6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.3462204270051933,
|
|
"eval_steps": 3000,
|
|
"global_step": 3000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.74217529296875,
|
|
"epoch": 0.0005770340450086555,
|
|
"grad_norm": 4.34375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.8326,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 14330.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.742151832580566,
|
|
"epoch": 0.001154068090017311,
|
|
"grad_norm": 4.65625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.8057,
|
|
"mean_token_accuracy": 8.11688310932368e-05,
|
|
"num_tokens": 26284.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.742152214050293,
|
|
"epoch": 0.0017311021350259665,
|
|
"grad_norm": 5.125,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.7851,
|
|
"mean_token_accuracy": 0.00030720371869392694,
|
|
"num_tokens": 38394.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.742230319976807,
|
|
"epoch": 0.002308136180034622,
|
|
"grad_norm": 4.8125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.7433,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 51341.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.742213916778564,
|
|
"epoch": 0.0028851702250432777,
|
|
"grad_norm": 4.4375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 10.64,
|
|
"mean_token_accuracy": 0.003926298324950039,
|
|
"num_tokens": 64559.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.741898727416991,
|
|
"epoch": 0.003462204270051933,
|
|
"grad_norm": 3.921875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.5216,
|
|
"mean_token_accuracy": 0.03795875590294599,
|
|
"num_tokens": 76688.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.740620136260986,
|
|
"epoch": 0.004039238315060588,
|
|
"grad_norm": 3.46875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.3693,
|
|
"mean_token_accuracy": 0.05394260324537754,
|
|
"num_tokens": 88392.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.736398124694825,
|
|
"epoch": 0.004616272360069244,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.278,
|
|
"mean_token_accuracy": 0.052969465777277944,
|
|
"num_tokens": 100542.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.728193473815917,
|
|
"epoch": 0.0051933064050779,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 10.0828,
|
|
"mean_token_accuracy": 0.05751506164669991,
|
|
"num_tokens": 113190.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.716622734069825,
|
|
"epoch": 0.005770340450086555,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 10.0239,
|
|
"mean_token_accuracy": 0.05997682772576809,
|
|
"num_tokens": 125554.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.704752922058105,
|
|
"epoch": 0.006347374495095211,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.9661,
|
|
"mean_token_accuracy": 0.06483750529587269,
|
|
"num_tokens": 138527.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.696050262451172,
|
|
"epoch": 0.006924408540103866,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 10.0065,
|
|
"mean_token_accuracy": 0.0495222195982933,
|
|
"num_tokens": 150404.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.69492769241333,
|
|
"epoch": 0.0075014425851125215,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.9359,
|
|
"mean_token_accuracy": 0.055068480968475345,
|
|
"num_tokens": 163743.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.692989349365234,
|
|
"epoch": 0.008078476630121177,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.9027,
|
|
"mean_token_accuracy": 0.052650950476527215,
|
|
"num_tokens": 175657.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.689637851715087,
|
|
"epoch": 0.008655510675129832,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.8572,
|
|
"mean_token_accuracy": 0.053944576904177664,
|
|
"num_tokens": 188756.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.678643798828125,
|
|
"epoch": 0.009232544720138488,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.801,
|
|
"mean_token_accuracy": 0.053839181736111644,
|
|
"num_tokens": 200548.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.661964607238769,
|
|
"epoch": 0.009809578765147143,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.7136,
|
|
"mean_token_accuracy": 0.06665473207831382,
|
|
"num_tokens": 213307.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.63293104171753,
|
|
"epoch": 0.0103866128101558,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.6765,
|
|
"mean_token_accuracy": 0.06476713679730892,
|
|
"num_tokens": 226863.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.615675067901611,
|
|
"epoch": 0.010963646855164455,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 9.632,
|
|
"mean_token_accuracy": 0.06121704056859016,
|
|
"num_tokens": 238655.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.613676834106446,
|
|
"epoch": 0.01154068090017311,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 9.5655,
|
|
"mean_token_accuracy": 0.0704349122941494,
|
|
"num_tokens": 251118.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.56223793029785,
|
|
"epoch": 0.012117714945181766,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 9.4708,
|
|
"mean_token_accuracy": 0.07793616428971291,
|
|
"num_tokens": 263665.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.50258274078369,
|
|
"epoch": 0.012694748990190421,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 9.4156,
|
|
"mean_token_accuracy": 0.07520635947585105,
|
|
"num_tokens": 276531.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.506224632263184,
|
|
"epoch": 0.013271783035199077,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 9.367,
|
|
"mean_token_accuracy": 0.0757908646017313,
|
|
"num_tokens": 289878.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.472508811950684,
|
|
"epoch": 0.013848817080207732,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 9.2817,
|
|
"mean_token_accuracy": 0.07052403129637241,
|
|
"num_tokens": 302705.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 10.418921184539794,
|
|
"epoch": 0.014425851125216388,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 9.1572,
|
|
"mean_token_accuracy": 0.08047313243150711,
|
|
"num_tokens": 314775.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 10.330512046813965,
|
|
"epoch": 0.015002885170225043,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 9.1596,
|
|
"mean_token_accuracy": 0.07958029508590699,
|
|
"num_tokens": 328563.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 10.242788600921632,
|
|
"epoch": 0.015579919215233698,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 9.0052,
|
|
"mean_token_accuracy": 0.08549408987164497,
|
|
"num_tokens": 341820.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 10.257353591918946,
|
|
"epoch": 0.016156953260242354,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.9633,
|
|
"mean_token_accuracy": 0.08436901345849038,
|
|
"num_tokens": 354994.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 10.1291428565979,
|
|
"epoch": 0.01673398730525101,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 8.8768,
|
|
"mean_token_accuracy": 0.08217294588685035,
|
|
"num_tokens": 365852.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 10.04762372970581,
|
|
"epoch": 0.017311021350259664,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 8.8657,
|
|
"mean_token_accuracy": 0.07920254692435265,
|
|
"num_tokens": 379147.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 10.023890781402589,
|
|
"epoch": 0.01788805539526832,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 8.8181,
|
|
"mean_token_accuracy": 0.0735938459634781,
|
|
"num_tokens": 392257.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 9.896601295471191,
|
|
"epoch": 0.018465089440276975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 8.7072,
|
|
"mean_token_accuracy": 0.07832617908716202,
|
|
"num_tokens": 405249.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 9.709205722808838,
|
|
"epoch": 0.019042123485285632,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 8.6516,
|
|
"mean_token_accuracy": 0.08040346056222916,
|
|
"num_tokens": 417819.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 9.60182809829712,
|
|
"epoch": 0.019619157530294286,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 8.5351,
|
|
"mean_token_accuracy": 0.08392796665430069,
|
|
"num_tokens": 429364.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 9.431674385070801,
|
|
"epoch": 0.020196191575302943,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 8.5151,
|
|
"mean_token_accuracy": 0.08911501616239548,
|
|
"num_tokens": 441804.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 9.291469860076905,
|
|
"epoch": 0.0207732256203116,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 8.4571,
|
|
"mean_token_accuracy": 0.08912580311298371,
|
|
"num_tokens": 453886.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 9.148678588867188,
|
|
"epoch": 0.021350259665320254,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 8.4362,
|
|
"mean_token_accuracy": 0.08946132510900498,
|
|
"num_tokens": 465828.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 9.080477714538574,
|
|
"epoch": 0.02192729371032891,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 8.3788,
|
|
"mean_token_accuracy": 0.09273218810558319,
|
|
"num_tokens": 478783.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.97773780822754,
|
|
"epoch": 0.022504327755337564,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 8.4168,
|
|
"mean_token_accuracy": 0.08846393302083015,
|
|
"num_tokens": 491167.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 8.89993076324463,
|
|
"epoch": 0.02308136180034622,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 8.3844,
|
|
"mean_token_accuracy": 0.09320372641086579,
|
|
"num_tokens": 503511.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.787849521636963,
|
|
"epoch": 0.023658395845354875,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 8.2705,
|
|
"mean_token_accuracy": 0.0978940948843956,
|
|
"num_tokens": 515816.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 8.848995685577393,
|
|
"epoch": 0.024235429890363532,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 8.3781,
|
|
"mean_token_accuracy": 0.08895341083407401,
|
|
"num_tokens": 528919.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 8.744617557525634,
|
|
"epoch": 0.024812463935372186,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 8.2875,
|
|
"mean_token_accuracy": 0.10044435858726501,
|
|
"num_tokens": 540973.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 8.707606983184814,
|
|
"epoch": 0.025389497980380843,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 8.2458,
|
|
"mean_token_accuracy": 0.10567026063799859,
|
|
"num_tokens": 553265.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 8.753429126739501,
|
|
"epoch": 0.025966532025389497,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.000112,
|
|
"loss": 8.3474,
|
|
"mean_token_accuracy": 0.0927657037973404,
|
|
"num_tokens": 567534.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 8.750615215301513,
|
|
"epoch": 0.026543566070398154,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 8.2643,
|
|
"mean_token_accuracy": 0.09682516902685165,
|
|
"num_tokens": 579297.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 8.695602512359619,
|
|
"epoch": 0.027120600115406807,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 8.2384,
|
|
"mean_token_accuracy": 0.09817592948675155,
|
|
"num_tokens": 592554.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 8.732758808135987,
|
|
"epoch": 0.027697634160415464,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 8.2291,
|
|
"mean_token_accuracy": 0.09817634895443916,
|
|
"num_tokens": 605038.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 8.617175579071045,
|
|
"epoch": 0.02827466820542412,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 8.2451,
|
|
"mean_token_accuracy": 0.09733725637197495,
|
|
"num_tokens": 617172.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 8.57886381149292,
|
|
"epoch": 0.028851702250432775,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 8.1868,
|
|
"mean_token_accuracy": 0.09926503598690033,
|
|
"num_tokens": 629243.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 8.597729873657226,
|
|
"epoch": 0.029428736295441432,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000127,
|
|
"loss": 8.2453,
|
|
"mean_token_accuracy": 0.09898478463292122,
|
|
"num_tokens": 641487.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 8.657223415374755,
|
|
"epoch": 0.030005770340450086,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 8.2382,
|
|
"mean_token_accuracy": 0.08884634375572205,
|
|
"num_tokens": 653214.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 8.59217348098755,
|
|
"epoch": 0.030582804385458743,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 8.1923,
|
|
"mean_token_accuracy": 0.11060753613710403,
|
|
"num_tokens": 666549.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 8.513946914672852,
|
|
"epoch": 0.031159838430467397,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 8.2137,
|
|
"mean_token_accuracy": 0.10257397592067719,
|
|
"num_tokens": 679443.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 8.499358367919921,
|
|
"epoch": 0.031736872475476054,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 8.2136,
|
|
"mean_token_accuracy": 0.09787259846925736,
|
|
"num_tokens": 692929.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 8.5993070602417,
|
|
"epoch": 0.03231390652048471,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 8.133,
|
|
"mean_token_accuracy": 0.1011851780116558,
|
|
"num_tokens": 705605.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 8.563784217834472,
|
|
"epoch": 0.03289094056549336,
|
|
"grad_norm": 0.7109375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 8.2181,
|
|
"mean_token_accuracy": 0.09577601477503776,
|
|
"num_tokens": 719064.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 8.528156089782716,
|
|
"epoch": 0.03346797461050202,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 8.148,
|
|
"mean_token_accuracy": 0.10154027119278908,
|
|
"num_tokens": 732572.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 8.501526927947998,
|
|
"epoch": 0.034045008655510675,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 8.1452,
|
|
"mean_token_accuracy": 0.09947796389460564,
|
|
"num_tokens": 745161.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 8.492893695831299,
|
|
"epoch": 0.03462204270051933,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 8.1182,
|
|
"mean_token_accuracy": 0.1088537909090519,
|
|
"num_tokens": 756180.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 8.508162879943848,
|
|
"epoch": 0.03519907674552799,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000152,
|
|
"loss": 8.142,
|
|
"mean_token_accuracy": 0.10471795424818993,
|
|
"num_tokens": 768568.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 8.514046001434327,
|
|
"epoch": 0.03577611079053664,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 8.1756,
|
|
"mean_token_accuracy": 0.10089959502220154,
|
|
"num_tokens": 781580.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 8.390854835510254,
|
|
"epoch": 0.0363531448355453,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 8.0541,
|
|
"mean_token_accuracy": 0.11660909354686737,
|
|
"num_tokens": 793486.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 8.494402980804443,
|
|
"epoch": 0.03693017888055395,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 8.1249,
|
|
"mean_token_accuracy": 0.10236181169748307,
|
|
"num_tokens": 805997.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 8.422712516784667,
|
|
"epoch": 0.03750721292556261,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 8.0829,
|
|
"mean_token_accuracy": 0.10648757740855216,
|
|
"num_tokens": 817681.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 8.429091262817384,
|
|
"epoch": 0.038084246970571264,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 8.0916,
|
|
"mean_token_accuracy": 0.11145856082439423,
|
|
"num_tokens": 830027.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 8.464876174926758,
|
|
"epoch": 0.03866128101557992,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 8.1081,
|
|
"mean_token_accuracy": 0.10330765470862388,
|
|
"num_tokens": 842862.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 8.401940250396729,
|
|
"epoch": 0.03923831506058857,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 8.0324,
|
|
"mean_token_accuracy": 0.10951320230960845,
|
|
"num_tokens": 856548.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 8.391893863677979,
|
|
"epoch": 0.03981534910559723,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 8.0417,
|
|
"mean_token_accuracy": 0.10960106775164605,
|
|
"num_tokens": 869651.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 8.451942253112794,
|
|
"epoch": 0.040392383150605886,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 8.0689,
|
|
"mean_token_accuracy": 0.1082707829773426,
|
|
"num_tokens": 880717.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 8.369545364379883,
|
|
"epoch": 0.04096941719561454,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 8.0521,
|
|
"mean_token_accuracy": 0.11259332075715064,
|
|
"num_tokens": 894066.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 8.282257270812988,
|
|
"epoch": 0.0415464512406232,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.9567,
|
|
"mean_token_accuracy": 0.11248702630400657,
|
|
"num_tokens": 905287.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 8.459172248840332,
|
|
"epoch": 0.042123485285631854,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000182,
|
|
"loss": 8.0392,
|
|
"mean_token_accuracy": 0.11402102708816528,
|
|
"num_tokens": 917512.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 8.318458461761475,
|
|
"epoch": 0.04270051933064051,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.9899,
|
|
"mean_token_accuracy": 0.10831499472260475,
|
|
"num_tokens": 930263.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 8.339896297454834,
|
|
"epoch": 0.04327755337564916,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 8.0425,
|
|
"mean_token_accuracy": 0.11203662231564522,
|
|
"num_tokens": 942330.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 8.366154861450195,
|
|
"epoch": 0.04385458742065782,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 8.0316,
|
|
"mean_token_accuracy": 0.10789357051253319,
|
|
"num_tokens": 954005.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 8.355004215240479,
|
|
"epoch": 0.044431621465666475,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 8.026,
|
|
"mean_token_accuracy": 0.1113132230937481,
|
|
"num_tokens": 966725.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 8.353032684326172,
|
|
"epoch": 0.04500865551067513,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 8.0044,
|
|
"mean_token_accuracy": 0.1139283761382103,
|
|
"num_tokens": 978021.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 8.344230270385742,
|
|
"epoch": 0.04558568955568378,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.9905,
|
|
"mean_token_accuracy": 0.11658623144030571,
|
|
"num_tokens": 991321.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 8.339315605163574,
|
|
"epoch": 0.04616272360069244,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.9818,
|
|
"mean_token_accuracy": 0.11692097708582878,
|
|
"num_tokens": 1004172.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 8.253484535217286,
|
|
"epoch": 0.0467397576457011,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.936,
|
|
"mean_token_accuracy": 0.11915154382586479,
|
|
"num_tokens": 1016513.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 8.23137845993042,
|
|
"epoch": 0.04731679169070975,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.9323,
|
|
"mean_token_accuracy": 0.11277970448136329,
|
|
"num_tokens": 1028536.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 8.298001146316528,
|
|
"epoch": 0.04789382573571841,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.8757,
|
|
"mean_token_accuracy": 0.12688373401761055,
|
|
"num_tokens": 1040534.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 8.242660903930664,
|
|
"epoch": 0.048470859780727064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.9649,
|
|
"mean_token_accuracy": 0.11573690325021743,
|
|
"num_tokens": 1054995.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 8.27421875,
|
|
"epoch": 0.04904789382573572,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.9873,
|
|
"mean_token_accuracy": 0.11399574726819992,
|
|
"num_tokens": 1067722.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 8.373875331878661,
|
|
"epoch": 0.04962492787074437,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.9637,
|
|
"mean_token_accuracy": 0.10732617229223251,
|
|
"num_tokens": 1079788.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 8.326363945007325,
|
|
"epoch": 0.05020196191575303,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.9539,
|
|
"mean_token_accuracy": 0.1163248635828495,
|
|
"num_tokens": 1092016.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 8.17879877090454,
|
|
"epoch": 0.050778995960761686,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.9654,
|
|
"mean_token_accuracy": 0.11178191602230073,
|
|
"num_tokens": 1104522.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 8.363206481933593,
|
|
"epoch": 0.05135603000577034,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.979,
|
|
"mean_token_accuracy": 0.12337485775351524,
|
|
"num_tokens": 1117239.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 8.268813133239746,
|
|
"epoch": 0.05193306405077899,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.9035,
|
|
"mean_token_accuracy": 0.11866443902254105,
|
|
"num_tokens": 1129061.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 8.266489696502685,
|
|
"epoch": 0.052510098095787654,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.8976,
|
|
"mean_token_accuracy": 0.11053306236863136,
|
|
"num_tokens": 1141409.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 8.20300588607788,
|
|
"epoch": 0.05308713214079631,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.9036,
|
|
"mean_token_accuracy": 0.11711592748761177,
|
|
"num_tokens": 1153623.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 8.255742359161378,
|
|
"epoch": 0.05366416618580496,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.9518,
|
|
"mean_token_accuracy": 0.11555556952953339,
|
|
"num_tokens": 1166877.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 8.26829776763916,
|
|
"epoch": 0.054241200230813615,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.9228,
|
|
"mean_token_accuracy": 0.11642130017280579,
|
|
"num_tokens": 1179625.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 8.19015064239502,
|
|
"epoch": 0.054818234275822275,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.9401,
|
|
"mean_token_accuracy": 0.11644659489393235,
|
|
"num_tokens": 1193586.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 8.207570362091065,
|
|
"epoch": 0.05539526832083093,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.8841,
|
|
"mean_token_accuracy": 0.12152690812945366,
|
|
"num_tokens": 1207086.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 8.263338947296143,
|
|
"epoch": 0.05597230236583958,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.8895,
|
|
"mean_token_accuracy": 0.11943561136722565,
|
|
"num_tokens": 1219389.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 8.21270751953125,
|
|
"epoch": 0.05654933641084824,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.825,
|
|
"mean_token_accuracy": 0.12387257441878319,
|
|
"num_tokens": 1232080.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 8.094493389129639,
|
|
"epoch": 0.0571263704558569,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000247,
|
|
"loss": 7.874,
|
|
"mean_token_accuracy": 0.12492263168096543,
|
|
"num_tokens": 1246775.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 8.204738426208497,
|
|
"epoch": 0.05770340450086555,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 7.9068,
|
|
"mean_token_accuracy": 0.114556435495615,
|
|
"num_tokens": 1258839.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 8.169677925109863,
|
|
"epoch": 0.058280438545874204,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 7.8279,
|
|
"mean_token_accuracy": 0.12553127557039262,
|
|
"num_tokens": 1270710.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 8.218509674072266,
|
|
"epoch": 0.058857472590882864,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.786,
|
|
"mean_token_accuracy": 0.12104848474264145,
|
|
"num_tokens": 1281930.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 8.104724454879761,
|
|
"epoch": 0.05943450663589152,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.8534,
|
|
"mean_token_accuracy": 0.11715041622519493,
|
|
"num_tokens": 1294548.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 8.166370916366578,
|
|
"epoch": 0.06001154068090017,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 7.8064,
|
|
"mean_token_accuracy": 0.11803867742419243,
|
|
"num_tokens": 1307588.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 8.132765865325927,
|
|
"epoch": 0.060588574725908825,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.7863,
|
|
"mean_token_accuracy": 0.12690332680940627,
|
|
"num_tokens": 1319478.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 8.216028451919556,
|
|
"epoch": 0.061165608770917486,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.8708,
|
|
"mean_token_accuracy": 0.11611150279641151,
|
|
"num_tokens": 1332950.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 8.090120029449462,
|
|
"epoch": 0.06174264281592614,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.7615,
|
|
"mean_token_accuracy": 0.12739897295832633,
|
|
"num_tokens": 1345510.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 8.01339612007141,
|
|
"epoch": 0.06231967686093479,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.8042,
|
|
"mean_token_accuracy": 0.12997828647494317,
|
|
"num_tokens": 1359388.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 8.145500087738037,
|
|
"epoch": 0.06289671090594345,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.8149,
|
|
"mean_token_accuracy": 0.12175369709730148,
|
|
"num_tokens": 1373067.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 8.04567756652832,
|
|
"epoch": 0.06347374495095211,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 7.7835,
|
|
"mean_token_accuracy": 0.12414814531803131,
|
|
"num_tokens": 1385718.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 8.235342979431152,
|
|
"epoch": 0.06405077899596076,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000277,
|
|
"loss": 7.7898,
|
|
"mean_token_accuracy": 0.12540573999285698,
|
|
"num_tokens": 1398788.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 8.071519756317139,
|
|
"epoch": 0.06462781304096941,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 7.7882,
|
|
"mean_token_accuracy": 0.12845603749155998,
|
|
"num_tokens": 1411752.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 8.075310802459716,
|
|
"epoch": 0.06520484708597807,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.8443,
|
|
"mean_token_accuracy": 0.12352012917399406,
|
|
"num_tokens": 1423979.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 8.11637830734253,
|
|
"epoch": 0.06578188113098672,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 7.8721,
|
|
"mean_token_accuracy": 0.11852672100067138,
|
|
"num_tokens": 1437009.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 8.124029541015625,
|
|
"epoch": 0.06635891517599539,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000287,
|
|
"loss": 7.7174,
|
|
"mean_token_accuracy": 0.12357776835560799,
|
|
"num_tokens": 1448220.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 8.00622100830078,
|
|
"epoch": 0.06693594922100404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.7566,
|
|
"mean_token_accuracy": 0.12290028035640717,
|
|
"num_tokens": 1460024.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 8.137111854553222,
|
|
"epoch": 0.0675129832660127,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 7.7451,
|
|
"mean_token_accuracy": 0.1224621057510376,
|
|
"num_tokens": 1472283.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 8.003714799880981,
|
|
"epoch": 0.06809001731102135,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 7.7908,
|
|
"mean_token_accuracy": 0.12675876170396805,
|
|
"num_tokens": 1486565.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.9941528797149655,
|
|
"epoch": 0.06866705135603,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 7.7704,
|
|
"mean_token_accuracy": 0.1255685530602932,
|
|
"num_tokens": 1498708.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 8.076406526565552,
|
|
"epoch": 0.06924408540103866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 7.7121,
|
|
"mean_token_accuracy": 0.1268436163663864,
|
|
"num_tokens": 1511318.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.977707815170288,
|
|
"epoch": 0.06982111944604731,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 7.695,
|
|
"mean_token_accuracy": 0.13601174131035804,
|
|
"num_tokens": 1525415.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 8.098061847686768,
|
|
"epoch": 0.07039815349105598,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 7.7433,
|
|
"mean_token_accuracy": 0.12430487498641014,
|
|
"num_tokens": 1538757.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.966400146484375,
|
|
"epoch": 0.07097518753606463,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000307,
|
|
"loss": 7.6977,
|
|
"mean_token_accuracy": 0.12538538724184037,
|
|
"num_tokens": 1550619.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 8.005772590637207,
|
|
"epoch": 0.07155222158107329,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 7.7496,
|
|
"mean_token_accuracy": 0.12077321037650109,
|
|
"num_tokens": 1562588.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.989212322235107,
|
|
"epoch": 0.07212925562608194,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000312,
|
|
"loss": 7.6787,
|
|
"mean_token_accuracy": 0.12967532649636268,
|
|
"num_tokens": 1574892.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 7.974766254425049,
|
|
"epoch": 0.0727062896710906,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 7.7117,
|
|
"mean_token_accuracy": 0.12752822190523147,
|
|
"num_tokens": 1587525.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 8.038787698745727,
|
|
"epoch": 0.07328332371609925,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000317,
|
|
"loss": 7.6921,
|
|
"mean_token_accuracy": 0.12393600195646286,
|
|
"num_tokens": 1600350.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.9325361251831055,
|
|
"epoch": 0.0738603577611079,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.6823,
|
|
"mean_token_accuracy": 0.12833620086312295,
|
|
"num_tokens": 1613318.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 8.086976289749146,
|
|
"epoch": 0.07443739180611655,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 7.8105,
|
|
"mean_token_accuracy": 0.12034560292959214,
|
|
"num_tokens": 1626757.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.982501125335693,
|
|
"epoch": 0.07501442585112522,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 7.6224,
|
|
"mean_token_accuracy": 0.13317669555544853,
|
|
"num_tokens": 1639185.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.921093416213989,
|
|
"epoch": 0.07559145989613388,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 7.727,
|
|
"mean_token_accuracy": 0.12360085397958756,
|
|
"num_tokens": 1652009.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.985281324386596,
|
|
"epoch": 0.07616849394114253,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 7.7099,
|
|
"mean_token_accuracy": 0.12278636991977691,
|
|
"num_tokens": 1665604.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.997657918930054,
|
|
"epoch": 0.07674552798615118,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 7.6893,
|
|
"mean_token_accuracy": 0.12272793427109718,
|
|
"num_tokens": 1679036.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.8749652862548825,
|
|
"epoch": 0.07732256203115984,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 7.664,
|
|
"mean_token_accuracy": 0.13161094784736632,
|
|
"num_tokens": 1691512.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 8.132879447937011,
|
|
"epoch": 0.07789959607616849,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 7.7292,
|
|
"mean_token_accuracy": 0.12437204793095588,
|
|
"num_tokens": 1704589.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 7.819326114654541,
|
|
"epoch": 0.07847663012117714,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 7.7067,
|
|
"mean_token_accuracy": 0.12104201540350915,
|
|
"num_tokens": 1718612.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 7.861719846725464,
|
|
"epoch": 0.07905366416618581,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 7.6127,
|
|
"mean_token_accuracy": 0.12460441142320633,
|
|
"num_tokens": 1730472.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 8.00782494544983,
|
|
"epoch": 0.07963069821119446,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 7.7467,
|
|
"mean_token_accuracy": 0.12077393978834153,
|
|
"num_tokens": 1742535.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 8.006076240539551,
|
|
"epoch": 0.08020773225620312,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 7.7141,
|
|
"mean_token_accuracy": 0.12221984565258026,
|
|
"num_tokens": 1753877.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 7.926956653594971,
|
|
"epoch": 0.08078476630121177,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 7.6293,
|
|
"mean_token_accuracy": 0.12848915457725524,
|
|
"num_tokens": 1766413.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 7.813401508331299,
|
|
"epoch": 0.08136180034622043,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000352,
|
|
"loss": 7.4754,
|
|
"mean_token_accuracy": 0.13737191781401634,
|
|
"num_tokens": 1779719.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 7.915401935577393,
|
|
"epoch": 0.08193883439122908,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 7.6389,
|
|
"mean_token_accuracy": 0.13027774319052696,
|
|
"num_tokens": 1791448.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 7.866633939743042,
|
|
"epoch": 0.08251586843623773,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 7.6429,
|
|
"mean_token_accuracy": 0.12651973143219947,
|
|
"num_tokens": 1803802.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 7.941481637954712,
|
|
"epoch": 0.0830929024812464,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 7.6641,
|
|
"mean_token_accuracy": 0.12703499272465707,
|
|
"num_tokens": 1817545.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 7.91947979927063,
|
|
"epoch": 0.08366993652625505,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 7.6464,
|
|
"mean_token_accuracy": 0.12531809359788895,
|
|
"num_tokens": 1830115.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 7.799381828308105,
|
|
"epoch": 0.08424697057126371,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 7.5711,
|
|
"mean_token_accuracy": 0.12959943637251853,
|
|
"num_tokens": 1844707.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.925750207901001,
|
|
"epoch": 0.08482400461627236,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000367,
|
|
"loss": 7.6557,
|
|
"mean_token_accuracy": 0.12370599582791328,
|
|
"num_tokens": 1858719.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 7.862723875045776,
|
|
"epoch": 0.08540103866128101,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 7.5893,
|
|
"mean_token_accuracy": 0.12989407479763032,
|
|
"num_tokens": 1870421.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 7.863739395141602,
|
|
"epoch": 0.08597807270628967,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000372,
|
|
"loss": 7.6572,
|
|
"mean_token_accuracy": 0.1180440478026867,
|
|
"num_tokens": 1883792.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 7.822341585159302,
|
|
"epoch": 0.08655510675129832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 7.6349,
|
|
"mean_token_accuracy": 0.12786092832684517,
|
|
"num_tokens": 1896209.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 7.870438051223755,
|
|
"epoch": 0.08713214079630698,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 7.5787,
|
|
"mean_token_accuracy": 0.1304923750460148,
|
|
"num_tokens": 1908520.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.85968918800354,
|
|
"epoch": 0.08770917484131564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 7.5898,
|
|
"mean_token_accuracy": 0.12856273204088212,
|
|
"num_tokens": 1922489.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 7.790146064758301,
|
|
"epoch": 0.0882862088863243,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 7.5841,
|
|
"mean_token_accuracy": 0.1291157804429531,
|
|
"num_tokens": 1935206.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 7.834140348434448,
|
|
"epoch": 0.08886324293133295,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 7.5396,
|
|
"mean_token_accuracy": 0.13339237496256828,
|
|
"num_tokens": 1948798.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 7.79986310005188,
|
|
"epoch": 0.0894402769763416,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 7.537,
|
|
"mean_token_accuracy": 0.13368105366826058,
|
|
"num_tokens": 1961095.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 7.886825084686279,
|
|
"epoch": 0.09001731102135026,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 7.5479,
|
|
"mean_token_accuracy": 0.12701786160469056,
|
|
"num_tokens": 1974229.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 7.805331611633301,
|
|
"epoch": 0.09059434506635891,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 7.6401,
|
|
"mean_token_accuracy": 0.12609824389219285,
|
|
"num_tokens": 1986334.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 7.807611322402954,
|
|
"epoch": 0.09117137911136756,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 7.5884,
|
|
"mean_token_accuracy": 0.12830588668584825,
|
|
"num_tokens": 2000337.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 7.795743417739868,
|
|
"epoch": 0.09174841315637623,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 7.51,
|
|
"mean_token_accuracy": 0.13368136137723924,
|
|
"num_tokens": 2012048.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 7.784616470336914,
|
|
"epoch": 0.09232544720138489,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 7.529,
|
|
"mean_token_accuracy": 0.13036411479115487,
|
|
"num_tokens": 2025244.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 7.810312700271607,
|
|
"epoch": 0.09290248124639354,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 7.5725,
|
|
"mean_token_accuracy": 0.13225525096058846,
|
|
"num_tokens": 2036542.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 7.813270044326782,
|
|
"epoch": 0.0934795152914022,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 7.5115,
|
|
"mean_token_accuracy": 0.13005766347050668,
|
|
"num_tokens": 2049358.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 7.700181245803833,
|
|
"epoch": 0.09405654933641085,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 7.5409,
|
|
"mean_token_accuracy": 0.12904200404882432,
|
|
"num_tokens": 2062114.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 7.861858272552491,
|
|
"epoch": 0.0946335833814195,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 7.5139,
|
|
"mean_token_accuracy": 0.13364754766225814,
|
|
"num_tokens": 2074236.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 7.705525732040405,
|
|
"epoch": 0.09521061742642815,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000412,
|
|
"loss": 7.4266,
|
|
"mean_token_accuracy": 0.13591486886143683,
|
|
"num_tokens": 2086320.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 7.766620826721192,
|
|
"epoch": 0.09578765147143682,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 7.4885,
|
|
"mean_token_accuracy": 0.13510627821087837,
|
|
"num_tokens": 2099119.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 7.711123943328857,
|
|
"epoch": 0.09636468551644548,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 7.5148,
|
|
"mean_token_accuracy": 0.1323984071612358,
|
|
"num_tokens": 2111795.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 7.660836982727051,
|
|
"epoch": 0.09694171956145413,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 7.4957,
|
|
"mean_token_accuracy": 0.11923368275165558,
|
|
"num_tokens": 2126621.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 7.764021539688111,
|
|
"epoch": 0.09751875360646278,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 7.3964,
|
|
"mean_token_accuracy": 0.1446671850979328,
|
|
"num_tokens": 2139770.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 7.73313717842102,
|
|
"epoch": 0.09809578765147144,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 7.4817,
|
|
"mean_token_accuracy": 0.13560690730810165,
|
|
"num_tokens": 2151683.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 7.648449945449829,
|
|
"epoch": 0.09867282169648009,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 7.4604,
|
|
"mean_token_accuracy": 0.1294977843761444,
|
|
"num_tokens": 2163178.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 7.755085849761963,
|
|
"epoch": 0.09924985574148874,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 7.5485,
|
|
"mean_token_accuracy": 0.12189057022333145,
|
|
"num_tokens": 2176312.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 7.789842224121093,
|
|
"epoch": 0.0998268897864974,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 7.48,
|
|
"mean_token_accuracy": 0.12981949299573897,
|
|
"num_tokens": 2189045.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 7.571734762191772,
|
|
"epoch": 0.10040392383150606,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 7.4754,
|
|
"mean_token_accuracy": 0.12462260350584983,
|
|
"num_tokens": 2202083.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 7.715145778656006,
|
|
"epoch": 0.10098095787651472,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 7.5248,
|
|
"mean_token_accuracy": 0.1264673389494419,
|
|
"num_tokens": 2215775.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 7.77250919342041,
|
|
"epoch": 0.10155799192152337,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 7.4774,
|
|
"mean_token_accuracy": 0.12318376153707504,
|
|
"num_tokens": 2228387.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 7.6760975360870365,
|
|
"epoch": 0.10213502596653203,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 7.4827,
|
|
"mean_token_accuracy": 0.13410628139972686,
|
|
"num_tokens": 2241491.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 7.5755048274993895,
|
|
"epoch": 0.10271206001154068,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 7.4057,
|
|
"mean_token_accuracy": 0.13969002217054366,
|
|
"num_tokens": 2255282.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 7.67344913482666,
|
|
"epoch": 0.10328909405654933,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 7.4078,
|
|
"mean_token_accuracy": 0.13210881277918815,
|
|
"num_tokens": 2268081.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 7.641108894348145,
|
|
"epoch": 0.10386612810155799,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 7.3767,
|
|
"mean_token_accuracy": 0.1385306254029274,
|
|
"num_tokens": 2281069.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 7.662174987792969,
|
|
"epoch": 0.10444316214656665,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 7.4474,
|
|
"mean_token_accuracy": 0.12799655497074128,
|
|
"num_tokens": 2293606.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 7.689595937728882,
|
|
"epoch": 0.10502019619157531,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 7.4478,
|
|
"mean_token_accuracy": 0.12830137014389037,
|
|
"num_tokens": 2304973.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 7.686489248275757,
|
|
"epoch": 0.10559723023658396,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 7.4863,
|
|
"mean_token_accuracy": 0.12266820147633553,
|
|
"num_tokens": 2319016.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 7.6014503002166744,
|
|
"epoch": 0.10617426428159261,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 7.4463,
|
|
"mean_token_accuracy": 0.1375369183719158,
|
|
"num_tokens": 2330599.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 7.717125272750854,
|
|
"epoch": 0.10675129832660127,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 7.4444,
|
|
"mean_token_accuracy": 0.12856984063982962,
|
|
"num_tokens": 2343153.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 7.697896146774292,
|
|
"epoch": 0.10732833237160992,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 7.4695,
|
|
"mean_token_accuracy": 0.12443050369620323,
|
|
"num_tokens": 2356762.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 7.53573899269104,
|
|
"epoch": 0.10790536641661858,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 7.4916,
|
|
"mean_token_accuracy": 0.13005805611610413,
|
|
"num_tokens": 2369581.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 7.7132821559906,
|
|
"epoch": 0.10848240046162723,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 7.4025,
|
|
"mean_token_accuracy": 0.1298571690917015,
|
|
"num_tokens": 2381419.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 7.599806404113769,
|
|
"epoch": 0.1090594345066359,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000472,
|
|
"loss": 7.404,
|
|
"mean_token_accuracy": 0.1387295603752136,
|
|
"num_tokens": 2393586.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 7.5154454708099365,
|
|
"epoch": 0.10963646855164455,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 7.3841,
|
|
"mean_token_accuracy": 0.13711024671792985,
|
|
"num_tokens": 2407720.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 7.691217041015625,
|
|
"epoch": 0.1102135025966532,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 7.4341,
|
|
"mean_token_accuracy": 0.12648762315511702,
|
|
"num_tokens": 2421089.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 7.593528985977173,
|
|
"epoch": 0.11079053664166186,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 7.3719,
|
|
"mean_token_accuracy": 0.13786724731326103,
|
|
"num_tokens": 2432859.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 7.563003826141357,
|
|
"epoch": 0.11136757068667051,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 7.3823,
|
|
"mean_token_accuracy": 0.1313467375934124,
|
|
"num_tokens": 2445072.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 7.626921939849853,
|
|
"epoch": 0.11194460473167916,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 7.3802,
|
|
"mean_token_accuracy": 0.13656689301133157,
|
|
"num_tokens": 2458724.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 7.551381254196167,
|
|
"epoch": 0.11252163877668782,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000487,
|
|
"loss": 7.4385,
|
|
"mean_token_accuracy": 0.13167190551757812,
|
|
"num_tokens": 2472976.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 7.675592613220215,
|
|
"epoch": 0.11309867282169649,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 7.4166,
|
|
"mean_token_accuracy": 0.12921208068728446,
|
|
"num_tokens": 2486164.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 7.476428079605102,
|
|
"epoch": 0.11367570686670514,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000492,
|
|
"loss": 7.3646,
|
|
"mean_token_accuracy": 0.13289769142866134,
|
|
"num_tokens": 2499395.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 7.640331506729126,
|
|
"epoch": 0.1142527409117138,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 7.3659,
|
|
"mean_token_accuracy": 0.13304105922579765,
|
|
"num_tokens": 2512163.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 7.560707950592041,
|
|
"epoch": 0.11482977495672245,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 7.3714,
|
|
"mean_token_accuracy": 0.12891542091965674,
|
|
"num_tokens": 2523634.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 7.603393411636352,
|
|
"epoch": 0.1154068090017311,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 7.4008,
|
|
"mean_token_accuracy": 0.1331055149435997,
|
|
"num_tokens": 2536237.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 7.625240325927734,
|
|
"epoch": 0.11598384304673975,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999999975783157,
|
|
"loss": 7.3994,
|
|
"mean_token_accuracy": 0.11986244916915893,
|
|
"num_tokens": 2548035.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 7.594330739974976,
|
|
"epoch": 0.11656087709174841,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999999877402236,
|
|
"loss": 7.3344,
|
|
"mean_token_accuracy": 0.13319490626454353,
|
|
"num_tokens": 2561670.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 7.533303833007812,
|
|
"epoch": 0.11713791113675708,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999999703343686,
|
|
"loss": 7.3709,
|
|
"mean_token_accuracy": 0.1304928630590439,
|
|
"num_tokens": 2573471.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 7.531730508804321,
|
|
"epoch": 0.11771494518176573,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999999453607515,
|
|
"loss": 7.3175,
|
|
"mean_token_accuracy": 0.13719066530466079,
|
|
"num_tokens": 2586534.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 7.636745643615723,
|
|
"epoch": 0.11829197922677438,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999999128193729,
|
|
"loss": 7.3719,
|
|
"mean_token_accuracy": 0.12794509902596474,
|
|
"num_tokens": 2597970.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 7.373585796356201,
|
|
"epoch": 0.11886901327178304,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499999872710234,
|
|
"loss": 7.308,
|
|
"mean_token_accuracy": 0.13802397325634957,
|
|
"num_tokens": 2610924.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 7.593305397033691,
|
|
"epoch": 0.11944604731679169,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999998250333361,
|
|
"loss": 7.3737,
|
|
"mean_token_accuracy": 0.13383316844701768,
|
|
"num_tokens": 2623571.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 7.540350818634034,
|
|
"epoch": 0.12002308136180034,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499999769788681,
|
|
"loss": 7.3823,
|
|
"mean_token_accuracy": 0.1317036457359791,
|
|
"num_tokens": 2636063.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 7.56674108505249,
|
|
"epoch": 0.120600115406809,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999997069762703,
|
|
"loss": 7.3334,
|
|
"mean_token_accuracy": 0.1320666678249836,
|
|
"num_tokens": 2648621.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 7.478792190551758,
|
|
"epoch": 0.12117714945181765,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999996365961062,
|
|
"loss": 7.2548,
|
|
"mean_token_accuracy": 0.13802519217133521,
|
|
"num_tokens": 2661794.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 7.471138048171997,
|
|
"epoch": 0.12175418349682632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999995586481912,
|
|
"loss": 7.3311,
|
|
"mean_token_accuracy": 0.1260454349219799,
|
|
"num_tokens": 2674048.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 7.464170122146607,
|
|
"epoch": 0.12233121754183497,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999994731325276,
|
|
"loss": 7.2485,
|
|
"mean_token_accuracy": 0.13324502855539322,
|
|
"num_tokens": 2685510.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 7.5221740245819095,
|
|
"epoch": 0.12290825158684363,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999993800491187,
|
|
"loss": 7.3328,
|
|
"mean_token_accuracy": 0.13226443603634835,
|
|
"num_tokens": 2698414.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 7.50278525352478,
|
|
"epoch": 0.12348528563185228,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999992793979672,
|
|
"loss": 7.3332,
|
|
"mean_token_accuracy": 0.1338995724916458,
|
|
"num_tokens": 2711343.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 7.443923377990723,
|
|
"epoch": 0.12406231967686093,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999991711790769,
|
|
"loss": 7.2217,
|
|
"mean_token_accuracy": 0.14058572947978973,
|
|
"num_tokens": 2723123.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 7.387674856185913,
|
|
"epoch": 0.12463935372186959,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999990553924511,
|
|
"loss": 7.2621,
|
|
"mean_token_accuracy": 0.13784897848963737,
|
|
"num_tokens": 2736015.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 7.483056497573853,
|
|
"epoch": 0.12521638776687824,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999989320380939,
|
|
"loss": 7.2327,
|
|
"mean_token_accuracy": 0.1457214944064617,
|
|
"num_tokens": 2747561.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 7.438428640365601,
|
|
"epoch": 0.1257934218118869,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999988011160094,
|
|
"loss": 7.2835,
|
|
"mean_token_accuracy": 0.13277626112103463,
|
|
"num_tokens": 2758992.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 7.489367580413818,
|
|
"epoch": 0.12637045585689555,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499998662626202,
|
|
"loss": 7.2773,
|
|
"mean_token_accuracy": 0.13354492634534837,
|
|
"num_tokens": 2771164.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 7.357281446456909,
|
|
"epoch": 0.12694748990190421,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999985165686764,
|
|
"loss": 7.2575,
|
|
"mean_token_accuracy": 0.1360307179391384,
|
|
"num_tokens": 2784400.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 7.427149534225464,
|
|
"epoch": 0.12752452394691285,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999983629434373,
|
|
"loss": 7.223,
|
|
"mean_token_accuracy": 0.13857290968298913,
|
|
"num_tokens": 2795729.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 7.424337244033813,
|
|
"epoch": 0.12810155799192152,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999982017504901,
|
|
"loss": 7.307,
|
|
"mean_token_accuracy": 0.13230945765972138,
|
|
"num_tokens": 2808118.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 7.445949077606201,
|
|
"epoch": 0.1286785920369302,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999980329898401,
|
|
"loss": 7.236,
|
|
"mean_token_accuracy": 0.1337020590901375,
|
|
"num_tokens": 2821118.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 7.446945095062256,
|
|
"epoch": 0.12925562608193883,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000499997856661493,
|
|
"loss": 7.233,
|
|
"mean_token_accuracy": 0.13448369577527047,
|
|
"num_tokens": 2833636.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 7.35188136100769,
|
|
"epoch": 0.1298326601269475,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499997672765455,
|
|
"loss": 7.2509,
|
|
"mean_token_accuracy": 0.1398313045501709,
|
|
"num_tokens": 2846617.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 7.367458200454712,
|
|
"epoch": 0.13040969417195614,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999974813017318,
|
|
"loss": 7.2097,
|
|
"mean_token_accuracy": 0.14283193722367288,
|
|
"num_tokens": 2859191.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 7.45753436088562,
|
|
"epoch": 0.1309867282169648,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999972822703301,
|
|
"loss": 7.2303,
|
|
"mean_token_accuracy": 0.13343884348869323,
|
|
"num_tokens": 2872592.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 7.310500621795654,
|
|
"epoch": 0.13156376226197344,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999970756712567,
|
|
"loss": 7.2068,
|
|
"mean_token_accuracy": 0.14036742150783538,
|
|
"num_tokens": 2884094.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 7.466288280487061,
|
|
"epoch": 0.1321407963069821,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999968615045183,
|
|
"loss": 7.265,
|
|
"mean_token_accuracy": 0.1353508099913597,
|
|
"num_tokens": 2896947.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 7.352451229095459,
|
|
"epoch": 0.13271783035199078,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999966397701222,
|
|
"loss": 7.2677,
|
|
"mean_token_accuracy": 0.13296897783875467,
|
|
"num_tokens": 2909029.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 7.461985635757446,
|
|
"epoch": 0.13329486439699942,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999964104680759,
|
|
"loss": 7.2432,
|
|
"mean_token_accuracy": 0.13714048266410828,
|
|
"num_tokens": 2920778.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 7.354297304153443,
|
|
"epoch": 0.13387189844200809,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999961735983871,
|
|
"loss": 7.1539,
|
|
"mean_token_accuracy": 0.14073749631643295,
|
|
"num_tokens": 2933754.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 7.476262760162354,
|
|
"epoch": 0.13444893248701673,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999959291610639,
|
|
"loss": 7.2608,
|
|
"mean_token_accuracy": 0.13915467262268066,
|
|
"num_tokens": 2946019.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 7.351610231399536,
|
|
"epoch": 0.1350259665320254,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999956771561143,
|
|
"loss": 7.2192,
|
|
"mean_token_accuracy": 0.13505645617842674,
|
|
"num_tokens": 2959688.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 7.36425518989563,
|
|
"epoch": 0.13560300057703403,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999954175835469,
|
|
"loss": 7.1361,
|
|
"mean_token_accuracy": 0.14523073583841323,
|
|
"num_tokens": 2971211.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 7.323524904251099,
|
|
"epoch": 0.1361800346220427,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999951504433703,
|
|
"loss": 7.2293,
|
|
"mean_token_accuracy": 0.13175321519374847,
|
|
"num_tokens": 2983559.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 7.404617214202881,
|
|
"epoch": 0.13675706866705137,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999948757355935,
|
|
"loss": 7.2025,
|
|
"mean_token_accuracy": 0.1324743650853634,
|
|
"num_tokens": 2995053.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 7.352153348922729,
|
|
"epoch": 0.13733410271206,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499994593460226,
|
|
"loss": 7.1457,
|
|
"mean_token_accuracy": 0.13915842920541763,
|
|
"num_tokens": 3006143.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 7.277075576782226,
|
|
"epoch": 0.13791113675706868,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999943036172771,
|
|
"loss": 7.147,
|
|
"mean_token_accuracy": 0.14147392511367798,
|
|
"num_tokens": 3018793.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 7.392578411102295,
|
|
"epoch": 0.13848817080207732,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004999940062067565,
|
|
"loss": 7.1464,
|
|
"mean_token_accuracy": 0.13925720006227493,
|
|
"num_tokens": 3031547.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 7.269504356384277,
|
|
"epoch": 0.13906520484708598,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999937012286742,
|
|
"loss": 7.1604,
|
|
"mean_token_accuracy": 0.13719142302870752,
|
|
"num_tokens": 3044035.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 7.297099208831787,
|
|
"epoch": 0.13964223889209462,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999933886830405,
|
|
"loss": 7.1862,
|
|
"mean_token_accuracy": 0.14078905582427978,
|
|
"num_tokens": 3056238.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 7.321411800384522,
|
|
"epoch": 0.1402192729371033,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000499993068569866,
|
|
"loss": 7.1833,
|
|
"mean_token_accuracy": 0.14090409278869628,
|
|
"num_tokens": 3069250.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 7.357383728027344,
|
|
"epoch": 0.14079630698211196,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999927408891614,
|
|
"loss": 7.1557,
|
|
"mean_token_accuracy": 0.13715188950300217,
|
|
"num_tokens": 3082048.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 7.301809167861938,
|
|
"epoch": 0.1413733410271206,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999924056409378,
|
|
"loss": 7.2215,
|
|
"mean_token_accuracy": 0.13659722208976746,
|
|
"num_tokens": 3094588.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 7.427079439163208,
|
|
"epoch": 0.14195037507212926,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999920628252063,
|
|
"loss": 7.2441,
|
|
"mean_token_accuracy": 0.128413824737072,
|
|
"num_tokens": 3108067.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 7.301552772521973,
|
|
"epoch": 0.1425274091171379,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999917124419785,
|
|
"loss": 7.1715,
|
|
"mean_token_accuracy": 0.1430498704314232,
|
|
"num_tokens": 3120524.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 7.375691175460815,
|
|
"epoch": 0.14310444316214657,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999913544912664,
|
|
"loss": 7.2377,
|
|
"mean_token_accuracy": 0.13174993246793748,
|
|
"num_tokens": 3133533.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 7.397565317153931,
|
|
"epoch": 0.1436814772071552,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999909889730817,
|
|
"loss": 7.2182,
|
|
"mean_token_accuracy": 0.137331123650074,
|
|
"num_tokens": 3146183.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 7.296873569488525,
|
|
"epoch": 0.14425851125216388,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999906158874368,
|
|
"loss": 7.1694,
|
|
"mean_token_accuracy": 0.13684176057577133,
|
|
"num_tokens": 3158436.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 7.299059915542602,
|
|
"epoch": 0.14483554529717255,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999902352343444,
|
|
"loss": 7.1194,
|
|
"mean_token_accuracy": 0.1443310186266899,
|
|
"num_tokens": 3170426.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 7.344976425170898,
|
|
"epoch": 0.1454125793421812,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999898470138171,
|
|
"loss": 7.1264,
|
|
"mean_token_accuracy": 0.13932598382234573,
|
|
"num_tokens": 3182865.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 7.26788363456726,
|
|
"epoch": 0.14598961338718985,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999894512258681,
|
|
"loss": 7.1381,
|
|
"mean_token_accuracy": 0.13955464959144592,
|
|
"num_tokens": 3195674.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 7.33721137046814,
|
|
"epoch": 0.1465666474321985,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999890478705107,
|
|
"loss": 7.114,
|
|
"mean_token_accuracy": 0.14049444273114203,
|
|
"num_tokens": 3208848.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 7.3063184261322025,
|
|
"epoch": 0.14714368147720716,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999886369477585,
|
|
"loss": 7.2017,
|
|
"mean_token_accuracy": 0.1356468491256237,
|
|
"num_tokens": 3221179.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 7.336249351501465,
|
|
"epoch": 0.1477207155222158,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999882184576251,
|
|
"loss": 7.2815,
|
|
"mean_token_accuracy": 0.13257396966218948,
|
|
"num_tokens": 3233671.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 7.405120134353638,
|
|
"epoch": 0.14829774956722447,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999877924001248,
|
|
"loss": 7.1979,
|
|
"mean_token_accuracy": 0.13243449851870537,
|
|
"num_tokens": 3247219.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 7.313788509368896,
|
|
"epoch": 0.1488747836122331,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999873587752718,
|
|
"loss": 7.1673,
|
|
"mean_token_accuracy": 0.13630512207746506,
|
|
"num_tokens": 3259444.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 7.180786943435669,
|
|
"epoch": 0.14945181765724178,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004999869175830808,
|
|
"loss": 7.019,
|
|
"mean_token_accuracy": 0.14473430812358856,
|
|
"num_tokens": 3272092.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 7.377786588668823,
|
|
"epoch": 0.15002885170225044,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004999864688235666,
|
|
"loss": 7.1995,
|
|
"mean_token_accuracy": 0.12725819498300553,
|
|
"num_tokens": 3284260.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 7.249001407623291,
|
|
"epoch": 0.15060588574725908,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999860124967442,
|
|
"loss": 7.1613,
|
|
"mean_token_accuracy": 0.13158362433314325,
|
|
"num_tokens": 3296662.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 7.297910118103028,
|
|
"epoch": 0.15118291979226775,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999855486026291,
|
|
"loss": 7.1213,
|
|
"mean_token_accuracy": 0.14045775979757308,
|
|
"num_tokens": 3307782.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 7.283909845352173,
|
|
"epoch": 0.1517599538372764,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999850771412369,
|
|
"loss": 7.1728,
|
|
"mean_token_accuracy": 0.13270583972334862,
|
|
"num_tokens": 3320519.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 7.31526288986206,
|
|
"epoch": 0.15233698788228506,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999845981125832,
|
|
"loss": 7.0413,
|
|
"mean_token_accuracy": 0.14500000029802323,
|
|
"num_tokens": 3331722.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 7.212509202957153,
|
|
"epoch": 0.1529140219272937,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999841115166844,
|
|
"loss": 7.1385,
|
|
"mean_token_accuracy": 0.13171057179570198,
|
|
"num_tokens": 3345143.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 7.255769968032837,
|
|
"epoch": 0.15349105597230236,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999836173535568,
|
|
"loss": 7.0707,
|
|
"mean_token_accuracy": 0.14495590403676034,
|
|
"num_tokens": 3358946.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 7.313462114334106,
|
|
"epoch": 0.15406809001731103,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999831156232169,
|
|
"loss": 7.1788,
|
|
"mean_token_accuracy": 0.13734060302376747,
|
|
"num_tokens": 3372465.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 7.221960115432739,
|
|
"epoch": 0.15464512406231967,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999826063256818,
|
|
"loss": 7.0636,
|
|
"mean_token_accuracy": 0.1419673442840576,
|
|
"num_tokens": 3384392.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 7.322636604309082,
|
|
"epoch": 0.15522215810732834,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004999820894609683,
|
|
"loss": 7.1346,
|
|
"mean_token_accuracy": 0.12882967665791512,
|
|
"num_tokens": 3398137.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 7.281394720077515,
|
|
"epoch": 0.15579919215233698,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999815650290941,
|
|
"loss": 7.1003,
|
|
"mean_token_accuracy": 0.13911654129624368,
|
|
"num_tokens": 3410353.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 7.242393922805786,
|
|
"epoch": 0.15637622619734565,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999810330300766,
|
|
"loss": 7.0515,
|
|
"mean_token_accuracy": 0.13970422446727754,
|
|
"num_tokens": 3423206.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 7.206804037094116,
|
|
"epoch": 0.1569532602423543,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499980493463934,
|
|
"loss": 7.1134,
|
|
"mean_token_accuracy": 0.1346282660961151,
|
|
"num_tokens": 3436780.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 7.3222535133361815,
|
|
"epoch": 0.15753029428736295,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999799463306841,
|
|
"loss": 7.1791,
|
|
"mean_token_accuracy": 0.13330562338232993,
|
|
"num_tokens": 3450285.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 7.289401626586914,
|
|
"epoch": 0.15810732833237162,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999793916303455,
|
|
"loss": 7.0678,
|
|
"mean_token_accuracy": 0.14209839105606079,
|
|
"num_tokens": 3462157.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 7.195488595962525,
|
|
"epoch": 0.15868436237738026,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999788293629368,
|
|
"loss": 7.0299,
|
|
"mean_token_accuracy": 0.14806710481643676,
|
|
"num_tokens": 3475027.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 7.218692922592163,
|
|
"epoch": 0.15926139642238893,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.000499978259528477,
|
|
"loss": 7.1068,
|
|
"mean_token_accuracy": 0.14241924211382867,
|
|
"num_tokens": 3489111.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 7.240436649322509,
|
|
"epoch": 0.15983843046739757,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999776821269852,
|
|
"loss": 7.0521,
|
|
"mean_token_accuracy": 0.13724546879529953,
|
|
"num_tokens": 3501673.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 7.110876035690308,
|
|
"epoch": 0.16041546451240624,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999770971584807,
|
|
"loss": 6.9797,
|
|
"mean_token_accuracy": 0.1431804358959198,
|
|
"num_tokens": 3513511.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 7.26352219581604,
|
|
"epoch": 0.16099249855741488,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999765046229834,
|
|
"loss": 7.1193,
|
|
"mean_token_accuracy": 0.13453444615006446,
|
|
"num_tokens": 3525218.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 7.1966602325439455,
|
|
"epoch": 0.16156953260242354,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000499975904520513,
|
|
"loss": 6.9928,
|
|
"mean_token_accuracy": 0.1506774343550205,
|
|
"num_tokens": 3537006.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 7.221553230285645,
|
|
"epoch": 0.1621465666474322,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00049997529685109,
|
|
"loss": 7.1169,
|
|
"mean_token_accuracy": 0.13538158535957337,
|
|
"num_tokens": 3549873.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 7.317210006713867,
|
|
"epoch": 0.16272360069244085,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999746816147344,
|
|
"loss": 7.1801,
|
|
"mean_token_accuracy": 0.1276666961610317,
|
|
"num_tokens": 3563542.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 7.172958326339722,
|
|
"epoch": 0.16330063473744952,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999740588114673,
|
|
"loss": 7.0726,
|
|
"mean_token_accuracy": 0.13991388827562332,
|
|
"num_tokens": 3575679.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 7.290738105773926,
|
|
"epoch": 0.16387766878245816,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999734284413095,
|
|
"loss": 7.0954,
|
|
"mean_token_accuracy": 0.14116299375891686,
|
|
"num_tokens": 3588605.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 7.13003716468811,
|
|
"epoch": 0.16445470282746683,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499972790504282,
|
|
"loss": 7.0764,
|
|
"mean_token_accuracy": 0.1506669543683529,
|
|
"num_tokens": 3601894.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 7.193125915527344,
|
|
"epoch": 0.16503173687247547,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004999721450004067,
|
|
"loss": 7.0103,
|
|
"mean_token_accuracy": 0.14832852333784102,
|
|
"num_tokens": 3614436.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 7.113531923294067,
|
|
"epoch": 0.16560877091748413,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999714919297049,
|
|
"loss": 6.9698,
|
|
"mean_token_accuracy": 0.14278605505824088,
|
|
"num_tokens": 3627590.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 7.303047561645508,
|
|
"epoch": 0.1661858049624928,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999708312921987,
|
|
"loss": 7.1398,
|
|
"mean_token_accuracy": 0.1305020570755005,
|
|
"num_tokens": 3640834.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 7.112206935882568,
|
|
"epoch": 0.16676283900750144,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999701630879103,
|
|
"loss": 6.9822,
|
|
"mean_token_accuracy": 0.14259293228387832,
|
|
"num_tokens": 3653024.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 7.1947370052337645,
|
|
"epoch": 0.1673398730525101,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999694873168623,
|
|
"loss": 7.0366,
|
|
"mean_token_accuracy": 0.1446026474237442,
|
|
"num_tokens": 3665311.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 7.208151340484619,
|
|
"epoch": 0.16791690709751875,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999688039790773,
|
|
"loss": 7.0803,
|
|
"mean_token_accuracy": 0.1384113185107708,
|
|
"num_tokens": 3679102.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 7.164588069915771,
|
|
"epoch": 0.16849394114252741,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999681130745784,
|
|
"loss": 6.9906,
|
|
"mean_token_accuracy": 0.14679074734449388,
|
|
"num_tokens": 3690046.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 7.1119578838348385,
|
|
"epoch": 0.16907097518753605,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999674146033888,
|
|
"loss": 7.0146,
|
|
"mean_token_accuracy": 0.1386751838028431,
|
|
"num_tokens": 3703668.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 7.215666484832764,
|
|
"epoch": 0.16964800923254472,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999667085655318,
|
|
"loss": 7.0317,
|
|
"mean_token_accuracy": 0.142906092107296,
|
|
"num_tokens": 3715852.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 7.163801479339599,
|
|
"epoch": 0.1702250432775534,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999659949610313,
|
|
"loss": 6.9624,
|
|
"mean_token_accuracy": 0.1409413382411003,
|
|
"num_tokens": 3728310.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 7.225057554244995,
|
|
"epoch": 0.17080207732256203,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999652737899114,
|
|
"loss": 7.0428,
|
|
"mean_token_accuracy": 0.13530816361308098,
|
|
"num_tokens": 3741323.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 7.164874649047851,
|
|
"epoch": 0.1713791113675707,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999645450521963,
|
|
"loss": 7.0429,
|
|
"mean_token_accuracy": 0.13799375295639038,
|
|
"num_tokens": 3752667.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 7.169693231582642,
|
|
"epoch": 0.17195614541257934,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999638087479104,
|
|
"loss": 7.0422,
|
|
"mean_token_accuracy": 0.13898203894495964,
|
|
"num_tokens": 3764282.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 7.190469121932983,
|
|
"epoch": 0.172533179457588,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004999630648770786,
|
|
"loss": 7.0687,
|
|
"mean_token_accuracy": 0.13370918706059456,
|
|
"num_tokens": 3778280.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 7.144445991516113,
|
|
"epoch": 0.17311021350259664,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999623134397257,
|
|
"loss": 7.0879,
|
|
"mean_token_accuracy": 0.14445693269371987,
|
|
"num_tokens": 3791010.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 7.24975266456604,
|
|
"epoch": 0.1736872475476053,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999615544358774,
|
|
"loss": 7.0116,
|
|
"mean_token_accuracy": 0.13824615478515626,
|
|
"num_tokens": 3802738.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 7.121045970916748,
|
|
"epoch": 0.17426428159261395,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999607878655587,
|
|
"loss": 7.0366,
|
|
"mean_token_accuracy": 0.14151245802640916,
|
|
"num_tokens": 3815448.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 7.1481671810150145,
|
|
"epoch": 0.17484131563762262,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999600137287958,
|
|
"loss": 7.0332,
|
|
"mean_token_accuracy": 0.1367475040256977,
|
|
"num_tokens": 3829833.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 7.121943235397339,
|
|
"epoch": 0.17541834968263129,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999592320256146,
|
|
"loss": 7.0023,
|
|
"mean_token_accuracy": 0.1391633428633213,
|
|
"num_tokens": 3841544.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 7.198780822753906,
|
|
"epoch": 0.17599538372763993,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004999584427560412,
|
|
"loss": 6.9958,
|
|
"mean_token_accuracy": 0.13729065656661987,
|
|
"num_tokens": 3853886.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 7.095717239379883,
|
|
"epoch": 0.1765724177726486,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004999576459201024,
|
|
"loss": 7.0104,
|
|
"mean_token_accuracy": 0.1445713609457016,
|
|
"num_tokens": 3867942.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 7.133176279067993,
|
|
"epoch": 0.17714945181765723,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499956841517825,
|
|
"loss": 7.0257,
|
|
"mean_token_accuracy": 0.14167340844869614,
|
|
"num_tokens": 3881764.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 7.127892589569091,
|
|
"epoch": 0.1777264858626659,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.000499956029549236,
|
|
"loss": 6.9289,
|
|
"mean_token_accuracy": 0.1465323746204376,
|
|
"num_tokens": 3893979.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 7.17246675491333,
|
|
"epoch": 0.17830351990767454,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999552100143625,
|
|
"loss": 7.0449,
|
|
"mean_token_accuracy": 0.13901807218790055,
|
|
"num_tokens": 3905934.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 7.145467090606689,
|
|
"epoch": 0.1788805539526832,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999543829132324,
|
|
"loss": 6.9948,
|
|
"mean_token_accuracy": 0.14433147236704827,
|
|
"num_tokens": 3918348.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 7.112019491195679,
|
|
"epoch": 0.17945758799769188,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999535482458734,
|
|
"loss": 6.9814,
|
|
"mean_token_accuracy": 0.13943516984581947,
|
|
"num_tokens": 3931863.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 7.105517101287842,
|
|
"epoch": 0.18003462204270052,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004999527060123135,
|
|
"loss": 6.9699,
|
|
"mean_token_accuracy": 0.1462463617324829,
|
|
"num_tokens": 3945108.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 7.1699309825897215,
|
|
"epoch": 0.18061165608770918,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999518562125811,
|
|
"loss": 6.9963,
|
|
"mean_token_accuracy": 0.13957771062850952,
|
|
"num_tokens": 3956695.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 7.086351537704468,
|
|
"epoch": 0.18118869013271782,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004999509988467047,
|
|
"loss": 6.9873,
|
|
"mean_token_accuracy": 0.1385016493499279,
|
|
"num_tokens": 3970458.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 7.148052930831909,
|
|
"epoch": 0.1817657241777265,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999501339147132,
|
|
"loss": 6.9739,
|
|
"mean_token_accuracy": 0.13998864516615867,
|
|
"num_tokens": 3981962.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 7.1447553634643555,
|
|
"epoch": 0.18234275822273513,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999492614166357,
|
|
"loss": 6.982,
|
|
"mean_token_accuracy": 0.13720383271574974,
|
|
"num_tokens": 3993512.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 7.046021413803101,
|
|
"epoch": 0.1829197922677438,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999483813525014,
|
|
"loss": 6.8679,
|
|
"mean_token_accuracy": 0.15238967761397362,
|
|
"num_tokens": 4005826.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 7.077240610122681,
|
|
"epoch": 0.18349682631275246,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999474937223403,
|
|
"loss": 6.9461,
|
|
"mean_token_accuracy": 0.14126977398991586,
|
|
"num_tokens": 4018927.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 7.139278173446655,
|
|
"epoch": 0.1840738603577611,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004999465985261818,
|
|
"loss": 6.9951,
|
|
"mean_token_accuracy": 0.13713297992944717,
|
|
"num_tokens": 4030970.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 7.041838884353638,
|
|
"epoch": 0.18465089440276977,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004999456957640562,
|
|
"loss": 6.9665,
|
|
"mean_token_accuracy": 0.14336296245455743,
|
|
"num_tokens": 4043396.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 7.167615985870361,
|
|
"epoch": 0.1852279284477784,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999447854359939,
|
|
"loss": 6.9946,
|
|
"mean_token_accuracy": 0.13789970949292182,
|
|
"num_tokens": 4055588.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 7.082289409637451,
|
|
"epoch": 0.18580496249278708,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004999438675420255,
|
|
"loss": 6.9775,
|
|
"mean_token_accuracy": 0.1350480891764164,
|
|
"num_tokens": 4068036.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 7.123587226867675,
|
|
"epoch": 0.18638199653779572,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999429420821818,
|
|
"loss": 7.015,
|
|
"mean_token_accuracy": 0.1355690099298954,
|
|
"num_tokens": 4080531.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 7.1394895076751705,
|
|
"epoch": 0.1869590305828044,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.000499942009056494,
|
|
"loss": 6.9259,
|
|
"mean_token_accuracy": 0.14576323702931404,
|
|
"num_tokens": 4093614.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 7.157642984390259,
|
|
"epoch": 0.18753606462781305,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999410684649935,
|
|
"loss": 7.0282,
|
|
"mean_token_accuracy": 0.13709268644452094,
|
|
"num_tokens": 4106836.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 7.0767253875732425,
|
|
"epoch": 0.1881130986728217,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999401203077119,
|
|
"loss": 6.9509,
|
|
"mean_token_accuracy": 0.14356981962919235,
|
|
"num_tokens": 4118739.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 7.107544803619385,
|
|
"epoch": 0.18869013271783036,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499939164584681,
|
|
"loss": 6.9214,
|
|
"mean_token_accuracy": 0.14475391134619714,
|
|
"num_tokens": 4131174.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 7.091096496582031,
|
|
"epoch": 0.189267166762839,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999382012959331,
|
|
"loss": 6.9713,
|
|
"mean_token_accuracy": 0.13550762236118316,
|
|
"num_tokens": 4143459.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 7.121346950531006,
|
|
"epoch": 0.18984420080784767,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999372304415005,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.13536836579442024,
|
|
"num_tokens": 4155864.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.936057138442993,
|
|
"epoch": 0.1904212348528563,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999362520214159,
|
|
"loss": 6.8156,
|
|
"mean_token_accuracy": 0.14860668629407883,
|
|
"num_tokens": 4168433.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 7.137879848480225,
|
|
"epoch": 0.19099826889786498,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999352660357122,
|
|
"loss": 6.9852,
|
|
"mean_token_accuracy": 0.13815735951066016,
|
|
"num_tokens": 4180852.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 7.092313289642334,
|
|
"epoch": 0.19157530294287364,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999342724844226,
|
|
"loss": 6.9307,
|
|
"mean_token_accuracy": 0.14323657527565956,
|
|
"num_tokens": 4194712.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 7.107403707504273,
|
|
"epoch": 0.19215233698788228,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999332713675804,
|
|
"loss": 6.9964,
|
|
"mean_token_accuracy": 0.14108359590172767,
|
|
"num_tokens": 4207970.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 7.045479440689087,
|
|
"epoch": 0.19272937103289095,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999322626852193,
|
|
"loss": 6.9161,
|
|
"mean_token_accuracy": 0.1442576117813587,
|
|
"num_tokens": 4220893.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 7.002764892578125,
|
|
"epoch": 0.1933064050778996,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999312464373734,
|
|
"loss": 6.8981,
|
|
"mean_token_accuracy": 0.13980508148670195,
|
|
"num_tokens": 4232463.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 7.067962741851806,
|
|
"epoch": 0.19388343912290826,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999302226240767,
|
|
"loss": 6.8634,
|
|
"mean_token_accuracy": 0.1389753997325897,
|
|
"num_tokens": 4244604.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 7.014446783065796,
|
|
"epoch": 0.1944604731679169,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004999291912453637,
|
|
"loss": 6.9458,
|
|
"mean_token_accuracy": 0.14495371729135514,
|
|
"num_tokens": 4257260.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 7.177657508850098,
|
|
"epoch": 0.19503750721292556,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999281523012691,
|
|
"loss": 6.9024,
|
|
"mean_token_accuracy": 0.13922334164381028,
|
|
"num_tokens": 4269885.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 7.044678115844727,
|
|
"epoch": 0.1956145412579342,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004999271057918278,
|
|
"loss": 7.0126,
|
|
"mean_token_accuracy": 0.13741706758737565,
|
|
"num_tokens": 4281560.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 7.127787733078003,
|
|
"epoch": 0.19619157530294287,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999260517170751,
|
|
"loss": 6.8977,
|
|
"mean_token_accuracy": 0.14665021896362304,
|
|
"num_tokens": 4293746.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 7.0871453285217285,
|
|
"epoch": 0.19676860934795154,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999249900770463,
|
|
"loss": 6.9355,
|
|
"mean_token_accuracy": 0.1397123083472252,
|
|
"num_tokens": 4306595.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 7.123568153381347,
|
|
"epoch": 0.19734564339296018,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999239208717772,
|
|
"loss": 6.8848,
|
|
"mean_token_accuracy": 0.14523950070142747,
|
|
"num_tokens": 4318705.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.925599145889282,
|
|
"epoch": 0.19792267743796885,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999228441013037,
|
|
"loss": 6.9293,
|
|
"mean_token_accuracy": 0.14079967737197877,
|
|
"num_tokens": 4331321.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 7.063972091674804,
|
|
"epoch": 0.1984997114829775,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499921759765662,
|
|
"loss": 6.8839,
|
|
"mean_token_accuracy": 0.14801763668656348,
|
|
"num_tokens": 4343517.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 7.0327746868133545,
|
|
"epoch": 0.19907674552798615,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004999206678648888,
|
|
"loss": 6.9032,
|
|
"mean_token_accuracy": 0.14797452092170715,
|
|
"num_tokens": 4356342.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.983541250228882,
|
|
"epoch": 0.1996537795729948,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999195683990206,
|
|
"loss": 6.8887,
|
|
"mean_token_accuracy": 0.1441090725362301,
|
|
"num_tokens": 4369078.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 7.019094848632813,
|
|
"epoch": 0.20023081361800346,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999184613680945,
|
|
"loss": 6.8854,
|
|
"mean_token_accuracy": 0.13662683367729186,
|
|
"num_tokens": 4382091.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 7.010761690139771,
|
|
"epoch": 0.20080784766301213,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999173467721476,
|
|
"loss": 6.9208,
|
|
"mean_token_accuracy": 0.1393657937645912,
|
|
"num_tokens": 4393919.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 7.006711435317993,
|
|
"epoch": 0.20138488170802077,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004999162246112175,
|
|
"loss": 6.8789,
|
|
"mean_token_accuracy": 0.1454889804124832,
|
|
"num_tokens": 4407054.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 7.003733777999878,
|
|
"epoch": 0.20196191575302944,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004999150948853419,
|
|
"loss": 6.94,
|
|
"mean_token_accuracy": 0.137217216193676,
|
|
"num_tokens": 4420180.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 7.14780068397522,
|
|
"epoch": 0.20253894979803808,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004999139575945587,
|
|
"loss": 6.9242,
|
|
"mean_token_accuracy": 0.150433312356472,
|
|
"num_tokens": 4433248.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.930108451843262,
|
|
"epoch": 0.20311598384304674,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999128127389065,
|
|
"loss": 6.9106,
|
|
"mean_token_accuracy": 0.14306253790855408,
|
|
"num_tokens": 4446340.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 7.059494829177856,
|
|
"epoch": 0.20369301788805538,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004999116603184233,
|
|
"loss": 6.9249,
|
|
"mean_token_accuracy": 0.140160171687603,
|
|
"num_tokens": 4459918.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.981036758422851,
|
|
"epoch": 0.20427005193306405,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999105003331482,
|
|
"loss": 6.8797,
|
|
"mean_token_accuracy": 0.1448831871151924,
|
|
"num_tokens": 4472020.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 7.015055799484253,
|
|
"epoch": 0.20484708597807272,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999093327831202,
|
|
"loss": 6.8445,
|
|
"mean_token_accuracy": 0.14826457872986792,
|
|
"num_tokens": 4484269.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.998699283599853,
|
|
"epoch": 0.20542412002308136,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999081576683784,
|
|
"loss": 6.9411,
|
|
"mean_token_accuracy": 0.13955088704824448,
|
|
"num_tokens": 4498040.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 7.111977243423462,
|
|
"epoch": 0.20600115406809003,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999069749889626,
|
|
"loss": 6.8938,
|
|
"mean_token_accuracy": 0.14736564159393312,
|
|
"num_tokens": 4509701.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.967676115036011,
|
|
"epoch": 0.20657818811309867,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004999057847449123,
|
|
"loss": 6.9249,
|
|
"mean_token_accuracy": 0.13947466611862183,
|
|
"num_tokens": 4521840.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 7.0544905185699465,
|
|
"epoch": 0.20715522215810733,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999045869362678,
|
|
"loss": 6.9169,
|
|
"mean_token_accuracy": 0.1435271330177784,
|
|
"num_tokens": 4534241.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 7.035863065719605,
|
|
"epoch": 0.20773225620311597,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499903381563069,
|
|
"loss": 6.8669,
|
|
"mean_token_accuracy": 0.1447395406663418,
|
|
"num_tokens": 4547255.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 7.061683273315429,
|
|
"epoch": 0.20830929024812464,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999021686253568,
|
|
"loss": 6.902,
|
|
"mean_token_accuracy": 0.14312518313527106,
|
|
"num_tokens": 4559538.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.928671979904175,
|
|
"epoch": 0.2088863242931333,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004999009481231719,
|
|
"loss": 6.8802,
|
|
"mean_token_accuracy": 0.14481844902038574,
|
|
"num_tokens": 4571444.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.93266978263855,
|
|
"epoch": 0.20946335833814195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004998997200565553,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.15741085708141328,
|
|
"num_tokens": 4586294.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 7.03538408279419,
|
|
"epoch": 0.21004039238315061,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998984844255483,
|
|
"loss": 6.8886,
|
|
"mean_token_accuracy": 0.14464563131332397,
|
|
"num_tokens": 4599661.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.98320894241333,
|
|
"epoch": 0.21061742642815925,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004998972412301925,
|
|
"loss": 6.8964,
|
|
"mean_token_accuracy": 0.14106034338474274,
|
|
"num_tokens": 4611305.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 7.015894365310669,
|
|
"epoch": 0.21119446047316792,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998959904705297,
|
|
"loss": 6.9004,
|
|
"mean_token_accuracy": 0.13522190302610398,
|
|
"num_tokens": 4623992.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 7.014666414260864,
|
|
"epoch": 0.21177149451817656,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004998947321466021,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.1404628872871399,
|
|
"num_tokens": 4636495.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.996430206298828,
|
|
"epoch": 0.21234852856318523,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998934662584518,
|
|
"loss": 6.8858,
|
|
"mean_token_accuracy": 0.14315241277217866,
|
|
"num_tokens": 4650266.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 7.023065519332886,
|
|
"epoch": 0.2129255626081939,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004998921928061214,
|
|
"loss": 6.8519,
|
|
"mean_token_accuracy": 0.14534742385149002,
|
|
"num_tokens": 4663238.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.998432397842407,
|
|
"epoch": 0.21350259665320254,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998909117896539,
|
|
"loss": 6.8968,
|
|
"mean_token_accuracy": 0.14261196106672286,
|
|
"num_tokens": 4675501.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.991396522521972,
|
|
"epoch": 0.2140796306982112,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998896232090922,
|
|
"loss": 6.8619,
|
|
"mean_token_accuracy": 0.13769274204969406,
|
|
"num_tokens": 4688996.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 7.000917768478393,
|
|
"epoch": 0.21465666474321984,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998883270644798,
|
|
"loss": 6.9589,
|
|
"mean_token_accuracy": 0.138343658298254,
|
|
"num_tokens": 4703226.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 7.035671234130859,
|
|
"epoch": 0.2152336987882285,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998870233558602,
|
|
"loss": 6.8455,
|
|
"mean_token_accuracy": 0.14217291474342347,
|
|
"num_tokens": 4715825.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.937395477294922,
|
|
"epoch": 0.21581073283323715,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998857120832774,
|
|
"loss": 6.842,
|
|
"mean_token_accuracy": 0.14556335806846618,
|
|
"num_tokens": 4727819.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 7.042612791061401,
|
|
"epoch": 0.21638776687824582,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998843932467751,
|
|
"loss": 6.875,
|
|
"mean_token_accuracy": 0.14139556288719177,
|
|
"num_tokens": 4742890.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.9743971824646,
|
|
"epoch": 0.21696480092325446,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998830668463982,
|
|
"loss": 6.8641,
|
|
"mean_token_accuracy": 0.1403570555150509,
|
|
"num_tokens": 4755609.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.923630332946777,
|
|
"epoch": 0.21754183496826313,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998817328821909,
|
|
"loss": 6.842,
|
|
"mean_token_accuracy": 0.14689554423093795,
|
|
"num_tokens": 4766674.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.97991976737976,
|
|
"epoch": 0.2181188690132718,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998803913541983,
|
|
"loss": 6.8786,
|
|
"mean_token_accuracy": 0.14042821601033212,
|
|
"num_tokens": 4779639.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 7.112171745300293,
|
|
"epoch": 0.21869590305828043,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998790422624654,
|
|
"loss": 6.9663,
|
|
"mean_token_accuracy": 0.13750633150339125,
|
|
"num_tokens": 4791702.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.947701549530029,
|
|
"epoch": 0.2192729371032891,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004998776856070376,
|
|
"loss": 6.7836,
|
|
"mean_token_accuracy": 0.15090153217315674,
|
|
"num_tokens": 4805756.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.948662805557251,
|
|
"epoch": 0.21984997114829774,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004998763213879606,
|
|
"loss": 6.843,
|
|
"mean_token_accuracy": 0.145341220498085,
|
|
"num_tokens": 4817941.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.965862226486206,
|
|
"epoch": 0.2204270051933064,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004998749496052803,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.14902952387928964,
|
|
"num_tokens": 4832298.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.848330736160278,
|
|
"epoch": 0.22100403923831505,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998735702590426,
|
|
"loss": 6.8195,
|
|
"mean_token_accuracy": 0.1508714735507965,
|
|
"num_tokens": 4844814.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 7.058192014694214,
|
|
"epoch": 0.22158107328332372,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998721833492942,
|
|
"loss": 6.8856,
|
|
"mean_token_accuracy": 0.1431492656469345,
|
|
"num_tokens": 4857888.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.893492078781128,
|
|
"epoch": 0.22215810732833238,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004998707888760816,
|
|
"loss": 6.7919,
|
|
"mean_token_accuracy": 0.14359032064676286,
|
|
"num_tokens": 4870479.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.971369791030884,
|
|
"epoch": 0.22273514137334102,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998693868394516,
|
|
"loss": 6.7938,
|
|
"mean_token_accuracy": 0.1480065330862999,
|
|
"num_tokens": 4883294.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 7.05402398109436,
|
|
"epoch": 0.2233121754183497,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998679772394516,
|
|
"loss": 6.9319,
|
|
"mean_token_accuracy": 0.13698863312602044,
|
|
"num_tokens": 4896331.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.9416258335113525,
|
|
"epoch": 0.22388920946335833,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998665600761289,
|
|
"loss": 6.8675,
|
|
"mean_token_accuracy": 0.14291590824723244,
|
|
"num_tokens": 4908857.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.996976089477539,
|
|
"epoch": 0.224466243508367,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499865135349531,
|
|
"loss": 6.8545,
|
|
"mean_token_accuracy": 0.14505003690719603,
|
|
"num_tokens": 4921564.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.967352771759034,
|
|
"epoch": 0.22504327755337564,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998637030597061,
|
|
"loss": 6.8762,
|
|
"mean_token_accuracy": 0.14787980914115906,
|
|
"num_tokens": 4934960.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.854097366333008,
|
|
"epoch": 0.2256203115983843,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998622632067022,
|
|
"loss": 6.7272,
|
|
"mean_token_accuracy": 0.15127141177654266,
|
|
"num_tokens": 4946942.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.964528608322143,
|
|
"epoch": 0.22619734564339297,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998608157905678,
|
|
"loss": 6.8454,
|
|
"mean_token_accuracy": 0.13881651386618615,
|
|
"num_tokens": 4960751.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.9480382919311525,
|
|
"epoch": 0.2267743796884016,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998593608113515,
|
|
"loss": 6.8417,
|
|
"mean_token_accuracy": 0.14182508513331413,
|
|
"num_tokens": 4973551.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.950195169448852,
|
|
"epoch": 0.22735141373341028,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998578982691024,
|
|
"loss": 6.87,
|
|
"mean_token_accuracy": 0.14090688973665239,
|
|
"num_tokens": 4986224.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.947819328308105,
|
|
"epoch": 0.22792844777841892,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004998564281638694,
|
|
"loss": 6.8368,
|
|
"mean_token_accuracy": 0.14499269127845765,
|
|
"num_tokens": 4999874.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.946592903137207,
|
|
"epoch": 0.2285054818234276,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004998549504957023,
|
|
"loss": 6.8382,
|
|
"mean_token_accuracy": 0.1452639691531658,
|
|
"num_tokens": 5013106.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.935692501068115,
|
|
"epoch": 0.22908251586843623,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998534652646506,
|
|
"loss": 6.8023,
|
|
"mean_token_accuracy": 0.14065282493829728,
|
|
"num_tokens": 5026145.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.941158723831177,
|
|
"epoch": 0.2296595499134449,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004998519724707642,
|
|
"loss": 6.8182,
|
|
"mean_token_accuracy": 0.14938395619392394,
|
|
"num_tokens": 5039216.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.966537952423096,
|
|
"epoch": 0.23023658395845356,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004998504721140934,
|
|
"loss": 6.795,
|
|
"mean_token_accuracy": 0.14359883442521096,
|
|
"num_tokens": 5051956.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.932427787780762,
|
|
"epoch": 0.2308136180034622,
|
|
"grad_norm": 0.77734375,
|
|
"learning_rate": 0.0004998489641946887,
|
|
"loss": 6.8764,
|
|
"mean_token_accuracy": 0.14441612362861633,
|
|
"num_tokens": 5065325.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.94489541053772,
|
|
"epoch": 0.23139065204847087,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004998474487126009,
|
|
"loss": 6.875,
|
|
"mean_token_accuracy": 0.14884231835603715,
|
|
"num_tokens": 5077776.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.97218074798584,
|
|
"epoch": 0.2319676860934795,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998459256678806,
|
|
"loss": 6.8698,
|
|
"mean_token_accuracy": 0.14031682312488555,
|
|
"num_tokens": 5091167.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 7.01816759109497,
|
|
"epoch": 0.23254472013848818,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004998443950605796,
|
|
"loss": 6.8068,
|
|
"mean_token_accuracy": 0.14413101896643638,
|
|
"num_tokens": 5103321.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.925113582611084,
|
|
"epoch": 0.23312175418349682,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998428568907488,
|
|
"loss": 6.8077,
|
|
"mean_token_accuracy": 0.14342234432697296,
|
|
"num_tokens": 5116999.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.899875020980835,
|
|
"epoch": 0.23369878822850548,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004998413111584403,
|
|
"loss": 6.803,
|
|
"mean_token_accuracy": 0.14782628118991853,
|
|
"num_tokens": 5130429.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.895891237258911,
|
|
"epoch": 0.23427582227351415,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004998397578637059,
|
|
"loss": 6.7544,
|
|
"mean_token_accuracy": 0.14964505434036254,
|
|
"num_tokens": 5142728.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.994881963729858,
|
|
"epoch": 0.2348528563185228,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.000499838197006598,
|
|
"loss": 6.854,
|
|
"mean_token_accuracy": 0.14518777132034302,
|
|
"num_tokens": 5155105.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.9891077995300295,
|
|
"epoch": 0.23542989036353146,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.000499836628587169,
|
|
"loss": 6.8814,
|
|
"mean_token_accuracy": 0.13513262197375298,
|
|
"num_tokens": 5169206.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.860302734375,
|
|
"epoch": 0.2360069244085401,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004998350526054716,
|
|
"loss": 6.7535,
|
|
"mean_token_accuracy": 0.1476128190755844,
|
|
"num_tokens": 5182007.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.977161026000976,
|
|
"epoch": 0.23658395845354876,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004998334690615591,
|
|
"loss": 6.7814,
|
|
"mean_token_accuracy": 0.14299210011959076,
|
|
"num_tokens": 5195137.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.875006675720215,
|
|
"epoch": 0.2371609924985574,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004998318779554844,
|
|
"loss": 6.7999,
|
|
"mean_token_accuracy": 0.14403216391801835,
|
|
"num_tokens": 5207713.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.91954345703125,
|
|
"epoch": 0.23773802654356607,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004998302792873012,
|
|
"loss": 6.7539,
|
|
"mean_token_accuracy": 0.1439061000943184,
|
|
"num_tokens": 5220125.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.926095628738404,
|
|
"epoch": 0.23831506058857474,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998286730570631,
|
|
"loss": 6.8071,
|
|
"mean_token_accuracy": 0.1458573669195175,
|
|
"num_tokens": 5232142.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.897360849380493,
|
|
"epoch": 0.23889209463358338,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998270592648245,
|
|
"loss": 6.7912,
|
|
"mean_token_accuracy": 0.15026629641652106,
|
|
"num_tokens": 5245517.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.937630748748779,
|
|
"epoch": 0.23946912867859205,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004998254379106394,
|
|
"loss": 6.7863,
|
|
"mean_token_accuracy": 0.14699850231409073,
|
|
"num_tokens": 5257862.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.865565061569214,
|
|
"epoch": 0.2400461627236007,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998238089945622,
|
|
"loss": 6.7348,
|
|
"mean_token_accuracy": 0.15117276906967164,
|
|
"num_tokens": 5270141.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.878887939453125,
|
|
"epoch": 0.24062319676860935,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004998221725166479,
|
|
"loss": 6.7593,
|
|
"mean_token_accuracy": 0.15452364832162857,
|
|
"num_tokens": 5283143.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.871646356582642,
|
|
"epoch": 0.241200230813618,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998205284769516,
|
|
"loss": 6.8235,
|
|
"mean_token_accuracy": 0.13959436044096946,
|
|
"num_tokens": 5295340.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.964116764068604,
|
|
"epoch": 0.24177726485862666,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998188768755285,
|
|
"loss": 6.7683,
|
|
"mean_token_accuracy": 0.14472750276327134,
|
|
"num_tokens": 5306821.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.834314155578613,
|
|
"epoch": 0.2423542989036353,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004998172177124341,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.14368025809526444,
|
|
"num_tokens": 5319428.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 7.012720727920533,
|
|
"epoch": 0.24293133294864397,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004998155509877242,
|
|
"loss": 6.8145,
|
|
"mean_token_accuracy": 0.13865589946508408,
|
|
"num_tokens": 5331777.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.713190269470215,
|
|
"epoch": 0.24350836699365264,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499813876701455,
|
|
"loss": 6.7742,
|
|
"mean_token_accuracy": 0.14583554863929749,
|
|
"num_tokens": 5344533.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.8935747146606445,
|
|
"epoch": 0.24408540103866128,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998121948536828,
|
|
"loss": 6.7137,
|
|
"mean_token_accuracy": 0.15403580144047738,
|
|
"num_tokens": 5357123.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.924336910247803,
|
|
"epoch": 0.24466243508366994,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004998105054444639,
|
|
"loss": 6.8329,
|
|
"mean_token_accuracy": 0.13986173048615455,
|
|
"num_tokens": 5370123.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.897236251831055,
|
|
"epoch": 0.24523946912867858,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004998088084738555,
|
|
"loss": 6.7763,
|
|
"mean_token_accuracy": 0.15366744846105576,
|
|
"num_tokens": 5382870.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.823340272903442,
|
|
"epoch": 0.24581650317368725,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004998071039419144,
|
|
"loss": 6.7582,
|
|
"mean_token_accuracy": 0.14249610602855683,
|
|
"num_tokens": 5395052.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.9604456424713135,
|
|
"epoch": 0.2463935372186959,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.000499805391848698,
|
|
"loss": 6.7837,
|
|
"mean_token_accuracy": 0.1490890696644783,
|
|
"num_tokens": 5406720.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.8235283374786375,
|
|
"epoch": 0.24697057126370456,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499803672194264,
|
|
"loss": 6.7838,
|
|
"mean_token_accuracy": 0.14721129089593887,
|
|
"num_tokens": 5419465.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.8882369041442875,
|
|
"epoch": 0.24754760530871323,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004998019449786701,
|
|
"loss": 6.7894,
|
|
"mean_token_accuracy": 0.14069402888417243,
|
|
"num_tokens": 5432434.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.860111331939697,
|
|
"epoch": 0.24812463935372187,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004998002102019744,
|
|
"loss": 6.7522,
|
|
"mean_token_accuracy": 0.15137931406497956,
|
|
"num_tokens": 5445249.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.983528804779053,
|
|
"epoch": 0.24870167339873053,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004997984678642354,
|
|
"loss": 6.7916,
|
|
"mean_token_accuracy": 0.1442440040409565,
|
|
"num_tokens": 5458996.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.853938817977905,
|
|
"epoch": 0.24927870744373917,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004997967179655115,
|
|
"loss": 6.7744,
|
|
"mean_token_accuracy": 0.14349499493837356,
|
|
"num_tokens": 5472174.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.808877658843994,
|
|
"epoch": 0.24985574148874784,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997949605058617,
|
|
"loss": 6.7069,
|
|
"mean_token_accuracy": 0.15367118269205093,
|
|
"num_tokens": 5484464.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.934421110153198,
|
|
"epoch": 0.2504327755337565,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997931954853451,
|
|
"loss": 6.8061,
|
|
"mean_token_accuracy": 0.14632220715284347,
|
|
"num_tokens": 5497278.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.86837854385376,
|
|
"epoch": 0.2510098095787651,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.000499791422904021,
|
|
"loss": 6.8287,
|
|
"mean_token_accuracy": 0.1460747793316841,
|
|
"num_tokens": 5510847.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.842457818984985,
|
|
"epoch": 0.2515868436237738,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997896427619491,
|
|
"loss": 6.7482,
|
|
"mean_token_accuracy": 0.14972207546234131,
|
|
"num_tokens": 5522543.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.892645740509034,
|
|
"epoch": 0.25216387766878245,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004997878550591892,
|
|
"loss": 6.7552,
|
|
"mean_token_accuracy": 0.1436435416340828,
|
|
"num_tokens": 5534856.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.831497383117676,
|
|
"epoch": 0.2527409117137911,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004997860597958013,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.1602167546749115,
|
|
"num_tokens": 5546881.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.895463514328003,
|
|
"epoch": 0.2533179457587998,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004997842569718461,
|
|
"loss": 6.7887,
|
|
"mean_token_accuracy": 0.14391066506505013,
|
|
"num_tokens": 5559711.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.865831708908081,
|
|
"epoch": 0.25389497980380843,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.000499782446587384,
|
|
"loss": 6.7843,
|
|
"mean_token_accuracy": 0.1506132774055004,
|
|
"num_tokens": 5573553.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.900459480285645,
|
|
"epoch": 0.25447201384881707,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.000499780628642476,
|
|
"loss": 6.7603,
|
|
"mean_token_accuracy": 0.13870777040719987,
|
|
"num_tokens": 5586046.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.854037666320801,
|
|
"epoch": 0.2550490478938257,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997788031371834,
|
|
"loss": 6.7603,
|
|
"mean_token_accuracy": 0.14891895428299903,
|
|
"num_tokens": 5597876.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.933327293395996,
|
|
"epoch": 0.2556260819388344,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004997769700715672,
|
|
"loss": 6.6716,
|
|
"mean_token_accuracy": 0.1543987885117531,
|
|
"num_tokens": 5611264.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.804627752304077,
|
|
"epoch": 0.25620311598384304,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997751294456892,
|
|
"loss": 6.7679,
|
|
"mean_token_accuracy": 0.1464955747127533,
|
|
"num_tokens": 5625093.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.852876806259156,
|
|
"epoch": 0.2567801500288517,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004997732812596114,
|
|
"loss": 6.7744,
|
|
"mean_token_accuracy": 0.14379966408014297,
|
|
"num_tokens": 5637206.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.857150936126709,
|
|
"epoch": 0.2573571840738604,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997714255133961,
|
|
"loss": 6.6563,
|
|
"mean_token_accuracy": 0.15202945172786714,
|
|
"num_tokens": 5649136.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.837795639038086,
|
|
"epoch": 0.257934218118869,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997695622071054,
|
|
"loss": 6.6956,
|
|
"mean_token_accuracy": 0.15131831020116807,
|
|
"num_tokens": 5660714.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.87720136642456,
|
|
"epoch": 0.25851125216387766,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997676913408021,
|
|
"loss": 6.7654,
|
|
"mean_token_accuracy": 0.14454615712165833,
|
|
"num_tokens": 5673295.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.8868872165679935,
|
|
"epoch": 0.2590882862088863,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004997658129145493,
|
|
"loss": 6.777,
|
|
"mean_token_accuracy": 0.14726119190454484,
|
|
"num_tokens": 5686822.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.793786144256591,
|
|
"epoch": 0.259665320253895,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997639269284099,
|
|
"loss": 6.8295,
|
|
"mean_token_accuracy": 0.1436148166656494,
|
|
"num_tokens": 5700621.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.9439198017120365,
|
|
"epoch": 0.26024235429890363,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997620333824476,
|
|
"loss": 6.7379,
|
|
"mean_token_accuracy": 0.15637929141521453,
|
|
"num_tokens": 5713565.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.800307655334473,
|
|
"epoch": 0.2608193883439123,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997601322767258,
|
|
"loss": 6.783,
|
|
"mean_token_accuracy": 0.1416866213083267,
|
|
"num_tokens": 5726487.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.966365957260132,
|
|
"epoch": 0.26139642238892097,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997582236113087,
|
|
"loss": 6.8581,
|
|
"mean_token_accuracy": 0.1411590591073036,
|
|
"num_tokens": 5739934.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.865359163284301,
|
|
"epoch": 0.2619734564339296,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004997563073862603,
|
|
"loss": 6.8048,
|
|
"mean_token_accuracy": 0.13894407004117965,
|
|
"num_tokens": 5752187.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.836117839813232,
|
|
"epoch": 0.26255049047893825,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004997543836016453,
|
|
"loss": 6.7345,
|
|
"mean_token_accuracy": 0.14709190279245377,
|
|
"num_tokens": 5764850.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.9021507740020756,
|
|
"epoch": 0.2631275245239469,
|
|
"grad_norm": 0.71484375,
|
|
"learning_rate": 0.0004997524522575281,
|
|
"loss": 6.8019,
|
|
"mean_token_accuracy": 0.14260414987802505,
|
|
"num_tokens": 5778577.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.944571781158447,
|
|
"epoch": 0.2637045585689556,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004997505133539738,
|
|
"loss": 6.7487,
|
|
"mean_token_accuracy": 0.1511955589056015,
|
|
"num_tokens": 5791699.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.796835660934448,
|
|
"epoch": 0.2642815926139642,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997485668910476,
|
|
"loss": 6.7555,
|
|
"mean_token_accuracy": 0.14254892766475677,
|
|
"num_tokens": 5804553.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.993517017364502,
|
|
"epoch": 0.26485862665897286,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004997466128688151,
|
|
"loss": 6.7579,
|
|
"mean_token_accuracy": 0.14862642660737038,
|
|
"num_tokens": 5816758.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.853436231613159,
|
|
"epoch": 0.26543566070398156,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.000499744651287342,
|
|
"loss": 6.7812,
|
|
"mean_token_accuracy": 0.13678565695881845,
|
|
"num_tokens": 5831048.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.919308710098266,
|
|
"epoch": 0.2660126947489902,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.000499742682146694,
|
|
"loss": 6.7909,
|
|
"mean_token_accuracy": 0.13784368932247162,
|
|
"num_tokens": 5843159.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.807005167007446,
|
|
"epoch": 0.26658972879399884,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004997407054469377,
|
|
"loss": 6.6791,
|
|
"mean_token_accuracy": 0.15264758318662644,
|
|
"num_tokens": 5856078.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.854742860794067,
|
|
"epoch": 0.2671667628390075,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004997387211881392,
|
|
"loss": 6.706,
|
|
"mean_token_accuracy": 0.14707566574215888,
|
|
"num_tokens": 5867835.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.8351672172546385,
|
|
"epoch": 0.26774379688401617,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004997367293703656,
|
|
"loss": 6.7444,
|
|
"mean_token_accuracy": 0.13954102098941804,
|
|
"num_tokens": 5881179.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.878024482727051,
|
|
"epoch": 0.2683208309290248,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997347299936837,
|
|
"loss": 6.7195,
|
|
"mean_token_accuracy": 0.14241515398025512,
|
|
"num_tokens": 5892774.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.870539665222168,
|
|
"epoch": 0.26889786497403345,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997327230581608,
|
|
"loss": 6.756,
|
|
"mean_token_accuracy": 0.1463689960539341,
|
|
"num_tokens": 5905857.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.805995798110962,
|
|
"epoch": 0.26947489901904215,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997307085638644,
|
|
"loss": 6.7166,
|
|
"mean_token_accuracy": 0.14379769265651704,
|
|
"num_tokens": 5918128.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.918767642974854,
|
|
"epoch": 0.2700519330640508,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004997286865108621,
|
|
"loss": 6.8232,
|
|
"mean_token_accuracy": 0.14087387174367905,
|
|
"num_tokens": 5930606.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.841729688644409,
|
|
"epoch": 0.2706289671090594,
|
|
"grad_norm": 0.88671875,
|
|
"learning_rate": 0.0004997266568992222,
|
|
"loss": 6.7696,
|
|
"mean_token_accuracy": 0.13774231299757958,
|
|
"num_tokens": 5944139.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.887184953689575,
|
|
"epoch": 0.27120600115406807,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004997246197290128,
|
|
"loss": 6.7646,
|
|
"mean_token_accuracy": 0.14507462382316588,
|
|
"num_tokens": 5956779.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.837090969085693,
|
|
"epoch": 0.27178303519907676,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997225750003024,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.15230057314038276,
|
|
"num_tokens": 5971510.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.695552968978882,
|
|
"epoch": 0.2723600692440854,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997205227131599,
|
|
"loss": 6.7371,
|
|
"mean_token_accuracy": 0.1434318020939827,
|
|
"num_tokens": 5983877.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.974739694595337,
|
|
"epoch": 0.27293710328909404,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004997184628676542,
|
|
"loss": 6.7617,
|
|
"mean_token_accuracy": 0.14533916413784026,
|
|
"num_tokens": 5996739.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.768356561660767,
|
|
"epoch": 0.27351413733410274,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004997163954638546,
|
|
"loss": 6.7255,
|
|
"mean_token_accuracy": 0.15101923793554306,
|
|
"num_tokens": 6009289.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.87177038192749,
|
|
"epoch": 0.2740911713791114,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997143205018306,
|
|
"loss": 6.794,
|
|
"mean_token_accuracy": 0.14188004285097122,
|
|
"num_tokens": 6021375.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.898721408843994,
|
|
"epoch": 0.27466820542412,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004997122379816523,
|
|
"loss": 6.7271,
|
|
"mean_token_accuracy": 0.14577853456139564,
|
|
"num_tokens": 6034182.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.774568223953247,
|
|
"epoch": 0.27524523946912866,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004997101479033893,
|
|
"loss": 6.7104,
|
|
"mean_token_accuracy": 0.1492339551448822,
|
|
"num_tokens": 6046486.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.845656013488769,
|
|
"epoch": 0.27582227351413735,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004997080502671122,
|
|
"loss": 6.7644,
|
|
"mean_token_accuracy": 0.14610921069979668,
|
|
"num_tokens": 6060867.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.7973473072052,
|
|
"epoch": 0.276399307559146,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004997059450728913,
|
|
"loss": 6.6264,
|
|
"mean_token_accuracy": 0.15345287024974824,
|
|
"num_tokens": 6073000.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.76253228187561,
|
|
"epoch": 0.27697634160415463,
|
|
"grad_norm": 0.796875,
|
|
"learning_rate": 0.0004997038323207977,
|
|
"loss": 6.6906,
|
|
"mean_token_accuracy": 0.14774474650621414,
|
|
"num_tokens": 6085884.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.787846565246582,
|
|
"epoch": 0.2775533756491633,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997017120109022,
|
|
"loss": 6.6146,
|
|
"mean_token_accuracy": 0.15057797580957413,
|
|
"num_tokens": 6098230.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.782491827011109,
|
|
"epoch": 0.27813040969417197,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996995841432762,
|
|
"loss": 6.6701,
|
|
"mean_token_accuracy": 0.15104399472475052,
|
|
"num_tokens": 6111568.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.779537677764893,
|
|
"epoch": 0.2787074437391806,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004996974487179915,
|
|
"loss": 6.646,
|
|
"mean_token_accuracy": 0.14741345196962358,
|
|
"num_tokens": 6123992.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.796364402770996,
|
|
"epoch": 0.27928447778418924,
|
|
"grad_norm": 0.83203125,
|
|
"learning_rate": 0.0004996953057351195,
|
|
"loss": 6.686,
|
|
"mean_token_accuracy": 0.1465798109769821,
|
|
"num_tokens": 6135452.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.774402904510498,
|
|
"epoch": 0.27986151182919794,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996931551947327,
|
|
"loss": 6.5866,
|
|
"mean_token_accuracy": 0.15778433084487914,
|
|
"num_tokens": 6150144.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.837385368347168,
|
|
"epoch": 0.2804385458742066,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004996909970969031,
|
|
"loss": 6.7329,
|
|
"mean_token_accuracy": 0.14868736639618874,
|
|
"num_tokens": 6163397.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.832604503631591,
|
|
"epoch": 0.2810155799192152,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996888314417034,
|
|
"loss": 6.7233,
|
|
"mean_token_accuracy": 0.14309920221567154,
|
|
"num_tokens": 6175579.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.790614795684815,
|
|
"epoch": 0.2815926139642239,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996866582292067,
|
|
"loss": 6.7063,
|
|
"mean_token_accuracy": 0.15070078819990157,
|
|
"num_tokens": 6189229.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.777169132232666,
|
|
"epoch": 0.28216964800923255,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004996844774594856,
|
|
"loss": 6.6934,
|
|
"mean_token_accuracy": 0.1502875879406929,
|
|
"num_tokens": 6203817.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.82915768623352,
|
|
"epoch": 0.2827466820542412,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996822891326138,
|
|
"loss": 6.7206,
|
|
"mean_token_accuracy": 0.14171916842460633,
|
|
"num_tokens": 6216098.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.812518548965454,
|
|
"epoch": 0.28332371609924983,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004996800932486648,
|
|
"loss": 6.7166,
|
|
"mean_token_accuracy": 0.14603719413280486,
|
|
"num_tokens": 6228987.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.742992639541626,
|
|
"epoch": 0.28390075014425853,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004996778898077126,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.15222399532794953,
|
|
"num_tokens": 6241676.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 6.889522314071655,
|
|
"epoch": 0.28447778418926717,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996756788098309,
|
|
"loss": 6.702,
|
|
"mean_token_accuracy": 0.14694569408893585,
|
|
"num_tokens": 6254744.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.758044672012329,
|
|
"epoch": 0.2850548182342758,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 0.0004996734602550945,
|
|
"loss": 6.6596,
|
|
"mean_token_accuracy": 0.1465069644153118,
|
|
"num_tokens": 6268242.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.747747182846069,
|
|
"epoch": 0.2856318522792845,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004996712341435779,
|
|
"loss": 6.5867,
|
|
"mean_token_accuracy": 0.1545226328074932,
|
|
"num_tokens": 6279904.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 6.745885562896729,
|
|
"epoch": 0.28620888632429314,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996690004753559,
|
|
"loss": 6.7018,
|
|
"mean_token_accuracy": 0.14820884317159652,
|
|
"num_tokens": 6292885.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.753550338745117,
|
|
"epoch": 0.2867859203693018,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004996667592505037,
|
|
"loss": 6.6887,
|
|
"mean_token_accuracy": 0.15229137539863585,
|
|
"num_tokens": 6306278.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.884258556365967,
|
|
"epoch": 0.2873629544143104,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996645104690967,
|
|
"loss": 6.7179,
|
|
"mean_token_accuracy": 0.13899706602096557,
|
|
"num_tokens": 6320360.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.700476408004761,
|
|
"epoch": 0.2879399884593191,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996622541312103,
|
|
"loss": 6.7035,
|
|
"mean_token_accuracy": 0.144860952347517,
|
|
"num_tokens": 6332778.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.817806053161621,
|
|
"epoch": 0.28851702250432776,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996599902369207,
|
|
"loss": 6.6808,
|
|
"mean_token_accuracy": 0.14956472143530847,
|
|
"num_tokens": 6345028.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.786530876159668,
|
|
"epoch": 0.2890940565493364,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004996577187863039,
|
|
"loss": 6.6425,
|
|
"mean_token_accuracy": 0.15257902592420577,
|
|
"num_tokens": 6356931.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.698649883270264,
|
|
"epoch": 0.2896710905943451,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004996554397794364,
|
|
"loss": 6.5883,
|
|
"mean_token_accuracy": 0.15760106444358826,
|
|
"num_tokens": 6370247.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 6.7704665184021,
|
|
"epoch": 0.29024812463935373,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004996531532163947,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.14782440811395645,
|
|
"num_tokens": 6382352.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.754695749282837,
|
|
"epoch": 0.2908251586843624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996508590972558,
|
|
"loss": 6.6397,
|
|
"mean_token_accuracy": 0.14761101007461547,
|
|
"num_tokens": 6395949.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.754686546325684,
|
|
"epoch": 0.291402192729371,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004996485574220969,
|
|
"loss": 6.6647,
|
|
"mean_token_accuracy": 0.15044545978307725,
|
|
"num_tokens": 6408469.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.768384695053101,
|
|
"epoch": 0.2919792267743797,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004996462481909953,
|
|
"loss": 6.6579,
|
|
"mean_token_accuracy": 0.1553287237882614,
|
|
"num_tokens": 6419953.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.790286922454834,
|
|
"epoch": 0.29255626081938835,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996439314040287,
|
|
"loss": 6.7094,
|
|
"mean_token_accuracy": 0.143075567483902,
|
|
"num_tokens": 6432567.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 6.826392459869385,
|
|
"epoch": 0.293133294864397,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499641607061275,
|
|
"loss": 6.6549,
|
|
"mean_token_accuracy": 0.1453825443983078,
|
|
"num_tokens": 6445951.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 6.742476511001587,
|
|
"epoch": 0.2937103289094057,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996392751628126,
|
|
"loss": 6.7032,
|
|
"mean_token_accuracy": 0.15503485202789308,
|
|
"num_tokens": 6458799.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 6.815782499313355,
|
|
"epoch": 0.2942873629544143,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996369357087196,
|
|
"loss": 6.7065,
|
|
"mean_token_accuracy": 0.1430730052292347,
|
|
"num_tokens": 6471423.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.799359512329102,
|
|
"epoch": 0.29486439699942296,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000499634588699075,
|
|
"loss": 6.7392,
|
|
"mean_token_accuracy": 0.14322351813316345,
|
|
"num_tokens": 6484248.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.833653163909912,
|
|
"epoch": 0.2954414310444316,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996322341339575,
|
|
"loss": 6.6637,
|
|
"mean_token_accuracy": 0.14406396448612213,
|
|
"num_tokens": 6497048.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.775566720962525,
|
|
"epoch": 0.2960184650894403,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004996298720134465,
|
|
"loss": 6.6848,
|
|
"mean_token_accuracy": 0.14442287534475326,
|
|
"num_tokens": 6508840.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.7831347465515135,
|
|
"epoch": 0.29659549913444894,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004996275023376213,
|
|
"loss": 6.6583,
|
|
"mean_token_accuracy": 0.1537433847784996,
|
|
"num_tokens": 6520976.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.741522121429443,
|
|
"epoch": 0.2971725331794576,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004996251251065615,
|
|
"loss": 6.673,
|
|
"mean_token_accuracy": 0.15090716034173965,
|
|
"num_tokens": 6533009.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.822439098358155,
|
|
"epoch": 0.2977495672244662,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004996227403203473,
|
|
"loss": 6.6662,
|
|
"mean_token_accuracy": 0.14721700698137283,
|
|
"num_tokens": 6545196.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.812913274765014,
|
|
"epoch": 0.2983266012694749,
|
|
"grad_norm": 0.859375,
|
|
"learning_rate": 0.0004996203479790589,
|
|
"loss": 6.7017,
|
|
"mean_token_accuracy": 0.1475054517388344,
|
|
"num_tokens": 6557479.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.819405889511108,
|
|
"epoch": 0.29890363531448355,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996179480827764,
|
|
"loss": 6.7114,
|
|
"mean_token_accuracy": 0.14923257529735565,
|
|
"num_tokens": 6569832.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.738608884811401,
|
|
"epoch": 0.2994806693594922,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.000499615540631581,
|
|
"loss": 6.6737,
|
|
"mean_token_accuracy": 0.14806562215089797,
|
|
"num_tokens": 6581651.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.774818849563599,
|
|
"epoch": 0.3000577034045009,
|
|
"grad_norm": 0.765625,
|
|
"learning_rate": 0.0004996131256255534,
|
|
"loss": 6.7423,
|
|
"mean_token_accuracy": 0.14710890799760817,
|
|
"num_tokens": 6596331.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.817371892929077,
|
|
"epoch": 0.3006347374495095,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004996107030647749,
|
|
"loss": 6.6685,
|
|
"mean_token_accuracy": 0.14770287573337554,
|
|
"num_tokens": 6609712.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.759057664871216,
|
|
"epoch": 0.30121177149451817,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004996082729493269,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.1502513587474823,
|
|
"num_tokens": 6622780.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.784829711914062,
|
|
"epoch": 0.3017888055395268,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004996058352792913,
|
|
"loss": 6.7561,
|
|
"mean_token_accuracy": 0.1468655101954937,
|
|
"num_tokens": 6636288.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 6.858647060394287,
|
|
"epoch": 0.3023658395845355,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.00049960339005475,
|
|
"loss": 6.7313,
|
|
"mean_token_accuracy": 0.1382056713104248,
|
|
"num_tokens": 6649883.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.787996578216553,
|
|
"epoch": 0.30294287362954414,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004996009372757852,
|
|
"loss": 6.6803,
|
|
"mean_token_accuracy": 0.14866930097341538,
|
|
"num_tokens": 6662241.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.705225419998169,
|
|
"epoch": 0.3035199076745528,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004995984769424795,
|
|
"loss": 6.6389,
|
|
"mean_token_accuracy": 0.14856984168291093,
|
|
"num_tokens": 6674790.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.879620838165283,
|
|
"epoch": 0.3040969417195615,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004995960090549155,
|
|
"loss": 6.6451,
|
|
"mean_token_accuracy": 0.14790016412734985,
|
|
"num_tokens": 6687713.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 6.629987955093384,
|
|
"epoch": 0.3046739757645701,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004995935336131764,
|
|
"loss": 6.6574,
|
|
"mean_token_accuracy": 0.1474847599864006,
|
|
"num_tokens": 6701123.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 6.796099090576172,
|
|
"epoch": 0.30525100980957875,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004995910506173452,
|
|
"loss": 6.6029,
|
|
"mean_token_accuracy": 0.15525631308555604,
|
|
"num_tokens": 6712674.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.721958589553833,
|
|
"epoch": 0.3058280438545874,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995885600675059,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.15212517231702805,
|
|
"num_tokens": 6724840.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 6.760172510147095,
|
|
"epoch": 0.3064050778995961,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995860619637415,
|
|
"loss": 6.7425,
|
|
"mean_token_accuracy": 0.13689624965190889,
|
|
"num_tokens": 6738746.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.875043773651123,
|
|
"epoch": 0.30698211194460473,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004995835563061367,
|
|
"loss": 6.6436,
|
|
"mean_token_accuracy": 0.1482662469148636,
|
|
"num_tokens": 6751620.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 6.727645397186279,
|
|
"epoch": 0.30755914598961337,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004995810430947756,
|
|
"loss": 6.6337,
|
|
"mean_token_accuracy": 0.1513223595917225,
|
|
"num_tokens": 6763957.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 6.559813404083252,
|
|
"epoch": 0.30813618003462206,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004995785223297426,
|
|
"loss": 6.5468,
|
|
"mean_token_accuracy": 0.1547765851020813,
|
|
"num_tokens": 6776211.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.862458086013794,
|
|
"epoch": 0.3087132140796307,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995759940111225,
|
|
"loss": 6.786,
|
|
"mean_token_accuracy": 0.14168819040060043,
|
|
"num_tokens": 6789745.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.805125570297241,
|
|
"epoch": 0.30929024812463934,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004995734581390005,
|
|
"loss": 6.7054,
|
|
"mean_token_accuracy": 0.14849800616502762,
|
|
"num_tokens": 6801771.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.708049964904785,
|
|
"epoch": 0.309867282169648,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995709147134617,
|
|
"loss": 6.6365,
|
|
"mean_token_accuracy": 0.14683517664670945,
|
|
"num_tokens": 6813993.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.818436479568481,
|
|
"epoch": 0.3104443162146567,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995683637345919,
|
|
"loss": 6.7144,
|
|
"mean_token_accuracy": 0.14922749251127243,
|
|
"num_tokens": 6826833.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.754158878326416,
|
|
"epoch": 0.3110213502596653,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004995658052024765,
|
|
"loss": 6.6478,
|
|
"mean_token_accuracy": 0.1457843691110611,
|
|
"num_tokens": 6838947.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.80776834487915,
|
|
"epoch": 0.31159838430467396,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004995632391172019,
|
|
"loss": 6.7147,
|
|
"mean_token_accuracy": 0.14534788727760314,
|
|
"num_tokens": 6851781.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.8032268524169925,
|
|
"epoch": 0.31217541834968265,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995606654788543,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.1524400979280472,
|
|
"num_tokens": 6863479.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.714714527130127,
|
|
"epoch": 0.3127524523946913,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004995580842875202,
|
|
"loss": 6.593,
|
|
"mean_token_accuracy": 0.15386273488402366,
|
|
"num_tokens": 6877000.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.8048097610473635,
|
|
"epoch": 0.31332948643969993,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004995554955432866,
|
|
"loss": 6.6981,
|
|
"mean_token_accuracy": 0.14284373223781585,
|
|
"num_tokens": 6888878.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.769490671157837,
|
|
"epoch": 0.3139065204847086,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995528992462404,
|
|
"loss": 6.6196,
|
|
"mean_token_accuracy": 0.14831875115633011,
|
|
"num_tokens": 6902147.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 6.750906562805175,
|
|
"epoch": 0.31448355452971727,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.000499550295396469,
|
|
"loss": 6.6661,
|
|
"mean_token_accuracy": 0.15283936485648156,
|
|
"num_tokens": 6914927.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.761933422088623,
|
|
"epoch": 0.3150605885747259,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004995476839940598,
|
|
"loss": 6.6683,
|
|
"mean_token_accuracy": 0.1505434513092041,
|
|
"num_tokens": 6927757.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.762182760238647,
|
|
"epoch": 0.31563762261973455,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.000499545065039101,
|
|
"loss": 6.6725,
|
|
"mean_token_accuracy": 0.1466390758752823,
|
|
"num_tokens": 6941039.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.781767749786377,
|
|
"epoch": 0.31621465666474324,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995424385316803,
|
|
"loss": 6.7293,
|
|
"mean_token_accuracy": 0.14698702692985535,
|
|
"num_tokens": 6954876.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.725474309921265,
|
|
"epoch": 0.3167916907097519,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004995398044718863,
|
|
"loss": 6.5811,
|
|
"mean_token_accuracy": 0.1516340285539627,
|
|
"num_tokens": 6966889.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.753961610794067,
|
|
"epoch": 0.3173687247547605,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995371628598074,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.1514896869659424,
|
|
"num_tokens": 6979894.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 6.722421312332154,
|
|
"epoch": 0.31794575879976916,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004995345136955328,
|
|
"loss": 6.6356,
|
|
"mean_token_accuracy": 0.1484585776925087,
|
|
"num_tokens": 6992734.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.755990600585937,
|
|
"epoch": 0.31852279284477786,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995318569791512,
|
|
"loss": 6.663,
|
|
"mean_token_accuracy": 0.14797065705060958,
|
|
"num_tokens": 7006504.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.7291755199432375,
|
|
"epoch": 0.3190998268897865,
|
|
"grad_norm": 0.79296875,
|
|
"learning_rate": 0.0004995291927107522,
|
|
"loss": 6.5971,
|
|
"mean_token_accuracy": 0.15441082864999772,
|
|
"num_tokens": 7018978.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.710022735595703,
|
|
"epoch": 0.31967686093479514,
|
|
"grad_norm": 0.7578125,
|
|
"learning_rate": 0.0004995265208904252,
|
|
"loss": 6.6868,
|
|
"mean_token_accuracy": 0.1457875519990921,
|
|
"num_tokens": 7031294.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.80343861579895,
|
|
"epoch": 0.32025389497980383,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004995238415182603,
|
|
"loss": 6.6386,
|
|
"mean_token_accuracy": 0.1497604802250862,
|
|
"num_tokens": 7044139.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.643225526809692,
|
|
"epoch": 0.3208309290248125,
|
|
"grad_norm": 0.875,
|
|
"learning_rate": 0.0004995211545943476,
|
|
"loss": 6.5431,
|
|
"mean_token_accuracy": 0.15468174815177918,
|
|
"num_tokens": 7056232.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.770214605331421,
|
|
"epoch": 0.3214079630698211,
|
|
"grad_norm": 0.7890625,
|
|
"learning_rate": 0.0004995184601187772,
|
|
"loss": 6.6978,
|
|
"mean_token_accuracy": 0.1458260402083397,
|
|
"num_tokens": 7070125.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.735332918167114,
|
|
"epoch": 0.32198499711482975,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.00049951575809164,
|
|
"loss": 6.5678,
|
|
"mean_token_accuracy": 0.15374045222997665,
|
|
"num_tokens": 7083535.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 6.679257535934449,
|
|
"epoch": 0.32256203115983845,
|
|
"grad_norm": 0.85546875,
|
|
"learning_rate": 0.0004995130485130269,
|
|
"loss": 6.537,
|
|
"mean_token_accuracy": 0.15215112119913102,
|
|
"num_tokens": 7095081.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.756899642944336,
|
|
"epoch": 0.3231390652048471,
|
|
"grad_norm": 0.8203125,
|
|
"learning_rate": 0.0004995103313830289,
|
|
"loss": 6.6676,
|
|
"mean_token_accuracy": 0.14167121201753616,
|
|
"num_tokens": 7107764.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.7260784149169925,
|
|
"epoch": 0.3237160992498557,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004995076067017373,
|
|
"loss": 6.6009,
|
|
"mean_token_accuracy": 0.1534109964966774,
|
|
"num_tokens": 7119754.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 6.6373598098754885,
|
|
"epoch": 0.3242931332948644,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004995048744692439,
|
|
"loss": 6.6299,
|
|
"mean_token_accuracy": 0.15635569840669633,
|
|
"num_tokens": 7132087.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 6.691185474395752,
|
|
"epoch": 0.32487016733987306,
|
|
"grad_norm": 0.89453125,
|
|
"learning_rate": 0.0004995021346856405,
|
|
"loss": 6.6053,
|
|
"mean_token_accuracy": 0.14959825202822685,
|
|
"num_tokens": 7143325.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.7681121826171875,
|
|
"epoch": 0.3254472013848817,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004994993873510196,
|
|
"loss": 6.5619,
|
|
"mean_token_accuracy": 0.15113845020532607,
|
|
"num_tokens": 7154771.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 6.670676565170288,
|
|
"epoch": 0.32602423542989034,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994966324654731,
|
|
"loss": 6.6585,
|
|
"mean_token_accuracy": 0.14671303182840348,
|
|
"num_tokens": 7168352.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.619832849502563,
|
|
"epoch": 0.32660126947489904,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.000499493870029094,
|
|
"loss": 6.4456,
|
|
"mean_token_accuracy": 0.16549365520477294,
|
|
"num_tokens": 7180618.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.737293481826782,
|
|
"epoch": 0.3271783035199077,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994911000419749,
|
|
"loss": 6.6031,
|
|
"mean_token_accuracy": 0.14624983444809914,
|
|
"num_tokens": 7192634.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 6.660342025756836,
|
|
"epoch": 0.3277553375649163,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994883225042093,
|
|
"loss": 6.6186,
|
|
"mean_token_accuracy": 0.15046972185373306,
|
|
"num_tokens": 7205839.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.736796808242798,
|
|
"epoch": 0.328332371609925,
|
|
"grad_norm": 0.73828125,
|
|
"learning_rate": 0.0004994855374158905,
|
|
"loss": 6.627,
|
|
"mean_token_accuracy": 0.15292316824197769,
|
|
"num_tokens": 7218371.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 6.6943048477172855,
|
|
"epoch": 0.32890940565493365,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000499482744777112,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.1693370446562767,
|
|
"num_tokens": 7231506.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 6.649769687652588,
|
|
"epoch": 0.3294864396999423,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.000499479944587968,
|
|
"loss": 6.5888,
|
|
"mean_token_accuracy": 0.1511973798274994,
|
|
"num_tokens": 7243088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.694813299179077,
|
|
"epoch": 0.33006347374495093,
|
|
"grad_norm": 0.828125,
|
|
"learning_rate": 0.0004994771368485526,
|
|
"loss": 6.5163,
|
|
"mean_token_accuracy": 0.1597664922475815,
|
|
"num_tokens": 7255383.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.647224283218383,
|
|
"epoch": 0.3306405077899596,
|
|
"grad_norm": 0.80078125,
|
|
"learning_rate": 0.0004994743215589602,
|
|
"loss": 6.608,
|
|
"mean_token_accuracy": 0.15329548567533494,
|
|
"num_tokens": 7268270.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.673927307128906,
|
|
"epoch": 0.33121754183496827,
|
|
"grad_norm": 0.8515625,
|
|
"learning_rate": 0.0004994714987192854,
|
|
"loss": 6.5362,
|
|
"mean_token_accuracy": 0.1510409414768219,
|
|
"num_tokens": 7281108.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.702598619461059,
|
|
"epoch": 0.3317945758799769,
|
|
"grad_norm": 0.76171875,
|
|
"learning_rate": 0.0004994686683296234,
|
|
"loss": 6.5981,
|
|
"mean_token_accuracy": 0.14916437938809396,
|
|
"num_tokens": 7293961.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.701837539672852,
|
|
"epoch": 0.3323716099249856,
|
|
"grad_norm": 0.8046875,
|
|
"learning_rate": 0.0004994658303900691,
|
|
"loss": 6.6155,
|
|
"mean_token_accuracy": 0.15184523910284042,
|
|
"num_tokens": 7306574.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.728485918045044,
|
|
"epoch": 0.33294864396999424,
|
|
"grad_norm": 0.78515625,
|
|
"learning_rate": 0.0004994629849007182,
|
|
"loss": 6.6466,
|
|
"mean_token_accuracy": 0.14797799810767173,
|
|
"num_tokens": 7319046.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 6.79762864112854,
|
|
"epoch": 0.3335256780150029,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994601318616663,
|
|
"loss": 6.64,
|
|
"mean_token_accuracy": 0.14297626465559005,
|
|
"num_tokens": 7332033.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 6.6803630828857425,
|
|
"epoch": 0.3341027120600115,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 0.0004994572712730092,
|
|
"loss": 6.6512,
|
|
"mean_token_accuracy": 0.14246861189603804,
|
|
"num_tokens": 7344658.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.816131925582885,
|
|
"epoch": 0.3346797461050202,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994544031348434,
|
|
"loss": 6.5279,
|
|
"mean_token_accuracy": 0.15453597754240037,
|
|
"num_tokens": 7357252.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.603551912307739,
|
|
"epoch": 0.33525678015002885,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004994515274472653,
|
|
"loss": 6.4869,
|
|
"mean_token_accuracy": 0.1610173389315605,
|
|
"num_tokens": 7369280.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.595618057250976,
|
|
"epoch": 0.3358338141950375,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004994486442103715,
|
|
"loss": 6.4916,
|
|
"mean_token_accuracy": 0.1597081333398819,
|
|
"num_tokens": 7383017.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.698597812652588,
|
|
"epoch": 0.3364108482400462,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499445753424259,
|
|
"loss": 6.6324,
|
|
"mean_token_accuracy": 0.1377485029399395,
|
|
"num_tokens": 7395634.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.708563899993896,
|
|
"epoch": 0.33698788228505483,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994428550890251,
|
|
"loss": 6.601,
|
|
"mean_token_accuracy": 0.15198962539434432,
|
|
"num_tokens": 7408590.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.720327949523925,
|
|
"epoch": 0.33756491633006347,
|
|
"grad_norm": 0.84375,
|
|
"learning_rate": 0.0004994399492047672,
|
|
"loss": 6.5912,
|
|
"mean_token_accuracy": 0.1499352663755417,
|
|
"num_tokens": 7420202.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.670965766906738,
|
|
"epoch": 0.3381419503750721,
|
|
"grad_norm": 0.84765625,
|
|
"learning_rate": 0.0004994370357715832,
|
|
"loss": 6.5504,
|
|
"mean_token_accuracy": 0.16089099049568176,
|
|
"num_tokens": 7432664.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 6.661357879638672,
|
|
"epoch": 0.3387189844200808,
|
|
"grad_norm": 0.75390625,
|
|
"learning_rate": 0.000499434114789571,
|
|
"loss": 6.7051,
|
|
"mean_token_accuracy": 0.1464277185499668,
|
|
"num_tokens": 7446084.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 6.714499425888062,
|
|
"epoch": 0.33929601846508944,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994311862588286,
|
|
"loss": 6.5508,
|
|
"mean_token_accuracy": 0.15420828610658646,
|
|
"num_tokens": 7458314.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.676367473602295,
|
|
"epoch": 0.3398730525100981,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 0.0004994282501794551,
|
|
"loss": 6.5995,
|
|
"mean_token_accuracy": 0.15544719249010086,
|
|
"num_tokens": 7471995.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.703731489181519,
|
|
"epoch": 0.3404500865551068,
|
|
"grad_norm": 0.7734375,
|
|
"learning_rate": 0.0004994253065515486,
|
|
"loss": 6.622,
|
|
"mean_token_accuracy": 0.1454193964600563,
|
|
"num_tokens": 7485676.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.740993881225586,
|
|
"epoch": 0.3410271206001154,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 0.0004994223553752084,
|
|
"loss": 6.5061,
|
|
"mean_token_accuracy": 0.15575395077466964,
|
|
"num_tokens": 7497057.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 6.6203021049499515,
|
|
"epoch": 0.34160415464512406,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 0.0004994193966505339,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.15374020338058472,
|
|
"num_tokens": 7510625.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.623828363418579,
|
|
"epoch": 0.3421811886901327,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 0.0004994164303776244,
|
|
"loss": 6.5414,
|
|
"mean_token_accuracy": 0.15313206017017364,
|
|
"num_tokens": 7522677.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.613079309463501,
|
|
"epoch": 0.3427582227351414,
|
|
"grad_norm": 0.78125,
|
|
"learning_rate": 0.0004994134565565797,
|
|
"loss": 6.4729,
|
|
"mean_token_accuracy": 0.15777821689844132,
|
|
"num_tokens": 7535406.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 6.725028848648071,
|
|
"epoch": 0.34333525678015003,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004994104751875,
|
|
"loss": 6.6259,
|
|
"mean_token_accuracy": 0.1496363550424576,
|
|
"num_tokens": 7547577.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.7461694240570065,
|
|
"epoch": 0.3439122908251587,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 0.0004994074862704854,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.15172602161765097,
|
|
"num_tokens": 7561734.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.712504768371582,
|
|
"epoch": 0.3444893248701673,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004994044898056363,
|
|
"loss": 6.6621,
|
|
"mean_token_accuracy": 0.14886820018291474,
|
|
"num_tokens": 7574256.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 6.752849674224853,
|
|
"epoch": 0.345066358915176,
|
|
"grad_norm": 0.8125,
|
|
"learning_rate": 0.0004994014857930538,
|
|
"loss": 6.5801,
|
|
"mean_token_accuracy": 0.15615265667438508,
|
|
"num_tokens": 7587149.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.642135143280029,
|
|
"epoch": 0.34564339296018465,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004993984742328387,
|
|
"loss": 6.5502,
|
|
"mean_token_accuracy": 0.15114353597164154,
|
|
"num_tokens": 7599124.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 6.641741514205933,
|
|
"epoch": 0.3462204270051933,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 0.0004993954551250925,
|
|
"loss": 6.5556,
|
|
"mean_token_accuracy": 0.1523570418357849,
|
|
"num_tokens": 7612070.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3462204270051933,
|
|
"eval_entropy": 6.5966810582204065,
|
|
"eval_loss": 6.6427154541015625,
|
|
"eval_mean_token_accuracy": 0.1525940384301639,
|
|
"eval_num_tokens": 7612070.0,
|
|
"eval_runtime": 17.8197,
|
|
"eval_samples_per_second": 1578.922,
|
|
"eval_steps_per_second": 197.365,
|
|
"step": 3000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 86650,
|
|
"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": 1665254915112960.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|