
|
"loss": 4.9718,
|
|
"mean_token_accuracy": 0.21298659443855286,
|
|
"num_tokens": 26532723.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.309935235977173,
|
|
"epoch": 1.2053123955897094,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048594221991996814,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.21626179665327072,
|
|
"num_tokens": 26541933.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.318564176559448,
|
|
"epoch": 1.2057300367524224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048593186024244373,
|
|
"loss": 4.9879,
|
|
"mean_token_accuracy": 0.2114737421274185,
|
|
"num_tokens": 26552071.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.367073488235474,
|
|
"epoch": 1.2061476779151352,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004859214968723033,
|
|
"loss": 5.0073,
|
|
"mean_token_accuracy": 0.209544737637043,
|
|
"num_tokens": 26561470.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.327428531646729,
|
|
"epoch": 1.2065653190778483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048591112980972813,
|
|
"loss": 4.8313,
|
|
"mean_token_accuracy": 0.22608863711357116,
|
|
"num_tokens": 26570448.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.359742879867554,
|
|
"epoch": 1.2069829602405613,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004859007590548997,
|
|
"loss": 4.9149,
|
|
"mean_token_accuracy": 0.21175689548254012,
|
|
"num_tokens": 26579206.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.233920907974243,
|
|
"epoch": 1.2074006014032743,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048589038460799974,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.21138938814401625,
|
|
"num_tokens": 26587955.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.269325160980225,
|
|
"epoch": 1.2078182425659874,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004858800064692097,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.21000116914510727,
|
|
"num_tokens": 26597635.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.323833465576172,
|
|
"epoch": 1.2082358837287004,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048586962463871124,
|
|
"loss": 4.823,
|
|
"mean_token_accuracy": 0.2257804661989212,
|
|
"num_tokens": 26606245.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.353737545013428,
|
|
"epoch": 1.2086535248914134,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048585923911668625,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.20958715677261353,
|
|
"num_tokens": 26614464.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.3094933986663815,
|
|
"epoch": 1.2090711660541262,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048584884990331644,
|
|
"loss": 4.932,
|
|
"mean_token_accuracy": 0.2166315272450447,
|
|
"num_tokens": 26623436.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.309448099136352,
|
|
"epoch": 1.2094888072168393,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048583845699878375,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.21908650547266006,
|
|
"num_tokens": 26632415.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.24619870185852,
|
|
"epoch": 1.2099064483795523,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004858280604032701,
|
|
"loss": 4.7569,
|
|
"mean_token_accuracy": 0.22624566704034804,
|
|
"num_tokens": 26641618.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.350720024108886,
|
|
"epoch": 1.2103240895422653,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00048581766011695745,
|
|
"loss": 4.9649,
|
|
"mean_token_accuracy": 0.20945643931627272,
|
|
"num_tokens": 26651290.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.327399778366089,
|
|
"epoch": 1.2107417307049784,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048580725614002785,
|
|
"loss": 4.858,
|
|
"mean_token_accuracy": 0.21865999400615693,
|
|
"num_tokens": 26660945.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.271085023880005,
|
|
"epoch": 1.2111593718676912,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048579684847266353,
|
|
"loss": 4.8499,
|
|
"mean_token_accuracy": 0.21794893741607665,
|
|
"num_tokens": 26670221.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.281561756134034,
|
|
"epoch": 1.2115770130304042,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004857864371150467,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.22182633578777314,
|
|
"num_tokens": 26679074.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.384877014160156,
|
|
"epoch": 1.2119946541931172,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048577602206735943,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.2129413366317749,
|
|
"num_tokens": 26689124.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.218738031387329,
|
|
"epoch": 1.2124122953558303,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004857656033297843,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.22439024299383165,
|
|
"num_tokens": 26698421.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.271650695800782,
|
|
"epoch": 1.2128299365185433,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00048575518090250347,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.22476147264242172,
|
|
"num_tokens": 26706432.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.292372369766236,
|
|
"epoch": 1.2132475776812564,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004857447547856996,
|
|
"loss": 4.8471,
|
|
"mean_token_accuracy": 0.21744336038827897,
|
|
"num_tokens": 26715224.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.346169757843017,
|
|
"epoch": 1.2136652188439694,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004857343249795552,
|
|
"loss": 4.8575,
|
|
"mean_token_accuracy": 0.21627590656280518,
|
|
"num_tokens": 26724311.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.277516555786133,
|
|
"epoch": 1.2140828600066822,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004857238914842526,
|
|
"loss": 4.8912,
|
|
"mean_token_accuracy": 0.20660692006349562,
|
|
"num_tokens": 26734012.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.311799716949463,
|
|
"epoch": 1.2145005011693952,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048571345429997473,
|
|
"loss": 4.8048,
|
|
"mean_token_accuracy": 0.2193123698234558,
|
|
"num_tokens": 26742745.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.266531276702881,
|
|
"epoch": 1.2149181423321083,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048570301342690416,
|
|
"loss": 4.8319,
|
|
"mean_token_accuracy": 0.22856603413820267,
|
|
"num_tokens": 26751856.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.155004024505615,
|
|
"epoch": 1.2153357834948213,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004856925688652238,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22501174509525299,
|
|
"num_tokens": 26761359.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.256842947006225,
|
|
"epoch": 1.2157534246575343,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048568212061511634,
|
|
"loss": 4.7733,
|
|
"mean_token_accuracy": 0.22293663173913955,
|
|
"num_tokens": 26770588.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.356494808197022,
|
|
"epoch": 1.2161710658202471,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048567166867676475,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.21302710771560668,
|
|
"num_tokens": 26780637.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.269391632080078,
|
|
"epoch": 1.2165887069829602,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048566121305035207,
|
|
"loss": 4.809,
|
|
"mean_token_accuracy": 0.2238632246851921,
|
|
"num_tokens": 26789387.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.326649570465088,
|
|
"epoch": 1.2170063481456732,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048565075373606126,
|
|
"loss": 4.9067,
|
|
"mean_token_accuracy": 0.21431868076324462,
|
|
"num_tokens": 26798677.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.38335599899292,
|
|
"epoch": 1.2174239893083862,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048564029073407545,
|
|
"loss": 4.8766,
|
|
"mean_token_accuracy": 0.21885229051113128,
|
|
"num_tokens": 26807457.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.323902606964111,
|
|
"epoch": 1.2178416304710993,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004856298240445778,
|
|
"loss": 4.8654,
|
|
"mean_token_accuracy": 0.2140050858259201,
|
|
"num_tokens": 26816832.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.257620000839234,
|
|
"epoch": 1.2182592716338123,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004856193536677515,
|
|
"loss": 4.8497,
|
|
"mean_token_accuracy": 0.21872137635946273,
|
|
"num_tokens": 26826534.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.3156215190887455,
|
|
"epoch": 1.2186769127965253,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048560887960377995,
|
|
"loss": 4.9251,
|
|
"mean_token_accuracy": 0.2118704929947853,
|
|
"num_tokens": 26835981.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.292657995223999,
|
|
"epoch": 1.2190945539592382,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048559840185284647,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.22171190679073333,
|
|
"num_tokens": 26845321.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.228299808502197,
|
|
"epoch": 1.2195121951219512,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048558792041513446,
|
|
"loss": 4.7425,
|
|
"mean_token_accuracy": 0.21947605460882186,
|
|
"num_tokens": 26853866.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.246435689926147,
|
|
"epoch": 1.2199298362846642,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004855774352908273,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.21934428215026855,
|
|
"num_tokens": 26863581.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.355377626419068,
|
|
"epoch": 1.2203474774473773,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004855669464801088,
|
|
"loss": 4.8646,
|
|
"mean_token_accuracy": 0.21628391593694687,
|
|
"num_tokens": 26873481.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.394048976898193,
|
|
"epoch": 1.2207651186100903,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048555645398316237,
|
|
"loss": 4.981,
|
|
"mean_token_accuracy": 0.20974211096763612,
|
|
"num_tokens": 26882222.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.31308650970459,
|
|
"epoch": 1.221182759772803,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004855459578001718,
|
|
"loss": 4.906,
|
|
"mean_token_accuracy": 0.212378890812397,
|
|
"num_tokens": 26891305.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.265502548217773,
|
|
"epoch": 1.2216004009355161,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004855354579313208,
|
|
"loss": 4.8568,
|
|
"mean_token_accuracy": 0.21856818348169327,
|
|
"num_tokens": 26901759.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.328189325332642,
|
|
"epoch": 1.2220180420982292,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004855249543767932,
|
|
"loss": 4.9231,
|
|
"mean_token_accuracy": 0.20627068728208542,
|
|
"num_tokens": 26911183.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.357437038421631,
|
|
"epoch": 1.2224356832609422,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048551444713677285,
|
|
"loss": 4.9119,
|
|
"mean_token_accuracy": 0.20907391607761383,
|
|
"num_tokens": 26921185.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.324467372894287,
|
|
"epoch": 1.2228533244236552,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048550393621144374,
|
|
"loss": 4.7414,
|
|
"mean_token_accuracy": 0.22182883620262145,
|
|
"num_tokens": 26930034.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.244652938842774,
|
|
"epoch": 1.2232709655863683,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004854934216009898,
|
|
"loss": 4.7971,
|
|
"mean_token_accuracy": 0.2220032885670662,
|
|
"num_tokens": 26939273.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.252768039703369,
|
|
"epoch": 1.2236886067490813,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004854829033055951,
|
|
"loss": 4.8124,
|
|
"mean_token_accuracy": 0.21972059160470964,
|
|
"num_tokens": 26948924.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.2539831638336185,
|
|
"epoch": 1.2241062479117941,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004854723813254439,
|
|
"loss": 4.7456,
|
|
"mean_token_accuracy": 0.22485262155532837,
|
|
"num_tokens": 26957492.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.289710426330567,
|
|
"epoch": 1.2245238890745072,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004854618556607203,
|
|
"loss": 4.953,
|
|
"mean_token_accuracy": 0.21279072463512422,
|
|
"num_tokens": 26967114.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.3759222507476805,
|
|
"epoch": 1.2249415302372202,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048545132631160856,
|
|
"loss": 4.9008,
|
|
"mean_token_accuracy": 0.208928382396698,
|
|
"num_tokens": 26976661.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.336704063415527,
|
|
"epoch": 1.2253591713999332,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004854407932782931,
|
|
"loss": 4.9024,
|
|
"mean_token_accuracy": 0.21249025762081147,
|
|
"num_tokens": 26986044.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.2696455955505375,
|
|
"epoch": 1.2257768125626463,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004854302565609582,
|
|
"loss": 4.908,
|
|
"mean_token_accuracy": 0.21436883360147477,
|
|
"num_tokens": 26995166.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.2917258739471436,
|
|
"epoch": 1.226194453725359,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048541971615978833,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.209498330950737,
|
|
"num_tokens": 27004245.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.373892688751221,
|
|
"epoch": 1.226612094888072,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048540917207496806,
|
|
"loss": 4.9716,
|
|
"mean_token_accuracy": 0.21084311306476594,
|
|
"num_tokens": 27013278.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.2743549823760985,
|
|
"epoch": 1.2270297360507851,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048539862430668204,
|
|
"loss": 4.8155,
|
|
"mean_token_accuracy": 0.21489666402339935,
|
|
"num_tokens": 27022387.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.302745962142945,
|
|
"epoch": 1.2274473772134982,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048538807285511474,
|
|
"loss": 4.8738,
|
|
"mean_token_accuracy": 0.21680776327848433,
|
|
"num_tokens": 27031760.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.310967206954956,
|
|
"epoch": 1.2278650183762112,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048537751772045103,
|
|
"loss": 4.8276,
|
|
"mean_token_accuracy": 0.22148662209510803,
|
|
"num_tokens": 27040908.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.285741376876831,
|
|
"epoch": 1.2282826595389242,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004853669589028757,
|
|
"loss": 4.8399,
|
|
"mean_token_accuracy": 0.21420278549194335,
|
|
"num_tokens": 27049989.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.251460170745849,
|
|
"epoch": 1.2287003007016373,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004853563964025734,
|
|
"loss": 4.8301,
|
|
"mean_token_accuracy": 0.21846381276845933,
|
|
"num_tokens": 27058706.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.239066553115845,
|
|
"epoch": 1.22911794186435,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048534583021972926,
|
|
"loss": 4.8164,
|
|
"mean_token_accuracy": 0.22162171006202697,
|
|
"num_tokens": 27067604.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.298876237869263,
|
|
"epoch": 1.2295355830270631,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004853352603545281,
|
|
"loss": 4.8468,
|
|
"mean_token_accuracy": 0.22004488706588746,
|
|
"num_tokens": 27076489.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.272461032867431,
|
|
"epoch": 1.2299532241897762,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004853246868071551,
|
|
"loss": 4.8177,
|
|
"mean_token_accuracy": 0.21881693452596665,
|
|
"num_tokens": 27085750.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.298204183578491,
|
|
"epoch": 1.2303708653524892,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00048531410957779533,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.21630230098962783,
|
|
"num_tokens": 27095509.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.285034227371216,
|
|
"epoch": 1.2307885065152022,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004853035286666338,
|
|
"loss": 4.8355,
|
|
"mean_token_accuracy": 0.21437689214944838,
|
|
"num_tokens": 27105054.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.322489213943482,
|
|
"epoch": 1.231206147677915,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000485292944073856,
|
|
"loss": 4.9349,
|
|
"mean_token_accuracy": 0.21130228340625762,
|
|
"num_tokens": 27113497.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.368675804138183,
|
|
"epoch": 1.231623788840628,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000485282355799647,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.2193445846438408,
|
|
"num_tokens": 27122718.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.296363449096679,
|
|
"epoch": 1.232041430003341,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048527176384419217,
|
|
"loss": 4.8391,
|
|
"mean_token_accuracy": 0.22136377543210983,
|
|
"num_tokens": 27132361.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.33229284286499,
|
|
"epoch": 1.2324590711660541,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048526116820767713,
|
|
"loss": 4.8388,
|
|
"mean_token_accuracy": 0.2175703078508377,
|
|
"num_tokens": 27141430.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.3013335227966305,
|
|
"epoch": 1.2328767123287672,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004852505688902872,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.2172665387392044,
|
|
"num_tokens": 27150154.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.336981391906738,
|
|
"epoch": 1.2332943534914802,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004852399658922079,
|
|
"loss": 4.867,
|
|
"mean_token_accuracy": 0.22232827842235564,
|
|
"num_tokens": 27159314.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.376015520095825,
|
|
"epoch": 1.2337119946541932,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004852293592136251,
|
|
"loss": 4.8779,
|
|
"mean_token_accuracy": 0.21136181354522704,
|
|
"num_tokens": 27167537.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.361434841156006,
|
|
"epoch": 1.234129635816906,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004852187488547242,
|
|
"loss": 4.8965,
|
|
"mean_token_accuracy": 0.21187645345926284,
|
|
"num_tokens": 27177037.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.366490125656128,
|
|
"epoch": 1.234547276979619,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048520813481569116,
|
|
"loss": 4.9159,
|
|
"mean_token_accuracy": 0.21072989702224731,
|
|
"num_tokens": 27186498.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.314163017272949,
|
|
"epoch": 1.2349649181423321,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004851975170967116,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.22537866979837418,
|
|
"num_tokens": 27195170.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.313639497756958,
|
|
"epoch": 1.2353825593050451,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004851868956979715,
|
|
"loss": 4.8371,
|
|
"mean_token_accuracy": 0.21945143789052962,
|
|
"num_tokens": 27204756.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.1697132110595705,
|
|
"epoch": 1.2358002004677582,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004851762706196568,
|
|
"loss": 4.796,
|
|
"mean_token_accuracy": 0.21030900925397872,
|
|
"num_tokens": 27213607.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.296873903274536,
|
|
"epoch": 1.236217841630471,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048516564186195353,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.21650363504886627,
|
|
"num_tokens": 27222887.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.313908576965332,
|
|
"epoch": 1.236635482793184,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048515500942504763,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.22117195129394532,
|
|
"num_tokens": 27231374.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.376058626174927,
|
|
"epoch": 1.237053123955897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048514437330912544,
|
|
"loss": 4.954,
|
|
"mean_token_accuracy": 0.20541544407606124,
|
|
"num_tokens": 27239929.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.291946220397949,
|
|
"epoch": 1.23747076511861,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048513373351437294,
|
|
"loss": 4.8274,
|
|
"mean_token_accuracy": 0.2132383480668068,
|
|
"num_tokens": 27249789.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.297772455215454,
|
|
"epoch": 1.2378884062813231,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048512309004097653,
|
|
"loss": 4.8515,
|
|
"mean_token_accuracy": 0.2113387629389763,
|
|
"num_tokens": 27259773.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.388635778427124,
|
|
"epoch": 1.2383060474440362,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004851124428891226,
|
|
"loss": 4.9672,
|
|
"mean_token_accuracy": 0.20877982974052428,
|
|
"num_tokens": 27268494.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.338715839385986,
|
|
"epoch": 1.2387236886067492,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004851017920589973,
|
|
"loss": 4.8686,
|
|
"mean_token_accuracy": 0.20927378237247468,
|
|
"num_tokens": 27276914.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.3160933494567875,
|
|
"epoch": 1.239141329769462,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004850911375507873,
|
|
"loss": 4.8756,
|
|
"mean_token_accuracy": 0.21857189536094665,
|
|
"num_tokens": 27286091.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.320493507385254,
|
|
"epoch": 1.239558970932175,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048508047936467907,
|
|
"loss": 4.9133,
|
|
"mean_token_accuracy": 0.21557260155677796,
|
|
"num_tokens": 27295201.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.341425371170044,
|
|
"epoch": 1.239976612094888,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048506981750085914,
|
|
"loss": 4.9612,
|
|
"mean_token_accuracy": 0.21064301282167436,
|
|
"num_tokens": 27303900.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.324868869781494,
|
|
"epoch": 1.240394253257601,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00048505915195951423,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.2208365336060524,
|
|
"num_tokens": 27312613.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.2863000392913815,
|
|
"epoch": 1.2408118944203141,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048504848274083095,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.2115367516875267,
|
|
"num_tokens": 27322047.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.417201185226441,
|
|
"epoch": 1.241229535583027,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048503780984499625,
|
|
"loss": 5.0924,
|
|
"mean_token_accuracy": 0.2015346869826317,
|
|
"num_tokens": 27332163.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.379379177093506,
|
|
"epoch": 1.24164717674574,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004850271332721968,
|
|
"loss": 4.9006,
|
|
"mean_token_accuracy": 0.21151832938194276,
|
|
"num_tokens": 27343838.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.343622446060181,
|
|
"epoch": 1.242064817908453,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004850164530226196,
|
|
"loss": 4.8663,
|
|
"mean_token_accuracy": 0.22036096304655076,
|
|
"num_tokens": 27352362.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.313168478012085,
|
|
"epoch": 1.242482459071166,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004850057690964515,
|
|
"loss": 4.9819,
|
|
"mean_token_accuracy": 0.20046741366386414,
|
|
"num_tokens": 27361444.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.266669130325317,
|
|
"epoch": 1.242900100233879,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048499508149387973,
|
|
"loss": 4.7866,
|
|
"mean_token_accuracy": 0.21779994517564774,
|
|
"num_tokens": 27370872.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.326110601425171,
|
|
"epoch": 1.2433177413965921,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048498439021509124,
|
|
"loss": 4.8624,
|
|
"mean_token_accuracy": 0.21661933064460753,
|
|
"num_tokens": 27380628.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.331454181671143,
|
|
"epoch": 1.2437353825593052,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004849736952602732,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.21785832196474075,
|
|
"num_tokens": 27390187.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.4016834735870365,
|
|
"epoch": 1.244153023722018,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000484962996629613,
|
|
"loss": 5.0733,
|
|
"mean_token_accuracy": 0.2022506207227707,
|
|
"num_tokens": 27400307.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.332730770111084,
|
|
"epoch": 1.244570664884731,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048495229432329775,
|
|
"loss": 4.8874,
|
|
"mean_token_accuracy": 0.2125076338648796,
|
|
"num_tokens": 27410060.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.3340222358703615,
|
|
"epoch": 1.244988306047444,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048494158834151485,
|
|
"loss": 4.9175,
|
|
"mean_token_accuracy": 0.21331647336483,
|
|
"num_tokens": 27419119.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.305416393280029,
|
|
"epoch": 1.245405947210157,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048493087868445176,
|
|
"loss": 4.81,
|
|
"mean_token_accuracy": 0.22290702760219575,
|
|
"num_tokens": 27428052.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.303903102874756,
|
|
"epoch": 1.24582358837287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048492016535229594,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.22014310359954833,
|
|
"num_tokens": 27436418.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.339519691467285,
|
|
"epoch": 1.246241229535583,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004849094483452349,
|
|
"loss": 4.9791,
|
|
"mean_token_accuracy": 0.21203061044216157,
|
|
"num_tokens": 27445609.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.293126726150513,
|
|
"epoch": 1.246658870698296,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004848987276634564,
|
|
"loss": 4.9391,
|
|
"mean_token_accuracy": 0.2157802477478981,
|
|
"num_tokens": 27456250.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.333510303497315,
|
|
"epoch": 1.247076511861009,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048488800330714795,
|
|
"loss": 4.8625,
|
|
"mean_token_accuracy": 0.20993169844150544,
|
|
"num_tokens": 27466134.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.2689817428588865,
|
|
"epoch": 1.247494153023722,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00048487727527649733,
|
|
"loss": 4.8533,
|
|
"mean_token_accuracy": 0.21730221807956696,
|
|
"num_tokens": 27476097.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.274343252182007,
|
|
"epoch": 1.247911794186435,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048486654357169246,
|
|
"loss": 4.8542,
|
|
"mean_token_accuracy": 0.2156984403729439,
|
|
"num_tokens": 27485850.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.302305746078491,
|
|
"epoch": 1.248329435349148,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004848558081929211,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.21646545380353927,
|
|
"num_tokens": 27494169.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.283707523345948,
|
|
"epoch": 1.2487470765118611,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004848450691403712,
|
|
"loss": 4.8785,
|
|
"mean_token_accuracy": 0.21309243738651276,
|
|
"num_tokens": 27502599.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.191489505767822,
|
|
"epoch": 1.249164717674574,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004848343264142307,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.23608574271202087,
|
|
"num_tokens": 27511278.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.355430459976196,
|
|
"epoch": 1.249582358837287,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004848235800146879,
|
|
"loss": 4.887,
|
|
"mean_token_accuracy": 0.2120361417531967,
|
|
"num_tokens": 27521040.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.2890739917755125,
|
|
"epoch": 1.25,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004848128299419306,
|
|
"loss": 4.8821,
|
|
"mean_token_accuracy": 0.2098961666226387,
|
|
"num_tokens": 27530893.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.314749383926392,
|
|
"epoch": 1.250417641162713,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00048480207619614726,
|
|
"loss": 4.9326,
|
|
"mean_token_accuracy": 0.2089676320552826,
|
|
"num_tokens": 27540401.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.216175127029419,
|
|
"epoch": 1.250835282325426,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000484791318777526,
|
|
"loss": 4.7196,
|
|
"mean_token_accuracy": 0.22853955179452895,
|
|
"num_tokens": 27549951.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.3027379512786865,
|
|
"epoch": 1.2512529234881389,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00048478055768625517,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.2174242243170738,
|
|
"num_tokens": 27559170.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.25973539352417,
|
|
"epoch": 1.251670564650852,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048476979292252323,
|
|
"loss": 4.7184,
|
|
"mean_token_accuracy": 0.22467818409204482,
|
|
"num_tokens": 27567094.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.326577806472779,
|
|
"epoch": 1.252088205813565,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004847590244865185,
|
|
"loss": 4.8436,
|
|
"mean_token_accuracy": 0.21752322763204573,
|
|
"num_tokens": 27575141.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.335418081283569,
|
|
"epoch": 1.252505846976278,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048474825237842964,
|
|
"loss": 4.9105,
|
|
"mean_token_accuracy": 0.21185650527477265,
|
|
"num_tokens": 27584094.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.338655853271485,
|
|
"epoch": 1.252923488138991,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000484737476598445,
|
|
"loss": 4.9851,
|
|
"mean_token_accuracy": 0.20382583141326904,
|
|
"num_tokens": 27593157.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.252923488138991,
|
|
"eval_entropy": 5.017163972989959,
|
|
"eval_loss": 4.870966911315918,
|
|
"eval_mean_token_accuracy": 0.22649230087581163,
|
|
"eval_num_tokens": 27593157.0,
|
|
"eval_runtime": 45.942,
|
|
"eval_samples_per_second": 821.971,
|
|
"eval_steps_per_second": 102.76,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119720,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 3000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 6062070923919360.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|