6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.25058469762779817,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 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
|
|
}
|
|
],
|
|
"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": 1217734590136320.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|