48123 lines
1.3 MiB
48123 lines
1.3 MiB
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 2.6954568428146235,
|
|
"eval_steps": 3000,
|
|
"global_step": 24000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 10.69199733734131,
|
|
"epoch": 0.0005615769079575448,
|
|
"grad_norm": 14.125,
|
|
"learning_rate": 2e-06,
|
|
"loss": 10.84,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 11659.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 10.691959762573243,
|
|
"epoch": 0.0011231538159150896,
|
|
"grad_norm": 14.875,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 10.7444,
|
|
"mean_token_accuracy": 7.587253348901868e-05,
|
|
"num_tokens": 21794.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 10.691159057617188,
|
|
"epoch": 0.0016847307238726343,
|
|
"grad_norm": 10.5625,
|
|
"learning_rate": 7e-06,
|
|
"loss": 10.4856,
|
|
"mean_token_accuracy": 0.01876390671823174,
|
|
"num_tokens": 33206.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 10.683279323577882,
|
|
"epoch": 0.0022463076318301792,
|
|
"grad_norm": 6.25,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 10.1599,
|
|
"mean_token_accuracy": 0.034115538187325004,
|
|
"num_tokens": 44487.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 10.643766784667969,
|
|
"epoch": 0.002807884539787724,
|
|
"grad_norm": 4.09375,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 9.8718,
|
|
"mean_token_accuracy": 0.04097060300409794,
|
|
"num_tokens": 56062.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.59372034072876,
|
|
"epoch": 0.0033694614477452686,
|
|
"grad_norm": 3.21875,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 9.6884,
|
|
"mean_token_accuracy": 0.0397952314466238,
|
|
"num_tokens": 67453.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.589542388916016,
|
|
"epoch": 0.003931038355702813,
|
|
"grad_norm": 2.71875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 9.6654,
|
|
"mean_token_accuracy": 0.040205162949860096,
|
|
"num_tokens": 78527.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.591767120361329,
|
|
"epoch": 0.0044926152636603585,
|
|
"grad_norm": 2.578125,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 9.5713,
|
|
"mean_token_accuracy": 0.04592900909483433,
|
|
"num_tokens": 89267.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.579859638214112,
|
|
"epoch": 0.005054192171617903,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.5319,
|
|
"mean_token_accuracy": 0.04604604430496693,
|
|
"num_tokens": 102035.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.586153793334962,
|
|
"epoch": 0.005615769079575448,
|
|
"grad_norm": 2.671875,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.4905,
|
|
"mean_token_accuracy": 0.04422647394239902,
|
|
"num_tokens": 112734.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.576881599426269,
|
|
"epoch": 0.006177345987532993,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.4077,
|
|
"mean_token_accuracy": 0.03770475871860981,
|
|
"num_tokens": 123854.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.551261711120606,
|
|
"epoch": 0.006738922895490537,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.3296,
|
|
"mean_token_accuracy": 0.04481921121478081,
|
|
"num_tokens": 133444.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.531212902069091,
|
|
"epoch": 0.007300499803448083,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.2183,
|
|
"mean_token_accuracy": 0.05932291820645332,
|
|
"num_tokens": 144678.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.393140697479248,
|
|
"epoch": 0.007862076711405626,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.1453,
|
|
"mean_token_accuracy": 0.056172562018036845,
|
|
"num_tokens": 155866.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.388829708099365,
|
|
"epoch": 0.008423653619363172,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.0724,
|
|
"mean_token_accuracy": 0.06042071580886841,
|
|
"num_tokens": 166965.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.462674045562744,
|
|
"epoch": 0.008985230527320717,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 8.9521,
|
|
"mean_token_accuracy": 0.0692318245768547,
|
|
"num_tokens": 177423.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.331163120269775,
|
|
"epoch": 0.00954680743527826,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 8.8328,
|
|
"mean_token_accuracy": 0.07574180811643601,
|
|
"num_tokens": 188687.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.222314929962158,
|
|
"epoch": 0.010108384343235806,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 8.7904,
|
|
"mean_token_accuracy": 0.07162599004805088,
|
|
"num_tokens": 200173.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.237919807434082,
|
|
"epoch": 0.010669961251193351,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.6616,
|
|
"mean_token_accuracy": 0.07694140449166298,
|
|
"num_tokens": 210877.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.136093044281006,
|
|
"epoch": 0.011231538159150897,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.5155,
|
|
"mean_token_accuracy": 0.0797793373465538,
|
|
"num_tokens": 221770.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.076034641265869,
|
|
"epoch": 0.01179311506710844,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.4363,
|
|
"mean_token_accuracy": 0.08221952021121978,
|
|
"num_tokens": 232140.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 9.958266925811767,
|
|
"epoch": 0.012354691975065986,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.3904,
|
|
"mean_token_accuracy": 0.07742410823702812,
|
|
"num_tokens": 244186.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 9.92665433883667,
|
|
"epoch": 0.012916268883023531,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.1995,
|
|
"mean_token_accuracy": 0.08315626531839371,
|
|
"num_tokens": 254805.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 9.761961746215821,
|
|
"epoch": 0.013477845790981074,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.0418,
|
|
"mean_token_accuracy": 0.09004319682717324,
|
|
"num_tokens": 265055.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.711062622070312,
|
|
"epoch": 0.01403942269893862,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 7.9103,
|
|
"mean_token_accuracy": 0.08997093960642814,
|
|
"num_tokens": 275850.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.528320026397704,
|
|
"epoch": 0.014600999606896165,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.8455,
|
|
"mean_token_accuracy": 0.08536324948072434,
|
|
"num_tokens": 286802.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.43552894592285,
|
|
"epoch": 0.015162576514853709,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 7.8037,
|
|
"mean_token_accuracy": 0.08595463857054711,
|
|
"num_tokens": 297070.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.212979316711426,
|
|
"epoch": 0.015724153422811252,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 7.6719,
|
|
"mean_token_accuracy": 0.08102959841489792,
|
|
"num_tokens": 309617.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 8.98444652557373,
|
|
"epoch": 0.0162857303307688,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.5759,
|
|
"mean_token_accuracy": 0.0875118389725685,
|
|
"num_tokens": 321310.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.683964824676513,
|
|
"epoch": 0.016847307238726343,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.4529,
|
|
"mean_token_accuracy": 0.09075084403157234,
|
|
"num_tokens": 332243.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.567935752868653,
|
|
"epoch": 0.017408884146683887,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.3707,
|
|
"mean_token_accuracy": 0.09007078930735588,
|
|
"num_tokens": 342847.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.343489074707032,
|
|
"epoch": 0.017970461054641434,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.2838,
|
|
"mean_token_accuracy": 0.09157189652323723,
|
|
"num_tokens": 353570.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.204969120025634,
|
|
"epoch": 0.018532037962598977,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.2465,
|
|
"mean_token_accuracy": 0.09896112084388733,
|
|
"num_tokens": 364330.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.996236562728882,
|
|
"epoch": 0.01909361487055652,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.2602,
|
|
"mean_token_accuracy": 0.09376133009791374,
|
|
"num_tokens": 374930.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.048484230041504,
|
|
"epoch": 0.019655191778514068,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.2096,
|
|
"mean_token_accuracy": 0.09344206750392914,
|
|
"num_tokens": 384690.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.837320470809937,
|
|
"epoch": 0.020216768686471612,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.1975,
|
|
"mean_token_accuracy": 0.0976659506559372,
|
|
"num_tokens": 395753.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.850379133224488,
|
|
"epoch": 0.020778345594429155,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.1482,
|
|
"mean_token_accuracy": 0.09964234381914139,
|
|
"num_tokens": 407049.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.762841367721558,
|
|
"epoch": 0.021339922502386702,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.1287,
|
|
"mean_token_accuracy": 0.10560355857014656,
|
|
"num_tokens": 417942.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.797861766815186,
|
|
"epoch": 0.021901499410344246,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.1548,
|
|
"mean_token_accuracy": 0.10006576329469681,
|
|
"num_tokens": 428151.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.798689174652099,
|
|
"epoch": 0.022463076318301793,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.2293,
|
|
"mean_token_accuracy": 0.09349132850766181,
|
|
"num_tokens": 439837.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.697256374359131,
|
|
"epoch": 0.023024653226259337,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.0368,
|
|
"mean_token_accuracy": 0.1030456155538559,
|
|
"num_tokens": 450357.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.727653217315674,
|
|
"epoch": 0.02358623013421688,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.0594,
|
|
"mean_token_accuracy": 0.10246213376522065,
|
|
"num_tokens": 461174.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.568133020401001,
|
|
"epoch": 0.024147807042174427,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.1079,
|
|
"mean_token_accuracy": 0.10158494561910629,
|
|
"num_tokens": 472785.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.636423826217651,
|
|
"epoch": 0.02470938395013197,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.0786,
|
|
"mean_token_accuracy": 0.10676130950450897,
|
|
"num_tokens": 483248.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.532600831985474,
|
|
"epoch": 0.025270960858089515,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.9308,
|
|
"mean_token_accuracy": 0.10589632242918015,
|
|
"num_tokens": 494690.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.67465763092041,
|
|
"epoch": 0.025832537766047062,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.1502,
|
|
"mean_token_accuracy": 0.10144523307681083,
|
|
"num_tokens": 506192.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.504990577697754,
|
|
"epoch": 0.026394114674004605,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.0149,
|
|
"mean_token_accuracy": 0.10282881110906601,
|
|
"num_tokens": 517152.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.417121648788452,
|
|
"epoch": 0.02695569158196215,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9465,
|
|
"mean_token_accuracy": 0.11191134601831436,
|
|
"num_tokens": 527836.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.521721506118775,
|
|
"epoch": 0.027517268489919696,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.074,
|
|
"mean_token_accuracy": 0.10694148242473603,
|
|
"num_tokens": 539491.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.5123631954193115,
|
|
"epoch": 0.02807884539787724,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.0457,
|
|
"mean_token_accuracy": 0.10798109769821167,
|
|
"num_tokens": 550816.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.512091779708863,
|
|
"epoch": 0.028640422305834783,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.0864,
|
|
"mean_token_accuracy": 0.10389656201004982,
|
|
"num_tokens": 561566.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.469761371612549,
|
|
"epoch": 0.02920199921379233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.10888160541653633,
|
|
"num_tokens": 573032.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.406926107406616,
|
|
"epoch": 0.029763576121749874,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9295,
|
|
"mean_token_accuracy": 0.11083082705736161,
|
|
"num_tokens": 584140.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.479501533508301,
|
|
"epoch": 0.030325153029707418,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.9942,
|
|
"mean_token_accuracy": 0.11373844891786575,
|
|
"num_tokens": 595097.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.397661972045898,
|
|
"epoch": 0.030886729937664965,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.0078,
|
|
"mean_token_accuracy": 0.10632957443594933,
|
|
"num_tokens": 606797.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.419397830963135,
|
|
"epoch": 0.031448306845622505,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9786,
|
|
"mean_token_accuracy": 0.10562919154763221,
|
|
"num_tokens": 618187.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.363228178024292,
|
|
"epoch": 0.032009883753580055,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.9095,
|
|
"mean_token_accuracy": 0.11332885026931763,
|
|
"num_tokens": 629829.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.330576467514038,
|
|
"epoch": 0.0325714606615376,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.9224,
|
|
"mean_token_accuracy": 0.11370442360639572,
|
|
"num_tokens": 640914.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.378089332580567,
|
|
"epoch": 0.03313303756949514,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.9324,
|
|
"mean_token_accuracy": 0.10816294327378273,
|
|
"num_tokens": 653057.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.25587100982666,
|
|
"epoch": 0.033694614477452686,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8538,
|
|
"mean_token_accuracy": 0.11798578426241875,
|
|
"num_tokens": 663437.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.289643287658691,
|
|
"epoch": 0.03425619138541023,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9274,
|
|
"mean_token_accuracy": 0.10952336639165879,
|
|
"num_tokens": 675416.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.191143465042114,
|
|
"epoch": 0.03481776829336777,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.7139,
|
|
"mean_token_accuracy": 0.11911309286952018,
|
|
"num_tokens": 686633.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.206870460510254,
|
|
"epoch": 0.035379345201325324,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8231,
|
|
"mean_token_accuracy": 0.11704705879092217,
|
|
"num_tokens": 698065.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.289987993240357,
|
|
"epoch": 0.03594092210928287,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8248,
|
|
"mean_token_accuracy": 0.11439744681119919,
|
|
"num_tokens": 708652.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.232913827896118,
|
|
"epoch": 0.03650249901724041,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.9881,
|
|
"mean_token_accuracy": 0.10934536978602409,
|
|
"num_tokens": 720199.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.196808099746704,
|
|
"epoch": 0.037064075925197955,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9619,
|
|
"mean_token_accuracy": 0.10815565586090088,
|
|
"num_tokens": 732964.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.188594055175781,
|
|
"epoch": 0.0376256528331555,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.7203,
|
|
"mean_token_accuracy": 0.11759673580527305,
|
|
"num_tokens": 743528.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.216085720062256,
|
|
"epoch": 0.03818722974111304,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7942,
|
|
"mean_token_accuracy": 0.11542778238654136,
|
|
"num_tokens": 754365.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.035056495666504,
|
|
"epoch": 0.03874880664907059,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7182,
|
|
"mean_token_accuracy": 0.11288121640682221,
|
|
"num_tokens": 766094.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.112251138687133,
|
|
"epoch": 0.039310383557028136,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7712,
|
|
"mean_token_accuracy": 0.11812571287155152,
|
|
"num_tokens": 777275.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.1510889530181885,
|
|
"epoch": 0.03987196046498568,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.844,
|
|
"mean_token_accuracy": 0.1156160980463028,
|
|
"num_tokens": 789436.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.172001838684082,
|
|
"epoch": 0.040433537372943223,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8679,
|
|
"mean_token_accuracy": 0.11365923285484314,
|
|
"num_tokens": 800164.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.032376146316528,
|
|
"epoch": 0.04099511428090077,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.73,
|
|
"mean_token_accuracy": 0.1194022923707962,
|
|
"num_tokens": 811797.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.035384750366211,
|
|
"epoch": 0.04155669118885831,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.744,
|
|
"mean_token_accuracy": 0.12005754113197327,
|
|
"num_tokens": 824158.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.067680978775025,
|
|
"epoch": 0.04211826809681586,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7441,
|
|
"mean_token_accuracy": 0.12421485558152198,
|
|
"num_tokens": 835803.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.172079133987427,
|
|
"epoch": 0.042679845004773405,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8204,
|
|
"mean_token_accuracy": 0.11587870791554451,
|
|
"num_tokens": 848106.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.041548442840576,
|
|
"epoch": 0.04324142191273095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7849,
|
|
"mean_token_accuracy": 0.11313552036881447,
|
|
"num_tokens": 859101.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.045945501327514,
|
|
"epoch": 0.04380299882068849,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.6582,
|
|
"mean_token_accuracy": 0.12235154137015343,
|
|
"num_tokens": 870309.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 6.961396837234497,
|
|
"epoch": 0.044364575728646036,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7449,
|
|
"mean_token_accuracy": 0.11937168762087821,
|
|
"num_tokens": 881515.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.038133382797241,
|
|
"epoch": 0.044926152636603586,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7085,
|
|
"mean_token_accuracy": 0.12275884225964546,
|
|
"num_tokens": 892129.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 6.987507295608521,
|
|
"epoch": 0.04548772954456113,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7253,
|
|
"mean_token_accuracy": 0.11545129716396332,
|
|
"num_tokens": 903186.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.024265384674072,
|
|
"epoch": 0.046049306452518673,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6962,
|
|
"mean_token_accuracy": 0.12458662018179893,
|
|
"num_tokens": 913471.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.011588430404663,
|
|
"epoch": 0.04661088336047622,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.11497079506516457,
|
|
"num_tokens": 924283.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 6.955825996398926,
|
|
"epoch": 0.04717246026843376,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7257,
|
|
"mean_token_accuracy": 0.12139789834618568,
|
|
"num_tokens": 934975.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 6.922592639923096,
|
|
"epoch": 0.047734037176391304,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.6052,
|
|
"mean_token_accuracy": 0.12621162980794906,
|
|
"num_tokens": 945587.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 6.930565118789673,
|
|
"epoch": 0.048295614084348855,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.6627,
|
|
"mean_token_accuracy": 0.11665054634213448,
|
|
"num_tokens": 955935.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 6.9625404357910154,
|
|
"epoch": 0.0488571909923064,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.6217,
|
|
"mean_token_accuracy": 0.12234737649559975,
|
|
"num_tokens": 967960.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.918611526489258,
|
|
"epoch": 0.04941876790026394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6711,
|
|
"mean_token_accuracy": 0.12240631505846977,
|
|
"num_tokens": 979680.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 6.917942047119141,
|
|
"epoch": 0.049980344808221486,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7478,
|
|
"mean_token_accuracy": 0.12340849041938781,
|
|
"num_tokens": 990600.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.053799295425415,
|
|
"epoch": 0.05054192171617903,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.12520086020231247,
|
|
"num_tokens": 1002331.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 6.887303018569947,
|
|
"epoch": 0.05110349862413657,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.5812,
|
|
"mean_token_accuracy": 0.12343053072690964,
|
|
"num_tokens": 1013473.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.888548421859741,
|
|
"epoch": 0.051665075532094124,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6644,
|
|
"mean_token_accuracy": 0.12126656621694565,
|
|
"num_tokens": 1024434.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.952251386642456,
|
|
"epoch": 0.05222665244005167,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.6902,
|
|
"mean_token_accuracy": 0.11487246379256248,
|
|
"num_tokens": 1035452.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 6.930226802825928,
|
|
"epoch": 0.05278822934800921,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.563,
|
|
"mean_token_accuracy": 0.12226332053542137,
|
|
"num_tokens": 1046213.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.727850151062012,
|
|
"epoch": 0.053349806255966754,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.5962,
|
|
"mean_token_accuracy": 0.12299741804599762,
|
|
"num_tokens": 1057469.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.949178981781006,
|
|
"epoch": 0.0539113831639243,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.7449,
|
|
"mean_token_accuracy": 0.11885052472352982,
|
|
"num_tokens": 1069543.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.829960346221924,
|
|
"epoch": 0.05447296007188184,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6032,
|
|
"mean_token_accuracy": 0.12388219833374023,
|
|
"num_tokens": 1080476.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.998953199386596,
|
|
"epoch": 0.05503453697983939,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7311,
|
|
"mean_token_accuracy": 0.12146280780434608,
|
|
"num_tokens": 1091700.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.7566276550292965,
|
|
"epoch": 0.055596113887796936,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.12116920575499535,
|
|
"num_tokens": 1103056.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.9239182472229,
|
|
"epoch": 0.05615769079575448,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.12681836783885955,
|
|
"num_tokens": 1114836.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.807825708389283,
|
|
"epoch": 0.05671926770371202,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.12368799895048141,
|
|
"num_tokens": 1125993.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.843410921096802,
|
|
"epoch": 0.05728084461166957,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.6499,
|
|
"mean_token_accuracy": 0.12425459921360016,
|
|
"num_tokens": 1136719.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.831955003738403,
|
|
"epoch": 0.05784242151962711,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.5187,
|
|
"mean_token_accuracy": 0.12717537805438042,
|
|
"num_tokens": 1146947.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.8093184471130375,
|
|
"epoch": 0.05840399842758466,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6549,
|
|
"mean_token_accuracy": 0.1217711940407753,
|
|
"num_tokens": 1157974.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.776603937149048,
|
|
"epoch": 0.058965575335542204,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.5957,
|
|
"mean_token_accuracy": 0.12135538086295128,
|
|
"num_tokens": 1168573.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.728848695755005,
|
|
"epoch": 0.05952715224349975,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.4734,
|
|
"mean_token_accuracy": 0.1271596685051918,
|
|
"num_tokens": 1178446.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.797522687911988,
|
|
"epoch": 0.06008872915145729,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.12605770081281661,
|
|
"num_tokens": 1190558.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.782135057449341,
|
|
"epoch": 0.060650306059414835,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.684,
|
|
"mean_token_accuracy": 0.12132162749767303,
|
|
"num_tokens": 1201929.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.717436075210571,
|
|
"epoch": 0.06121188296737238,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.5219,
|
|
"mean_token_accuracy": 0.12698362171649932,
|
|
"num_tokens": 1213155.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.891464042663574,
|
|
"epoch": 0.06177345987532993,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.5834,
|
|
"mean_token_accuracy": 0.12621916830539703,
|
|
"num_tokens": 1223961.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.545057249069214,
|
|
"epoch": 0.06233503678328747,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.4808,
|
|
"mean_token_accuracy": 0.12663164362311363,
|
|
"num_tokens": 1233888.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.767652130126953,
|
|
"epoch": 0.06289661369124501,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.5989,
|
|
"mean_token_accuracy": 0.11711542010307312,
|
|
"num_tokens": 1244405.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.754672956466675,
|
|
"epoch": 0.06345819059920256,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.5399,
|
|
"mean_token_accuracy": 0.12238047644495964,
|
|
"num_tokens": 1257099.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.819364261627197,
|
|
"epoch": 0.06401976750716011,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.6517,
|
|
"mean_token_accuracy": 0.12521917819976808,
|
|
"num_tokens": 1267965.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.710899448394775,
|
|
"epoch": 0.06458134441511765,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5609,
|
|
"mean_token_accuracy": 0.1245420053601265,
|
|
"num_tokens": 1280075.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.763568544387818,
|
|
"epoch": 0.0651429213230752,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.558,
|
|
"mean_token_accuracy": 0.1273508958518505,
|
|
"num_tokens": 1290574.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.691582345962525,
|
|
"epoch": 0.06570449823103273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.5351,
|
|
"mean_token_accuracy": 0.13094205483794213,
|
|
"num_tokens": 1302680.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.729927682876587,
|
|
"epoch": 0.06626607513899029,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.12820309847593309,
|
|
"num_tokens": 1314577.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.720426177978515,
|
|
"epoch": 0.06682765204694784,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6534,
|
|
"mean_token_accuracy": 0.127957072108984,
|
|
"num_tokens": 1326560.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.889089202880859,
|
|
"epoch": 0.06738922895490537,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.7183,
|
|
"mean_token_accuracy": 0.11803506314754486,
|
|
"num_tokens": 1339105.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.515667247772217,
|
|
"epoch": 0.06795080586286292,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.3725,
|
|
"mean_token_accuracy": 0.13529646024107933,
|
|
"num_tokens": 1349914.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.7512102127075195,
|
|
"epoch": 0.06851238277082046,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6063,
|
|
"mean_token_accuracy": 0.12086223512887954,
|
|
"num_tokens": 1361700.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.72710428237915,
|
|
"epoch": 0.06907395967877801,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.6141,
|
|
"mean_token_accuracy": 0.12547043561935425,
|
|
"num_tokens": 1373103.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.627476501464844,
|
|
"epoch": 0.06963553658673555,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.13028801828622819,
|
|
"num_tokens": 1383742.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.588920402526855,
|
|
"epoch": 0.0701971134946931,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5754,
|
|
"mean_token_accuracy": 0.12626228407025336,
|
|
"num_tokens": 1396656.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.6745930194854735,
|
|
"epoch": 0.07075869040265065,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.4518,
|
|
"mean_token_accuracy": 0.14176289066672326,
|
|
"num_tokens": 1406709.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.6905371189117435,
|
|
"epoch": 0.07132026731060818,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.4806,
|
|
"mean_token_accuracy": 0.1374201662838459,
|
|
"num_tokens": 1417793.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.665899324417114,
|
|
"epoch": 0.07188184421856574,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5627,
|
|
"mean_token_accuracy": 0.13078077808022498,
|
|
"num_tokens": 1429093.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.610226154327393,
|
|
"epoch": 0.07244342112652327,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.492,
|
|
"mean_token_accuracy": 0.13368908688426018,
|
|
"num_tokens": 1440907.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.695104122161865,
|
|
"epoch": 0.07300499803448082,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.5606,
|
|
"mean_token_accuracy": 0.12654911056160928,
|
|
"num_tokens": 1452089.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.7353943347930905,
|
|
"epoch": 0.07356657494243837,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5794,
|
|
"mean_token_accuracy": 0.12776191011071206,
|
|
"num_tokens": 1464378.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.62319712638855,
|
|
"epoch": 0.07412815185039591,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.5055,
|
|
"mean_token_accuracy": 0.13134382292628288,
|
|
"num_tokens": 1476678.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.5715944290161135,
|
|
"epoch": 0.07468972875835346,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.3478,
|
|
"mean_token_accuracy": 0.1335635580122471,
|
|
"num_tokens": 1486808.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.715902948379517,
|
|
"epoch": 0.075251305666311,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6385,
|
|
"mean_token_accuracy": 0.1281900115311146,
|
|
"num_tokens": 1499281.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.594720935821533,
|
|
"epoch": 0.07581288257426855,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5429,
|
|
"mean_token_accuracy": 0.12866927832365035,
|
|
"num_tokens": 1510202.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.640082120895386,
|
|
"epoch": 0.07637445948222608,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.4175,
|
|
"mean_token_accuracy": 0.13352399095892906,
|
|
"num_tokens": 1521492.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.529734992980957,
|
|
"epoch": 0.07693603639018363,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.4224,
|
|
"mean_token_accuracy": 0.1373117059469223,
|
|
"num_tokens": 1532856.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.563913011550904,
|
|
"epoch": 0.07749761329814119,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.4298,
|
|
"mean_token_accuracy": 0.13284594789147378,
|
|
"num_tokens": 1543408.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.5086448192596436,
|
|
"epoch": 0.07805919020609872,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.4744,
|
|
"mean_token_accuracy": 0.1292234666645527,
|
|
"num_tokens": 1555474.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.665031242370605,
|
|
"epoch": 0.07862076711405627,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5664,
|
|
"mean_token_accuracy": 0.1303274817764759,
|
|
"num_tokens": 1567484.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.562999153137207,
|
|
"epoch": 0.07918234402201381,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.3967,
|
|
"mean_token_accuracy": 0.13949733674526216,
|
|
"num_tokens": 1578204.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.614490175247193,
|
|
"epoch": 0.07974392092997136,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.3833,
|
|
"mean_token_accuracy": 0.1383664131164551,
|
|
"num_tokens": 1589012.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.435742950439453,
|
|
"epoch": 0.08030549783792891,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.3943,
|
|
"mean_token_accuracy": 0.1336691454052925,
|
|
"num_tokens": 1601099.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.609636449813843,
|
|
"epoch": 0.08086707474588645,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.572,
|
|
"mean_token_accuracy": 0.12780067026615144,
|
|
"num_tokens": 1612814.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.573339128494263,
|
|
"epoch": 0.081428651653844,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.4532,
|
|
"mean_token_accuracy": 0.13029669150710105,
|
|
"num_tokens": 1624953.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.592752456665039,
|
|
"epoch": 0.08199022856180153,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.4967,
|
|
"mean_token_accuracy": 0.12852037101984023,
|
|
"num_tokens": 1635673.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.508557653427124,
|
|
"epoch": 0.08255180546975908,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.13426842764019967,
|
|
"num_tokens": 1647282.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.531473875045776,
|
|
"epoch": 0.08311338237771662,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.4091,
|
|
"mean_token_accuracy": 0.13616270646452905,
|
|
"num_tokens": 1658426.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.508967781066895,
|
|
"epoch": 0.08367495928567417,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.4464,
|
|
"mean_token_accuracy": 0.13434510231018065,
|
|
"num_tokens": 1669958.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.531551885604858,
|
|
"epoch": 0.08423653619363172,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.496,
|
|
"mean_token_accuracy": 0.1306629441678524,
|
|
"num_tokens": 1682409.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.5382561683654785,
|
|
"epoch": 0.08479811310158926,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.4142,
|
|
"mean_token_accuracy": 0.1416614383459091,
|
|
"num_tokens": 1692409.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.598318290710449,
|
|
"epoch": 0.08535969000954681,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.5122,
|
|
"mean_token_accuracy": 0.1292322888970375,
|
|
"num_tokens": 1705018.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.487031126022339,
|
|
"epoch": 0.08592126691750435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4388,
|
|
"mean_token_accuracy": 0.13245034515857695,
|
|
"num_tokens": 1715625.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.529515266418457,
|
|
"epoch": 0.0864828438254619,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5178,
|
|
"mean_token_accuracy": 0.125034099817276,
|
|
"num_tokens": 1727045.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.638304615020752,
|
|
"epoch": 0.08704442073341945,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5797,
|
|
"mean_token_accuracy": 0.13172487169504166,
|
|
"num_tokens": 1737374.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.570305490493775,
|
|
"epoch": 0.08760599764137698,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5729,
|
|
"mean_token_accuracy": 0.1319825679063797,
|
|
"num_tokens": 1747788.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.380049180984497,
|
|
"epoch": 0.08816757454933453,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.2706,
|
|
"mean_token_accuracy": 0.14245652109384538,
|
|
"num_tokens": 1757769.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.499381113052368,
|
|
"epoch": 0.08872915145729207,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.3888,
|
|
"mean_token_accuracy": 0.12719078063964845,
|
|
"num_tokens": 1769246.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.573248052597046,
|
|
"epoch": 0.08929072836524962,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5119,
|
|
"mean_token_accuracy": 0.131352935731411,
|
|
"num_tokens": 1781306.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.474650239944458,
|
|
"epoch": 0.08985230527320717,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.413,
|
|
"mean_token_accuracy": 0.13447367399930954,
|
|
"num_tokens": 1792888.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.4736183166503904,
|
|
"epoch": 0.09041388218116471,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4328,
|
|
"mean_token_accuracy": 0.13652909994125367,
|
|
"num_tokens": 1802938.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.540951681137085,
|
|
"epoch": 0.09097545908912226,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4417,
|
|
"mean_token_accuracy": 0.13303363993763923,
|
|
"num_tokens": 1814738.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.546661281585694,
|
|
"epoch": 0.0915370359970798,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.5162,
|
|
"mean_token_accuracy": 0.13302921801805495,
|
|
"num_tokens": 1825100.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.376165437698364,
|
|
"epoch": 0.09209861290503735,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.3468,
|
|
"mean_token_accuracy": 0.13940613865852355,
|
|
"num_tokens": 1835879.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.615822601318359,
|
|
"epoch": 0.09266018981299488,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.12611727342009543,
|
|
"num_tokens": 1848352.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.488889122009278,
|
|
"epoch": 0.09322176672095243,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4528,
|
|
"mean_token_accuracy": 0.13165955916047095,
|
|
"num_tokens": 1859687.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.441867017745972,
|
|
"epoch": 0.09378334362890998,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4471,
|
|
"mean_token_accuracy": 0.13207249566912652,
|
|
"num_tokens": 1871438.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.437953948974609,
|
|
"epoch": 0.09434492053686752,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.317,
|
|
"mean_token_accuracy": 0.1421381339430809,
|
|
"num_tokens": 1881519.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.583179473876953,
|
|
"epoch": 0.09490649744482507,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.5235,
|
|
"mean_token_accuracy": 0.1294063374400139,
|
|
"num_tokens": 1892428.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.5530884742736815,
|
|
"epoch": 0.09546807435278261,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.3993,
|
|
"mean_token_accuracy": 0.13649718686938286,
|
|
"num_tokens": 1903760.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.441016054153442,
|
|
"epoch": 0.09602965126074016,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4656,
|
|
"mean_token_accuracy": 0.12715155258774757,
|
|
"num_tokens": 1915430.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.446907186508179,
|
|
"epoch": 0.09659122816869771,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.4209,
|
|
"mean_token_accuracy": 0.1297461584210396,
|
|
"num_tokens": 1925709.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.458964443206787,
|
|
"epoch": 0.09715280507665525,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4711,
|
|
"mean_token_accuracy": 0.13050815761089324,
|
|
"num_tokens": 1938148.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.31799168586731,
|
|
"epoch": 0.0977143819846128,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.3348,
|
|
"mean_token_accuracy": 0.138660329580307,
|
|
"num_tokens": 1949028.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.477993202209473,
|
|
"epoch": 0.09827595889257033,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.3788,
|
|
"mean_token_accuracy": 0.1366566650569439,
|
|
"num_tokens": 1960353.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.498833131790161,
|
|
"epoch": 0.09883753580052788,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4888,
|
|
"mean_token_accuracy": 0.1329733595252037,
|
|
"num_tokens": 1972335.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.404474306106567,
|
|
"epoch": 0.09939911270848542,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.13555458709597587,
|
|
"num_tokens": 1982851.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.407796001434326,
|
|
"epoch": 0.09996068961644297,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.3255,
|
|
"mean_token_accuracy": 0.13792148530483245,
|
|
"num_tokens": 1993931.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.429170560836792,
|
|
"epoch": 0.10052226652440052,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4634,
|
|
"mean_token_accuracy": 0.13388581573963165,
|
|
"num_tokens": 2004838.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.3420192241668705,
|
|
"epoch": 0.10108384343235806,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.2468,
|
|
"mean_token_accuracy": 0.1361763894557953,
|
|
"num_tokens": 2015620.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.4620874404907225,
|
|
"epoch": 0.10164542034031561,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3865,
|
|
"mean_token_accuracy": 0.13934891074895858,
|
|
"num_tokens": 2027489.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.273737144470215,
|
|
"epoch": 0.10220699724827315,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.2673,
|
|
"mean_token_accuracy": 0.14417464286088943,
|
|
"num_tokens": 2038475.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.300836038589478,
|
|
"epoch": 0.1027685741562307,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.1379096359014511,
|
|
"num_tokens": 2048938.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.325875759124756,
|
|
"epoch": 0.10333015106418825,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.3679,
|
|
"mean_token_accuracy": 0.1302135966718197,
|
|
"num_tokens": 2060372.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.354682302474975,
|
|
"epoch": 0.10389172797214578,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.3505,
|
|
"mean_token_accuracy": 0.13487576618790625,
|
|
"num_tokens": 2071558.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.366049098968506,
|
|
"epoch": 0.10445330488010333,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3933,
|
|
"mean_token_accuracy": 0.13562066927552224,
|
|
"num_tokens": 2082350.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.407677173614502,
|
|
"epoch": 0.10501488178806087,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4426,
|
|
"mean_token_accuracy": 0.1333223059773445,
|
|
"num_tokens": 2093448.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.589928674697876,
|
|
"epoch": 0.10557645869601842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4712,
|
|
"mean_token_accuracy": 0.13386278226971626,
|
|
"num_tokens": 2104171.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.296870374679566,
|
|
"epoch": 0.10613803560397596,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.3689,
|
|
"mean_token_accuracy": 0.1341085195541382,
|
|
"num_tokens": 2114496.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.430097818374634,
|
|
"epoch": 0.10669961251193351,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.361,
|
|
"mean_token_accuracy": 0.13727748170495033,
|
|
"num_tokens": 2125930.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.391914176940918,
|
|
"epoch": 0.10726118941989106,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.2988,
|
|
"mean_token_accuracy": 0.14066791236400605,
|
|
"num_tokens": 2136452.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.334331274032593,
|
|
"epoch": 0.1078227663278486,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.423,
|
|
"mean_token_accuracy": 0.13491920307278632,
|
|
"num_tokens": 2148233.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.278422260284424,
|
|
"epoch": 0.10838434323580615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.1412498541176319,
|
|
"num_tokens": 2159475.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.32360987663269,
|
|
"epoch": 0.10894592014376368,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3321,
|
|
"mean_token_accuracy": 0.13456659838557244,
|
|
"num_tokens": 2170042.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.306992149353027,
|
|
"epoch": 0.10950749705172123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3404,
|
|
"mean_token_accuracy": 0.13353059962391853,
|
|
"num_tokens": 2182234.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.304850292205811,
|
|
"epoch": 0.11006907395967878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3209,
|
|
"mean_token_accuracy": 0.13740065470337867,
|
|
"num_tokens": 2192477.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.2778017044067385,
|
|
"epoch": 0.11063065086763632,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3165,
|
|
"mean_token_accuracy": 0.13349851667881013,
|
|
"num_tokens": 2203082.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.335120153427124,
|
|
"epoch": 0.11119222777559387,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2766,
|
|
"mean_token_accuracy": 0.1371467188000679,
|
|
"num_tokens": 2213684.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.285449409484864,
|
|
"epoch": 0.11175380468355141,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.3063,
|
|
"mean_token_accuracy": 0.13364971727132796,
|
|
"num_tokens": 2225524.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.384835195541382,
|
|
"epoch": 0.11231538159150896,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.26,
|
|
"mean_token_accuracy": 0.13841750770807265,
|
|
"num_tokens": 2236004.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.345810842514038,
|
|
"epoch": 0.1128769584994665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499999997707492,
|
|
"loss": 6.4186,
|
|
"mean_token_accuracy": 0.12697779908776283,
|
|
"num_tokens": 2247730.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.38932580947876,
|
|
"epoch": 0.11343853540742405,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999999883941787,
|
|
"loss": 6.3762,
|
|
"mean_token_accuracy": 0.1392652601003647,
|
|
"num_tokens": 2260132.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.30682406425476,
|
|
"epoch": 0.1140001123153816,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999719167785,
|
|
"loss": 6.331,
|
|
"mean_token_accuracy": 0.1405606284737587,
|
|
"num_tokens": 2270060.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.300048065185547,
|
|
"epoch": 0.11456168922333913,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999999482752917,
|
|
"loss": 6.357,
|
|
"mean_token_accuracy": 0.13881335780024529,
|
|
"num_tokens": 2281568.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.372472620010376,
|
|
"epoch": 0.11512326613129668,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004999999174697195,
|
|
"loss": 6.3714,
|
|
"mean_token_accuracy": 0.13230287730693818,
|
|
"num_tokens": 2293325.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.375746154785157,
|
|
"epoch": 0.11568484303925422,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999998795000627,
|
|
"loss": 6.3781,
|
|
"mean_token_accuracy": 0.1413520097732544,
|
|
"num_tokens": 2304780.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.2897717475891115,
|
|
"epoch": 0.11624641994721177,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999998343663223,
|
|
"loss": 6.2999,
|
|
"mean_token_accuracy": 0.1347263291478157,
|
|
"num_tokens": 2315999.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.392402696609497,
|
|
"epoch": 0.11680799685516932,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999997820685,
|
|
"loss": 6.459,
|
|
"mean_token_accuracy": 0.13655742704868318,
|
|
"num_tokens": 2326695.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.343186712265014,
|
|
"epoch": 0.11736957376312686,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999997226065974,
|
|
"loss": 6.2883,
|
|
"mean_token_accuracy": 0.14464715570211412,
|
|
"num_tokens": 2336925.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.270289373397827,
|
|
"epoch": 0.11793115067108441,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999996559806163,
|
|
"loss": 6.1969,
|
|
"mean_token_accuracy": 0.14032867401838303,
|
|
"num_tokens": 2347431.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.202204418182373,
|
|
"epoch": 0.11849272757904195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999995821905589,
|
|
"loss": 6.3097,
|
|
"mean_token_accuracy": 0.14124003648757935,
|
|
"num_tokens": 2359894.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.309885120391845,
|
|
"epoch": 0.1190543044869995,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999995012364276,
|
|
"loss": 6.3339,
|
|
"mean_token_accuracy": 0.1370592251420021,
|
|
"num_tokens": 2371181.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.306979990005493,
|
|
"epoch": 0.11961588139495703,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999994131182248,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.13838291838765143,
|
|
"num_tokens": 2381531.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.35607795715332,
|
|
"epoch": 0.12017745830291458,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999993178359535,
|
|
"loss": 6.355,
|
|
"mean_token_accuracy": 0.1394966445863247,
|
|
"num_tokens": 2391573.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.261186027526856,
|
|
"epoch": 0.12073903521087213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999992153896166,
|
|
"loss": 6.3136,
|
|
"mean_token_accuracy": 0.139385873824358,
|
|
"num_tokens": 2402822.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.275346755981445,
|
|
"epoch": 0.12130061211882967,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999991057792175,
|
|
"loss": 6.239,
|
|
"mean_token_accuracy": 0.13587720692157745,
|
|
"num_tokens": 2414322.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.344015407562256,
|
|
"epoch": 0.12186218902678722,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999989890047596,
|
|
"loss": 6.4254,
|
|
"mean_token_accuracy": 0.14123198837041856,
|
|
"num_tokens": 2426560.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.3500110626220705,
|
|
"epoch": 0.12242376593474476,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999988650662467,
|
|
"loss": 6.3292,
|
|
"mean_token_accuracy": 0.13752200379967688,
|
|
"num_tokens": 2437723.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.181330251693725,
|
|
"epoch": 0.12298534284270231,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999987339636825,
|
|
"loss": 6.2744,
|
|
"mean_token_accuracy": 0.14474433213472365,
|
|
"num_tokens": 2448497.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.24086971282959,
|
|
"epoch": 0.12354691975065986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999985956970713,
|
|
"loss": 6.1501,
|
|
"mean_token_accuracy": 0.1460134916007519,
|
|
"num_tokens": 2459089.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.194115257263183,
|
|
"epoch": 0.1241084966586174,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999984502664178,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.1463638111948967,
|
|
"num_tokens": 2469882.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.311574697494507,
|
|
"epoch": 0.12467007356657495,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999982976717261,
|
|
"loss": 6.2866,
|
|
"mean_token_accuracy": 0.14146196469664574,
|
|
"num_tokens": 2482120.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.229846334457397,
|
|
"epoch": 0.1252316504745325,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999981379130016,
|
|
"loss": 6.2776,
|
|
"mean_token_accuracy": 0.14120347276329995,
|
|
"num_tokens": 2492626.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.350741004943847,
|
|
"epoch": 0.12579322738249002,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.000499997970990249,
|
|
"loss": 6.3394,
|
|
"mean_token_accuracy": 0.13675267696380616,
|
|
"num_tokens": 2506347.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.1441210269927975,
|
|
"epoch": 0.12635480429044757,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999977969034737,
|
|
"loss": 6.2228,
|
|
"mean_token_accuracy": 0.14602547585964204,
|
|
"num_tokens": 2516584.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.257932376861572,
|
|
"epoch": 0.12691638119840512,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999976156526814,
|
|
"loss": 6.2654,
|
|
"mean_token_accuracy": 0.1448154129087925,
|
|
"num_tokens": 2526731.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.25107250213623,
|
|
"epoch": 0.12747795810636267,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999974272378776,
|
|
"loss": 6.1746,
|
|
"mean_token_accuracy": 0.14796190187335015,
|
|
"num_tokens": 2537180.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.249812936782837,
|
|
"epoch": 0.12803953501432022,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999972316590685,
|
|
"loss": 6.2552,
|
|
"mean_token_accuracy": 0.14051769748330117,
|
|
"num_tokens": 2547617.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.184178209304809,
|
|
"epoch": 0.12860111192227774,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999970289162604,
|
|
"loss": 6.1305,
|
|
"mean_token_accuracy": 0.1504683867096901,
|
|
"num_tokens": 2557743.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.158236503601074,
|
|
"epoch": 0.1291626888302353,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999968190094595,
|
|
"loss": 6.2303,
|
|
"mean_token_accuracy": 0.14085211753845214,
|
|
"num_tokens": 2568351.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.255946779251099,
|
|
"epoch": 0.12972426573819285,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999966019386727,
|
|
"loss": 6.2956,
|
|
"mean_token_accuracy": 0.1466837540268898,
|
|
"num_tokens": 2579703.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.278928565979004,
|
|
"epoch": 0.1302858426461504,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999963777039067,
|
|
"loss": 6.2721,
|
|
"mean_token_accuracy": 0.1395919069647789,
|
|
"num_tokens": 2591197.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.206645822525024,
|
|
"epoch": 0.13084741955410795,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499996146305169,
|
|
"loss": 6.2382,
|
|
"mean_token_accuracy": 0.138199520111084,
|
|
"num_tokens": 2601836.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.127915143966675,
|
|
"epoch": 0.13140899646206547,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999959077424665,
|
|
"loss": 6.1883,
|
|
"mean_token_accuracy": 0.1469881147146225,
|
|
"num_tokens": 2613513.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.19788556098938,
|
|
"epoch": 0.13197057337002302,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999956620158072,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.14186860024929046,
|
|
"num_tokens": 2625246.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.174941778182983,
|
|
"epoch": 0.13253215027798057,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999954091251987,
|
|
"loss": 6.1827,
|
|
"mean_token_accuracy": 0.14362877011299133,
|
|
"num_tokens": 2636375.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.236839866638183,
|
|
"epoch": 0.13309372718593812,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999951490706491,
|
|
"loss": 6.2803,
|
|
"mean_token_accuracy": 0.14121622070670128,
|
|
"num_tokens": 2648586.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.25318398475647,
|
|
"epoch": 0.13365530409389567,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999948818521667,
|
|
"loss": 6.2896,
|
|
"mean_token_accuracy": 0.14876099526882172,
|
|
"num_tokens": 2660847.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.262707948684692,
|
|
"epoch": 0.1342168810018532,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049999460746976,
|
|
"loss": 6.1967,
|
|
"mean_token_accuracy": 0.1488579124212265,
|
|
"num_tokens": 2671160.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.28086223602295,
|
|
"epoch": 0.13477845790981074,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999943259234377,
|
|
"loss": 6.3232,
|
|
"mean_token_accuracy": 0.1395305424928665,
|
|
"num_tokens": 2681622.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.096985816955566,
|
|
"epoch": 0.1353400348177683,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999940372132089,
|
|
"loss": 6.1266,
|
|
"mean_token_accuracy": 0.14814743399620056,
|
|
"num_tokens": 2691503.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.2123407363891605,
|
|
"epoch": 0.13590161172572585,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999937413390826,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.14390229135751725,
|
|
"num_tokens": 2702207.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.2210283279418945,
|
|
"epoch": 0.1364631886336834,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999934383010683,
|
|
"loss": 6.2273,
|
|
"mean_token_accuracy": 0.13937842920422555,
|
|
"num_tokens": 2713178.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.2355101108551025,
|
|
"epoch": 0.13702476554164092,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999931280991757,
|
|
"loss": 6.2215,
|
|
"mean_token_accuracy": 0.15077248811721802,
|
|
"num_tokens": 2723717.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.212197589874267,
|
|
"epoch": 0.13758634244959847,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999928107334146,
|
|
"loss": 6.3009,
|
|
"mean_token_accuracy": 0.14038375541567802,
|
|
"num_tokens": 2735669.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.169046878814697,
|
|
"epoch": 0.13814791935755602,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999924862037952,
|
|
"loss": 6.1964,
|
|
"mean_token_accuracy": 0.14300856739282608,
|
|
"num_tokens": 2746087.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.144366025924683,
|
|
"epoch": 0.13870949626551357,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999921545103278,
|
|
"loss": 6.2061,
|
|
"mean_token_accuracy": 0.14115993231534957,
|
|
"num_tokens": 2757143.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.342315292358398,
|
|
"epoch": 0.1392710731734711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999918156530229,
|
|
"loss": 6.3124,
|
|
"mean_token_accuracy": 0.14043705612421037,
|
|
"num_tokens": 2769340.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.167529439926147,
|
|
"epoch": 0.13983265008142864,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999914696318913,
|
|
"loss": 6.2324,
|
|
"mean_token_accuracy": 0.14253571182489394,
|
|
"num_tokens": 2779514.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.215117454528809,
|
|
"epoch": 0.1403942269893862,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999911164469441,
|
|
"loss": 6.1716,
|
|
"mean_token_accuracy": 0.14638045579195022,
|
|
"num_tokens": 2790801.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.150897598266601,
|
|
"epoch": 0.14095580389734375,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999907560981925,
|
|
"loss": 6.1577,
|
|
"mean_token_accuracy": 0.1422869920730591,
|
|
"num_tokens": 2801082.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.115649127960205,
|
|
"epoch": 0.1415173808053013,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999903885856479,
|
|
"loss": 6.1729,
|
|
"mean_token_accuracy": 0.14438655823469163,
|
|
"num_tokens": 2812719.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.191334629058838,
|
|
"epoch": 0.14207895771325882,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499990013909322,
|
|
"loss": 6.1778,
|
|
"mean_token_accuracy": 0.13971620053052902,
|
|
"num_tokens": 2823766.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.134991407394409,
|
|
"epoch": 0.14264053462121637,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499989632069227,
|
|
"loss": 6.2602,
|
|
"mean_token_accuracy": 0.14011294320225715,
|
|
"num_tokens": 2834801.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.191428804397583,
|
|
"epoch": 0.14320211152917392,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999892430653747,
|
|
"loss": 6.0776,
|
|
"mean_token_accuracy": 0.14458837285637854,
|
|
"num_tokens": 2845769.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.094238376617431,
|
|
"epoch": 0.14376368843713147,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999888468977776,
|
|
"loss": 6.1127,
|
|
"mean_token_accuracy": 0.14914896190166474,
|
|
"num_tokens": 2856001.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.171784067153931,
|
|
"epoch": 0.14432526534508902,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999884435664485,
|
|
"loss": 6.1584,
|
|
"mean_token_accuracy": 0.14499107077717782,
|
|
"num_tokens": 2867703.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.036443662643433,
|
|
"epoch": 0.14488684225304654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999880330714,
|
|
"loss": 6.1071,
|
|
"mean_token_accuracy": 0.14794510155916213,
|
|
"num_tokens": 2878671.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.188154554367065,
|
|
"epoch": 0.1454484191610041,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999876154126453,
|
|
"loss": 6.2189,
|
|
"mean_token_accuracy": 0.139739553630352,
|
|
"num_tokens": 2890137.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.1498771667480465,
|
|
"epoch": 0.14600999606896164,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999871905901977,
|
|
"loss": 6.1234,
|
|
"mean_token_accuracy": 0.1464032292366028,
|
|
"num_tokens": 2900344.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.0827178955078125,
|
|
"epoch": 0.1465715729769192,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999867586040706,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.1437415286898613,
|
|
"num_tokens": 2912270.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.200682878494263,
|
|
"epoch": 0.14713314988487675,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999863194542779,
|
|
"loss": 6.2118,
|
|
"mean_token_accuracy": 0.13623538836836815,
|
|
"num_tokens": 2924677.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.07335467338562,
|
|
"epoch": 0.14769472679283427,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999858731408336,
|
|
"loss": 6.1296,
|
|
"mean_token_accuracy": 0.14736221581697465,
|
|
"num_tokens": 2935794.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.175930118560791,
|
|
"epoch": 0.14825630370079182,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999854196637518,
|
|
"loss": 6.2555,
|
|
"mean_token_accuracy": 0.13842563405632974,
|
|
"num_tokens": 2945958.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.238176393508911,
|
|
"epoch": 0.14881788060874937,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999849590230469,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.14000826627016066,
|
|
"num_tokens": 2957536.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.148218727111816,
|
|
"epoch": 0.14937945751670692,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999844912187336,
|
|
"loss": 6.1913,
|
|
"mean_token_accuracy": 0.14294830784201623,
|
|
"num_tokens": 2967787.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.1945525169372555,
|
|
"epoch": 0.14994103442466447,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499984016250827,
|
|
"loss": 6.2067,
|
|
"mean_token_accuracy": 0.13826904371380805,
|
|
"num_tokens": 2980522.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 5.966804313659668,
|
|
"epoch": 0.150502611332622,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499983534119342,
|
|
"loss": 6.1388,
|
|
"mean_token_accuracy": 0.14656713455915452,
|
|
"num_tokens": 2990497.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.274156188964843,
|
|
"epoch": 0.15106418824057954,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004999830448242941,
|
|
"loss": 6.2332,
|
|
"mean_token_accuracy": 0.14296478927135467,
|
|
"num_tokens": 3002931.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.141962671279908,
|
|
"epoch": 0.1516257651485371,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999825483656986,
|
|
"loss": 6.156,
|
|
"mean_token_accuracy": 0.1505702443420887,
|
|
"num_tokens": 3014137.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.2523428440094,
|
|
"epoch": 0.15218734205649465,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999820447435716,
|
|
"loss": 6.3274,
|
|
"mean_token_accuracy": 0.13458315059542655,
|
|
"num_tokens": 3026145.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.138166666030884,
|
|
"epoch": 0.15274891896445217,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999815339579291,
|
|
"loss": 6.1712,
|
|
"mean_token_accuracy": 0.14355397075414658,
|
|
"num_tokens": 3037068.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.16013355255127,
|
|
"epoch": 0.15331049587240972,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999810160087872,
|
|
"loss": 6.0994,
|
|
"mean_token_accuracy": 0.14831770956516266,
|
|
"num_tokens": 3047836.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.168116474151612,
|
|
"epoch": 0.15387207278036727,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999804908961626,
|
|
"loss": 6.2286,
|
|
"mean_token_accuracy": 0.1443933680653572,
|
|
"num_tokens": 3060309.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.171547555923462,
|
|
"epoch": 0.15443364968832482,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999799586200719,
|
|
"loss": 6.2005,
|
|
"mean_token_accuracy": 0.14509918689727783,
|
|
"num_tokens": 3071789.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.1539019584655765,
|
|
"epoch": 0.15499522659628237,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499979419180532,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.1455280564725399,
|
|
"num_tokens": 3081756.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.111848592758179,
|
|
"epoch": 0.1555568035042399,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999788725775601,
|
|
"loss": 6.2161,
|
|
"mean_token_accuracy": 0.14064385145902633,
|
|
"num_tokens": 3093456.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.234532213211059,
|
|
"epoch": 0.15611838041219744,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999783188111737,
|
|
"loss": 6.1529,
|
|
"mean_token_accuracy": 0.15091142654418946,
|
|
"num_tokens": 3104565.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.103633165359497,
|
|
"epoch": 0.156679957320155,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999777578813904,
|
|
"loss": 6.1579,
|
|
"mean_token_accuracy": 0.14539188742637635,
|
|
"num_tokens": 3115577.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.097013330459594,
|
|
"epoch": 0.15724153422811254,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499977189788228,
|
|
"loss": 6.0538,
|
|
"mean_token_accuracy": 0.1482097752392292,
|
|
"num_tokens": 3126019.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.163146924972534,
|
|
"epoch": 0.1578031111360701,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999766145317046,
|
|
"loss": 6.2181,
|
|
"mean_token_accuracy": 0.13583666682243348,
|
|
"num_tokens": 3136191.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.162729549407959,
|
|
"epoch": 0.15836468804402762,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999760321118385,
|
|
"loss": 6.0858,
|
|
"mean_token_accuracy": 0.14940220788121222,
|
|
"num_tokens": 3147737.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.025310707092285,
|
|
"epoch": 0.15892626495198517,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999754425286483,
|
|
"loss": 6.1533,
|
|
"mean_token_accuracy": 0.1457144483923912,
|
|
"num_tokens": 3158494.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.223312425613403,
|
|
"epoch": 0.15948784185994272,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999748457821529,
|
|
"loss": 6.1982,
|
|
"mean_token_accuracy": 0.14512955993413926,
|
|
"num_tokens": 3170550.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.002134227752686,
|
|
"epoch": 0.16004941876790027,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.000499974241872371,
|
|
"loss": 6.173,
|
|
"mean_token_accuracy": 0.14995696693658828,
|
|
"num_tokens": 3182860.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.145843410491944,
|
|
"epoch": 0.16061099567585782,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999736307993221,
|
|
"loss": 6.1589,
|
|
"mean_token_accuracy": 0.1427552342414856,
|
|
"num_tokens": 3193807.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.033665990829467,
|
|
"epoch": 0.16117257258381534,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999730125630255,
|
|
"loss": 6.0343,
|
|
"mean_token_accuracy": 0.14640598148107528,
|
|
"num_tokens": 3203959.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.114152240753174,
|
|
"epoch": 0.1617341494917729,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999723871635008,
|
|
"loss": 6.05,
|
|
"mean_token_accuracy": 0.15276473239064217,
|
|
"num_tokens": 3215416.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.174462223052979,
|
|
"epoch": 0.16229572639973044,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999717546007681,
|
|
"loss": 6.1968,
|
|
"mean_token_accuracy": 0.13907519057393075,
|
|
"num_tokens": 3226938.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.01826319694519,
|
|
"epoch": 0.162857303307688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999711148748476,
|
|
"loss": 6.0076,
|
|
"mean_token_accuracy": 0.15116169303655624,
|
|
"num_tokens": 3238406.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.0103428840637205,
|
|
"epoch": 0.16341888021564555,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999704679857594,
|
|
"loss": 6.0333,
|
|
"mean_token_accuracy": 0.1464739538729191,
|
|
"num_tokens": 3249695.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.189427709579467,
|
|
"epoch": 0.16398045712360307,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999698139335243,
|
|
"loss": 6.1762,
|
|
"mean_token_accuracy": 0.14912961125373841,
|
|
"num_tokens": 3259656.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.0474467277526855,
|
|
"epoch": 0.16454203403156062,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999691527181632,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.15426421761512757,
|
|
"num_tokens": 3269712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 5.944938468933105,
|
|
"epoch": 0.16510361093951817,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999684843396968,
|
|
"loss": 6.0062,
|
|
"mean_token_accuracy": 0.15657223016023636,
|
|
"num_tokens": 3280343.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.05485725402832,
|
|
"epoch": 0.16566518784747572,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999678087981467,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.15069780349731446,
|
|
"num_tokens": 3291649.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.21270523071289,
|
|
"epoch": 0.16622676475543324,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004999671260935343,
|
|
"loss": 6.2278,
|
|
"mean_token_accuracy": 0.1479203850030899,
|
|
"num_tokens": 3304190.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 5.936612796783447,
|
|
"epoch": 0.1667883416633908,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999664362258814,
|
|
"loss": 5.9433,
|
|
"mean_token_accuracy": 0.1585344895720482,
|
|
"num_tokens": 3313966.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.14134840965271,
|
|
"epoch": 0.16734991857134834,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999657391952099,
|
|
"loss": 6.2044,
|
|
"mean_token_accuracy": 0.14634429141879082,
|
|
"num_tokens": 3326017.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.099699068069458,
|
|
"epoch": 0.1679114954793059,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499965035001542,
|
|
"loss": 6.0878,
|
|
"mean_token_accuracy": 0.1465717777609825,
|
|
"num_tokens": 3338264.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.0834414005279545,
|
|
"epoch": 0.16847307238726345,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999643236449001,
|
|
"loss": 6.1281,
|
|
"mean_token_accuracy": 0.15561570674180986,
|
|
"num_tokens": 3348901.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.077313470840454,
|
|
"epoch": 0.16903464929522097,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999636051253069,
|
|
"loss": 6.0809,
|
|
"mean_token_accuracy": 0.15013315677642822,
|
|
"num_tokens": 3358441.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.141596937179566,
|
|
"epoch": 0.16959622620317852,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999628794427854,
|
|
"loss": 6.1594,
|
|
"mean_token_accuracy": 0.1495223045349121,
|
|
"num_tokens": 3369334.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.033642292022705,
|
|
"epoch": 0.17015780311113607,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999621465973583,
|
|
"loss": 6.1466,
|
|
"mean_token_accuracy": 0.1485290877521038,
|
|
"num_tokens": 3380698.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.292063999176025,
|
|
"epoch": 0.17071938001909362,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999614065890495,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.14258649721741676,
|
|
"num_tokens": 3391061.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.035744714736938,
|
|
"epoch": 0.17128095692705117,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999606594178821,
|
|
"loss": 6.206,
|
|
"mean_token_accuracy": 0.14634663388133048,
|
|
"num_tokens": 3403983.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.211483716964722,
|
|
"epoch": 0.1718425338350087,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049995990508388,
|
|
"loss": 6.137,
|
|
"mean_token_accuracy": 0.14936505407094955,
|
|
"num_tokens": 3413838.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 5.965998554229737,
|
|
"epoch": 0.17240411074296624,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999591435870674,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.1488761007785797,
|
|
"num_tokens": 3423978.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.155382394790649,
|
|
"epoch": 0.1729656876509238,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999583749274684,
|
|
"loss": 6.1435,
|
|
"mean_token_accuracy": 0.15120792090892793,
|
|
"num_tokens": 3433416.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 5.947936916351319,
|
|
"epoch": 0.17352726455888134,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999575991051074,
|
|
"loss": 5.9987,
|
|
"mean_token_accuracy": 0.15397366210818292,
|
|
"num_tokens": 3444983.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.043239402770996,
|
|
"epoch": 0.1740888414668389,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999568161200093,
|
|
"loss": 5.9785,
|
|
"mean_token_accuracy": 0.15082329958677293,
|
|
"num_tokens": 3455808.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 5.976273250579834,
|
|
"epoch": 0.17465041837479642,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999560259721989,
|
|
"loss": 6.1215,
|
|
"mean_token_accuracy": 0.14532301798462868,
|
|
"num_tokens": 3467503.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.260001564025879,
|
|
"epoch": 0.17521199528275397,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999552286617014,
|
|
"loss": 6.326,
|
|
"mean_token_accuracy": 0.1441342644393444,
|
|
"num_tokens": 3479941.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.030442523956299,
|
|
"epoch": 0.17577357219071152,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999544241885421,
|
|
"loss": 6.0042,
|
|
"mean_token_accuracy": 0.15812455415725707,
|
|
"num_tokens": 3491069.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.056136274337769,
|
|
"epoch": 0.17633514909866907,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999536125527467,
|
|
"loss": 6.1824,
|
|
"mean_token_accuracy": 0.14446716159582138,
|
|
"num_tokens": 3502065.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.2176953792572025,
|
|
"epoch": 0.17689672600662662,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499952793754341,
|
|
"loss": 6.1444,
|
|
"mean_token_accuracy": 0.15198023170232772,
|
|
"num_tokens": 3514228.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.030651617050171,
|
|
"epoch": 0.17745830291458414,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999519677933512,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.1505001425743103,
|
|
"num_tokens": 3525801.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.083348560333252,
|
|
"epoch": 0.1780198798225417,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999511346698035,
|
|
"loss": 6.0093,
|
|
"mean_token_accuracy": 0.14821343570947648,
|
|
"num_tokens": 3536431.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 5.9785850048065186,
|
|
"epoch": 0.17858145673049924,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.0004999502943837244,
|
|
"loss": 6.1211,
|
|
"mean_token_accuracy": 0.14956868812441826,
|
|
"num_tokens": 3549098.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.202871322631836,
|
|
"epoch": 0.1791430336384568,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999494469351406,
|
|
"loss": 6.0691,
|
|
"mean_token_accuracy": 0.1480709992349148,
|
|
"num_tokens": 3560532.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 5.9555768966674805,
|
|
"epoch": 0.17970461054641435,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999485923240793,
|
|
"loss": 6.0849,
|
|
"mean_token_accuracy": 0.14840494394302367,
|
|
"num_tokens": 3572175.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.107180643081665,
|
|
"epoch": 0.18026618745437187,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999477305505675,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.16300127431750297,
|
|
"num_tokens": 3582862.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.1141856670379635,
|
|
"epoch": 0.18082776436232942,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999468616146328,
|
|
"loss": 6.1825,
|
|
"mean_token_accuracy": 0.15161287486553193,
|
|
"num_tokens": 3594685.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 5.94605827331543,
|
|
"epoch": 0.18138934127028697,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999459855163026,
|
|
"loss": 5.972,
|
|
"mean_token_accuracy": 0.1625172182917595,
|
|
"num_tokens": 3604847.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.103135251998902,
|
|
"epoch": 0.18195091817824452,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499945102255605,
|
|
"loss": 6.054,
|
|
"mean_token_accuracy": 0.1522398680448532,
|
|
"num_tokens": 3615549.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.004732656478882,
|
|
"epoch": 0.18251249508620204,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999442118325682,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.1601618841290474,
|
|
"num_tokens": 3626300.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.001117134094239,
|
|
"epoch": 0.1830740719941596,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999433142472205,
|
|
"loss": 6.0022,
|
|
"mean_token_accuracy": 0.15320078432559966,
|
|
"num_tokens": 3637832.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.015522909164429,
|
|
"epoch": 0.18363564890211714,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004999424094995902,
|
|
"loss": 6.0363,
|
|
"mean_token_accuracy": 0.14825773611664772,
|
|
"num_tokens": 3649179.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.044634246826172,
|
|
"epoch": 0.1841972258100747,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999414975897066,
|
|
"loss": 6.0829,
|
|
"mean_token_accuracy": 0.14763242304325103,
|
|
"num_tokens": 3660011.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.159467792510986,
|
|
"epoch": 0.18475880271803224,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.0004999405785175983,
|
|
"loss": 6.1561,
|
|
"mean_token_accuracy": 0.14462535828351974,
|
|
"num_tokens": 3672791.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 5.92794132232666,
|
|
"epoch": 0.18532037962598977,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999396522832949,
|
|
"loss": 5.9746,
|
|
"mean_token_accuracy": 0.14504419267177582,
|
|
"num_tokens": 3684709.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 5.973066902160644,
|
|
"epoch": 0.18588195653394732,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999387188868256,
|
|
"loss": 5.9508,
|
|
"mean_token_accuracy": 0.15417686551809312,
|
|
"num_tokens": 3694675.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 5.916463327407837,
|
|
"epoch": 0.18644353344190487,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004999377783282203,
|
|
"loss": 5.9505,
|
|
"mean_token_accuracy": 0.14933737069368364,
|
|
"num_tokens": 3706384.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.128504753112793,
|
|
"epoch": 0.18700511034986242,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999368306075089,
|
|
"loss": 6.0327,
|
|
"mean_token_accuracy": 0.15195935666561128,
|
|
"num_tokens": 3717419.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 5.989669895172119,
|
|
"epoch": 0.18756668725781997,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999358757247215,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.152767513692379,
|
|
"num_tokens": 3727306.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.138838481903076,
|
|
"epoch": 0.1881282641657775,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999349136798886,
|
|
"loss": 6.1893,
|
|
"mean_token_accuracy": 0.14532702267169953,
|
|
"num_tokens": 3739476.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.0092527866363525,
|
|
"epoch": 0.18868984107373504,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999339444730409,
|
|
"loss": 5.9494,
|
|
"mean_token_accuracy": 0.15688171833753586,
|
|
"num_tokens": 3751035.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.019771957397461,
|
|
"epoch": 0.1892514179816926,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999329681042092,
|
|
"loss": 6.0386,
|
|
"mean_token_accuracy": 0.1538560003042221,
|
|
"num_tokens": 3762881.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 5.984057855606079,
|
|
"epoch": 0.18981299488965014,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999319845734243,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.15006775856018068,
|
|
"num_tokens": 3774180.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.981182193756103,
|
|
"epoch": 0.1903745717976077,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999309938807181,
|
|
"loss": 6.0545,
|
|
"mean_token_accuracy": 0.1547319382429123,
|
|
"num_tokens": 3784864.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.1529374599456785,
|
|
"epoch": 0.19093614870556522,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999299960261216,
|
|
"loss": 6.0276,
|
|
"mean_token_accuracy": 0.14776145964860915,
|
|
"num_tokens": 3797693.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.001488113403321,
|
|
"epoch": 0.19149772561352277,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999289910096669,
|
|
"loss": 6.0625,
|
|
"mean_token_accuracy": 0.15112081915140152,
|
|
"num_tokens": 3809379.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 5.932614946365357,
|
|
"epoch": 0.19205930252148032,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999279788313858,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.15991028100252153,
|
|
"num_tokens": 3819473.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.836278581619263,
|
|
"epoch": 0.19262087942943787,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999269594913107,
|
|
"loss": 5.8975,
|
|
"mean_token_accuracy": 0.15740557461977006,
|
|
"num_tokens": 3831037.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.986707925796509,
|
|
"epoch": 0.19318245633739542,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004999259329894739,
|
|
"loss": 6.0239,
|
|
"mean_token_accuracy": 0.15171116292476655,
|
|
"num_tokens": 3841767.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.904497194290161,
|
|
"epoch": 0.19374403324535294,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999248993259081,
|
|
"loss": 5.8524,
|
|
"mean_token_accuracy": 0.1618407890200615,
|
|
"num_tokens": 3851629.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 5.943421697616577,
|
|
"epoch": 0.1943056101533105,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999238585006463,
|
|
"loss": 5.9368,
|
|
"mean_token_accuracy": 0.15554058328270912,
|
|
"num_tokens": 3863247.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.010688257217407,
|
|
"epoch": 0.19486718706126804,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999228105137218,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.15478108823299408,
|
|
"num_tokens": 3873949.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 5.9788285255432125,
|
|
"epoch": 0.1954287639692256,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999217553651676,
|
|
"loss": 6.0231,
|
|
"mean_token_accuracy": 0.1538798376917839,
|
|
"num_tokens": 3884992.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.0841248512268065,
|
|
"epoch": 0.19599034087718312,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999206930550175,
|
|
"loss": 6.1552,
|
|
"mean_token_accuracy": 0.15780816972255707,
|
|
"num_tokens": 3897029.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 5.975784158706665,
|
|
"epoch": 0.19655191778514067,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999196235833054,
|
|
"loss": 6.0106,
|
|
"mean_token_accuracy": 0.14999836683273315,
|
|
"num_tokens": 3909510.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.004339599609375,
|
|
"epoch": 0.19711349469309822,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999185469500651,
|
|
"loss": 5.9054,
|
|
"mean_token_accuracy": 0.15378687232732774,
|
|
"num_tokens": 3920593.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.044984769821167,
|
|
"epoch": 0.19767507160105577,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499917463155331,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.14715591371059417,
|
|
"num_tokens": 3932215.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.002836465835571,
|
|
"epoch": 0.19823664850901332,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999163721991378,
|
|
"loss": 5.9946,
|
|
"mean_token_accuracy": 0.15849560648202896,
|
|
"num_tokens": 3943876.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 5.868329048156738,
|
|
"epoch": 0.19879822541697084,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00049991527408152,
|
|
"loss": 5.99,
|
|
"mean_token_accuracy": 0.15757318139076232,
|
|
"num_tokens": 3954533.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.096402406692505,
|
|
"epoch": 0.1993598023249284,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999141688025127,
|
|
"loss": 6.0397,
|
|
"mean_token_accuracy": 0.1561959594488144,
|
|
"num_tokens": 3965722.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 5.9315564155578615,
|
|
"epoch": 0.19992137923288594,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499913056362151,
|
|
"loss": 5.9636,
|
|
"mean_token_accuracy": 0.15444938093423843,
|
|
"num_tokens": 3976737.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.066930055618286,
|
|
"epoch": 0.2004829561408435,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999119367604703,
|
|
"loss": 6.0435,
|
|
"mean_token_accuracy": 0.15687376260757446,
|
|
"num_tokens": 3986102.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.019561910629273,
|
|
"epoch": 0.20104453304880104,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999108099975064,
|
|
"loss": 6.0286,
|
|
"mean_token_accuracy": 0.15214875042438508,
|
|
"num_tokens": 3996534.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 5.899537181854248,
|
|
"epoch": 0.20160610995675857,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499909676073295,
|
|
"loss": 5.9332,
|
|
"mean_token_accuracy": 0.15285612195730208,
|
|
"num_tokens": 4006947.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.956607484817505,
|
|
"epoch": 0.20216768686471612,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999085349878723,
|
|
"loss": 5.9775,
|
|
"mean_token_accuracy": 0.16392070800065994,
|
|
"num_tokens": 4017723.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 5.945090866088867,
|
|
"epoch": 0.20272926377267367,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999073867412746,
|
|
"loss": 6.0448,
|
|
"mean_token_accuracy": 0.14959224089980125,
|
|
"num_tokens": 4028347.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 5.973555707931519,
|
|
"epoch": 0.20329084068063122,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999062313335385,
|
|
"loss": 5.9107,
|
|
"mean_token_accuracy": 0.15792374908924103,
|
|
"num_tokens": 4039648.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.071758031845093,
|
|
"epoch": 0.20385241758858877,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999050687647008,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.15182322710752488,
|
|
"num_tokens": 4050786.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 5.987163734436035,
|
|
"epoch": 0.2044139944965463,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004999038990347984,
|
|
"loss": 6.0045,
|
|
"mean_token_accuracy": 0.15671864449977874,
|
|
"num_tokens": 4061184.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.081359481811523,
|
|
"epoch": 0.20497557140450384,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999027221438688,
|
|
"loss": 6.1371,
|
|
"mean_token_accuracy": 0.15203218758106232,
|
|
"num_tokens": 4073607.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.913217067718506,
|
|
"epoch": 0.2055371483124614,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499901538091949,
|
|
"loss": 5.9466,
|
|
"mean_token_accuracy": 0.15213279873132707,
|
|
"num_tokens": 4083924.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.989058113098144,
|
|
"epoch": 0.20609872522041894,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999003468790773,
|
|
"loss": 5.9445,
|
|
"mean_token_accuracy": 0.1569296732544899,
|
|
"num_tokens": 4094083.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 5.978657531738281,
|
|
"epoch": 0.2066603021283765,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998991485052911,
|
|
"loss": 5.977,
|
|
"mean_token_accuracy": 0.16102480739355088,
|
|
"num_tokens": 4105124.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.050256776809692,
|
|
"epoch": 0.20722187903633402,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499897942970629,
|
|
"loss": 6.1242,
|
|
"mean_token_accuracy": 0.14630307406187057,
|
|
"num_tokens": 4116792.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.172934484481812,
|
|
"epoch": 0.20778345594429157,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.000499896730275129,
|
|
"loss": 6.1203,
|
|
"mean_token_accuracy": 0.1498411238193512,
|
|
"num_tokens": 4127441.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.002869939804077,
|
|
"epoch": 0.20834503285224912,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00049989551041883,
|
|
"loss": 6.122,
|
|
"mean_token_accuracy": 0.1481037177145481,
|
|
"num_tokens": 4138696.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 5.970435333251953,
|
|
"epoch": 0.20890660976020667,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998942834017707,
|
|
"loss": 5.9747,
|
|
"mean_token_accuracy": 0.15272988379001617,
|
|
"num_tokens": 4151254.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.9465700626373295,
|
|
"epoch": 0.2094681866681642,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998930492239901,
|
|
"loss": 5.9417,
|
|
"mean_token_accuracy": 0.1490399457514286,
|
|
"num_tokens": 4162046.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 5.929416513442993,
|
|
"epoch": 0.21002976357612174,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998918078855277,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.15742434859275817,
|
|
"num_tokens": 4172409.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.905488348007202,
|
|
"epoch": 0.2105913404840793,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004998905593864227,
|
|
"loss": 6.0486,
|
|
"mean_token_accuracy": 0.15691976398229598,
|
|
"num_tokens": 4182949.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.005948495864868,
|
|
"epoch": 0.21115291739203684,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998893037267153,
|
|
"loss": 6.0075,
|
|
"mean_token_accuracy": 0.15736858546733856,
|
|
"num_tokens": 4194164.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.075479507446289,
|
|
"epoch": 0.2117144942999944,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998880409064452,
|
|
"loss": 5.9782,
|
|
"mean_token_accuracy": 0.15652812123298646,
|
|
"num_tokens": 4206056.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.917818641662597,
|
|
"epoch": 0.21227607120795192,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998867709256527,
|
|
"loss": 6.0464,
|
|
"mean_token_accuracy": 0.15186507552862166,
|
|
"num_tokens": 4216660.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 5.961790704727173,
|
|
"epoch": 0.21283764811590947,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499885493784378,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.15845142155885697,
|
|
"num_tokens": 4228495.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.986710071563721,
|
|
"epoch": 0.21339922502386702,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998842094826621,
|
|
"loss": 5.9148,
|
|
"mean_token_accuracy": 0.16144272834062576,
|
|
"num_tokens": 4238560.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.073420858383178,
|
|
"epoch": 0.21396080193182457,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998829180205458,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.14855025336146355,
|
|
"num_tokens": 4250553.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 5.998498582839966,
|
|
"epoch": 0.21452237883978212,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998816193980701,
|
|
"loss": 6.0515,
|
|
"mean_token_accuracy": 0.1510763570666313,
|
|
"num_tokens": 4262050.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.14221158027649,
|
|
"epoch": 0.21508395574773964,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998803136152764,
|
|
"loss": 6.0223,
|
|
"mean_token_accuracy": 0.14946622550487518,
|
|
"num_tokens": 4273019.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 5.92807354927063,
|
|
"epoch": 0.2156455326556972,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998790006722063,
|
|
"loss": 5.8816,
|
|
"mean_token_accuracy": 0.16204874515533446,
|
|
"num_tokens": 4283585.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.8864278316497805,
|
|
"epoch": 0.21620710956365474,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998776805689016,
|
|
"loss": 5.9586,
|
|
"mean_token_accuracy": 0.15603998452425002,
|
|
"num_tokens": 4294905.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.072697687149048,
|
|
"epoch": 0.2167686864716123,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998763533054045,
|
|
"loss": 6.0863,
|
|
"mean_token_accuracy": 0.1533777520060539,
|
|
"num_tokens": 4305926.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.925010728836059,
|
|
"epoch": 0.21733026337956984,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998750188817568,
|
|
"loss": 6.058,
|
|
"mean_token_accuracy": 0.150500325858593,
|
|
"num_tokens": 4318297.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 5.986216497421265,
|
|
"epoch": 0.21789184028752737,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998736772980015,
|
|
"loss": 5.8775,
|
|
"mean_token_accuracy": 0.16325863003730773,
|
|
"num_tokens": 4328795.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.907973289489746,
|
|
"epoch": 0.21845341719548492,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000499872328554181,
|
|
"loss": 5.8886,
|
|
"mean_token_accuracy": 0.1554047629237175,
|
|
"num_tokens": 4340279.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.068842029571533,
|
|
"epoch": 0.21901499410344247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998709726503383,
|
|
"loss": 6.0561,
|
|
"mean_token_accuracy": 0.1501077175140381,
|
|
"num_tokens": 4352157.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 5.955055046081543,
|
|
"epoch": 0.21957657101140002,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998696095865168,
|
|
"loss": 5.897,
|
|
"mean_token_accuracy": 0.15995442271232604,
|
|
"num_tokens": 4361909.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.730102634429931,
|
|
"epoch": 0.22013814791935757,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998682393627595,
|
|
"loss": 5.8254,
|
|
"mean_token_accuracy": 0.15582716166973115,
|
|
"num_tokens": 4372177.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.933818626403808,
|
|
"epoch": 0.2206997248273151,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998668619791104,
|
|
"loss": 5.8732,
|
|
"mean_token_accuracy": 0.1587201938033104,
|
|
"num_tokens": 4382872.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.905340623855591,
|
|
"epoch": 0.22126130173527264,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998654774356131,
|
|
"loss": 5.9699,
|
|
"mean_token_accuracy": 0.15593308657407762,
|
|
"num_tokens": 4393623.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.907887887954712,
|
|
"epoch": 0.2218228786432302,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998640857323118,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.15534867942333222,
|
|
"num_tokens": 4404215.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.064648962020874,
|
|
"epoch": 0.22238445555118774,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998626868692509,
|
|
"loss": 6.1578,
|
|
"mean_token_accuracy": 0.15266190096735954,
|
|
"num_tokens": 4415978.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.978055763244629,
|
|
"epoch": 0.2229460324591453,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998612808464748,
|
|
"loss": 5.9185,
|
|
"mean_token_accuracy": 0.1604282557964325,
|
|
"num_tokens": 4427060.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.944674348831176,
|
|
"epoch": 0.22350760936710282,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998598676640283,
|
|
"loss": 5.9861,
|
|
"mean_token_accuracy": 0.15214295759797097,
|
|
"num_tokens": 4438145.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.08530912399292,
|
|
"epoch": 0.22406918627506037,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998584473219563,
|
|
"loss": 6.0554,
|
|
"mean_token_accuracy": 0.1587221294641495,
|
|
"num_tokens": 4449324.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.903869676589966,
|
|
"epoch": 0.22463076318301792,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998570198203043,
|
|
"loss": 5.7953,
|
|
"mean_token_accuracy": 0.1570117339491844,
|
|
"num_tokens": 4459728.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.88097767829895,
|
|
"epoch": 0.22519234009097547,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998555851591175,
|
|
"loss": 5.9978,
|
|
"mean_token_accuracy": 0.16080355495214463,
|
|
"num_tokens": 4471164.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.0333850383758545,
|
|
"epoch": 0.225753916998933,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004998541433384416,
|
|
"loss": 6.0504,
|
|
"mean_token_accuracy": 0.15572140067815782,
|
|
"num_tokens": 4483349.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.0429106712341305,
|
|
"epoch": 0.22631549390689054,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998526943583226,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.15771206319332123,
|
|
"num_tokens": 4495311.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.924639892578125,
|
|
"epoch": 0.2268770708148481,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998512382188066,
|
|
"loss": 5.9688,
|
|
"mean_token_accuracy": 0.15513758808374406,
|
|
"num_tokens": 4507017.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.992367076873779,
|
|
"epoch": 0.22743864772280564,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998497749199401,
|
|
"loss": 5.9937,
|
|
"mean_token_accuracy": 0.1526365488767624,
|
|
"num_tokens": 4517746.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.032519912719726,
|
|
"epoch": 0.2280002246307632,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998483044617694,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14750580340623856,
|
|
"num_tokens": 4529149.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.030290651321411,
|
|
"epoch": 0.22856180153872072,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998468268443416,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.15775412023067475,
|
|
"num_tokens": 4540630.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.819119691848755,
|
|
"epoch": 0.22912337844667827,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998453420677034,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.15414910539984703,
|
|
"num_tokens": 4552877.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.0394634246826175,
|
|
"epoch": 0.22968495535463582,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998438501319025,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.16143840849399566,
|
|
"num_tokens": 4563634.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.893660259246826,
|
|
"epoch": 0.23024653226259337,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998423510369862,
|
|
"loss": 5.9216,
|
|
"mean_token_accuracy": 0.163277006149292,
|
|
"num_tokens": 4574007.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.921794652938843,
|
|
"epoch": 0.23080810917055092,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998408447830022,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.15314771682024003,
|
|
"num_tokens": 4584146.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.937058544158935,
|
|
"epoch": 0.23136968607850844,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998393313699985,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.15111495107412337,
|
|
"num_tokens": 4594839.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.123587226867675,
|
|
"epoch": 0.231931262986466,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998378107980233,
|
|
"loss": 6.1128,
|
|
"mean_token_accuracy": 0.14634541124105455,
|
|
"num_tokens": 4608229.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.988157129287719,
|
|
"epoch": 0.23249283989442354,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004998362830671249,
|
|
"loss": 5.9118,
|
|
"mean_token_accuracy": 0.15399982333183287,
|
|
"num_tokens": 4619206.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.830771350860596,
|
|
"epoch": 0.2330544168023811,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998347481773522,
|
|
"loss": 5.939,
|
|
"mean_token_accuracy": 0.16280597448349,
|
|
"num_tokens": 4628966.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.950791311264038,
|
|
"epoch": 0.23361599371033864,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998332061287538,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.15719278901815414,
|
|
"num_tokens": 4639935.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.976275014877319,
|
|
"epoch": 0.23417757061829617,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499831656921379,
|
|
"loss": 6.065,
|
|
"mean_token_accuracy": 0.1518533706665039,
|
|
"num_tokens": 4651998.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.062891149520874,
|
|
"epoch": 0.23473914752625372,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499830100555277,
|
|
"loss": 6.0584,
|
|
"mean_token_accuracy": 0.1517246574163437,
|
|
"num_tokens": 4664002.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.9623480319976805,
|
|
"epoch": 0.23530072443421127,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998285370304974,
|
|
"loss": 5.9293,
|
|
"mean_token_accuracy": 0.15818354934453965,
|
|
"num_tokens": 4675343.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.996997594833374,
|
|
"epoch": 0.23586230134216882,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00049982696634709,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.1616687372326851,
|
|
"num_tokens": 4686410.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.936463117599487,
|
|
"epoch": 0.23642387825012637,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998253885051048,
|
|
"loss": 6.0201,
|
|
"mean_token_accuracy": 0.15326433777809143,
|
|
"num_tokens": 4697768.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.100189256668091,
|
|
"epoch": 0.2369854551580839,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499823803504592,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.15419370904564858,
|
|
"num_tokens": 4709933.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.993178224563598,
|
|
"epoch": 0.23754703206604144,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998222113456022,
|
|
"loss": 6.0493,
|
|
"mean_token_accuracy": 0.1489183008670807,
|
|
"num_tokens": 4721385.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.890592288970947,
|
|
"epoch": 0.238108608973999,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998206120281858,
|
|
"loss": 5.8685,
|
|
"mean_token_accuracy": 0.1633332997560501,
|
|
"num_tokens": 4732562.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.884363508224487,
|
|
"epoch": 0.23867018588195654,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499819005552394,
|
|
"loss": 5.8792,
|
|
"mean_token_accuracy": 0.15853570103645326,
|
|
"num_tokens": 4742794.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.837559032440185,
|
|
"epoch": 0.23923176278991407,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004998173919182779,
|
|
"loss": 5.8616,
|
|
"mean_token_accuracy": 0.1604430302977562,
|
|
"num_tokens": 4754903.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.9406506538391115,
|
|
"epoch": 0.23979333969787162,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499815771125889,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.15427519828081132,
|
|
"num_tokens": 4766165.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.9188025951385494,
|
|
"epoch": 0.24035491660582917,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998141431752785,
|
|
"loss": 5.9184,
|
|
"mean_token_accuracy": 0.15893685966730117,
|
|
"num_tokens": 4776551.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.034300327301025,
|
|
"epoch": 0.24091649351378672,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998125080664987,
|
|
"loss": 6.0939,
|
|
"mean_token_accuracy": 0.1525190368294716,
|
|
"num_tokens": 4788344.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.9868241310119625,
|
|
"epoch": 0.24147807042174427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998108657996012,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.15438547730445862,
|
|
"num_tokens": 4799314.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.9253113746643065,
|
|
"epoch": 0.2420396473297018,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998092163746387,
|
|
"loss": 5.9349,
|
|
"mean_token_accuracy": 0.16056873500347138,
|
|
"num_tokens": 4809588.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.8701903343200685,
|
|
"epoch": 0.24260122423765934,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998075597916636,
|
|
"loss": 5.7562,
|
|
"mean_token_accuracy": 0.16604280918836595,
|
|
"num_tokens": 4820076.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.9389283657073975,
|
|
"epoch": 0.2431628011456169,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998058960507286,
|
|
"loss": 6.0367,
|
|
"mean_token_accuracy": 0.15002979561686516,
|
|
"num_tokens": 4831504.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.881774282455444,
|
|
"epoch": 0.24372437805357444,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998042251518866,
|
|
"loss": 5.8802,
|
|
"mean_token_accuracy": 0.15729590505361557,
|
|
"num_tokens": 4842826.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.8496815204620365,
|
|
"epoch": 0.244285954961532,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998025470951908,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.16225429326295854,
|
|
"num_tokens": 4853279.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.957265853881836,
|
|
"epoch": 0.24484753186948952,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998008618806949,
|
|
"loss": 5.9213,
|
|
"mean_token_accuracy": 0.16333475559949875,
|
|
"num_tokens": 4863332.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.962638473510742,
|
|
"epoch": 0.24540910877744707,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997991695084523,
|
|
"loss": 6.0566,
|
|
"mean_token_accuracy": 0.14747042953968048,
|
|
"num_tokens": 4874217.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.0260858058929445,
|
|
"epoch": 0.24597068568540462,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997974699785169,
|
|
"loss": 5.9064,
|
|
"mean_token_accuracy": 0.16339460611343384,
|
|
"num_tokens": 4885322.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.819237565994262,
|
|
"epoch": 0.24653226259336217,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997957632909429,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.15775319337844848,
|
|
"num_tokens": 4895546.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.086778259277343,
|
|
"epoch": 0.24709383950131972,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997940494457846,
|
|
"loss": 6.0564,
|
|
"mean_token_accuracy": 0.1528075724840164,
|
|
"num_tokens": 4906957.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.024942302703858,
|
|
"epoch": 0.24765541640927724,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997923284430967,
|
|
"loss": 5.9929,
|
|
"mean_token_accuracy": 0.14885835349559784,
|
|
"num_tokens": 4917965.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.866191291809082,
|
|
"epoch": 0.2482169933172348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997906002829338,
|
|
"loss": 5.8855,
|
|
"mean_token_accuracy": 0.16118354648351668,
|
|
"num_tokens": 4928585.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.916089773178101,
|
|
"epoch": 0.24877857022519234,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499788864965351,
|
|
"loss": 5.8858,
|
|
"mean_token_accuracy": 0.15575789362192155,
|
|
"num_tokens": 4939818.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.965532827377319,
|
|
"epoch": 0.2493401471331499,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997871224904036,
|
|
"loss": 5.98,
|
|
"mean_token_accuracy": 0.1508565679192543,
|
|
"num_tokens": 4951752.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.827750968933105,
|
|
"epoch": 0.24990172404110744,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997853728581468,
|
|
"loss": 5.8161,
|
|
"mean_token_accuracy": 0.1646944299340248,
|
|
"num_tokens": 4961846.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.95909481048584,
|
|
"epoch": 0.250463300949065,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997836160686368,
|
|
"loss": 5.9583,
|
|
"mean_token_accuracy": 0.15396301597356796,
|
|
"num_tokens": 4973693.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.956462955474853,
|
|
"epoch": 0.25102487785702254,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997818521219291,
|
|
"loss": 5.8866,
|
|
"mean_token_accuracy": 0.1603934332728386,
|
|
"num_tokens": 4986156.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.8751894474029545,
|
|
"epoch": 0.25158645476498004,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997800810180803,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.15617042332887648,
|
|
"num_tokens": 4997615.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.96913776397705,
|
|
"epoch": 0.2521480316729376,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997783027571464,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.1606399178504944,
|
|
"num_tokens": 5007655.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.879551124572754,
|
|
"epoch": 0.25270960858089514,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997765173391841,
|
|
"loss": 5.9554,
|
|
"mean_token_accuracy": 0.1597429096698761,
|
|
"num_tokens": 5018933.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.037764549255371,
|
|
"epoch": 0.2532711854888527,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997747247642505,
|
|
"loss": 5.9753,
|
|
"mean_token_accuracy": 0.15459429025650023,
|
|
"num_tokens": 5030495.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.930814743041992,
|
|
"epoch": 0.25383276239681024,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997729250324023,
|
|
"loss": 6.0208,
|
|
"mean_token_accuracy": 0.152151720225811,
|
|
"num_tokens": 5041553.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.959843635559082,
|
|
"epoch": 0.2543943393047678,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997711181436971,
|
|
"loss": 5.94,
|
|
"mean_token_accuracy": 0.15976212471723555,
|
|
"num_tokens": 5052312.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.988469648361206,
|
|
"epoch": 0.25495591621272534,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997693040981922,
|
|
"loss": 6.1231,
|
|
"mean_token_accuracy": 0.1494268372654915,
|
|
"num_tokens": 5063445.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.01909031867981,
|
|
"epoch": 0.2555174931206829,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997674828959456,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.15913700312376022,
|
|
"num_tokens": 5073052.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.919397306442261,
|
|
"epoch": 0.25607907002864044,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997656545370151,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.15869781970977784,
|
|
"num_tokens": 5084174.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.975394916534424,
|
|
"epoch": 0.256640646936598,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499763819021459,
|
|
"loss": 5.9366,
|
|
"mean_token_accuracy": 0.1589258521795273,
|
|
"num_tokens": 5094106.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.002953243255615,
|
|
"epoch": 0.2572022238445555,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004997619763493357,
|
|
"loss": 6.0269,
|
|
"mean_token_accuracy": 0.15607377290725707,
|
|
"num_tokens": 5106963.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.8494157791137695,
|
|
"epoch": 0.25776380075251304,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.000499760126520704,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15646326541900635,
|
|
"num_tokens": 5119476.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.044357061386108,
|
|
"epoch": 0.2583253776604706,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997582695356225,
|
|
"loss": 6.0626,
|
|
"mean_token_accuracy": 0.1513483703136444,
|
|
"num_tokens": 5132169.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.878989505767822,
|
|
"epoch": 0.25888695456842814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997564053941507,
|
|
"loss": 5.9071,
|
|
"mean_token_accuracy": 0.15743234679102897,
|
|
"num_tokens": 5143354.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.887942600250244,
|
|
"epoch": 0.2594485314763857,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997545340963478,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.15517181158065796,
|
|
"num_tokens": 5154624.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.0336226463317875,
|
|
"epoch": 0.26001010838434324,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997526556422733,
|
|
"loss": 5.8721,
|
|
"mean_token_accuracy": 0.1567656323313713,
|
|
"num_tokens": 5165349.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.863103628158569,
|
|
"epoch": 0.2605716852923008,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004997507700319872,
|
|
"loss": 5.9555,
|
|
"mean_token_accuracy": 0.1557866856455803,
|
|
"num_tokens": 5175874.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.922141408920288,
|
|
"epoch": 0.26113326220025834,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997488772655492,
|
|
"loss": 5.8352,
|
|
"mean_token_accuracy": 0.16336635500192642,
|
|
"num_tokens": 5186591.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.844820261001587,
|
|
"epoch": 0.2616948391082159,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997469773430199,
|
|
"loss": 5.9473,
|
|
"mean_token_accuracy": 0.16148907244205474,
|
|
"num_tokens": 5197307.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.896266222000122,
|
|
"epoch": 0.2622564160161734,
|
|
"grad_norm": 0.87109375,
|
|
"learning_rate": 0.0004997450702644596,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.15877846628427505,
|
|
"num_tokens": 5209868.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.924633741378784,
|
|
"epoch": 0.26281799292413094,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997431560299292,
|
|
"loss": 5.9231,
|
|
"mean_token_accuracy": 0.15989050269126892,
|
|
"num_tokens": 5220365.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.944304752349853,
|
|
"epoch": 0.2633795698320885,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004997412346394894,
|
|
"loss": 5.834,
|
|
"mean_token_accuracy": 0.15482053458690642,
|
|
"num_tokens": 5231575.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.866419935226441,
|
|
"epoch": 0.26394114674004604,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997393060932017,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.15795815736055374,
|
|
"num_tokens": 5241852.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.962919664382935,
|
|
"epoch": 0.2645027236480036,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997373703911273,
|
|
"loss": 5.9739,
|
|
"mean_token_accuracy": 0.15711618214845657,
|
|
"num_tokens": 5254536.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.002066612243652,
|
|
"epoch": 0.26506430055596114,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997354275333277,
|
|
"loss": 5.8842,
|
|
"mean_token_accuracy": 0.15617608428001403,
|
|
"num_tokens": 5264946.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.679558563232422,
|
|
"epoch": 0.2656258774639187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499733477519865,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.15967741459608079,
|
|
"num_tokens": 5275527.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.902612113952637,
|
|
"epoch": 0.26618745437187624,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997315203508013,
|
|
"loss": 5.8837,
|
|
"mean_token_accuracy": 0.15513267517089843,
|
|
"num_tokens": 5285471.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.831973838806152,
|
|
"epoch": 0.2667490312798338,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997295560261988,
|
|
"loss": 5.8057,
|
|
"mean_token_accuracy": 0.15760743468999863,
|
|
"num_tokens": 5295743.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.89382266998291,
|
|
"epoch": 0.26731060818779134,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049972758454612,
|
|
"loss": 5.9519,
|
|
"mean_token_accuracy": 0.15221580266952514,
|
|
"num_tokens": 5307963.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.93057165145874,
|
|
"epoch": 0.26787218509574884,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997256059106279,
|
|
"loss": 5.8382,
|
|
"mean_token_accuracy": 0.16068274080753325,
|
|
"num_tokens": 5318394.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.959908103942871,
|
|
"epoch": 0.2684337620037064,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997236201197853,
|
|
"loss": 6.0647,
|
|
"mean_token_accuracy": 0.14594504833221436,
|
|
"num_tokens": 5331728.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.980408430099487,
|
|
"epoch": 0.26899533891166394,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997216271736554,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.16780572682619094,
|
|
"num_tokens": 5342825.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.926927518844605,
|
|
"epoch": 0.2695569158196215,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997196270723018,
|
|
"loss": 5.8545,
|
|
"mean_token_accuracy": 0.15406033545732498,
|
|
"num_tokens": 5354232.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.896172904968262,
|
|
"epoch": 0.27011849272757904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004997176198157881,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.154250118881464,
|
|
"num_tokens": 5364807.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.911499881744385,
|
|
"epoch": 0.2706800696355366,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997156054041781,
|
|
"loss": 5.9182,
|
|
"mean_token_accuracy": 0.15305136442184447,
|
|
"num_tokens": 5375593.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.901667356491089,
|
|
"epoch": 0.27124164654349414,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997135838375362,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.1642325833439827,
|
|
"num_tokens": 5386740.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.836700773239135,
|
|
"epoch": 0.2718032234514517,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004997115551159267,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.16053027510643006,
|
|
"num_tokens": 5397732.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.038162803649902,
|
|
"epoch": 0.27236480035940924,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499709519239414,
|
|
"loss": 5.913,
|
|
"mean_token_accuracy": 0.15328923463821412,
|
|
"num_tokens": 5409392.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.7375201225280765,
|
|
"epoch": 0.2729263772673668,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997074762080632,
|
|
"loss": 5.8808,
|
|
"mean_token_accuracy": 0.1645394131541252,
|
|
"num_tokens": 5420903.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.848090887069702,
|
|
"epoch": 0.2734879541753243,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499705426021939,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.15687702000141143,
|
|
"num_tokens": 5432631.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.903999853134155,
|
|
"epoch": 0.27404953108328184,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499703368681107,
|
|
"loss": 5.7843,
|
|
"mean_token_accuracy": 0.16448869407176972,
|
|
"num_tokens": 5443463.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.943267393112182,
|
|
"epoch": 0.2746111079912394,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004997013041856326,
|
|
"loss": 6.091,
|
|
"mean_token_accuracy": 0.1532382771372795,
|
|
"num_tokens": 5455903.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.921958017349243,
|
|
"epoch": 0.27517268489919694,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996992325355815,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.15618202090263367,
|
|
"num_tokens": 5467201.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.923684930801391,
|
|
"epoch": 0.2757342618071545,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996971537310198,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.15881394743919372,
|
|
"num_tokens": 5478109.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.954914569854736,
|
|
"epoch": 0.27629583871511204,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004996950677720133,
|
|
"loss": 5.9197,
|
|
"mean_token_accuracy": 0.15350393652915956,
|
|
"num_tokens": 5489621.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.837770414352417,
|
|
"epoch": 0.2768574156230696,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000499692974658629,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.16119124591350556,
|
|
"num_tokens": 5500606.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.917882061004638,
|
|
"epoch": 0.27741899253102714,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996908743909331,
|
|
"loss": 5.8125,
|
|
"mean_token_accuracy": 0.1658737137913704,
|
|
"num_tokens": 5510768.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.814739227294922,
|
|
"epoch": 0.2779805694389847,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996887669689926,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.1627394124865532,
|
|
"num_tokens": 5522210.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.897688150405884,
|
|
"epoch": 0.2785421463469422,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996866523928747,
|
|
"loss": 5.957,
|
|
"mean_token_accuracy": 0.15570937544107438,
|
|
"num_tokens": 5533055.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.033761405944825,
|
|
"epoch": 0.27910372325489974,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996845306626467,
|
|
"loss": 5.9712,
|
|
"mean_token_accuracy": 0.1545345276594162,
|
|
"num_tokens": 5544345.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.881541776657104,
|
|
"epoch": 0.2796653001628573,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996824017783759,
|
|
"loss": 5.8838,
|
|
"mean_token_accuracy": 0.1547561228275299,
|
|
"num_tokens": 5556734.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.915271615982055,
|
|
"epoch": 0.28022687707081484,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996802657401304,
|
|
"loss": 5.9166,
|
|
"mean_token_accuracy": 0.15897395685315133,
|
|
"num_tokens": 5566874.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.96377158164978,
|
|
"epoch": 0.2807884539787724,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996781225479781,
|
|
"loss": 5.9268,
|
|
"mean_token_accuracy": 0.15026624351739884,
|
|
"num_tokens": 5578812.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.955607175827026,
|
|
"epoch": 0.28135003088672994,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996759722019872,
|
|
"loss": 5.971,
|
|
"mean_token_accuracy": 0.1573779821395874,
|
|
"num_tokens": 5590021.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.935986137390136,
|
|
"epoch": 0.2819116077946875,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996738147022262,
|
|
"loss": 5.9927,
|
|
"mean_token_accuracy": 0.1486438363790512,
|
|
"num_tokens": 5600921.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.9097339630126955,
|
|
"epoch": 0.28247318470264504,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996716500487638,
|
|
"loss": 5.8868,
|
|
"mean_token_accuracy": 0.15973623543977739,
|
|
"num_tokens": 5610615.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.794392156600952,
|
|
"epoch": 0.2830347616106026,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499669478241669,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.159597747027874,
|
|
"num_tokens": 5621596.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.034035968780517,
|
|
"epoch": 0.28359633851856014,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996672992810108,
|
|
"loss": 5.8562,
|
|
"mean_token_accuracy": 0.16451989412307738,
|
|
"num_tokens": 5633047.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.8009015083312985,
|
|
"epoch": 0.28415791542651764,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996651131668587,
|
|
"loss": 5.8476,
|
|
"mean_token_accuracy": 0.15795179605484008,
|
|
"num_tokens": 5644970.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.8380271911621096,
|
|
"epoch": 0.2847194923344752,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996629198992823,
|
|
"loss": 5.9632,
|
|
"mean_token_accuracy": 0.15440421998500825,
|
|
"num_tokens": 5656631.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.936119413375854,
|
|
"epoch": 0.28528106924243274,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004996607194783513,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.1549352765083313,
|
|
"num_tokens": 5668808.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.823132276535034,
|
|
"epoch": 0.2858426461503903,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996585119041359,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.1564148411154747,
|
|
"num_tokens": 5679493.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.972305202484131,
|
|
"epoch": 0.28640422305834784,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996562971767063,
|
|
"loss": 5.8787,
|
|
"mean_token_accuracy": 0.16313901394605637,
|
|
"num_tokens": 5689879.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.90954475402832,
|
|
"epoch": 0.2869657999663054,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499654075296133,
|
|
"loss": 5.9669,
|
|
"mean_token_accuracy": 0.15989068448543547,
|
|
"num_tokens": 5699934.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.840920352935791,
|
|
"epoch": 0.28752737687426294,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499651846262487,
|
|
"loss": 5.8848,
|
|
"mean_token_accuracy": 0.16583120375871657,
|
|
"num_tokens": 5710171.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.9403012752532955,
|
|
"epoch": 0.2880889537822205,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996496100758389,
|
|
"loss": 5.8924,
|
|
"mean_token_accuracy": 0.15079000890254973,
|
|
"num_tokens": 5721190.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 6.004739475250244,
|
|
"epoch": 0.28865053069017804,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004996473667362604,
|
|
"loss": 5.9997,
|
|
"mean_token_accuracy": 0.15434087961912155,
|
|
"num_tokens": 5733706.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.847912883758545,
|
|
"epoch": 0.28921210759813554,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996451162438224,
|
|
"loss": 5.9651,
|
|
"mean_token_accuracy": 0.16153858602046967,
|
|
"num_tokens": 5745712.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.814180088043213,
|
|
"epoch": 0.2897736845060931,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996428585985967,
|
|
"loss": 5.7713,
|
|
"mean_token_accuracy": 0.17209184318780898,
|
|
"num_tokens": 5757915.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.8850490093231205,
|
|
"epoch": 0.29033526141405064,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996405938006553,
|
|
"loss": 5.9153,
|
|
"mean_token_accuracy": 0.162559674680233,
|
|
"num_tokens": 5768788.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.906909847259522,
|
|
"epoch": 0.2908968383220082,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996383218500703,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.15892737954854966,
|
|
"num_tokens": 5779806.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.798295259475708,
|
|
"epoch": 0.29145841522996574,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499636042746914,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.15552390217781067,
|
|
"num_tokens": 5790177.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.888185977935791,
|
|
"epoch": 0.2920199921379233,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499633756491259,
|
|
"loss": 5.8386,
|
|
"mean_token_accuracy": 0.16393716782331466,
|
|
"num_tokens": 5800251.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.911457777023315,
|
|
"epoch": 0.29258156904588084,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996314630831781,
|
|
"loss": 5.9226,
|
|
"mean_token_accuracy": 0.16139961034059525,
|
|
"num_tokens": 5812210.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.936538457870483,
|
|
"epoch": 0.2931431459538384,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996291625227443,
|
|
"loss": 5.9052,
|
|
"mean_token_accuracy": 0.16226045042276382,
|
|
"num_tokens": 5823280.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.9634246826171875,
|
|
"epoch": 0.29370472286179594,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996268548100307,
|
|
"loss": 5.9836,
|
|
"mean_token_accuracy": 0.15235772579908372,
|
|
"num_tokens": 5835076.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.800026893615723,
|
|
"epoch": 0.2942662997697535,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499624539945111,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.16759044528007508,
|
|
"num_tokens": 5845376.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.827654123306274,
|
|
"epoch": 0.294827876677711,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996222179280589,
|
|
"loss": 5.8235,
|
|
"mean_token_accuracy": 0.1543615683913231,
|
|
"num_tokens": 5857124.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.908602380752564,
|
|
"epoch": 0.29538945358566854,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996198887589481,
|
|
"loss": 5.9194,
|
|
"mean_token_accuracy": 0.15195261538028718,
|
|
"num_tokens": 5868681.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.923360443115234,
|
|
"epoch": 0.2959510304936261,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996175524378531,
|
|
"loss": 5.9016,
|
|
"mean_token_accuracy": 0.1616549476981163,
|
|
"num_tokens": 5880532.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.887218236923218,
|
|
"epoch": 0.29651260740158364,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499615208964848,
|
|
"loss": 5.8615,
|
|
"mean_token_accuracy": 0.1611190915107727,
|
|
"num_tokens": 5891582.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.891259670257568,
|
|
"epoch": 0.2970741843095412,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996128583400077,
|
|
"loss": 5.8643,
|
|
"mean_token_accuracy": 0.15494512170553207,
|
|
"num_tokens": 5903543.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.823057651519775,
|
|
"epoch": 0.29763576121749874,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996105005634066,
|
|
"loss": 5.8263,
|
|
"mean_token_accuracy": 0.16598099768161773,
|
|
"num_tokens": 5913140.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.846201181411743,
|
|
"epoch": 0.2981973381254563,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996081356351202,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.16204901039600372,
|
|
"num_tokens": 5924010.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.89202766418457,
|
|
"epoch": 0.29875891503341384,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996057635552237,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1546384647488594,
|
|
"num_tokens": 5936246.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.920505714416504,
|
|
"epoch": 0.2993204919413714,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996033843237925,
|
|
"loss": 5.8988,
|
|
"mean_token_accuracy": 0.1529396116733551,
|
|
"num_tokens": 5947594.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.925133943557739,
|
|
"epoch": 0.29988206884932894,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996009979409025,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.1516793191432953,
|
|
"num_tokens": 5957660.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.700359630584717,
|
|
"epoch": 0.30044364575728644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995986044066295,
|
|
"loss": 5.6562,
|
|
"mean_token_accuracy": 0.16879596710205078,
|
|
"num_tokens": 5968881.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.853354215621948,
|
|
"epoch": 0.301005222665244,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00049959620372105,
|
|
"loss": 5.827,
|
|
"mean_token_accuracy": 0.1607290267944336,
|
|
"num_tokens": 5980032.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.761854076385498,
|
|
"epoch": 0.30156679957320154,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004995937958842401,
|
|
"loss": 5.8271,
|
|
"mean_token_accuracy": 0.16057847291231156,
|
|
"num_tokens": 5991781.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.842853689193726,
|
|
"epoch": 0.3021283764811591,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995913808962767,
|
|
"loss": 5.8726,
|
|
"mean_token_accuracy": 0.15679309368133545,
|
|
"num_tokens": 6002303.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.955978202819824,
|
|
"epoch": 0.30268995338911664,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004995889587572366,
|
|
"loss": 5.9421,
|
|
"mean_token_accuracy": 0.16047051846981047,
|
|
"num_tokens": 6011523.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.921958112716675,
|
|
"epoch": 0.3032515302970742,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499586529467197,
|
|
"loss": 5.7573,
|
|
"mean_token_accuracy": 0.1624143198132515,
|
|
"num_tokens": 6022169.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.688100337982178,
|
|
"epoch": 0.30381310720503174,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004995840930262351,
|
|
"loss": 5.8048,
|
|
"mean_token_accuracy": 0.1632087327539921,
|
|
"num_tokens": 6033393.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.892455244064331,
|
|
"epoch": 0.3043746841129893,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995816494344287,
|
|
"loss": 5.8762,
|
|
"mean_token_accuracy": 0.15626945048570634,
|
|
"num_tokens": 6045365.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.877195835113525,
|
|
"epoch": 0.30493626102094684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995791986918554,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.16077566295862197,
|
|
"num_tokens": 6057482.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.91087236404419,
|
|
"epoch": 0.30549783792890434,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995767407985933,
|
|
"loss": 5.8045,
|
|
"mean_token_accuracy": 0.16352560371160507,
|
|
"num_tokens": 6068194.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.8684210777282715,
|
|
"epoch": 0.3060594148368619,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995742757547207,
|
|
"loss": 5.8676,
|
|
"mean_token_accuracy": 0.16073331981897354,
|
|
"num_tokens": 6080540.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.772074127197266,
|
|
"epoch": 0.30662099174481944,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499571803560316,
|
|
"loss": 5.9062,
|
|
"mean_token_accuracy": 0.16154931038618087,
|
|
"num_tokens": 6092464.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.9210954189300535,
|
|
"epoch": 0.307182568652777,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995693242154581,
|
|
"loss": 5.8483,
|
|
"mean_token_accuracy": 0.16159511357545853,
|
|
"num_tokens": 6103242.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.8642387866973875,
|
|
"epoch": 0.30774414556073454,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995668377202258,
|
|
"loss": 5.8995,
|
|
"mean_token_accuracy": 0.16059732884168626,
|
|
"num_tokens": 6116383.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.8038359642028805,
|
|
"epoch": 0.3083057224686921,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995643440746982,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.17047392278909684,
|
|
"num_tokens": 6126883.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.845919179916382,
|
|
"epoch": 0.30886729937664964,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995618432789548,
|
|
"loss": 5.8948,
|
|
"mean_token_accuracy": 0.15591834336519242,
|
|
"num_tokens": 6139613.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.912436485290527,
|
|
"epoch": 0.3094288762846072,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995593353330753,
|
|
"loss": 5.9525,
|
|
"mean_token_accuracy": 0.15195179283618926,
|
|
"num_tokens": 6151950.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.8443773746490475,
|
|
"epoch": 0.30999045319256474,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004995568202371393,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.16946211010217666,
|
|
"num_tokens": 6161563.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.733523893356323,
|
|
"epoch": 0.3105520301005223,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995542979912272,
|
|
"loss": 5.7569,
|
|
"mean_token_accuracy": 0.16979626566171646,
|
|
"num_tokens": 6170966.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.8455491065979,
|
|
"epoch": 0.3111136070084798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004995517685954192,
|
|
"loss": 5.8253,
|
|
"mean_token_accuracy": 0.1628107637166977,
|
|
"num_tokens": 6182563.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.925236988067627,
|
|
"epoch": 0.31167518391643734,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004995492320497958,
|
|
"loss": 5.942,
|
|
"mean_token_accuracy": 0.15330271273851395,
|
|
"num_tokens": 6194495.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.890429449081421,
|
|
"epoch": 0.3122367608243949,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995466883544376,
|
|
"loss": 5.8378,
|
|
"mean_token_accuracy": 0.15787812322378159,
|
|
"num_tokens": 6206594.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.852018165588379,
|
|
"epoch": 0.31279833773235244,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995441375094258,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.15727385357022286,
|
|
"num_tokens": 6218371.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.92617712020874,
|
|
"epoch": 0.31335991464031,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995415795148417,
|
|
"loss": 5.792,
|
|
"mean_token_accuracy": 0.16471333503723146,
|
|
"num_tokens": 6228723.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.894465827941895,
|
|
"epoch": 0.31392149154826754,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995390143707665,
|
|
"loss": 5.9859,
|
|
"mean_token_accuracy": 0.16086607724428176,
|
|
"num_tokens": 6240535.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.770377111434937,
|
|
"epoch": 0.3144830684562251,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995364420772821,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.16809894442558287,
|
|
"num_tokens": 6250643.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.803590869903564,
|
|
"epoch": 0.31504464536418264,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004995338626344702,
|
|
"loss": 5.811,
|
|
"mean_token_accuracy": 0.15963360369205476,
|
|
"num_tokens": 6259569.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.849584341049194,
|
|
"epoch": 0.3156062222721402,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499531276042413,
|
|
"loss": 5.9635,
|
|
"mean_token_accuracy": 0.16318879276514053,
|
|
"num_tokens": 6271108.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.959302282333374,
|
|
"epoch": 0.31616779918009774,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995286823011929,
|
|
"loss": 5.7944,
|
|
"mean_token_accuracy": 0.1569117486476898,
|
|
"num_tokens": 6282352.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.800611162185669,
|
|
"epoch": 0.31672937608805524,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995260814108926,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.15762576460838318,
|
|
"num_tokens": 6294946.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.787460851669311,
|
|
"epoch": 0.3172909529960128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995234733715947,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.1648264065384865,
|
|
"num_tokens": 6305552.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.852634286880493,
|
|
"epoch": 0.31785252990397034,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995208581833824,
|
|
"loss": 5.7964,
|
|
"mean_token_accuracy": 0.17010432332754136,
|
|
"num_tokens": 6315815.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.810712432861328,
|
|
"epoch": 0.3184141068119279,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004995182358463388,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.16378075629472733,
|
|
"num_tokens": 6327384.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.902743816375732,
|
|
"epoch": 0.31897568371988544,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995156063605475,
|
|
"loss": 5.8133,
|
|
"mean_token_accuracy": 0.156479349732399,
|
|
"num_tokens": 6338083.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.93860764503479,
|
|
"epoch": 0.319537260627843,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995129697260922,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.16261689811944963,
|
|
"num_tokens": 6349058.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.752696514129639,
|
|
"epoch": 0.32009883753580054,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995103259430569,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.16424888297915458,
|
|
"num_tokens": 6359655.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.962045001983642,
|
|
"epoch": 0.3206604144437581,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004995076750115258,
|
|
"loss": 5.9625,
|
|
"mean_token_accuracy": 0.1578860342502594,
|
|
"num_tokens": 6372088.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.874738883972168,
|
|
"epoch": 0.32122199135171564,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995050169315832,
|
|
"loss": 5.8723,
|
|
"mean_token_accuracy": 0.15489131957292557,
|
|
"num_tokens": 6382946.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.825060510635376,
|
|
"epoch": 0.32178356825967314,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995023517033138,
|
|
"loss": 5.8555,
|
|
"mean_token_accuracy": 0.15830326005816459,
|
|
"num_tokens": 6392591.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.798574829101563,
|
|
"epoch": 0.3223451451676307,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994996793268024,
|
|
"loss": 5.8013,
|
|
"mean_token_accuracy": 0.16411383152008058,
|
|
"num_tokens": 6403159.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.871509552001953,
|
|
"epoch": 0.32290672207558824,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004994969998021342,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.16091817617416382,
|
|
"num_tokens": 6414232.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.89113826751709,
|
|
"epoch": 0.3234682989835458,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994943131293944,
|
|
"loss": 5.8018,
|
|
"mean_token_accuracy": 0.17012230753898622,
|
|
"num_tokens": 6425762.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.764307022094727,
|
|
"epoch": 0.32402987589150334,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004994916193086687,
|
|
"loss": 5.8535,
|
|
"mean_token_accuracy": 0.15552848875522612,
|
|
"num_tokens": 6439077.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.911887264251709,
|
|
"epoch": 0.3245914527994609,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994889183400428,
|
|
"loss": 5.9207,
|
|
"mean_token_accuracy": 0.15717577636241914,
|
|
"num_tokens": 6450425.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.864399003982544,
|
|
"epoch": 0.32515302970741844,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004994862102236025,
|
|
"loss": 5.8702,
|
|
"mean_token_accuracy": 0.15890682712197304,
|
|
"num_tokens": 6461347.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.929317331314087,
|
|
"epoch": 0.325714606615376,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994834949594342,
|
|
"loss": 5.8569,
|
|
"mean_token_accuracy": 0.16072623133659364,
|
|
"num_tokens": 6472428.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.843264627456665,
|
|
"epoch": 0.32627618352333354,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994807725476246,
|
|
"loss": 5.8215,
|
|
"mean_token_accuracy": 0.16909091621637345,
|
|
"num_tokens": 6483393.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.799573183059692,
|
|
"epoch": 0.3268377604312911,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994780429882599,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.16213589757680893,
|
|
"num_tokens": 6493520.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.797100687026978,
|
|
"epoch": 0.3273993373392486,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004994753062814274,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.17201152443885803,
|
|
"num_tokens": 6505282.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.936969232559204,
|
|
"epoch": 0.32796091424720614,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004994725624272139,
|
|
"loss": 5.9204,
|
|
"mean_token_accuracy": 0.16258904635906218,
|
|
"num_tokens": 6516808.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.8536591053009035,
|
|
"epoch": 0.3285224911551637,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994698114257071,
|
|
"loss": 5.8889,
|
|
"mean_token_accuracy": 0.15758193880319596,
|
|
"num_tokens": 6529184.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.807791328430175,
|
|
"epoch": 0.32908406806312124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994670532769944,
|
|
"loss": 5.714,
|
|
"mean_token_accuracy": 0.17135922312736512,
|
|
"num_tokens": 6539909.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.777865743637085,
|
|
"epoch": 0.3296456449710788,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994642879811637,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.16615391075611113,
|
|
"num_tokens": 6550870.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.783542823791504,
|
|
"epoch": 0.33020722187903634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499461515538303,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.1643565073609352,
|
|
"num_tokens": 6561784.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.812904691696167,
|
|
"epoch": 0.3307687987869939,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994587359485006,
|
|
"loss": 5.7965,
|
|
"mean_token_accuracy": 0.16411405503749849,
|
|
"num_tokens": 6573422.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.899852323532104,
|
|
"epoch": 0.33133037569495144,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000499455949211845,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.16602167785167693,
|
|
"num_tokens": 6584565.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.879082441329956,
|
|
"epoch": 0.331891952602909,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004994531553284248,
|
|
"loss": 5.7735,
|
|
"mean_token_accuracy": 0.16534640789031982,
|
|
"num_tokens": 6594238.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.761241102218628,
|
|
"epoch": 0.3324535295108665,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994503542983293,
|
|
"loss": 5.8393,
|
|
"mean_token_accuracy": 0.15874847620725632,
|
|
"num_tokens": 6606309.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.942394256591797,
|
|
"epoch": 0.33301510641882404,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004994475461216472,
|
|
"loss": 5.9289,
|
|
"mean_token_accuracy": 0.15209423899650573,
|
|
"num_tokens": 6617916.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.823106193542481,
|
|
"epoch": 0.3335766833267816,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994447307984684,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.1635408341884613,
|
|
"num_tokens": 6627951.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.82645468711853,
|
|
"epoch": 0.33413826023473914,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994419083288823,
|
|
"loss": 5.8445,
|
|
"mean_token_accuracy": 0.16017935127019883,
|
|
"num_tokens": 6639285.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.8130076885223385,
|
|
"epoch": 0.3346998371426967,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994390787129787,
|
|
"loss": 5.7106,
|
|
"mean_token_accuracy": 0.16786744594573974,
|
|
"num_tokens": 6649973.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.691775798797607,
|
|
"epoch": 0.33526141405065424,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994362419508478,
|
|
"loss": 5.7358,
|
|
"mean_token_accuracy": 0.16457985043525697,
|
|
"num_tokens": 6660625.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.848007583618164,
|
|
"epoch": 0.3358229909586118,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00049943339804258,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.15529035329818724,
|
|
"num_tokens": 6673191.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.920690488815308,
|
|
"epoch": 0.33638456786656934,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994305469882657,
|
|
"loss": 5.8128,
|
|
"mean_token_accuracy": 0.16549630016088485,
|
|
"num_tokens": 6683993.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.748003721237183,
|
|
"epoch": 0.3369461447745269,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994276887879957,
|
|
"loss": 5.8422,
|
|
"mean_token_accuracy": 0.16537389457225798,
|
|
"num_tokens": 6694881.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.3369461447745269,
|
|
"eval_entropy": 5.695829511641964,
|
|
"eval_loss": 5.859601020812988,
|
|
"eval_mean_token_accuracy": 0.16699215644086057,
|
|
"eval_num_tokens": 6694881.0,
|
|
"eval_runtime": 23.9604,
|
|
"eval_samples_per_second": 1294.343,
|
|
"eval_steps_per_second": 161.809,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.886764144897461,
|
|
"epoch": 0.33750772168248444,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994248234418611,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.15897639989852905,
|
|
"num_tokens": 6706648.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.846153974533081,
|
|
"epoch": 0.33806929859044194,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499421950949953,
|
|
"loss": 5.8371,
|
|
"mean_token_accuracy": 0.16358864456415176,
|
|
"num_tokens": 6716858.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.733007431030273,
|
|
"epoch": 0.3386308754983995,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000499419071312363,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.16296664178371428,
|
|
"num_tokens": 6726558.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.921378755569458,
|
|
"epoch": 0.33919245240635704,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994161845291828,
|
|
"loss": 5.8037,
|
|
"mean_token_accuracy": 0.16026717722415923,
|
|
"num_tokens": 6737819.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.825274991989136,
|
|
"epoch": 0.3397540293143146,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994132906005041,
|
|
"loss": 5.7366,
|
|
"mean_token_accuracy": 0.16748765707015992,
|
|
"num_tokens": 6748593.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.6835109233856205,
|
|
"epoch": 0.34031560622227214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004994103895264193,
|
|
"loss": 5.8519,
|
|
"mean_token_accuracy": 0.15417855679988862,
|
|
"num_tokens": 6760631.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.8887598514556885,
|
|
"epoch": 0.3408771831302297,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994074813070207,
|
|
"loss": 5.7667,
|
|
"mean_token_accuracy": 0.15880861431360244,
|
|
"num_tokens": 6772318.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.731730842590332,
|
|
"epoch": 0.34143876003818724,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004994045659424007,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.16396609246730803,
|
|
"num_tokens": 6782684.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.828501892089844,
|
|
"epoch": 0.3420003369461448,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994016434326524,
|
|
"loss": 5.6815,
|
|
"mean_token_accuracy": 0.16565727740526198,
|
|
"num_tokens": 6793895.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.740383768081665,
|
|
"epoch": 0.34256191385410234,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993987137778687,
|
|
"loss": 5.749,
|
|
"mean_token_accuracy": 0.16589704751968384,
|
|
"num_tokens": 6804794.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.889779853820801,
|
|
"epoch": 0.3431234907620599,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499395776978143,
|
|
"loss": 5.8785,
|
|
"mean_token_accuracy": 0.15585301518440248,
|
|
"num_tokens": 6815976.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.907194375991821,
|
|
"epoch": 0.3436850676700174,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993928330335686,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.15648076683282852,
|
|
"num_tokens": 6828027.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.8209069728851315,
|
|
"epoch": 0.34424664457797494,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993898819442395,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.1570139303803444,
|
|
"num_tokens": 6839195.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.644024229049682,
|
|
"epoch": 0.3448082214859325,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993869237102494,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.15853152871131898,
|
|
"num_tokens": 6851731.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.848816585540772,
|
|
"epoch": 0.34536979839389004,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004993839583316927,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.1687858909368515,
|
|
"num_tokens": 6862916.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.948011064529419,
|
|
"epoch": 0.3459313753018476,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993809858086638,
|
|
"loss": 5.9359,
|
|
"mean_token_accuracy": 0.15469270795583726,
|
|
"num_tokens": 6876003.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.8251800537109375,
|
|
"epoch": 0.34649295220980514,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004993780061412571,
|
|
"loss": 5.9036,
|
|
"mean_token_accuracy": 0.161135134100914,
|
|
"num_tokens": 6886040.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.870102119445801,
|
|
"epoch": 0.3470545291177627,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004993750193295678,
|
|
"loss": 5.8079,
|
|
"mean_token_accuracy": 0.16270331144332886,
|
|
"num_tokens": 6896758.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.8884580612182615,
|
|
"epoch": 0.34761610602572024,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993720253736909,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.16169939935207367,
|
|
"num_tokens": 6907287.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.817321062088013,
|
|
"epoch": 0.3481776829336778,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993690242737216,
|
|
"loss": 5.8719,
|
|
"mean_token_accuracy": 0.15542412102222442,
|
|
"num_tokens": 6918992.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.967472648620605,
|
|
"epoch": 0.3487392598416353,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993660160297555,
|
|
"loss": 5.8874,
|
|
"mean_token_accuracy": 0.15584431886672973,
|
|
"num_tokens": 6931493.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.80349440574646,
|
|
"epoch": 0.34930083674959284,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993630006418885,
|
|
"loss": 5.7052,
|
|
"mean_token_accuracy": 0.1646087646484375,
|
|
"num_tokens": 6941807.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.866411018371582,
|
|
"epoch": 0.3498624136575504,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993599781102166,
|
|
"loss": 5.9027,
|
|
"mean_token_accuracy": 0.1581380099058151,
|
|
"num_tokens": 6953436.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 6.0376232147216795,
|
|
"epoch": 0.35042399056550794,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993569484348359,
|
|
"loss": 6.0279,
|
|
"mean_token_accuracy": 0.15094916820526122,
|
|
"num_tokens": 6965247.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.8442713737487795,
|
|
"epoch": 0.3509855674734655,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993539116158429,
|
|
"loss": 5.8054,
|
|
"mean_token_accuracy": 0.1681532084941864,
|
|
"num_tokens": 6976605.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.818090486526489,
|
|
"epoch": 0.35154714438142304,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993508676533346,
|
|
"loss": 5.7544,
|
|
"mean_token_accuracy": 0.17177048474550247,
|
|
"num_tokens": 6986205.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.745467042922973,
|
|
"epoch": 0.3521087212893806,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993478165474074,
|
|
"loss": 5.723,
|
|
"mean_token_accuracy": 0.16777762919664382,
|
|
"num_tokens": 6997699.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.714036464691162,
|
|
"epoch": 0.35267029819733814,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993447582981588,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.16031949520111083,
|
|
"num_tokens": 7008968.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.880342483520508,
|
|
"epoch": 0.3532318751052957,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000499341692905686,
|
|
"loss": 5.7753,
|
|
"mean_token_accuracy": 0.16022212356328963,
|
|
"num_tokens": 7020633.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.8059327602386475,
|
|
"epoch": 0.35379345201325324,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004993386203700868,
|
|
"loss": 5.6907,
|
|
"mean_token_accuracy": 0.17187599688768387,
|
|
"num_tokens": 7031187.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.800093936920166,
|
|
"epoch": 0.35435502892121074,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993355406914589,
|
|
"loss": 5.9237,
|
|
"mean_token_accuracy": 0.15861159414052964,
|
|
"num_tokens": 7042662.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.887630367279053,
|
|
"epoch": 0.3549166058291683,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993324538699003,
|
|
"loss": 5.905,
|
|
"mean_token_accuracy": 0.16245097368955613,
|
|
"num_tokens": 7054297.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.9388939380645756,
|
|
"epoch": 0.35547818273712584,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993293599055094,
|
|
"loss": 5.7689,
|
|
"mean_token_accuracy": 0.16640488058328629,
|
|
"num_tokens": 7064961.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.868810749053955,
|
|
"epoch": 0.3560397596450834,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993262587983848,
|
|
"loss": 5.9018,
|
|
"mean_token_accuracy": 0.1621847480535507,
|
|
"num_tokens": 7076857.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.81254096031189,
|
|
"epoch": 0.35660133655304094,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499323150548625,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.16407814472913743,
|
|
"num_tokens": 7088926.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.748864269256591,
|
|
"epoch": 0.3571629134609985,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004993200351563291,
|
|
"loss": 5.7056,
|
|
"mean_token_accuracy": 0.1668672129511833,
|
|
"num_tokens": 7099478.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.79847526550293,
|
|
"epoch": 0.35772449036895604,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993169126215962,
|
|
"loss": 5.766,
|
|
"mean_token_accuracy": 0.16984602808952332,
|
|
"num_tokens": 7111776.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.915297222137451,
|
|
"epoch": 0.3582860672769136,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004993137829445259,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.16224229335784912,
|
|
"num_tokens": 7123084.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.777560901641846,
|
|
"epoch": 0.35884764418487114,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004993106461252177,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.1651140809059143,
|
|
"num_tokens": 7134973.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.830048608779907,
|
|
"epoch": 0.3594092210928287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004993075021637716,
|
|
"loss": 5.8438,
|
|
"mean_token_accuracy": 0.15864692032337188,
|
|
"num_tokens": 7147227.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.857310438156128,
|
|
"epoch": 0.3599707980007862,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004993043510602875,
|
|
"loss": 5.8127,
|
|
"mean_token_accuracy": 0.16189404875040053,
|
|
"num_tokens": 7158201.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.697170543670654,
|
|
"epoch": 0.36053237490874374,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000499301192814866,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.16861216574907303,
|
|
"num_tokens": 7168909.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.923234319686889,
|
|
"epoch": 0.3610939518167013,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992980274276074,
|
|
"loss": 5.8843,
|
|
"mean_token_accuracy": 0.1593233212828636,
|
|
"num_tokens": 7179877.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.872871541976929,
|
|
"epoch": 0.36165552872465884,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992948548986128,
|
|
"loss": 5.7948,
|
|
"mean_token_accuracy": 0.1708411380648613,
|
|
"num_tokens": 7190823.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.736656856536865,
|
|
"epoch": 0.3622171056326164,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992916752279829,
|
|
"loss": 5.7208,
|
|
"mean_token_accuracy": 0.16443556696176528,
|
|
"num_tokens": 7201700.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.83797173500061,
|
|
"epoch": 0.36277868254057394,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499288488415819,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.16873592883348465,
|
|
"num_tokens": 7213618.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.945992469787598,
|
|
"epoch": 0.3633402594485315,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004992852944622229,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.16125134378671646,
|
|
"num_tokens": 7226207.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.766380691528321,
|
|
"epoch": 0.36390183635648904,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992820933672958,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.1637185886502266,
|
|
"num_tokens": 7237545.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.81719183921814,
|
|
"epoch": 0.3644634132644466,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004992788851311399,
|
|
"loss": 5.7702,
|
|
"mean_token_accuracy": 0.16504835039377214,
|
|
"num_tokens": 7247799.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.802454233169556,
|
|
"epoch": 0.3650249901724041,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992756697538574,
|
|
"loss": 5.7621,
|
|
"mean_token_accuracy": 0.15942460298538208,
|
|
"num_tokens": 7260229.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.750087070465088,
|
|
"epoch": 0.36558656708036164,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004992724472355505,
|
|
"loss": 5.8644,
|
|
"mean_token_accuracy": 0.16067747250199318,
|
|
"num_tokens": 7271457.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.830528402328492,
|
|
"epoch": 0.3661481439883192,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992692175763219,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.162417733669281,
|
|
"num_tokens": 7282124.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.905847883224487,
|
|
"epoch": 0.36670972089627674,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004992659807762745,
|
|
"loss": 5.882,
|
|
"mean_token_accuracy": 0.1609184294939041,
|
|
"num_tokens": 7292981.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.034037303924561,
|
|
"epoch": 0.3672712978042343,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992627368355112,
|
|
"loss": 6.0246,
|
|
"mean_token_accuracy": 0.1552102506160736,
|
|
"num_tokens": 7304591.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.904659271240234,
|
|
"epoch": 0.36783287471219184,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004992594857541355,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.16395703405141832,
|
|
"num_tokens": 7315918.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.840758275985718,
|
|
"epoch": 0.3683944516201494,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004992562275322506,
|
|
"loss": 5.8606,
|
|
"mean_token_accuracy": 0.16057509034872056,
|
|
"num_tokens": 7327725.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.955318355560303,
|
|
"epoch": 0.36895602852810694,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004992529621699606,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.15757713988423347,
|
|
"num_tokens": 7339787.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.870289611816406,
|
|
"epoch": 0.3695176054360645,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992496896673692,
|
|
"loss": 5.8593,
|
|
"mean_token_accuracy": 0.16306575238704682,
|
|
"num_tokens": 7351284.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.727367639541626,
|
|
"epoch": 0.37007918234402204,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004992464100245809,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.16900086402893066,
|
|
"num_tokens": 7362105.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.787231397628784,
|
|
"epoch": 0.37064075925197953,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992431232416997,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.1634974807500839,
|
|
"num_tokens": 7375204.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.990011501312256,
|
|
"epoch": 0.3712023361599371,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992398293188307,
|
|
"loss": 5.9264,
|
|
"mean_token_accuracy": 0.15928469598293304,
|
|
"num_tokens": 7385853.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.869418478012085,
|
|
"epoch": 0.37176391306789464,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992365282560784,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.15744265019893647,
|
|
"num_tokens": 7397459.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.786304140090943,
|
|
"epoch": 0.3723254899758522,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004992332200535483,
|
|
"loss": 5.7771,
|
|
"mean_token_accuracy": 0.15811904519796371,
|
|
"num_tokens": 7408996.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.88443775177002,
|
|
"epoch": 0.37288706688380974,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004992299047113452,
|
|
"loss": 5.8708,
|
|
"mean_token_accuracy": 0.1527439683675766,
|
|
"num_tokens": 7419938.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.858075571060181,
|
|
"epoch": 0.3734486437917673,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004992265822295752,
|
|
"loss": 5.8775,
|
|
"mean_token_accuracy": 0.156579452753067,
|
|
"num_tokens": 7430181.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.89394326210022,
|
|
"epoch": 0.37401022069972484,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004992232526083438,
|
|
"loss": 5.8428,
|
|
"mean_token_accuracy": 0.16179504096508027,
|
|
"num_tokens": 7440774.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.923043632507325,
|
|
"epoch": 0.3745717976076824,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000499219915847757,
|
|
"loss": 5.7594,
|
|
"mean_token_accuracy": 0.16297794580459596,
|
|
"num_tokens": 7451744.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.691926431655884,
|
|
"epoch": 0.37513337451563994,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992165719479211,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.16425829529762268,
|
|
"num_tokens": 7463731.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.901089715957641,
|
|
"epoch": 0.37569495142359743,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992132209089427,
|
|
"loss": 5.7853,
|
|
"mean_token_accuracy": 0.16836556494235994,
|
|
"num_tokens": 7474392.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.80761866569519,
|
|
"epoch": 0.376256528331555,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004992098627309283,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.1741283878684044,
|
|
"num_tokens": 7484860.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.746652841567993,
|
|
"epoch": 0.37681810523951254,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499206497413985,
|
|
"loss": 5.768,
|
|
"mean_token_accuracy": 0.16497739255428315,
|
|
"num_tokens": 7495877.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.878225040435791,
|
|
"epoch": 0.3773796821474701,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004992031249582197,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.16588372737169266,
|
|
"num_tokens": 7506879.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.749741554260254,
|
|
"epoch": 0.37794125905542764,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991997453637401,
|
|
"loss": 5.6786,
|
|
"mean_token_accuracy": 0.16683669239282609,
|
|
"num_tokens": 7517405.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.758454847335815,
|
|
"epoch": 0.3785028359633852,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991963586306536,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.1604207620024681,
|
|
"num_tokens": 7528832.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.8242714405059814,
|
|
"epoch": 0.37906441287134274,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991929647590682,
|
|
"loss": 5.733,
|
|
"mean_token_accuracy": 0.159584142267704,
|
|
"num_tokens": 7541048.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.823900842666626,
|
|
"epoch": 0.3796259897793003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991895637490917,
|
|
"loss": 5.7513,
|
|
"mean_token_accuracy": 0.1718425542116165,
|
|
"num_tokens": 7551849.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.72793231010437,
|
|
"epoch": 0.38018756668725784,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991861556008326,
|
|
"loss": 5.7761,
|
|
"mean_token_accuracy": 0.17318898737430571,
|
|
"num_tokens": 7563148.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.946691608428955,
|
|
"epoch": 0.3807491435952154,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004991827403143992,
|
|
"loss": 5.965,
|
|
"mean_token_accuracy": 0.154804065823555,
|
|
"num_tokens": 7575119.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.891312742233277,
|
|
"epoch": 0.3813107205031729,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991793178899006,
|
|
"loss": 5.8036,
|
|
"mean_token_accuracy": 0.16566188633441925,
|
|
"num_tokens": 7585899.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.84417200088501,
|
|
"epoch": 0.38187229741113043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004991758883274455,
|
|
"loss": 5.7231,
|
|
"mean_token_accuracy": 0.17008434534072875,
|
|
"num_tokens": 7598938.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.668083715438843,
|
|
"epoch": 0.382433874319088,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004991724516271432,
|
|
"loss": 5.7827,
|
|
"mean_token_accuracy": 0.15895904302597047,
|
|
"num_tokens": 7610087.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.961612510681152,
|
|
"epoch": 0.38299545122704554,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004991690077891032,
|
|
"loss": 5.9209,
|
|
"mean_token_accuracy": 0.1562424823641777,
|
|
"num_tokens": 7622186.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.877179956436157,
|
|
"epoch": 0.3835570281350031,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991655568134348,
|
|
"loss": 5.8561,
|
|
"mean_token_accuracy": 0.15569303855299949,
|
|
"num_tokens": 7633501.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.7371251583099365,
|
|
"epoch": 0.38411860504296064,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004991620987002483,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.16081503182649612,
|
|
"num_tokens": 7643656.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.903097438812256,
|
|
"epoch": 0.3846801819509182,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991586334496536,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.16309674829244614,
|
|
"num_tokens": 7654565.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.871581935882569,
|
|
"epoch": 0.38524175885887574,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004991551610617611,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.1725019782781601,
|
|
"num_tokens": 7664725.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.7043211460113525,
|
|
"epoch": 0.3858033357668333,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004991516815366812,
|
|
"loss": 5.7871,
|
|
"mean_token_accuracy": 0.16514737606048585,
|
|
"num_tokens": 7674772.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.87477388381958,
|
|
"epoch": 0.38636491267479084,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000499148194874525,
|
|
"loss": 5.8503,
|
|
"mean_token_accuracy": 0.15458273887634277,
|
|
"num_tokens": 7686488.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.943272972106934,
|
|
"epoch": 0.38692648958274833,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004991447010754032,
|
|
"loss": 5.8431,
|
|
"mean_token_accuracy": 0.16273746341466905,
|
|
"num_tokens": 7698842.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.763972473144531,
|
|
"epoch": 0.3874880664907059,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991412001394273,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.16672782599925995,
|
|
"num_tokens": 7709255.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.6297224998474125,
|
|
"epoch": 0.38804964339866344,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004991376920667086,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.16626047492027282,
|
|
"num_tokens": 7720182.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.776465606689453,
|
|
"epoch": 0.388611220306621,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004991341768573589,
|
|
"loss": 5.7004,
|
|
"mean_token_accuracy": 0.17453826367855071,
|
|
"num_tokens": 7730944.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.815778064727783,
|
|
"epoch": 0.38917279721457854,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00049913065451149,
|
|
"loss": 5.785,
|
|
"mean_token_accuracy": 0.16372839957475663,
|
|
"num_tokens": 7741686.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.837787342071533,
|
|
"epoch": 0.3897343741225361,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991271250292141,
|
|
"loss": 5.7699,
|
|
"mean_token_accuracy": 0.16615443229675292,
|
|
"num_tokens": 7752245.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.67790961265564,
|
|
"epoch": 0.39029595103049364,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991235884106437,
|
|
"loss": 5.7466,
|
|
"mean_token_accuracy": 0.1583719566464424,
|
|
"num_tokens": 7762622.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.9347912788391115,
|
|
"epoch": 0.3908575279384512,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004991200446558913,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.16751627624034882,
|
|
"num_tokens": 7773550.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.788717985153198,
|
|
"epoch": 0.39141910484640874,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004991164937650698,
|
|
"loss": 5.7659,
|
|
"mean_token_accuracy": 0.15754962861537933,
|
|
"num_tokens": 7784988.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.897488117218018,
|
|
"epoch": 0.39198068175436623,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004991129357382922,
|
|
"loss": 5.8375,
|
|
"mean_token_accuracy": 0.16491298228502274,
|
|
"num_tokens": 7797706.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.813823890686035,
|
|
"epoch": 0.3925422586623238,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004991093705756718,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.16541284024715425,
|
|
"num_tokens": 7808960.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.6959394931793215,
|
|
"epoch": 0.39310383557028133,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004991057982773221,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.176891328394413,
|
|
"num_tokens": 7819271.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.79116039276123,
|
|
"epoch": 0.3936654124782389,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991022188433569,
|
|
"loss": 5.8267,
|
|
"mean_token_accuracy": 0.16208814084529877,
|
|
"num_tokens": 7832257.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.975289344787598,
|
|
"epoch": 0.39422698938619644,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00049909863227389,
|
|
"loss": 5.8383,
|
|
"mean_token_accuracy": 0.15807894468307496,
|
|
"num_tokens": 7842684.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.819514751434326,
|
|
"epoch": 0.394788566294154,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990950385690358,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.15922531485557556,
|
|
"num_tokens": 7855031.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.737144613265992,
|
|
"epoch": 0.39535014320211154,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004990914377289088,
|
|
"loss": 5.6428,
|
|
"mean_token_accuracy": 0.16459074914455413,
|
|
"num_tokens": 7865291.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.718155193328857,
|
|
"epoch": 0.3959117201100691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004990878297536233,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.16776801496744156,
|
|
"num_tokens": 7876401.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.696614551544189,
|
|
"epoch": 0.39647329701802664,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990842146432946,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.1654868945479393,
|
|
"num_tokens": 7887787.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.739422702789307,
|
|
"epoch": 0.3970348739259842,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990805923980375,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.1678236559033394,
|
|
"num_tokens": 7898550.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.737449979782104,
|
|
"epoch": 0.3975964508339417,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990769630179673,
|
|
"loss": 5.813,
|
|
"mean_token_accuracy": 0.161118945479393,
|
|
"num_tokens": 7909254.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.9880448341369625,
|
|
"epoch": 0.39815802774189923,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990733265032,
|
|
"loss": 5.8475,
|
|
"mean_token_accuracy": 0.16548922508955002,
|
|
"num_tokens": 7920164.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.783662557601929,
|
|
"epoch": 0.3987196046498568,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004990696828538508,
|
|
"loss": 5.7764,
|
|
"mean_token_accuracy": 0.1619616702198982,
|
|
"num_tokens": 7931390.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.739901924133301,
|
|
"epoch": 0.39928118155781434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499066032070036,
|
|
"loss": 5.8041,
|
|
"mean_token_accuracy": 0.16207121163606644,
|
|
"num_tokens": 7943765.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.77688193321228,
|
|
"epoch": 0.3998427584657719,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004990623741518719,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1703217387199402,
|
|
"num_tokens": 7954621.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.741475296020508,
|
|
"epoch": 0.40040433537372944,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499058709099475,
|
|
"loss": 5.833,
|
|
"mean_token_accuracy": 0.15856752842664718,
|
|
"num_tokens": 7966063.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.890545272827149,
|
|
"epoch": 0.400965912281687,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004990550369129618,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.16446599662303923,
|
|
"num_tokens": 7977391.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.836398935317993,
|
|
"epoch": 0.40152748918964454,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990513575924494,
|
|
"loss": 5.8602,
|
|
"mean_token_accuracy": 0.16039051860570908,
|
|
"num_tokens": 7988786.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.803277540206909,
|
|
"epoch": 0.4020890660976021,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990476711380548,
|
|
"loss": 5.6708,
|
|
"mean_token_accuracy": 0.16602781116962434,
|
|
"num_tokens": 8000848.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.795250701904297,
|
|
"epoch": 0.40265064300555964,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990439775498954,
|
|
"loss": 5.8304,
|
|
"mean_token_accuracy": 0.1595678821206093,
|
|
"num_tokens": 8012621.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.9635570526123045,
|
|
"epoch": 0.40321221991351713,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000499040276828089,
|
|
"loss": 5.8741,
|
|
"mean_token_accuracy": 0.15838356912136078,
|
|
"num_tokens": 8023599.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.6793303966522215,
|
|
"epoch": 0.4037737968214747,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004990365689727533,
|
|
"loss": 5.6955,
|
|
"mean_token_accuracy": 0.1689381405711174,
|
|
"num_tokens": 8037151.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.8145331859588625,
|
|
"epoch": 0.40433537372943223,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990328539840062,
|
|
"loss": 5.8927,
|
|
"mean_token_accuracy": 0.1599131479859352,
|
|
"num_tokens": 8048606.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.794629907608032,
|
|
"epoch": 0.4048969506373898,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004990291318619663,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.18030896484851838,
|
|
"num_tokens": 8058430.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.683138036727906,
|
|
"epoch": 0.40545852754534734,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004990254026067518,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.16754030138254167,
|
|
"num_tokens": 8069554.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.8404065608978275,
|
|
"epoch": 0.4060201044533049,
|
|
"grad_norm": 3.078125,
|
|
"learning_rate": 0.0004990216662184817,
|
|
"loss": 5.8338,
|
|
"mean_token_accuracy": 0.1567133218050003,
|
|
"num_tokens": 8082131.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.772003126144409,
|
|
"epoch": 0.40658168136126244,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004990179226972749,
|
|
"loss": 5.6698,
|
|
"mean_token_accuracy": 0.16911280602216722,
|
|
"num_tokens": 8093454.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.885181283950805,
|
|
"epoch": 0.40714325826922,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990141720432504,
|
|
"loss": 5.9286,
|
|
"mean_token_accuracy": 0.153592312335968,
|
|
"num_tokens": 8105502.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.827719736099243,
|
|
"epoch": 0.40770483517717754,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004990104142565279,
|
|
"loss": 5.7962,
|
|
"mean_token_accuracy": 0.15946278274059295,
|
|
"num_tokens": 8116524.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.81666202545166,
|
|
"epoch": 0.40826641208513503,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000499006649337227,
|
|
"loss": 5.7834,
|
|
"mean_token_accuracy": 0.17219170331954955,
|
|
"num_tokens": 8126949.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.826323175430298,
|
|
"epoch": 0.4088279889930926,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004990028772854674,
|
|
"loss": 5.7372,
|
|
"mean_token_accuracy": 0.1711343288421631,
|
|
"num_tokens": 8137346.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.736019849777222,
|
|
"epoch": 0.40938956590105013,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004989990981013693,
|
|
"loss": 5.7688,
|
|
"mean_token_accuracy": 0.15842943340539933,
|
|
"num_tokens": 8148499.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.808359241485595,
|
|
"epoch": 0.4099511428090077,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498995311785053,
|
|
"loss": 5.7966,
|
|
"mean_token_accuracy": 0.16432369500398636,
|
|
"num_tokens": 8159645.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.848784399032593,
|
|
"epoch": 0.41051271971696524,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989915183366392,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.16495027989149094,
|
|
"num_tokens": 8171033.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.703339099884033,
|
|
"epoch": 0.4110742966249228,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989877177562485,
|
|
"loss": 5.7525,
|
|
"mean_token_accuracy": 0.16168197095394135,
|
|
"num_tokens": 8181582.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.693508815765381,
|
|
"epoch": 0.41163587353288034,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498983910044002,
|
|
"loss": 5.6546,
|
|
"mean_token_accuracy": 0.1664942368865013,
|
|
"num_tokens": 8192432.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.902666187286377,
|
|
"epoch": 0.4121974504408379,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989800952000209,
|
|
"loss": 5.8258,
|
|
"mean_token_accuracy": 0.1659553498029709,
|
|
"num_tokens": 8203995.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.72920184135437,
|
|
"epoch": 0.41275902734879544,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989762732244268,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.1710478037595749,
|
|
"num_tokens": 8214323.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.696265459060669,
|
|
"epoch": 0.413320604256753,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004989724441173413,
|
|
"loss": 5.7392,
|
|
"mean_token_accuracy": 0.15900575518608093,
|
|
"num_tokens": 8226285.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.899669361114502,
|
|
"epoch": 0.4138821811647105,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989686078788862,
|
|
"loss": 5.8949,
|
|
"mean_token_accuracy": 0.1595530889928341,
|
|
"num_tokens": 8237961.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.764301395416259,
|
|
"epoch": 0.41444375807266803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989647645091839,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.17082756161689758,
|
|
"num_tokens": 8248463.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.796138715744019,
|
|
"epoch": 0.4150053349806256,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004989609140083565,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.1687775045633316,
|
|
"num_tokens": 8260342.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.809588813781739,
|
|
"epoch": 0.41556691188858313,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989570563765269,
|
|
"loss": 5.896,
|
|
"mean_token_accuracy": 0.163447105884552,
|
|
"num_tokens": 8272055.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.990705490112305,
|
|
"epoch": 0.4161284887965407,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004989531916138176,
|
|
"loss": 5.8341,
|
|
"mean_token_accuracy": 0.16277446299791337,
|
|
"num_tokens": 8282129.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.877596235275268,
|
|
"epoch": 0.41669006570449824,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989493197203519,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.16486470699310302,
|
|
"num_tokens": 8294663.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.708257484436035,
|
|
"epoch": 0.4172516426124558,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000498945440696253,
|
|
"loss": 5.6572,
|
|
"mean_token_accuracy": 0.16825253665447235,
|
|
"num_tokens": 8305882.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.766684532165527,
|
|
"epoch": 0.41781321952041334,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989415545416444,
|
|
"loss": 5.7586,
|
|
"mean_token_accuracy": 0.16602006405591965,
|
|
"num_tokens": 8316604.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.880210542678833,
|
|
"epoch": 0.4183747964283709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989376612566498,
|
|
"loss": 5.8357,
|
|
"mean_token_accuracy": 0.16286633312702178,
|
|
"num_tokens": 8328126.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.812762784957886,
|
|
"epoch": 0.4189363733363284,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004989337608413933,
|
|
"loss": 5.7808,
|
|
"mean_token_accuracy": 0.16223454102873802,
|
|
"num_tokens": 8339050.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.700385856628418,
|
|
"epoch": 0.41949795024428593,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989298532959989,
|
|
"loss": 5.5958,
|
|
"mean_token_accuracy": 0.1702934354543686,
|
|
"num_tokens": 8350216.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.778660583496094,
|
|
"epoch": 0.4200595271522435,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989259386205912,
|
|
"loss": 5.7694,
|
|
"mean_token_accuracy": 0.16529154330492019,
|
|
"num_tokens": 8362311.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.821306037902832,
|
|
"epoch": 0.42062110406020103,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004989220168152948,
|
|
"loss": 5.9452,
|
|
"mean_token_accuracy": 0.16443587392568587,
|
|
"num_tokens": 8373751.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.8550763607025145,
|
|
"epoch": 0.4211826809681586,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989180878802346,
|
|
"loss": 5.7637,
|
|
"mean_token_accuracy": 0.1636385902762413,
|
|
"num_tokens": 8384932.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.803427219390869,
|
|
"epoch": 0.42174425787611614,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004989141518155354,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.1680624231696129,
|
|
"num_tokens": 8394973.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.845605945587158,
|
|
"epoch": 0.4223058347840737,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989102086213229,
|
|
"loss": 5.7992,
|
|
"mean_token_accuracy": 0.16670042723417283,
|
|
"num_tokens": 8406590.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.713793849945068,
|
|
"epoch": 0.42286741169203124,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989062582977225,
|
|
"loss": 5.7223,
|
|
"mean_token_accuracy": 0.16826532781124115,
|
|
"num_tokens": 8417127.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.841227006912232,
|
|
"epoch": 0.4234289885999888,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989023008448599,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.16535673588514327,
|
|
"num_tokens": 8429442.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.814213991165161,
|
|
"epoch": 0.42399056550794634,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988983362628614,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.16802022755146026,
|
|
"num_tokens": 8439375.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.742303895950317,
|
|
"epoch": 0.42455214241590383,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988943645518528,
|
|
"loss": 5.7524,
|
|
"mean_token_accuracy": 0.16185249835252763,
|
|
"num_tokens": 8449817.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.752679920196533,
|
|
"epoch": 0.4251137193238614,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988903857119611,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.17161817252635955,
|
|
"num_tokens": 8460096.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.76074481010437,
|
|
"epoch": 0.42567529623181893,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988863997433125,
|
|
"loss": 5.7642,
|
|
"mean_token_accuracy": 0.16799037605524064,
|
|
"num_tokens": 8470241.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.829303550720215,
|
|
"epoch": 0.4262368731397765,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988824066460341,
|
|
"loss": 5.7775,
|
|
"mean_token_accuracy": 0.15977050364017487,
|
|
"num_tokens": 8481438.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.820899963378906,
|
|
"epoch": 0.42679845004773403,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498878406420253,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.16151625514030457,
|
|
"num_tokens": 8492588.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.69872932434082,
|
|
"epoch": 0.4273600269556916,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988743990660967,
|
|
"loss": 5.7577,
|
|
"mean_token_accuracy": 0.16909127980470656,
|
|
"num_tokens": 8502298.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.719389152526856,
|
|
"epoch": 0.42792160386364914,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988703845836927,
|
|
"loss": 5.6151,
|
|
"mean_token_accuracy": 0.16614673882722855,
|
|
"num_tokens": 8513507.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.803830862045288,
|
|
"epoch": 0.4284831807716067,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004988663629731687,
|
|
"loss": 5.7045,
|
|
"mean_token_accuracy": 0.17288311272859574,
|
|
"num_tokens": 8523888.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.72745156288147,
|
|
"epoch": 0.42904475767956424,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498862334234653,
|
|
"loss": 5.6538,
|
|
"mean_token_accuracy": 0.17681024968624115,
|
|
"num_tokens": 8534032.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.75491623878479,
|
|
"epoch": 0.4296063345875218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988582983682737,
|
|
"loss": 5.7883,
|
|
"mean_token_accuracy": 0.16662777364253997,
|
|
"num_tokens": 8545544.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.849988603591919,
|
|
"epoch": 0.4301679114954793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004988542553741594,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.16920416206121444,
|
|
"num_tokens": 8555428.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.713437700271607,
|
|
"epoch": 0.43072948840343683,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988502052524388,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.16877689063549042,
|
|
"num_tokens": 8566456.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.716613626480102,
|
|
"epoch": 0.4312910653113944,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004988461480032408,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.16707538068294525,
|
|
"num_tokens": 8578125.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.733826112747193,
|
|
"epoch": 0.43185264221935193,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988420836266946,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.15979516208171846,
|
|
"num_tokens": 8589530.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.818900156021118,
|
|
"epoch": 0.4324142191273095,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004988380121229298,
|
|
"loss": 5.8268,
|
|
"mean_token_accuracy": 0.16639951169490813,
|
|
"num_tokens": 8601655.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.790640592575073,
|
|
"epoch": 0.43297579603526704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988339334920757,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.16661467850208284,
|
|
"num_tokens": 8613355.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.7519673824310305,
|
|
"epoch": 0.4335373729432246,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988298477342625,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.17181873172521592,
|
|
"num_tokens": 8624154.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.797175741195678,
|
|
"epoch": 0.43409894985118214,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049882575484962,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.1668313190340996,
|
|
"num_tokens": 8633888.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.781188535690307,
|
|
"epoch": 0.4346605267591397,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988216548382787,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.16496998816728592,
|
|
"num_tokens": 8644965.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.790895175933838,
|
|
"epoch": 0.4352221036670972,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988175477003691,
|
|
"loss": 5.6934,
|
|
"mean_token_accuracy": 0.17174509465694426,
|
|
"num_tokens": 8655483.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.768792247772216,
|
|
"epoch": 0.43578368057505473,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498813433436022,
|
|
"loss": 5.6684,
|
|
"mean_token_accuracy": 0.16458337008953094,
|
|
"num_tokens": 8666443.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.814293336868286,
|
|
"epoch": 0.4363452574830123,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004988093120453684,
|
|
"loss": 5.7331,
|
|
"mean_token_accuracy": 0.1673333004117012,
|
|
"num_tokens": 8677198.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.694704341888428,
|
|
"epoch": 0.43690683439096983,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004988051835285394,
|
|
"loss": 5.794,
|
|
"mean_token_accuracy": 0.1586110770702362,
|
|
"num_tokens": 8688303.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.840091180801392,
|
|
"epoch": 0.4374684112989274,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004988010478856667,
|
|
"loss": 5.7496,
|
|
"mean_token_accuracy": 0.1625588357448578,
|
|
"num_tokens": 8700326.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.735308885574341,
|
|
"epoch": 0.43802998820688493,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987969051168816,
|
|
"loss": 5.6969,
|
|
"mean_token_accuracy": 0.16656334847211837,
|
|
"num_tokens": 8711101.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.747889757156372,
|
|
"epoch": 0.4385915651148425,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987927552223165,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.16011185348033904,
|
|
"num_tokens": 8721751.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.876703500747681,
|
|
"epoch": 0.43915314202280004,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004987885982021032,
|
|
"loss": 5.923,
|
|
"mean_token_accuracy": 0.15848976969718934,
|
|
"num_tokens": 8733550.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.824368000030518,
|
|
"epoch": 0.4397147189307576,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004987844340563741,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.1692325010895729,
|
|
"num_tokens": 8744218.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.752807331085205,
|
|
"epoch": 0.44027629583871514,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987802627852619,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.16270145028829575,
|
|
"num_tokens": 8756531.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.903487777709961,
|
|
"epoch": 0.44083787274667263,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004987760843888992,
|
|
"loss": 5.8062,
|
|
"mean_token_accuracy": 0.166811740398407,
|
|
"num_tokens": 8768114.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.7804687976837155,
|
|
"epoch": 0.4413994496546302,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987718988674193,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.15925536304712296,
|
|
"num_tokens": 8780010.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.891220283508301,
|
|
"epoch": 0.44196102656258773,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987677062209552,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.1611478492617607,
|
|
"num_tokens": 8792183.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.817219877243042,
|
|
"epoch": 0.4425226034705453,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987635064496407,
|
|
"loss": 5.8581,
|
|
"mean_token_accuracy": 0.15837597846984863,
|
|
"num_tokens": 8804513.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.725110673904419,
|
|
"epoch": 0.44308418037850283,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004987592995536093,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.1678770124912262,
|
|
"num_tokens": 8814918.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.79458212852478,
|
|
"epoch": 0.4436457572864604,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987550855329951,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.1642073079943657,
|
|
"num_tokens": 8826176.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.698785972595215,
|
|
"epoch": 0.44420733419441794,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987508643879322,
|
|
"loss": 5.7181,
|
|
"mean_token_accuracy": 0.16428748816251754,
|
|
"num_tokens": 8837242.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.849932479858398,
|
|
"epoch": 0.4447689111023755,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004987466361185549,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.16795441806316375,
|
|
"num_tokens": 8848972.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.6293586730957035,
|
|
"epoch": 0.44533048801033304,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987424007249979,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.1604418694972992,
|
|
"num_tokens": 8861108.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.770846128463745,
|
|
"epoch": 0.4458920649182906,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004987381582073962,
|
|
"loss": 5.7603,
|
|
"mean_token_accuracy": 0.16394788175821304,
|
|
"num_tokens": 8872161.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 6.036405611038208,
|
|
"epoch": 0.4464536418262481,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987339085658848,
|
|
"loss": 5.8381,
|
|
"mean_token_accuracy": 0.1662450149655342,
|
|
"num_tokens": 8882497.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.60550446510315,
|
|
"epoch": 0.44701521873420563,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004987296518005988,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.1710640922188759,
|
|
"num_tokens": 8893155.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.664576864242553,
|
|
"epoch": 0.4475767956421632,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000498725387911674,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.17508065104484558,
|
|
"num_tokens": 8904478.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.713468599319458,
|
|
"epoch": 0.44813837255012073,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004987211168992461,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.16204013973474501,
|
|
"num_tokens": 8915470.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.782445240020752,
|
|
"epoch": 0.4486999494580783,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498716838763451,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.16941280514001847,
|
|
"num_tokens": 8925644.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.776318597793579,
|
|
"epoch": 0.44926152636603583,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498712553504425,
|
|
"loss": 5.7371,
|
|
"mean_token_accuracy": 0.1644042417407036,
|
|
"num_tokens": 8937000.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.777050876617432,
|
|
"epoch": 0.4498231032739934,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004987082611223046,
|
|
"loss": 5.7285,
|
|
"mean_token_accuracy": 0.16219525635242463,
|
|
"num_tokens": 8948258.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.760573625564575,
|
|
"epoch": 0.45038468018195094,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004987039616172265,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.16296723783016204,
|
|
"num_tokens": 8960107.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.810834264755249,
|
|
"epoch": 0.4509462570899085,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986996549893273,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.16663117855787277,
|
|
"num_tokens": 8969612.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.7778235912323,
|
|
"epoch": 0.451507833997866,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986953412387445,
|
|
"loss": 5.8321,
|
|
"mean_token_accuracy": 0.16157644242048264,
|
|
"num_tokens": 8980970.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.784807443618774,
|
|
"epoch": 0.45206941090582353,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004986910203656151,
|
|
"loss": 5.7504,
|
|
"mean_token_accuracy": 0.16776563972234726,
|
|
"num_tokens": 8992218.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.6815488815307615,
|
|
"epoch": 0.4526309878137811,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004986866923700769,
|
|
"loss": 5.6796,
|
|
"mean_token_accuracy": 0.16920140832662584,
|
|
"num_tokens": 9003737.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.847456932067871,
|
|
"epoch": 0.45319256472173863,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004986823572522677,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.166916099190712,
|
|
"num_tokens": 9015427.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.756457328796387,
|
|
"epoch": 0.4537541416296962,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004986780150123254,
|
|
"loss": 5.7465,
|
|
"mean_token_accuracy": 0.16183993145823478,
|
|
"num_tokens": 9025003.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.722242927551269,
|
|
"epoch": 0.45431571853765373,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004986736656503885,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.1649579644203186,
|
|
"num_tokens": 9036074.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.886012601852417,
|
|
"epoch": 0.4548772954456113,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986693091665952,
|
|
"loss": 5.7262,
|
|
"mean_token_accuracy": 0.16319333016872406,
|
|
"num_tokens": 9046878.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.787053918838501,
|
|
"epoch": 0.45543887235356884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986649455610845,
|
|
"loss": 5.7824,
|
|
"mean_token_accuracy": 0.16606189608573912,
|
|
"num_tokens": 9058366.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.810052108764649,
|
|
"epoch": 0.4560004492615264,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000498660574833995,
|
|
"loss": 5.8023,
|
|
"mean_token_accuracy": 0.1629299119114876,
|
|
"num_tokens": 9069542.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.889910268783569,
|
|
"epoch": 0.45656202616948394,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004986561969854661,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.15835504978895187,
|
|
"num_tokens": 9081219.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.791186380386352,
|
|
"epoch": 0.45712360307744143,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004986518120156373,
|
|
"loss": 5.6585,
|
|
"mean_token_accuracy": 0.17095888108015062,
|
|
"num_tokens": 9092101.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.74450831413269,
|
|
"epoch": 0.457685179985399,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000498647419924648,
|
|
"loss": 5.7183,
|
|
"mean_token_accuracy": 0.16321291476488115,
|
|
"num_tokens": 9101900.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.896109914779663,
|
|
"epoch": 0.45824675689335653,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000498643020712638,
|
|
"loss": 5.8607,
|
|
"mean_token_accuracy": 0.1589878261089325,
|
|
"num_tokens": 9114369.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.7966124534606935,
|
|
"epoch": 0.4588083338013141,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986386143797475,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.16787811517715454,
|
|
"num_tokens": 9126548.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.775979137420654,
|
|
"epoch": 0.45936991070927163,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986342009261169,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.1698113664984703,
|
|
"num_tokens": 9138070.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.859607601165772,
|
|
"epoch": 0.4599314876172292,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986297803518865,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.16200243085622787,
|
|
"num_tokens": 9149489.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.762571048736572,
|
|
"epoch": 0.46049306452518673,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986253526571971,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.1771351307630539,
|
|
"num_tokens": 9160363.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.839546632766724,
|
|
"epoch": 0.4610546414331443,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986209178421899,
|
|
"loss": 5.7961,
|
|
"mean_token_accuracy": 0.16267647296190263,
|
|
"num_tokens": 9171619.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.726217317581177,
|
|
"epoch": 0.46161621834110184,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000498616475907006,
|
|
"loss": 5.6318,
|
|
"mean_token_accuracy": 0.16940359473228456,
|
|
"num_tokens": 9182828.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.804625988006592,
|
|
"epoch": 0.46217779524905933,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004986120268517865,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.16845984905958175,
|
|
"num_tokens": 9195249.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.7279651165008545,
|
|
"epoch": 0.4627393721570169,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004986075706766736,
|
|
"loss": 5.6107,
|
|
"mean_token_accuracy": 0.1685888111591339,
|
|
"num_tokens": 9205770.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.718081617355347,
|
|
"epoch": 0.46330094906497443,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004986031073818088,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.1704689159989357,
|
|
"num_tokens": 9216367.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.745043182373047,
|
|
"epoch": 0.463862525972932,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985986369673343,
|
|
"loss": 5.7443,
|
|
"mean_token_accuracy": 0.15560253709554672,
|
|
"num_tokens": 9228524.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.729569149017334,
|
|
"epoch": 0.46442410288088953,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004985941594333926,
|
|
"loss": 5.697,
|
|
"mean_token_accuracy": 0.17092883437871934,
|
|
"num_tokens": 9238907.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.829591894149781,
|
|
"epoch": 0.4649856797888471,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498589674780126,
|
|
"loss": 5.8496,
|
|
"mean_token_accuracy": 0.1654239699244499,
|
|
"num_tokens": 9250491.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.78412094116211,
|
|
"epoch": 0.46554725669680463,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004985851830076775,
|
|
"loss": 5.6244,
|
|
"mean_token_accuracy": 0.17385055720806122,
|
|
"num_tokens": 9260984.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.8113926410675045,
|
|
"epoch": 0.4661088336047622,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985806841161901,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.1639147825539112,
|
|
"num_tokens": 9272416.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.83788161277771,
|
|
"epoch": 0.46667041051271974,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000498576178105807,
|
|
"loss": 5.7851,
|
|
"mean_token_accuracy": 0.16480545103549957,
|
|
"num_tokens": 9284513.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.79778823852539,
|
|
"epoch": 0.4672319874206773,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004985716649766717,
|
|
"loss": 5.6693,
|
|
"mean_token_accuracy": 0.17508763074874878,
|
|
"num_tokens": 9293422.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.674432039260864,
|
|
"epoch": 0.4677935643286348,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004985671447289277,
|
|
"loss": 5.6591,
|
|
"mean_token_accuracy": 0.16806172132492064,
|
|
"num_tokens": 9304735.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.722658967971801,
|
|
"epoch": 0.46835514123659233,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004985626173627194,
|
|
"loss": 5.7555,
|
|
"mean_token_accuracy": 0.1668326213955879,
|
|
"num_tokens": 9315659.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.782317972183227,
|
|
"epoch": 0.4689167181445499,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004985580828781904,
|
|
"loss": 5.7821,
|
|
"mean_token_accuracy": 0.16752771735191346,
|
|
"num_tokens": 9327106.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.909115791320801,
|
|
"epoch": 0.46947829505250743,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004985535412754855,
|
|
"loss": 5.8264,
|
|
"mean_token_accuracy": 0.16992503702640532,
|
|
"num_tokens": 9338762.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.7819764614105225,
|
|
"epoch": 0.470039871960465,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000498548992554749,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.16478354185819627,
|
|
"num_tokens": 9349495.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.836339902877808,
|
|
"epoch": 0.47060144886842253,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985444367161259,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.1722177416086197,
|
|
"num_tokens": 9360830.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.7116124629974365,
|
|
"epoch": 0.4711630257763801,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004985398737597614,
|
|
"loss": 5.6691,
|
|
"mean_token_accuracy": 0.16971368193626404,
|
|
"num_tokens": 9371668.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.795318555831909,
|
|
"epoch": 0.47172460268433763,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985353036858004,
|
|
"loss": 5.7898,
|
|
"mean_token_accuracy": 0.16455770283937454,
|
|
"num_tokens": 9383437.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.747787284851074,
|
|
"epoch": 0.4722861795922952,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004985307264943887,
|
|
"loss": 5.6313,
|
|
"mean_token_accuracy": 0.17282156348228456,
|
|
"num_tokens": 9394597.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.621947431564331,
|
|
"epoch": 0.47284775650025274,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004985261421856721,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.17287973314523697,
|
|
"num_tokens": 9404322.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.874908494949341,
|
|
"epoch": 0.47340933340821023,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985215507597963,
|
|
"loss": 5.9318,
|
|
"mean_token_accuracy": 0.15236857384443284,
|
|
"num_tokens": 9416740.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.888829374313355,
|
|
"epoch": 0.4739709103161678,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985169522169076,
|
|
"loss": 5.7371,
|
|
"mean_token_accuracy": 0.17069852352142334,
|
|
"num_tokens": 9428617.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.62801308631897,
|
|
"epoch": 0.47453248722412533,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004985123465571526,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.17174948155879974,
|
|
"num_tokens": 9439686.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.734438419342041,
|
|
"epoch": 0.4750940641320829,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004985077337806777,
|
|
"loss": 5.6614,
|
|
"mean_token_accuracy": 0.17259624004364013,
|
|
"num_tokens": 9450378.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.831440830230713,
|
|
"epoch": 0.47565564104004043,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004985031138876299,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.16325171142816544,
|
|
"num_tokens": 9461659.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.744169569015503,
|
|
"epoch": 0.476217217947998,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984984868781563,
|
|
"loss": 5.7435,
|
|
"mean_token_accuracy": 0.16722533851861954,
|
|
"num_tokens": 9472528.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.742637252807617,
|
|
"epoch": 0.47677879485595553,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004984938527524041,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.17739695608615874,
|
|
"num_tokens": 9483388.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.641309309005737,
|
|
"epoch": 0.4773403717639131,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498489211510521,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.180770543217659,
|
|
"num_tokens": 9495178.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.720116806030274,
|
|
"epoch": 0.47790194867187064,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004984845631526547,
|
|
"loss": 5.774,
|
|
"mean_token_accuracy": 0.16083385795354843,
|
|
"num_tokens": 9506226.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.819266080856323,
|
|
"epoch": 0.47846352557982813,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984799076789534,
|
|
"loss": 5.6678,
|
|
"mean_token_accuracy": 0.16451866030693055,
|
|
"num_tokens": 9517671.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.73471884727478,
|
|
"epoch": 0.4790251024877857,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984752450895649,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.1741185948252678,
|
|
"num_tokens": 9527637.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.843851518630982,
|
|
"epoch": 0.47958667939574323,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498470575384638,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.158755823969841,
|
|
"num_tokens": 9539686.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.829662656784057,
|
|
"epoch": 0.4801482563037008,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004984658985643214,
|
|
"loss": 5.7923,
|
|
"mean_token_accuracy": 0.17045938074588776,
|
|
"num_tokens": 9550775.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.788260841369629,
|
|
"epoch": 0.48070983321165833,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004984612146287638,
|
|
"loss": 5.7179,
|
|
"mean_token_accuracy": 0.1664621651172638,
|
|
"num_tokens": 9561760.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.710859394073486,
|
|
"epoch": 0.4812714101196159,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984565235781147,
|
|
"loss": 5.739,
|
|
"mean_token_accuracy": 0.16497448831796646,
|
|
"num_tokens": 9573899.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.771726846694946,
|
|
"epoch": 0.48183298702757343,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498451825412523,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1671557232737541,
|
|
"num_tokens": 9584336.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.867096042633056,
|
|
"epoch": 0.482394563935531,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004984471201321386,
|
|
"loss": 5.8894,
|
|
"mean_token_accuracy": 0.16078047305345536,
|
|
"num_tokens": 9596614.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.863018131256103,
|
|
"epoch": 0.48295614084348854,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004984424077371112,
|
|
"loss": 5.7282,
|
|
"mean_token_accuracy": 0.16814042925834655,
|
|
"num_tokens": 9606796.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.75321683883667,
|
|
"epoch": 0.4835177177514461,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004984376882275909,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.16570119559764862,
|
|
"num_tokens": 9617705.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.653896427154541,
|
|
"epoch": 0.4840792946594036,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004984329616037279,
|
|
"loss": 5.7102,
|
|
"mean_token_accuracy": 0.1715118706226349,
|
|
"num_tokens": 9628098.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.7214408874511715,
|
|
"epoch": 0.48464087156736113,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004984282278656727,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.177660708129406,
|
|
"num_tokens": 9637697.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.721050691604614,
|
|
"epoch": 0.4852024484753187,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984234870135762,
|
|
"loss": 5.5719,
|
|
"mean_token_accuracy": 0.17628056854009627,
|
|
"num_tokens": 9648221.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.787235927581787,
|
|
"epoch": 0.48576402538327623,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984187390475891,
|
|
"loss": 5.7498,
|
|
"mean_token_accuracy": 0.16280767023563386,
|
|
"num_tokens": 9660182.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.743753147125244,
|
|
"epoch": 0.4863256022912338,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004984139839678628,
|
|
"loss": 5.7674,
|
|
"mean_token_accuracy": 0.16657089442014694,
|
|
"num_tokens": 9672121.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.851155090332031,
|
|
"epoch": 0.48688717919919133,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004984092217745486,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.16990053057670593,
|
|
"num_tokens": 9682651.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.773957777023315,
|
|
"epoch": 0.4874487561071489,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984044524677981,
|
|
"loss": 5.8171,
|
|
"mean_token_accuracy": 0.15835769325494767,
|
|
"num_tokens": 9693989.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.709145450592041,
|
|
"epoch": 0.48801033301510643,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983996760477632,
|
|
"loss": 5.6682,
|
|
"mean_token_accuracy": 0.17094674706459045,
|
|
"num_tokens": 9703802.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.771444463729859,
|
|
"epoch": 0.488571909923064,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000498394892514596,
|
|
"loss": 5.6273,
|
|
"mean_token_accuracy": 0.1780262529850006,
|
|
"num_tokens": 9714287.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.695860910415649,
|
|
"epoch": 0.48913348683102154,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004983901018684486,
|
|
"loss": 5.6435,
|
|
"mean_token_accuracy": 0.16862788647413254,
|
|
"num_tokens": 9724819.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.778994798660278,
|
|
"epoch": 0.48969506373897903,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983853041094739,
|
|
"loss": 5.7994,
|
|
"mean_token_accuracy": 0.15891390144824982,
|
|
"num_tokens": 9736326.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.824983692169189,
|
|
"epoch": 0.4902566406469366,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983804992378243,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.16666850298643113,
|
|
"num_tokens": 9747883.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.711586046218872,
|
|
"epoch": 0.49081821755489413,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983756872536532,
|
|
"loss": 5.6642,
|
|
"mean_token_accuracy": 0.1676034614443779,
|
|
"num_tokens": 9758191.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.864538288116455,
|
|
"epoch": 0.4913797944628517,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004983708681571134,
|
|
"loss": 5.7669,
|
|
"mean_token_accuracy": 0.16125464141368867,
|
|
"num_tokens": 9768852.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.81319408416748,
|
|
"epoch": 0.49194137137080923,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004983660419483586,
|
|
"loss": 5.7026,
|
|
"mean_token_accuracy": 0.1664854660630226,
|
|
"num_tokens": 9779033.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.653231382369995,
|
|
"epoch": 0.4925029482787668,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004983612086275424,
|
|
"loss": 5.6329,
|
|
"mean_token_accuracy": 0.17090303152799607,
|
|
"num_tokens": 9790777.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.925910806655883,
|
|
"epoch": 0.49306452518672433,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983563681948187,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.15540677905082703,
|
|
"num_tokens": 9802305.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.864315462112427,
|
|
"epoch": 0.4936261020946819,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004983515206503416,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.1645990327000618,
|
|
"num_tokens": 9813590.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.724923372268677,
|
|
"epoch": 0.49418767900263944,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983466659942655,
|
|
"loss": 5.7847,
|
|
"mean_token_accuracy": 0.16188060939311982,
|
|
"num_tokens": 9824080.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.786849927902222,
|
|
"epoch": 0.49474925591059693,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004983418042267449,
|
|
"loss": 5.6702,
|
|
"mean_token_accuracy": 0.16590235233306885,
|
|
"num_tokens": 9835441.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.7217631340026855,
|
|
"epoch": 0.4953108328185545,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004983369353479345,
|
|
"loss": 5.6542,
|
|
"mean_token_accuracy": 0.1716426745057106,
|
|
"num_tokens": 9846750.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.85619044303894,
|
|
"epoch": 0.49587240972651203,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004983320593579895,
|
|
"loss": 5.8146,
|
|
"mean_token_accuracy": 0.16174422949552536,
|
|
"num_tokens": 9857987.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.80463662147522,
|
|
"epoch": 0.4964339866344696,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983271762570653,
|
|
"loss": 5.7547,
|
|
"mean_token_accuracy": 0.1635700836777687,
|
|
"num_tokens": 9869736.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.74100341796875,
|
|
"epoch": 0.49699556354242713,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498322286045317,
|
|
"loss": 5.7388,
|
|
"mean_token_accuracy": 0.16133737117052077,
|
|
"num_tokens": 9881610.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.759617280960083,
|
|
"epoch": 0.4975571404503847,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983173887229006,
|
|
"loss": 5.7232,
|
|
"mean_token_accuracy": 0.1672542944550514,
|
|
"num_tokens": 9893203.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.768886137008667,
|
|
"epoch": 0.49811871735834223,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004983124842899719,
|
|
"loss": 5.631,
|
|
"mean_token_accuracy": 0.1670058399438858,
|
|
"num_tokens": 9904392.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.558861207962036,
|
|
"epoch": 0.4986802942662998,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004983075727466871,
|
|
"loss": 5.6366,
|
|
"mean_token_accuracy": 0.16862301230430604,
|
|
"num_tokens": 9916184.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.801784610748291,
|
|
"epoch": 0.49924187117425733,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004983026540932026,
|
|
"loss": 5.7542,
|
|
"mean_token_accuracy": 0.1744879812002182,
|
|
"num_tokens": 9927516.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.764729642868042,
|
|
"epoch": 0.4998034480822149,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004982977283296749,
|
|
"loss": 5.7726,
|
|
"mean_token_accuracy": 0.16294186413288117,
|
|
"num_tokens": 9939182.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.843990135192871,
|
|
"epoch": 0.5003650249901724,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000498292795456261,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.1632004827260971,
|
|
"num_tokens": 9950382.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.838791275024414,
|
|
"epoch": 0.50092660189813,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004982878554731178,
|
|
"loss": 5.7783,
|
|
"mean_token_accuracy": 0.16980281323194504,
|
|
"num_tokens": 9961053.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.775715589523315,
|
|
"epoch": 0.5014881788060875,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982829083804028,
|
|
"loss": 5.6871,
|
|
"mean_token_accuracy": 0.1725940003991127,
|
|
"num_tokens": 9971313.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.708573484420777,
|
|
"epoch": 0.5020497557140451,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004982779541782733,
|
|
"loss": 5.6997,
|
|
"mean_token_accuracy": 0.1771649584174156,
|
|
"num_tokens": 9981257.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.713446712493896,
|
|
"epoch": 0.5026113326220026,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982729928668872,
|
|
"loss": 5.6169,
|
|
"mean_token_accuracy": 0.16980833560228348,
|
|
"num_tokens": 9991860.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.711110782623291,
|
|
"epoch": 0.5031729095299601,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004982680244464024,
|
|
"loss": 5.7244,
|
|
"mean_token_accuracy": 0.1682138755917549,
|
|
"num_tokens": 10002320.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.844463920593261,
|
|
"epoch": 0.5037344864379176,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004982630489169771,
|
|
"loss": 5.8205,
|
|
"mean_token_accuracy": 0.16214855760335922,
|
|
"num_tokens": 10013187.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.752076053619385,
|
|
"epoch": 0.5042960633458752,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982580662787697,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.1817475825548172,
|
|
"num_tokens": 10024268.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.775974416732788,
|
|
"epoch": 0.5048576402538327,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004982530765319389,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.16369644924998283,
|
|
"num_tokens": 10034738.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.856912851333618,
|
|
"epoch": 0.5054192171617903,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982480796766436,
|
|
"loss": 5.7692,
|
|
"mean_token_accuracy": 0.16682460606098176,
|
|
"num_tokens": 10045666.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.711333608627319,
|
|
"epoch": 0.5059807940697478,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004982430757130429,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.17160190939903258,
|
|
"num_tokens": 10057084.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.684904003143311,
|
|
"epoch": 0.5065423709777054,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004982380646412959,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.1675004705786705,
|
|
"num_tokens": 10066754.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.624693202972412,
|
|
"epoch": 0.5071039478856629,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982330464615625,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.1736236557364464,
|
|
"num_tokens": 10078139.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.795777940750122,
|
|
"epoch": 0.5076655247936205,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004982280211740023,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.16825804412364959,
|
|
"num_tokens": 10089652.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.56435341835022,
|
|
"epoch": 0.508227101701578,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982229887787753,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17702490240335464,
|
|
"num_tokens": 10100642.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.730996751785279,
|
|
"epoch": 0.5087886786095356,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982179492760418,
|
|
"loss": 5.7451,
|
|
"mean_token_accuracy": 0.1642565608024597,
|
|
"num_tokens": 10112036.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.723961591720581,
|
|
"epoch": 0.5093502555174931,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982129026659621,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.16866052895784378,
|
|
"num_tokens": 10121653.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.750852870941162,
|
|
"epoch": 0.5099118324254507,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004982078489486972,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.16526857912540435,
|
|
"num_tokens": 10132271.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.64841251373291,
|
|
"epoch": 0.5104734093334082,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004982027881244076,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.16694321632385253,
|
|
"num_tokens": 10143411.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.768961429595947,
|
|
"epoch": 0.5110349862413658,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004981977201932549,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.1735060140490532,
|
|
"num_tokens": 10154338.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.78614239692688,
|
|
"epoch": 0.5115965631493233,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004981926451554001,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.16850772649049758,
|
|
"num_tokens": 10164810.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.70502724647522,
|
|
"epoch": 0.5121581400572809,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981875630110048,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.17295267581939697,
|
|
"num_tokens": 10176323.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.775968074798584,
|
|
"epoch": 0.5127197169652384,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981824737602311,
|
|
"loss": 5.7023,
|
|
"mean_token_accuracy": 0.1713700607419014,
|
|
"num_tokens": 10187110.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.6774474620819095,
|
|
"epoch": 0.513281293873196,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004981773774032409,
|
|
"loss": 5.6658,
|
|
"mean_token_accuracy": 0.1672620877623558,
|
|
"num_tokens": 10199099.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.737269306182862,
|
|
"epoch": 0.5138428707811534,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004981722739401962,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.16981650441884993,
|
|
"num_tokens": 10209726.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.77852611541748,
|
|
"epoch": 0.514404447689111,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049816716337126,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.16715380549430847,
|
|
"num_tokens": 10220858.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.5843123435974125,
|
|
"epoch": 0.5149660245970685,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981620456965946,
|
|
"loss": 5.5767,
|
|
"mean_token_accuracy": 0.1753990486264229,
|
|
"num_tokens": 10232250.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.8313751220703125,
|
|
"epoch": 0.5155276015050261,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981569209163633,
|
|
"loss": 5.7691,
|
|
"mean_token_accuracy": 0.1599658399820328,
|
|
"num_tokens": 10244584.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.8322389125823975,
|
|
"epoch": 0.5160891784129836,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004981517890307288,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.1663820281624794,
|
|
"num_tokens": 10255926.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.7266191959381105,
|
|
"epoch": 0.5166507553209412,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498146650039855,
|
|
"loss": 5.7248,
|
|
"mean_token_accuracy": 0.16537322103977203,
|
|
"num_tokens": 10266691.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.743765544891358,
|
|
"epoch": 0.5172123322288987,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004981415039439054,
|
|
"loss": 5.7986,
|
|
"mean_token_accuracy": 0.16448924094438552,
|
|
"num_tokens": 10277744.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.754795694351197,
|
|
"epoch": 0.5177739091368563,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004981363507430436,
|
|
"loss": 5.6379,
|
|
"mean_token_accuracy": 0.17169588655233384,
|
|
"num_tokens": 10288792.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.765963935852051,
|
|
"epoch": 0.5183354860448138,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981311904374339,
|
|
"loss": 5.683,
|
|
"mean_token_accuracy": 0.1679953932762146,
|
|
"num_tokens": 10299569.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.674673461914063,
|
|
"epoch": 0.5188970629527714,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004981260230272405,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.17208833247423172,
|
|
"num_tokens": 10309742.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.826390123367309,
|
|
"epoch": 0.5194586398607289,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004981208485126281,
|
|
"loss": 5.7237,
|
|
"mean_token_accuracy": 0.16487168222665788,
|
|
"num_tokens": 10320603.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.6965149402618405,
|
|
"epoch": 0.5200202167686865,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004981156668937613,
|
|
"loss": 5.6687,
|
|
"mean_token_accuracy": 0.17033723443746568,
|
|
"num_tokens": 10331498.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.7486166000366214,
|
|
"epoch": 0.520581793676644,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004981104781708051,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.17158917486667633,
|
|
"num_tokens": 10342002.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.751145839691162,
|
|
"epoch": 0.5211433705846016,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004981052823439247,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.17173486053943635,
|
|
"num_tokens": 10351797.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.684526252746582,
|
|
"epoch": 0.5217049474925591,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004981000794132858,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.1721396490931511,
|
|
"num_tokens": 10362538.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.7123863697052,
|
|
"epoch": 0.5222665244005167,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004980948693790536,
|
|
"loss": 5.6288,
|
|
"mean_token_accuracy": 0.17359593361616135,
|
|
"num_tokens": 10373365.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.594706010818482,
|
|
"epoch": 0.5228281013084742,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004980896522413943,
|
|
"loss": 5.6105,
|
|
"mean_token_accuracy": 0.1676344931125641,
|
|
"num_tokens": 10385087.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.714381551742553,
|
|
"epoch": 0.5233896782164318,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004980844280004739,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.16516276001930236,
|
|
"num_tokens": 10396014.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.7259293556213375,
|
|
"epoch": 0.5239512551243893,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004980791966564589,
|
|
"loss": 5.6567,
|
|
"mean_token_accuracy": 0.16828372180461884,
|
|
"num_tokens": 10407844.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.676039743423462,
|
|
"epoch": 0.5245128320323468,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980739582095158,
|
|
"loss": 5.7122,
|
|
"mean_token_accuracy": 0.16512629091739656,
|
|
"num_tokens": 10419892.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.7812426567077635,
|
|
"epoch": 0.5250744089403043,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004980687126598111,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.16482717394828797,
|
|
"num_tokens": 10430686.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.746427869796753,
|
|
"epoch": 0.5256359858482619,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980634600075123,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.16327853351831437,
|
|
"num_tokens": 10443785.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.619085836410522,
|
|
"epoch": 0.5261975627562194,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980582002527863,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.1755577355623245,
|
|
"num_tokens": 10454889.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.749862194061279,
|
|
"epoch": 0.526759139664177,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980529333958008,
|
|
"loss": 5.7728,
|
|
"mean_token_accuracy": 0.16234699189662932,
|
|
"num_tokens": 10466525.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.817795467376709,
|
|
"epoch": 0.5273207165721345,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004980476594367233,
|
|
"loss": 5.7167,
|
|
"mean_token_accuracy": 0.1696426585316658,
|
|
"num_tokens": 10476329.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.818607234954834,
|
|
"epoch": 0.5278822934800921,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004980423783757219,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.1678716391324997,
|
|
"num_tokens": 10487178.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.726896953582764,
|
|
"epoch": 0.5284438703880496,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980370902129646,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.15968317091464995,
|
|
"num_tokens": 10499293.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.882290554046631,
|
|
"epoch": 0.5290054472960072,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00049803179494862,
|
|
"loss": 5.9012,
|
|
"mean_token_accuracy": 0.15440506264567375,
|
|
"num_tokens": 10511762.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.746896409988404,
|
|
"epoch": 0.5295670242039647,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980264925828563,
|
|
"loss": 5.6264,
|
|
"mean_token_accuracy": 0.17390570193529128,
|
|
"num_tokens": 10521725.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.650912284851074,
|
|
"epoch": 0.5301286011119223,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004980211831158427,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.1688406854867935,
|
|
"num_tokens": 10531764.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.751105928421021,
|
|
"epoch": 0.5306901780198798,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004980158665477481,
|
|
"loss": 5.6629,
|
|
"mean_token_accuracy": 0.16897214204072952,
|
|
"num_tokens": 10542127.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.8114818096160885,
|
|
"epoch": 0.5312517549278374,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004980105428787419,
|
|
"loss": 5.745,
|
|
"mean_token_accuracy": 0.1624537155032158,
|
|
"num_tokens": 10552580.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.777641820907593,
|
|
"epoch": 0.5318133318357949,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004980052121089934,
|
|
"loss": 5.6897,
|
|
"mean_token_accuracy": 0.16472815871238708,
|
|
"num_tokens": 10562961.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.842762088775634,
|
|
"epoch": 0.5323749087437525,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979998742386725,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.17186302542686463,
|
|
"num_tokens": 10573210.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.615639781951904,
|
|
"epoch": 0.53293648565171,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004979945292679492,
|
|
"loss": 5.6413,
|
|
"mean_token_accuracy": 0.16917951554059982,
|
|
"num_tokens": 10583878.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.8078375339508055,
|
|
"epoch": 0.5334980625596676,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004979891771969935,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.16554457247257232,
|
|
"num_tokens": 10593420.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.757600927352906,
|
|
"epoch": 0.5340596394676251,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000497983818025976,
|
|
"loss": 5.7309,
|
|
"mean_token_accuracy": 0.1641060709953308,
|
|
"num_tokens": 10604213.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.742426633834839,
|
|
"epoch": 0.5346212163755827,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979784517550671,
|
|
"loss": 5.7097,
|
|
"mean_token_accuracy": 0.16690609902143477,
|
|
"num_tokens": 10615502.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.8370613098144535,
|
|
"epoch": 0.5351827932835401,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004979730783844379,
|
|
"loss": 5.7763,
|
|
"mean_token_accuracy": 0.1616876393556595,
|
|
"num_tokens": 10627589.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.68374080657959,
|
|
"epoch": 0.5357443701914977,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004979676979142595,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.17053748071193695,
|
|
"num_tokens": 10638365.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.695065212249756,
|
|
"epoch": 0.5363059470994552,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000497962310344703,
|
|
"loss": 5.7267,
|
|
"mean_token_accuracy": 0.16930074691772462,
|
|
"num_tokens": 10650664.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.81259241104126,
|
|
"epoch": 0.5368675240074128,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00049795691567594,
|
|
"loss": 5.7657,
|
|
"mean_token_accuracy": 0.16950975954532624,
|
|
"num_tokens": 10662418.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.778849029541016,
|
|
"epoch": 0.5374291009153703,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004979515139081426,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.1676219344139099,
|
|
"num_tokens": 10672793.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.663295078277588,
|
|
"epoch": 0.5379906778233279,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004979461050414822,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.1763066604733467,
|
|
"num_tokens": 10684082.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.647389650344849,
|
|
"epoch": 0.5385522547312854,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979406890761315,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.16752851158380508,
|
|
"num_tokens": 10694490.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.696194839477539,
|
|
"epoch": 0.539113831639243,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004979352660122629,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.16965416371822356,
|
|
"num_tokens": 10704731.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.720260715484619,
|
|
"epoch": 0.5396754085472005,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004979298358500488,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.17208992540836335,
|
|
"num_tokens": 10715735.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.688508367538452,
|
|
"epoch": 0.5402369854551581,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004979243985896624,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.1707595556974411,
|
|
"num_tokens": 10726951.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.658755779266357,
|
|
"epoch": 0.5407985623631156,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979189542312765,
|
|
"loss": 5.6845,
|
|
"mean_token_accuracy": 0.1615520939230919,
|
|
"num_tokens": 10737609.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.721249723434449,
|
|
"epoch": 0.5413601392710732,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004979135027750649,
|
|
"loss": 5.5789,
|
|
"mean_token_accuracy": 0.17817058265209199,
|
|
"num_tokens": 10748957.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.729371452331543,
|
|
"epoch": 0.5419217161790307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979080442212007,
|
|
"loss": 5.7677,
|
|
"mean_token_accuracy": 0.16021177172660828,
|
|
"num_tokens": 10759398.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.75501184463501,
|
|
"epoch": 0.5424832930869883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004979025785698581,
|
|
"loss": 5.7488,
|
|
"mean_token_accuracy": 0.1632383644580841,
|
|
"num_tokens": 10770436.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.714452028274536,
|
|
"epoch": 0.5430448699949458,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978971058212108,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.18060631901025773,
|
|
"num_tokens": 10781160.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.787505388259888,
|
|
"epoch": 0.5436064469029034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004978916259754331,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.1764016181230545,
|
|
"num_tokens": 10793170.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.678378772735596,
|
|
"epoch": 0.5441680238108609,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978861390326998,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.16902426183223723,
|
|
"num_tokens": 10803515.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.743325138092041,
|
|
"epoch": 0.5447296007188185,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004978806449931854,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.16652368605136872,
|
|
"num_tokens": 10814508.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.720365381240844,
|
|
"epoch": 0.545291177626776,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978751438570647,
|
|
"loss": 5.7758,
|
|
"mean_token_accuracy": 0.16612116992473602,
|
|
"num_tokens": 10825924.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.818812465667724,
|
|
"epoch": 0.5458527545347336,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004978696356245129,
|
|
"loss": 5.7593,
|
|
"mean_token_accuracy": 0.16557697504758834,
|
|
"num_tokens": 10837854.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.781116628646851,
|
|
"epoch": 0.546414331442691,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004978641202957057,
|
|
"loss": 5.6525,
|
|
"mean_token_accuracy": 0.1687871664762497,
|
|
"num_tokens": 10848279.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.591874265670777,
|
|
"epoch": 0.5469759083506486,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978585978708183,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.16745017170906068,
|
|
"num_tokens": 10859615.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.789039373397827,
|
|
"epoch": 0.5475374852586061,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004978530683500267,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.16729694455862046,
|
|
"num_tokens": 10871388.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.763914108276367,
|
|
"epoch": 0.5480990621665637,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004978475317335071,
|
|
"loss": 5.6953,
|
|
"mean_token_accuracy": 0.16814433187246322,
|
|
"num_tokens": 10882411.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.690453386306762,
|
|
"epoch": 0.5486606390745212,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004978419880214356,
|
|
"loss": 5.7978,
|
|
"mean_token_accuracy": 0.16985139697790147,
|
|
"num_tokens": 10894116.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.716488027572632,
|
|
"epoch": 0.5492222159824788,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004978364372139887,
|
|
"loss": 5.5763,
|
|
"mean_token_accuracy": 0.17307210266590117,
|
|
"num_tokens": 10904514.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.706024026870727,
|
|
"epoch": 0.5497837928904363,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004978308793113434,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.172774338722229,
|
|
"num_tokens": 10915602.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.679816198348999,
|
|
"epoch": 0.5503453697983939,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004978253143136762,
|
|
"loss": 5.6123,
|
|
"mean_token_accuracy": 0.17491503208875656,
|
|
"num_tokens": 10926172.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.768089532852173,
|
|
"epoch": 0.5509069467063514,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004978197422211647,
|
|
"loss": 5.7276,
|
|
"mean_token_accuracy": 0.16194030344486238,
|
|
"num_tokens": 10938435.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.62318377494812,
|
|
"epoch": 0.551468523614309,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004978141630339863,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.16984103322029115,
|
|
"num_tokens": 10949118.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.694841146469116,
|
|
"epoch": 0.5520301005222665,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978085767523184,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.1675533503293991,
|
|
"num_tokens": 10960120.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.749897003173828,
|
|
"epoch": 0.5525916774302241,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497802983376339,
|
|
"loss": 5.6453,
|
|
"mean_token_accuracy": 0.17328166514635085,
|
|
"num_tokens": 10971210.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.660398054122925,
|
|
"epoch": 0.5531532543381816,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977973829062263,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.17784592062234877,
|
|
"num_tokens": 10983446.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.823080062866211,
|
|
"epoch": 0.5537148312461392,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004977917753421585,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.168024505674839,
|
|
"num_tokens": 10994776.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.783946752548218,
|
|
"epoch": 0.5542764081540967,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000497786160684314,
|
|
"loss": 5.6654,
|
|
"mean_token_accuracy": 0.16811609417200088,
|
|
"num_tokens": 11005280.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.655294036865234,
|
|
"epoch": 0.5548379850620543,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004977805389328719,
|
|
"loss": 5.6632,
|
|
"mean_token_accuracy": 0.16550666093826294,
|
|
"num_tokens": 11017509.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.766216039657593,
|
|
"epoch": 0.5553995619700118,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000497774910088011,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.1684647172689438,
|
|
"num_tokens": 11029087.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.7780187129974365,
|
|
"epoch": 0.5559611388779694,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004977692741499106,
|
|
"loss": 5.73,
|
|
"mean_token_accuracy": 0.16323009133338928,
|
|
"num_tokens": 11041144.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.893393087387085,
|
|
"epoch": 0.5565227157859269,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00049776363111875,
|
|
"loss": 5.8058,
|
|
"mean_token_accuracy": 0.16435927748680115,
|
|
"num_tokens": 11054050.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.674776077270508,
|
|
"epoch": 0.5570842926938844,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004977579809947091,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17371438443660736,
|
|
"num_tokens": 11064257.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.754918098449707,
|
|
"epoch": 0.5576458696018419,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004977523237779676,
|
|
"loss": 5.7426,
|
|
"mean_token_accuracy": 0.16856040209531784,
|
|
"num_tokens": 11075568.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.74004340171814,
|
|
"epoch": 0.5582074465097995,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004977466594687057,
|
|
"loss": 5.6893,
|
|
"mean_token_accuracy": 0.1678532615303993,
|
|
"num_tokens": 11087078.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.879389715194702,
|
|
"epoch": 0.558769023417757,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004977409880671039,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.16045501381158828,
|
|
"num_tokens": 11100655.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.79177041053772,
|
|
"epoch": 0.5593306003257146,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004977353095733427,
|
|
"loss": 5.7301,
|
|
"mean_token_accuracy": 0.1673631638288498,
|
|
"num_tokens": 11110675.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.7390031814575195,
|
|
"epoch": 0.5598921772336721,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004977296239876026,
|
|
"loss": 5.7394,
|
|
"mean_token_accuracy": 0.16650383174419403,
|
|
"num_tokens": 11122337.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.84137716293335,
|
|
"epoch": 0.5604537541416297,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497723931310065,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.17311953008174896,
|
|
"num_tokens": 11132672.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.762862777709961,
|
|
"epoch": 0.5610153310495872,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004977182315409111,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.1720680683851242,
|
|
"num_tokens": 11143740.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.657700443267823,
|
|
"epoch": 0.5615769079575448,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004977125246803224,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1703295223414898,
|
|
"num_tokens": 11153722.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.731232309341431,
|
|
"epoch": 0.5621384848655023,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004977068107284803,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.16670638769865037,
|
|
"num_tokens": 11165042.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.720973968505859,
|
|
"epoch": 0.5627000617734599,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004977010896855672,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.17485188841819763,
|
|
"num_tokens": 11176834.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.683609962463379,
|
|
"epoch": 0.5632616386814174,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004976953615517649,
|
|
"loss": 5.6886,
|
|
"mean_token_accuracy": 0.16945749074220656,
|
|
"num_tokens": 11188442.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.682967281341552,
|
|
"epoch": 0.563823215589375,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000497689626327256,
|
|
"loss": 5.5846,
|
|
"mean_token_accuracy": 0.17421470284461976,
|
|
"num_tokens": 11197855.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.748038911819458,
|
|
"epoch": 0.5643847924973325,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497683884012223,
|
|
"loss": 5.7092,
|
|
"mean_token_accuracy": 0.16534993499517442,
|
|
"num_tokens": 11209300.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.711824750900268,
|
|
"epoch": 0.5649463694052901,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976781346068487,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.16874791383743287,
|
|
"num_tokens": 11222175.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.816490364074707,
|
|
"epoch": 0.5655079463132476,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004976723781113163,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.16723892986774444,
|
|
"num_tokens": 11233277.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.795160245895386,
|
|
"epoch": 0.5660695232212052,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004976666145258089,
|
|
"loss": 5.7222,
|
|
"mean_token_accuracy": 0.16821972131729127,
|
|
"num_tokens": 11245241.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.8035813331604,
|
|
"epoch": 0.5666311001291627,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004976608438505103,
|
|
"loss": 5.7578,
|
|
"mean_token_accuracy": 0.16516544073820114,
|
|
"num_tokens": 11257359.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.689214563369751,
|
|
"epoch": 0.5671926770371203,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004976550660856041,
|
|
"loss": 5.6911,
|
|
"mean_token_accuracy": 0.16714785099029542,
|
|
"num_tokens": 11270651.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.761755514144897,
|
|
"epoch": 0.5677542539450777,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000497649281231274,
|
|
"loss": 5.6421,
|
|
"mean_token_accuracy": 0.1724102735519409,
|
|
"num_tokens": 11280164.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.667131090164185,
|
|
"epoch": 0.5683158308530353,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004976434892877046,
|
|
"loss": 5.5951,
|
|
"mean_token_accuracy": 0.170241841673851,
|
|
"num_tokens": 11290156.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.683420705795288,
|
|
"epoch": 0.5688774077609928,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004976376902550802,
|
|
"loss": 5.6404,
|
|
"mean_token_accuracy": 0.1745462015271187,
|
|
"num_tokens": 11301929.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.672666549682617,
|
|
"epoch": 0.5694389846689504,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004976318841335854,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.17033572643995284,
|
|
"num_tokens": 11312805.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.5513694286346436,
|
|
"epoch": 0.5700005615769079,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004976260709234049,
|
|
"loss": 5.4776,
|
|
"mean_token_accuracy": 0.17846701443195342,
|
|
"num_tokens": 11322316.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.673481464385986,
|
|
"epoch": 0.5705621384848655,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000497620250624724,
|
|
"loss": 5.6625,
|
|
"mean_token_accuracy": 0.168160979449749,
|
|
"num_tokens": 11332994.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.731102514266968,
|
|
"epoch": 0.571123715392823,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497614423237728,
|
|
"loss": 5.6478,
|
|
"mean_token_accuracy": 0.16410341411828994,
|
|
"num_tokens": 11344355.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.755961799621582,
|
|
"epoch": 0.5716852923007806,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004976085887626026,
|
|
"loss": 5.6859,
|
|
"mean_token_accuracy": 0.1644878640770912,
|
|
"num_tokens": 11356275.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.714043235778808,
|
|
"epoch": 0.5722468692087381,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004976027471995331,
|
|
"loss": 5.6722,
|
|
"mean_token_accuracy": 0.16714242249727249,
|
|
"num_tokens": 11368624.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.838095092773438,
|
|
"epoch": 0.5728084461166957,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000497596898548706,
|
|
"loss": 5.7902,
|
|
"mean_token_accuracy": 0.1670762538909912,
|
|
"num_tokens": 11380520.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.72771463394165,
|
|
"epoch": 0.5733700230246532,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004975910428103072,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.1712417036294937,
|
|
"num_tokens": 11392293.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.77564263343811,
|
|
"epoch": 0.5739315999326108,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004975851799845233,
|
|
"loss": 5.7477,
|
|
"mean_token_accuracy": 0.1609713301062584,
|
|
"num_tokens": 11403866.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.7174805164337155,
|
|
"epoch": 0.5744931768405683,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497579310071541,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.1773075968027115,
|
|
"num_tokens": 11415334.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.695023250579834,
|
|
"epoch": 0.5750547537485259,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975734330715471,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.17263314127922058,
|
|
"num_tokens": 11426840.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.828223514556885,
|
|
"epoch": 0.5756163306564834,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004975675489847287,
|
|
"loss": 5.8743,
|
|
"mean_token_accuracy": 0.16070988178253173,
|
|
"num_tokens": 11438497.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.744170665740967,
|
|
"epoch": 0.576177907564441,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004975616578112734,
|
|
"loss": 5.5937,
|
|
"mean_token_accuracy": 0.1733261078596115,
|
|
"num_tokens": 11448705.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.8107377052307125,
|
|
"epoch": 0.5767394844723985,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004975557595513684,
|
|
"loss": 5.8578,
|
|
"mean_token_accuracy": 0.15883452147245408,
|
|
"num_tokens": 11460610.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.74539532661438,
|
|
"epoch": 0.5773010613803561,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975498542052018,
|
|
"loss": 5.605,
|
|
"mean_token_accuracy": 0.17099628299474717,
|
|
"num_tokens": 11471170.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.679078483581543,
|
|
"epoch": 0.5778626382883136,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004975439417729615,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.17529835253953935,
|
|
"num_tokens": 11482090.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.65677580833435,
|
|
"epoch": 0.5784242151962711,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004975380222548358,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.1676223248243332,
|
|
"num_tokens": 11493650.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.793863105773926,
|
|
"epoch": 0.5789857921042286,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004975320956510131,
|
|
"loss": 5.6804,
|
|
"mean_token_accuracy": 0.16365675926208495,
|
|
"num_tokens": 11505903.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.800598621368408,
|
|
"epoch": 0.5795473690121862,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975261619616822,
|
|
"loss": 5.7216,
|
|
"mean_token_accuracy": 0.16538747251033784,
|
|
"num_tokens": 11517194.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.749587106704712,
|
|
"epoch": 0.5801089459201437,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004975202211870321,
|
|
"loss": 5.7385,
|
|
"mean_token_accuracy": 0.17027612626552582,
|
|
"num_tokens": 11528683.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.798511075973511,
|
|
"epoch": 0.5806705228281013,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004975142733272518,
|
|
"loss": 5.7564,
|
|
"mean_token_accuracy": 0.170464625954628,
|
|
"num_tokens": 11541940.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.699113464355468,
|
|
"epoch": 0.5812320997360588,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004975083183825306,
|
|
"loss": 5.6437,
|
|
"mean_token_accuracy": 0.16955529302358627,
|
|
"num_tokens": 11553045.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.673072004318238,
|
|
"epoch": 0.5817936766440164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004975023563530584,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.1740681931376457,
|
|
"num_tokens": 11564401.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.739364957809448,
|
|
"epoch": 0.5823552535519739,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004974963872390249,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.16787558943033218,
|
|
"num_tokens": 11576424.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.767311382293701,
|
|
"epoch": 0.5829168304599315,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00049749041104062,
|
|
"loss": 5.6521,
|
|
"mean_token_accuracy": 0.1702180325984955,
|
|
"num_tokens": 11587853.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.693006944656372,
|
|
"epoch": 0.583478407367889,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974844277580343,
|
|
"loss": 5.6409,
|
|
"mean_token_accuracy": 0.17287682145833969,
|
|
"num_tokens": 11597938.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.89892430305481,
|
|
"epoch": 0.5840399842758466,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004974784373914579,
|
|
"loss": 5.8141,
|
|
"mean_token_accuracy": 0.16825189739465712,
|
|
"num_tokens": 11610077.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.726883411407471,
|
|
"epoch": 0.5846015611838041,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974724399410818,
|
|
"loss": 5.6849,
|
|
"mean_token_accuracy": 0.1705661192536354,
|
|
"num_tokens": 11622079.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.64487771987915,
|
|
"epoch": 0.5851631380917617,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004974664354070971,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.17759737819433213,
|
|
"num_tokens": 11633047.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.698882293701172,
|
|
"epoch": 0.5857247149997192,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004974604237896947,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.17522530853748322,
|
|
"num_tokens": 11643858.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.64196810722351,
|
|
"epoch": 0.5862862919076768,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004974544050890662,
|
|
"loss": 5.5945,
|
|
"mean_token_accuracy": 0.17349391728639602,
|
|
"num_tokens": 11654550.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.656215047836303,
|
|
"epoch": 0.5868478688156343,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000497448379305403,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.17360166013240813,
|
|
"num_tokens": 11665787.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.778688240051269,
|
|
"epoch": 0.5874094457235919,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004974423464388973,
|
|
"loss": 5.7384,
|
|
"mean_token_accuracy": 0.16588782221078874,
|
|
"num_tokens": 11677717.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.717018556594849,
|
|
"epoch": 0.5879710226315494,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.000497436306489741,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.17217543125152587,
|
|
"num_tokens": 11687714.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.634124279022217,
|
|
"epoch": 0.588532599539507,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004974302594581264,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.1784164071083069,
|
|
"num_tokens": 11698777.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.730188989639283,
|
|
"epoch": 0.5890941764474645,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004974242053442461,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.17433087080717086,
|
|
"num_tokens": 11710922.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.689811277389526,
|
|
"epoch": 0.589655753355422,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004974181441482927,
|
|
"loss": 5.6588,
|
|
"mean_token_accuracy": 0.1682141453027725,
|
|
"num_tokens": 11721450.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.627566766738892,
|
|
"epoch": 0.5902173302633795,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974120758704595,
|
|
"loss": 5.5726,
|
|
"mean_token_accuracy": 0.17209893763065337,
|
|
"num_tokens": 11732458.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.652285432815551,
|
|
"epoch": 0.5907789071713371,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004974060005109394,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.1728219747543335,
|
|
"num_tokens": 11742649.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.679883909225464,
|
|
"epoch": 0.5913404840792946,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000497399918069926,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.17694215178489686,
|
|
"num_tokens": 11753811.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.728500938415527,
|
|
"epoch": 0.5919020609872522,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004973938285476131,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.16357526928186417,
|
|
"num_tokens": 11763965.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.768399477005005,
|
|
"epoch": 0.5924636378952097,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004973877319441943,
|
|
"loss": 5.6805,
|
|
"mean_token_accuracy": 0.17441145181655884,
|
|
"num_tokens": 11774323.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.699795436859131,
|
|
"epoch": 0.5930252148031673,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973816282598639,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.16491901576519014,
|
|
"num_tokens": 11786157.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.776006031036377,
|
|
"epoch": 0.5935867917111248,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004973755174948162,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.17518796324729918,
|
|
"num_tokens": 11797344.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.546476364135742,
|
|
"epoch": 0.5941483686190824,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004973693996492458,
|
|
"loss": 5.5957,
|
|
"mean_token_accuracy": 0.1724376916885376,
|
|
"num_tokens": 11808149.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.6592247009277346,
|
|
"epoch": 0.5947099455270399,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004973632747233475,
|
|
"loss": 5.6068,
|
|
"mean_token_accuracy": 0.17740679681301116,
|
|
"num_tokens": 11820203.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.744556331634522,
|
|
"epoch": 0.5952715224349975,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004973571427173163,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.1680813506245613,
|
|
"num_tokens": 11830172.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.703446102142334,
|
|
"epoch": 0.595833099342955,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973510036313473,
|
|
"loss": 5.6335,
|
|
"mean_token_accuracy": 0.17647795230150223,
|
|
"num_tokens": 11840203.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.77345495223999,
|
|
"epoch": 0.5963946762509126,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973448574656362,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.16958763003349303,
|
|
"num_tokens": 11851002.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.626795053482056,
|
|
"epoch": 0.5969562531588701,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004973387042203786,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17143273502588272,
|
|
"num_tokens": 11861559.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.679839086532593,
|
|
"epoch": 0.5975178300668277,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004973325438957704,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.17016649395227432,
|
|
"num_tokens": 11872535.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.762483692169189,
|
|
"epoch": 0.5980794069747852,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004973263764920079,
|
|
"loss": 5.6715,
|
|
"mean_token_accuracy": 0.1738652765750885,
|
|
"num_tokens": 11884308.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.806181383132935,
|
|
"epoch": 0.5986409838827428,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004973202020092871,
|
|
"loss": 5.7519,
|
|
"mean_token_accuracy": 0.16892225295305252,
|
|
"num_tokens": 11896136.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.712234687805176,
|
|
"epoch": 0.5992025607907003,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000497314020447805,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.17853899747133256,
|
|
"num_tokens": 11906497.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.742883348464966,
|
|
"epoch": 0.5997641376986579,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004973078318077583,
|
|
"loss": 5.7007,
|
|
"mean_token_accuracy": 0.1634941890835762,
|
|
"num_tokens": 11917872.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.782249879837036,
|
|
"epoch": 0.6003257146066153,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000497301636089344,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.16188825368881227,
|
|
"num_tokens": 11929727.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.714706230163574,
|
|
"epoch": 0.6008872915145729,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004972954332927592,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.172914457321167,
|
|
"num_tokens": 11939996.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.655025053024292,
|
|
"epoch": 0.6014488684225304,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004972892234182018,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.1797083854675293,
|
|
"num_tokens": 11950683.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.645558881759643,
|
|
"epoch": 0.602010445330488,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004972830064658692,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.16968246847391127,
|
|
"num_tokens": 11962447.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.741198587417602,
|
|
"epoch": 0.6025720222384455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004972767824359596,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.1680271163582802,
|
|
"num_tokens": 11972740.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.702940845489502,
|
|
"epoch": 0.6031335991464031,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972705513286709,
|
|
"loss": 5.5656,
|
|
"mean_token_accuracy": 0.17291281819343568,
|
|
"num_tokens": 11983292.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.757178688049317,
|
|
"epoch": 0.6036951760543606,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972643131442017,
|
|
"loss": 5.7817,
|
|
"mean_token_accuracy": 0.16330262422561645,
|
|
"num_tokens": 11996384.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.837067937850952,
|
|
"epoch": 0.6042567529623182,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004972580678827506,
|
|
"loss": 5.7172,
|
|
"mean_token_accuracy": 0.17756523787975312,
|
|
"num_tokens": 12006938.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.593442964553833,
|
|
"epoch": 0.6048183298702757,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004972518155445163,
|
|
"loss": 5.5172,
|
|
"mean_token_accuracy": 0.17432504147291183,
|
|
"num_tokens": 12018729.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.8429059982299805,
|
|
"epoch": 0.6053799067782333,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004972455561296982,
|
|
"loss": 5.8669,
|
|
"mean_token_accuracy": 0.16173077821731568,
|
|
"num_tokens": 12029625.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.736613702774048,
|
|
"epoch": 0.6059414836861908,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004972392896384952,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16894275844097137,
|
|
"num_tokens": 12040243.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.816641330718994,
|
|
"epoch": 0.6065030605941484,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972330160711071,
|
|
"loss": 5.8494,
|
|
"mean_token_accuracy": 0.1588730737566948,
|
|
"num_tokens": 12051961.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.768970632553101,
|
|
"epoch": 0.6070646375021059,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004972267354277336,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.16878389567136765,
|
|
"num_tokens": 12063969.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.707594966888427,
|
|
"epoch": 0.6076262144100635,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004972204477085746,
|
|
"loss": 5.6049,
|
|
"mean_token_accuracy": 0.17066328525543212,
|
|
"num_tokens": 12075682.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.76522536277771,
|
|
"epoch": 0.608187791318021,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004972141529138303,
|
|
"loss": 5.7495,
|
|
"mean_token_accuracy": 0.17008795440196992,
|
|
"num_tokens": 12086595.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.778849744796753,
|
|
"epoch": 0.6087493682259786,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004972078510437013,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.16765085905790328,
|
|
"num_tokens": 12099421.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.77406792640686,
|
|
"epoch": 0.6093109451339361,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004972015420983882,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.16803952753543855,
|
|
"num_tokens": 12109680.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.607671546936035,
|
|
"epoch": 0.6098725220418937,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004971952260780915,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.17912654280662538,
|
|
"num_tokens": 12121196.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.657910251617432,
|
|
"epoch": 0.6104340989498512,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497188902983013,
|
|
"loss": 5.5493,
|
|
"mean_token_accuracy": 0.16684468388557433,
|
|
"num_tokens": 12132262.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.781585264205932,
|
|
"epoch": 0.6109956758578087,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971825728133535,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.17029269635677338,
|
|
"num_tokens": 12143747.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.912602138519287,
|
|
"epoch": 0.6115572527657662,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004971762355693146,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.16162934452295302,
|
|
"num_tokens": 12155887.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.670290422439575,
|
|
"epoch": 0.6121188296737238,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004971698912510983,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.1679929792881012,
|
|
"num_tokens": 12166718.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.728014612197876,
|
|
"epoch": 0.6126804065816813,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004971635398589066,
|
|
"loss": 5.7619,
|
|
"mean_token_accuracy": 0.16809399127960206,
|
|
"num_tokens": 12178540.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.892739295959473,
|
|
"epoch": 0.6132419834896389,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004971571813929415,
|
|
"loss": 5.7893,
|
|
"mean_token_accuracy": 0.1642976239323616,
|
|
"num_tokens": 12189820.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.716569328308106,
|
|
"epoch": 0.6138035603975964,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971508158534056,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.17245467007160187,
|
|
"num_tokens": 12201679.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.733164882659912,
|
|
"epoch": 0.614365137305554,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971444432405015,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.16714466065168382,
|
|
"num_tokens": 12213793.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.8958207130432125,
|
|
"epoch": 0.6149267142135115,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004971380635544323,
|
|
"loss": 5.7911,
|
|
"mean_token_accuracy": 0.1678582414984703,
|
|
"num_tokens": 12224519.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.856304883956909,
|
|
"epoch": 0.6154882911214691,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004971316767954009,
|
|
"loss": 5.7897,
|
|
"mean_token_accuracy": 0.16010832339525222,
|
|
"num_tokens": 12236401.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.7706811904907225,
|
|
"epoch": 0.6160498680294266,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004971252829636108,
|
|
"loss": 5.8137,
|
|
"mean_token_accuracy": 0.15960222035646437,
|
|
"num_tokens": 12247670.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.722423982620239,
|
|
"epoch": 0.6166114449373842,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004971188820592656,
|
|
"loss": 5.6696,
|
|
"mean_token_accuracy": 0.17000555098056794,
|
|
"num_tokens": 12258877.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.726262998580933,
|
|
"epoch": 0.6171730218453417,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000497112474082569,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.16906244307756424,
|
|
"num_tokens": 12268507.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.729124641418457,
|
|
"epoch": 0.6177345987532993,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497106059033725,
|
|
"loss": 5.6415,
|
|
"mean_token_accuracy": 0.16383383572101592,
|
|
"num_tokens": 12280420.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.614401769638062,
|
|
"epoch": 0.6182961756612568,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004970996369129381,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.16856159120798112,
|
|
"num_tokens": 12290876.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.706183195114136,
|
|
"epoch": 0.6188577525692144,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970932077204125,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.17552035599946975,
|
|
"num_tokens": 12301831.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.645649766921997,
|
|
"epoch": 0.6194193294771719,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000497086771456353,
|
|
"loss": 5.5708,
|
|
"mean_token_accuracy": 0.17358496636152268,
|
|
"num_tokens": 12312678.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.75670051574707,
|
|
"epoch": 0.6199809063851295,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004970803281209646,
|
|
"loss": 5.7344,
|
|
"mean_token_accuracy": 0.16434017866849898,
|
|
"num_tokens": 12322905.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.703006029129028,
|
|
"epoch": 0.620542483293087,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004970738777144524,
|
|
"loss": 5.6067,
|
|
"mean_token_accuracy": 0.17090702652931214,
|
|
"num_tokens": 12333091.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.737433195114136,
|
|
"epoch": 0.6211040602010446,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004970674202370218,
|
|
"loss": 5.614,
|
|
"mean_token_accuracy": 0.1722594529390335,
|
|
"num_tokens": 12346310.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.692054891586304,
|
|
"epoch": 0.621665637109002,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004970609556888785,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.1692933440208435,
|
|
"num_tokens": 12357138.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.7690403938293455,
|
|
"epoch": 0.6222272140169596,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970544840702282,
|
|
"loss": 5.6419,
|
|
"mean_token_accuracy": 0.17450788766145706,
|
|
"num_tokens": 12367382.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.674743509292602,
|
|
"epoch": 0.6227887909249171,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970480053812771,
|
|
"loss": 5.6282,
|
|
"mean_token_accuracy": 0.16198393255472182,
|
|
"num_tokens": 12380357.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.808923578262329,
|
|
"epoch": 0.6233503678328747,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004970415196222312,
|
|
"loss": 5.8068,
|
|
"mean_token_accuracy": 0.15982981026172638,
|
|
"num_tokens": 12392187.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.711451530456543,
|
|
"epoch": 0.6239119447408322,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004970350267932973,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.17200725376605988,
|
|
"num_tokens": 12402924.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.780665159225464,
|
|
"epoch": 0.6244735216487898,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497028526894682,
|
|
"loss": 5.7819,
|
|
"mean_token_accuracy": 0.16798316985368728,
|
|
"num_tokens": 12413554.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.802480316162109,
|
|
"epoch": 0.6250350985567473,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970220199265923,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.17256978005170823,
|
|
"num_tokens": 12424525.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.678088045120239,
|
|
"epoch": 0.6255966754647049,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004970155058892354,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.17323838025331498,
|
|
"num_tokens": 12436405.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.7366368770599365,
|
|
"epoch": 0.6261582523726624,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004970089847828187,
|
|
"loss": 5.7125,
|
|
"mean_token_accuracy": 0.16818446069955825,
|
|
"num_tokens": 12446909.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.796042251586914,
|
|
"epoch": 0.62671982928062,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004970024566075497,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.17036909162998198,
|
|
"num_tokens": 12458739.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.671016454696655,
|
|
"epoch": 0.6272814061885775,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004969959213636365,
|
|
"loss": 5.6352,
|
|
"mean_token_accuracy": 0.16721768230199813,
|
|
"num_tokens": 12469529.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.759432458877564,
|
|
"epoch": 0.6278429830965351,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004969893790512871,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.16599516421556473,
|
|
"num_tokens": 12480067.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.687450170516968,
|
|
"epoch": 0.6284045600044926,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004969828296707097,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.17800821363925934,
|
|
"num_tokens": 12491043.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.618677759170533,
|
|
"epoch": 0.6289661369124502,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004969762732221129,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.1769825577735901,
|
|
"num_tokens": 12501852.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.727178621292114,
|
|
"epoch": 0.6295277138204077,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004969697097057054,
|
|
"loss": 5.7901,
|
|
"mean_token_accuracy": 0.1657552167773247,
|
|
"num_tokens": 12512696.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.784889030456543,
|
|
"epoch": 0.6300892907283653,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969631391216964,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.17386947721242904,
|
|
"num_tokens": 12523643.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.714351654052734,
|
|
"epoch": 0.6306508676363228,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969565614702948,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.16870810687541962,
|
|
"num_tokens": 12534827.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.594786167144775,
|
|
"epoch": 0.6312124445442804,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969499767517104,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.17086122632026673,
|
|
"num_tokens": 12545977.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.579933786392212,
|
|
"epoch": 0.6317740214522379,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004969433849661525,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.16783222258090974,
|
|
"num_tokens": 12555890.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.639198684692383,
|
|
"epoch": 0.6323355983601955,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969367861138313,
|
|
"loss": 5.6306,
|
|
"mean_token_accuracy": 0.17302785217761993,
|
|
"num_tokens": 12566412.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.783965921401977,
|
|
"epoch": 0.6328971752681529,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004969301801949565,
|
|
"loss": 5.6637,
|
|
"mean_token_accuracy": 0.16837894916534424,
|
|
"num_tokens": 12577175.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.663029146194458,
|
|
"epoch": 0.6334587521761105,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000496923567209739,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.16810460537672042,
|
|
"num_tokens": 12588760.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.65317006111145,
|
|
"epoch": 0.634020329084068,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004969169471583889,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.17247953563928603,
|
|
"num_tokens": 12599899.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.7562490940094,
|
|
"epoch": 0.6345819059920256,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969103200411171,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.1819773271679878,
|
|
"num_tokens": 12610836.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.633259582519531,
|
|
"epoch": 0.6351434828999831,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004969036858581346,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.17736711204051972,
|
|
"num_tokens": 12621855.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.699457168579102,
|
|
"epoch": 0.6357050598079407,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004968970446096527,
|
|
"loss": 5.6765,
|
|
"mean_token_accuracy": 0.17143414169549942,
|
|
"num_tokens": 12632964.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.6392772674560545,
|
|
"epoch": 0.6362666367158982,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496890396295883,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.1813375934958458,
|
|
"num_tokens": 12643717.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.738263511657715,
|
|
"epoch": 0.6368282136238558,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004968837409170368,
|
|
"loss": 5.6306,
|
|
"mean_token_accuracy": 0.1659584939479828,
|
|
"num_tokens": 12654491.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.667073154449463,
|
|
"epoch": 0.6373897905318133,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004968770784733263,
|
|
"loss": 5.6833,
|
|
"mean_token_accuracy": 0.17058739066123962,
|
|
"num_tokens": 12666128.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.80188946723938,
|
|
"epoch": 0.6379513674397709,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004968704089649636,
|
|
"loss": 5.7579,
|
|
"mean_token_accuracy": 0.16748515665531158,
|
|
"num_tokens": 12677957.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.735835361480713,
|
|
"epoch": 0.6385129443477284,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004968637323921611,
|
|
"loss": 5.5886,
|
|
"mean_token_accuracy": 0.175058613717556,
|
|
"num_tokens": 12687964.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.573977756500244,
|
|
"epoch": 0.639074521255686,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004968570487551312,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1661873370409012,
|
|
"num_tokens": 12698805.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.773652219772339,
|
|
"epoch": 0.6396360981636435,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004968503580540869,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.17248007655143738,
|
|
"num_tokens": 12709942.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.79822006225586,
|
|
"epoch": 0.6401976750716011,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004968436602892411,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.17039266228675842,
|
|
"num_tokens": 12721856.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.547451829910278,
|
|
"epoch": 0.6407592519795586,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004968369554608071,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.1689848929643631,
|
|
"num_tokens": 12732619.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.643662405014038,
|
|
"epoch": 0.6413208288875162,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968302435689985,
|
|
"loss": 5.6189,
|
|
"mean_token_accuracy": 0.1717173457145691,
|
|
"num_tokens": 12743478.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.677690744400024,
|
|
"epoch": 0.6418824057954737,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004968235246140288,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.16772045642137529,
|
|
"num_tokens": 12754761.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.75284972190857,
|
|
"epoch": 0.6424439827034313,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004968167985961121,
|
|
"loss": 5.6728,
|
|
"mean_token_accuracy": 0.1740880772471428,
|
|
"num_tokens": 12765803.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.7251951694488525,
|
|
"epoch": 0.6430055596113888,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004968100655154625,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.16545101404190063,
|
|
"num_tokens": 12777882.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.78673791885376,
|
|
"epoch": 0.6435671365193463,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004968033253722943,
|
|
"loss": 5.6983,
|
|
"mean_token_accuracy": 0.16673177778720855,
|
|
"num_tokens": 12788268.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.723522281646728,
|
|
"epoch": 0.6441287134273038,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004967965781668223,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.1726821169257164,
|
|
"num_tokens": 12800506.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.6851358890533445,
|
|
"epoch": 0.6446902903352614,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004967898238992613,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.1702310025691986,
|
|
"num_tokens": 12813040.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.8075498104095455,
|
|
"epoch": 0.6452518672432189,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004967830625698262,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.17280594855546952,
|
|
"num_tokens": 12825534.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.694971704483033,
|
|
"epoch": 0.6458134441511765,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004967762941787323,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.1711387887597084,
|
|
"num_tokens": 12835882.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.692767381668091,
|
|
"epoch": 0.646375021059134,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004967695187261952,
|
|
"loss": 5.7741,
|
|
"mean_token_accuracy": 0.16599494963884354,
|
|
"num_tokens": 12847663.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.918551349639893,
|
|
"epoch": 0.6469365979670916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967627362124306,
|
|
"loss": 5.9165,
|
|
"mean_token_accuracy": 0.16107620000839235,
|
|
"num_tokens": 12860789.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.809067821502685,
|
|
"epoch": 0.6474981748750491,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004967559466376546,
|
|
"loss": 5.6502,
|
|
"mean_token_accuracy": 0.16848702877759933,
|
|
"num_tokens": 12872509.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.67712025642395,
|
|
"epoch": 0.6480597517830067,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004967491500020831,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.1710699163377285,
|
|
"num_tokens": 12884321.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.583442497253418,
|
|
"epoch": 0.6486213286909642,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004967423463059328,
|
|
"loss": 5.5249,
|
|
"mean_token_accuracy": 0.17490473687648772,
|
|
"num_tokens": 12894559.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.708324337005616,
|
|
"epoch": 0.6491829055989218,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004967355355494201,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.17839192748069763,
|
|
"num_tokens": 12904934.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.788845252990723,
|
|
"epoch": 0.6497444825068793,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000496728717732762,
|
|
"loss": 5.7476,
|
|
"mean_token_accuracy": 0.1606523036956787,
|
|
"num_tokens": 12916551.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.700107192993164,
|
|
"epoch": 0.6503060594148369,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004967218928561755,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.16659311354160308,
|
|
"num_tokens": 12928097.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.752476549148559,
|
|
"epoch": 0.6508676363227944,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004967150609198779,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.17775413244962693,
|
|
"num_tokens": 12939161.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.57533540725708,
|
|
"epoch": 0.651429213230752,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004967082219240869,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.17241576611995696,
|
|
"num_tokens": 12950862.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.695456552505493,
|
|
"epoch": 0.6519907901387095,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004967013758690199,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.16945968866348265,
|
|
"num_tokens": 12962333.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.712745952606201,
|
|
"epoch": 0.6525523670466671,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004966945227548953,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.16942909955978394,
|
|
"num_tokens": 12973136.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.674942588806152,
|
|
"epoch": 0.6531139439546246,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966876625819309,
|
|
"loss": 5.6183,
|
|
"mean_token_accuracy": 0.16683624237775802,
|
|
"num_tokens": 12983602.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.686498308181763,
|
|
"epoch": 0.6536755208625822,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966807953503456,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.17992538064718247,
|
|
"num_tokens": 12994129.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.722739791870117,
|
|
"epoch": 0.6542370977705396,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004966739210603578,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.1726296916604042,
|
|
"num_tokens": 13005071.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.7870251655578615,
|
|
"epoch": 0.6547986746784972,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004966670397121862,
|
|
"loss": 5.7638,
|
|
"mean_token_accuracy": 0.16760697066783906,
|
|
"num_tokens": 13016202.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.838914012908935,
|
|
"epoch": 0.6553602515864547,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004966601513060502,
|
|
"loss": 5.7832,
|
|
"mean_token_accuracy": 0.15765969604253768,
|
|
"num_tokens": 13028468.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.750772476196289,
|
|
"epoch": 0.6559218284944123,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000496653255842169,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.1685607388615608,
|
|
"num_tokens": 13039667.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.714856767654419,
|
|
"epoch": 0.6564834054023698,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004966463533207621,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.16423157453536988,
|
|
"num_tokens": 13051583.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.709032106399536,
|
|
"epoch": 0.6570449823103274,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004966394437420493,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.16966672092676163,
|
|
"num_tokens": 13062401.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.633921480178833,
|
|
"epoch": 0.6576065592182849,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004966325271062508,
|
|
"loss": 5.555,
|
|
"mean_token_accuracy": 0.1757974371314049,
|
|
"num_tokens": 13074219.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.7800849914550785,
|
|
"epoch": 0.6581681361262425,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004966256034135866,
|
|
"loss": 5.7583,
|
|
"mean_token_accuracy": 0.16613198518753053,
|
|
"num_tokens": 13086073.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.748238897323608,
|
|
"epoch": 0.6587297130342,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004966186726642772,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.1687328413128853,
|
|
"num_tokens": 13096340.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.7063556671142575,
|
|
"epoch": 0.6592912899421576,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004966117348585434,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.172160741686821,
|
|
"num_tokens": 13107273.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.591187620162964,
|
|
"epoch": 0.6598528668501151,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004966047899966059,
|
|
"loss": 5.5918,
|
|
"mean_token_accuracy": 0.16808079481124877,
|
|
"num_tokens": 13117388.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.738665199279785,
|
|
"epoch": 0.6604144437580727,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000496597838078686,
|
|
"loss": 5.7127,
|
|
"mean_token_accuracy": 0.16613983362913132,
|
|
"num_tokens": 13128720.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.84275860786438,
|
|
"epoch": 0.6609760206660302,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496590879105005,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.17708108574151993,
|
|
"num_tokens": 13139405.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.756698274612427,
|
|
"epoch": 0.6615375975739878,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004965839130757845,
|
|
"loss": 5.7188,
|
|
"mean_token_accuracy": 0.1700200155377388,
|
|
"num_tokens": 13151408.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.7110710620880125,
|
|
"epoch": 0.6620991744819453,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004965769399912462,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.17346349209547043,
|
|
"num_tokens": 13162592.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.753345966339111,
|
|
"epoch": 0.6626607513899029,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004965699598516122,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.17533411979675292,
|
|
"num_tokens": 13173040.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.681469964981079,
|
|
"epoch": 0.6632223282978604,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004965629726571047,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.17050910145044326,
|
|
"num_tokens": 13185475.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.761954593658447,
|
|
"epoch": 0.663783905205818,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004965559784079463,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.17331943809986114,
|
|
"num_tokens": 13196481.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.701173448562622,
|
|
"epoch": 0.6643454821137755,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965489771043596,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.1777922108769417,
|
|
"num_tokens": 13207947.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.537551403045654,
|
|
"epoch": 0.664907059021733,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004965419687465676,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.18254093825817108,
|
|
"num_tokens": 13219392.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.595963001251221,
|
|
"epoch": 0.6654686359296905,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004965349533347934,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.17730499058961868,
|
|
"num_tokens": 13231556.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.706314420700073,
|
|
"epoch": 0.6660302128376481,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004965279308692602,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.17761783301830292,
|
|
"num_tokens": 13241287.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.580294990539551,
|
|
"epoch": 0.6665917897456056,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004965209013501919,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.16694261282682418,
|
|
"num_tokens": 13254120.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.681415176391601,
|
|
"epoch": 0.6671533666535632,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004965138647778122,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.16876449584960937,
|
|
"num_tokens": 13265745.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.812445211410522,
|
|
"epoch": 0.6677149435615207,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496506821152345,
|
|
"loss": 5.7057,
|
|
"mean_token_accuracy": 0.16847524791955948,
|
|
"num_tokens": 13277791.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.622484540939331,
|
|
"epoch": 0.6682765204694783,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964997704740147,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.17113676518201829,
|
|
"num_tokens": 13288078.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.658145761489868,
|
|
"epoch": 0.6688380973774358,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000496492712743046,
|
|
"loss": 5.6212,
|
|
"mean_token_accuracy": 0.17363058030605316,
|
|
"num_tokens": 13300547.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.759668588638306,
|
|
"epoch": 0.6693996742853934,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964856479596632,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.1671416938304901,
|
|
"num_tokens": 13310339.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.799163675308227,
|
|
"epoch": 0.6699612511933509,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004964785761240915,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.1702686607837677,
|
|
"num_tokens": 13321294.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.73330283164978,
|
|
"epoch": 0.6705228281013085,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004964714972365562,
|
|
"loss": 5.677,
|
|
"mean_token_accuracy": 0.16910976767539979,
|
|
"num_tokens": 13332608.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.681737422943115,
|
|
"epoch": 0.671084405009266,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004964644112972824,
|
|
"loss": 5.6103,
|
|
"mean_token_accuracy": 0.1824873298406601,
|
|
"num_tokens": 13344169.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.621775817871094,
|
|
"epoch": 0.6716459819172236,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004964573183064959,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.17329125851392746,
|
|
"num_tokens": 13355713.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.740686750411987,
|
|
"epoch": 0.6722075588251811,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964502182644225,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.17253406047821046,
|
|
"num_tokens": 13366644.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.682976579666137,
|
|
"epoch": 0.6727691357331387,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964431111712883,
|
|
"loss": 5.6301,
|
|
"mean_token_accuracy": 0.16924109756946565,
|
|
"num_tokens": 13378125.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.68867039680481,
|
|
"epoch": 0.6733307126410962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004964359970273195,
|
|
"loss": 5.6853,
|
|
"mean_token_accuracy": 0.1685509651899338,
|
|
"num_tokens": 13389681.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.773538112640381,
|
|
"epoch": 0.6738922895490538,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004964288758327426,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.17139559984207153,
|
|
"num_tokens": 13399814.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.6738922895490538,
|
|
"eval_entropy": 5.5897311230802895,
|
|
"eval_loss": 5.669083118438721,
|
|
"eval_mean_token_accuracy": 0.17649661723369633,
|
|
"eval_num_tokens": 13399814.0,
|
|
"eval_runtime": 23.9271,
|
|
"eval_samples_per_second": 1296.145,
|
|
"eval_steps_per_second": 162.034,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.761659574508667,
|
|
"epoch": 0.6744538664570113,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004964217475877846,
|
|
"loss": 5.6826,
|
|
"mean_token_accuracy": 0.17530367821455,
|
|
"num_tokens": 13410614.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.713591384887695,
|
|
"epoch": 0.6750154433649689,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000496414612292672,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.1689791962504387,
|
|
"num_tokens": 13421392.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.779674005508423,
|
|
"epoch": 0.6755770202729264,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004964074699476325,
|
|
"loss": 5.7253,
|
|
"mean_token_accuracy": 0.1670072689652443,
|
|
"num_tokens": 13432004.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.713666820526123,
|
|
"epoch": 0.6761385971808839,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004964003205528933,
|
|
"loss": 5.5734,
|
|
"mean_token_accuracy": 0.1713683232665062,
|
|
"num_tokens": 13442450.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.707172918319702,
|
|
"epoch": 0.6767001740888414,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004963931641086819,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.16926868110895157,
|
|
"num_tokens": 13453848.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.679394388198853,
|
|
"epoch": 0.677261750996799,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004963860006152262,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.17169004827737808,
|
|
"num_tokens": 13465119.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.659357357025146,
|
|
"epoch": 0.6778233279047565,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004963788300727546,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.17482503205537797,
|
|
"num_tokens": 13475937.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.650514841079712,
|
|
"epoch": 0.6783849048127141,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004963716524814951,
|
|
"loss": 5.5875,
|
|
"mean_token_accuracy": 0.17779508084058762,
|
|
"num_tokens": 13487430.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.7497828006744385,
|
|
"epoch": 0.6789464817206716,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004963644678416763,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.17571300119161606,
|
|
"num_tokens": 13499631.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.713581848144531,
|
|
"epoch": 0.6795080586286292,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000496357276153527,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.16955469846725463,
|
|
"num_tokens": 13511753.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.697400522232056,
|
|
"epoch": 0.6800696355365867,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004963500774172763,
|
|
"loss": 5.7205,
|
|
"mean_token_accuracy": 0.1653860405087471,
|
|
"num_tokens": 13524228.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.808965158462525,
|
|
"epoch": 0.6806312124445443,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496342871633153,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.1691532164812088,
|
|
"num_tokens": 13535700.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.7298479080200195,
|
|
"epoch": 0.6811927893525018,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004963356588013871,
|
|
"loss": 5.727,
|
|
"mean_token_accuracy": 0.1661018580198288,
|
|
"num_tokens": 13547337.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.6549307346344,
|
|
"epoch": 0.6817543662604594,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004963284389222078,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.1701306775212288,
|
|
"num_tokens": 13558350.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.697028970718383,
|
|
"epoch": 0.6823159431684169,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963212119958453,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.1712794005870819,
|
|
"num_tokens": 13569230.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.717619371414185,
|
|
"epoch": 0.6828775200763745,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004963139780225295,
|
|
"loss": 5.7083,
|
|
"mean_token_accuracy": 0.17372886538505555,
|
|
"num_tokens": 13580502.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.7519784450531,
|
|
"epoch": 0.683439096984332,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004963067370024909,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.1758707121014595,
|
|
"num_tokens": 13591524.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.750894594192505,
|
|
"epoch": 0.6840006738922896,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004962994889359598,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.1788666859269142,
|
|
"num_tokens": 13602432.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.591702938079834,
|
|
"epoch": 0.6845622508002471,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962922338231673,
|
|
"loss": 5.5667,
|
|
"mean_token_accuracy": 0.18202456831932068,
|
|
"num_tokens": 13613052.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.581661558151245,
|
|
"epoch": 0.6851238277082047,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004962849716643441,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.17367575019598008,
|
|
"num_tokens": 13623961.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.6419919490814205,
|
|
"epoch": 0.6856854046161622,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004962777024597216,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.17128756791353225,
|
|
"num_tokens": 13635285.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.863709497451782,
|
|
"epoch": 0.6862469815241198,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004962704262095314,
|
|
"loss": 5.7421,
|
|
"mean_token_accuracy": 0.16478036493062972,
|
|
"num_tokens": 13647720.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.676465892791748,
|
|
"epoch": 0.6868085584320772,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004962631429140048,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.1700219139456749,
|
|
"num_tokens": 13659726.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.7783043384552,
|
|
"epoch": 0.6873701353400348,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000496255852573374,
|
|
"loss": 5.7769,
|
|
"mean_token_accuracy": 0.16442790478467942,
|
|
"num_tokens": 13670332.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.825065469741821,
|
|
"epoch": 0.6879317122479923,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004962485551878711,
|
|
"loss": 5.7195,
|
|
"mean_token_accuracy": 0.16384955495595932,
|
|
"num_tokens": 13682419.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.582127332687378,
|
|
"epoch": 0.6884932891559499,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004962412507577283,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.17686719000339507,
|
|
"num_tokens": 13692698.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.641467332839966,
|
|
"epoch": 0.6890548660639074,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962339392831783,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.16948507428169252,
|
|
"num_tokens": 13704791.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.7600044250488285,
|
|
"epoch": 0.689616442971865,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000496226620764454,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.17407870292663574,
|
|
"num_tokens": 13715860.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.672449970245362,
|
|
"epoch": 0.6901780198798225,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000496219295201788,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.17806624621152878,
|
|
"num_tokens": 13727029.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.670860242843628,
|
|
"epoch": 0.6907395967877801,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004962119625954141,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.17852981835603715,
|
|
"num_tokens": 13737168.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.819549417495727,
|
|
"epoch": 0.6913011736957376,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004962046229455653,
|
|
"loss": 5.7075,
|
|
"mean_token_accuracy": 0.16180982887744905,
|
|
"num_tokens": 13749828.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.675706672668457,
|
|
"epoch": 0.6918627506036952,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004961972762524757,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.16948773115873336,
|
|
"num_tokens": 13761617.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.702488946914673,
|
|
"epoch": 0.6924243275116527,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496189922516379,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.17705490589141845,
|
|
"num_tokens": 13772721.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.608817863464355,
|
|
"epoch": 0.6929859044196103,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961825617375093,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.17198578715324403,
|
|
"num_tokens": 13783215.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.635896825790406,
|
|
"epoch": 0.6935474813275678,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004961751939161011,
|
|
"loss": 5.5153,
|
|
"mean_token_accuracy": 0.17812756896018983,
|
|
"num_tokens": 13793496.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.563325023651123,
|
|
"epoch": 0.6941090582355254,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000496167819052389,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.17381619065999984,
|
|
"num_tokens": 13802818.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.813595533370972,
|
|
"epoch": 0.6946706351434829,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961604371466077,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.16662748605012895,
|
|
"num_tokens": 13814449.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.720846796035767,
|
|
"epoch": 0.6952322120514405,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004961530481989923,
|
|
"loss": 5.6771,
|
|
"mean_token_accuracy": 0.17422028481960297,
|
|
"num_tokens": 13825369.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.581100940704346,
|
|
"epoch": 0.695793788959398,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004961456522097782,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.1712140694260597,
|
|
"num_tokens": 13837992.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.729876708984375,
|
|
"epoch": 0.6963553658673556,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004961382491792006,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.16685957461595535,
|
|
"num_tokens": 13849771.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.681436252593994,
|
|
"epoch": 0.6969169427753131,
|
|
"grad_norm": 3.0,
|
|
"learning_rate": 0.0004961308391074953,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.17330627143383026,
|
|
"num_tokens": 13861997.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.717130088806153,
|
|
"epoch": 0.6974785196832706,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004961234219948986,
|
|
"loss": 5.7104,
|
|
"mean_token_accuracy": 0.16821808516979217,
|
|
"num_tokens": 13872972.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.58402681350708,
|
|
"epoch": 0.6980400965912281,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961159978416461,
|
|
"loss": 5.4845,
|
|
"mean_token_accuracy": 0.175821690261364,
|
|
"num_tokens": 13883139.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.6680896282196045,
|
|
"epoch": 0.6986016734991857,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004961085666479746,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.1738399550318718,
|
|
"num_tokens": 13894326.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.7257953643798825,
|
|
"epoch": 0.6991632504071432,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004961011284141206,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.17541969567537308,
|
|
"num_tokens": 13905525.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.683678340911865,
|
|
"epoch": 0.6997248273151008,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004960936831403209,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.17366371005773545,
|
|
"num_tokens": 13915973.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.650081205368042,
|
|
"epoch": 0.7002864042230583,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960862308268126,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.18039967715740204,
|
|
"num_tokens": 13926380.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.657723665237427,
|
|
"epoch": 0.7008479811310159,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004960787714738329,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.16768791526556015,
|
|
"num_tokens": 13938523.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.628818035125732,
|
|
"epoch": 0.7014095580389734,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004960713050816194,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.17659661173820496,
|
|
"num_tokens": 13949343.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.707599067687989,
|
|
"epoch": 0.701971134946931,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004960638316504098,
|
|
"loss": 5.7123,
|
|
"mean_token_accuracy": 0.17048256993293762,
|
|
"num_tokens": 13960056.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.781730461120605,
|
|
"epoch": 0.7025327118548885,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004960563511804421,
|
|
"loss": 5.6766,
|
|
"mean_token_accuracy": 0.17059859037399291,
|
|
"num_tokens": 13971932.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.802457332611084,
|
|
"epoch": 0.7030942887628461,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004960488636719545,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.1728135496377945,
|
|
"num_tokens": 13981992.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.692510747909546,
|
|
"epoch": 0.7036558656708036,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004960413691251852,
|
|
"loss": 5.6285,
|
|
"mean_token_accuracy": 0.17995460629463195,
|
|
"num_tokens": 13992215.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.675698900222779,
|
|
"epoch": 0.7042174425787612,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004960338675403731,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.18567170798778534,
|
|
"num_tokens": 14002689.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.702763223648072,
|
|
"epoch": 0.7047790194867187,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004960263589177568,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.173016756772995,
|
|
"num_tokens": 14014951.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.62267541885376,
|
|
"epoch": 0.7053405963946763,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004960188432575757,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.17654383480548858,
|
|
"num_tokens": 14025502.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.75745849609375,
|
|
"epoch": 0.7059021733026338,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960113205600688,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.177627032995224,
|
|
"num_tokens": 14036576.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.690681982040405,
|
|
"epoch": 0.7064637502105914,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004960037908254757,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.1759755104780197,
|
|
"num_tokens": 14046493.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.733213758468628,
|
|
"epoch": 0.7070253271185489,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004959962540540361,
|
|
"loss": 5.7058,
|
|
"mean_token_accuracy": 0.17643107175827027,
|
|
"num_tokens": 14057297.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.651870679855347,
|
|
"epoch": 0.7075869040265065,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959887102459903,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.17602535486221313,
|
|
"num_tokens": 14068947.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.641904973983765,
|
|
"epoch": 0.7081484809344639,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004959811594015781,
|
|
"loss": 5.5883,
|
|
"mean_token_accuracy": 0.17512256056070327,
|
|
"num_tokens": 14078979.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.604806184768677,
|
|
"epoch": 0.7087100578424215,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004959736015210401,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.17633567601442338,
|
|
"num_tokens": 14089785.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.667655754089355,
|
|
"epoch": 0.709271634750379,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959660366046169,
|
|
"loss": 5.6284,
|
|
"mean_token_accuracy": 0.17565469443798065,
|
|
"num_tokens": 14099921.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.636227464675903,
|
|
"epoch": 0.7098332116583366,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004959584646525494,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.17429418861865997,
|
|
"num_tokens": 14110965.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.6782396793365475,
|
|
"epoch": 0.7103947885662941,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004959508856650788,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.17324938476085663,
|
|
"num_tokens": 14122409.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.758002996444702,
|
|
"epoch": 0.7109563654742517,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004959432996424463,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17611083537340164,
|
|
"num_tokens": 14134017.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.705021858215332,
|
|
"epoch": 0.7115179423822092,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004959357065848932,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.1701839804649353,
|
|
"num_tokens": 14144843.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.713117885589599,
|
|
"epoch": 0.7120795192901668,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004959281064926618,
|
|
"loss": 5.5898,
|
|
"mean_token_accuracy": 0.17254902869462968,
|
|
"num_tokens": 14155944.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.729945087432862,
|
|
"epoch": 0.7126410961981243,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959204993659936,
|
|
"loss": 5.6358,
|
|
"mean_token_accuracy": 0.17331005185842513,
|
|
"num_tokens": 14167064.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.725948619842529,
|
|
"epoch": 0.7132026731060819,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959128852051311,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.17247204780578612,
|
|
"num_tokens": 14178583.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.614906215667725,
|
|
"epoch": 0.7137642500140394,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004959052640103167,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.17402423769235612,
|
|
"num_tokens": 14188752.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.622827434539795,
|
|
"epoch": 0.714325826921997,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495897635781793,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1811547949910164,
|
|
"num_tokens": 14199962.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.6531750679016115,
|
|
"epoch": 0.7148874038299545,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004958900005198029,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.17695132941007613,
|
|
"num_tokens": 14209877.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.642162084579468,
|
|
"epoch": 0.7154489807379121,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004958823582245894,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.1773078754544258,
|
|
"num_tokens": 14220672.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.788432502746582,
|
|
"epoch": 0.7160105576458696,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958747088963961,
|
|
"loss": 5.6062,
|
|
"mean_token_accuracy": 0.17611269801855087,
|
|
"num_tokens": 14232348.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.659993648529053,
|
|
"epoch": 0.7165721345538272,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004958670525354663,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.16871958523988723,
|
|
"num_tokens": 14243985.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.585564374923706,
|
|
"epoch": 0.7171337114617847,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000495859389142044,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.18107901513576508,
|
|
"num_tokens": 14253548.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.758929347991943,
|
|
"epoch": 0.7176952883697423,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.000495851718716373,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.17230201363563538,
|
|
"num_tokens": 14264757.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.61860761642456,
|
|
"epoch": 0.7182568652776998,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004958440412586977,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.18185316920280456,
|
|
"num_tokens": 14275946.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.659633016586303,
|
|
"epoch": 0.7188184421856574,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004958363567692624,
|
|
"loss": 5.6258,
|
|
"mean_token_accuracy": 0.16648518443107604,
|
|
"num_tokens": 14287006.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.783971786499023,
|
|
"epoch": 0.7193800190936148,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004958286652483118,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.16668132990598677,
|
|
"num_tokens": 14299328.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.751309776306153,
|
|
"epoch": 0.7199415960015724,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004958209666960909,
|
|
"loss": 5.6325,
|
|
"mean_token_accuracy": 0.17574937492609025,
|
|
"num_tokens": 14310048.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.600087118148804,
|
|
"epoch": 0.7205031729095299,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004958132611128448,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.17607790902256965,
|
|
"num_tokens": 14321107.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.681232357025147,
|
|
"epoch": 0.7210647498174875,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004958055484988188,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.1770709589123726,
|
|
"num_tokens": 14332561.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.779023790359497,
|
|
"epoch": 0.721626326725445,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004957978288542585,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.17088700830936432,
|
|
"num_tokens": 14343238.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.610882043838501,
|
|
"epoch": 0.7221879036334026,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004957901021794098,
|
|
"loss": 5.5824,
|
|
"mean_token_accuracy": 0.17638989239931108,
|
|
"num_tokens": 14356067.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.689892864227295,
|
|
"epoch": 0.7227494805413601,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004957823684745184,
|
|
"loss": 5.6219,
|
|
"mean_token_accuracy": 0.17579033523797988,
|
|
"num_tokens": 14367302.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.625109624862671,
|
|
"epoch": 0.7233110574493177,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004957746277398309,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1807323217391968,
|
|
"num_tokens": 14377535.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.715607213973999,
|
|
"epoch": 0.7238726343572752,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957668799755937,
|
|
"loss": 5.6759,
|
|
"mean_token_accuracy": 0.16836657524108886,
|
|
"num_tokens": 14389493.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.725277471542358,
|
|
"epoch": 0.7244342112652328,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004957591251820532,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.1736565798521042,
|
|
"num_tokens": 14401564.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.688845920562744,
|
|
"epoch": 0.7249957881731903,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957513633594567,
|
|
"loss": 5.6374,
|
|
"mean_token_accuracy": 0.17719704955816268,
|
|
"num_tokens": 14412123.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.6299666404724125,
|
|
"epoch": 0.7255573650811479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957435945080512,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.1735016569495201,
|
|
"num_tokens": 14423614.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.748258829116821,
|
|
"epoch": 0.7261189419891054,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004957358186280839,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.1689170554280281,
|
|
"num_tokens": 14434830.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.698912239074707,
|
|
"epoch": 0.726680518897063,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004957280357198026,
|
|
"loss": 5.6487,
|
|
"mean_token_accuracy": 0.17471132874488832,
|
|
"num_tokens": 14445015.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.696842956542969,
|
|
"epoch": 0.7272420958050205,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004957202457834551,
|
|
"loss": 5.7397,
|
|
"mean_token_accuracy": 0.1646079272031784,
|
|
"num_tokens": 14455809.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.686672210693359,
|
|
"epoch": 0.7278036727129781,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004957124488192893,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17868067771196366,
|
|
"num_tokens": 14466565.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.747532606124878,
|
|
"epoch": 0.7283652496209356,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004957046448275535,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.18294082581996918,
|
|
"num_tokens": 14477383.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.648335313796997,
|
|
"epoch": 0.7289268265288932,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004956968338084961,
|
|
"loss": 5.6089,
|
|
"mean_token_accuracy": 0.17285848706960677,
|
|
"num_tokens": 14489968.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.721648502349853,
|
|
"epoch": 0.7294884034368507,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004956890157623661,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.17409726977348328,
|
|
"num_tokens": 14500808.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.702211809158325,
|
|
"epoch": 0.7300499803448082,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004956811906894122,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17562953531742095,
|
|
"num_tokens": 14511444.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.661644124984742,
|
|
"epoch": 0.7306115572527657,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004956733585898836,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.17513482123613358,
|
|
"num_tokens": 14522562.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.614447593688965,
|
|
"epoch": 0.7311731341607233,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004956655194640297,
|
|
"loss": 5.6046,
|
|
"mean_token_accuracy": 0.17422065734863282,
|
|
"num_tokens": 14533497.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.717681074142456,
|
|
"epoch": 0.7317347110686808,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004956576733121,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.16607823669910432,
|
|
"num_tokens": 14545637.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.79359393119812,
|
|
"epoch": 0.7322962879766384,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004956498201343444,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.16798721849918366,
|
|
"num_tokens": 14556826.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.582854890823365,
|
|
"epoch": 0.7328578648845959,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000495641959931013,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.16726584285497664,
|
|
"num_tokens": 14567315.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.649461936950684,
|
|
"epoch": 0.7334194417925535,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956340927023561,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.1769120752811432,
|
|
"num_tokens": 14577685.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.703219652175903,
|
|
"epoch": 0.733981018700511,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000495626218448624,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.17614085525274276,
|
|
"num_tokens": 14588885.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.686504268646241,
|
|
"epoch": 0.7345425956084686,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004956183371700676,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.17757701128721237,
|
|
"num_tokens": 14599774.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.798830604553222,
|
|
"epoch": 0.7351041725164261,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004956104488669377,
|
|
"loss": 5.6659,
|
|
"mean_token_accuracy": 0.16752137690782548,
|
|
"num_tokens": 14612101.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.8568212509155275,
|
|
"epoch": 0.7356657494243837,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004956025535394856,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.15637542828917503,
|
|
"num_tokens": 14622151.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.727231359481811,
|
|
"epoch": 0.7362273263323412,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004955946511879626,
|
|
"loss": 5.6319,
|
|
"mean_token_accuracy": 0.1686676949262619,
|
|
"num_tokens": 14634631.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.625584840774536,
|
|
"epoch": 0.7367889032402988,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004955867418126205,
|
|
"loss": 5.5874,
|
|
"mean_token_accuracy": 0.1750003680586815,
|
|
"num_tokens": 14645429.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.616389274597168,
|
|
"epoch": 0.7373504801482563,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004955788254137108,
|
|
"loss": 5.5858,
|
|
"mean_token_accuracy": 0.17674731016159057,
|
|
"num_tokens": 14657309.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.648408317565918,
|
|
"epoch": 0.7379120570562139,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004955709019914857,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.17500240504741668,
|
|
"num_tokens": 14668578.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.718561315536499,
|
|
"epoch": 0.7384736339641714,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004955629715461977,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.16865023821592331,
|
|
"num_tokens": 14679120.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.778608083724976,
|
|
"epoch": 0.739035210872129,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004955550340780991,
|
|
"loss": 5.6744,
|
|
"mean_token_accuracy": 0.1694789245724678,
|
|
"num_tokens": 14690849.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.753150987625122,
|
|
"epoch": 0.7395967877800865,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004955470895874427,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.17123454064130783,
|
|
"num_tokens": 14702431.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.601886320114136,
|
|
"epoch": 0.7401583646880441,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004955391380744813,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.18116904944181442,
|
|
"num_tokens": 14714271.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.651697826385498,
|
|
"epoch": 0.7407199415960015,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004955311795394684,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.17349733114242555,
|
|
"num_tokens": 14724796.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.719136381149292,
|
|
"epoch": 0.7412815185039591,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.000495523213982657,
|
|
"loss": 5.5991,
|
|
"mean_token_accuracy": 0.16785625219345093,
|
|
"num_tokens": 14735331.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.775799417495728,
|
|
"epoch": 0.7418430954119166,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004955152414043011,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.17304898500442506,
|
|
"num_tokens": 14748595.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.733573627471924,
|
|
"epoch": 0.7424046723198742,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004955072618046543,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.1732630178332329,
|
|
"num_tokens": 14759501.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.607497501373291,
|
|
"epoch": 0.7429662492278317,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004954992751839708,
|
|
"loss": 5.6222,
|
|
"mean_token_accuracy": 0.17292320132255554,
|
|
"num_tokens": 14769752.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.722657155990601,
|
|
"epoch": 0.7435278261357893,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004954912815425048,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.17188743948936464,
|
|
"num_tokens": 14781166.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.628565931320191,
|
|
"epoch": 0.7440894030437468,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000495483280880511,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.18368534594774247,
|
|
"num_tokens": 14790536.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.7260270595550535,
|
|
"epoch": 0.7446509799517044,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000495475273198244,
|
|
"loss": 5.6971,
|
|
"mean_token_accuracy": 0.16831562370061875,
|
|
"num_tokens": 14801673.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.700561618804931,
|
|
"epoch": 0.7452125568596619,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004954672584959588,
|
|
"loss": 5.5871,
|
|
"mean_token_accuracy": 0.1710066929459572,
|
|
"num_tokens": 14812345.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.780966806411743,
|
|
"epoch": 0.7457741337676195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004954592367739104,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.1665782019495964,
|
|
"num_tokens": 14823620.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.749325132369995,
|
|
"epoch": 0.746335710675577,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004954512080323546,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.18026617914438248,
|
|
"num_tokens": 14833487.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.552410316467285,
|
|
"epoch": 0.7468972875835346,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004954431722715468,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.17756489366292955,
|
|
"num_tokens": 14844421.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.599313735961914,
|
|
"epoch": 0.7474588644914921,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004954351294917428,
|
|
"loss": 5.598,
|
|
"mean_token_accuracy": 0.1814298763871193,
|
|
"num_tokens": 14855525.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.767684125900269,
|
|
"epoch": 0.7480204413994497,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004954270796931989,
|
|
"loss": 5.6689,
|
|
"mean_token_accuracy": 0.1680884465575218,
|
|
"num_tokens": 14866717.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.636875915527344,
|
|
"epoch": 0.7485820183074072,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004954190228761712,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.17375942468643188,
|
|
"num_tokens": 14877372.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.622308683395386,
|
|
"epoch": 0.7491435952153648,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004954109590409164,
|
|
"loss": 5.6192,
|
|
"mean_token_accuracy": 0.17433239370584488,
|
|
"num_tokens": 14888618.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.664903020858764,
|
|
"epoch": 0.7497051721233223,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004954028881876911,
|
|
"loss": 5.6324,
|
|
"mean_token_accuracy": 0.17436057925224305,
|
|
"num_tokens": 14900421.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.75382022857666,
|
|
"epoch": 0.7502667490312799,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004953948103167524,
|
|
"loss": 5.5908,
|
|
"mean_token_accuracy": 0.1725509688258171,
|
|
"num_tokens": 14910634.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.774740934371948,
|
|
"epoch": 0.7508283259392374,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004953867254283575,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.16812112629413606,
|
|
"num_tokens": 14921408.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.667041063308716,
|
|
"epoch": 0.7513899028471949,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004953786335227636,
|
|
"loss": 5.6267,
|
|
"mean_token_accuracy": 0.17939901053905488,
|
|
"num_tokens": 14933435.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.619827556610107,
|
|
"epoch": 0.7519514797551524,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953705346002287,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.16830154359340668,
|
|
"num_tokens": 14946488.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.627918767929077,
|
|
"epoch": 0.75251305666311,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004953624286610106,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.17827337086200715,
|
|
"num_tokens": 14958053.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.722825527191162,
|
|
"epoch": 0.7530746335710675,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953543157053672,
|
|
"loss": 5.594,
|
|
"mean_token_accuracy": 0.16801025718450546,
|
|
"num_tokens": 14968922.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.726508474349975,
|
|
"epoch": 0.7536362104790251,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004953461957335569,
|
|
"loss": 5.6012,
|
|
"mean_token_accuracy": 0.17428140938282013,
|
|
"num_tokens": 14979541.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.658913087844849,
|
|
"epoch": 0.7541977873869826,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004953380687458382,
|
|
"loss": 5.6236,
|
|
"mean_token_accuracy": 0.1669877514243126,
|
|
"num_tokens": 14990009.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.676482152938843,
|
|
"epoch": 0.7547593642949402,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004953299347424701,
|
|
"loss": 5.6355,
|
|
"mean_token_accuracy": 0.17174317240715026,
|
|
"num_tokens": 15001712.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.80409803390503,
|
|
"epoch": 0.7553209412028977,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004953217937237114,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.17649359703063966,
|
|
"num_tokens": 15012574.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.613854694366455,
|
|
"epoch": 0.7558825181108553,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004953136456898212,
|
|
"loss": 5.5823,
|
|
"mean_token_accuracy": 0.17598111182451248,
|
|
"num_tokens": 15023034.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.757526016235351,
|
|
"epoch": 0.7564440950188128,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004953054906410593,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.1701991707086563,
|
|
"num_tokens": 15033925.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.7040527820587155,
|
|
"epoch": 0.7570056719267704,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004952973285776848,
|
|
"loss": 5.6085,
|
|
"mean_token_accuracy": 0.18221036493778228,
|
|
"num_tokens": 15044947.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.648647403717041,
|
|
"epoch": 0.7575672488347279,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004952891594999582,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.17978119254112243,
|
|
"num_tokens": 15054784.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.6401115417480465,
|
|
"epoch": 0.7581288257426855,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004952809834081392,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.16652532070875167,
|
|
"num_tokens": 15066272.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.758087396621704,
|
|
"epoch": 0.758690402650643,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004952728003024883,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.1661433383822441,
|
|
"num_tokens": 15079504.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.715632152557373,
|
|
"epoch": 0.7592519795586006,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004952646101832659,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.17571005523204802,
|
|
"num_tokens": 15089623.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.598669719696045,
|
|
"epoch": 0.7598135564665581,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004952564130507331,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.17055969089269638,
|
|
"num_tokens": 15100816.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.650894975662231,
|
|
"epoch": 0.7603751333745157,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004952482089051506,
|
|
"loss": 5.6303,
|
|
"mean_token_accuracy": 0.1743953749537468,
|
|
"num_tokens": 15111697.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.79354510307312,
|
|
"epoch": 0.7609367102824732,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004952399977467796,
|
|
"loss": 5.6927,
|
|
"mean_token_accuracy": 0.16901832371950148,
|
|
"num_tokens": 15122869.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.613598251342774,
|
|
"epoch": 0.7614982871904308,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004952317795758817,
|
|
"loss": 5.4926,
|
|
"mean_token_accuracy": 0.17467166483402252,
|
|
"num_tokens": 15134709.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.5768311500549315,
|
|
"epoch": 0.7620598640983883,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004952235543927185,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1797581896185875,
|
|
"num_tokens": 15145319.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.661306858062744,
|
|
"epoch": 0.7626214410063458,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000495215322197552,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16929468512535095,
|
|
"num_tokens": 15156463.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.790685796737671,
|
|
"epoch": 0.7631830179143033,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004952070829906442,
|
|
"loss": 5.7025,
|
|
"mean_token_accuracy": 0.16224280372262,
|
|
"num_tokens": 15167618.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.701229572296143,
|
|
"epoch": 0.7637445948222609,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004951988367722574,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.1705644652247429,
|
|
"num_tokens": 15179312.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.609913730621338,
|
|
"epoch": 0.7643061717302184,
|
|
"grad_norm": 1.9765625,
|
|
"learning_rate": 0.0004951905835426544,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.17650253027677537,
|
|
"num_tokens": 15191370.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.6970398902893065,
|
|
"epoch": 0.764867748638176,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951823233020976,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1837317630648613,
|
|
"num_tokens": 15201060.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.575574493408203,
|
|
"epoch": 0.7654293255461335,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004951740560508504,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.17918746024370194,
|
|
"num_tokens": 15212186.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.652350664138794,
|
|
"epoch": 0.7659909024540911,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004951657817891758,
|
|
"loss": 5.5035,
|
|
"mean_token_accuracy": 0.18071949779987334,
|
|
"num_tokens": 15223301.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.6948141098022464,
|
|
"epoch": 0.7665524793620486,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004951575005173373,
|
|
"loss": 5.6482,
|
|
"mean_token_accuracy": 0.16965311914682388,
|
|
"num_tokens": 15234475.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.699067497253418,
|
|
"epoch": 0.7671140562700062,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004951492122355986,
|
|
"loss": 5.6283,
|
|
"mean_token_accuracy": 0.16850069016218186,
|
|
"num_tokens": 15245877.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.758517694473267,
|
|
"epoch": 0.7676756331779637,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004951409169442236,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.1719433158636093,
|
|
"num_tokens": 15257375.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.664356136322022,
|
|
"epoch": 0.7682372100859213,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004951326146434765,
|
|
"loss": 5.6377,
|
|
"mean_token_accuracy": 0.17386048585176467,
|
|
"num_tokens": 15268079.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.614561605453491,
|
|
"epoch": 0.7687987869938788,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004951243053336214,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.1731279045343399,
|
|
"num_tokens": 15278678.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.790929460525513,
|
|
"epoch": 0.7693603639018364,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004951159890149232,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.1674549788236618,
|
|
"num_tokens": 15290080.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.774200201034546,
|
|
"epoch": 0.7699219408097939,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004951076656876466,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.17061976641416549,
|
|
"num_tokens": 15300602.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.714830207824707,
|
|
"epoch": 0.7704835177177515,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004950993353520564,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.17638174295425416,
|
|
"num_tokens": 15312823.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.747722816467285,
|
|
"epoch": 0.771045094625709,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000495090998008418,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.17176947444677354,
|
|
"num_tokens": 15323870.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.649303817749024,
|
|
"epoch": 0.7716066715336666,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000495082653656997,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.1764069527387619,
|
|
"num_tokens": 15334887.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.693717432022095,
|
|
"epoch": 0.7721682484416241,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004950743022980587,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.1700300544500351,
|
|
"num_tokens": 15345871.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.627660703659058,
|
|
"epoch": 0.7727298253495817,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004950659439318696,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.1803757965564728,
|
|
"num_tokens": 15356530.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.6457091808319095,
|
|
"epoch": 0.7732914022575391,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004950575785586952,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.1733783781528473,
|
|
"num_tokens": 15368756.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.747574520111084,
|
|
"epoch": 0.7738529791654967,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004950492061788023,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.18018330931663512,
|
|
"num_tokens": 15379450.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.6891344547271725,
|
|
"epoch": 0.7744145560734542,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004950408267924573,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.16904707252979279,
|
|
"num_tokens": 15389501.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.539901161193848,
|
|
"epoch": 0.7749761329814118,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004950324403999271,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.17730834782123567,
|
|
"num_tokens": 15400608.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.748326778411865,
|
|
"epoch": 0.7755377098893693,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004950240470014785,
|
|
"loss": 5.6476,
|
|
"mean_token_accuracy": 0.17182130515575408,
|
|
"num_tokens": 15411709.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.694216775894165,
|
|
"epoch": 0.7760992867973269,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004950156465973791,
|
|
"loss": 5.5185,
|
|
"mean_token_accuracy": 0.18505675792694093,
|
|
"num_tokens": 15422292.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.682144498825073,
|
|
"epoch": 0.7766608637052844,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.000495007239187896,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.1698872670531273,
|
|
"num_tokens": 15434439.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.69565715789795,
|
|
"epoch": 0.777222440613242,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004949988247732972,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.17025801092386245,
|
|
"num_tokens": 15445480.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.663097906112671,
|
|
"epoch": 0.7777840175211995,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004949904033538504,
|
|
"loss": 5.5901,
|
|
"mean_token_accuracy": 0.17332608103752137,
|
|
"num_tokens": 15456960.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.62755765914917,
|
|
"epoch": 0.7783455944291571,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000494981974929824,
|
|
"loss": 5.5996,
|
|
"mean_token_accuracy": 0.17255747467279434,
|
|
"num_tokens": 15468169.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.725860166549682,
|
|
"epoch": 0.7789071713371146,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000494973539501486,
|
|
"loss": 5.5731,
|
|
"mean_token_accuracy": 0.17692328989505768,
|
|
"num_tokens": 15478740.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.717451572418213,
|
|
"epoch": 0.7794687482450722,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004949650970691052,
|
|
"loss": 5.6758,
|
|
"mean_token_accuracy": 0.16785881519317628,
|
|
"num_tokens": 15489705.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.586813354492188,
|
|
"epoch": 0.7800303251530297,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004949566476329505,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.17540114521980285,
|
|
"num_tokens": 15500549.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.824460697174072,
|
|
"epoch": 0.7805919020609873,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004949481911932908,
|
|
"loss": 5.645,
|
|
"mean_token_accuracy": 0.17161364406347274,
|
|
"num_tokens": 15511124.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.687227773666382,
|
|
"epoch": 0.7811534789689448,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004949397277503954,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.17486044019460678,
|
|
"num_tokens": 15521810.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.665184068679809,
|
|
"epoch": 0.7817150558769024,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.0004949312573045338,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.17281483262777328,
|
|
"num_tokens": 15533108.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.701936197280884,
|
|
"epoch": 0.7822766327848599,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004949227798559757,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.16948259770870208,
|
|
"num_tokens": 15544841.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.68751711845398,
|
|
"epoch": 0.7828382096928175,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004949142954049909,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.1744911015033722,
|
|
"num_tokens": 15556297.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.622859048843384,
|
|
"epoch": 0.783399786600775,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004949058039518496,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.18035289645195007,
|
|
"num_tokens": 15566607.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.743546056747436,
|
|
"epoch": 0.7839613635087325,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004948973054968222,
|
|
"loss": 5.6851,
|
|
"mean_token_accuracy": 0.1643693193793297,
|
|
"num_tokens": 15577435.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.719946193695068,
|
|
"epoch": 0.78452294041669,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004948888000401794,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.17366245985031128,
|
|
"num_tokens": 15587844.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.7868115425109865,
|
|
"epoch": 0.7850845173246476,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004948802875821918,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.17047105282545089,
|
|
"num_tokens": 15599586.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.620378684997559,
|
|
"epoch": 0.7856460942326051,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004948717681231308,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.17032734006643296,
|
|
"num_tokens": 15610838.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.711033630371094,
|
|
"epoch": 0.7862076711405627,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004948632416632672,
|
|
"loss": 5.6186,
|
|
"mean_token_accuracy": 0.1747157543897629,
|
|
"num_tokens": 15622652.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.754448986053466,
|
|
"epoch": 0.7867692480485202,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004948547082028728,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.16360728889703752,
|
|
"num_tokens": 15634280.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.6426290512084964,
|
|
"epoch": 0.7873308249564778,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004948461677422193,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.1830253303050995,
|
|
"num_tokens": 15644088.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.661613988876343,
|
|
"epoch": 0.7878924018644353,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004948376202815785,
|
|
"loss": 5.6772,
|
|
"mean_token_accuracy": 0.16506017744541168,
|
|
"num_tokens": 15654968.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.658158016204834,
|
|
"epoch": 0.7884539787723929,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004948290658212225,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.17666928917169572,
|
|
"num_tokens": 15666758.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.550996541976929,
|
|
"epoch": 0.7890155556803504,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004948205043614239,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.1858266234397888,
|
|
"num_tokens": 15677295.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.722598266601563,
|
|
"epoch": 0.789577132588308,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.0004948119359024551,
|
|
"loss": 5.6526,
|
|
"mean_token_accuracy": 0.17219128161668779,
|
|
"num_tokens": 15689508.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.742277669906616,
|
|
"epoch": 0.7901387094962655,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004948033604445891,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.17576043605804442,
|
|
"num_tokens": 15701289.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.603391170501709,
|
|
"epoch": 0.7907002864042231,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004947947779880988,
|
|
"loss": 5.5395,
|
|
"mean_token_accuracy": 0.17437019497156142,
|
|
"num_tokens": 15711579.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.706953048706055,
|
|
"epoch": 0.7912618633121806,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004947861885332576,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.17553916871547698,
|
|
"num_tokens": 15722629.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.708155775070191,
|
|
"epoch": 0.7918234402201382,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004947775920803388,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.16608199030160903,
|
|
"num_tokens": 15735818.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.6027140617370605,
|
|
"epoch": 0.7923850171280957,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004947689886296162,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.17234212309122085,
|
|
"num_tokens": 15746914.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.637384271621704,
|
|
"epoch": 0.7929465940360533,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000494760378181364,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1672011837363243,
|
|
"num_tokens": 15757597.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.650219583511353,
|
|
"epoch": 0.7935081709440108,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004947517607358559,
|
|
"loss": 5.4808,
|
|
"mean_token_accuracy": 0.17977314740419387,
|
|
"num_tokens": 15768860.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.673953199386597,
|
|
"epoch": 0.7940697478519684,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004947431362933666,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.1669449657201767,
|
|
"num_tokens": 15779476.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.6543577194213865,
|
|
"epoch": 0.7946313247599258,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004947345048541706,
|
|
"loss": 5.6474,
|
|
"mean_token_accuracy": 0.16842045038938522,
|
|
"num_tokens": 15792142.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.696052408218383,
|
|
"epoch": 0.7951929016678834,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004947258664185427,
|
|
"loss": 5.6058,
|
|
"mean_token_accuracy": 0.17291992157697678,
|
|
"num_tokens": 15802307.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.6719152450561525,
|
|
"epoch": 0.7957544785758409,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004947172209867581,
|
|
"loss": 5.5614,
|
|
"mean_token_accuracy": 0.1727038398385048,
|
|
"num_tokens": 15812986.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.611334562301636,
|
|
"epoch": 0.7963160554837985,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004947085685590919,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.18099294006824493,
|
|
"num_tokens": 15823938.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.598259305953979,
|
|
"epoch": 0.796877632391756,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004946999091358196,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.17846065163612365,
|
|
"num_tokens": 15835813.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.7230072021484375,
|
|
"epoch": 0.7974392092997136,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000494691242717217,
|
|
"loss": 5.5618,
|
|
"mean_token_accuracy": 0.17889661490917205,
|
|
"num_tokens": 15846203.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.6960001468658445,
|
|
"epoch": 0.7980007862076711,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004946825693035601,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.17864030003547668,
|
|
"num_tokens": 15856919.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.686487913131714,
|
|
"epoch": 0.7985623631156287,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000494673888895125,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.16441151946783067,
|
|
"num_tokens": 15867149.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.602589797973633,
|
|
"epoch": 0.7991239400235862,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004946652014921881,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.17629572302103041,
|
|
"num_tokens": 15877229.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.690700101852417,
|
|
"epoch": 0.7996855169315438,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004946565070950259,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.17562888264656068,
|
|
"num_tokens": 15888799.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.649559879302979,
|
|
"epoch": 0.8002470938395013,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004946478057039153,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.1850351944565773,
|
|
"num_tokens": 15900144.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.707769203186035,
|
|
"epoch": 0.8008086707474589,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004946390973191335,
|
|
"loss": 5.6989,
|
|
"mean_token_accuracy": 0.1644160196185112,
|
|
"num_tokens": 15912030.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.707042646408081,
|
|
"epoch": 0.8013702476554164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004946303819409575,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.1746719852089882,
|
|
"num_tokens": 15923606.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.607723999023437,
|
|
"epoch": 0.801931824563374,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004946216595696652,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.17781541496515274,
|
|
"num_tokens": 15935077.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.539192247390747,
|
|
"epoch": 0.8024934014713315,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004946129302055338,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.17681455314159394,
|
|
"num_tokens": 15945331.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.640668201446533,
|
|
"epoch": 0.8030549783792891,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004946041938488417,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.17352225184440612,
|
|
"num_tokens": 15957031.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.722363901138306,
|
|
"epoch": 0.8036165552872466,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004945954504998668,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.1765743911266327,
|
|
"num_tokens": 15967545.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.756625652313232,
|
|
"epoch": 0.8041781321952042,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004945867001588877,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.16390444785356523,
|
|
"num_tokens": 15978700.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.647306489944458,
|
|
"epoch": 0.8047397091031617,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004945779428261827,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.1769125446677208,
|
|
"num_tokens": 15989712.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.770856189727783,
|
|
"epoch": 0.8053012860111193,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.000494569178502031,
|
|
"loss": 5.7631,
|
|
"mean_token_accuracy": 0.16481125205755234,
|
|
"num_tokens": 16002380.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.767297792434692,
|
|
"epoch": 0.8058628629190767,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004945604071867114,
|
|
"loss": 5.5316,
|
|
"mean_token_accuracy": 0.17414472848176957,
|
|
"num_tokens": 16013749.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.7201861381530765,
|
|
"epoch": 0.8064244398270343,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004945516288805035,
|
|
"loss": 5.7107,
|
|
"mean_token_accuracy": 0.16690435707569123,
|
|
"num_tokens": 16025131.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.7086530208587645,
|
|
"epoch": 0.8069860167349918,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004945428435836864,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.17193285077810289,
|
|
"num_tokens": 16037269.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.821916770935059,
|
|
"epoch": 0.8075475936429494,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004945340512965401,
|
|
"loss": 5.7809,
|
|
"mean_token_accuracy": 0.1602990061044693,
|
|
"num_tokens": 16050992.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.632455158233642,
|
|
"epoch": 0.8081091705509069,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004945252520193443,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.16854160726070405,
|
|
"num_tokens": 16062309.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.781417274475098,
|
|
"epoch": 0.8086707474588645,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004945164457523795,
|
|
"loss": 5.6499,
|
|
"mean_token_accuracy": 0.17174242436885834,
|
|
"num_tokens": 16073079.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.743130016326904,
|
|
"epoch": 0.809232324366822,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004945076324959258,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1771923154592514,
|
|
"num_tokens": 16082885.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.540170049667358,
|
|
"epoch": 0.8097939012747796,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004944988122502641,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.18088305592536927,
|
|
"num_tokens": 16094173.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.634492969512939,
|
|
"epoch": 0.8103554781827371,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000494489985015675,
|
|
"loss": 5.538,
|
|
"mean_token_accuracy": 0.1762974038720131,
|
|
"num_tokens": 16106351.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.605233764648437,
|
|
"epoch": 0.8109170550906947,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004944811507924396,
|
|
"loss": 5.5393,
|
|
"mean_token_accuracy": 0.17757706046104432,
|
|
"num_tokens": 16116892.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.74546709060669,
|
|
"epoch": 0.8114786319986522,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004944723095808393,
|
|
"loss": 5.682,
|
|
"mean_token_accuracy": 0.17023035436868666,
|
|
"num_tokens": 16128316.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.647548866271973,
|
|
"epoch": 0.8120402089066098,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004944634613811555,
|
|
"loss": 5.5099,
|
|
"mean_token_accuracy": 0.175094273686409,
|
|
"num_tokens": 16139245.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.6284726619720455,
|
|
"epoch": 0.8126017858145673,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00049445460619367,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.17416229099035263,
|
|
"num_tokens": 16150893.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.722608184814453,
|
|
"epoch": 0.8131633627225249,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004944457440186648,
|
|
"loss": 5.7053,
|
|
"mean_token_accuracy": 0.16060589104890824,
|
|
"num_tokens": 16163430.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.802824831008911,
|
|
"epoch": 0.8137249396304824,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004944368748564219,
|
|
"loss": 5.5737,
|
|
"mean_token_accuracy": 0.17386958450078965,
|
|
"num_tokens": 16173954.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.716937685012818,
|
|
"epoch": 0.81428651653844,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004944279987072238,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.1704520985484123,
|
|
"num_tokens": 16185491.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.6306427955627445,
|
|
"epoch": 0.8148480934463975,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004944191155713531,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.1877261981368065,
|
|
"num_tokens": 16195301.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.688060569763183,
|
|
"epoch": 0.8154096703543551,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004944102254490928,
|
|
"loss": 5.6083,
|
|
"mean_token_accuracy": 0.168195141851902,
|
|
"num_tokens": 16206620.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.669605016708374,
|
|
"epoch": 0.8159712472623126,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004944013283407257,
|
|
"loss": 5.686,
|
|
"mean_token_accuracy": 0.16892174035310745,
|
|
"num_tokens": 16218693.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.744264316558838,
|
|
"epoch": 0.8165328241702701,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004943924242465352,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.17684537470340728,
|
|
"num_tokens": 16229124.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.62593183517456,
|
|
"epoch": 0.8170944010782276,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004943835131668049,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.1755410522222519,
|
|
"num_tokens": 16239999.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.655383110046387,
|
|
"epoch": 0.8176559779861852,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004943745951018184,
|
|
"loss": 5.6326,
|
|
"mean_token_accuracy": 0.17760412991046906,
|
|
"num_tokens": 16251027.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.691645860671997,
|
|
"epoch": 0.8182175548941427,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004943656700518597,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.17768313288688659,
|
|
"num_tokens": 16262924.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.779166221618652,
|
|
"epoch": 0.8187791318021003,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004943567380172129,
|
|
"loss": 5.7112,
|
|
"mean_token_accuracy": 0.17177675664424896,
|
|
"num_tokens": 16274481.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.706970739364624,
|
|
"epoch": 0.8193407087100578,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943477989981627,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.1762496441602707,
|
|
"num_tokens": 16285214.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.6909974098205565,
|
|
"epoch": 0.8199022856180154,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004943388529949933,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.1706026941537857,
|
|
"num_tokens": 16296077.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.784282588958741,
|
|
"epoch": 0.8204638625259729,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004943299000079899,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.17167358845472336,
|
|
"num_tokens": 16307514.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.762131214141846,
|
|
"epoch": 0.8210254394339305,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004943209400374373,
|
|
"loss": 5.6078,
|
|
"mean_token_accuracy": 0.1716308429837227,
|
|
"num_tokens": 16318734.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.600044870376587,
|
|
"epoch": 0.821587016341888,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.000494311973083621,
|
|
"loss": 5.6424,
|
|
"mean_token_accuracy": 0.17753166407346727,
|
|
"num_tokens": 16329057.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.651105165481567,
|
|
"epoch": 0.8221485932498456,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004943029991468264,
|
|
"loss": 5.5596,
|
|
"mean_token_accuracy": 0.17607780247926713,
|
|
"num_tokens": 16339646.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.7665081977844235,
|
|
"epoch": 0.8227101701578031,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004942940182273393,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.16933035999536514,
|
|
"num_tokens": 16349783.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.715436887741089,
|
|
"epoch": 0.8232717470657607,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.0004942850303254455,
|
|
"loss": 5.5601,
|
|
"mean_token_accuracy": 0.1771124243736267,
|
|
"num_tokens": 16361078.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.604397392272949,
|
|
"epoch": 0.8238333239737182,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004942760354414313,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.1766835182905197,
|
|
"num_tokens": 16371308.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.689634704589844,
|
|
"epoch": 0.8243949008816758,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004942670335755831,
|
|
"loss": 5.6176,
|
|
"mean_token_accuracy": 0.17666667103767394,
|
|
"num_tokens": 16382682.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.785108470916748,
|
|
"epoch": 0.8249564777896333,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004942580247281876,
|
|
"loss": 5.6351,
|
|
"mean_token_accuracy": 0.1720591351389885,
|
|
"num_tokens": 16393715.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.617673921585083,
|
|
"epoch": 0.8255180546975909,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004942490088995315,
|
|
"loss": 5.6161,
|
|
"mean_token_accuracy": 0.17232610583305358,
|
|
"num_tokens": 16406332.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.671286725997925,
|
|
"epoch": 0.8260796316055484,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004942399860899018,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.17277848571538926,
|
|
"num_tokens": 16417702.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.7068438053131105,
|
|
"epoch": 0.826641208513506,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004942309562995862,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.17227465510368348,
|
|
"num_tokens": 16428497.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.710024023056031,
|
|
"epoch": 0.8272027854214634,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004942219195288716,
|
|
"loss": 5.5927,
|
|
"mean_token_accuracy": 0.17463483959436416,
|
|
"num_tokens": 16440637.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.66672191619873,
|
|
"epoch": 0.827764362329421,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004942128757780463,
|
|
"loss": 5.6087,
|
|
"mean_token_accuracy": 0.1679465427994728,
|
|
"num_tokens": 16453213.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.664534425735473,
|
|
"epoch": 0.8283259392373785,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004942038250473979,
|
|
"loss": 5.6406,
|
|
"mean_token_accuracy": 0.17242703437805176,
|
|
"num_tokens": 16464345.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.650595664978027,
|
|
"epoch": 0.8288875161453361,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004941947673372147,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.18228107690811157,
|
|
"num_tokens": 16475399.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.607121562957763,
|
|
"epoch": 0.8294490930532936,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004941857026477851,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.1728833258152008,
|
|
"num_tokens": 16485439.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.585851812362671,
|
|
"epoch": 0.8300106699612512,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004941766309793978,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.17544439285993577,
|
|
"num_tokens": 16496765.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.595633125305175,
|
|
"epoch": 0.8305722468692087,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004941675523323414,
|
|
"loss": 5.5328,
|
|
"mean_token_accuracy": 0.1751713216304779,
|
|
"num_tokens": 16509199.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.751244449615479,
|
|
"epoch": 0.8311338237771663,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004941584667069052,
|
|
"loss": 5.6721,
|
|
"mean_token_accuracy": 0.17280540615320206,
|
|
"num_tokens": 16520073.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.627272701263427,
|
|
"epoch": 0.8316954006851238,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004941493741033784,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.1722569540143013,
|
|
"num_tokens": 16530919.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.70499062538147,
|
|
"epoch": 0.8322569775930814,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004941402745220507,
|
|
"loss": 5.5859,
|
|
"mean_token_accuracy": 0.1740868628025055,
|
|
"num_tokens": 16542591.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.761544179916382,
|
|
"epoch": 0.8328185545010389,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004941311679632115,
|
|
"loss": 5.5895,
|
|
"mean_token_accuracy": 0.17211009114980697,
|
|
"num_tokens": 16554984.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.596306419372558,
|
|
"epoch": 0.8333801314089965,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.000494122054427151,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.17624468952417374,
|
|
"num_tokens": 16566598.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.701521301269532,
|
|
"epoch": 0.833941708316954,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004941129339141592,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.16912623196840287,
|
|
"num_tokens": 16577868.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.697638034820557,
|
|
"epoch": 0.8345032852249116,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004941038064245267,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.1742946684360504,
|
|
"num_tokens": 16587891.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.615270614624023,
|
|
"epoch": 0.8350648621328691,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000494094671958544,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.17959122359752655,
|
|
"num_tokens": 16599924.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.582325267791748,
|
|
"epoch": 0.8356264390408267,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004940855305165019,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.17839037925004958,
|
|
"num_tokens": 16609958.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.69533896446228,
|
|
"epoch": 0.8361880159487842,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004940763820986916,
|
|
"loss": 5.6159,
|
|
"mean_token_accuracy": 0.1738503873348236,
|
|
"num_tokens": 16621159.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.760712909698486,
|
|
"epoch": 0.8367495928567418,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004940672267054044,
|
|
"loss": 5.6994,
|
|
"mean_token_accuracy": 0.17308063209056854,
|
|
"num_tokens": 16632263.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.63359432220459,
|
|
"epoch": 0.8373111697646993,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004940580643369316,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.16974733620882035,
|
|
"num_tokens": 16644117.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.537625980377197,
|
|
"epoch": 0.8378727466726568,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004940488949935651,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.17976295799016953,
|
|
"num_tokens": 16654529.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.648278713226318,
|
|
"epoch": 0.8384343235806143,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004940397186755968,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.1785047546029091,
|
|
"num_tokens": 16666191.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.702542400360107,
|
|
"epoch": 0.8389959004885719,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004940305353833191,
|
|
"loss": 5.5032,
|
|
"mean_token_accuracy": 0.17609313875436783,
|
|
"num_tokens": 16677252.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.604600524902343,
|
|
"epoch": 0.8395574773965294,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000494021345117024,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.17477979362010956,
|
|
"num_tokens": 16689487.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.581219625473023,
|
|
"epoch": 0.840119054304487,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004940121478770044,
|
|
"loss": 5.4608,
|
|
"mean_token_accuracy": 0.18123612999916078,
|
|
"num_tokens": 16699955.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.532689046859741,
|
|
"epoch": 0.8406806312124445,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004940029436635531,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.17479868680238725,
|
|
"num_tokens": 16711071.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.635745573043823,
|
|
"epoch": 0.8412422081204021,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004939937324769631,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.17918366491794585,
|
|
"num_tokens": 16722115.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.665900421142578,
|
|
"epoch": 0.8418037850283596,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004939845143175276,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.17039643377065658,
|
|
"num_tokens": 16733146.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.584039497375488,
|
|
"epoch": 0.8423653619363172,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004939752891855404,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.16949642300605774,
|
|
"num_tokens": 16745543.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.694911146163941,
|
|
"epoch": 0.8429269388442747,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004939660570812951,
|
|
"loss": 5.6134,
|
|
"mean_token_accuracy": 0.17634372413158417,
|
|
"num_tokens": 16755782.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.784466218948364,
|
|
"epoch": 0.8434885157522323,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004939568180050855,
|
|
"loss": 5.6348,
|
|
"mean_token_accuracy": 0.1729939252138138,
|
|
"num_tokens": 16767509.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.625599431991577,
|
|
"epoch": 0.8440500926601898,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004939475719572059,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.1716425210237503,
|
|
"num_tokens": 16779257.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.580572605133057,
|
|
"epoch": 0.8446116695681474,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004939383189379507,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.1775943398475647,
|
|
"num_tokens": 16790769.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.669438171386719,
|
|
"epoch": 0.8451732464761049,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004939290589476145,
|
|
"loss": 5.5367,
|
|
"mean_token_accuracy": 0.1782092869281769,
|
|
"num_tokens": 16800054.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.701548528671265,
|
|
"epoch": 0.8457348233840625,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004939197919864922,
|
|
"loss": 5.6405,
|
|
"mean_token_accuracy": 0.16795653551816941,
|
|
"num_tokens": 16811485.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.743744516372681,
|
|
"epoch": 0.84629640029202,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004939105180548788,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.17420586198568344,
|
|
"num_tokens": 16822683.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.69385256767273,
|
|
"epoch": 0.8468579771999776,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004939012371530696,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.17445822805166245,
|
|
"num_tokens": 16834200.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.755211734771729,
|
|
"epoch": 0.8474195541079351,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004938919492813601,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.1718561217188835,
|
|
"num_tokens": 16846399.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.743296718597412,
|
|
"epoch": 0.8479811310158927,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004938826544400461,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.16646169126033783,
|
|
"num_tokens": 16858322.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.690462636947632,
|
|
"epoch": 0.8485427079238502,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004938733526294234,
|
|
"loss": 5.5818,
|
|
"mean_token_accuracy": 0.17537809908390045,
|
|
"num_tokens": 16869537.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.8506536960601805,
|
|
"epoch": 0.8491042848318077,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004938640438497883,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.17254287898540496,
|
|
"num_tokens": 16881566.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.596148204803467,
|
|
"epoch": 0.8496658617397652,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004938547281014372,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.17922513335943221,
|
|
"num_tokens": 16892959.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.660215950012207,
|
|
"epoch": 0.8502274386477228,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004938454053846666,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.16697646528482438,
|
|
"num_tokens": 16904809.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.731725788116455,
|
|
"epoch": 0.8507890155556803,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004938360756997735,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.1631454199552536,
|
|
"num_tokens": 16916969.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.6071836948394775,
|
|
"epoch": 0.8513505924636379,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004938267390470547,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.1790877029299736,
|
|
"num_tokens": 16928253.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.6170654296875,
|
|
"epoch": 0.8519121693715954,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004938173954268079,
|
|
"loss": 5.5636,
|
|
"mean_token_accuracy": 0.17241461127996444,
|
|
"num_tokens": 16939875.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.797070264816284,
|
|
"epoch": 0.852473746279553,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004938080448393302,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.17684994339942933,
|
|
"num_tokens": 16950173.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.64099702835083,
|
|
"epoch": 0.8530353231875105,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004937986872849195,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.17734148502349853,
|
|
"num_tokens": 16960933.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.582088565826416,
|
|
"epoch": 0.8535969000954681,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004937893227638738,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.17856923788785933,
|
|
"num_tokens": 16972284.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.632130146026611,
|
|
"epoch": 0.8541584770034256,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004937799512764912,
|
|
"loss": 5.5067,
|
|
"mean_token_accuracy": 0.18227265328168868,
|
|
"num_tokens": 16983541.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.722725582122803,
|
|
"epoch": 0.8547200539113832,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00049377057282307,
|
|
"loss": 5.6507,
|
|
"mean_token_accuracy": 0.170784093439579,
|
|
"num_tokens": 16993773.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.748830890655517,
|
|
"epoch": 0.8552816308193407,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000493761187403909,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.17131761759519576,
|
|
"num_tokens": 17005287.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.745778656005859,
|
|
"epoch": 0.8558432077272983,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000493751795019307,
|
|
"loss": 5.5711,
|
|
"mean_token_accuracy": 0.17338719069957734,
|
|
"num_tokens": 17015664.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.647946548461914,
|
|
"epoch": 0.8564047846352558,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004937423956695629,
|
|
"loss": 5.4885,
|
|
"mean_token_accuracy": 0.17829207926988602,
|
|
"num_tokens": 17026876.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.584289979934693,
|
|
"epoch": 0.8569663615432134,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004937329893549762,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.1878029689192772,
|
|
"num_tokens": 17037321.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.66028413772583,
|
|
"epoch": 0.8575279384511709,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004937235760758462,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.17169709950685502,
|
|
"num_tokens": 17047506.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.752160596847534,
|
|
"epoch": 0.8580895153591285,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004937141558324726,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.1706238195300102,
|
|
"num_tokens": 17059710.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.771691226959229,
|
|
"epoch": 0.858651092267086,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004937047286251556,
|
|
"loss": 5.6557,
|
|
"mean_token_accuracy": 0.16590932607650757,
|
|
"num_tokens": 17070956.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.698937940597534,
|
|
"epoch": 0.8592126691750436,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004936952944541952,
|
|
"loss": 5.636,
|
|
"mean_token_accuracy": 0.1701555222272873,
|
|
"num_tokens": 17081404.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.720247459411621,
|
|
"epoch": 0.859774246083001,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004936858533198917,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.17044817507267,
|
|
"num_tokens": 17092692.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.631472158432007,
|
|
"epoch": 0.8603358229909586,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000493676405222546,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.1753968134522438,
|
|
"num_tokens": 17103730.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.680803394317627,
|
|
"epoch": 0.8608973998989161,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004936669501624586,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.1716475084424019,
|
|
"num_tokens": 17115086.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.676701879501342,
|
|
"epoch": 0.8614589768068737,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004936574881399308,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.17499450743198394,
|
|
"num_tokens": 17125928.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.694210958480835,
|
|
"epoch": 0.8620205537148312,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004936480191552637,
|
|
"loss": 5.6022,
|
|
"mean_token_accuracy": 0.16884357035160064,
|
|
"num_tokens": 17137328.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.691303730010986,
|
|
"epoch": 0.8625821306227888,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004936385432087589,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.17725287824869157,
|
|
"num_tokens": 17148274.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.68599681854248,
|
|
"epoch": 0.8631437075307463,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004936290603007181,
|
|
"loss": 5.6081,
|
|
"mean_token_accuracy": 0.17466700077056885,
|
|
"num_tokens": 17158834.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.642597389221192,
|
|
"epoch": 0.8637052844387039,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.0004936195704314432,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.17301729917526246,
|
|
"num_tokens": 17169276.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.623114156723022,
|
|
"epoch": 0.8642668613466614,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004936100736012363,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.17950795441865922,
|
|
"num_tokens": 17180642.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.623469495773316,
|
|
"epoch": 0.864828438254619,
|
|
"grad_norm": 3.75,
|
|
"learning_rate": 0.0004936005698104,
|
|
"loss": 5.5797,
|
|
"mean_token_accuracy": 0.1778384640812874,
|
|
"num_tokens": 17192477.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.755904293060302,
|
|
"epoch": 0.8653900151625765,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004935910590592367,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.1742580860853195,
|
|
"num_tokens": 17202653.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.5930798053741455,
|
|
"epoch": 0.8659515920705341,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004935815413480494,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.18493536859750748,
|
|
"num_tokens": 17212607.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.649550819396973,
|
|
"epoch": 0.8665131689784916,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000493572016677141,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.18015509247779846,
|
|
"num_tokens": 17223701.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.698745775222778,
|
|
"epoch": 0.8670747458864492,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004935624850468148,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.17810380160808564,
|
|
"num_tokens": 17234878.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.644769525527954,
|
|
"epoch": 0.8676363227944067,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004935529464573742,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.181055548787117,
|
|
"num_tokens": 17245813.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.668835830688477,
|
|
"epoch": 0.8681978997023643,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004935434009091232,
|
|
"loss": 5.6484,
|
|
"mean_token_accuracy": 0.17038645595312119,
|
|
"num_tokens": 17257378.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.683637571334839,
|
|
"epoch": 0.8687594766103218,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935338484023655,
|
|
"loss": 5.5738,
|
|
"mean_token_accuracy": 0.17647527307271957,
|
|
"num_tokens": 17269108.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.709376668930053,
|
|
"epoch": 0.8693210535182794,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004935242889374052,
|
|
"loss": 5.5573,
|
|
"mean_token_accuracy": 0.1723323032259941,
|
|
"num_tokens": 17280643.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.7429304122924805,
|
|
"epoch": 0.8698826304262369,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004935147225145469,
|
|
"loss": 5.6039,
|
|
"mean_token_accuracy": 0.17040304988622665,
|
|
"num_tokens": 17291236.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.724596738815308,
|
|
"epoch": 0.8704442073341944,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004935051491340951,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.1641794964671135,
|
|
"num_tokens": 17303547.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.772427749633789,
|
|
"epoch": 0.8710057842421519,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004934955687963546,
|
|
"loss": 5.67,
|
|
"mean_token_accuracy": 0.16841694563627244,
|
|
"num_tokens": 17314803.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.676794385910034,
|
|
"epoch": 0.8715673611501095,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004934859815016304,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.17323208898305892,
|
|
"num_tokens": 17326009.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.728955554962158,
|
|
"epoch": 0.872128938058067,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004934763872502278,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.17600940316915512,
|
|
"num_tokens": 17337078.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.712660694122315,
|
|
"epoch": 0.8726905149660246,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004934667860424523,
|
|
"loss": 5.6607,
|
|
"mean_token_accuracy": 0.1724629208445549,
|
|
"num_tokens": 17349266.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.548857116699219,
|
|
"epoch": 0.8732520918739821,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004934571778786096,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.177022847533226,
|
|
"num_tokens": 17360327.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.7217004776000975,
|
|
"epoch": 0.8738136687819397,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004934475627590057,
|
|
"loss": 5.6328,
|
|
"mean_token_accuracy": 0.16501476615667343,
|
|
"num_tokens": 17372727.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.791033172607422,
|
|
"epoch": 0.8743752456898972,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004934379406839466,
|
|
"loss": 5.689,
|
|
"mean_token_accuracy": 0.16976454704999924,
|
|
"num_tokens": 17384160.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.695014572143554,
|
|
"epoch": 0.8749368225978548,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004934283116537387,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.17003939300775528,
|
|
"num_tokens": 17396009.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.684281635284424,
|
|
"epoch": 0.8754983995058123,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004934186756686888,
|
|
"loss": 5.5896,
|
|
"mean_token_accuracy": 0.18018183410167693,
|
|
"num_tokens": 17406903.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.611761426925659,
|
|
"epoch": 0.8760599764137699,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004934090327291034,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.18282824605703354,
|
|
"num_tokens": 17417694.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.678828001022339,
|
|
"epoch": 0.8766215533217274,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004933993828352898,
|
|
"loss": 5.7037,
|
|
"mean_token_accuracy": 0.17537779957056046,
|
|
"num_tokens": 17428731.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.653815221786499,
|
|
"epoch": 0.877183130229685,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004933897259875551,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.17921098321676254,
|
|
"num_tokens": 17439242.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.653625059127807,
|
|
"epoch": 0.8777447071376425,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004933800621862069,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.17184631079435347,
|
|
"num_tokens": 17449980.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.737390089035034,
|
|
"epoch": 0.8783062840456001,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004933703914315527,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.16485216468572617,
|
|
"num_tokens": 17464140.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.802713108062744,
|
|
"epoch": 0.8788678609535576,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004933607137239006,
|
|
"loss": 5.6794,
|
|
"mean_token_accuracy": 0.16709450185298919,
|
|
"num_tokens": 17476246.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.700329065322876,
|
|
"epoch": 0.8794294378615152,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004933510290635587,
|
|
"loss": 5.6729,
|
|
"mean_token_accuracy": 0.16323288530111313,
|
|
"num_tokens": 17488169.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.628879976272583,
|
|
"epoch": 0.8799910147694727,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004933413374508353,
|
|
"loss": 5.4966,
|
|
"mean_token_accuracy": 0.18120042681694032,
|
|
"num_tokens": 17498465.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.72340030670166,
|
|
"epoch": 0.8805525916774303,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004933316388860391,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.18224168121814727,
|
|
"num_tokens": 17509217.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.604537725448608,
|
|
"epoch": 0.8811141685853877,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004933219333694787,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1800143763422966,
|
|
"num_tokens": 17519851.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.596671485900879,
|
|
"epoch": 0.8816757454933453,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004933122209014634,
|
|
"loss": 5.6221,
|
|
"mean_token_accuracy": 0.172597998380661,
|
|
"num_tokens": 17532144.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.713442754745484,
|
|
"epoch": 0.8822373224013028,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004933025014823022,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.18564504384994507,
|
|
"num_tokens": 17542929.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.765399217605591,
|
|
"epoch": 0.8827988993092604,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004932927751123048,
|
|
"loss": 5.688,
|
|
"mean_token_accuracy": 0.1656603366136551,
|
|
"num_tokens": 17554931.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.628981876373291,
|
|
"epoch": 0.8833604762172179,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004932830417917808,
|
|
"loss": 5.4908,
|
|
"mean_token_accuracy": 0.17961080223321915,
|
|
"num_tokens": 17566026.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.663094472885132,
|
|
"epoch": 0.8839220531251755,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.00049327330152104,
|
|
"loss": 5.6052,
|
|
"mean_token_accuracy": 0.17467530816793442,
|
|
"num_tokens": 17578396.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.731671619415283,
|
|
"epoch": 0.884483630033133,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004932635543003927,
|
|
"loss": 5.5832,
|
|
"mean_token_accuracy": 0.17580243200063705,
|
|
"num_tokens": 17590559.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.693300533294678,
|
|
"epoch": 0.8850452069410906,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004932538001301491,
|
|
"loss": 5.5592,
|
|
"mean_token_accuracy": 0.17190149873495103,
|
|
"num_tokens": 17600833.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.623101806640625,
|
|
"epoch": 0.8856067838490481,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004932440390106199,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.18049022555351257,
|
|
"num_tokens": 17612166.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.681110191345215,
|
|
"epoch": 0.8861683607570057,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004932342709421159,
|
|
"loss": 5.654,
|
|
"mean_token_accuracy": 0.17037189304828643,
|
|
"num_tokens": 17623070.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.756334829330444,
|
|
"epoch": 0.8867299376649632,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000493224495924948,
|
|
"loss": 5.7049,
|
|
"mean_token_accuracy": 0.16897829324007035,
|
|
"num_tokens": 17633319.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.7080238342285154,
|
|
"epoch": 0.8872915145729208,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004932147139594276,
|
|
"loss": 5.5212,
|
|
"mean_token_accuracy": 0.17253592759370803,
|
|
"num_tokens": 17643818.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.634365177154541,
|
|
"epoch": 0.8878530914808783,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004932049250458659,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.1762784257531166,
|
|
"num_tokens": 17655665.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.67090482711792,
|
|
"epoch": 0.8884146683888359,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004931951291845749,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.18168685287237168,
|
|
"num_tokens": 17666200.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.651503849029541,
|
|
"epoch": 0.8889762452967934,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004931853263758663,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1698780193924904,
|
|
"num_tokens": 17677299.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.6418108463287355,
|
|
"epoch": 0.889537822204751,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004931755166200523,
|
|
"loss": 5.4936,
|
|
"mean_token_accuracy": 0.18307234048843385,
|
|
"num_tokens": 17687870.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.624146795272827,
|
|
"epoch": 0.8900993991127085,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004931656999174452,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.1746792510151863,
|
|
"num_tokens": 17698853.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.647106504440307,
|
|
"epoch": 0.8906609760206661,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004931558762683577,
|
|
"loss": 5.5863,
|
|
"mean_token_accuracy": 0.17398217171430588,
|
|
"num_tokens": 17709897.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.667969655990601,
|
|
"epoch": 0.8912225529286236,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004931460456731024,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.17649135142564773,
|
|
"num_tokens": 17720974.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.816218900680542,
|
|
"epoch": 0.8917841298365812,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004931362081319925,
|
|
"loss": 5.728,
|
|
"mean_token_accuracy": 0.16669692397117614,
|
|
"num_tokens": 17734449.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.605280160903931,
|
|
"epoch": 0.8923457067445386,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004931263636453409,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.18089240044355392,
|
|
"num_tokens": 17744735.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.611375331878662,
|
|
"epoch": 0.8929072836524962,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004931165122134616,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.1795281410217285,
|
|
"num_tokens": 17755641.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.659450197219849,
|
|
"epoch": 0.8934688605604537,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004931066538366677,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.1653539150953293,
|
|
"num_tokens": 17767621.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.801513242721557,
|
|
"epoch": 0.8940304374684113,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004930967885152734,
|
|
"loss": 5.7048,
|
|
"mean_token_accuracy": 0.17148170471191407,
|
|
"num_tokens": 17779507.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.653532075881958,
|
|
"epoch": 0.8945920143763688,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004930869162495929,
|
|
"loss": 5.534,
|
|
"mean_token_accuracy": 0.1737334132194519,
|
|
"num_tokens": 17790371.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.652678155899048,
|
|
"epoch": 0.8951535912843264,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004930770370399403,
|
|
"loss": 5.5519,
|
|
"mean_token_accuracy": 0.180663301050663,
|
|
"num_tokens": 17800903.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.778237247467041,
|
|
"epoch": 0.8957151681922839,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004930671508866303,
|
|
"loss": 5.7363,
|
|
"mean_token_accuracy": 0.1609813392162323,
|
|
"num_tokens": 17812053.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.703821754455566,
|
|
"epoch": 0.8962767451002415,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004930572577899776,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.18012819886207582,
|
|
"num_tokens": 17822113.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.617430734634399,
|
|
"epoch": 0.896838322008199,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004930473577502972,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.1737213149666786,
|
|
"num_tokens": 17832741.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.525353956222534,
|
|
"epoch": 0.8973998989161566,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004930374507679044,
|
|
"loss": 5.4559,
|
|
"mean_token_accuracy": 0.17217440605163575,
|
|
"num_tokens": 17842968.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.770102500915527,
|
|
"epoch": 0.8979614758241141,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004930275368431146,
|
|
"loss": 5.7246,
|
|
"mean_token_accuracy": 0.16206833869218826,
|
|
"num_tokens": 17854295.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.762260866165161,
|
|
"epoch": 0.8985230527320717,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004930176159762435,
|
|
"loss": 5.6491,
|
|
"mean_token_accuracy": 0.1736169084906578,
|
|
"num_tokens": 17865597.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.51307783126831,
|
|
"epoch": 0.8990846296400292,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004930076881676069,
|
|
"loss": 5.4033,
|
|
"mean_token_accuracy": 0.1824817478656769,
|
|
"num_tokens": 17877405.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.776148986816406,
|
|
"epoch": 0.8996462065479868,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004929977534175211,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.17300699204206466,
|
|
"num_tokens": 17889273.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.690951871871948,
|
|
"epoch": 0.9002077834559443,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004929878117263021,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.18159338533878328,
|
|
"num_tokens": 17899761.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.605482196807861,
|
|
"epoch": 0.9007693603639019,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004929778630942668,
|
|
"loss": 5.5233,
|
|
"mean_token_accuracy": 0.17722438275814056,
|
|
"num_tokens": 17910607.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.694642734527588,
|
|
"epoch": 0.9013309372718594,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004929679075217317,
|
|
"loss": 5.5892,
|
|
"mean_token_accuracy": 0.1711652860045433,
|
|
"num_tokens": 17922538.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.756507778167725,
|
|
"epoch": 0.901892514179817,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004929579450090139,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.1729684889316559,
|
|
"num_tokens": 17933313.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.713122892379761,
|
|
"epoch": 0.9024540910877745,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004929479755564305,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.1717493712902069,
|
|
"num_tokens": 17944893.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.694264364242554,
|
|
"epoch": 0.903015667995732,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004929379991642991,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.17288902550935745,
|
|
"num_tokens": 17955019.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.748342227935791,
|
|
"epoch": 0.9035772449036895,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004929280158329373,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.17052851468324662,
|
|
"num_tokens": 17965793.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.621027660369873,
|
|
"epoch": 0.9041388218116471,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000492918025562663,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.1798245221376419,
|
|
"num_tokens": 17975709.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.74473385810852,
|
|
"epoch": 0.9047003987196046,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004929080283537942,
|
|
"loss": 5.6681,
|
|
"mean_token_accuracy": 0.17205129265785218,
|
|
"num_tokens": 17985405.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.801194858551026,
|
|
"epoch": 0.9052619756275622,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004928980242066492,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.164870385825634,
|
|
"num_tokens": 17997105.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.693590450286865,
|
|
"epoch": 0.9058235525355197,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004928880131215467,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.18127355575561524,
|
|
"num_tokens": 18007914.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.580331611633301,
|
|
"epoch": 0.9063851294434773,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004928779950988053,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.1781117409467697,
|
|
"num_tokens": 18018328.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.726330327987671,
|
|
"epoch": 0.9069467063514348,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000492867970138744,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.17253135591745378,
|
|
"num_tokens": 18028568.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.721500825881958,
|
|
"epoch": 0.9075082832593924,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004928579382416821,
|
|
"loss": 5.5651,
|
|
"mean_token_accuracy": 0.17368777096271515,
|
|
"num_tokens": 18038655.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.6272046089172365,
|
|
"epoch": 0.9080698601673499,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000492847899407939,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.1774340182542801,
|
|
"num_tokens": 18049716.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.572261381149292,
|
|
"epoch": 0.9086314370753075,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004928378536378341,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.17788090854883193,
|
|
"num_tokens": 18062530.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.634653329849243,
|
|
"epoch": 0.909193013983265,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004928278009316877,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.17149213552474976,
|
|
"num_tokens": 18073076.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.781269645690918,
|
|
"epoch": 0.9097545908912226,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004928177412898195,
|
|
"loss": 5.5415,
|
|
"mean_token_accuracy": 0.1750569149851799,
|
|
"num_tokens": 18083759.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.611255264282226,
|
|
"epoch": 0.9103161677991801,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004928076747125499,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.17623679488897323,
|
|
"num_tokens": 18095980.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.676711750030518,
|
|
"epoch": 0.9108777447071377,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004927976012001995,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.18180532306432723,
|
|
"num_tokens": 18106672.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.682359600067139,
|
|
"epoch": 0.9114393216150952,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004927875207530889,
|
|
"loss": 5.5843,
|
|
"mean_token_accuracy": 0.17720671892166137,
|
|
"num_tokens": 18117481.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.648852872848511,
|
|
"epoch": 0.9120008985230528,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004927774333715394,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.1770884022116661,
|
|
"num_tokens": 18127602.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.704408836364746,
|
|
"epoch": 0.9125624754310103,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004927673390558718,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.17160902470350264,
|
|
"num_tokens": 18140109.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.651796293258667,
|
|
"epoch": 0.9131240523389679,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004927572378064077,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.1826114058494568,
|
|
"num_tokens": 18150271.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.652785587310791,
|
|
"epoch": 0.9136856292469253,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004927471296234687,
|
|
"loss": 5.5914,
|
|
"mean_token_accuracy": 0.17776049822568893,
|
|
"num_tokens": 18160746.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.74228982925415,
|
|
"epoch": 0.9142472061548829,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004927370145073767,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.1723599538207054,
|
|
"num_tokens": 18172271.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.617870855331421,
|
|
"epoch": 0.9148087830628404,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004927268924584536,
|
|
"loss": 5.5143,
|
|
"mean_token_accuracy": 0.17771777957677842,
|
|
"num_tokens": 18183116.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.581591367721558,
|
|
"epoch": 0.915370359970798,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004927167634770219,
|
|
"loss": 5.4877,
|
|
"mean_token_accuracy": 0.1830562487244606,
|
|
"num_tokens": 18195147.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.685018539428711,
|
|
"epoch": 0.9159319368787555,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000492706627563404,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.17168653160333633,
|
|
"num_tokens": 18206217.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.632122325897217,
|
|
"epoch": 0.9164935137867131,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004926964847179225,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.17168980538845063,
|
|
"num_tokens": 18217434.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.673951530456543,
|
|
"epoch": 0.9170550906946706,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004926863349409006,
|
|
"loss": 5.5755,
|
|
"mean_token_accuracy": 0.17168763279914856,
|
|
"num_tokens": 18229277.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.649858522415161,
|
|
"epoch": 0.9176166676026282,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004926761782326613,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.1778325006365776,
|
|
"num_tokens": 18240320.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.553313732147217,
|
|
"epoch": 0.9181782445105857,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004926660145935282,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.17954605370759963,
|
|
"num_tokens": 18250380.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.688686084747315,
|
|
"epoch": 0.9187398214185433,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004926558440238247,
|
|
"loss": 5.6471,
|
|
"mean_token_accuracy": 0.17253658026456833,
|
|
"num_tokens": 18261703.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.703602361679077,
|
|
"epoch": 0.9193013983265008,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004926456665238746,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.16524005234241484,
|
|
"num_tokens": 18272472.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.745394611358643,
|
|
"epoch": 0.9198629752344584,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004926354820940023,
|
|
"loss": 5.6479,
|
|
"mean_token_accuracy": 0.1751138225197792,
|
|
"num_tokens": 18282168.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.774199628829956,
|
|
"epoch": 0.9204245521424159,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004926252907345317,
|
|
"loss": 5.6558,
|
|
"mean_token_accuracy": 0.16767536401748656,
|
|
"num_tokens": 18293750.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.673816728591919,
|
|
"epoch": 0.9209861290503735,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004926150924457874,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.1784728467464447,
|
|
"num_tokens": 18304568.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.589570665359497,
|
|
"epoch": 0.921547705958331,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004926048872280943,
|
|
"loss": 5.5066,
|
|
"mean_token_accuracy": 0.17553699016571045,
|
|
"num_tokens": 18315129.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.552234077453614,
|
|
"epoch": 0.9221092828662886,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.000492594675081777,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17450139820575714,
|
|
"num_tokens": 18324628.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.558914661407471,
|
|
"epoch": 0.9226708597742461,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000492584456007161,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.18473241925239564,
|
|
"num_tokens": 18334899.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.7117359161376955,
|
|
"epoch": 0.9232324366822037,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004925742300045716,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.18072808980941774,
|
|
"num_tokens": 18345719.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.69600396156311,
|
|
"epoch": 0.9237940135901612,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004925639970743341,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17595994621515273,
|
|
"num_tokens": 18355814.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.6686724662780765,
|
|
"epoch": 0.9243555904981187,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004925537572167746,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.16898559629917145,
|
|
"num_tokens": 18366746.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.631911897659302,
|
|
"epoch": 0.9249171674060762,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004925435104322192,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.1808200404047966,
|
|
"num_tokens": 18375846.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.5890521049499515,
|
|
"epoch": 0.9254787443140338,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000492533256720994,
|
|
"loss": 5.5983,
|
|
"mean_token_accuracy": 0.17320639044046401,
|
|
"num_tokens": 18386850.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.620068836212158,
|
|
"epoch": 0.9260403212219913,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004925229960834256,
|
|
"loss": 5.473,
|
|
"mean_token_accuracy": 0.18279864341020585,
|
|
"num_tokens": 18396347.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.625076961517334,
|
|
"epoch": 0.9266018981299489,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004925127285198407,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.17717241495847702,
|
|
"num_tokens": 18406583.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.683979511260986,
|
|
"epoch": 0.9271634750379064,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000492502454030566,
|
|
"loss": 5.6598,
|
|
"mean_token_accuracy": 0.17038192301988603,
|
|
"num_tokens": 18418586.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.695053768157959,
|
|
"epoch": 0.927725051945864,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004924921726159288,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.17574006617069243,
|
|
"num_tokens": 18429752.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.693711280822754,
|
|
"epoch": 0.9282866288538215,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004924818842762565,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.17145896553993226,
|
|
"num_tokens": 18440663.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.601040029525757,
|
|
"epoch": 0.9288482057617791,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004924715890118768,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.17853964418172835,
|
|
"num_tokens": 18451497.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.631322526931763,
|
|
"epoch": 0.9294097826697366,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004924612868231173,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.17173729091882706,
|
|
"num_tokens": 18462794.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.681131792068482,
|
|
"epoch": 0.9299713595776942,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004924509777103059,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.17871456742286682,
|
|
"num_tokens": 18472973.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.741029167175293,
|
|
"epoch": 0.9305329364856517,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004924406616737712,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.17547629326581954,
|
|
"num_tokens": 18484451.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.690219879150391,
|
|
"epoch": 0.9310945133936093,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004924303387138415,
|
|
"loss": 5.5088,
|
|
"mean_token_accuracy": 0.18424760699272155,
|
|
"num_tokens": 18496412.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.689821767807007,
|
|
"epoch": 0.9316560903015668,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004924200088308455,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.17829930782318115,
|
|
"num_tokens": 18508547.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.631864261627197,
|
|
"epoch": 0.9322176672095244,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000492409672025112,
|
|
"loss": 5.5845,
|
|
"mean_token_accuracy": 0.1763853833079338,
|
|
"num_tokens": 18518954.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.585439920425415,
|
|
"epoch": 0.9327792441174819,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004923993282969703,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.17674497961997987,
|
|
"num_tokens": 18530444.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.662316799163818,
|
|
"epoch": 0.9333408210254395,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004923889776467495,
|
|
"loss": 5.5149,
|
|
"mean_token_accuracy": 0.1739640235900879,
|
|
"num_tokens": 18541612.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.65343542098999,
|
|
"epoch": 0.933902397933397,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004923786200747795,
|
|
"loss": 5.6616,
|
|
"mean_token_accuracy": 0.17635414600372315,
|
|
"num_tokens": 18553316.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.671051549911499,
|
|
"epoch": 0.9344639748413546,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00049236825558139,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1770639404654503,
|
|
"num_tokens": 18564468.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.63475284576416,
|
|
"epoch": 0.9350255517493121,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004923578841669108,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.17903632968664168,
|
|
"num_tokens": 18575536.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.625029373168945,
|
|
"epoch": 0.9355871286572696,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004923475058316723,
|
|
"loss": 5.5976,
|
|
"mean_token_accuracy": 0.16649289578199386,
|
|
"num_tokens": 18586906.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.693419122695923,
|
|
"epoch": 0.9361487055652271,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004923371205760049,
|
|
"loss": 5.5872,
|
|
"mean_token_accuracy": 0.1770857334136963,
|
|
"num_tokens": 18599064.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.679988765716553,
|
|
"epoch": 0.9367102824731847,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004923267284002394,
|
|
"loss": 5.6127,
|
|
"mean_token_accuracy": 0.1727571114897728,
|
|
"num_tokens": 18610057.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.588805341720581,
|
|
"epoch": 0.9372718593811422,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004923163293047065,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.1811217650771141,
|
|
"num_tokens": 18620008.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.549160051345825,
|
|
"epoch": 0.9378334362890998,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004923059232897374,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.17653147429227828,
|
|
"num_tokens": 18630599.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.641821670532226,
|
|
"epoch": 0.9383950131970573,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.0004922955103556633,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17712246924638747,
|
|
"num_tokens": 18643898.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.688621377944946,
|
|
"epoch": 0.9389565901050149,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000492285090502816,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.1701018825173378,
|
|
"num_tokens": 18654760.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.748991823196411,
|
|
"epoch": 0.9395181670129724,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004922746637315272,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1785283789038658,
|
|
"num_tokens": 18666036.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.683083534240723,
|
|
"epoch": 0.94007974392093,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004922642300421288,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.17138388007879257,
|
|
"num_tokens": 18677806.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.6514660835266115,
|
|
"epoch": 0.9406413208288875,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000492253789434953,
|
|
"loss": 5.7165,
|
|
"mean_token_accuracy": 0.17123143523931503,
|
|
"num_tokens": 18688971.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.62733678817749,
|
|
"epoch": 0.9412028977368451,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004922433419103323,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.17309036999940872,
|
|
"num_tokens": 18700153.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.814475679397583,
|
|
"epoch": 0.9417644746448026,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004922328874685993,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.17277702391147615,
|
|
"num_tokens": 18711935.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.570269012451172,
|
|
"epoch": 0.9423260515527602,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004922224261100869,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.17691634595394135,
|
|
"num_tokens": 18722694.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.639089107513428,
|
|
"epoch": 0.9428876284607177,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004922119578351283,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.17720753848552703,
|
|
"num_tokens": 18733443.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.7299501419067385,
|
|
"epoch": 0.9434492053686753,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004922014826440566,
|
|
"loss": 5.5324,
|
|
"mean_token_accuracy": 0.17335634529590607,
|
|
"num_tokens": 18743965.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.710513257980347,
|
|
"epoch": 0.9440107822766328,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004921910005372056,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.17963121086359024,
|
|
"num_tokens": 18755712.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.640870714187622,
|
|
"epoch": 0.9445723591845904,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004921805115149088,
|
|
"loss": 5.5216,
|
|
"mean_token_accuracy": 0.17827638983726501,
|
|
"num_tokens": 18766756.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.6685035705566404,
|
|
"epoch": 0.9451339360925479,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004921700155775002,
|
|
"loss": 5.6272,
|
|
"mean_token_accuracy": 0.1680072546005249,
|
|
"num_tokens": 18776932.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.7400336265563965,
|
|
"epoch": 0.9456955130005055,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004921595127253142,
|
|
"loss": 5.5397,
|
|
"mean_token_accuracy": 0.1733703002333641,
|
|
"num_tokens": 18787197.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.615275478363037,
|
|
"epoch": 0.9462570899084629,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004921490029586852,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.17929631620645523,
|
|
"num_tokens": 18797861.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.610781955718994,
|
|
"epoch": 0.9468186668164205,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004921384862779475,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.17076777517795563,
|
|
"num_tokens": 18809111.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.629825782775879,
|
|
"epoch": 0.947380243724378,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004921279626834363,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.18722035735845566,
|
|
"num_tokens": 18820236.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.620464324951172,
|
|
"epoch": 0.9479418206323356,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004921174321754865,
|
|
"loss": 5.5306,
|
|
"mean_token_accuracy": 0.17501709014177322,
|
|
"num_tokens": 18831942.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.656056499481201,
|
|
"epoch": 0.9485033975402931,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004921068947544335,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.1795904278755188,
|
|
"num_tokens": 18843271.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.636099624633789,
|
|
"epoch": 0.9490649744482507,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004920963504206128,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.1753099024295807,
|
|
"num_tokens": 18856285.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.718980216979981,
|
|
"epoch": 0.9496265513562082,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00049208579917436,
|
|
"loss": 5.6233,
|
|
"mean_token_accuracy": 0.17174718677997589,
|
|
"num_tokens": 18867203.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.72203516960144,
|
|
"epoch": 0.9501881282641658,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004920752410160113,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.1661757580935955,
|
|
"num_tokens": 18878598.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.763786125183105,
|
|
"epoch": 0.9507497051721233,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004920646759459026,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1740238443017006,
|
|
"num_tokens": 18890233.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.745761299133301,
|
|
"epoch": 0.9513112820800809,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004920541039643705,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.1718573421239853,
|
|
"num_tokens": 18900362.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.707382488250732,
|
|
"epoch": 0.9518728589880384,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004920435250717515,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.18245701640844345,
|
|
"num_tokens": 18911924.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.645588779449463,
|
|
"epoch": 0.952434435895996,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004920329392683826,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.17342214286327362,
|
|
"num_tokens": 18923931.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.63425087928772,
|
|
"epoch": 0.9529960128039535,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004920223465546006,
|
|
"loss": 5.5087,
|
|
"mean_token_accuracy": 0.17417115420103074,
|
|
"num_tokens": 18935859.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.7128466129302975,
|
|
"epoch": 0.9535575897119111,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004920117469307429,
|
|
"loss": 5.6225,
|
|
"mean_token_accuracy": 0.16998782902956008,
|
|
"num_tokens": 18946939.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.701489686965942,
|
|
"epoch": 0.9541191666198686,
|
|
"grad_norm": 1.9453125,
|
|
"learning_rate": 0.0004920011403971471,
|
|
"loss": 5.6001,
|
|
"mean_token_accuracy": 0.1682334840297699,
|
|
"num_tokens": 18958067.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.672072982788086,
|
|
"epoch": 0.9546807435278262,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004919905269541508,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.18022983372211457,
|
|
"num_tokens": 18967920.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.703696012496948,
|
|
"epoch": 0.9552423204357837,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000491979906602092,
|
|
"loss": 5.5426,
|
|
"mean_token_accuracy": 0.18027961552143096,
|
|
"num_tokens": 18978244.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.672524309158325,
|
|
"epoch": 0.9558038973437413,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004919692793413089,
|
|
"loss": 5.5005,
|
|
"mean_token_accuracy": 0.17284238785505296,
|
|
"num_tokens": 18988464.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.561907958984375,
|
|
"epoch": 0.9563654742516988,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919586451721396,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18105681389570236,
|
|
"num_tokens": 18998318.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.537799835205078,
|
|
"epoch": 0.9569270511596563,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004919480040949229,
|
|
"loss": 5.4585,
|
|
"mean_token_accuracy": 0.18256353437900544,
|
|
"num_tokens": 19009802.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.742551279067993,
|
|
"epoch": 0.9574886280676138,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919373561099977,
|
|
"loss": 5.655,
|
|
"mean_token_accuracy": 0.17528429478406907,
|
|
"num_tokens": 19020174.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.715784358978271,
|
|
"epoch": 0.9580502049755714,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000491926701217703,
|
|
"loss": 5.5768,
|
|
"mean_token_accuracy": 0.17329147160053254,
|
|
"num_tokens": 19031505.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.60780439376831,
|
|
"epoch": 0.9586117818835289,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004919160394183779,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17882321029901505,
|
|
"num_tokens": 19042052.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.8012824058532715,
|
|
"epoch": 0.9591733587914865,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000491905370712362,
|
|
"loss": 5.6917,
|
|
"mean_token_accuracy": 0.16911431699991225,
|
|
"num_tokens": 19052050.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.743633985519409,
|
|
"epoch": 0.959734935699444,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004918946950999949,
|
|
"loss": 5.597,
|
|
"mean_token_accuracy": 0.17632216066122056,
|
|
"num_tokens": 19062053.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.60989785194397,
|
|
"epoch": 0.9602965126074016,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004918840125816167,
|
|
"loss": 5.56,
|
|
"mean_token_accuracy": 0.17322750091552735,
|
|
"num_tokens": 19073095.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.69147424697876,
|
|
"epoch": 0.9608580895153591,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004918733231575673,
|
|
"loss": 5.603,
|
|
"mean_token_accuracy": 0.1803808957338333,
|
|
"num_tokens": 19084521.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.712701225280762,
|
|
"epoch": 0.9614196664233167,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004918626268281874,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.17296867966651916,
|
|
"num_tokens": 19096372.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.77578387260437,
|
|
"epoch": 0.9619812433312742,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004918519235938171,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.16620417684316635,
|
|
"num_tokens": 19108535.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.795299959182739,
|
|
"epoch": 0.9625428202392318,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004918412134547976,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.18113145977258682,
|
|
"num_tokens": 19119480.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.669289398193359,
|
|
"epoch": 0.9631043971471893,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004918304964114696,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.17587678730487824,
|
|
"num_tokens": 19131168.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.714877080917359,
|
|
"epoch": 0.9636659740551469,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004918197724641747,
|
|
"loss": 5.7133,
|
|
"mean_token_accuracy": 0.1696150705218315,
|
|
"num_tokens": 19142454.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.745925092697144,
|
|
"epoch": 0.9642275509631044,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.000491809041613254,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.17436073273420333,
|
|
"num_tokens": 19154682.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.622589588165283,
|
|
"epoch": 0.964789127871062,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004917983038590495,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.17552960067987441,
|
|
"num_tokens": 19165190.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.714442539215088,
|
|
"epoch": 0.9653507047790195,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004917875592019028,
|
|
"loss": 5.62,
|
|
"mean_token_accuracy": 0.18550368398427963,
|
|
"num_tokens": 19176075.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.723754024505615,
|
|
"epoch": 0.9659122816869771,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004917768076421561,
|
|
"loss": 5.6368,
|
|
"mean_token_accuracy": 0.17450472414493562,
|
|
"num_tokens": 19188450.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.618573141098023,
|
|
"epoch": 0.9664738585949346,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004917660491801518,
|
|
"loss": 5.5002,
|
|
"mean_token_accuracy": 0.18101489990949632,
|
|
"num_tokens": 19201254.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.60259690284729,
|
|
"epoch": 0.9670354355028922,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004917552838162324,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.17486478239297867,
|
|
"num_tokens": 19214062.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.647714471817016,
|
|
"epoch": 0.9675970124108496,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004917445115507408,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.1825477138161659,
|
|
"num_tokens": 19224844.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.716549396514893,
|
|
"epoch": 0.9681585893188072,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004917337323840198,
|
|
"loss": 5.6754,
|
|
"mean_token_accuracy": 0.16997099071741104,
|
|
"num_tokens": 19237347.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.7693475723266605,
|
|
"epoch": 0.9687201662267647,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004917229463164128,
|
|
"loss": 5.5317,
|
|
"mean_token_accuracy": 0.17363337129354478,
|
|
"num_tokens": 19248743.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.6307563304901125,
|
|
"epoch": 0.9692817431347223,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004917121533482631,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.17544113993644714,
|
|
"num_tokens": 19259904.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.568870973587036,
|
|
"epoch": 0.9698433200426798,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004917013534799144,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.17763842195272445,
|
|
"num_tokens": 19271388.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.63384313583374,
|
|
"epoch": 0.9704048969506374,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916905467117104,
|
|
"loss": 5.5929,
|
|
"mean_token_accuracy": 0.1758931651711464,
|
|
"num_tokens": 19282790.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.661542987823486,
|
|
"epoch": 0.9709664738585949,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004916797330439955,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1813986286520958,
|
|
"num_tokens": 19293389.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.662568521499634,
|
|
"epoch": 0.9715280507665525,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004916689124771138,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.1749889686703682,
|
|
"num_tokens": 19304593.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.656019639968872,
|
|
"epoch": 0.97208962767451,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004916580850114099,
|
|
"loss": 5.5045,
|
|
"mean_token_accuracy": 0.1728900045156479,
|
|
"num_tokens": 19317388.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.719638395309448,
|
|
"epoch": 0.9726512045824676,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004916472506472286,
|
|
"loss": 5.5637,
|
|
"mean_token_accuracy": 0.1767612650990486,
|
|
"num_tokens": 19329228.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.759158706665039,
|
|
"epoch": 0.9732127814904251,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004916364093849147,
|
|
"loss": 5.5251,
|
|
"mean_token_accuracy": 0.17813380360603331,
|
|
"num_tokens": 19339421.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.528590393066406,
|
|
"epoch": 0.9737743583983827,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004916255612248136,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.18374335318803786,
|
|
"num_tokens": 19349618.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.514968919754028,
|
|
"epoch": 0.9743359353063402,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004916147061672706,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.17703751623630523,
|
|
"num_tokens": 19361324.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.690497255325317,
|
|
"epoch": 0.9748975122142978,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004916038442126314,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.17250583320856094,
|
|
"num_tokens": 19373631.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.637275552749633,
|
|
"epoch": 0.9754590891222553,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004915929753612416,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.1686199814081192,
|
|
"num_tokens": 19384682.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.7076808452606205,
|
|
"epoch": 0.9760206660302129,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004915820996134477,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.17097554057836534,
|
|
"num_tokens": 19396344.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.715520906448364,
|
|
"epoch": 0.9765822429381704,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004915712169695956,
|
|
"loss": 5.4709,
|
|
"mean_token_accuracy": 0.17768008708953859,
|
|
"num_tokens": 19406921.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.5799322605133055,
|
|
"epoch": 0.977143819846128,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000491560327430032,
|
|
"loss": 5.5836,
|
|
"mean_token_accuracy": 0.17545484155416488,
|
|
"num_tokens": 19416851.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.641220235824585,
|
|
"epoch": 0.9777053967540855,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004915494309951035,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.1732786163687706,
|
|
"num_tokens": 19428180.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.815205240249634,
|
|
"epoch": 0.9782669736620431,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004915385276651573,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.1736613154411316,
|
|
"num_tokens": 19439575.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.726061391830444,
|
|
"epoch": 0.9788285505700005,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004915276174405403,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.17773232907056807,
|
|
"num_tokens": 19452074.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.552633142471313,
|
|
"epoch": 0.9793901274779581,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004915167003215999,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.17970690727233887,
|
|
"num_tokens": 19463085.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.757761764526367,
|
|
"epoch": 0.9799517043859156,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004915057763086838,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.1632278084754944,
|
|
"num_tokens": 19472726.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.652647209167481,
|
|
"epoch": 0.9805132812938732,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00049149484540214,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.1745603084564209,
|
|
"num_tokens": 19482275.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.671991872787475,
|
|
"epoch": 0.9810748582018307,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004914839076023161,
|
|
"loss": 5.5716,
|
|
"mean_token_accuracy": 0.1779387578368187,
|
|
"num_tokens": 19492782.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.572877264022827,
|
|
"epoch": 0.9816364351097883,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004914729629095609,
|
|
"loss": 5.4909,
|
|
"mean_token_accuracy": 0.1752992242574692,
|
|
"num_tokens": 19505709.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.720830345153809,
|
|
"epoch": 0.9821980120177458,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004914620113242224,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.17738298028707505,
|
|
"num_tokens": 19516269.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.682257652282715,
|
|
"epoch": 0.9827595889257034,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004914510528466495,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.17359429150819777,
|
|
"num_tokens": 19526786.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.663797616958618,
|
|
"epoch": 0.9833211658336609,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004914400874771913,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.1709943488240242,
|
|
"num_tokens": 19537865.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.547435903549195,
|
|
"epoch": 0.9838827427416185,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004914291152161967,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.17917720079421998,
|
|
"num_tokens": 19548320.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.648394823074341,
|
|
"epoch": 0.984444319649576,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.000491418136064015,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.17600739896297454,
|
|
"num_tokens": 19558856.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.721270656585693,
|
|
"epoch": 0.9850058965575336,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000491407150020996,
|
|
"loss": 5.6202,
|
|
"mean_token_accuracy": 0.1765390709042549,
|
|
"num_tokens": 19570792.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.714193677902221,
|
|
"epoch": 0.9855674734654911,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004913961570874895,
|
|
"loss": 5.5154,
|
|
"mean_token_accuracy": 0.1830105021595955,
|
|
"num_tokens": 19581982.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.600076007843017,
|
|
"epoch": 0.9861290503734487,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004913851572638453,
|
|
"loss": 5.4785,
|
|
"mean_token_accuracy": 0.17621346861124038,
|
|
"num_tokens": 19592882.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.732886934280396,
|
|
"epoch": 0.9866906272814062,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004913741505504138,
|
|
"loss": 5.6872,
|
|
"mean_token_accuracy": 0.17119225561618806,
|
|
"num_tokens": 19605967.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.754200792312622,
|
|
"epoch": 0.9872522041893638,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004913631369475454,
|
|
"loss": 5.52,
|
|
"mean_token_accuracy": 0.1800520732998848,
|
|
"num_tokens": 19616494.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.717560911178589,
|
|
"epoch": 0.9878137810973213,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004913521164555909,
|
|
"loss": 5.6256,
|
|
"mean_token_accuracy": 0.17602189779281616,
|
|
"num_tokens": 19627013.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.6537947177886965,
|
|
"epoch": 0.9883753580052789,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000491341089074901,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.17930024564266206,
|
|
"num_tokens": 19639099.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.556262731552124,
|
|
"epoch": 0.9889369349132364,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000491330054805827,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.17944550812244414,
|
|
"num_tokens": 19650650.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.721939134597778,
|
|
"epoch": 0.9894985118211939,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004913190136487201,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.17561214566230773,
|
|
"num_tokens": 19662869.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.663711595535278,
|
|
"epoch": 0.9900600887291514,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004913079656039318,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.17974113076925277,
|
|
"num_tokens": 19673232.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.6064043045043945,
|
|
"epoch": 0.990621665637109,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004912969106718142,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.17540547698736192,
|
|
"num_tokens": 19685069.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.679324293136597,
|
|
"epoch": 0.9911832425450665,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.000491285848852719,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.16739898920059204,
|
|
"num_tokens": 19697018.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.7190502166748045,
|
|
"epoch": 0.9917448194530241,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004912747801469984,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.17672994881868362,
|
|
"num_tokens": 19707922.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.576621341705322,
|
|
"epoch": 0.9923063963609816,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.000491263704555005,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.17915810346603395,
|
|
"num_tokens": 19718693.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.610715532302857,
|
|
"epoch": 0.9928679732689392,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004912526220770913,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.17728226631879807,
|
|
"num_tokens": 19730846.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.609979581832886,
|
|
"epoch": 0.9934295501768967,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004912415327136103,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.17937719821929932,
|
|
"num_tokens": 19742099.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.684210729598999,
|
|
"epoch": 0.9939911270848543,
|
|
"grad_norm": 3.578125,
|
|
"learning_rate": 0.000491230436464915,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.17783138453960418,
|
|
"num_tokens": 19753216.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.661396884918213,
|
|
"epoch": 0.9945527039928118,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004912193333313589,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.17773212492465973,
|
|
"num_tokens": 19765316.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.675089502334595,
|
|
"epoch": 0.9951142809007694,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004912082233132951,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.17728288918733598,
|
|
"num_tokens": 19776208.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.703807687759399,
|
|
"epoch": 0.9956758578087269,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004911971064110778,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.1788608655333519,
|
|
"num_tokens": 19788065.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.614440059661865,
|
|
"epoch": 0.9962374347166845,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911859826250607,
|
|
"loss": 5.4856,
|
|
"mean_token_accuracy": 0.17918349653482438,
|
|
"num_tokens": 19799388.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.678346061706543,
|
|
"epoch": 0.996799011624642,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004911748519555981,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1749073877930641,
|
|
"num_tokens": 19809933.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.785956239700317,
|
|
"epoch": 0.9973605885325996,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004911637144030444,
|
|
"loss": 5.6653,
|
|
"mean_token_accuracy": 0.17404208183288575,
|
|
"num_tokens": 19821566.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.744418382644653,
|
|
"epoch": 0.9979221654405571,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004911525699677541,
|
|
"loss": 5.6185,
|
|
"mean_token_accuracy": 0.17414195835590363,
|
|
"num_tokens": 19833727.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.734260416030883,
|
|
"epoch": 0.9984837423485147,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004911414186500822,
|
|
"loss": 5.6245,
|
|
"mean_token_accuracy": 0.17345949858427048,
|
|
"num_tokens": 19845176.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.600122356414795,
|
|
"epoch": 0.9990453192564722,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004911302604503837,
|
|
"loss": 5.5284,
|
|
"mean_token_accuracy": 0.1696407601237297,
|
|
"num_tokens": 19857528.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.66111044883728,
|
|
"epoch": 0.9996068961644298,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004911190953690139,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.17762039303779603,
|
|
"num_tokens": 19868232.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.636859205034044,
|
|
"epoch": 1.0001123153815914,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004911079234063284,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.18010648091634116,
|
|
"num_tokens": 19877881.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.520360994338989,
|
|
"epoch": 1.000673892289549,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004910967445626826,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.18123285323381425,
|
|
"num_tokens": 19888398.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.707045364379883,
|
|
"epoch": 1.0012354691975065,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004910855588384327,
|
|
"loss": 5.4792,
|
|
"mean_token_accuracy": 0.17772954255342482,
|
|
"num_tokens": 19899661.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.739729022979736,
|
|
"epoch": 1.0017970461054642,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004910743662339348,
|
|
"loss": 5.5288,
|
|
"mean_token_accuracy": 0.1798144742846489,
|
|
"num_tokens": 19911073.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.585374593734741,
|
|
"epoch": 1.0023586230134216,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004910631667495452,
|
|
"loss": 5.4651,
|
|
"mean_token_accuracy": 0.17701857537031174,
|
|
"num_tokens": 19922567.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.638380002975464,
|
|
"epoch": 1.0029201999213793,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.0004910519603856207,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.17570638209581374,
|
|
"num_tokens": 19934547.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.685271501541138,
|
|
"epoch": 1.0034817768293367,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004910407471425179,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.17674654871225357,
|
|
"num_tokens": 19947659.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.676312017440796,
|
|
"epoch": 1.0040433537372944,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.000491029527020594,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.17461029440164566,
|
|
"num_tokens": 19958150.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.619139766693115,
|
|
"epoch": 1.0046049306452518,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004910183000202061,
|
|
"loss": 5.4433,
|
|
"mean_token_accuracy": 0.1796451598405838,
|
|
"num_tokens": 19968173.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.61542387008667,
|
|
"epoch": 1.0051665075532095,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004910070661417119,
|
|
"loss": 5.5039,
|
|
"mean_token_accuracy": 0.1765804871916771,
|
|
"num_tokens": 19978543.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.645347976684571,
|
|
"epoch": 1.005728084461167,
|
|
"grad_norm": 3.671875,
|
|
"learning_rate": 0.0004909958253854687,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.17577382922172546,
|
|
"num_tokens": 19989586.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.665614080429077,
|
|
"epoch": 1.0062896613691246,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004909845777518347,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.17679118365049362,
|
|
"num_tokens": 20000524.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.72092456817627,
|
|
"epoch": 1.006851238277082,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004909733232411681,
|
|
"loss": 5.583,
|
|
"mean_token_accuracy": 0.17497947663068772,
|
|
"num_tokens": 20012935.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.69691309928894,
|
|
"epoch": 1.0074128151850397,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004909620618538271,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.17664757668972014,
|
|
"num_tokens": 20024435.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.661853790283203,
|
|
"epoch": 1.007974392092997,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004909507935901702,
|
|
"loss": 5.5456,
|
|
"mean_token_accuracy": 0.1704924300312996,
|
|
"num_tokens": 20036017.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.632135391235352,
|
|
"epoch": 1.0085359690009548,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004909395184505564,
|
|
"loss": 5.5452,
|
|
"mean_token_accuracy": 0.17420265078544617,
|
|
"num_tokens": 20047216.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.623674011230468,
|
|
"epoch": 1.0090975459089122,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004909282364353445,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.18121083676815034,
|
|
"num_tokens": 20057439.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.635589361190796,
|
|
"epoch": 1.0096591228168699,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004909169475448938,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.17496005594730377,
|
|
"num_tokens": 20069602.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.605824279785156,
|
|
"epoch": 1.0102206997248273,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004909056517795638,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.17887651473283767,
|
|
"num_tokens": 20081366.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.69526162147522,
|
|
"epoch": 1.010782276632785,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004908943491397141,
|
|
"loss": 5.49,
|
|
"mean_token_accuracy": 0.1825063332915306,
|
|
"num_tokens": 20091384.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 1.010782276632785,
|
|
"eval_entropy": 5.5115505368063245,
|
|
"eval_loss": 5.58587646484375,
|
|
"eval_mean_token_accuracy": 0.18099574048071138,
|
|
"eval_num_tokens": 20091384.0,
|
|
"eval_runtime": 23.8437,
|
|
"eval_samples_per_second": 1300.682,
|
|
"eval_steps_per_second": 162.601,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.707508993148804,
|
|
"epoch": 1.0113438535407424,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004908830396257045,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.17169265896081926,
|
|
"num_tokens": 20102953.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.648795175552368,
|
|
"epoch": 1.0119054304486998,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004908717232378953,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.18231723308563233,
|
|
"num_tokens": 20113672.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.660697746276855,
|
|
"epoch": 1.0124670073566575,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004908603999766467,
|
|
"loss": 5.492,
|
|
"mean_token_accuracy": 0.18013499975204467,
|
|
"num_tokens": 20125143.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.634253692626953,
|
|
"epoch": 1.013028584264615,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004908490698423191,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.17621614336967467,
|
|
"num_tokens": 20135489.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.5843713760375975,
|
|
"epoch": 1.0135901611725726,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004908377328352736,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.18222546875476836,
|
|
"num_tokens": 20146768.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.423814153671264,
|
|
"epoch": 1.01415173808053,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004908263889558709,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.18339865356683732,
|
|
"num_tokens": 20156894.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.645891427993774,
|
|
"epoch": 1.0147133149884877,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004908150382044722,
|
|
"loss": 5.5398,
|
|
"mean_token_accuracy": 0.18084353506565093,
|
|
"num_tokens": 20168174.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.713699436187744,
|
|
"epoch": 1.0152748918964452,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000490803680581439,
|
|
"loss": 5.6153,
|
|
"mean_token_accuracy": 0.17119869440793992,
|
|
"num_tokens": 20179962.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.650843572616577,
|
|
"epoch": 1.0158364688044028,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.000490792316087133,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.17954716235399246,
|
|
"num_tokens": 20189842.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.62874698638916,
|
|
"epoch": 1.0163980457123603,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004907809447219158,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.18054344952106477,
|
|
"num_tokens": 20200471.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.646729040145874,
|
|
"epoch": 1.016959622620318,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004907695664861498,
|
|
"loss": 5.475,
|
|
"mean_token_accuracy": 0.17355210930109025,
|
|
"num_tokens": 20212145.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.642369413375855,
|
|
"epoch": 1.0175211995282754,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004907581813801971,
|
|
"loss": 5.4818,
|
|
"mean_token_accuracy": 0.1817522495985031,
|
|
"num_tokens": 20222454.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.728996276855469,
|
|
"epoch": 1.018082776436233,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004907467894044202,
|
|
"loss": 5.5988,
|
|
"mean_token_accuracy": 0.1693163126707077,
|
|
"num_tokens": 20233402.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.562401247024536,
|
|
"epoch": 1.0186443533441905,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004907353905591817,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.18326259404420853,
|
|
"num_tokens": 20244102.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.711722755432129,
|
|
"epoch": 1.0192059302521481,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000490723984844845,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.1717848598957062,
|
|
"num_tokens": 20255003.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.66737060546875,
|
|
"epoch": 1.0197675071601056,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004907125722617727,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18053005188703536,
|
|
"num_tokens": 20265211.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.545109796524048,
|
|
"epoch": 1.0203290840680632,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004907011528103285,
|
|
"loss": 5.4171,
|
|
"mean_token_accuracy": 0.1811046779155731,
|
|
"num_tokens": 20276552.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.697446632385254,
|
|
"epoch": 1.0208906609760207,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004906897264908759,
|
|
"loss": 5.5412,
|
|
"mean_token_accuracy": 0.18040314316749573,
|
|
"num_tokens": 20286805.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.68587064743042,
|
|
"epoch": 1.0214522378839783,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004906782933037789,
|
|
"loss": 5.5018,
|
|
"mean_token_accuracy": 0.1781139776110649,
|
|
"num_tokens": 20298536.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.5922259330749515,
|
|
"epoch": 1.0220138147919358,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004906668532494012,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.17583202421665192,
|
|
"num_tokens": 20309842.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.5888443946838375,
|
|
"epoch": 1.0225753916998932,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004906554063281074,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.17998040318489075,
|
|
"num_tokens": 20320413.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.651104354858399,
|
|
"epoch": 1.0231369686078509,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004906439525402618,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.1794575944542885,
|
|
"num_tokens": 20331812.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.585034275054932,
|
|
"epoch": 1.0236985455158083,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004906324918862291,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.18211107403039933,
|
|
"num_tokens": 20342148.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.6750434875488285,
|
|
"epoch": 1.024260122423766,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004906210243663742,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1779532700777054,
|
|
"num_tokens": 20353843.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.680265140533447,
|
|
"epoch": 1.0248216993317234,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004906095499810622,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.17839338332414628,
|
|
"num_tokens": 20364846.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.624419069290161,
|
|
"epoch": 1.025383276239681,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004905980687306586,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.18353347331285477,
|
|
"num_tokens": 20376874.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.5959867477417,
|
|
"epoch": 1.0259448531476385,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004905865806155288,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.1744560644030571,
|
|
"num_tokens": 20388189.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.6281476497650145,
|
|
"epoch": 1.0265064300555962,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004905750856360387,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.17732060998678206,
|
|
"num_tokens": 20399155.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.664930248260498,
|
|
"epoch": 1.0270680069635536,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004905635837925543,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1824602425098419,
|
|
"num_tokens": 20410569.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.556336879730225,
|
|
"epoch": 1.0276295838715113,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004905520750854418,
|
|
"loss": 5.4525,
|
|
"mean_token_accuracy": 0.1814337268471718,
|
|
"num_tokens": 20420438.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.62693510055542,
|
|
"epoch": 1.0281911607794687,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004905405595150674,
|
|
"loss": 5.4925,
|
|
"mean_token_accuracy": 0.17690642029047013,
|
|
"num_tokens": 20431874.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.613407373428345,
|
|
"epoch": 1.0287527376874264,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004905290370817982,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.17767318934202195,
|
|
"num_tokens": 20442792.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.663718366622925,
|
|
"epoch": 1.0293143145953838,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000490517507786001,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.17496270835399627,
|
|
"num_tokens": 20454410.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.758614444732666,
|
|
"epoch": 1.0298758915033415,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004905059716280425,
|
|
"loss": 5.6189,
|
|
"mean_token_accuracy": 0.17097005844116211,
|
|
"num_tokens": 20467072.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.678477811813354,
|
|
"epoch": 1.030437468411299,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004904944286082904,
|
|
"loss": 5.5427,
|
|
"mean_token_accuracy": 0.17613910138607025,
|
|
"num_tokens": 20477697.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.578521060943603,
|
|
"epoch": 1.0309990453192566,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004904828787271121,
|
|
"loss": 5.3872,
|
|
"mean_token_accuracy": 0.18485177308321,
|
|
"num_tokens": 20489024.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.578377962112427,
|
|
"epoch": 1.031560622227214,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004904713219848753,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.17540112286806106,
|
|
"num_tokens": 20499928.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.600791692733765,
|
|
"epoch": 1.0321221991351717,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004904597583819481,
|
|
"loss": 5.5231,
|
|
"mean_token_accuracy": 0.17264363020658494,
|
|
"num_tokens": 20511085.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.6821449279785154,
|
|
"epoch": 1.032683776043129,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004904481879186987,
|
|
"loss": 5.3844,
|
|
"mean_token_accuracy": 0.17880915701389313,
|
|
"num_tokens": 20522164.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.681869411468506,
|
|
"epoch": 1.0332453529510865,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004904366105954954,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.1770383298397064,
|
|
"num_tokens": 20534187.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.6953693389892575,
|
|
"epoch": 1.0338069298590442,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004904250264127067,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.18155114799737931,
|
|
"num_tokens": 20545819.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.693621635437012,
|
|
"epoch": 1.0343685067670016,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004904134353707018,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.17302919328212737,
|
|
"num_tokens": 20556803.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.657413816452026,
|
|
"epoch": 1.0349300836749593,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004904018374698496,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17520078420639038,
|
|
"num_tokens": 20567366.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.629397916793823,
|
|
"epoch": 1.0354916605829168,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004903902327105191,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.17431037425994872,
|
|
"num_tokens": 20579182.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.617108392715454,
|
|
"epoch": 1.0360532374908744,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004903786210930803,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.1793763220310211,
|
|
"num_tokens": 20590346.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.652606201171875,
|
|
"epoch": 1.0366148143988319,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004903670026179025,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.18030413538217543,
|
|
"num_tokens": 20601279.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.616877174377441,
|
|
"epoch": 1.0371763913067895,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000490355377285356,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.18081976026296614,
|
|
"num_tokens": 20612163.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.647373533248901,
|
|
"epoch": 1.037737968214747,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004903437450958106,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.1802780345082283,
|
|
"num_tokens": 20622587.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.645787572860717,
|
|
"epoch": 1.0382995451227046,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004903321060496369,
|
|
"loss": 5.5753,
|
|
"mean_token_accuracy": 0.17147308886051177,
|
|
"num_tokens": 20633341.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.600132751464844,
|
|
"epoch": 1.038861122030662,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004903204601472054,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.18079103529453278,
|
|
"num_tokens": 20644582.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.6399486541748045,
|
|
"epoch": 1.0394226989386197,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004903088073888869,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.18739220649003982,
|
|
"num_tokens": 20654936.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.572191190719605,
|
|
"epoch": 1.0399842758465772,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004902971477750526,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.17384833693504334,
|
|
"num_tokens": 20666348.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.703599882125855,
|
|
"epoch": 1.0405458527545348,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004902854813060736,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.17603288739919662,
|
|
"num_tokens": 20677482.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.678930711746216,
|
|
"epoch": 1.0411074296624923,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004902738079823213,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.1778710514307022,
|
|
"num_tokens": 20688369.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.587229251861572,
|
|
"epoch": 1.04166900657045,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004902621278041674,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.1689196139574051,
|
|
"num_tokens": 20698933.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.631027269363403,
|
|
"epoch": 1.0422305834784074,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004902504407719839,
|
|
"loss": 5.3995,
|
|
"mean_token_accuracy": 0.18056726157665254,
|
|
"num_tokens": 20710192.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.57021198272705,
|
|
"epoch": 1.042792160386365,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004902387468861429,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.17660564929246902,
|
|
"num_tokens": 20721408.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.524291706085205,
|
|
"epoch": 1.0433537372943225,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004902270461470169,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.1836919829249382,
|
|
"num_tokens": 20732155.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.652797746658325,
|
|
"epoch": 1.04391531420228,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000490215338554978,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.18660892993211747,
|
|
"num_tokens": 20741819.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.66568078994751,
|
|
"epoch": 1.0444768911102376,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004902036241103994,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.17766152024269105,
|
|
"num_tokens": 20754931.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.61118369102478,
|
|
"epoch": 1.045038468018195,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004901919028136539,
|
|
"loss": 5.5769,
|
|
"mean_token_accuracy": 0.17305736541748046,
|
|
"num_tokens": 20766533.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.610023736953735,
|
|
"epoch": 1.0456000449261527,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004901801746651147,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.18430131375789643,
|
|
"num_tokens": 20777055.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.569052362442017,
|
|
"epoch": 1.04616162183411,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004901684396651554,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.18292508125305176,
|
|
"num_tokens": 20786871.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.682566928863525,
|
|
"epoch": 1.0467231987420678,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004901566978141494,
|
|
"loss": 5.5338,
|
|
"mean_token_accuracy": 0.1775057777762413,
|
|
"num_tokens": 20798546.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.62388801574707,
|
|
"epoch": 1.0472847756500252,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004901449491124708,
|
|
"loss": 5.4588,
|
|
"mean_token_accuracy": 0.1753029018640518,
|
|
"num_tokens": 20809657.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.553660583496094,
|
|
"epoch": 1.0478463525579829,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004901331935604936,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.17557449638843536,
|
|
"num_tokens": 20819662.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.527672052383423,
|
|
"epoch": 1.0484079294659403,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000490121431158592,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.186506050825119,
|
|
"num_tokens": 20830554.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.6324080467224125,
|
|
"epoch": 1.048969506373898,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004901096619071407,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1718663454055786,
|
|
"num_tokens": 20842003.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.636424446105957,
|
|
"epoch": 1.0495310832818554,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004900978858065142,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.1849648877978325,
|
|
"num_tokens": 20853453.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.743824434280396,
|
|
"epoch": 1.050092660189813,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004900861028570877,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.1756438285112381,
|
|
"num_tokens": 20867296.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.606584072113037,
|
|
"epoch": 1.0506542370977705,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004900743130592362,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.18236349225044252,
|
|
"num_tokens": 20878951.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.683361768722534,
|
|
"epoch": 1.0512158140057282,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004900625164133351,
|
|
"loss": 5.5406,
|
|
"mean_token_accuracy": 0.17790716290473937,
|
|
"num_tokens": 20891103.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.702412128448486,
|
|
"epoch": 1.0517773909136856,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004900507129197601,
|
|
"loss": 5.6287,
|
|
"mean_token_accuracy": 0.17244322448968888,
|
|
"num_tokens": 20903570.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.715984773635864,
|
|
"epoch": 1.0523389678216433,
|
|
"grad_norm": 2.34375,
|
|
"learning_rate": 0.0004900389025788871,
|
|
"loss": 5.5681,
|
|
"mean_token_accuracy": 0.17239335775375367,
|
|
"num_tokens": 20914156.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.627608680725098,
|
|
"epoch": 1.0529005447296007,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000490027085391092,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.1799492508172989,
|
|
"num_tokens": 20925192.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.638004016876221,
|
|
"epoch": 1.0534621216375584,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000490015261356751,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.19279878884553908,
|
|
"num_tokens": 20935281.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.726856470108032,
|
|
"epoch": 1.0540236985455158,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004900034304762408,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.1792500138282776,
|
|
"num_tokens": 20947397.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.529204988479615,
|
|
"epoch": 1.0545852754534732,
|
|
"grad_norm": 2.609375,
|
|
"learning_rate": 0.000489991592749938,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.18403242528438568,
|
|
"num_tokens": 20958473.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.69219651222229,
|
|
"epoch": 1.055146852361431,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004899797481782193,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.16997140645980835,
|
|
"num_tokens": 20970112.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.605134344100952,
|
|
"epoch": 1.0557084292693883,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004899678967614623,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.176979897916317,
|
|
"num_tokens": 20980762.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.5694581985473635,
|
|
"epoch": 1.056270006177346,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004899560385000439,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.18455475121736525,
|
|
"num_tokens": 20991663.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.561851215362549,
|
|
"epoch": 1.0568315830853034,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000489944173394342,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.183576737344265,
|
|
"num_tokens": 21002121.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.586403322219849,
|
|
"epoch": 1.0573931599932611,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004899323014447342,
|
|
"loss": 5.4569,
|
|
"mean_token_accuracy": 0.1725597470998764,
|
|
"num_tokens": 21013791.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.557858800888061,
|
|
"epoch": 1.0579547369012186,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004899204226515985,
|
|
"loss": 5.4053,
|
|
"mean_token_accuracy": 0.17941731214523315,
|
|
"num_tokens": 21022977.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.638604307174683,
|
|
"epoch": 1.0585163138091762,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004899085370153133,
|
|
"loss": 5.5552,
|
|
"mean_token_accuracy": 0.17534208446741104,
|
|
"num_tokens": 21036372.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.7567222118377686,
|
|
"epoch": 1.0590778907171337,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004898966445362569,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.16735798716545106,
|
|
"num_tokens": 21047984.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.718659114837647,
|
|
"epoch": 1.0596394676250913,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004898847452148079,
|
|
"loss": 5.5054,
|
|
"mean_token_accuracy": 0.17448755353689194,
|
|
"num_tokens": 21060127.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.640578556060791,
|
|
"epoch": 1.0602010445330488,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004898728390513454,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.17993971556425095,
|
|
"num_tokens": 21070659.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.583226060867309,
|
|
"epoch": 1.0607626214410064,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004898609260462483,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.18368871212005616,
|
|
"num_tokens": 21081667.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.583122873306275,
|
|
"epoch": 1.0613241983489639,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004898490061998961,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.182714281976223,
|
|
"num_tokens": 21094275.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.647475051879883,
|
|
"epoch": 1.0618857752569215,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004898370795126681,
|
|
"loss": 5.5089,
|
|
"mean_token_accuracy": 0.17455472350120543,
|
|
"num_tokens": 21106360.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.640259695053101,
|
|
"epoch": 1.062447352164879,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004898251459849441,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.17549148052930832,
|
|
"num_tokens": 21117647.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.526062297821045,
|
|
"epoch": 1.0630089290728366,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004898132056171041,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.18563006371259688,
|
|
"num_tokens": 21129599.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.615424251556396,
|
|
"epoch": 1.063570505980794,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004898012584095285,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.1787340186536312,
|
|
"num_tokens": 21140573.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.663884067535401,
|
|
"epoch": 1.0641320828887517,
|
|
"grad_norm": 3.609375,
|
|
"learning_rate": 0.0004897893043625975,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.17812761068344116,
|
|
"num_tokens": 21151899.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.678170156478882,
|
|
"epoch": 1.0646936597967092,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004897773434766917,
|
|
"loss": 5.6018,
|
|
"mean_token_accuracy": 0.16957082152366637,
|
|
"num_tokens": 21162748.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.672392177581787,
|
|
"epoch": 1.0652552367046666,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000489765375752192,
|
|
"loss": 5.4841,
|
|
"mean_token_accuracy": 0.174918232858181,
|
|
"num_tokens": 21172962.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.64464750289917,
|
|
"epoch": 1.0658168136126243,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004897534011894793,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.18241391330957413,
|
|
"num_tokens": 21183805.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.520845937728882,
|
|
"epoch": 1.0663783905205817,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004897414197889352,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.1830639883875847,
|
|
"num_tokens": 21195129.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.563352870941162,
|
|
"epoch": 1.0669399674285394,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.000489729431550941,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.17020124942064285,
|
|
"num_tokens": 21206300.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.676118469238281,
|
|
"epoch": 1.0675015443364968,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004897174364758783,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.1766913816332817,
|
|
"num_tokens": 21217137.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.606015634536743,
|
|
"epoch": 1.0680631212444545,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004897054345641291,
|
|
"loss": 5.4289,
|
|
"mean_token_accuracy": 0.1819976568222046,
|
|
"num_tokens": 21228399.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.610036134719849,
|
|
"epoch": 1.068624698152412,
|
|
"grad_norm": 1.984375,
|
|
"learning_rate": 0.0004896934258160757,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.17573488652706146,
|
|
"num_tokens": 21239396.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.611205911636352,
|
|
"epoch": 1.0691862750603696,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.0004896814102321004,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.1766739994287491,
|
|
"num_tokens": 21249966.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.604861736297607,
|
|
"epoch": 1.069747851968327,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004896693878125857,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.1815433382987976,
|
|
"num_tokens": 21260157.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.60617413520813,
|
|
"epoch": 1.0703094288762847,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004896573585579144,
|
|
"loss": 5.5211,
|
|
"mean_token_accuracy": 0.18009959012269974,
|
|
"num_tokens": 21270738.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.614497184753418,
|
|
"epoch": 1.070871005784242,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004896453224684695,
|
|
"loss": 5.4537,
|
|
"mean_token_accuracy": 0.1829637199640274,
|
|
"num_tokens": 21282469.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.604954481124878,
|
|
"epoch": 1.0714325826921998,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004896332795446345,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.1758398801088333,
|
|
"num_tokens": 21293474.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.631824398040772,
|
|
"epoch": 1.0719941596001572,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004896212297867924,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.1704126328229904,
|
|
"num_tokens": 21304904.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.675357913970947,
|
|
"epoch": 1.0725557365081149,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004896091731953271,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.18020249903202057,
|
|
"num_tokens": 21315407.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.585581684112549,
|
|
"epoch": 1.0731173134160723,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004895971097706227,
|
|
"loss": 5.4205,
|
|
"mean_token_accuracy": 0.18315251171588898,
|
|
"num_tokens": 21326496.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.574116182327271,
|
|
"epoch": 1.07367889032403,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004895850395130629,
|
|
"loss": 5.5094,
|
|
"mean_token_accuracy": 0.1746429145336151,
|
|
"num_tokens": 21339449.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.6082679271698,
|
|
"epoch": 1.0742404672319874,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004895729624230323,
|
|
"loss": 5.5584,
|
|
"mean_token_accuracy": 0.17270775586366655,
|
|
"num_tokens": 21350431.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.66397876739502,
|
|
"epoch": 1.074802044139945,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004895608785009153,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.1801927149295807,
|
|
"num_tokens": 21361168.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.639418220520019,
|
|
"epoch": 1.0753636210479025,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004895487877470969,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.18104951977729797,
|
|
"num_tokens": 21372635.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.543292808532715,
|
|
"epoch": 1.07592519795586,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004895366901619617,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.178116013109684,
|
|
"num_tokens": 21384051.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.64618821144104,
|
|
"epoch": 1.0764867748638176,
|
|
"grad_norm": 2.234375,
|
|
"learning_rate": 0.0004895245857458951,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.1749254956841469,
|
|
"num_tokens": 21397496.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.593995046615601,
|
|
"epoch": 1.077048351771775,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004895124744992825,
|
|
"loss": 5.5396,
|
|
"mean_token_accuracy": 0.17334416806697844,
|
|
"num_tokens": 21409349.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.634131193161011,
|
|
"epoch": 1.0776099286797327,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004895003564225095,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.18222051709890366,
|
|
"num_tokens": 21421843.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.57165937423706,
|
|
"epoch": 1.0781715055876901,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004894882315159621,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.1826613038778305,
|
|
"num_tokens": 21433230.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.642829179763794,
|
|
"epoch": 1.0787330824956478,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000489476099780026,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.17681605368852615,
|
|
"num_tokens": 21444295.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.6687110424041744,
|
|
"epoch": 1.0792946594036052,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004894639612150879,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.1754288926720619,
|
|
"num_tokens": 21455721.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.63464035987854,
|
|
"epoch": 1.079856236311563,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004894518158215339,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.1806491196155548,
|
|
"num_tokens": 21466514.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.5776721954345705,
|
|
"epoch": 1.0804178132195204,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.000489439663599751,
|
|
"loss": 5.4836,
|
|
"mean_token_accuracy": 0.17720255851745606,
|
|
"num_tokens": 21478782.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.66216549873352,
|
|
"epoch": 1.080979390127478,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000489427504550126,
|
|
"loss": 5.4806,
|
|
"mean_token_accuracy": 0.1865155041217804,
|
|
"num_tokens": 21490428.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.52768030166626,
|
|
"epoch": 1.0815409670354355,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004894153386730462,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.1778653621673584,
|
|
"num_tokens": 21501530.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.588586807250977,
|
|
"epoch": 1.0821025439433931,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004894031659688988,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.18477288782596588,
|
|
"num_tokens": 21512122.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.530970621109009,
|
|
"epoch": 1.0826641208513506,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004893909864380714,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.17734417617321013,
|
|
"num_tokens": 21521896.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.595498943328858,
|
|
"epoch": 1.0832256977593082,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000489378800080952,
|
|
"loss": 5.5198,
|
|
"mean_token_accuracy": 0.1742045059800148,
|
|
"num_tokens": 21533584.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.591215991973877,
|
|
"epoch": 1.0837872746672657,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893666068979283,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.17979392260313035,
|
|
"num_tokens": 21545432.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.652005338668824,
|
|
"epoch": 1.0843488515752233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004893544068893887,
|
|
"loss": 5.4842,
|
|
"mean_token_accuracy": 0.17896706461906434,
|
|
"num_tokens": 21556547.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.630813360214233,
|
|
"epoch": 1.0849104284831808,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004893422000557217,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.17727217078208923,
|
|
"num_tokens": 21567354.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.6717311382293705,
|
|
"epoch": 1.0854720053911384,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004893299863973159,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.17590038627386093,
|
|
"num_tokens": 21578694.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.525763511657715,
|
|
"epoch": 1.0860335822990959,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004893177659145601,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.18927086591720582,
|
|
"num_tokens": 21589365.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.611567449569702,
|
|
"epoch": 1.0865951592070533,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004893055386078438,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.17692719101905824,
|
|
"num_tokens": 21600766.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.676785326004028,
|
|
"epoch": 1.087156736115011,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004892933044775558,
|
|
"loss": 5.6411,
|
|
"mean_token_accuracy": 0.17028353065252305,
|
|
"num_tokens": 21613969.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.584120893478394,
|
|
"epoch": 1.0877183130229684,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004892810635240859,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.1779574230313301,
|
|
"num_tokens": 21626302.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.601050662994385,
|
|
"epoch": 1.088279889930926,
|
|
"grad_norm": 3.421875,
|
|
"learning_rate": 0.0004892688157478238,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.1799305185675621,
|
|
"num_tokens": 21637058.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.649675607681274,
|
|
"epoch": 1.0888414668388835,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004892565611491597,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.17121419310569763,
|
|
"num_tokens": 21648729.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.548161745071411,
|
|
"epoch": 1.0894030437468412,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004892442997284834,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.18702690452337264,
|
|
"num_tokens": 21659961.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.570842647552491,
|
|
"epoch": 1.0899646206547986,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004892320314861855,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.18691338896751403,
|
|
"num_tokens": 21670577.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.60824065208435,
|
|
"epoch": 1.0905261975627563,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004892197564226568,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.18847449868917465,
|
|
"num_tokens": 21679882.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.643086957931518,
|
|
"epoch": 1.0910877744707137,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004892074745382878,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.18136143833398818,
|
|
"num_tokens": 21690595.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.5712522029876705,
|
|
"epoch": 1.0916493513786714,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004891951858334698,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.18010281175374984,
|
|
"num_tokens": 21701251.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.645194625854492,
|
|
"epoch": 1.0922109282866288,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004891828903085939,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.17897659689188003,
|
|
"num_tokens": 21713286.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.657762432098389,
|
|
"epoch": 1.0927725051945865,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004891705879640518,
|
|
"loss": 5.6226,
|
|
"mean_token_accuracy": 0.17332690805196763,
|
|
"num_tokens": 21725508.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.608103656768799,
|
|
"epoch": 1.093334082102544,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004891582788002351,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17881702035665512,
|
|
"num_tokens": 21736467.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.69095664024353,
|
|
"epoch": 1.0938956590105016,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004891459628175358,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.1845870152115822,
|
|
"num_tokens": 21746114.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.546126985549927,
|
|
"epoch": 1.094457235918459,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000489133640016346,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.17861364483833314,
|
|
"num_tokens": 21757145.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.6242228031158445,
|
|
"epoch": 1.0950188128264167,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004891213103970579,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.17192888855934144,
|
|
"num_tokens": 21768294.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.64376745223999,
|
|
"epoch": 1.095580389734374,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004891089739600643,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.1768464758992195,
|
|
"num_tokens": 21779667.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.545671033859253,
|
|
"epoch": 1.0961419666423318,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004890966307057581,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.1851275384426117,
|
|
"num_tokens": 21789635.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.54192419052124,
|
|
"epoch": 1.0967035435502892,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.000489084280634532,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1891099900007248,
|
|
"num_tokens": 21799462.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.546526098251343,
|
|
"epoch": 1.0972651204582466,
|
|
"grad_norm": 1.9921875,
|
|
"learning_rate": 0.0004890719237467794,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.1840835064649582,
|
|
"num_tokens": 21811520.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.719901657104492,
|
|
"epoch": 1.0978266973662043,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004890595600428937,
|
|
"loss": 5.4922,
|
|
"mean_token_accuracy": 0.1782437965273857,
|
|
"num_tokens": 21821997.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.639668321609497,
|
|
"epoch": 1.0983882742741617,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004890471895232684,
|
|
"loss": 5.535,
|
|
"mean_token_accuracy": 0.17326714247465133,
|
|
"num_tokens": 21833353.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.5320212841033936,
|
|
"epoch": 1.0989498511821194,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004890348121882978,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.18393592685461044,
|
|
"num_tokens": 21843691.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.517736625671387,
|
|
"epoch": 1.0995114280900768,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004890224280383758,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.18015834987163543,
|
|
"num_tokens": 21853771.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.5037566184997555,
|
|
"epoch": 1.1000730049980345,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004890100370738966,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.18704588413238527,
|
|
"num_tokens": 21863424.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.606740283966064,
|
|
"epoch": 1.100634581905992,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004889976392952548,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.18175214678049087,
|
|
"num_tokens": 21875407.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.625884532928467,
|
|
"epoch": 1.1011961588139496,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004889852347028452,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.17489999979734422,
|
|
"num_tokens": 21887081.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.5561384677886965,
|
|
"epoch": 1.101757735721907,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004889728232970626,
|
|
"loss": 5.4203,
|
|
"mean_token_accuracy": 0.17963528782129287,
|
|
"num_tokens": 21897858.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.539708185195923,
|
|
"epoch": 1.1023193126298647,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004889604050783025,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.17901625037193297,
|
|
"num_tokens": 21907985.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.578413295745849,
|
|
"epoch": 1.1028808895378222,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048894798004696,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.17565921545028687,
|
|
"num_tokens": 21918726.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.5618284225463865,
|
|
"epoch": 1.1034424664457798,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004889355482034309,
|
|
"loss": 5.4395,
|
|
"mean_token_accuracy": 0.1786981239914894,
|
|
"num_tokens": 21929027.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.571590423583984,
|
|
"epoch": 1.1040040433537373,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004889231095481111,
|
|
"loss": 5.3438,
|
|
"mean_token_accuracy": 0.19128917157649994,
|
|
"num_tokens": 21938356.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.561736965179444,
|
|
"epoch": 1.104565620261695,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004889106640813964,
|
|
"loss": 5.3814,
|
|
"mean_token_accuracy": 0.1824903279542923,
|
|
"num_tokens": 21947889.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.633959245681763,
|
|
"epoch": 1.1051271971696524,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004888982118036831,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.18075614422559738,
|
|
"num_tokens": 21958409.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.597603797912598,
|
|
"epoch": 1.10568877407761,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004888857527153679,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.17604378312826158,
|
|
"num_tokens": 21970120.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.586305141448975,
|
|
"epoch": 1.1062503509855675,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004888732868168473,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.18160055279731752,
|
|
"num_tokens": 21981499.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.49609260559082,
|
|
"epoch": 1.1068119278935251,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004888608141085183,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.19190258979797364,
|
|
"num_tokens": 21991263.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.550536584854126,
|
|
"epoch": 1.1073735048014826,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004888483345907781,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.18011860996484758,
|
|
"num_tokens": 22001582.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.570600366592407,
|
|
"epoch": 1.10793508170944,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000488835848264024,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1896669164299965,
|
|
"num_tokens": 22012447.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.584665775299072,
|
|
"epoch": 1.1084966586173977,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004888233551286534,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.1763281151652336,
|
|
"num_tokens": 22024865.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.540510988235473,
|
|
"epoch": 1.109058235525355,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004888108551850644,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.17687635719776154,
|
|
"num_tokens": 22036298.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.6540594577789305,
|
|
"epoch": 1.1096198124333128,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004887983484336548,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18306748420000077,
|
|
"num_tokens": 22047499.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.60211706161499,
|
|
"epoch": 1.1101813893412702,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004887858348748229,
|
|
"loss": 5.4656,
|
|
"mean_token_accuracy": 0.18048064708709716,
|
|
"num_tokens": 22057612.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.606729316711426,
|
|
"epoch": 1.1107429662492279,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000488773314508967,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.1797344297170639,
|
|
"num_tokens": 22068566.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.5970851421356205,
|
|
"epoch": 1.1113045431571853,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004887607873364859,
|
|
"loss": 5.3907,
|
|
"mean_token_accuracy": 0.1815165773034096,
|
|
"num_tokens": 22079821.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.579369592666626,
|
|
"epoch": 1.111866120065143,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004887482533577786,
|
|
"loss": 5.4419,
|
|
"mean_token_accuracy": 0.17782216072082518,
|
|
"num_tokens": 22090143.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.589296436309814,
|
|
"epoch": 1.1124276969731004,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004887357125732438,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.1826336681842804,
|
|
"num_tokens": 22101601.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.561112356185913,
|
|
"epoch": 1.112989273881058,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000488723164983281,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.18409797698259353,
|
|
"num_tokens": 22113102.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.673022747039795,
|
|
"epoch": 1.1135508507890155,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004887106105882898,
|
|
"loss": 5.5494,
|
|
"mean_token_accuracy": 0.17877606749534608,
|
|
"num_tokens": 22124650.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.668352746963501,
|
|
"epoch": 1.1141124276969732,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004886980493886699,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.18425817638635636,
|
|
"num_tokens": 22136637.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.595417881011963,
|
|
"epoch": 1.1146740046049306,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004886854813848212,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.18328417837619781,
|
|
"num_tokens": 22149318.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.503446912765503,
|
|
"epoch": 1.1152355815128883,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004886729065771439,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.18344067335128783,
|
|
"num_tokens": 22159410.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.528563976287842,
|
|
"epoch": 1.1157971584208457,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004886603249660384,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.18433099538087844,
|
|
"num_tokens": 22170017.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.526228427886963,
|
|
"epoch": 1.1163587353288034,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004886477365519052,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.18204993456602098,
|
|
"num_tokens": 22179961.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.655697298049927,
|
|
"epoch": 1.1169203122367608,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004886351413351453,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.172687067091465,
|
|
"num_tokens": 22191415.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.698980331420898,
|
|
"epoch": 1.1174818891447185,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004886225393161596,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.18980360627174378,
|
|
"num_tokens": 22205354.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.678971433639527,
|
|
"epoch": 1.118043466052676,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004886099304953495,
|
|
"loss": 5.5229,
|
|
"mean_token_accuracy": 0.17776025235652923,
|
|
"num_tokens": 22216989.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.658865547180175,
|
|
"epoch": 1.1186050429606333,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004885973148731162,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.1729778304696083,
|
|
"num_tokens": 22228421.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.567265558242798,
|
|
"epoch": 1.119166619868591,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004885846924498617,
|
|
"loss": 5.3782,
|
|
"mean_token_accuracy": 0.1802075445652008,
|
|
"num_tokens": 22240621.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.513255596160889,
|
|
"epoch": 1.1197281967765484,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004885720632259876,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.1871098354458809,
|
|
"num_tokens": 22250936.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.569849061965942,
|
|
"epoch": 1.120289773684506,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.0004885594272018963,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.17855152785778045,
|
|
"num_tokens": 22261766.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.614282560348511,
|
|
"epoch": 1.1208513505924635,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048854678437799,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.18513642996549606,
|
|
"num_tokens": 22271831.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.52294659614563,
|
|
"epoch": 1.1214129275004212,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004885341347546713,
|
|
"loss": 5.4556,
|
|
"mean_token_accuracy": 0.178518845140934,
|
|
"num_tokens": 22283756.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.481682634353637,
|
|
"epoch": 1.1219745044083786,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004885214783323428,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.1828600913286209,
|
|
"num_tokens": 22294576.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.530295324325562,
|
|
"epoch": 1.1225360813163363,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004885088151114076,
|
|
"loss": 5.4634,
|
|
"mean_token_accuracy": 0.1800905853509903,
|
|
"num_tokens": 22305003.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.574592733383179,
|
|
"epoch": 1.1230976582242937,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004884961450922691,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.18305280208587646,
|
|
"num_tokens": 22316505.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.632885074615478,
|
|
"epoch": 1.1236592351322514,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004884834682753305,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.18159876614809037,
|
|
"num_tokens": 22327853.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.6088550090789795,
|
|
"epoch": 1.1242208120402089,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004884707846609953,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.17990944385528565,
|
|
"num_tokens": 22337386.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.585424852371216,
|
|
"epoch": 1.1247823889481665,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004884580942496677,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.17330081313848494,
|
|
"num_tokens": 22348742.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.712924528121948,
|
|
"epoch": 1.125343965856124,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004884453970417515,
|
|
"loss": 5.5051,
|
|
"mean_token_accuracy": 0.1765771582722664,
|
|
"num_tokens": 22360083.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.628228855133057,
|
|
"epoch": 1.1259055427640816,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.000488432693037651,
|
|
"loss": 5.4477,
|
|
"mean_token_accuracy": 0.17336840629577638,
|
|
"num_tokens": 22370982.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.557705450057983,
|
|
"epoch": 1.126467119672039,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000488419982237771,
|
|
"loss": 5.409,
|
|
"mean_token_accuracy": 0.18768612444400787,
|
|
"num_tokens": 22382383.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.553377866744995,
|
|
"epoch": 1.1270286965799967,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004884072646425157,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.1791058823466301,
|
|
"num_tokens": 22393994.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.531031465530395,
|
|
"epoch": 1.1275902734879542,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004883945402522907,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.18705665469169616,
|
|
"num_tokens": 22405354.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.53762378692627,
|
|
"epoch": 1.1281518503959118,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004883818090675005,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.17994299978017808,
|
|
"num_tokens": 22416708.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.49211368560791,
|
|
"epoch": 1.1287134273038693,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004883690710885507,
|
|
"loss": 5.3772,
|
|
"mean_token_accuracy": 0.18579760044813157,
|
|
"num_tokens": 22427724.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.612806797027588,
|
|
"epoch": 1.1292750042118267,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004883563263158471,
|
|
"loss": 5.4662,
|
|
"mean_token_accuracy": 0.1794513553380966,
|
|
"num_tokens": 22437823.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.625531768798828,
|
|
"epoch": 1.1298365811197844,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004883435747497952,
|
|
"loss": 5.5146,
|
|
"mean_token_accuracy": 0.17785282284021378,
|
|
"num_tokens": 22450155.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.643441009521484,
|
|
"epoch": 1.130398158027742,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004883308163908012,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.18328592777252198,
|
|
"num_tokens": 22460484.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.5535094261169435,
|
|
"epoch": 1.1309597349356995,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.0004883180512392714,
|
|
"loss": 5.4638,
|
|
"mean_token_accuracy": 0.17974253445863725,
|
|
"num_tokens": 22472063.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.510358095169067,
|
|
"epoch": 1.131521311843657,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004883052792956119,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.18902051001787185,
|
|
"num_tokens": 22483669.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.626377582550049,
|
|
"epoch": 1.1320828887516146,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004882925005602296,
|
|
"loss": 5.5106,
|
|
"mean_token_accuracy": 0.17363036721944808,
|
|
"num_tokens": 22495505.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.593221712112427,
|
|
"epoch": 1.132644465659572,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004882797150335314,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1805385559797287,
|
|
"num_tokens": 22505260.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.618656492233276,
|
|
"epoch": 1.1332060425675297,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048826692271592434,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.17494348287582398,
|
|
"num_tokens": 22516362.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.692310619354248,
|
|
"epoch": 1.133767619475487,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 0.0004882541236078158,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.17862657457590103,
|
|
"num_tokens": 22527760.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.829783535003662,
|
|
"epoch": 1.1343291963834448,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00048824131770961316,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.17289739102125168,
|
|
"num_tokens": 22540601.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.605794954299927,
|
|
"epoch": 1.1348907732914022,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048822850502172437,
|
|
"loss": 5.474,
|
|
"mean_token_accuracy": 0.177017043530941,
|
|
"num_tokens": 22552469.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.456769847869873,
|
|
"epoch": 1.1354523501993599,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004882156855445571,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.1829116314649582,
|
|
"num_tokens": 22563552.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.576366853713989,
|
|
"epoch": 1.1360139271073173,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004882028592785199,
|
|
"loss": 5.4031,
|
|
"mean_token_accuracy": 0.17882005274295806,
|
|
"num_tokens": 22575619.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.56858720779419,
|
|
"epoch": 1.136575504015275,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048819002622402095,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.18442476838827132,
|
|
"num_tokens": 22585854.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.619029808044433,
|
|
"epoch": 1.1371370809232324,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004881771863814688,
|
|
"loss": 5.4041,
|
|
"mean_token_accuracy": 0.1881781354546547,
|
|
"num_tokens": 22595899.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.5712381362915036,
|
|
"epoch": 1.13769865783119,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00048816433975127244,
|
|
"loss": 5.3894,
|
|
"mean_token_accuracy": 0.18613488972187042,
|
|
"num_tokens": 22607517.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.616883230209351,
|
|
"epoch": 1.1382602347391475,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004881514863338407,
|
|
"loss": 5.4958,
|
|
"mean_token_accuracy": 0.1800430253148079,
|
|
"num_tokens": 22618531.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.500371074676513,
|
|
"epoch": 1.1388218116471052,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048813862612958307,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.1838152140378952,
|
|
"num_tokens": 22629193.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.615572118759156,
|
|
"epoch": 1.1393833885550626,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004881257591389089,
|
|
"loss": 5.4676,
|
|
"mean_token_accuracy": 0.18250392079353334,
|
|
"num_tokens": 22639794.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.605712604522705,
|
|
"epoch": 1.13994496546302,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048811288536222794,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.1901552528142929,
|
|
"num_tokens": 22650061.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.565939426422119,
|
|
"epoch": 1.1405065423709777,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048810000479995,
|
|
"loss": 5.4971,
|
|
"mean_token_accuracy": 0.1784619688987732,
|
|
"num_tokens": 22661399.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.708422899246216,
|
|
"epoch": 1.1410681192789354,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048808711745248524,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.17593513131141664,
|
|
"num_tokens": 22672445.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.660270690917969,
|
|
"epoch": 1.1416296961868928,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048807422332024404,
|
|
"loss": 5.3906,
|
|
"mean_token_accuracy": 0.18507332652807235,
|
|
"num_tokens": 22682545.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.589328861236572,
|
|
"epoch": 1.1421912730948502,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004880613224036369,
|
|
"loss": 5.4497,
|
|
"mean_token_accuracy": 0.17755909860134125,
|
|
"num_tokens": 22693885.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.517170667648315,
|
|
"epoch": 1.142752850002808,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048804841470307466,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.1824245736002922,
|
|
"num_tokens": 22703841.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.676496458053589,
|
|
"epoch": 1.1433144269107653,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048803550021896824,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.18140770345926285,
|
|
"num_tokens": 22714142.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.600740146636963,
|
|
"epoch": 1.143876003818723,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004880225789517289,
|
|
"loss": 5.4188,
|
|
"mean_token_accuracy": 0.17553980201482772,
|
|
"num_tokens": 22725056.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.492700099945068,
|
|
"epoch": 1.1444375807266804,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000488009650901768,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.18247698545455932,
|
|
"num_tokens": 22735664.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.5516565322875975,
|
|
"epoch": 1.144999157634638,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048799671606949724,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.18179060965776445,
|
|
"num_tokens": 22748071.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.652445507049561,
|
|
"epoch": 1.1455607345425955,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00048798377445532837,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.17985798716545104,
|
|
"num_tokens": 22759477.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.520776271820068,
|
|
"epoch": 1.1461223114505532,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004879708260596736,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.1892823740839958,
|
|
"num_tokens": 22769955.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.504472398757935,
|
|
"epoch": 1.1466838883585107,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004879578708829451,
|
|
"loss": 5.4454,
|
|
"mean_token_accuracy": 0.17878516614437104,
|
|
"num_tokens": 22781216.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.529893207550049,
|
|
"epoch": 1.1472454652664683,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004879449089255553,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.18322905004024506,
|
|
"num_tokens": 22792581.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.503857231140136,
|
|
"epoch": 1.1478070421744258,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004879319401879171,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.18465619683265685,
|
|
"num_tokens": 22803305.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.638623046875,
|
|
"epoch": 1.1483686190823834,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 0.00048791896467044335,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.18128663897514344,
|
|
"num_tokens": 22815558.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.583691930770874,
|
|
"epoch": 1.1489301959903409,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048790598237354716,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.18757555931806563,
|
|
"num_tokens": 22825428.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.6097852230072025,
|
|
"epoch": 1.1494917728982985,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004878929932976419,
|
|
"loss": 5.4409,
|
|
"mean_token_accuracy": 0.17990537881851196,
|
|
"num_tokens": 22836294.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.6217035293579105,
|
|
"epoch": 1.150053349806256,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004878799974431412,
|
|
"loss": 5.5387,
|
|
"mean_token_accuracy": 0.1817946895956993,
|
|
"num_tokens": 22847835.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.652410936355591,
|
|
"epoch": 1.1506149267142134,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004878669948104588,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.17479046881198884,
|
|
"num_tokens": 22859726.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.533027219772339,
|
|
"epoch": 1.151176503622171,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048785398540000867,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.18222623318433762,
|
|
"num_tokens": 22871250.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.618240547180176,
|
|
"epoch": 1.1517380805301287,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048784096921220514,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.17742048799991608,
|
|
"num_tokens": 22882034.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.709335136413574,
|
|
"epoch": 1.1522996574380862,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004878279462474627,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.17774581015110016,
|
|
"num_tokens": 22894606.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.555956649780273,
|
|
"epoch": 1.1528612343460436,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.00048781491650619574,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.18275917023420335,
|
|
"num_tokens": 22905246.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.599154758453369,
|
|
"epoch": 1.1534228112540013,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048780187998881944,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.18211308419704436,
|
|
"num_tokens": 22916202.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.589418745040893,
|
|
"epoch": 1.1539843881619587,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004877888366957486,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.1833593249320984,
|
|
"num_tokens": 22926451.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.594960784912109,
|
|
"epoch": 1.1545459650699164,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004877757866273988,
|
|
"loss": 5.4396,
|
|
"mean_token_accuracy": 0.18194506466388702,
|
|
"num_tokens": 22936618.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.609849309921264,
|
|
"epoch": 1.1551075419778738,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004877627297841853,
|
|
"loss": 5.4764,
|
|
"mean_token_accuracy": 0.17302081137895584,
|
|
"num_tokens": 22948278.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.529412889480591,
|
|
"epoch": 1.1556691188858315,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004877496661665241,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.18273839205503464,
|
|
"num_tokens": 22959928.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.513144540786743,
|
|
"epoch": 1.156230695793789,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000487736595774831,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.18085602968931197,
|
|
"num_tokens": 22971050.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.5293793201446535,
|
|
"epoch": 1.1567922727017466,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048772351860952215,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.18178831338882445,
|
|
"num_tokens": 22981471.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.684435224533081,
|
|
"epoch": 1.157353849609704,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004877104346710139,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.17956517934799193,
|
|
"num_tokens": 22992526.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.5787193298339846,
|
|
"epoch": 1.1579154265176617,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000487697343959723,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.18364362865686418,
|
|
"num_tokens": 23003408.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.55914306640625,
|
|
"epoch": 1.158477003425619,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004876842464760661,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.18216581046581268,
|
|
"num_tokens": 23013406.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.570200777053833,
|
|
"epoch": 1.1590385803335768,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048767114222046036,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.18314363807439804,
|
|
"num_tokens": 23024960.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.684716510772705,
|
|
"epoch": 1.1596001572415342,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000487658031193323,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.17828988432884216,
|
|
"num_tokens": 23037514.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.610880517959595,
|
|
"epoch": 1.1601617341494919,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004876449133950714,
|
|
"loss": 5.5504,
|
|
"mean_token_accuracy": 0.17151972204446791,
|
|
"num_tokens": 23048460.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.649914121627807,
|
|
"epoch": 1.1607233110574493,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004876317888261233,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.17986980825662613,
|
|
"num_tokens": 23058866.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.514005708694458,
|
|
"epoch": 1.1612848879654067,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048761865748689657,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.17695862352848052,
|
|
"num_tokens": 23069097.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.648540258407593,
|
|
"epoch": 1.1618464648733644,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048760551937780927,
|
|
"loss": 5.4436,
|
|
"mean_token_accuracy": 0.17663593590259552,
|
|
"num_tokens": 23079553.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.557674741744995,
|
|
"epoch": 1.162408041781322,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048759237449927986,
|
|
"loss": 5.4356,
|
|
"mean_token_accuracy": 0.18033038675785065,
|
|
"num_tokens": 23090554.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.476955986022949,
|
|
"epoch": 1.1629696186892795,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048757922285172674,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.18847220838069917,
|
|
"num_tokens": 23101740.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.65234956741333,
|
|
"epoch": 1.163531195597237,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048756606443556874,
|
|
"loss": 5.4272,
|
|
"mean_token_accuracy": 0.18381717950105667,
|
|
"num_tokens": 23112842.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.529042720794678,
|
|
"epoch": 1.1640927725051946,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048755289925122474,
|
|
"loss": 5.437,
|
|
"mean_token_accuracy": 0.17884793132543564,
|
|
"num_tokens": 23123822.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.601006364822387,
|
|
"epoch": 1.164654349413152,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004875397272991141,
|
|
"loss": 5.4437,
|
|
"mean_token_accuracy": 0.17712559551000595,
|
|
"num_tokens": 23134045.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.567840242385865,
|
|
"epoch": 1.1652159263211097,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000487526548579656,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17337518483400344,
|
|
"num_tokens": 23144200.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.596815538406372,
|
|
"epoch": 1.1657775032290671,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048751336309327026,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.1837295800447464,
|
|
"num_tokens": 23155671.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.675365209579468,
|
|
"epoch": 1.1663390801370248,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004875001708403766,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.17615631520748137,
|
|
"num_tokens": 23166644.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.580383539199829,
|
|
"epoch": 1.1669006570449822,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048748697182139503,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.1827227756381035,
|
|
"num_tokens": 23177074.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.638866949081421,
|
|
"epoch": 1.16746223395294,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004874737660367459,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.16965461671352386,
|
|
"num_tokens": 23188724.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.565866136550904,
|
|
"epoch": 1.1680238108608973,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00048746055348684967,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.18135719895362853,
|
|
"num_tokens": 23198459.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.662868070602417,
|
|
"epoch": 1.168585387768855,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000487447334172127,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.17532780766487122,
|
|
"num_tokens": 23208991.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.554470634460449,
|
|
"epoch": 1.1691469646768125,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048743410809299877,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.18204366117715837,
|
|
"num_tokens": 23219309.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.591141414642334,
|
|
"epoch": 1.1697085415847701,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004874208752498862,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.17678394466638564,
|
|
"num_tokens": 23230551.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.675060176849366,
|
|
"epoch": 1.1702701184927276,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004874076356432106,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.17707670331001282,
|
|
"num_tokens": 23242799.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.727300834655762,
|
|
"epoch": 1.1708316954006852,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048739438927339346,
|
|
"loss": 5.5623,
|
|
"mean_token_accuracy": 0.1729305535554886,
|
|
"num_tokens": 23255112.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.565155792236328,
|
|
"epoch": 1.1713932723086427,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048738113614085656,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.18622813671827315,
|
|
"num_tokens": 23264800.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.54418158531189,
|
|
"epoch": 1.1719548492166,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000487367876246022,
|
|
"loss": 5.3979,
|
|
"mean_token_accuracy": 0.17960639148950577,
|
|
"num_tokens": 23276672.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.579484224319458,
|
|
"epoch": 1.1725164261245578,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004873546095893118,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.18114617466926575,
|
|
"num_tokens": 23288282.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.573983669281006,
|
|
"epoch": 1.1730780030325154,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004873413361711485,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.17828475832939147,
|
|
"num_tokens": 23299078.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.599126958847046,
|
|
"epoch": 1.1736395799404729,
|
|
"grad_norm": 2.765625,
|
|
"learning_rate": 0.00048732805599195465,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.1820347160100937,
|
|
"num_tokens": 23310036.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.5171972751617435,
|
|
"epoch": 1.1742011568484303,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048731476905215326,
|
|
"loss": 5.3762,
|
|
"mean_token_accuracy": 0.18743654042482377,
|
|
"num_tokens": 23321029.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.582168626785278,
|
|
"epoch": 1.174762733756388,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004873014753521673,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.17818383127450943,
|
|
"num_tokens": 23331584.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.764650011062622,
|
|
"epoch": 1.1753243106643454,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004872881748924199,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.16799859702587128,
|
|
"num_tokens": 23343171.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.648540782928467,
|
|
"epoch": 1.175885887572303,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004872748676733347,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.1762285679578781,
|
|
"num_tokens": 23353047.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.584035062789917,
|
|
"epoch": 1.1764474644802605,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048726155369533547,
|
|
"loss": 5.4722,
|
|
"mean_token_accuracy": 0.17585816532373427,
|
|
"num_tokens": 23364447.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.636832857131958,
|
|
"epoch": 1.1770090413882182,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000487248232958846,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.18070174753665924,
|
|
"num_tokens": 23375616.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.663487958908081,
|
|
"epoch": 1.1775706182961756,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004872349054642904,
|
|
"loss": 5.5868,
|
|
"mean_token_accuracy": 0.1763940379023552,
|
|
"num_tokens": 23388176.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.710677242279052,
|
|
"epoch": 1.1781321952041333,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004872215712120932,
|
|
"loss": 5.5254,
|
|
"mean_token_accuracy": 0.18045922368764877,
|
|
"num_tokens": 23400563.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.642408990859986,
|
|
"epoch": 1.1786937721120907,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004872082302026788,
|
|
"loss": 5.4618,
|
|
"mean_token_accuracy": 0.17593727260828018,
|
|
"num_tokens": 23410740.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.578441429138183,
|
|
"epoch": 1.1792553490200484,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004871948824364721,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.17642915099859238,
|
|
"num_tokens": 23423086.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.653734445571899,
|
|
"epoch": 1.1798169259280058,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000487181527913898,
|
|
"loss": 5.5461,
|
|
"mean_token_accuracy": 0.17511175125837325,
|
|
"num_tokens": 23435869.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.632935810089111,
|
|
"epoch": 1.1803785028359635,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048716816663538177,
|
|
"loss": 5.408,
|
|
"mean_token_accuracy": 0.18747486174106598,
|
|
"num_tokens": 23446635.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.531740665435791,
|
|
"epoch": 1.180940079743921,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004871547986013488,
|
|
"loss": 5.4286,
|
|
"mean_token_accuracy": 0.18138348162174225,
|
|
"num_tokens": 23458214.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.60255389213562,
|
|
"epoch": 1.1815016566518786,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004871414238122248,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.18705986738204955,
|
|
"num_tokens": 23469383.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.523975133895874,
|
|
"epoch": 1.182063233559836,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004871280422684355,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.18303017616271972,
|
|
"num_tokens": 23480841.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.566573810577393,
|
|
"epoch": 1.1826248104677934,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048711465397040726,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.18075590282678605,
|
|
"num_tokens": 23490796.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.55094428062439,
|
|
"epoch": 1.183186387375751,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048710125891856604,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.18059412091970445,
|
|
"num_tokens": 23501759.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.584206295013428,
|
|
"epoch": 1.1837479642837088,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048708785711333845,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.18351688235998154,
|
|
"num_tokens": 23512209.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.670858573913574,
|
|
"epoch": 1.1843095411916662,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048707444855515124,
|
|
"loss": 5.5303,
|
|
"mean_token_accuracy": 0.1740177169442177,
|
|
"num_tokens": 23524316.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.588708400726318,
|
|
"epoch": 1.1848711180996236,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004870610332444314,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.17790944278240203,
|
|
"num_tokens": 23536199.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.557408046722412,
|
|
"epoch": 1.1854326950075813,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004870476111816059,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.17937919795513152,
|
|
"num_tokens": 23548034.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.658392858505249,
|
|
"epoch": 1.1859942719155387,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048703418236710234,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.1803872689604759,
|
|
"num_tokens": 23559280.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.63859715461731,
|
|
"epoch": 1.1865558488234964,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004870207468013481,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.18161755055189133,
|
|
"num_tokens": 23569163.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.575729131698608,
|
|
"epoch": 1.1871174257314538,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004870073044847711,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.17995693981647493,
|
|
"num_tokens": 23580526.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.5177947044372555,
|
|
"epoch": 1.1876790026394115,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004869938554177993,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.17938145846128464,
|
|
"num_tokens": 23590552.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.513608312606811,
|
|
"epoch": 1.188240579547369,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048698039960086084,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.18309620916843414,
|
|
"num_tokens": 23601889.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.6143230438232425,
|
|
"epoch": 1.1888021564553266,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004869669370343843,
|
|
"loss": 5.5489,
|
|
"mean_token_accuracy": 0.18416569381952286,
|
|
"num_tokens": 23613833.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.661723852157593,
|
|
"epoch": 1.189363733363284,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004869534677187983,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.18057761490345,
|
|
"num_tokens": 23625404.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.545695972442627,
|
|
"epoch": 1.1899253102712417,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004869399916545317,
|
|
"loss": 5.3668,
|
|
"mean_token_accuracy": 0.1850145384669304,
|
|
"num_tokens": 23635670.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.499211311340332,
|
|
"epoch": 1.1904868871791991,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004869265088420135,
|
|
"loss": 5.362,
|
|
"mean_token_accuracy": 0.1849723592400551,
|
|
"num_tokens": 23646893.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.494884300231933,
|
|
"epoch": 1.1910484640871568,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004869130192816731,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.1808501660823822,
|
|
"num_tokens": 23657733.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.520437622070313,
|
|
"epoch": 1.1916100409951143,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048689952297394,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.187630395591259,
|
|
"num_tokens": 23668100.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.689531898498535,
|
|
"epoch": 1.192171617903072,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004868860199192438,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.1763995423913002,
|
|
"num_tokens": 23678295.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.523567628860474,
|
|
"epoch": 1.1927331948110294,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004868725101180146,
|
|
"loss": 5.3317,
|
|
"mean_token_accuracy": 0.18992675095796585,
|
|
"num_tokens": 23689310.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.496167993545532,
|
|
"epoch": 1.1932947717189868,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004868589935706826,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.17801743596792222,
|
|
"num_tokens": 23699475.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.643945837020874,
|
|
"epoch": 1.1938563486269445,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048684547027767793,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.18472916334867479,
|
|
"num_tokens": 23710186.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.506883764266968,
|
|
"epoch": 1.1944179255349021,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004868319402394314,
|
|
"loss": 5.2959,
|
|
"mean_token_accuracy": 0.1838797226548195,
|
|
"num_tokens": 23720449.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.648060131072998,
|
|
"epoch": 1.1949795024428596,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048681840345637375,
|
|
"loss": 5.5683,
|
|
"mean_token_accuracy": 0.1765943244099617,
|
|
"num_tokens": 23732295.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.533672189712524,
|
|
"epoch": 1.195541079350817,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048680485992893597,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.17684003710746765,
|
|
"num_tokens": 23743616.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.667600297927857,
|
|
"epoch": 1.1961026562587747,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048679130965754926,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.17168480008840561,
|
|
"num_tokens": 23755288.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.6198302745819095,
|
|
"epoch": 1.196664233166732,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004867777526426451,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.18234363943338394,
|
|
"num_tokens": 23765916.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.46681547164917,
|
|
"epoch": 1.1972258100746898,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048676418888465525,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.18079063594341277,
|
|
"num_tokens": 23778891.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.588815402984619,
|
|
"epoch": 1.1977873869826472,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004867506183840114,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.18219840973615647,
|
|
"num_tokens": 23790402.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.569733476638794,
|
|
"epoch": 1.1983489638906049,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.0004867370411411459,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.18921457678079606,
|
|
"num_tokens": 23801928.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.619349956512451,
|
|
"epoch": 1.1989105407985623,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048672345715649066,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16789069920778274,
|
|
"num_tokens": 23812302.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.611575651168823,
|
|
"epoch": 1.19947211770652,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004867098664304785,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.1912614330649376,
|
|
"num_tokens": 23824033.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.559762620925904,
|
|
"epoch": 1.2000336946144774,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004866962689635422,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.1822371304035187,
|
|
"num_tokens": 23834907.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.6310875415802,
|
|
"epoch": 1.200595271522435,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048668266475611447,
|
|
"loss": 5.5819,
|
|
"mean_token_accuracy": 0.18251619189977647,
|
|
"num_tokens": 23846418.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.694875431060791,
|
|
"epoch": 1.2011568484303925,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004866690538086286,
|
|
"loss": 5.5322,
|
|
"mean_token_accuracy": 0.17549929320812224,
|
|
"num_tokens": 23858423.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.592958259582519,
|
|
"epoch": 1.2017184253383502,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048665543612151803,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.18499407768249512,
|
|
"num_tokens": 23868340.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.549270439147949,
|
|
"epoch": 1.2022800022463076,
|
|
"grad_norm": 2.4375,
|
|
"learning_rate": 0.00048664181169521625,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.18464810997247696,
|
|
"num_tokens": 23878752.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.633689022064209,
|
|
"epoch": 1.2028415791542653,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004866281805301571,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.18496203124523164,
|
|
"num_tokens": 23889374.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.647559022903442,
|
|
"epoch": 1.2034031560622227,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004866145426267746,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.17902116775512694,
|
|
"num_tokens": 23901651.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.472747087478638,
|
|
"epoch": 1.2039647329701804,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.000486600897985503,
|
|
"loss": 5.3952,
|
|
"mean_token_accuracy": 0.1853911966085434,
|
|
"num_tokens": 23911818.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.593332433700562,
|
|
"epoch": 1.2045263098781378,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048658724660677674,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.1875730887055397,
|
|
"num_tokens": 23923840.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.57358226776123,
|
|
"epoch": 1.2050878867860955,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004865735884910305,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.18911986649036408,
|
|
"num_tokens": 23935406.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.575223779678344,
|
|
"epoch": 1.205649463694053,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004865599236386991,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.18341104537248612,
|
|
"num_tokens": 23946350.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.495678043365478,
|
|
"epoch": 1.2062110406020103,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004865462520502177,
|
|
"loss": 5.3618,
|
|
"mean_token_accuracy": 0.18589737117290497,
|
|
"num_tokens": 23956315.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.528962707519531,
|
|
"epoch": 1.206772617509968,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004865325737260216,
|
|
"loss": 5.3054,
|
|
"mean_token_accuracy": 0.18295775055885316,
|
|
"num_tokens": 23966649.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.647669649124145,
|
|
"epoch": 1.2073341944179254,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048651888866654624,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.17256360948085786,
|
|
"num_tokens": 23977674.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.566156387329102,
|
|
"epoch": 1.207895771325883,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004865051968722275,
|
|
"loss": 5.4518,
|
|
"mean_token_accuracy": 0.17648880332708358,
|
|
"num_tokens": 23987985.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.633535718917846,
|
|
"epoch": 1.2084573482338405,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00048649149834350126,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.17389376312494279,
|
|
"num_tokens": 23998730.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.554980707168579,
|
|
"epoch": 1.2090189251417982,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004864777930808037,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.17327924221754074,
|
|
"num_tokens": 24008743.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.5833625316619875,
|
|
"epoch": 1.2095805020497556,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004864640810845711,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.18483488112688065,
|
|
"num_tokens": 24019805.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.646902084350586,
|
|
"epoch": 1.2101420789577133,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004864503623552402,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.1797222375869751,
|
|
"num_tokens": 24031437.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.616756439208984,
|
|
"epoch": 1.2107036558656707,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004864366368932478,
|
|
"loss": 5.5563,
|
|
"mean_token_accuracy": 0.17546114027500154,
|
|
"num_tokens": 24043922.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.612255811691284,
|
|
"epoch": 1.2112652327736284,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048642290469903083,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.18924498111009597,
|
|
"num_tokens": 24054755.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.600620985031128,
|
|
"epoch": 1.2118268096815858,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048640916577302664,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.1718810573220253,
|
|
"num_tokens": 24067347.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.598409843444824,
|
|
"epoch": 1.2123883865895435,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048639542011567243,
|
|
"loss": 5.4381,
|
|
"mean_token_accuracy": 0.18517098873853682,
|
|
"num_tokens": 24078938.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.618745279312134,
|
|
"epoch": 1.212949963497501,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004863816677274062,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.17869086265563966,
|
|
"num_tokens": 24090275.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.565074396133423,
|
|
"epoch": 1.2135115404054586,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048636790860866576,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1834280475974083,
|
|
"num_tokens": 24101518.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.642368221282959,
|
|
"epoch": 1.214073117313416,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004863541427598889,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.1758333683013916,
|
|
"num_tokens": 24113320.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.563575267791748,
|
|
"epoch": 1.2146346942213737,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004863403701815144,
|
|
"loss": 5.3737,
|
|
"mean_token_accuracy": 0.18375860899686813,
|
|
"num_tokens": 24124842.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.6540463924407955,
|
|
"epoch": 1.2151962711293312,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004863265908739805,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.18117696940898895,
|
|
"num_tokens": 24136391.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.628338050842285,
|
|
"epoch": 1.2157578480372888,
|
|
"grad_norm": 2.8125,
|
|
"learning_rate": 0.0004863128048377259,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.17926495224237443,
|
|
"num_tokens": 24147194.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.665416574478149,
|
|
"epoch": 1.2163194249452463,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004862990120731896,
|
|
"loss": 5.5477,
|
|
"mean_token_accuracy": 0.17671335339546204,
|
|
"num_tokens": 24158170.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.607841920852661,
|
|
"epoch": 1.2168810018532037,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048628521258081096,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18543900102376937,
|
|
"num_tokens": 24168671.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.5290426254272464,
|
|
"epoch": 1.2174425787611614,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048627140636102906,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.1857820063829422,
|
|
"num_tokens": 24179898.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.546850681304932,
|
|
"epoch": 1.2180041556691188,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004862575934142837,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18467561900615692,
|
|
"num_tokens": 24190622.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.7730693340301515,
|
|
"epoch": 1.2185657325770765,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.0004862437737410147,
|
|
"loss": 5.5889,
|
|
"mean_token_accuracy": 0.1700533226132393,
|
|
"num_tokens": 24202526.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.57174711227417,
|
|
"epoch": 1.219127309485034,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004862299473416619,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.17997485995292664,
|
|
"num_tokens": 24213186.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.522643566131592,
|
|
"epoch": 1.2196888863929916,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048621611421666573,
|
|
"loss": 5.4243,
|
|
"mean_token_accuracy": 0.18304997384548188,
|
|
"num_tokens": 24225490.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.6109250545501705,
|
|
"epoch": 1.220250463300949,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004862022743664665,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.18046089708805085,
|
|
"num_tokens": 24236653.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.565627908706665,
|
|
"epoch": 1.2208120402089067,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048618842779150494,
|
|
"loss": 5.3719,
|
|
"mean_token_accuracy": 0.18843224495649338,
|
|
"num_tokens": 24247843.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.52214732170105,
|
|
"epoch": 1.221373617116864,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00048617457449222205,
|
|
"loss": 5.4427,
|
|
"mean_token_accuracy": 0.18507715910673142,
|
|
"num_tokens": 24258332.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.622708559036255,
|
|
"epoch": 1.2219351940248218,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004861607144690587,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.1823110744357109,
|
|
"num_tokens": 24268685.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.620092105865479,
|
|
"epoch": 1.2224967709327792,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004861468477224563,
|
|
"loss": 5.4673,
|
|
"mean_token_accuracy": 0.17618953436613083,
|
|
"num_tokens": 24280660.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.589652872085571,
|
|
"epoch": 1.2230583478407369,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048613297425285635,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.18139639347791672,
|
|
"num_tokens": 24291649.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.553171396255493,
|
|
"epoch": 1.2236199247486943,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004861190940607007,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.18429923802614212,
|
|
"num_tokens": 24303108.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.572359323501587,
|
|
"epoch": 1.224181501656652,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004861052071464312,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.17342991679906844,
|
|
"num_tokens": 24315939.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.538340711593628,
|
|
"epoch": 1.2247430785646094,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048609131351048994,
|
|
"loss": 5.432,
|
|
"mean_token_accuracy": 0.1806234374642372,
|
|
"num_tokens": 24326916.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.617301177978516,
|
|
"epoch": 1.225304655472567,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004860774131533195,
|
|
"loss": 5.4705,
|
|
"mean_token_accuracy": 0.18296236097812651,
|
|
"num_tokens": 24337790.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.523585462570191,
|
|
"epoch": 1.2258662323805245,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00048606350607536235,
|
|
"loss": 5.2872,
|
|
"mean_token_accuracy": 0.19296668320894242,
|
|
"num_tokens": 24347930.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.569266366958618,
|
|
"epoch": 1.2264278092884822,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004860495922770612,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.18250273913145065,
|
|
"num_tokens": 24359213.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.54276704788208,
|
|
"epoch": 1.2269893861964396,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00048603567175885926,
|
|
"loss": 5.3544,
|
|
"mean_token_accuracy": 0.18154604882001876,
|
|
"num_tokens": 24371000.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.483095359802246,
|
|
"epoch": 1.227550963104397,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004860217445211997,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.18523183465003967,
|
|
"num_tokens": 24381301.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.630552959442139,
|
|
"epoch": 1.2281125400123547,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004860078105645259,
|
|
"loss": 5.5299,
|
|
"mean_token_accuracy": 0.173642535507679,
|
|
"num_tokens": 24391808.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.7053569793701175,
|
|
"epoch": 1.2286741169203121,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004859938698892816,
|
|
"loss": 5.6529,
|
|
"mean_token_accuracy": 0.1735002413392067,
|
|
"num_tokens": 24404220.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.638109493255615,
|
|
"epoch": 1.2292356938282698,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048597992249591065,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.1841175764799118,
|
|
"num_tokens": 24414906.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.537660598754883,
|
|
"epoch": 1.2297972707362272,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048596596838485704,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.17744858115911483,
|
|
"num_tokens": 24426469.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.503168392181396,
|
|
"epoch": 1.230358847644185,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004859520075565654,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.18326544016599655,
|
|
"num_tokens": 24437683.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.500739526748657,
|
|
"epoch": 1.2309204245521423,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048593804001147986,
|
|
"loss": 5.3087,
|
|
"mean_token_accuracy": 0.1862681970000267,
|
|
"num_tokens": 24449038.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.614598989486694,
|
|
"epoch": 1.2314820014601,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004859240657500453,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.18613068014383316,
|
|
"num_tokens": 24460228.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.580488538742065,
|
|
"epoch": 1.2320435783680574,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048591008477270675,
|
|
"loss": 5.4887,
|
|
"mean_token_accuracy": 0.1740068569779396,
|
|
"num_tokens": 24471222.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.577352666854859,
|
|
"epoch": 1.232605155276015,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048589609707990925,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.17964452207088472,
|
|
"num_tokens": 24482127.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.608374547958374,
|
|
"epoch": 1.2331667321839725,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048588210267209823,
|
|
"loss": 5.4105,
|
|
"mean_token_accuracy": 0.1806041419506073,
|
|
"num_tokens": 24492963.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.643153381347656,
|
|
"epoch": 1.2337283090919302,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048586810154971935,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.18467315584421157,
|
|
"num_tokens": 24502885.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.686823034286499,
|
|
"epoch": 1.2342898859998876,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048585409371321826,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.18148137778043746,
|
|
"num_tokens": 24514990.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.625125789642334,
|
|
"epoch": 1.2348514629078453,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048584007916304106,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.17604809254407883,
|
|
"num_tokens": 24525555.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.602579164505005,
|
|
"epoch": 1.2354130398158027,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00048582605789963395,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.17468535751104355,
|
|
"num_tokens": 24536350.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.666131258010864,
|
|
"epoch": 1.2359746167237604,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004858120299234434,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.17794036567211152,
|
|
"num_tokens": 24547756.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.516967296600342,
|
|
"epoch": 1.2365361936317179,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048579799523491607,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.1846114456653595,
|
|
"num_tokens": 24559897.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.5787187099456785,
|
|
"epoch": 1.2370977705396755,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004857839538344988,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.17730329036712647,
|
|
"num_tokens": 24570168.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.634731149673462,
|
|
"epoch": 1.237659347447633,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048576990572263875,
|
|
"loss": 5.3636,
|
|
"mean_token_accuracy": 0.1857059881091118,
|
|
"num_tokens": 24580918.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.569552850723267,
|
|
"epoch": 1.2382209243555904,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004857558508997831,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.17410874962806702,
|
|
"num_tokens": 24592378.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.6055773258209225,
|
|
"epoch": 1.238782501263548,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004857417893663794,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.18178618103265762,
|
|
"num_tokens": 24603666.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.559194707870484,
|
|
"epoch": 1.2393440781715055,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004857277211228754,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.17836459279060363,
|
|
"num_tokens": 24615299.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.598504304885864,
|
|
"epoch": 1.2399056550794632,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004857136461697191,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.18318089097738266,
|
|
"num_tokens": 24626138.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.553735160827637,
|
|
"epoch": 1.2404672319874206,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048569956450735853,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.17893289178609847,
|
|
"num_tokens": 24636720.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.601636695861816,
|
|
"epoch": 1.2410288088953783,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048568547613624206,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.17638325542211533,
|
|
"num_tokens": 24648147.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.586811208724976,
|
|
"epoch": 1.2415903858033357,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048567138105681833,
|
|
"loss": 5.4644,
|
|
"mean_token_accuracy": 0.18397458046674728,
|
|
"num_tokens": 24659825.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.597035837173462,
|
|
"epoch": 1.2421519627112934,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048565727926953617,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.18312924355268478,
|
|
"num_tokens": 24671583.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.572998476028443,
|
|
"epoch": 1.2427135396192508,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004856431707748445,
|
|
"loss": 5.336,
|
|
"mean_token_accuracy": 0.1801964372396469,
|
|
"num_tokens": 24682034.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.565976142883301,
|
|
"epoch": 1.2432751165272085,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004856290555731926,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.17961082011461257,
|
|
"num_tokens": 24693624.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.683384037017822,
|
|
"epoch": 1.243836693435166,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004856149336650299,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.18243033289909363,
|
|
"num_tokens": 24705340.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.6784751415252686,
|
|
"epoch": 1.2443982703431236,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004856008050508059,
|
|
"loss": 5.5208,
|
|
"mean_token_accuracy": 0.17765077948570251,
|
|
"num_tokens": 24717115.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.5842877388000485,
|
|
"epoch": 1.244959847251081,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004855866697309707,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.18390680998563766,
|
|
"num_tokens": 24727768.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.624321699142456,
|
|
"epoch": 1.2455214241590387,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004855725277059742,
|
|
"loss": 5.5219,
|
|
"mean_token_accuracy": 0.17082616835832595,
|
|
"num_tokens": 24740054.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.642755556106567,
|
|
"epoch": 1.246083001066996,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004855583789762668,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.17992781698703766,
|
|
"num_tokens": 24750658.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.727603387832642,
|
|
"epoch": 1.2466445779749538,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000485544223542299,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.17754979580640792,
|
|
"num_tokens": 24762730.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.532628583908081,
|
|
"epoch": 1.2472061548829112,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004855300614045214,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.18781628012657164,
|
|
"num_tokens": 24773865.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.467036533355713,
|
|
"epoch": 1.2477677317908689,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048551589256338497,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.18275701999664307,
|
|
"num_tokens": 24783030.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.53635802268982,
|
|
"epoch": 1.2483293086988263,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048550171701934087,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.1847753033041954,
|
|
"num_tokens": 24793177.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.702278137207031,
|
|
"epoch": 1.2488908856067837,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048548753477284053,
|
|
"loss": 5.4762,
|
|
"mean_token_accuracy": 0.18519136160612107,
|
|
"num_tokens": 24804796.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.617565441131592,
|
|
"epoch": 1.2494524625147414,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004854733458243354,
|
|
"loss": 5.4824,
|
|
"mean_token_accuracy": 0.17698035538196563,
|
|
"num_tokens": 24816806.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.579028367996216,
|
|
"epoch": 1.250014039422699,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004854591501742773,
|
|
"loss": 5.4241,
|
|
"mean_token_accuracy": 0.18605956733226775,
|
|
"num_tokens": 24826888.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.624572229385376,
|
|
"epoch": 1.2505756163306565,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048544494782311825,
|
|
"loss": 5.384,
|
|
"mean_token_accuracy": 0.18263110071420668,
|
|
"num_tokens": 24837731.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.521479701995849,
|
|
"epoch": 1.251137193238614,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048543073877131037,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.18520236015319824,
|
|
"num_tokens": 24847900.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.499649715423584,
|
|
"epoch": 1.2516987701465716,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048541652301930627,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.17603074461221696,
|
|
"num_tokens": 24858878.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.600009155273438,
|
|
"epoch": 1.252260347054529,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004854023005675585,
|
|
"loss": 5.414,
|
|
"mean_token_accuracy": 0.18104791790246963,
|
|
"num_tokens": 24870051.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.635410976409912,
|
|
"epoch": 1.2528219239624867,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004853880714165197,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.17741311639547347,
|
|
"num_tokens": 24881671.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.601282072067261,
|
|
"epoch": 1.2533835008704441,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048537383556664315,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.18032517433166503,
|
|
"num_tokens": 24892944.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.550411033630371,
|
|
"epoch": 1.2539450777784018,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004853595930183822,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.17592736780643464,
|
|
"num_tokens": 24903346.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.583200311660766,
|
|
"epoch": 1.2545066546863592,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004853453437721901,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.18016977608203888,
|
|
"num_tokens": 24913904.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.573392629623413,
|
|
"epoch": 1.255068231594317,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004853310878285208,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.1838017761707306,
|
|
"num_tokens": 24924635.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.623681974411011,
|
|
"epoch": 1.2556298085022743,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048531682518782797,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.17550791203975677,
|
|
"num_tokens": 24935466.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.6808753490448,
|
|
"epoch": 1.256191385410232,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048530255585056594,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.17956021726131438,
|
|
"num_tokens": 24948348.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.572185754776001,
|
|
"epoch": 1.2567529623181894,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004852882798171889,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.18664514273405075,
|
|
"num_tokens": 24959242.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.532141017913818,
|
|
"epoch": 1.2573145392261469,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004852739970881515,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.1837014824151993,
|
|
"num_tokens": 24969855.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.558584594726563,
|
|
"epoch": 1.2578761161341045,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048525970766390847,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.18368715047836304,
|
|
"num_tokens": 24980378.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.608485555648803,
|
|
"epoch": 1.2584376930420622,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004852454115449148,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.18013945966959,
|
|
"num_tokens": 24990646.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.6751298904418945,
|
|
"epoch": 1.2589992699500197,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004852311087316257,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.17049788534641266,
|
|
"num_tokens": 25002644.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.6370423316955565,
|
|
"epoch": 1.259560846857977,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004852167992244966,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.1861061230301857,
|
|
"num_tokens": 25012635.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.603090143203735,
|
|
"epoch": 1.2601224237659348,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000485202483023983,
|
|
"loss": 5.564,
|
|
"mean_token_accuracy": 0.17111812233924867,
|
|
"num_tokens": 25024289.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.595809459686279,
|
|
"epoch": 1.2606840006738924,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00048518816013054083,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.1857122927904129,
|
|
"num_tokens": 25035316.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.555857610702515,
|
|
"epoch": 1.2612455775818499,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048517383054462617,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18120528906583785,
|
|
"num_tokens": 25046011.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.623838901519775,
|
|
"epoch": 1.2618071544898073,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004851594942666952,
|
|
"loss": 5.4027,
|
|
"mean_token_accuracy": 0.181715627014637,
|
|
"num_tokens": 25057402.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.54107813835144,
|
|
"epoch": 1.262368731397765,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048514515129720445,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18256974816322327,
|
|
"num_tokens": 25068287.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.529361629486084,
|
|
"epoch": 1.2629303083057224,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004851308016366105,
|
|
"loss": 5.363,
|
|
"mean_token_accuracy": 0.18539973795413972,
|
|
"num_tokens": 25079534.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.498859500885009,
|
|
"epoch": 1.26349188521368,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.00048511644528537043,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.18430730998516082,
|
|
"num_tokens": 25090825.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.591787528991699,
|
|
"epoch": 1.2640534621216375,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004851020822439412,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.18224924057722092,
|
|
"num_tokens": 25101859.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.520960760116577,
|
|
"epoch": 1.2646150390295952,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048508771251278015,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.1899106577038765,
|
|
"num_tokens": 25111416.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.564133834838867,
|
|
"epoch": 1.2651766159375526,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004850733360923449,
|
|
"loss": 5.4623,
|
|
"mean_token_accuracy": 0.18021347373723984,
|
|
"num_tokens": 25122129.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.59199709892273,
|
|
"epoch": 1.2657381928455103,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004850589529830931,
|
|
"loss": 5.4426,
|
|
"mean_token_accuracy": 0.18468846678733825,
|
|
"num_tokens": 25132429.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.508084630966186,
|
|
"epoch": 1.2662997697534677,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00048504456318548285,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.18493908494710923,
|
|
"num_tokens": 25144242.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.665618133544922,
|
|
"epoch": 1.2668613466614254,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004850301666999722,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.18361348807811737,
|
|
"num_tokens": 25155332.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.657198286056518,
|
|
"epoch": 1.2674229235693828,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004850157635270196,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.18353936821222305,
|
|
"num_tokens": 25166024.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.5646045207977295,
|
|
"epoch": 1.2679845004773402,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004850013536670836,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.1885433465242386,
|
|
"num_tokens": 25176697.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.5398791313171385,
|
|
"epoch": 1.268546077385298,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004849869371206231,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18388876616954802,
|
|
"num_tokens": 25187421.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.5654467105865475,
|
|
"epoch": 1.2691076542932556,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048497251388809697,
|
|
"loss": 5.4562,
|
|
"mean_token_accuracy": 0.18446133881807328,
|
|
"num_tokens": 25198851.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.6553655624389645,
|
|
"epoch": 1.269669231201213,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004849580839699647,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.17793616354465486,
|
|
"num_tokens": 25209984.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.610251522064209,
|
|
"epoch": 1.2702308081091704,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.00048494364736668554,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.17918065786361695,
|
|
"num_tokens": 25220672.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.615945196151733,
|
|
"epoch": 1.270792385017128,
|
|
"grad_norm": 2.390625,
|
|
"learning_rate": 0.0004849292040787192,
|
|
"loss": 5.4215,
|
|
"mean_token_accuracy": 0.1835802286863327,
|
|
"num_tokens": 25231906.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.630214023590088,
|
|
"epoch": 1.2713539619250858,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004849147541065256,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.17847924530506135,
|
|
"num_tokens": 25242902.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.623560237884521,
|
|
"epoch": 1.2719155388330432,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004849002974505649,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.17962157726287842,
|
|
"num_tokens": 25254363.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.60678014755249,
|
|
"epoch": 1.2724771157410006,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048488583411129723,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.18200416266918182,
|
|
"num_tokens": 25267108.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.579688930511475,
|
|
"epoch": 1.2730386926489583,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004848713640891832,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.18338331580162048,
|
|
"num_tokens": 25278583.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.684441471099854,
|
|
"epoch": 1.2736002695569157,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004848568873846835,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.18076091706752778,
|
|
"num_tokens": 25289813.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.5357006072998045,
|
|
"epoch": 1.2741618464648734,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048484240399825925,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.18102050125598906,
|
|
"num_tokens": 25301003.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.513173770904541,
|
|
"epoch": 1.2747234233728308,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00048482791393037134,
|
|
"loss": 5.3744,
|
|
"mean_token_accuracy": 0.18561362475156784,
|
|
"num_tokens": 25312535.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.585785388946533,
|
|
"epoch": 1.2752850002807885,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048481341718148137,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18328526318073274,
|
|
"num_tokens": 25323333.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.645577335357666,
|
|
"epoch": 1.275846577188746,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048479891375205074,
|
|
"loss": 5.5307,
|
|
"mean_token_accuracy": 0.17883193045854567,
|
|
"num_tokens": 25334865.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.607233905792237,
|
|
"epoch": 1.2764081540967036,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048478440364254136,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.1781284287571907,
|
|
"num_tokens": 25346672.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.566584205627441,
|
|
"epoch": 1.276969731004661,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004847698868534152,
|
|
"loss": 5.4834,
|
|
"mean_token_accuracy": 0.18481787741184236,
|
|
"num_tokens": 25358702.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.606048727035523,
|
|
"epoch": 1.2775313079126187,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004847553633851345,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.1778454676270485,
|
|
"num_tokens": 25369813.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.67353892326355,
|
|
"epoch": 1.2780928848205761,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004847408332381616,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.17429344058036805,
|
|
"num_tokens": 25381042.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.580134344100952,
|
|
"epoch": 1.2786544617285336,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048472629641295933,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.17475285828113557,
|
|
"num_tokens": 25391286.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.560000419616699,
|
|
"epoch": 1.2792160386364912,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004847117529099904,
|
|
"loss": 5.3954,
|
|
"mean_token_accuracy": 0.18422052562236785,
|
|
"num_tokens": 25402335.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.530968904495239,
|
|
"epoch": 1.279777615544449,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00048469720272971797,
|
|
"loss": 5.3313,
|
|
"mean_token_accuracy": 0.18764818608760833,
|
|
"num_tokens": 25413484.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.650443029403687,
|
|
"epoch": 1.2803391924524063,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004846826458726052,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.17878019213676452,
|
|
"num_tokens": 25424276.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.466383647918701,
|
|
"epoch": 1.2809007693603638,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048466808233911567,
|
|
"loss": 5.3403,
|
|
"mean_token_accuracy": 0.1846219778060913,
|
|
"num_tokens": 25435178.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.437576675415039,
|
|
"epoch": 1.2814623462683215,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048465351212971313,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.1863858848810196,
|
|
"num_tokens": 25445792.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.555386161804199,
|
|
"epoch": 1.2820239231762791,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004846389352448614,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.1822787344455719,
|
|
"num_tokens": 25456598.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.568631410598755,
|
|
"epoch": 1.2825855000842366,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004846243516850247,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.1828199103474617,
|
|
"num_tokens": 25468311.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.62476282119751,
|
|
"epoch": 1.283147076992194,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004846097614506673,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.17778723686933517,
|
|
"num_tokens": 25480680.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.678446054458618,
|
|
"epoch": 1.2837086539001517,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048459516454225384,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.1844809889793396,
|
|
"num_tokens": 25492255.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.603737831115723,
|
|
"epoch": 1.284270230808109,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000484580560960249,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.1781509757041931,
|
|
"num_tokens": 25504530.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.52678370475769,
|
|
"epoch": 1.2848318077160668,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004845659507051178,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.18436024338006973,
|
|
"num_tokens": 25515273.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.6182005405426025,
|
|
"epoch": 1.2853933846240242,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004845513337773255,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.1807490035891533,
|
|
"num_tokens": 25526050.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.667512893676758,
|
|
"epoch": 1.2859549615319819,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048453671017733755,
|
|
"loss": 5.459,
|
|
"mean_token_accuracy": 0.17630999237298967,
|
|
"num_tokens": 25538372.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.7185976028442385,
|
|
"epoch": 1.2865165384399393,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004845220799056194,
|
|
"loss": 5.5625,
|
|
"mean_token_accuracy": 0.1805414229631424,
|
|
"num_tokens": 25549636.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.5848641872406,
|
|
"epoch": 1.287078115347897,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048450744296263685,
|
|
"loss": 5.4694,
|
|
"mean_token_accuracy": 0.18007947355508805,
|
|
"num_tokens": 25560850.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.581377792358398,
|
|
"epoch": 1.2876396922558544,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048449279934885625,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.18421742916107178,
|
|
"num_tokens": 25572433.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.681732702255249,
|
|
"epoch": 1.288201269163812,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004844781490647435,
|
|
"loss": 5.4798,
|
|
"mean_token_accuracy": 0.18070216327905655,
|
|
"num_tokens": 25582372.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.526977682113648,
|
|
"epoch": 1.2887628460717695,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004844634921107654,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.18807841539382936,
|
|
"num_tokens": 25592570.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.5763078212738035,
|
|
"epoch": 1.289324422979727,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048444882848738835,
|
|
"loss": 5.4654,
|
|
"mean_token_accuracy": 0.17428210526704788,
|
|
"num_tokens": 25603573.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.644854307174683,
|
|
"epoch": 1.2898859998876846,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048443415819507944,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.18149638473987578,
|
|
"num_tokens": 25614233.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.614844799041748,
|
|
"epoch": 1.2904475767956423,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004844194812343057,
|
|
"loss": 5.4312,
|
|
"mean_token_accuracy": 0.17748414278030394,
|
|
"num_tokens": 25625077.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.51409420967102,
|
|
"epoch": 1.2910091537035997,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004844047976055344,
|
|
"loss": 5.4546,
|
|
"mean_token_accuracy": 0.17588285505771636,
|
|
"num_tokens": 25636693.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.49900450706482,
|
|
"epoch": 1.2915707306115571,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048439010730923313,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.1822786495089531,
|
|
"num_tokens": 25647644.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.559824705123901,
|
|
"epoch": 1.2921323075195148,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048437541034586964,
|
|
"loss": 5.3488,
|
|
"mean_token_accuracy": 0.18998415023088455,
|
|
"num_tokens": 25659373.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.59814190864563,
|
|
"epoch": 1.2926938844274725,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048436070671591195,
|
|
"loss": 5.483,
|
|
"mean_token_accuracy": 0.184467414021492,
|
|
"num_tokens": 25670479.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.624522256851196,
|
|
"epoch": 1.29325546133543,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048434599641982806,
|
|
"loss": 5.4952,
|
|
"mean_token_accuracy": 0.18360517919063568,
|
|
"num_tokens": 25682748.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.569586515426636,
|
|
"epoch": 1.2938170382433873,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048433127945808645,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.18949444741010665,
|
|
"num_tokens": 25693170.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.5388373851776125,
|
|
"epoch": 1.294378615151345,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004843165558311558,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.17833870202302932,
|
|
"num_tokens": 25706009.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.62146954536438,
|
|
"epoch": 1.2949401920593024,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004843018255395048,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.18077232241630553,
|
|
"num_tokens": 25716036.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.60507550239563,
|
|
"epoch": 1.29550176896726,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048428708858360244,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.18492817431688308,
|
|
"num_tokens": 25726516.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.5519129753112795,
|
|
"epoch": 1.2960633458752175,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048427234496391816,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.1748302161693573,
|
|
"num_tokens": 25736340.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.486657285690308,
|
|
"epoch": 1.2966249227831752,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048425759468092113,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.17781427204608918,
|
|
"num_tokens": 25746439.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.549418163299561,
|
|
"epoch": 1.2971864996911326,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004842428377350811,
|
|
"loss": 5.3347,
|
|
"mean_token_accuracy": 0.18356838822364807,
|
|
"num_tokens": 25757065.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.561953067779541,
|
|
"epoch": 1.2977480765990903,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048422807412686796,
|
|
"loss": 5.3846,
|
|
"mean_token_accuracy": 0.17900499403476716,
|
|
"num_tokens": 25768021.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.633684825897217,
|
|
"epoch": 1.2983096535070477,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004842133038567519,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17979225069284438,
|
|
"num_tokens": 25780197.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.56424765586853,
|
|
"epoch": 1.2988712304150054,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000484198526925203,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.1794813022017479,
|
|
"num_tokens": 25790536.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.547435998916626,
|
|
"epoch": 1.2994328073229628,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004841837433326919,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.18306393623352052,
|
|
"num_tokens": 25802397.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.585913467407226,
|
|
"epoch": 1.2999943842309205,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004841689530796893,
|
|
"loss": 5.5044,
|
|
"mean_token_accuracy": 0.18291712403297425,
|
|
"num_tokens": 25813961.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.611777973175049,
|
|
"epoch": 1.300555961138878,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004841541561666661,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.1765737935900688,
|
|
"num_tokens": 25825610.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.561756134033203,
|
|
"epoch": 1.3011175380468356,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048413935259409343,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.18526591062545777,
|
|
"num_tokens": 25836076.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.54350528717041,
|
|
"epoch": 1.301679114954793,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048412454236244267,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.1877109318971634,
|
|
"num_tokens": 25847341.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.468132781982422,
|
|
"epoch": 1.3022406918627505,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048410972547218545,
|
|
"loss": 5.3344,
|
|
"mean_token_accuracy": 0.1879123255610466,
|
|
"num_tokens": 25856912.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.579463148117066,
|
|
"epoch": 1.3028022687707081,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048409490192379337,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.17762463241815568,
|
|
"num_tokens": 25868370.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.543521070480347,
|
|
"epoch": 1.3033638456786658,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004840800717177386,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.18641136437654496,
|
|
"num_tokens": 25879104.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.569950866699219,
|
|
"epoch": 1.3039254225866233,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004840652348544931,
|
|
"loss": 5.4728,
|
|
"mean_token_accuracy": 0.17264024019241334,
|
|
"num_tokens": 25889744.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.688677787780762,
|
|
"epoch": 1.3044869994945807,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004840503913345296,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.1729704812169075,
|
|
"num_tokens": 25901615.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.60819902420044,
|
|
"epoch": 1.3050485764025384,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004840355411583205,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.17723400443792342,
|
|
"num_tokens": 25911418.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.633505630493164,
|
|
"epoch": 1.3056101533104958,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048402068432633864,
|
|
"loss": 5.5213,
|
|
"mean_token_accuracy": 0.18241286426782607,
|
|
"num_tokens": 25922141.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.644653081893921,
|
|
"epoch": 1.3061717302184535,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004840058208390572,
|
|
"loss": 5.5121,
|
|
"mean_token_accuracy": 0.17880819588899613,
|
|
"num_tokens": 25933897.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.642878723144531,
|
|
"epoch": 1.306733307126411,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004839909506969494,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.1793980747461319,
|
|
"num_tokens": 25943960.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.65636100769043,
|
|
"epoch": 1.3072948840343686,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004839760739004886,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.17682792395353317,
|
|
"num_tokens": 25955104.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.546225595474243,
|
|
"epoch": 1.307856460942326,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048396119045014853,
|
|
"loss": 5.4364,
|
|
"mean_token_accuracy": 0.17862225770950318,
|
|
"num_tokens": 25965180.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.614621543884278,
|
|
"epoch": 1.3084180378502837,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004839463003464032,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.18488036394119262,
|
|
"num_tokens": 25976600.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.471648073196411,
|
|
"epoch": 1.308979614758241,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004839314035897265,
|
|
"loss": 5.4045,
|
|
"mean_token_accuracy": 0.17672015577554703,
|
|
"num_tokens": 25987509.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.546474266052246,
|
|
"epoch": 1.3095411916661988,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000483916500180593,
|
|
"loss": 5.346,
|
|
"mean_token_accuracy": 0.1887213930487633,
|
|
"num_tokens": 25997962.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.588915109634399,
|
|
"epoch": 1.3101027685741562,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048390159011947706,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.18289054483175277,
|
|
"num_tokens": 26008932.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.583460712432862,
|
|
"epoch": 1.3106643454821139,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004838866734068535,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.1762971833348274,
|
|
"num_tokens": 26020513.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.625772905349732,
|
|
"epoch": 1.3112259223900713,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.00048387175004319723,
|
|
"loss": 5.4869,
|
|
"mean_token_accuracy": 0.17528999596834183,
|
|
"num_tokens": 26032526.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.574745225906372,
|
|
"epoch": 1.311787499298029,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004838568200289834,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.18474198281764984,
|
|
"num_tokens": 26044216.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.545057678222657,
|
|
"epoch": 1.3123490762059864,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004838418833646875,
|
|
"loss": 5.3259,
|
|
"mean_token_accuracy": 0.18183980733156205,
|
|
"num_tokens": 26054012.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.603783464431762,
|
|
"epoch": 1.3129106531139438,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048382694005078485,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.17909120321273803,
|
|
"num_tokens": 26065365.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.629224348068237,
|
|
"epoch": 1.3134722300219015,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048381199008775165,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.17570256143808366,
|
|
"num_tokens": 26075964.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.534933280944824,
|
|
"epoch": 1.3140338069298592,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004837970334760635,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.18252165466547013,
|
|
"num_tokens": 26087572.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.538932609558105,
|
|
"epoch": 1.3145953838378166,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000483782070216197,
|
|
"loss": 5.3348,
|
|
"mean_token_accuracy": 0.18563566505908966,
|
|
"num_tokens": 26098612.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.615560293197632,
|
|
"epoch": 1.315156960745774,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004837671003086283,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.1806085541844368,
|
|
"num_tokens": 26109491.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.617796182632446,
|
|
"epoch": 1.3157185376537317,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004837521237538342,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.18350049406290053,
|
|
"num_tokens": 26120544.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.653694009780883,
|
|
"epoch": 1.3162801145616891,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004837371405522915,
|
|
"loss": 5.4956,
|
|
"mean_token_accuracy": 0.17320299297571182,
|
|
"num_tokens": 26131549.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.535081434249878,
|
|
"epoch": 1.3168416914696468,
|
|
"grad_norm": 2.453125,
|
|
"learning_rate": 0.00048372215070447734,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.18284115195274353,
|
|
"num_tokens": 26142871.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.69437837600708,
|
|
"epoch": 1.3174032683776042,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048370715421086884,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.17821001261472702,
|
|
"num_tokens": 26155293.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.656451463699341,
|
|
"epoch": 1.317964845285562,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004836921510719438,
|
|
"loss": 5.4867,
|
|
"mean_token_accuracy": 0.18781925588846207,
|
|
"num_tokens": 26167069.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.566701984405517,
|
|
"epoch": 1.3185264221935193,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004836771412881795,
|
|
"loss": 5.4946,
|
|
"mean_token_accuracy": 0.1695489391684532,
|
|
"num_tokens": 26179142.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.626594686508179,
|
|
"epoch": 1.319087999101477,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004836621248600542,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.1826922357082367,
|
|
"num_tokens": 26190059.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.615626382827759,
|
|
"epoch": 1.3196495760094344,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004836471017880459,
|
|
"loss": 5.4372,
|
|
"mean_token_accuracy": 0.178737074136734,
|
|
"num_tokens": 26199859.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.576315116882324,
|
|
"epoch": 1.320211152917392,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004836320720726329,
|
|
"loss": 5.4811,
|
|
"mean_token_accuracy": 0.17840957045555114,
|
|
"num_tokens": 26211920.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.611711549758911,
|
|
"epoch": 1.3207727298253495,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004836170357142939,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.18101833313703536,
|
|
"num_tokens": 26222875.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.621111011505127,
|
|
"epoch": 1.3213343067333072,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004836019927135076,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.17637555301189423,
|
|
"num_tokens": 26233549.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.521720743179321,
|
|
"epoch": 1.3218958836412646,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004835869430707529,
|
|
"loss": 5.3363,
|
|
"mean_token_accuracy": 0.19574303179979324,
|
|
"num_tokens": 26243886.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.478554534912109,
|
|
"epoch": 1.3224574605492223,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048357188678650905,
|
|
"loss": 5.3845,
|
|
"mean_token_accuracy": 0.1865053027868271,
|
|
"num_tokens": 26254475.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.668208026885987,
|
|
"epoch": 1.3230190374571797,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004835568238612553,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.17765906304121018,
|
|
"num_tokens": 26265412.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.723432540893555,
|
|
"epoch": 1.3235806143651372,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048354175429547155,
|
|
"loss": 5.4963,
|
|
"mean_token_accuracy": 0.1782914236187935,
|
|
"num_tokens": 26276942.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.599355840682984,
|
|
"epoch": 1.3241421912730948,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004835266780896374,
|
|
"loss": 5.4504,
|
|
"mean_token_accuracy": 0.1785310313105583,
|
|
"num_tokens": 26288009.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.67936429977417,
|
|
"epoch": 1.3247037681810525,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004835115952442329,
|
|
"loss": 5.6086,
|
|
"mean_token_accuracy": 0.17064086794853212,
|
|
"num_tokens": 26301583.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.7005024433135985,
|
|
"epoch": 1.32526534508901,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048349650575973843,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.17938229739665984,
|
|
"num_tokens": 26312922.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.5894428253173825,
|
|
"epoch": 1.3258269219969674,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048348140963663436,
|
|
"loss": 5.4494,
|
|
"mean_token_accuracy": 0.18334481120109558,
|
|
"num_tokens": 26324108.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.620400333404541,
|
|
"epoch": 1.326388498904925,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004834663068754012,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.17555374950170516,
|
|
"num_tokens": 26335669.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.5243054866790775,
|
|
"epoch": 1.3269500758128827,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004834511974765202,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.1873750254511833,
|
|
"num_tokens": 26346065.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.597712421417237,
|
|
"epoch": 1.3275116527208402,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048343608144047194,
|
|
"loss": 5.3497,
|
|
"mean_token_accuracy": 0.17996396422386168,
|
|
"num_tokens": 26357567.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.570871019363404,
|
|
"epoch": 1.3280732296287976,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048342095876773825,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.18115177750587463,
|
|
"num_tokens": 26367805.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.531180047988892,
|
|
"epoch": 1.3286348065367553,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004834058294588003,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.18657401502132415,
|
|
"num_tokens": 26379343.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.688341426849365,
|
|
"epoch": 1.3291963834447127,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048339069351413993,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.17514421790838242,
|
|
"num_tokens": 26392039.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.48055362701416,
|
|
"epoch": 1.3297579603526704,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000483375550934239,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.19581910222768784,
|
|
"num_tokens": 26403324.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.533324670791626,
|
|
"epoch": 1.3303195372606278,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004833604017195798,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.185368350148201,
|
|
"num_tokens": 26413435.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.582947397232056,
|
|
"epoch": 1.3308811141685855,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004833452458706445,
|
|
"loss": 5.5029,
|
|
"mean_token_accuracy": 0.17233147472143173,
|
|
"num_tokens": 26424254.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.645512676239013,
|
|
"epoch": 1.331442691076543,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004833300833879159,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.1806909367442131,
|
|
"num_tokens": 26435658.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.647691869735718,
|
|
"epoch": 1.3320042679845006,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004833149142718765,
|
|
"loss": 5.4948,
|
|
"mean_token_accuracy": 0.17807558178901672,
|
|
"num_tokens": 26447174.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.630060768127441,
|
|
"epoch": 1.332565844892458,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004832997385230096,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.17954639345407486,
|
|
"num_tokens": 26459303.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.569930171966552,
|
|
"epoch": 1.3331274218004157,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004832845561417981,
|
|
"loss": 5.4187,
|
|
"mean_token_accuracy": 0.17842208296060563,
|
|
"num_tokens": 26469981.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.541556739807129,
|
|
"epoch": 1.333688998708373,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004832693671287256,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.1876738950610161,
|
|
"num_tokens": 26481176.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.57940673828125,
|
|
"epoch": 1.3342505756163305,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004832541714842757,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18593909293413163,
|
|
"num_tokens": 26492795.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.64307222366333,
|
|
"epoch": 1.3348121525242882,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004832389692089321,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.17878035306930543,
|
|
"num_tokens": 26504731.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.640158843994141,
|
|
"epoch": 1.3353737294322459,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048322376030317905,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.18080338835716248,
|
|
"num_tokens": 26516816.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.597026348114014,
|
|
"epoch": 1.3359353063402033,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004832085447675007,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.1830771028995514,
|
|
"num_tokens": 26528861.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.664387655258179,
|
|
"epoch": 1.3364968832481607,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048319332260238153,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.18214741051197053,
|
|
"num_tokens": 26538816.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.694076776504517,
|
|
"epoch": 1.3370584601561184,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048317809380830624,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.1765454187989235,
|
|
"num_tokens": 26548959.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.528687858581543,
|
|
"epoch": 1.337620037064076,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004831628583857597,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.18512732535600662,
|
|
"num_tokens": 26559189.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.498491001129151,
|
|
"epoch": 1.3381816139720335,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048314761633522696,
|
|
"loss": 5.3472,
|
|
"mean_token_accuracy": 0.18605486005544664,
|
|
"num_tokens": 26570066.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.631161832809449,
|
|
"epoch": 1.338743190879991,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004831323676571934,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.18345458656549454,
|
|
"num_tokens": 26581489.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.637541675567627,
|
|
"epoch": 1.3393047677879486,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004831171123521446,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.1819349616765976,
|
|
"num_tokens": 26592051.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.584120893478394,
|
|
"epoch": 1.339866344695906,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004831018504205662,
|
|
"loss": 5.4612,
|
|
"mean_token_accuracy": 0.1835842251777649,
|
|
"num_tokens": 26602296.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.583396768569946,
|
|
"epoch": 1.3404279216038637,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048308658186294414,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.1795305609703064,
|
|
"num_tokens": 26613837.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.594451761245727,
|
|
"epoch": 1.3409894985118211,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004830713066797646,
|
|
"loss": 5.4725,
|
|
"mean_token_accuracy": 0.17832509875297547,
|
|
"num_tokens": 26624898.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.6317946434021,
|
|
"epoch": 1.3415510754197788,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048305602487151396,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.1818413183093071,
|
|
"num_tokens": 26636449.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.693394136428833,
|
|
"epoch": 1.3421126523277362,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004830407364386789,
|
|
"loss": 5.5646,
|
|
"mean_token_accuracy": 0.17916272580623627,
|
|
"num_tokens": 26649192.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.555139017105103,
|
|
"epoch": 1.342674229235694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000483025441381746,
|
|
"loss": 5.356,
|
|
"mean_token_accuracy": 0.18751205056905745,
|
|
"num_tokens": 26660005.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.651912784576416,
|
|
"epoch": 1.3432358061436513,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048301013970120235,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.18187321126461028,
|
|
"num_tokens": 26672165.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.551242303848267,
|
|
"epoch": 1.343797383051609,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048299483139753517,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.1830461472272873,
|
|
"num_tokens": 26683135.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.583597946166992,
|
|
"epoch": 1.3443589599595664,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004829795164712319,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.1882995054125786,
|
|
"num_tokens": 26693724.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.587089920043946,
|
|
"epoch": 1.3449205368675239,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048296419492278023,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.17947185039520264,
|
|
"num_tokens": 26705880.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.641551160812378,
|
|
"epoch": 1.3454821137754815,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004829488667526679,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.18154762238264083,
|
|
"num_tokens": 26716978.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.696810674667359,
|
|
"epoch": 1.3460436906834392,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048293353196138294,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.19292682260274888,
|
|
"num_tokens": 26728380.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.497617530822754,
|
|
"epoch": 1.3466052675913966,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048291819054941375,
|
|
"loss": 5.4058,
|
|
"mean_token_accuracy": 0.18837109804153443,
|
|
"num_tokens": 26739034.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.414792919158936,
|
|
"epoch": 1.347166844499354,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004829028425172487,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.192549729347229,
|
|
"num_tokens": 26750123.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.505549097061158,
|
|
"epoch": 1.3477284214073117,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048288748786537656,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.19367487877607345,
|
|
"num_tokens": 26760411.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.3477284214073117,
|
|
"eval_entropy": 5.39051130391717,
|
|
"eval_loss": 5.517776966094971,
|
|
"eval_mean_token_accuracy": 0.18610778976753564,
|
|
"eval_num_tokens": 26760411.0,
|
|
"eval_runtime": 23.8469,
|
|
"eval_samples_per_second": 1300.502,
|
|
"eval_steps_per_second": 162.579,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.585889005661011,
|
|
"epoch": 1.3482899983152694,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004828721265942861,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.18661164343357087,
|
|
"num_tokens": 26770821.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.595995330810547,
|
|
"epoch": 1.3488515752232269,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048285675870446653,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.18307780027389525,
|
|
"num_tokens": 26782099.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.658810949325561,
|
|
"epoch": 1.3494131521311843,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048284138419640724,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.17641989886760712,
|
|
"num_tokens": 26794056.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.615733098983765,
|
|
"epoch": 1.349974729039142,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004828260030705976,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.18218497782945633,
|
|
"num_tokens": 26804501.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.679863595962525,
|
|
"epoch": 1.3505363059470994,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048281061532752734,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.18045407384634018,
|
|
"num_tokens": 26814996.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.577938461303711,
|
|
"epoch": 1.351097882855057,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004827952209676866,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.18464621305465698,
|
|
"num_tokens": 26825838.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.604077005386353,
|
|
"epoch": 1.3516594597630145,
|
|
"grad_norm": 2.703125,
|
|
"learning_rate": 0.00048277981999156534,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.18549955189228057,
|
|
"num_tokens": 26836320.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.614146661758423,
|
|
"epoch": 1.3522210366709722,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048276441239965414,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18494748175144196,
|
|
"num_tokens": 26846485.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.681497287750244,
|
|
"epoch": 1.3527826135789296,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004827489981924434,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.17283745110034943,
|
|
"num_tokens": 26858554.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.571754503250122,
|
|
"epoch": 1.3533441904868873,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048273357737042393,
|
|
"loss": 5.4549,
|
|
"mean_token_accuracy": 0.18617189228534697,
|
|
"num_tokens": 26869538.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.664506721496582,
|
|
"epoch": 1.3539057673948447,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048271814993408694,
|
|
"loss": 5.5112,
|
|
"mean_token_accuracy": 0.17817587852478028,
|
|
"num_tokens": 26880284.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.616257190704346,
|
|
"epoch": 1.3544673443028024,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004827027158839233,
|
|
"loss": 5.5047,
|
|
"mean_token_accuracy": 0.17257015258073807,
|
|
"num_tokens": 26893180.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.548746871948242,
|
|
"epoch": 1.3550289212107598,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004826872752204248,
|
|
"loss": 5.3554,
|
|
"mean_token_accuracy": 0.18580685704946517,
|
|
"num_tokens": 26904213.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.608549880981445,
|
|
"epoch": 1.3555904981187172,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048267182794408276,
|
|
"loss": 5.4401,
|
|
"mean_token_accuracy": 0.18471905142068862,
|
|
"num_tokens": 26915566.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.546133279800415,
|
|
"epoch": 1.356152075026675,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004826563740553893,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.18516785800457,
|
|
"num_tokens": 26926253.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.558069133758545,
|
|
"epoch": 1.3567136519346326,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004826409135548363,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.19310805201530457,
|
|
"num_tokens": 26936723.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.556235599517822,
|
|
"epoch": 1.35727522884259,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004826254464429161,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.18442782312631606,
|
|
"num_tokens": 26947551.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.616001319885254,
|
|
"epoch": 1.3578368057505474,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048260997272012114,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.18708106130361557,
|
|
"num_tokens": 26959969.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.657316637039185,
|
|
"epoch": 1.358398382658505,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004825944923869441,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.17576923370361328,
|
|
"num_tokens": 26972511.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.69024691581726,
|
|
"epoch": 1.3589599595664628,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048257900544387795,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.17117462754249574,
|
|
"num_tokens": 26983827.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.675602579116822,
|
|
"epoch": 1.3595215364744202,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048256351189141574,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.17278515696525573,
|
|
"num_tokens": 26994668.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.536751079559326,
|
|
"epoch": 1.3600831133823776,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004825480117300508,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.1889660745859146,
|
|
"num_tokens": 27006313.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.6052240371704105,
|
|
"epoch": 1.3606446902903353,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048253250496027675,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.1805146485567093,
|
|
"num_tokens": 27017628.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.594814682006836,
|
|
"epoch": 1.3612062671982927,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048251699158258714,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.18400559276342393,
|
|
"num_tokens": 27028303.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.6249229431152346,
|
|
"epoch": 1.3617678441062504,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004825014715974761,
|
|
"loss": 5.476,
|
|
"mean_token_accuracy": 0.1764664202928543,
|
|
"num_tokens": 27039307.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.513945722579956,
|
|
"epoch": 1.3623294210142078,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048248594500543767,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.17984763532876968,
|
|
"num_tokens": 27049271.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.4565061092376705,
|
|
"epoch": 1.3628909979221655,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048247041180696633,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.19081157594919204,
|
|
"num_tokens": 27059510.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.720576190948487,
|
|
"epoch": 1.363452574830123,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004824548720025566,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.17137646228075026,
|
|
"num_tokens": 27071685.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.548969650268555,
|
|
"epoch": 1.3640141517380806,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.0004824393255927033,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.1827815443277359,
|
|
"num_tokens": 27081957.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.518862724304199,
|
|
"epoch": 1.364575728646038,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00048242377257790145,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.1864596351981163,
|
|
"num_tokens": 27091609.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.599923801422119,
|
|
"epoch": 1.3651373055539957,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00048240821295864614,
|
|
"loss": 5.5383,
|
|
"mean_token_accuracy": 0.17447945475578308,
|
|
"num_tokens": 27103889.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.646655035018921,
|
|
"epoch": 1.3656988824619531,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000482392646735433,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.1828615665435791,
|
|
"num_tokens": 27114186.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.49462103843689,
|
|
"epoch": 1.3662604593699106,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004823770739087574,
|
|
"loss": 5.3325,
|
|
"mean_token_accuracy": 0.18546338081359864,
|
|
"num_tokens": 27124677.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.670459222793579,
|
|
"epoch": 1.3668220362778682,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004823614944791154,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.18253377974033355,
|
|
"num_tokens": 27134873.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.5904539108276365,
|
|
"epoch": 1.367383613185826,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004823459084470031,
|
|
"loss": 5.5075,
|
|
"mean_token_accuracy": 0.1761165589094162,
|
|
"num_tokens": 27146107.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.535397148132324,
|
|
"epoch": 1.3679451900937833,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004823303158129165,
|
|
"loss": 5.3799,
|
|
"mean_token_accuracy": 0.18978891968727113,
|
|
"num_tokens": 27158821.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.575387191772461,
|
|
"epoch": 1.3685067670017408,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004823147165773523,
|
|
"loss": 5.3839,
|
|
"mean_token_accuracy": 0.18592496514320372,
|
|
"num_tokens": 27169513.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.507125425338745,
|
|
"epoch": 1.3690683439096984,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048229911074080715,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.1890491157770157,
|
|
"num_tokens": 27180059.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.5726015090942385,
|
|
"epoch": 1.369629920817656,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048228349830377787,
|
|
"loss": 5.4578,
|
|
"mean_token_accuracy": 0.1815523236989975,
|
|
"num_tokens": 27190738.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.548981714248657,
|
|
"epoch": 1.3701914977256135,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048226787926676165,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.18333657681941987,
|
|
"num_tokens": 27200664.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.538446712493896,
|
|
"epoch": 1.370753074633571,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048225225363025576,
|
|
"loss": 5.4237,
|
|
"mean_token_accuracy": 0.18574774116277695,
|
|
"num_tokens": 27211011.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.639319038391113,
|
|
"epoch": 1.3713146515415287,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048223662139475773,
|
|
"loss": 5.4822,
|
|
"mean_token_accuracy": 0.18328359127044677,
|
|
"num_tokens": 27221888.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.691953659057617,
|
|
"epoch": 1.371876228449486,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048222098256076523,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.17762732356786728,
|
|
"num_tokens": 27234671.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.477071714401245,
|
|
"epoch": 1.3724378053574438,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004822053371287763,
|
|
"loss": 5.2693,
|
|
"mean_token_accuracy": 0.19060673266649247,
|
|
"num_tokens": 27245283.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.608604431152344,
|
|
"epoch": 1.3729993822654012,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004821896850992891,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.18372732996940613,
|
|
"num_tokens": 27255056.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.660405158996582,
|
|
"epoch": 1.3735609591733589,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000482174026472802,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.17669060528278352,
|
|
"num_tokens": 27266893.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.56651930809021,
|
|
"epoch": 1.3741225360813163,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004821583612498135,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.17957343012094498,
|
|
"num_tokens": 27279504.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.694083499908447,
|
|
"epoch": 1.374684112989274,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048214268943082246,
|
|
"loss": 5.5423,
|
|
"mean_token_accuracy": 0.17686755657196046,
|
|
"num_tokens": 27290525.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.640714073181153,
|
|
"epoch": 1.3752456898972314,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004821270110163278,
|
|
"loss": 5.4022,
|
|
"mean_token_accuracy": 0.1799149051308632,
|
|
"num_tokens": 27301404.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.552162408828735,
|
|
"epoch": 1.375807266805189,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004821113260068288,
|
|
"loss": 5.3482,
|
|
"mean_token_accuracy": 0.1823091983795166,
|
|
"num_tokens": 27312635.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.492704629898071,
|
|
"epoch": 1.3763688437131465,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004820956344028249,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.18797036856412888,
|
|
"num_tokens": 27322485.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.623558902740479,
|
|
"epoch": 1.376930420621104,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048207993620481566,
|
|
"loss": 5.4508,
|
|
"mean_token_accuracy": 0.1802106872200966,
|
|
"num_tokens": 27332568.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.713538074493409,
|
|
"epoch": 1.3774919975290616,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004820642314133009,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.17607314139604568,
|
|
"num_tokens": 27343058.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.588006114959716,
|
|
"epoch": 1.3780535744370193,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048204852002878073,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.18973888009786605,
|
|
"num_tokens": 27355316.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.467084646224976,
|
|
"epoch": 1.3786151513449767,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048203280205175544,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.18872342258691788,
|
|
"num_tokens": 27366098.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.489220476150512,
|
|
"epoch": 1.3791767282529341,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004820170774827253,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.18969447612762452,
|
|
"num_tokens": 27376923.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.598177337646485,
|
|
"epoch": 1.3797383051608918,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004820013463221912,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.18417630940675736,
|
|
"num_tokens": 27386789.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.597951221466064,
|
|
"epoch": 1.3802998820688495,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.000481985608570654,
|
|
"loss": 5.4127,
|
|
"mean_token_accuracy": 0.18007537573575974,
|
|
"num_tokens": 27399241.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.542728328704834,
|
|
"epoch": 1.380861458976807,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004819698642286147,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.19170859605073928,
|
|
"num_tokens": 27409123.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.500060939788819,
|
|
"epoch": 1.3814230358847643,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048195411329657464,
|
|
"loss": 5.3496,
|
|
"mean_token_accuracy": 0.18411895185708999,
|
|
"num_tokens": 27419920.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.427645587921143,
|
|
"epoch": 1.381984612792722,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004819383557750353,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19216761291027068,
|
|
"num_tokens": 27429552.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.635105800628662,
|
|
"epoch": 1.3825461897006794,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048192259166449845,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.18053290694952012,
|
|
"num_tokens": 27440404.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.615930509567261,
|
|
"epoch": 1.383107766608637,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00048190682096546606,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.18077426850795747,
|
|
"num_tokens": 27452231.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.585415554046631,
|
|
"epoch": 1.3836693435165945,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048189104367844034,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18434198647737504,
|
|
"num_tokens": 27463658.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.574256515502929,
|
|
"epoch": 1.3842309204245522,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00048187525980392343,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.17794695645570754,
|
|
"num_tokens": 27475403.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.672405576705932,
|
|
"epoch": 1.3847924973325096,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000481859469342418,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.1766283169388771,
|
|
"num_tokens": 27487056.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.549100732803344,
|
|
"epoch": 1.3853540742404673,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004818436722944269,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18668753653764725,
|
|
"num_tokens": 27498659.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.691966390609741,
|
|
"epoch": 1.3859156511484247,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004818278686604531,
|
|
"loss": 5.5122,
|
|
"mean_token_accuracy": 0.18052745908498763,
|
|
"num_tokens": 27510577.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.5583571434021,
|
|
"epoch": 1.3864772280563824,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004818120584409996,
|
|
"loss": 5.4212,
|
|
"mean_token_accuracy": 0.18866800814867019,
|
|
"num_tokens": 27521441.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.573046255111694,
|
|
"epoch": 1.3870388049643398,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004817962416365701,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.19001773744821548,
|
|
"num_tokens": 27533443.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.5686070919036865,
|
|
"epoch": 1.3876003818722973,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048178041824766796,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.18802445083856584,
|
|
"num_tokens": 27543872.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.714857864379883,
|
|
"epoch": 1.388161958780255,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004817645882747971,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.17120420187711716,
|
|
"num_tokens": 27556556.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.645841360092163,
|
|
"epoch": 1.3887235356882126,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004817487517184616,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.17679672241210936,
|
|
"num_tokens": 27570739.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.628003692626953,
|
|
"epoch": 1.38928511259617,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004817329085791657,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.17694754153490067,
|
|
"num_tokens": 27582438.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.618165731430054,
|
|
"epoch": 1.3898466895041275,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004817170588574138,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.18481045812368393,
|
|
"num_tokens": 27593854.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.606811141967773,
|
|
"epoch": 1.3904082664120851,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004817012025537105,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.18541331291198732,
|
|
"num_tokens": 27604459.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.681241035461426,
|
|
"epoch": 1.3909698433200428,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004816853396685608,
|
|
"loss": 5.5866,
|
|
"mean_token_accuracy": 0.1704036697745323,
|
|
"num_tokens": 27617901.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.669640827178955,
|
|
"epoch": 1.3915314202280002,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048166947020246973,
|
|
"loss": 5.5058,
|
|
"mean_token_accuracy": 0.17653364390134813,
|
|
"num_tokens": 27628574.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.592009353637695,
|
|
"epoch": 1.3920929971359577,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00048165359415594245,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.18184642344713212,
|
|
"num_tokens": 27639195.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.459141445159912,
|
|
"epoch": 1.3926545740439153,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048163771152948473,
|
|
"loss": 5.3174,
|
|
"mean_token_accuracy": 0.19453292191028596,
|
|
"num_tokens": 27649898.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.58292441368103,
|
|
"epoch": 1.3932161509518728,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000481621822323602,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.1743151769042015,
|
|
"num_tokens": 27663617.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.497613096237183,
|
|
"epoch": 1.3937777278598305,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004816059265388004,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.1900067836046219,
|
|
"num_tokens": 27674823.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.607364845275879,
|
|
"epoch": 1.394339304767788,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048159002417558596,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.1809147208929062,
|
|
"num_tokens": 27686483.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.601730918884277,
|
|
"epoch": 1.3949008816757456,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004815741152344651,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.1915634498000145,
|
|
"num_tokens": 27697081.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.526267576217651,
|
|
"epoch": 1.395462458583703,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004815581997159442,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.18377683460712432,
|
|
"num_tokens": 27706710.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.5769476890563965,
|
|
"epoch": 1.3960240354916607,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00048154227762053003,
|
|
"loss": 5.5021,
|
|
"mean_token_accuracy": 0.17679376453161239,
|
|
"num_tokens": 27718213.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.579756546020508,
|
|
"epoch": 1.396585612399618,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004815263489487298,
|
|
"loss": 5.3998,
|
|
"mean_token_accuracy": 0.1837504878640175,
|
|
"num_tokens": 27729064.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.629360055923462,
|
|
"epoch": 1.3971471893075758,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004815104137010504,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.18515477627515792,
|
|
"num_tokens": 27740121.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.534917688369751,
|
|
"epoch": 1.3977087662155332,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004814944718779993,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.18807477355003357,
|
|
"num_tokens": 27751597.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.459851551055908,
|
|
"epoch": 1.3982703431234906,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004814785234800843,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.1866594061255455,
|
|
"num_tokens": 27761539.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.598157501220703,
|
|
"epoch": 1.3988319200314483,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048146256850781287,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.1821627363562584,
|
|
"num_tokens": 27772904.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.630623292922974,
|
|
"epoch": 1.399393496939406,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048144660696169327,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.1874600127339363,
|
|
"num_tokens": 27783706.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.510272884368897,
|
|
"epoch": 1.3999550738473634,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048143063884223365,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.1798023283481598,
|
|
"num_tokens": 27794503.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.4936628341674805,
|
|
"epoch": 1.4005166507553208,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004814146641499424,
|
|
"loss": 5.4062,
|
|
"mean_token_accuracy": 0.1811736837029457,
|
|
"num_tokens": 27805952.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.605747509002685,
|
|
"epoch": 1.4010782276632785,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048139868288532816,
|
|
"loss": 5.3941,
|
|
"mean_token_accuracy": 0.18283620476722717,
|
|
"num_tokens": 27817530.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.593621015548706,
|
|
"epoch": 1.4016398045712362,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004813826950488998,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.17434990406036377,
|
|
"num_tokens": 27829932.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.604751110076904,
|
|
"epoch": 1.4022013814791936,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048136670064116645,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.18359439373016356,
|
|
"num_tokens": 27840993.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.557286357879638,
|
|
"epoch": 1.402762958387151,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004813506996626373,
|
|
"loss": 5.3652,
|
|
"mean_token_accuracy": 0.18471413999795913,
|
|
"num_tokens": 27852727.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.565823936462403,
|
|
"epoch": 1.4033245352951087,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004813346921138218,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.17986350804567336,
|
|
"num_tokens": 27865183.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.550085353851318,
|
|
"epoch": 1.4038861122030661,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004813186779952297,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19148174673318863,
|
|
"num_tokens": 27877266.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.596786975860596,
|
|
"epoch": 1.4044476891110238,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004813026573073708,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.18038903623819352,
|
|
"num_tokens": 27888863.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.537422180175781,
|
|
"epoch": 1.4050092660189812,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004812866300507554,
|
|
"loss": 5.3637,
|
|
"mean_token_accuracy": 0.18719003051519395,
|
|
"num_tokens": 27900443.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.550710725784302,
|
|
"epoch": 1.405570842926939,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004812705962258936,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.1886860102415085,
|
|
"num_tokens": 27911241.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.582467174530029,
|
|
"epoch": 1.4061324198348963,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004812545558332961,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.18707015961408616,
|
|
"num_tokens": 27922171.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.458000421524048,
|
|
"epoch": 1.406693996742854,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048123850887347346,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.18714414536952972,
|
|
"num_tokens": 27933627.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.404601907730102,
|
|
"epoch": 1.4072555736508114,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00048122245534693676,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.18462032079696655,
|
|
"num_tokens": 27943585.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.600050687789917,
|
|
"epoch": 1.407817150558769,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004812063952541971,
|
|
"loss": 5.43,
|
|
"mean_token_accuracy": 0.1801453173160553,
|
|
"num_tokens": 27955554.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.638791036605835,
|
|
"epoch": 1.4083787274667265,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048119032859576577,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19196965396404267,
|
|
"num_tokens": 27966150.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.475493288040161,
|
|
"epoch": 1.408940304374684,
|
|
"grad_norm": 2.5,
|
|
"learning_rate": 0.0004811742553721545,
|
|
"loss": 5.3449,
|
|
"mean_token_accuracy": 0.1895449087023735,
|
|
"num_tokens": 27977436.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.563374710083008,
|
|
"epoch": 1.4095018812826416,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.00048115817558387494,
|
|
"loss": 5.5091,
|
|
"mean_token_accuracy": 0.17576901614665985,
|
|
"num_tokens": 27988325.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.675958681106567,
|
|
"epoch": 1.4100634581905993,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004811420892314391,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.18614630699157714,
|
|
"num_tokens": 27999760.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.66615629196167,
|
|
"epoch": 1.4106250350985567,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004811259963153592,
|
|
"loss": 5.4961,
|
|
"mean_token_accuracy": 0.17564602196216583,
|
|
"num_tokens": 28011333.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.506012010574341,
|
|
"epoch": 1.4111866120065142,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004811098968361476,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.19204129576683043,
|
|
"num_tokens": 28023464.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.505196952819825,
|
|
"epoch": 1.4117481889144718,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000481093790794317,
|
|
"loss": 5.3984,
|
|
"mean_token_accuracy": 0.18188293278217316,
|
|
"num_tokens": 28034205.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.64900803565979,
|
|
"epoch": 1.4123097658224295,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004810776781903801,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.17924264967441558,
|
|
"num_tokens": 28045846.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.582494878768921,
|
|
"epoch": 1.412871342730387,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048106155902485003,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.19069852083921432,
|
|
"num_tokens": 28057365.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.5884074687957765,
|
|
"epoch": 1.4134329196383444,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004810454332982401,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.1782055303454399,
|
|
"num_tokens": 28069098.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.6157220840454105,
|
|
"epoch": 1.413994496546302,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004810293010110635,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.18021179586648942,
|
|
"num_tokens": 28080008.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.644870138168335,
|
|
"epoch": 1.4145560734542595,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004810131621638342,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.18138028532266617,
|
|
"num_tokens": 28091657.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.489432239532471,
|
|
"epoch": 1.4151176503622171,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048099701675706583,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1844567060470581,
|
|
"num_tokens": 28102586.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.538968896865844,
|
|
"epoch": 1.4156792272701746,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004809808647912725,
|
|
"loss": 5.4457,
|
|
"mean_token_accuracy": 0.18205047249794007,
|
|
"num_tokens": 28113066.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.594004487991333,
|
|
"epoch": 1.4162408041781323,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004809647062669686,
|
|
"loss": 5.4242,
|
|
"mean_token_accuracy": 0.17429809868335724,
|
|
"num_tokens": 28124814.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.6967226505279545,
|
|
"epoch": 1.4168023810860897,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048094854118466856,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.1748545452952385,
|
|
"num_tokens": 28138009.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.459004163742065,
|
|
"epoch": 1.4173639579940474,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00048093236954488715,
|
|
"loss": 5.3701,
|
|
"mean_token_accuracy": 0.18421735167503356,
|
|
"num_tokens": 28149222.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.533692359924316,
|
|
"epoch": 1.4179255349020048,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004809161913481392,
|
|
"loss": 5.4254,
|
|
"mean_token_accuracy": 0.17891663387417794,
|
|
"num_tokens": 28161323.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.585741090774536,
|
|
"epoch": 1.4184871118099625,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048090000659493985,
|
|
"loss": 5.4126,
|
|
"mean_token_accuracy": 0.17910400331020354,
|
|
"num_tokens": 28173242.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.551761054992676,
|
|
"epoch": 1.41904868871792,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048088381528580445,
|
|
"loss": 5.3722,
|
|
"mean_token_accuracy": 0.1862117439508438,
|
|
"num_tokens": 28183927.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.576290416717529,
|
|
"epoch": 1.4196102656258773,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048086761742124846,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.18693946152925492,
|
|
"num_tokens": 28194375.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.603935098648071,
|
|
"epoch": 1.420171842533835,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048085141300178774,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.1831165999174118,
|
|
"num_tokens": 28206492.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.578638935089112,
|
|
"epoch": 1.4207334194417927,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048083520202793815,
|
|
"loss": 5.4615,
|
|
"mean_token_accuracy": 0.1781555250287056,
|
|
"num_tokens": 28217795.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.53762903213501,
|
|
"epoch": 1.42129499634975,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004808189845002159,
|
|
"loss": 5.403,
|
|
"mean_token_accuracy": 0.18676299452781678,
|
|
"num_tokens": 28228796.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.599796390533447,
|
|
"epoch": 1.4218565732577075,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004808027604191374,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.18361762017011643,
|
|
"num_tokens": 28238873.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.548507118225098,
|
|
"epoch": 1.4224181501656652,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048078652978521914,
|
|
"loss": 5.2394,
|
|
"mean_token_accuracy": 0.19392431974411012,
|
|
"num_tokens": 28249832.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.560743999481201,
|
|
"epoch": 1.4229797270736229,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048077029259897797,
|
|
"loss": 5.4422,
|
|
"mean_token_accuracy": 0.1773339942097664,
|
|
"num_tokens": 28261532.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.623722648620605,
|
|
"epoch": 1.4235413039815803,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048075404886093094,
|
|
"loss": 5.4669,
|
|
"mean_token_accuracy": 0.18488938212394715,
|
|
"num_tokens": 28272008.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.580114412307739,
|
|
"epoch": 1.4241028808895377,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.00048073779857159504,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.1829659014940262,
|
|
"num_tokens": 28283239.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.627001237869263,
|
|
"epoch": 1.4246644577974954,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 0.000480721541731488,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.1776173621416092,
|
|
"num_tokens": 28293597.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.566064929962158,
|
|
"epoch": 1.4252260347054528,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048070527834112727,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18889106959104537,
|
|
"num_tokens": 28305124.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.501169729232788,
|
|
"epoch": 1.4257876116134105,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004806890084010306,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.18639229387044906,
|
|
"num_tokens": 28315875.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.5809132099151615,
|
|
"epoch": 1.426349188521368,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048067273191171615,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.1830009788274765,
|
|
"num_tokens": 28327705.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.566604852676392,
|
|
"epoch": 1.4269107654293256,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004806564488737022,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.18997279107570647,
|
|
"num_tokens": 28338300.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.512650871276856,
|
|
"epoch": 1.427472342337283,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004806401592875071,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.18753411024808883,
|
|
"num_tokens": 28348485.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.51179986000061,
|
|
"epoch": 1.4280339192452407,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048062386315364964,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.18667262494564058,
|
|
"num_tokens": 28359118.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.514178895950318,
|
|
"epoch": 1.4285954961531981,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004806075604726485,
|
|
"loss": 5.3801,
|
|
"mean_token_accuracy": 0.18970838636159898,
|
|
"num_tokens": 28369608.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.607930850982666,
|
|
"epoch": 1.4291570730611558,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048059125124502304,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.18878730535507202,
|
|
"num_tokens": 28379709.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.545528411865234,
|
|
"epoch": 1.4297186499691132,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004805749354712924,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.18101436644792557,
|
|
"num_tokens": 28390758.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.742712688446045,
|
|
"epoch": 1.4302802268770707,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.000480558613151976,
|
|
"loss": 5.6574,
|
|
"mean_token_accuracy": 0.17389913350343705,
|
|
"num_tokens": 28403485.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.645611763000488,
|
|
"epoch": 1.4308418037850283,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004805422842875936,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.1823989912867546,
|
|
"num_tokens": 28413627.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.550973606109619,
|
|
"epoch": 1.431403380692986,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048052594887866524,
|
|
"loss": 5.3386,
|
|
"mean_token_accuracy": 0.19057314544916154,
|
|
"num_tokens": 28424202.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.4680736541748045,
|
|
"epoch": 1.4319649576009434,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048050960692571086,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.1896070957183838,
|
|
"num_tokens": 28435136.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.54513635635376,
|
|
"epoch": 1.4325265345089009,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.000480493258429251,
|
|
"loss": 5.3309,
|
|
"mean_token_accuracy": 0.18513444066047668,
|
|
"num_tokens": 28444915.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.577826070785522,
|
|
"epoch": 1.4330881114168585,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000480476903389806,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.1751777023077011,
|
|
"num_tokens": 28458295.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.6165436744689945,
|
|
"epoch": 1.4336496883248162,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004804605418078968,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.18563839048147202,
|
|
"num_tokens": 28469587.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.664580059051514,
|
|
"epoch": 1.4342112652327736,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00048044417368404426,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.17818004339933396,
|
|
"num_tokens": 28481498.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.607347679138184,
|
|
"epoch": 1.434772842140731,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00048042779901876946,
|
|
"loss": 5.5759,
|
|
"mean_token_accuracy": 0.17765217572450637,
|
|
"num_tokens": 28492626.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.659904527664184,
|
|
"epoch": 1.4353344190486887,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004804114178125939,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.18245236277580262,
|
|
"num_tokens": 28503882.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.616180086135865,
|
|
"epoch": 1.4358959959566462,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004803950300660391,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.19049710035324097,
|
|
"num_tokens": 28514786.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.525311088562011,
|
|
"epoch": 1.4364575728646038,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004803786357796269,
|
|
"loss": 5.4004,
|
|
"mean_token_accuracy": 0.18802606612443923,
|
|
"num_tokens": 28526045.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.606454467773437,
|
|
"epoch": 1.4370191497725613,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.00048036223495387934,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.17972600758075713,
|
|
"num_tokens": 28536773.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.615086889266967,
|
|
"epoch": 1.437580726680519,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004803458275893185,
|
|
"loss": 5.3599,
|
|
"mean_token_accuracy": 0.18374863266944885,
|
|
"num_tokens": 28548099.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.573108816146851,
|
|
"epoch": 1.4381423035884764,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004803294136864669,
|
|
"loss": 5.3951,
|
|
"mean_token_accuracy": 0.18625718504190444,
|
|
"num_tokens": 28559372.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.552915954589844,
|
|
"epoch": 1.438703880496434,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048031299324584716,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.18285591900348663,
|
|
"num_tokens": 28570106.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.564010381698608,
|
|
"epoch": 1.4392654574043915,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000480296566267982,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.18596163988113404,
|
|
"num_tokens": 28582417.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.62980899810791,
|
|
"epoch": 1.4398270343123492,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004802801327533947,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.17971126586198807,
|
|
"num_tokens": 28594341.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.581615734100342,
|
|
"epoch": 1.4403886112203066,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048026369270260814,
|
|
"loss": 5.4343,
|
|
"mean_token_accuracy": 0.18210468143224717,
|
|
"num_tokens": 28605580.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.654065465927124,
|
|
"epoch": 1.440950188128264,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004802472461161462,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.17722779512405396,
|
|
"num_tokens": 28617779.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.627855682373047,
|
|
"epoch": 1.4415117650362217,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004802307929945322,
|
|
"loss": 5.4474,
|
|
"mean_token_accuracy": 0.17789941430091857,
|
|
"num_tokens": 28629714.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.60779218673706,
|
|
"epoch": 1.4420733419441794,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 0.00048021433333829015,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.17929194271564483,
|
|
"num_tokens": 28641381.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.610367679595948,
|
|
"epoch": 1.4426349188521368,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048019786714794424,
|
|
"loss": 5.4681,
|
|
"mean_token_accuracy": 0.18213070929050446,
|
|
"num_tokens": 28653650.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.5697673797607425,
|
|
"epoch": 1.4431964957600942,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004801813944240186,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.18528765738010405,
|
|
"num_tokens": 28665252.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.519718074798584,
|
|
"epoch": 1.443758072668052,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004801649151670378,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.18642260879278183,
|
|
"num_tokens": 28677072.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.525624370574951,
|
|
"epoch": 1.4443196495760096,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004801484293775265,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.18166067749261855,
|
|
"num_tokens": 28688767.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.686496543884277,
|
|
"epoch": 1.444881226483967,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004801319370560097,
|
|
"loss": 5.6045,
|
|
"mean_token_accuracy": 0.18102736175060272,
|
|
"num_tokens": 28699773.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.667397832870483,
|
|
"epoch": 1.4454428033919244,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004801154382030124,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.18244498819112778,
|
|
"num_tokens": 28710971.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.560537624359131,
|
|
"epoch": 1.446004380299882,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00048009893281906004,
|
|
"loss": 5.341,
|
|
"mean_token_accuracy": 0.18899628818035125,
|
|
"num_tokens": 28721544.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.587601232528686,
|
|
"epoch": 1.4465659572078395,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048008242090467803,
|
|
"loss": 5.5606,
|
|
"mean_token_accuracy": 0.18092085123062135,
|
|
"num_tokens": 28733790.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.6851777076721195,
|
|
"epoch": 1.4471275341157972,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004800659024603923,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.1836370751261711,
|
|
"num_tokens": 28745218.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.650299787521362,
|
|
"epoch": 1.4476891110237546,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048004937748672864,
|
|
"loss": 5.4987,
|
|
"mean_token_accuracy": 0.17594158053398132,
|
|
"num_tokens": 28758061.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.520237255096435,
|
|
"epoch": 1.4482506879317123,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048003284598421327,
|
|
"loss": 5.3305,
|
|
"mean_token_accuracy": 0.19157976657152176,
|
|
"num_tokens": 28770037.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.609307479858399,
|
|
"epoch": 1.4488122648396697,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004800163079533726,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.18064249604940413,
|
|
"num_tokens": 28781052.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.5277965545654295,
|
|
"epoch": 1.4493738417476274,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004799997633947332,
|
|
"loss": 5.3629,
|
|
"mean_token_accuracy": 0.17652314752340317,
|
|
"num_tokens": 28791225.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.645425701141358,
|
|
"epoch": 1.4499354186555848,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00047998321230882174,
|
|
"loss": 5.4006,
|
|
"mean_token_accuracy": 0.1831412523984909,
|
|
"num_tokens": 28803022.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.551205062866211,
|
|
"epoch": 1.4504969955635425,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047996665469616536,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.18525278866291045,
|
|
"num_tokens": 28813789.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.6087347030639645,
|
|
"epoch": 1.4510585724715,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047995009055729114,
|
|
"loss": 5.4385,
|
|
"mean_token_accuracy": 0.18435774594545365,
|
|
"num_tokens": 28825015.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.705796241760254,
|
|
"epoch": 1.4516201493794574,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004799335198927266,
|
|
"loss": 5.5225,
|
|
"mean_token_accuracy": 0.17908140271902084,
|
|
"num_tokens": 28835852.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.5477447509765625,
|
|
"epoch": 1.452181726287415,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004799169427029993,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.1820475220680237,
|
|
"num_tokens": 28846684.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.595305013656616,
|
|
"epoch": 1.4527433031953727,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047990035898863706,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.18087156862020493,
|
|
"num_tokens": 28857402.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.547384738922119,
|
|
"epoch": 1.4533048801033301,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004798837687501679,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.1916884481906891,
|
|
"num_tokens": 28867866.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.515274333953857,
|
|
"epoch": 1.4538664570112876,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004798671719881201,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.1827548548579216,
|
|
"num_tokens": 28878102.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.681725740432739,
|
|
"epoch": 1.4544280339192452,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004798505687030221,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.1843093752861023,
|
|
"num_tokens": 28888981.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.5509264945983885,
|
|
"epoch": 1.454989610827203,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004798339588954025,
|
|
"loss": 5.3635,
|
|
"mean_token_accuracy": 0.18519885689020157,
|
|
"num_tokens": 28899733.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.49158673286438,
|
|
"epoch": 1.4555511877351603,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004798173425657903,
|
|
"loss": 5.3517,
|
|
"mean_token_accuracy": 0.18028103560209274,
|
|
"num_tokens": 28910701.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.645925426483155,
|
|
"epoch": 1.4561127646431178,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004798007197147144,
|
|
"loss": 5.4449,
|
|
"mean_token_accuracy": 0.1780916452407837,
|
|
"num_tokens": 28922627.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.60829496383667,
|
|
"epoch": 1.4566743415510754,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004797840903427042,
|
|
"loss": 5.4739,
|
|
"mean_token_accuracy": 0.18121501952409744,
|
|
"num_tokens": 28933292.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.497872447967529,
|
|
"epoch": 1.4572359184590329,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047976745445028906,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.18306667655706405,
|
|
"num_tokens": 28943898.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.5769209384918215,
|
|
"epoch": 1.4577974953669905,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047975081203799883,
|
|
"loss": 5.4499,
|
|
"mean_token_accuracy": 0.18102643638849258,
|
|
"num_tokens": 28955248.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.570764493942261,
|
|
"epoch": 1.458359072274948,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047973416310636327,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.19002750068902968,
|
|
"num_tokens": 28966905.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.620080184936524,
|
|
"epoch": 1.4589206491829056,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004797175076559126,
|
|
"loss": 5.4682,
|
|
"mean_token_accuracy": 0.1806783229112625,
|
|
"num_tokens": 28978515.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.560663747787475,
|
|
"epoch": 1.459482226090863,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047970084568717703,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.17838563323020934,
|
|
"num_tokens": 28990185.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.599980306625366,
|
|
"epoch": 1.4600438029988208,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004796841772006872,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.18105361312627793,
|
|
"num_tokens": 29000779.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.6843986988067625,
|
|
"epoch": 1.4606053799067782,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047966750219697376,
|
|
"loss": 5.5347,
|
|
"mean_token_accuracy": 0.17988489270210267,
|
|
"num_tokens": 29012066.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.745591259002685,
|
|
"epoch": 1.4611669568147359,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004796508206765677,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.17552620619535447,
|
|
"num_tokens": 29023416.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.553283214569092,
|
|
"epoch": 1.4617285337226933,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047963413264000005,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.18277395963668824,
|
|
"num_tokens": 29034469.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.559629774093628,
|
|
"epoch": 1.4622901106306507,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004796174380878023,
|
|
"loss": 5.3611,
|
|
"mean_token_accuracy": 0.1778925836086273,
|
|
"num_tokens": 29045306.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.487657308578491,
|
|
"epoch": 1.4628516875386084,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000479600737020506,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.1851709872484207,
|
|
"num_tokens": 29057114.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.57438325881958,
|
|
"epoch": 1.463413264446566,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004795840294386429,
|
|
"loss": 5.3337,
|
|
"mean_token_accuracy": 0.18038376569747924,
|
|
"num_tokens": 29067250.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.564788913726806,
|
|
"epoch": 1.4639748413545235,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047956731534274483,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.18642545044422149,
|
|
"num_tokens": 29078582.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.575995445251465,
|
|
"epoch": 1.464536418262481,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047955059473334425,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.18693907260894777,
|
|
"num_tokens": 29090113.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.533796167373657,
|
|
"epoch": 1.4650979951704386,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004795338676109733,
|
|
"loss": 5.3806,
|
|
"mean_token_accuracy": 0.1860339656472206,
|
|
"num_tokens": 29101117.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.621780157089233,
|
|
"epoch": 1.4656595720783963,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004795171339761647,
|
|
"loss": 5.4082,
|
|
"mean_token_accuracy": 0.1809263199567795,
|
|
"num_tokens": 29112569.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.634500360488891,
|
|
"epoch": 1.4662211489863537,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047950039382945126,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.18219986259937287,
|
|
"num_tokens": 29124462.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.557938528060913,
|
|
"epoch": 1.4667827258943111,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047948364717136587,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1889356017112732,
|
|
"num_tokens": 29135401.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.5670287132263185,
|
|
"epoch": 1.4673443028022688,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047946689400244196,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18120479136705397,
|
|
"num_tokens": 29146601.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.547059535980225,
|
|
"epoch": 1.4679058797102262,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047945013432321284,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.1829802453517914,
|
|
"num_tokens": 29157299.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.666776466369629,
|
|
"epoch": 1.468467456618184,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047943336813421205,
|
|
"loss": 5.4829,
|
|
"mean_token_accuracy": 0.17762909531593324,
|
|
"num_tokens": 29169101.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.481520175933838,
|
|
"epoch": 1.4690290335261413,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004794165954359736,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.1871815264225006,
|
|
"num_tokens": 29181286.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.550780820846557,
|
|
"epoch": 1.469590610434099,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004793998162290315,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.18171300888061523,
|
|
"num_tokens": 29191181.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.492182970046997,
|
|
"epoch": 1.4701521873420564,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004793830305139199,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.18462287187576293,
|
|
"num_tokens": 29202426.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.50663194656372,
|
|
"epoch": 1.470713764250014,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004793662382911734,
|
|
"loss": 5.3369,
|
|
"mean_token_accuracy": 0.18438518941402435,
|
|
"num_tokens": 29212817.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.530496501922608,
|
|
"epoch": 1.4712753411579715,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004793494395613265,
|
|
"loss": 5.3671,
|
|
"mean_token_accuracy": 0.1823864459991455,
|
|
"num_tokens": 29224644.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.57873215675354,
|
|
"epoch": 1.4718369180659292,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004793326343249144,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.18212794214487077,
|
|
"num_tokens": 29236443.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.682161521911621,
|
|
"epoch": 1.4723984949738866,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004793158225824718,
|
|
"loss": 5.5248,
|
|
"mean_token_accuracy": 0.1783716708421707,
|
|
"num_tokens": 29247687.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.615197038650512,
|
|
"epoch": 1.4729600718818443,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047929900433453423,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.18009614199399948,
|
|
"num_tokens": 29259739.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.595374965667725,
|
|
"epoch": 1.4735216487898017,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047928217958163703,
|
|
"loss": 5.438,
|
|
"mean_token_accuracy": 0.1839127093553543,
|
|
"num_tokens": 29270834.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.635689115524292,
|
|
"epoch": 1.4740832256977594,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047926534832431615,
|
|
"loss": 5.4094,
|
|
"mean_token_accuracy": 0.18478089720010757,
|
|
"num_tokens": 29282291.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.599294853210449,
|
|
"epoch": 1.4746448026057168,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004792485105631073,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.18000307083129882,
|
|
"num_tokens": 29293836.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.586259174346924,
|
|
"epoch": 1.4752063795136743,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.0004792316662985467,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.1740115761756897,
|
|
"num_tokens": 29305550.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.638527822494507,
|
|
"epoch": 1.475767956421632,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047921481553117053,
|
|
"loss": 5.4507,
|
|
"mean_token_accuracy": 0.18122911155223848,
|
|
"num_tokens": 29316973.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.557552814483643,
|
|
"epoch": 1.4763295333295896,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047919795826151544,
|
|
"loss": 5.3098,
|
|
"mean_token_accuracy": 0.18607680946588517,
|
|
"num_tokens": 29327743.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.49031548500061,
|
|
"epoch": 1.476891110237547,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004791810944901183,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.1845048800110817,
|
|
"num_tokens": 29338286.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.533817529678345,
|
|
"epoch": 1.4774526871455045,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004791642242175158,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.18180398195981978,
|
|
"num_tokens": 29348877.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.502128934860229,
|
|
"epoch": 1.4780142640534621,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047914734744424517,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19405648112297058,
|
|
"num_tokens": 29360072.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.619843435287476,
|
|
"epoch": 1.4785758409614196,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047913046417084393,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.18535992205142976,
|
|
"num_tokens": 29370744.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.634754276275634,
|
|
"epoch": 1.4791374178693772,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047911357439784947,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.17686494588851928,
|
|
"num_tokens": 29381463.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.556085014343262,
|
|
"epoch": 1.4796989947773347,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047909667812579964,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.18555031716823578,
|
|
"num_tokens": 29394227.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.509426689147949,
|
|
"epoch": 1.4802605716852923,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047907977535523253,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.18667313307523728,
|
|
"num_tokens": 29404754.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.4986778736114506,
|
|
"epoch": 1.4808221485932498,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004790628660866861,
|
|
"loss": 5.3853,
|
|
"mean_token_accuracy": 0.19360616207122802,
|
|
"num_tokens": 29416161.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.5577712059021,
|
|
"epoch": 1.4813837255012074,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004790459503206989,
|
|
"loss": 5.2859,
|
|
"mean_token_accuracy": 0.19368209093809127,
|
|
"num_tokens": 29426587.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.539028596878052,
|
|
"epoch": 1.4819453024091649,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004790290280578095,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.17941263020038606,
|
|
"num_tokens": 29437488.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.616853141784668,
|
|
"epoch": 1.4825068793171226,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047901209929855675,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.1799989625811577,
|
|
"num_tokens": 29448244.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.648119735717773,
|
|
"epoch": 1.48306845622508,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004789951640434796,
|
|
"loss": 5.4988,
|
|
"mean_token_accuracy": 0.18140285611152648,
|
|
"num_tokens": 29458260.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.690827798843384,
|
|
"epoch": 1.4836300331330377,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004789782222931173,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.18036139756441116,
|
|
"num_tokens": 29470874.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.531925821304322,
|
|
"epoch": 1.484191610040995,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047896127404800935,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.17926798164844512,
|
|
"num_tokens": 29481442.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.605688428878784,
|
|
"epoch": 1.4847531869489528,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004789443193086953,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1810471698641777,
|
|
"num_tokens": 29492727.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.644903087615967,
|
|
"epoch": 1.4853147638569102,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047892735807571505,
|
|
"loss": 5.4384,
|
|
"mean_token_accuracy": 0.17480256408452988,
|
|
"num_tokens": 29502729.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.657298564910889,
|
|
"epoch": 1.4858763407648676,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004789103903496086,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.18832939714193345,
|
|
"num_tokens": 29514315.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.587027883529663,
|
|
"epoch": 1.4864379176728253,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004788934161309161,
|
|
"loss": 5.3515,
|
|
"mean_token_accuracy": 0.18364473283290864,
|
|
"num_tokens": 29526030.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.503677463531494,
|
|
"epoch": 1.486999494580783,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047887643542017836,
|
|
"loss": 5.3454,
|
|
"mean_token_accuracy": 0.18798268884420394,
|
|
"num_tokens": 29536972.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.490767574310302,
|
|
"epoch": 1.4875610714887404,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047885944821793574,
|
|
"loss": 5.4109,
|
|
"mean_token_accuracy": 0.18332449495792388,
|
|
"num_tokens": 29547325.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.6293416023254395,
|
|
"epoch": 1.4881226483966978,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047884245452472926,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.18073239028453827,
|
|
"num_tokens": 29557944.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.484776592254638,
|
|
"epoch": 1.4886842253046555,
|
|
"grad_norm": 2.65625,
|
|
"learning_rate": 0.0004788254543410999,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.19112609773874284,
|
|
"num_tokens": 29568618.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.584316444396973,
|
|
"epoch": 1.489245802212613,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047880844766758914,
|
|
"loss": 5.4227,
|
|
"mean_token_accuracy": 0.17994505316019058,
|
|
"num_tokens": 29580682.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.616189908981323,
|
|
"epoch": 1.4898073791205706,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047879143450473824,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.17949798107147216,
|
|
"num_tokens": 29592302.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.629533576965332,
|
|
"epoch": 1.490368956028528,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047877441485308917,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.17971065789461135,
|
|
"num_tokens": 29603591.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.600602912902832,
|
|
"epoch": 1.4909305329364857,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047875738871318356,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.18405317664146423,
|
|
"num_tokens": 29615542.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.668489074707031,
|
|
"epoch": 1.4914921098444431,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004787403560855637,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.19061940908432007,
|
|
"num_tokens": 29626650.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.48064341545105,
|
|
"epoch": 1.4920536867524008,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004787233169707719,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.18301322758197786,
|
|
"num_tokens": 29637135.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.5765886306762695,
|
|
"epoch": 1.4926152636603582,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004787062713693507,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.17516811937093735,
|
|
"num_tokens": 29648862.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.609694910049439,
|
|
"epoch": 1.493176840568316,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047868921928184276,
|
|
"loss": 5.4158,
|
|
"mean_token_accuracy": 0.18490570038557053,
|
|
"num_tokens": 29661015.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.670847749710083,
|
|
"epoch": 1.4937384174762733,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004786721607087911,
|
|
"loss": 5.418,
|
|
"mean_token_accuracy": 0.1746524304151535,
|
|
"num_tokens": 29673521.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.64473032951355,
|
|
"epoch": 1.494299994384231,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004786550956507389,
|
|
"loss": 5.4757,
|
|
"mean_token_accuracy": 0.18373769670724868,
|
|
"num_tokens": 29685379.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.568165349960327,
|
|
"epoch": 1.4948615712921884,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004786380241082294,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.1825851783156395,
|
|
"num_tokens": 29696372.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.567620420455933,
|
|
"epoch": 1.495423148200146,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047862094608180623,
|
|
"loss": 5.3912,
|
|
"mean_token_accuracy": 0.18340630531311036,
|
|
"num_tokens": 29707401.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.48131365776062,
|
|
"epoch": 1.4959847251081035,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.0004786038615720132,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.18499315679073333,
|
|
"num_tokens": 29717524.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.614647436141968,
|
|
"epoch": 1.496546302016061,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047858677057939427,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.17974796444177626,
|
|
"num_tokens": 29728235.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.690982151031494,
|
|
"epoch": 1.4971078789240186,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047856967310449356,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.17656076848506927,
|
|
"num_tokens": 29738800.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.620916414260864,
|
|
"epoch": 1.4976694558319763,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047855256914785556,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1813055157661438,
|
|
"num_tokens": 29750346.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.497088479995727,
|
|
"epoch": 1.4982310327399337,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047853545871002476,
|
|
"loss": 5.3548,
|
|
"mean_token_accuracy": 0.18684277683496475,
|
|
"num_tokens": 29761931.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.460876178741455,
|
|
"epoch": 1.4987926096478912,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047851834179154595,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.18669348508119582,
|
|
"num_tokens": 29773333.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.544279527664185,
|
|
"epoch": 1.4993541865558488,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004785012183929643,
|
|
"loss": 5.3269,
|
|
"mean_token_accuracy": 0.1850905790925026,
|
|
"num_tokens": 29785125.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.529273557662964,
|
|
"epoch": 1.4999157634638065,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004784840885148249,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.18850936591625214,
|
|
"num_tokens": 29796288.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.636828851699829,
|
|
"epoch": 1.500477340371764,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004784669521576732,
|
|
"loss": 5.4573,
|
|
"mean_token_accuracy": 0.17883182913064957,
|
|
"num_tokens": 29806348.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.5930558204650875,
|
|
"epoch": 1.5010389172797214,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004784498093220549,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.18432245552539825,
|
|
"num_tokens": 29816342.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.473396492004395,
|
|
"epoch": 1.501600494187679,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004784326600085157,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.18149881213903427,
|
|
"num_tokens": 29826789.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.626882028579712,
|
|
"epoch": 1.5021620710956367,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047841550421760164,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.18408977389335632,
|
|
"num_tokens": 29837633.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.619445943832398,
|
|
"epoch": 1.502723648003594,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047839834194985916,
|
|
"loss": 5.4955,
|
|
"mean_token_accuracy": 0.18224534392356873,
|
|
"num_tokens": 29848498.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.627634572982788,
|
|
"epoch": 1.5032852249115516,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004783811732058345,
|
|
"loss": 5.455,
|
|
"mean_token_accuracy": 0.17971672862768173,
|
|
"num_tokens": 29859777.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.844952917098999,
|
|
"epoch": 1.5038468018195092,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047836399798607446,
|
|
"loss": 5.6593,
|
|
"mean_token_accuracy": 0.17112620621919633,
|
|
"num_tokens": 29873373.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.592832231521607,
|
|
"epoch": 1.5044083787274667,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047834681629112583,
|
|
"loss": 5.3989,
|
|
"mean_token_accuracy": 0.18673130720853806,
|
|
"num_tokens": 29884749.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.473502445220947,
|
|
"epoch": 1.5049699556354241,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004783296281215357,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.18657406270503998,
|
|
"num_tokens": 29895059.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.477139091491699,
|
|
"epoch": 1.5055315325433818,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004783124334778513,
|
|
"loss": 5.3884,
|
|
"mean_token_accuracy": 0.17926034033298494,
|
|
"num_tokens": 29906611.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.459420680999756,
|
|
"epoch": 1.5060931094513395,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004782952323606202,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.19235621988773347,
|
|
"num_tokens": 29918179.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.639381408691406,
|
|
"epoch": 1.506654686359297,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004782780247703901,
|
|
"loss": 5.4389,
|
|
"mean_token_accuracy": 0.18190394043922425,
|
|
"num_tokens": 29929612.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.54969539642334,
|
|
"epoch": 1.5072162632672543,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004782608107077088,
|
|
"loss": 5.2928,
|
|
"mean_token_accuracy": 0.18804145306348802,
|
|
"num_tokens": 29939569.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.5273175716400145,
|
|
"epoch": 1.507777840175212,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047824359017312445,
|
|
"loss": 5.354,
|
|
"mean_token_accuracy": 0.1872493490576744,
|
|
"num_tokens": 29950344.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.557539319992065,
|
|
"epoch": 1.5083394170831697,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004782263631671854,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.18957430869340897,
|
|
"num_tokens": 29960748.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.677507734298706,
|
|
"epoch": 1.508900993991127,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047820912969044014,
|
|
"loss": 5.5385,
|
|
"mean_token_accuracy": 0.17611076384782792,
|
|
"num_tokens": 29971678.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.488413333892822,
|
|
"epoch": 1.5094625708990845,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.00047819188974343734,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.18363492488861083,
|
|
"num_tokens": 29982477.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.530311059951782,
|
|
"epoch": 1.5100241478070422,
|
|
"grad_norm": 1.9375,
|
|
"learning_rate": 0.0004781746433267259,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18701654076576232,
|
|
"num_tokens": 29994539.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.622069597244263,
|
|
"epoch": 1.5105857247149999,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047815739044085515,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.19147217273712158,
|
|
"num_tokens": 30004821.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.682716417312622,
|
|
"epoch": 1.5111473016229573,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047814013108637423,
|
|
"loss": 5.4313,
|
|
"mean_token_accuracy": 0.1764886811375618,
|
|
"num_tokens": 30016343.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.548763847351074,
|
|
"epoch": 1.5117088785309147,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047812286526383274,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.1902618557214737,
|
|
"num_tokens": 30027719.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.507595443725586,
|
|
"epoch": 1.5122704554388724,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004781055929737804,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.1939205840229988,
|
|
"num_tokens": 30037988.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.598508644104004,
|
|
"epoch": 1.51283203234683,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047808831421676724,
|
|
"loss": 5.328,
|
|
"mean_token_accuracy": 0.18871976733207702,
|
|
"num_tokens": 30049736.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.623399925231934,
|
|
"epoch": 1.5133936092547875,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004780710289933435,
|
|
"loss": 5.4576,
|
|
"mean_token_accuracy": 0.18204808980226517,
|
|
"num_tokens": 30061963.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.571766138076782,
|
|
"epoch": 1.513955186162745,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004780537373040593,
|
|
"loss": 5.3999,
|
|
"mean_token_accuracy": 0.18639519512653352,
|
|
"num_tokens": 30072256.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.496780109405518,
|
|
"epoch": 1.5145167630707026,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047803643914946537,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.18464128226041793,
|
|
"num_tokens": 30084804.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.615262269973755,
|
|
"epoch": 1.51507833997866,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004780191345301125,
|
|
"loss": 5.4139,
|
|
"mean_token_accuracy": 0.18684685677289964,
|
|
"num_tokens": 30096938.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.645437574386596,
|
|
"epoch": 1.5156399168866175,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047800182344655165,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.18051115423440933,
|
|
"num_tokens": 30108233.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.549543190002441,
|
|
"epoch": 1.5162014937945751,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000477984505899334,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.18694088608026505,
|
|
"num_tokens": 30120246.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.508117389678955,
|
|
"epoch": 1.5167630707025328,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047796718188901095,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.19182707220315934,
|
|
"num_tokens": 30131213.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.476671361923218,
|
|
"epoch": 1.5173246476104902,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047794985141613413,
|
|
"loss": 5.2901,
|
|
"mean_token_accuracy": 0.18778764307498932,
|
|
"num_tokens": 30143300.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.520823907852173,
|
|
"epoch": 1.5178862245184477,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047793251448125526,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18340995758771897,
|
|
"num_tokens": 30153794.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.582877349853516,
|
|
"epoch": 1.5184478014264053,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004779151710849265,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.18108939230442048,
|
|
"num_tokens": 30165152.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.587832307815551,
|
|
"epoch": 1.519009378334363,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004778978212276999,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.18326867520809173,
|
|
"num_tokens": 30176338.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.561186170578003,
|
|
"epoch": 1.5195709552423204,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004778804649101281,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.18043728470802306,
|
|
"num_tokens": 30187666.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.559617567062378,
|
|
"epoch": 1.5201325321502779,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004778631021327636,
|
|
"loss": 5.4465,
|
|
"mean_token_accuracy": 0.17841438353061675,
|
|
"num_tokens": 30198892.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.523867177963257,
|
|
"epoch": 1.5206941090582355,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004778457328961592,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.18063599169254302,
|
|
"num_tokens": 30210677.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.570449638366699,
|
|
"epoch": 1.5212556859661932,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.00047782835720086797,
|
|
"loss": 5.3613,
|
|
"mean_token_accuracy": 0.1874137818813324,
|
|
"num_tokens": 30221217.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.616752004623413,
|
|
"epoch": 1.5218172628741506,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004778109750474432,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.17962039709091188,
|
|
"num_tokens": 30233576.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.520001697540283,
|
|
"epoch": 1.522378839782108,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004777935864364383,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.18394121676683425,
|
|
"num_tokens": 30244787.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.580974102020264,
|
|
"epoch": 1.5229404166900657,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.000477776191368407,
|
|
"loss": 5.4152,
|
|
"mean_token_accuracy": 0.18676693439483644,
|
|
"num_tokens": 30256656.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.571436548233033,
|
|
"epoch": 1.5235019935980234,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004777587898439031,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.18291739374399185,
|
|
"num_tokens": 30267715.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.659337663650513,
|
|
"epoch": 1.5240635705059808,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047774138186348073,
|
|
"loss": 5.4472,
|
|
"mean_token_accuracy": 0.17868887335062028,
|
|
"num_tokens": 30278119.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.645622730255127,
|
|
"epoch": 1.5246251474139383,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004777239674276941,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.18278489559888839,
|
|
"num_tokens": 30289899.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.533489322662353,
|
|
"epoch": 1.525186724321896,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004777065465370977,
|
|
"loss": 5.3747,
|
|
"mean_token_accuracy": 0.18681590557098388,
|
|
"num_tokens": 30300799.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.656773328781128,
|
|
"epoch": 1.5257483012298534,
|
|
"grad_norm": 2.59375,
|
|
"learning_rate": 0.0004776891191922463,
|
|
"loss": 5.5829,
|
|
"mean_token_accuracy": 0.18063005805015564,
|
|
"num_tokens": 30312955.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.634274911880493,
|
|
"epoch": 1.5263098781378108,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004776716853936947,
|
|
"loss": 5.372,
|
|
"mean_token_accuracy": 0.1815395697951317,
|
|
"num_tokens": 30323089.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.549135303497314,
|
|
"epoch": 1.5268714550457685,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000477654245141998,
|
|
"loss": 5.3036,
|
|
"mean_token_accuracy": 0.1976869970560074,
|
|
"num_tokens": 30333926.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.458971834182739,
|
|
"epoch": 1.5274330319537262,
|
|
"grad_norm": 3.171875,
|
|
"learning_rate": 0.0004776367984377116,
|
|
"loss": 5.4169,
|
|
"mean_token_accuracy": 0.1809849038720131,
|
|
"num_tokens": 30346347.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.534375953674316,
|
|
"epoch": 1.5279946088616836,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047761934528139086,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.18235376179218293,
|
|
"num_tokens": 30357757.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.71379599571228,
|
|
"epoch": 1.528556185769641,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004776018856735916,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.18436067998409272,
|
|
"num_tokens": 30369323.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.527826738357544,
|
|
"epoch": 1.5291177626775987,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004775844196148698,
|
|
"loss": 5.2993,
|
|
"mean_token_accuracy": 0.1910747319459915,
|
|
"num_tokens": 30380335.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.4362246036529545,
|
|
"epoch": 1.5296793395855564,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047756694710578146,
|
|
"loss": 5.3025,
|
|
"mean_token_accuracy": 0.18848207741975784,
|
|
"num_tokens": 30391338.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.572575855255127,
|
|
"epoch": 1.5302409164935138,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000477549468146883,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.1783496379852295,
|
|
"num_tokens": 30402917.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.554095268249512,
|
|
"epoch": 1.5308024934014712,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004775319827387309,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.19254619628190994,
|
|
"num_tokens": 30412690.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.545942783355713,
|
|
"epoch": 1.531364070309429,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004775144908818818,
|
|
"loss": 5.4132,
|
|
"mean_token_accuracy": 0.1838074341416359,
|
|
"num_tokens": 30423020.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.664450740814209,
|
|
"epoch": 1.5319256472173866,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047749699257689296,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.17054611444473267,
|
|
"num_tokens": 30434039.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.653837823867798,
|
|
"epoch": 1.532487224125344,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004774794878243212,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.17964228689670564,
|
|
"num_tokens": 30446743.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.630296039581299,
|
|
"epoch": 1.5330488010333014,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000477461976624724,
|
|
"loss": 5.412,
|
|
"mean_token_accuracy": 0.18327481150627137,
|
|
"num_tokens": 30456969.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.495607900619507,
|
|
"epoch": 1.533610377941259,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047744445897865905,
|
|
"loss": 5.4344,
|
|
"mean_token_accuracy": 0.18025231063365937,
|
|
"num_tokens": 30467497.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.549007511138916,
|
|
"epoch": 1.5341719548492168,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.000477426934886684,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.18151224106550218,
|
|
"num_tokens": 30479428.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.621812105178833,
|
|
"epoch": 1.5347335317571742,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047740940434935677,
|
|
"loss": 5.355,
|
|
"mean_token_accuracy": 0.18507908284664154,
|
|
"num_tokens": 30490193.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.639259243011475,
|
|
"epoch": 1.5352951086651316,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004773918673672356,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18106301724910737,
|
|
"num_tokens": 30500311.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.506987237930298,
|
|
"epoch": 1.5358566855730893,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047737432394087887,
|
|
"loss": 5.3459,
|
|
"mean_token_accuracy": 0.1893410339951515,
|
|
"num_tokens": 30512485.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.551708316802978,
|
|
"epoch": 1.5364182624810467,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047735677407084525,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.18832196146249772,
|
|
"num_tokens": 30523495.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.536428737640381,
|
|
"epoch": 1.5369798393890042,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004773392177576934,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.1868458703160286,
|
|
"num_tokens": 30533964.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.4667582511901855,
|
|
"epoch": 1.5375414162969618,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004773216550019824,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19098979085683823,
|
|
"num_tokens": 30544798.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.567803573608399,
|
|
"epoch": 1.5381029932049195,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047730408580427136,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.18216052204370498,
|
|
"num_tokens": 30555991.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.576338148117065,
|
|
"epoch": 1.538664570112877,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047728651016511994,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.18803689628839493,
|
|
"num_tokens": 30566848.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.583438348770142,
|
|
"epoch": 1.5392261470208344,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047726892808508744,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.19536068588495253,
|
|
"num_tokens": 30577361.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.527146673202514,
|
|
"epoch": 1.539787723928792,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004772513395647339,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.182659113407135,
|
|
"num_tokens": 30587685.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.519160556793213,
|
|
"epoch": 1.5403493008367497,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004772337446046192,
|
|
"loss": 5.4339,
|
|
"mean_token_accuracy": 0.1862038031220436,
|
|
"num_tokens": 30599864.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.5854333400726315,
|
|
"epoch": 1.5409108777447071,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047721614320530366,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.18416963815689086,
|
|
"num_tokens": 30610885.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.586000394821167,
|
|
"epoch": 1.5414724546526646,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047719853536734764,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.1843239888548851,
|
|
"num_tokens": 30622537.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.671787595748901,
|
|
"epoch": 1.5420340315606222,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004771809210913119,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.17570507079362868,
|
|
"num_tokens": 30635045.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.568944835662842,
|
|
"epoch": 1.54259560846858,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047716330037775724,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.17635239511728287,
|
|
"num_tokens": 30645998.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.55068302154541,
|
|
"epoch": 1.5431571853765373,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004771456732272446,
|
|
"loss": 5.3977,
|
|
"mean_token_accuracy": 0.18373042047023774,
|
|
"num_tokens": 30658744.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.489163398742676,
|
|
"epoch": 1.5437187622844948,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047712803964033545,
|
|
"loss": 5.2602,
|
|
"mean_token_accuracy": 0.1900855466723442,
|
|
"num_tokens": 30669420.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.4512412548065186,
|
|
"epoch": 1.5442803391924524,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047711039961759107,
|
|
"loss": 5.335,
|
|
"mean_token_accuracy": 0.18669517934322358,
|
|
"num_tokens": 30680037.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.616386079788208,
|
|
"epoch": 1.54484191610041,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004770927531595731,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.18870414793491364,
|
|
"num_tokens": 30691650.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.559491205215454,
|
|
"epoch": 1.5454034930083675,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00047707510026684353,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.1847032904624939,
|
|
"num_tokens": 30701876.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.739843034744263,
|
|
"epoch": 1.545965069916325,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047705744093996447,
|
|
"loss": 5.6262,
|
|
"mean_token_accuracy": 0.17855965942144394,
|
|
"num_tokens": 30714484.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.555372667312622,
|
|
"epoch": 1.5465266468242826,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000477039775179498,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.17662676125764848,
|
|
"num_tokens": 30725185.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.514773416519165,
|
|
"epoch": 1.54708822373224,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047702210298600684,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.18643611371517183,
|
|
"num_tokens": 30735522.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.562571334838867,
|
|
"epoch": 1.5476498006401975,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00047700442436005356,
|
|
"loss": 5.389,
|
|
"mean_token_accuracy": 0.19160792529582976,
|
|
"num_tokens": 30746353.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.608859634399414,
|
|
"epoch": 1.5482113775481552,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000476986739302201,
|
|
"loss": 5.3659,
|
|
"mean_token_accuracy": 0.1843172013759613,
|
|
"num_tokens": 30756245.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.618811702728271,
|
|
"epoch": 1.5487729544561128,
|
|
"grad_norm": 2.84375,
|
|
"learning_rate": 0.00047696904781301233,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.18534790277481078,
|
|
"num_tokens": 30767387.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.578681230545044,
|
|
"epoch": 1.5493345313640703,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004769513498930508,
|
|
"loss": 5.4236,
|
|
"mean_token_accuracy": 0.1828296571969986,
|
|
"num_tokens": 30780140.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.555319833755493,
|
|
"epoch": 1.5498961082720277,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047693364554288,
|
|
"loss": 5.3364,
|
|
"mean_token_accuracy": 0.19212772697210312,
|
|
"num_tokens": 30791137.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.522228002548218,
|
|
"epoch": 1.5504576851799854,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047691593476306373,
|
|
"loss": 5.3417,
|
|
"mean_token_accuracy": 0.190121853351593,
|
|
"num_tokens": 30801708.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.569636869430542,
|
|
"epoch": 1.551019262087943,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004768982175541656,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.18079390674829482,
|
|
"num_tokens": 30813519.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.629148292541504,
|
|
"epoch": 1.5515808389959005,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047688049391675006,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.1836312934756279,
|
|
"num_tokens": 30823786.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.519771671295166,
|
|
"epoch": 1.552142415903858,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004768627638513813,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.18635244369506837,
|
|
"num_tokens": 30834381.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.572727918624878,
|
|
"epoch": 1.5527039928118156,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004768450273586237,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.18707990050315856,
|
|
"num_tokens": 30844865.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.636979579925537,
|
|
"epoch": 1.5532655697197733,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047682728443904223,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.18165392726659774,
|
|
"num_tokens": 30857088.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.540115737915039,
|
|
"epoch": 1.5538271466277307,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00047680953509320176,
|
|
"loss": 5.484,
|
|
"mean_token_accuracy": 0.17973973155021666,
|
|
"num_tokens": 30868320.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.576774024963379,
|
|
"epoch": 1.5543887235356881,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004767917793216674,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.18898529559373856,
|
|
"num_tokens": 30878598.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.560929822921753,
|
|
"epoch": 1.5549503004436458,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047677401712500455,
|
|
"loss": 5.3297,
|
|
"mean_token_accuracy": 0.1884268954396248,
|
|
"num_tokens": 30889254.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.585692310333252,
|
|
"epoch": 1.5555118773516035,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004767562485037787,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.1879690706729889,
|
|
"num_tokens": 30901164.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.5375837802886965,
|
|
"epoch": 1.556073454259561,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00047673847345855566,
|
|
"loss": 5.3494,
|
|
"mean_token_accuracy": 0.18473469763994216,
|
|
"num_tokens": 30911828.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.569715547561645,
|
|
"epoch": 1.5566350311675183,
|
|
"grad_norm": 1.8203125,
|
|
"learning_rate": 0.0004767206919899014,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.19223359674215318,
|
|
"num_tokens": 30922050.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.459452533721924,
|
|
"epoch": 1.557196608075476,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000476702904098382,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.18634845465421676,
|
|
"num_tokens": 30932723.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.514444160461426,
|
|
"epoch": 1.5577581849834334,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000476685109784564,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.18941372632980347,
|
|
"num_tokens": 30943699.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.556163597106933,
|
|
"epoch": 1.5583197618913909,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047666730904901377,
|
|
"loss": 5.3973,
|
|
"mean_token_accuracy": 0.18496813774108886,
|
|
"num_tokens": 30954315.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.691150426864624,
|
|
"epoch": 1.5588813387993485,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047664950189229833,
|
|
"loss": 5.567,
|
|
"mean_token_accuracy": 0.1787819743156433,
|
|
"num_tokens": 30965840.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.6656523704528805,
|
|
"epoch": 1.5594429157073062,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004766316883149845,
|
|
"loss": 5.48,
|
|
"mean_token_accuracy": 0.18360925018787383,
|
|
"num_tokens": 30977051.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.506130266189575,
|
|
"epoch": 1.5600044926152636,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047661386831763955,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.18814768642187119,
|
|
"num_tokens": 30988730.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.484588384628296,
|
|
"epoch": 1.560566069523221,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047659604190083076,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.1909736305475235,
|
|
"num_tokens": 31000571.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.489278173446655,
|
|
"epoch": 1.5611276464311787,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00047657820906512585,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.19224498122930528,
|
|
"num_tokens": 31011003.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.667296743392944,
|
|
"epoch": 1.5616892233391364,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047656036981109256,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.18647705316543578,
|
|
"num_tokens": 31022510.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.6194446086883545,
|
|
"epoch": 1.5622508002470938,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047654252413929896,
|
|
"loss": 5.4149,
|
|
"mean_token_accuracy": 0.17969024926424026,
|
|
"num_tokens": 31033149.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.622061777114868,
|
|
"epoch": 1.5628123771550513,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00047652467205031317,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.18746209889650345,
|
|
"num_tokens": 31043626.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.586842489242554,
|
|
"epoch": 1.563373954063009,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047650681354470363,
|
|
"loss": 5.4864,
|
|
"mean_token_accuracy": 0.1803497463464737,
|
|
"num_tokens": 31055083.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.562326145172119,
|
|
"epoch": 1.5639355309709666,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00047648894862303907,
|
|
"loss": 5.3452,
|
|
"mean_token_accuracy": 0.18021564185619354,
|
|
"num_tokens": 31066763.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.587143516540527,
|
|
"epoch": 1.564497107878924,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047647107728588826,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18102402687072755,
|
|
"num_tokens": 31078722.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.58194899559021,
|
|
"epoch": 1.5650586847868815,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047645319953382024,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1848975583910942,
|
|
"num_tokens": 31090207.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.6022703647613525,
|
|
"epoch": 1.5656202616948391,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047643531536740405,
|
|
"loss": 5.4736,
|
|
"mean_token_accuracy": 0.1862543821334839,
|
|
"num_tokens": 31101943.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.528139591217041,
|
|
"epoch": 1.5661818386027968,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004764174247872094,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.1763678953051567,
|
|
"num_tokens": 31115032.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.669531059265137,
|
|
"epoch": 1.5667434155107542,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047639952779380586,
|
|
"loss": 5.3808,
|
|
"mean_token_accuracy": 0.18657408356666566,
|
|
"num_tokens": 31124965.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.64387092590332,
|
|
"epoch": 1.5673049924187117,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004763816243877632,
|
|
"loss": 5.3985,
|
|
"mean_token_accuracy": 0.18488985896110535,
|
|
"num_tokens": 31136692.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.512217807769775,
|
|
"epoch": 1.5678665693266693,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004763637145696515,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.18153032958507537,
|
|
"num_tokens": 31148352.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.5299042701721195,
|
|
"epoch": 1.5684281462346268,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000476345798340041,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.18571847528219224,
|
|
"num_tokens": 31159892.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.640148782730103,
|
|
"epoch": 1.5689897231425842,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004763278756995022,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.18106967806816102,
|
|
"num_tokens": 31170087.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.448140716552734,
|
|
"epoch": 1.5695513000505419,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047630994664860576,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.1852846547961235,
|
|
"num_tokens": 31180687.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.611355400085449,
|
|
"epoch": 1.5701128769584995,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004762920111879226,
|
|
"loss": 5.4629,
|
|
"mean_token_accuracy": 0.17907507270574569,
|
|
"num_tokens": 31192513.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.592083930969238,
|
|
"epoch": 1.570674453866457,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004762740693180237,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18534110486507416,
|
|
"num_tokens": 31203432.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.597428512573242,
|
|
"epoch": 1.5712360307744144,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047625612103948035,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.19148970097303392,
|
|
"num_tokens": 31214474.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.545741558074951,
|
|
"epoch": 1.571797607682372,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004762381663528641,
|
|
"loss": 5.4135,
|
|
"mean_token_accuracy": 0.17728037983179093,
|
|
"num_tokens": 31226489.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.453382587432861,
|
|
"epoch": 1.5723591845903298,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004762202052587466,
|
|
"loss": 5.297,
|
|
"mean_token_accuracy": 0.18508078008890153,
|
|
"num_tokens": 31237568.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.557778787612915,
|
|
"epoch": 1.5729207614982872,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004762022377576996,
|
|
"loss": 5.3245,
|
|
"mean_token_accuracy": 0.19467607885599136,
|
|
"num_tokens": 31248587.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.612200021743774,
|
|
"epoch": 1.5734823384062446,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004761842638502954,
|
|
"loss": 5.4298,
|
|
"mean_token_accuracy": 0.18529433012008667,
|
|
"num_tokens": 31259513.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.606029462814331,
|
|
"epoch": 1.5740439153142023,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004761662835371062,
|
|
"loss": 5.4276,
|
|
"mean_token_accuracy": 0.1814787670969963,
|
|
"num_tokens": 31270984.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.542925596237183,
|
|
"epoch": 1.57460549222216,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004761482968187045,
|
|
"loss": 5.3705,
|
|
"mean_token_accuracy": 0.1842801973223686,
|
|
"num_tokens": 31281907.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.44752950668335,
|
|
"epoch": 1.5751670691301174,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004761303036956631,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.1854703888297081,
|
|
"num_tokens": 31292903.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.646097707748413,
|
|
"epoch": 1.5757286460380748,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004761123041685547,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.18501624464988708,
|
|
"num_tokens": 31304185.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.624408197402954,
|
|
"epoch": 1.5762902229460325,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004760942982379526,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.18286630511283875,
|
|
"num_tokens": 31314806.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.592654800415039,
|
|
"epoch": 1.5768517998539902,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047607628590443004,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.1860525518655777,
|
|
"num_tokens": 31326361.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.637340927124024,
|
|
"epoch": 1.5774133767619476,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047605826716856056,
|
|
"loss": 5.3963,
|
|
"mean_token_accuracy": 0.18398367315530778,
|
|
"num_tokens": 31336549.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.610319995880127,
|
|
"epoch": 1.577974953669905,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004760402420309178,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.18121688514947892,
|
|
"num_tokens": 31346994.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.56962480545044,
|
|
"epoch": 1.5785365305778627,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004760222104920759,
|
|
"loss": 5.4083,
|
|
"mean_token_accuracy": 0.17990054190158844,
|
|
"num_tokens": 31358449.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.651726484298706,
|
|
"epoch": 1.5790981074858201,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004760041725526088,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.18298805356025696,
|
|
"num_tokens": 31368964.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.587783527374268,
|
|
"epoch": 1.5796596843937776,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047598612821309077,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.18857402354478836,
|
|
"num_tokens": 31379388.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.5122767925262455,
|
|
"epoch": 1.5802212613017352,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004759680774740966,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.18596961796283723,
|
|
"num_tokens": 31390757.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.531841039657593,
|
|
"epoch": 1.580782838209693,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004759500203362008,
|
|
"loss": 5.378,
|
|
"mean_token_accuracy": 0.18590110838413237,
|
|
"num_tokens": 31402309.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.5952691555023195,
|
|
"epoch": 1.5813444151176503,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004759319567999785,
|
|
"loss": 5.3798,
|
|
"mean_token_accuracy": 0.18703706860542296,
|
|
"num_tokens": 31412559.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.565596246719361,
|
|
"epoch": 1.5819059920256078,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004759138868660048,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.18036144673824311,
|
|
"num_tokens": 31424982.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.549834394454956,
|
|
"epoch": 1.5824675689335654,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047589581053485494,
|
|
"loss": 5.2417,
|
|
"mean_token_accuracy": 0.1944468140602112,
|
|
"num_tokens": 31434472.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.594235038757324,
|
|
"epoch": 1.583029145841523,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047587772780710455,
|
|
"loss": 5.4831,
|
|
"mean_token_accuracy": 0.18352097570896148,
|
|
"num_tokens": 31445458.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.575129890441895,
|
|
"epoch": 1.5835907227494805,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047585963868332945,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.1931656062602997,
|
|
"num_tokens": 31455851.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.470755672454834,
|
|
"epoch": 1.584152299657438,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004758415431641055,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.18584269136190415,
|
|
"num_tokens": 31466279.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.613654279708863,
|
|
"epoch": 1.5847138765653956,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004758234412500089,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.1872558295726776,
|
|
"num_tokens": 31477933.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.622108268737793,
|
|
"epoch": 1.5852754534733533,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047580533294161616,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.18082357794046403,
|
|
"num_tokens": 31487640.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.654519844055176,
|
|
"epoch": 1.5858370303813107,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004757872182395036,
|
|
"loss": 5.3769,
|
|
"mean_token_accuracy": 0.19146449863910675,
|
|
"num_tokens": 31499059.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.6156090259552,
|
|
"epoch": 1.5863986072892682,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047576909714424823,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.1847208097577095,
|
|
"num_tokens": 31510264.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.560900497436523,
|
|
"epoch": 1.5869601841972258,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047575096965642687,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.18618983775377274,
|
|
"num_tokens": 31520873.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.575673007965088,
|
|
"epoch": 1.5875217611051835,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047573283577661684,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.18498117476701736,
|
|
"num_tokens": 31533836.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.521556377410889,
|
|
"epoch": 1.588083338013141,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.0004757146955053955,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.17946489304304122,
|
|
"num_tokens": 31545091.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.586816453933716,
|
|
"epoch": 1.5886449149210984,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047569654884334036,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.18902197927236558,
|
|
"num_tokens": 31557139.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.634674739837647,
|
|
"epoch": 1.589206491829056,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004756783957910292,
|
|
"loss": 5.4063,
|
|
"mean_token_accuracy": 0.18744733929634094,
|
|
"num_tokens": 31567928.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.512551116943359,
|
|
"epoch": 1.5897680687370135,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047566023634904015,
|
|
"loss": 5.4198,
|
|
"mean_token_accuracy": 0.18288770020008088,
|
|
"num_tokens": 31578081.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.530811214447022,
|
|
"epoch": 1.590329645644971,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004756420705179513,
|
|
"loss": 5.3291,
|
|
"mean_token_accuracy": 0.1842991217970848,
|
|
"num_tokens": 31589648.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.550155401229858,
|
|
"epoch": 1.5908912225529286,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004756238982983412,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18208742439746856,
|
|
"num_tokens": 31601085.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.620860576629639,
|
|
"epoch": 1.5914527994608862,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004756057196907883,
|
|
"loss": 5.4531,
|
|
"mean_token_accuracy": 0.18767047673463821,
|
|
"num_tokens": 31612005.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.589659309387207,
|
|
"epoch": 1.5920143763688437,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047558753469587154,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.1817870557308197,
|
|
"num_tokens": 31623427.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.652512788772583,
|
|
"epoch": 1.5925759532768011,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047556934331416986,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.17600121796131135,
|
|
"num_tokens": 31635086.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.614661931991577,
|
|
"epoch": 1.5931375301847588,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004755511455462624,
|
|
"loss": 5.3957,
|
|
"mean_token_accuracy": 0.18349264860153197,
|
|
"num_tokens": 31646707.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.471439790725708,
|
|
"epoch": 1.5936991070927164,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004755329413927287,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.1882142409682274,
|
|
"num_tokens": 31657327.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.547740030288696,
|
|
"epoch": 1.5942606840006739,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004755147308541485,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.18643341958522797,
|
|
"num_tokens": 31668075.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.600361490249634,
|
|
"epoch": 1.5948222609086313,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047549651393110145,
|
|
"loss": 5.4323,
|
|
"mean_token_accuracy": 0.1777747690677643,
|
|
"num_tokens": 31680270.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.53249306678772,
|
|
"epoch": 1.595383837816589,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047547829062416757,
|
|
"loss": 5.2807,
|
|
"mean_token_accuracy": 0.1962743505835533,
|
|
"num_tokens": 31691271.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.492960405349732,
|
|
"epoch": 1.5959454147245467,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00047546006093392726,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.18896550089120864,
|
|
"num_tokens": 31702982.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.575291585922241,
|
|
"epoch": 1.596506991632504,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004754418248609608,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.18249155580997467,
|
|
"num_tokens": 31715129.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.65076699256897,
|
|
"epoch": 1.5970685685404615,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004754235824058489,
|
|
"loss": 5.4872,
|
|
"mean_token_accuracy": 0.18293681889772415,
|
|
"num_tokens": 31726392.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.66107063293457,
|
|
"epoch": 1.5976301454484192,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004754053335691724,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.18467244654893875,
|
|
"num_tokens": 31738143.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.62922887802124,
|
|
"epoch": 1.5981917223563769,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047538707835151237,
|
|
"loss": 5.4112,
|
|
"mean_token_accuracy": 0.1845652014017105,
|
|
"num_tokens": 31748510.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.4957598686218265,
|
|
"epoch": 1.5987532992643343,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047536881675345,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.18644551187753677,
|
|
"num_tokens": 31759378.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.668358612060547,
|
|
"epoch": 1.5993148761722917,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004753505487755669,
|
|
"loss": 5.5454,
|
|
"mean_token_accuracy": 0.17448632121086122,
|
|
"num_tokens": 31771627.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.535926389694214,
|
|
"epoch": 1.5998764530802494,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047533227441844453,
|
|
"loss": 5.3184,
|
|
"mean_token_accuracy": 0.19184106290340425,
|
|
"num_tokens": 31781990.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.553094482421875,
|
|
"epoch": 1.6004380299882068,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047531399368266485,
|
|
"loss": 5.3871,
|
|
"mean_token_accuracy": 0.1838410034775734,
|
|
"num_tokens": 31792144.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.641704130172729,
|
|
"epoch": 1.6009996068961643,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004752957065688099,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.18534481078386306,
|
|
"num_tokens": 31804022.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.632123041152954,
|
|
"epoch": 1.601561183804122,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000475277413077462,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.1814056470990181,
|
|
"num_tokens": 31815108.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.519651699066162,
|
|
"epoch": 1.6021227607120796,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047525911320920363,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.18549903780221938,
|
|
"num_tokens": 31825727.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.5349212169647215,
|
|
"epoch": 1.602684337620037,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004752408069646174,
|
|
"loss": 5.3566,
|
|
"mean_token_accuracy": 0.19341488927602768,
|
|
"num_tokens": 31836168.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.662608051300049,
|
|
"epoch": 1.6032459145279945,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047522249434428623,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.17931513488292694,
|
|
"num_tokens": 31847383.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.527265453338623,
|
|
"epoch": 1.6038074914359521,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004752041753487931,
|
|
"loss": 5.3117,
|
|
"mean_token_accuracy": 0.19098853915929795,
|
|
"num_tokens": 31858679.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.520384931564331,
|
|
"epoch": 1.6043690683439098,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004751858499787215,
|
|
"loss": 5.3949,
|
|
"mean_token_accuracy": 0.18870072960853576,
|
|
"num_tokens": 31870195.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.6801121711730955,
|
|
"epoch": 1.6049306452518672,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004751675182346547,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.18531239479780198,
|
|
"num_tokens": 31881175.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.5368622779846195,
|
|
"epoch": 1.6054922221598247,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047514918011717656,
|
|
"loss": 5.3278,
|
|
"mean_token_accuracy": 0.19377165883779526,
|
|
"num_tokens": 31891199.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.701432847976685,
|
|
"epoch": 1.6060537990677823,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047513083562687085,
|
|
"loss": 5.5161,
|
|
"mean_token_accuracy": 0.1771228864789009,
|
|
"num_tokens": 31903379.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.6661840915679935,
|
|
"epoch": 1.60661537597574,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004751124847643217,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.18890753537416458,
|
|
"num_tokens": 31913958.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.473924446105957,
|
|
"epoch": 1.6071769528836974,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004750941275301135,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.18569743484258652,
|
|
"num_tokens": 31924547.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.612487554550171,
|
|
"epoch": 1.6077385297916549,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004750757639248306,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1822247549891472,
|
|
"num_tokens": 31936987.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.57131175994873,
|
|
"epoch": 1.6083001066996125,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047505739394905776,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.18619537949562073,
|
|
"num_tokens": 31948165.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.595872831344605,
|
|
"epoch": 1.6088616836075702,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047503901760338003,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.18702429234981538,
|
|
"num_tokens": 31959206.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.557771492004394,
|
|
"epoch": 1.6094232605155276,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047502063488838225,
|
|
"loss": 5.3947,
|
|
"mean_token_accuracy": 0.1868795335292816,
|
|
"num_tokens": 31970804.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.499977064132691,
|
|
"epoch": 1.609984837423485,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047500224580464994,
|
|
"loss": 5.3112,
|
|
"mean_token_accuracy": 0.18872095495462418,
|
|
"num_tokens": 31982961.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.615857934951782,
|
|
"epoch": 1.6105464143314427,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047498385035276856,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18416281193494796,
|
|
"num_tokens": 31993812.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.5501796245574955,
|
|
"epoch": 1.6111079912394002,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004749654485333238,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.1883045732975006,
|
|
"num_tokens": 32004688.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.519079160690308,
|
|
"epoch": 1.6116695681473576,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.00047494704034690163,
|
|
"loss": 5.2919,
|
|
"mean_token_accuracy": 0.1862023040652275,
|
|
"num_tokens": 32014653.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.510220050811768,
|
|
"epoch": 1.6122311450553153,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047492862579408816,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.18165194988250732,
|
|
"num_tokens": 32025638.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.449088907241821,
|
|
"epoch": 1.612792721963273,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00047491020487546966,
|
|
"loss": 5.2761,
|
|
"mean_token_accuracy": 0.19184885025024415,
|
|
"num_tokens": 32036316.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.536197519302368,
|
|
"epoch": 1.6133542988712304,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004748917775916327,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.18972133994102477,
|
|
"num_tokens": 32047355.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.549909067153931,
|
|
"epoch": 1.6139158757791878,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00047487334394316405,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.1759962260723114,
|
|
"num_tokens": 32058897.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.593755054473877,
|
|
"epoch": 1.6144774526871455,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004748549039306506,
|
|
"loss": 5.3866,
|
|
"mean_token_accuracy": 0.18582611978054048,
|
|
"num_tokens": 32069932.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.549817228317261,
|
|
"epoch": 1.6150390295951031,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004748364575546795,
|
|
"loss": 5.3176,
|
|
"mean_token_accuracy": 0.18805965632200242,
|
|
"num_tokens": 32081359.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.470241498947144,
|
|
"epoch": 1.6156006065030606,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047481800481583806,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.1871670037508011,
|
|
"num_tokens": 32093050.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.579931831359863,
|
|
"epoch": 1.616162183411018,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004747995457147139,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18260763585567474,
|
|
"num_tokens": 32104623.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.519712162017822,
|
|
"epoch": 1.6167237603189757,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047478108025189467,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17755395621061326,
|
|
"num_tokens": 32115845.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.560166120529175,
|
|
"epoch": 1.6172853372269334,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047476260842796837,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.17936341166496278,
|
|
"num_tokens": 32127066.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.57271409034729,
|
|
"epoch": 1.6178469141348908,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004747441302435231,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.1821927696466446,
|
|
"num_tokens": 32138344.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.651772689819336,
|
|
"epoch": 1.6184084910428482,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047472564569914726,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.17916069626808168,
|
|
"num_tokens": 32149054.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.557945919036865,
|
|
"epoch": 1.618970067950806,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047470715479542945,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.17931825965642928,
|
|
"num_tokens": 32160385.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.602846002578735,
|
|
"epoch": 1.6195316448587636,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004746886575329584,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.1790321499109268,
|
|
"num_tokens": 32171856.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.558175992965698,
|
|
"epoch": 1.620093221766721,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047467015391232305,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.18015896528959274,
|
|
"num_tokens": 32182690.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.565619564056396,
|
|
"epoch": 1.6206547986746784,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047465164393411245,
|
|
"loss": 5.3709,
|
|
"mean_token_accuracy": 0.18628532588481903,
|
|
"num_tokens": 32194045.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.564471960067749,
|
|
"epoch": 1.621216375582636,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047463312759891615,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.17654105573892592,
|
|
"num_tokens": 32205699.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.627535152435303,
|
|
"epoch": 1.6217779524905935,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004746146049073236,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.17833087146282195,
|
|
"num_tokens": 32217974.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.4618672847747805,
|
|
"epoch": 1.622339529398551,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047459607585992466,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.18709846138954161,
|
|
"num_tokens": 32228723.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.521645164489746,
|
|
"epoch": 1.6229011063065086,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047457754045730923,
|
|
"loss": 5.4723,
|
|
"mean_token_accuracy": 0.17808499485254287,
|
|
"num_tokens": 32241048.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.524544954299927,
|
|
"epoch": 1.6234626832144663,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00047455899870006745,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.19054992645978927,
|
|
"num_tokens": 32251255.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.56829981803894,
|
|
"epoch": 1.6240242601224237,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004745404505887899,
|
|
"loss": 5.3946,
|
|
"mean_token_accuracy": 0.18267035484313965,
|
|
"num_tokens": 32262954.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.599731492996216,
|
|
"epoch": 1.6245858370303812,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004745218961240669,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.19022905230522155,
|
|
"num_tokens": 32275445.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.554810619354248,
|
|
"epoch": 1.6251474139383388,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004745033353064893,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.19046888798475264,
|
|
"num_tokens": 32285976.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.501206636428833,
|
|
"epoch": 1.6257089908462965,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004744847681366482,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.1909326434135437,
|
|
"num_tokens": 32296304.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.507631540298462,
|
|
"epoch": 1.626270567754254,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047446619461513466,
|
|
"loss": 5.3576,
|
|
"mean_token_accuracy": 0.19172045290470124,
|
|
"num_tokens": 32307085.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.5486973285675045,
|
|
"epoch": 1.6268321446622114,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004744476147425402,
|
|
"loss": 5.2845,
|
|
"mean_token_accuracy": 0.19661511480808258,
|
|
"num_tokens": 32316814.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.5310204982757565,
|
|
"epoch": 1.627393721570169,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00047442902851945634,
|
|
"loss": 5.3795,
|
|
"mean_token_accuracy": 0.1876860409975052,
|
|
"num_tokens": 32327820.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.611599493026733,
|
|
"epoch": 1.6279552984781267,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047441043594647486,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.18968273103237152,
|
|
"num_tokens": 32338185.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.550494861602783,
|
|
"epoch": 1.6285168753860841,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047439183702418765,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.18803541511297225,
|
|
"num_tokens": 32348537.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.487867832183838,
|
|
"epoch": 1.6290784522940416,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047437323175318716,
|
|
"loss": 5.4166,
|
|
"mean_token_accuracy": 0.17826031446456908,
|
|
"num_tokens": 32359094.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.434188508987427,
|
|
"epoch": 1.6296400292019992,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00047435462013406554,
|
|
"loss": 5.2486,
|
|
"mean_token_accuracy": 0.19759637415409087,
|
|
"num_tokens": 32370811.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.6134415626525875,
|
|
"epoch": 1.630201606109957,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004743360021674155,
|
|
"loss": 5.435,
|
|
"mean_token_accuracy": 0.18060946762561797,
|
|
"num_tokens": 32381522.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.591118431091308,
|
|
"epoch": 1.6307631830179143,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047431737785382996,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.18353510200977324,
|
|
"num_tokens": 32393221.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.668833446502686,
|
|
"epoch": 1.6313247599258718,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047429874719390165,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.18382403254508972,
|
|
"num_tokens": 32404007.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.578780221939087,
|
|
"epoch": 1.6318863368338294,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047428011018822404,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.1791157454252243,
|
|
"num_tokens": 32414318.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.561786746978759,
|
|
"epoch": 1.6324479137417869,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047426146683739043,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.18707036674022676,
|
|
"num_tokens": 32425493.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.599663257598877,
|
|
"epoch": 1.6330094906497443,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047424281714199436,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.18745899796485901,
|
|
"num_tokens": 32435765.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.648324489593506,
|
|
"epoch": 1.633571067557702,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047422416110262975,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.1898566797375679,
|
|
"num_tokens": 32446478.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.421393251419067,
|
|
"epoch": 1.6341326444656596,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00047420549871989053,
|
|
"loss": 5.4113,
|
|
"mean_token_accuracy": 0.18982436805963515,
|
|
"num_tokens": 32456866.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.58639702796936,
|
|
"epoch": 1.634694221373617,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000474186829994371,
|
|
"loss": 5.3145,
|
|
"mean_token_accuracy": 0.19399545043706895,
|
|
"num_tokens": 32466973.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.658341550827027,
|
|
"epoch": 1.6352557982815745,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00047416815492666564,
|
|
"loss": 5.4795,
|
|
"mean_token_accuracy": 0.18077365010976792,
|
|
"num_tokens": 32478118.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.479006004333496,
|
|
"epoch": 1.6358173751895322,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004741494735173689,
|
|
"loss": 5.2893,
|
|
"mean_token_accuracy": 0.19405859261751174,
|
|
"num_tokens": 32488255.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.655792331695556,
|
|
"epoch": 1.6363789520974898,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004741307857670757,
|
|
"loss": 5.3923,
|
|
"mean_token_accuracy": 0.18943797796964645,
|
|
"num_tokens": 32498685.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.580639123916626,
|
|
"epoch": 1.6369405290054473,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047411209167638106,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.18233271092176437,
|
|
"num_tokens": 32510457.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.468808269500732,
|
|
"epoch": 1.6375021059134047,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004740933912458801,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.18573978841304778,
|
|
"num_tokens": 32522495.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.6871685028076175,
|
|
"epoch": 1.6380636828213624,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00047407468447616845,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.18254947364330293,
|
|
"num_tokens": 32534891.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.56825852394104,
|
|
"epoch": 1.63862525972932,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047405597136784166,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.18654873073101044,
|
|
"num_tokens": 32545555.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.5157660961151125,
|
|
"epoch": 1.6391868366372775,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004740372519214955,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18810761868953704,
|
|
"num_tokens": 32556851.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.681010389328003,
|
|
"epoch": 1.639748413545235,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047401852613772604,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.1796854093670845,
|
|
"num_tokens": 32569028.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.74272723197937,
|
|
"epoch": 1.6403099904531926,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004739997940171295,
|
|
"loss": 5.4746,
|
|
"mean_token_accuracy": 0.1812252953648567,
|
|
"num_tokens": 32581510.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.524779748916626,
|
|
"epoch": 1.6408715673611503,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047398105556030234,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.18687957972288133,
|
|
"num_tokens": 32592914.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.452997636795044,
|
|
"epoch": 1.6414331442691077,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047396231076784123,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.1936187341809273,
|
|
"num_tokens": 32603931.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.598204326629639,
|
|
"epoch": 1.6419947211770651,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004739435596403429,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.19002971202135086,
|
|
"num_tokens": 32614508.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.530582571029663,
|
|
"epoch": 1.6425562980850228,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004739248021784046,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.19450278878211974,
|
|
"num_tokens": 32625393.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.454287052154541,
|
|
"epoch": 1.6431178749929805,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004739060383826234,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.19365008026361466,
|
|
"num_tokens": 32636645.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.648998975753784,
|
|
"epoch": 1.6436794519009377,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047388726825359673,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.17879440933465957,
|
|
"num_tokens": 32648792.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.544117498397827,
|
|
"epoch": 1.6442410288088953,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047386849179192235,
|
|
"loss": 5.3724,
|
|
"mean_token_accuracy": 0.19500995874404908,
|
|
"num_tokens": 32658825.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.602291631698608,
|
|
"epoch": 1.644802605716853,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047384970899819813,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.18812161535024643,
|
|
"num_tokens": 32670141.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.42455415725708,
|
|
"epoch": 1.6453641826248104,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004738309198730219,
|
|
"loss": 5.2268,
|
|
"mean_token_accuracy": 0.19659915566444397,
|
|
"num_tokens": 32681804.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.702473115921021,
|
|
"epoch": 1.6459257595327679,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047381212441699217,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.18059590458869934,
|
|
"num_tokens": 32692550.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.595619487762451,
|
|
"epoch": 1.6464873364407255,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004737933226307072,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.18726955205202103,
|
|
"num_tokens": 32703833.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.500187158584595,
|
|
"epoch": 1.6470489133486832,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047377451451476586,
|
|
"loss": 5.4048,
|
|
"mean_token_accuracy": 0.1826294779777527,
|
|
"num_tokens": 32713928.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.64390549659729,
|
|
"epoch": 1.6476104902566406,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004737557000697668,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18806727081537247,
|
|
"num_tokens": 32725393.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.617933464050293,
|
|
"epoch": 1.648172067164598,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004737368792963092,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18383493572473525,
|
|
"num_tokens": 32736047.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.537759923934937,
|
|
"epoch": 1.6487336440725557,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047371805219499223,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.18050235360860825,
|
|
"num_tokens": 32747960.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.486103200912476,
|
|
"epoch": 1.6492952209805134,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047369921876641547,
|
|
"loss": 5.3413,
|
|
"mean_token_accuracy": 0.1898680567741394,
|
|
"num_tokens": 32757851.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.5273966789245605,
|
|
"epoch": 1.6498567978884708,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.00047368037901117854,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1846054881811142,
|
|
"num_tokens": 32767317.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.631961679458618,
|
|
"epoch": 1.6504183747964283,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004736615329298812,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.18432583063840866,
|
|
"num_tokens": 32777729.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.591684007644654,
|
|
"epoch": 1.650979951704386,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047364268052312367,
|
|
"loss": 5.4482,
|
|
"mean_token_accuracy": 0.1784728452563286,
|
|
"num_tokens": 32789547.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.6037633419036865,
|
|
"epoch": 1.6515415286123436,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004736238217915061,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.19155059307813643,
|
|
"num_tokens": 32801487.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.621916961669922,
|
|
"epoch": 1.652103105520301,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047360495673562906,
|
|
"loss": 5.4219,
|
|
"mean_token_accuracy": 0.18967934399843217,
|
|
"num_tokens": 32813042.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.582465982437133,
|
|
"epoch": 1.6526646824282585,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004735860853560931,
|
|
"loss": 5.4017,
|
|
"mean_token_accuracy": 0.1818161725997925,
|
|
"num_tokens": 32825467.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.5573317527771,
|
|
"epoch": 1.6532262593362161,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00047356720765349926,
|
|
"loss": 5.3794,
|
|
"mean_token_accuracy": 0.1832003876566887,
|
|
"num_tokens": 32837113.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.670349550247193,
|
|
"epoch": 1.6537878362441738,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004735483236284485,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.18187854140996934,
|
|
"num_tokens": 32849779.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.509832859039307,
|
|
"epoch": 1.654349413152131,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.00047352943328154203,
|
|
"loss": 5.3777,
|
|
"mean_token_accuracy": 0.1862569645047188,
|
|
"num_tokens": 32861626.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.633265447616577,
|
|
"epoch": 1.6549109900600887,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.00047351053661338145,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1902396023273468,
|
|
"num_tokens": 32872875.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.562580347061157,
|
|
"epoch": 1.6554725669680463,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004734916336245684,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.19126229584217072,
|
|
"num_tokens": 32883899.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.468643760681152,
|
|
"epoch": 1.6560341438760038,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004734727243157047,
|
|
"loss": 5.2692,
|
|
"mean_token_accuracy": 0.1944427475333214,
|
|
"num_tokens": 32894255.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.548546504974365,
|
|
"epoch": 1.6565957207839612,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00047345380868739253,
|
|
"loss": 5.3385,
|
|
"mean_token_accuracy": 0.1873532623052597,
|
|
"num_tokens": 32903822.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.515184736251831,
|
|
"epoch": 1.6571572976919189,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004734348867402341,
|
|
"loss": 5.3287,
|
|
"mean_token_accuracy": 0.19080935716629027,
|
|
"num_tokens": 32915879.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.475447273254394,
|
|
"epoch": 1.6577188745998765,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004734159584748319,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18549595922231674,
|
|
"num_tokens": 32928161.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.561248540878296,
|
|
"epoch": 1.658280451507834,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00047339702389178874,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.19155019372701645,
|
|
"num_tokens": 32938399.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.551803207397461,
|
|
"epoch": 1.6588420284157914,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047337808299170725,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.1923631489276886,
|
|
"num_tokens": 32948221.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.531920433044434,
|
|
"epoch": 1.659403605323749,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047335913577519075,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.18917738944292067,
|
|
"num_tokens": 32959802.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.579497385025024,
|
|
"epoch": 1.6599651822317067,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047334018224284244,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.18457742482423783,
|
|
"num_tokens": 32970222.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.596690607070923,
|
|
"epoch": 1.6605267591396642,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004733212223952657,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.18806644380092621,
|
|
"num_tokens": 32982241.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.55825138092041,
|
|
"epoch": 1.6610883360476216,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00047330225623306443,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.1915961906313896,
|
|
"num_tokens": 32992584.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.566189002990723,
|
|
"epoch": 1.6616499129555793,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047328328375684237,
|
|
"loss": 5.5107,
|
|
"mean_token_accuracy": 0.18126624971628189,
|
|
"num_tokens": 33004080.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.527070617675781,
|
|
"epoch": 1.662211489863537,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004732643049672036,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.18956303596496582,
|
|
"num_tokens": 33015290.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.499928998947143,
|
|
"epoch": 1.6627730667714944,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004732453198647525,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.1901732161641121,
|
|
"num_tokens": 33026470.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.466233634948731,
|
|
"epoch": 1.6633346436794518,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004732263284500936,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.1903911903500557,
|
|
"num_tokens": 33036766.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.4966583251953125,
|
|
"epoch": 1.6638962205874095,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004732073307238314,
|
|
"loss": 5.3032,
|
|
"mean_token_accuracy": 0.1831813782453537,
|
|
"num_tokens": 33047675.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.580537176132202,
|
|
"epoch": 1.6644577974953672,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000473188326686571,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.18998884856700898,
|
|
"num_tokens": 33057613.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.657105350494385,
|
|
"epoch": 1.6650193744033244,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047316931633891736,
|
|
"loss": 5.467,
|
|
"mean_token_accuracy": 0.17953051254153252,
|
|
"num_tokens": 33070498.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.5625420093536375,
|
|
"epoch": 1.665580951311282,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004731502996814759,
|
|
"loss": 5.3243,
|
|
"mean_token_accuracy": 0.18923291862010955,
|
|
"num_tokens": 33082026.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.502161979675293,
|
|
"epoch": 1.6661425282192397,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00047313127671485194,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.18744719177484512,
|
|
"num_tokens": 33093841.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.619352769851685,
|
|
"epoch": 1.6667041051271971,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004731122474396514,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.18781189620494843,
|
|
"num_tokens": 33103817.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.618480443954468,
|
|
"epoch": 1.6672656820351546,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00047309321185648,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.18639908879995346,
|
|
"num_tokens": 33116006.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.551406002044677,
|
|
"epoch": 1.6678272589431122,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047307416996594386,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.18302186727523803,
|
|
"num_tokens": 33127649.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.510583925247192,
|
|
"epoch": 1.66838883585107,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004730551217686495,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19337385296821594,
|
|
"num_tokens": 33138748.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.596703290939331,
|
|
"epoch": 1.6689504127590273,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004730360672652031,
|
|
"loss": 5.4306,
|
|
"mean_token_accuracy": 0.18505453169345856,
|
|
"num_tokens": 33150504.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.513660144805908,
|
|
"epoch": 1.6695119896669848,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00047301700645621154,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.1782146617770195,
|
|
"num_tokens": 33160625.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.579544162750244,
|
|
"epoch": 1.6700735665749424,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004729979393422817,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.18842446953058242,
|
|
"num_tokens": 33172229.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.5924091815948485,
|
|
"epoch": 1.6706351434829,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004729788659240206,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18659709095954896,
|
|
"num_tokens": 33183234.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.612027978897094,
|
|
"epoch": 1.6711967203908575,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004729597862020358,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.18393837362527848,
|
|
"num_tokens": 33193976.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.516768169403076,
|
|
"epoch": 1.671758297298815,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047294070017693453,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.19232611060142518,
|
|
"num_tokens": 33205959.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.524567127227783,
|
|
"epoch": 1.6723198742067726,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047292160784932454,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.18973541855812073,
|
|
"num_tokens": 33218405.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.529152917861938,
|
|
"epoch": 1.6728814511147303,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00047290250921981386,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.18420242965221406,
|
|
"num_tokens": 33230778.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.524522113800049,
|
|
"epoch": 1.6734430280226877,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047288340428901053,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.18586020916700363,
|
|
"num_tokens": 33242069.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.5696129322052,
|
|
"epoch": 1.6740046049306452,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047286429305752283,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.18746148198843002,
|
|
"num_tokens": 33252942.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.630404424667359,
|
|
"epoch": 1.6745661818386028,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047284517552595933,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.18062890768051149,
|
|
"num_tokens": 33263892.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.461895418167114,
|
|
"epoch": 1.6751277587465605,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004728260516949287,
|
|
"loss": 5.31,
|
|
"mean_token_accuracy": 0.18734390884637833,
|
|
"num_tokens": 33274383.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.656695175170898,
|
|
"epoch": 1.6756893356545177,
|
|
"grad_norm": 2.421875,
|
|
"learning_rate": 0.0004728069215650399,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.18718907088041306,
|
|
"num_tokens": 33285897.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.6313635349273685,
|
|
"epoch": 1.6762509125624754,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004727877851369019,
|
|
"loss": 5.4178,
|
|
"mean_token_accuracy": 0.18419927209615708,
|
|
"num_tokens": 33297192.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.537465333938599,
|
|
"epoch": 1.676812489470433,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047276864241112417,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19167827665805817,
|
|
"num_tokens": 33308250.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.473515558242798,
|
|
"epoch": 1.6773740663783905,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004727494933883161,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.18753487765789031,
|
|
"num_tokens": 33318515.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.621397829055786,
|
|
"epoch": 1.677935643286348,
|
|
"grad_norm": 2.375,
|
|
"learning_rate": 0.0004727303380690876,
|
|
"loss": 5.4748,
|
|
"mean_token_accuracy": 0.18341102749109267,
|
|
"num_tokens": 33329762.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.633169651031494,
|
|
"epoch": 1.6784972201943056,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004727111764540484,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.18551748991012573,
|
|
"num_tokens": 33341054.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.570129013061523,
|
|
"epoch": 1.6790587971022632,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00047269200854380854,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.1938321053981781,
|
|
"num_tokens": 33351524.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.513936758041382,
|
|
"epoch": 1.6796203740102207,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00047267283433897854,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.18356804847717284,
|
|
"num_tokens": 33362953.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.470935344696045,
|
|
"epoch": 1.6801819509181781,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047265365384016887,
|
|
"loss": 5.2687,
|
|
"mean_token_accuracy": 0.19765151292085648,
|
|
"num_tokens": 33373209.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.494607067108154,
|
|
"epoch": 1.6807435278261358,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047263446704799017,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.1919275239109993,
|
|
"num_tokens": 33384775.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.495308494567871,
|
|
"epoch": 1.6813051047340934,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047261527396305343,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.19044806063175201,
|
|
"num_tokens": 33395457.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.6358702182769775,
|
|
"epoch": 1.6818666816420509,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00047259607458596966,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.1864623710513115,
|
|
"num_tokens": 33407506.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.6024314880371096,
|
|
"epoch": 1.6824282585500083,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047257686891735023,
|
|
"loss": 5.3579,
|
|
"mean_token_accuracy": 0.1865003615617752,
|
|
"num_tokens": 33418154.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.500241756439209,
|
|
"epoch": 1.682989835457966,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00047255765695780665,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.19208233952522277,
|
|
"num_tokens": 33428319.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.4757226467132565,
|
|
"epoch": 1.6835514123659236,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004725384387079507,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.1891019493341446,
|
|
"num_tokens": 33440429.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.715919542312622,
|
|
"epoch": 1.684112989273881,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047251921416839425,
|
|
"loss": 5.513,
|
|
"mean_token_accuracy": 0.179588620364666,
|
|
"num_tokens": 33451736.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.55006251335144,
|
|
"epoch": 1.6846745661818385,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004724999833397494,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.18499394059181212,
|
|
"num_tokens": 33461991.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.6846745661818385,
|
|
"eval_entropy": 5.353864653318975,
|
|
"eval_loss": 5.453826427459717,
|
|
"eval_mean_token_accuracy": 0.19033650214393974,
|
|
"eval_num_tokens": 33461991.0,
|
|
"eval_runtime": 23.8756,
|
|
"eval_samples_per_second": 1298.94,
|
|
"eval_steps_per_second": 162.383,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"entropy": 5.544108581542969,
|
|
"epoch": 1.6852361430897962,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004724807462226285,
|
|
"loss": 5.4492,
|
|
"mean_token_accuracy": 0.17914241403341294,
|
|
"num_tokens": 33473646.0,
|
|
"step": 15005
|
|
},
|
|
{
|
|
"entropy": 5.540371751785278,
|
|
"epoch": 1.6857977199977539,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000472461502817644,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.18724657893180846,
|
|
"num_tokens": 33485444.0,
|
|
"step": 15010
|
|
},
|
|
{
|
|
"entropy": 5.692107772827148,
|
|
"epoch": 1.6863592969057113,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004724422531254087,
|
|
"loss": 5.5576,
|
|
"mean_token_accuracy": 0.17865096479654313,
|
|
"num_tokens": 33497199.0,
|
|
"step": 15015
|
|
},
|
|
{
|
|
"entropy": 5.61740288734436,
|
|
"epoch": 1.6869208738136687,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004724229971465355,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.17749716341495514,
|
|
"num_tokens": 33509045.0,
|
|
"step": 15020
|
|
},
|
|
{
|
|
"entropy": 5.5371709823608395,
|
|
"epoch": 1.6874824507216264,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004724037348816375,
|
|
"loss": 5.247,
|
|
"mean_token_accuracy": 0.19715164303779603,
|
|
"num_tokens": 33519730.0,
|
|
"step": 15025
|
|
},
|
|
{
|
|
"entropy": 5.5326978206634525,
|
|
"epoch": 1.6880440276295838,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000472384466331328,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.18078390657901763,
|
|
"num_tokens": 33530393.0,
|
|
"step": 15030
|
|
},
|
|
{
|
|
"entropy": 5.558160638809204,
|
|
"epoch": 1.6886056045375413,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004723651914962205,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.18772499561309813,
|
|
"num_tokens": 33543592.0,
|
|
"step": 15035
|
|
},
|
|
{
|
|
"entropy": 5.592311525344849,
|
|
"epoch": 1.689167181445499,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047234591037692884,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.18432275652885438,
|
|
"num_tokens": 33554736.0,
|
|
"step": 15040
|
|
},
|
|
{
|
|
"entropy": 5.536983776092529,
|
|
"epoch": 1.6897287583534566,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047232662297406683,
|
|
"loss": 5.2776,
|
|
"mean_token_accuracy": 0.1946849763393402,
|
|
"num_tokens": 33565428.0,
|
|
"step": 15045
|
|
},
|
|
{
|
|
"entropy": 5.596999597549439,
|
|
"epoch": 1.690290335261414,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004723073292882485,
|
|
"loss": 5.6027,
|
|
"mean_token_accuracy": 0.1770312488079071,
|
|
"num_tokens": 33577102.0,
|
|
"step": 15050
|
|
},
|
|
{
|
|
"entropy": 5.6567872047424315,
|
|
"epoch": 1.6908519121693715,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00047228802932008836,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.18808227330446242,
|
|
"num_tokens": 33587325.0,
|
|
"step": 15055
|
|
},
|
|
{
|
|
"entropy": 5.655790328979492,
|
|
"epoch": 1.6914134890773291,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004722687230702009,
|
|
"loss": 5.4478,
|
|
"mean_token_accuracy": 0.18218927085399628,
|
|
"num_tokens": 33599294.0,
|
|
"step": 15060
|
|
},
|
|
{
|
|
"entropy": 5.575462055206299,
|
|
"epoch": 1.6919750659852868,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004722494105392007,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.18188184648752212,
|
|
"num_tokens": 33609025.0,
|
|
"step": 15065
|
|
},
|
|
{
|
|
"entropy": 5.644392585754394,
|
|
"epoch": 1.6925366428932442,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004722300917277029,
|
|
"loss": 5.44,
|
|
"mean_token_accuracy": 0.18101317584514617,
|
|
"num_tokens": 33620881.0,
|
|
"step": 15070
|
|
},
|
|
{
|
|
"entropy": 5.601105642318726,
|
|
"epoch": 1.6930982198012017,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004722107666363224,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.18792786151170732,
|
|
"num_tokens": 33631505.0,
|
|
"step": 15075
|
|
},
|
|
{
|
|
"entropy": 5.5875801086425785,
|
|
"epoch": 1.6936597967091593,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004721914352656746,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1802033856511116,
|
|
"num_tokens": 33642560.0,
|
|
"step": 15080
|
|
},
|
|
{
|
|
"entropy": 5.653385066986084,
|
|
"epoch": 1.694221373617117,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000472172097616375,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.1852569341659546,
|
|
"num_tokens": 33654706.0,
|
|
"step": 15085
|
|
},
|
|
{
|
|
"entropy": 5.648021984100342,
|
|
"epoch": 1.6947829505250744,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004721527536890394,
|
|
"loss": 5.441,
|
|
"mean_token_accuracy": 0.17734901160001754,
|
|
"num_tokens": 33665392.0,
|
|
"step": 15090
|
|
},
|
|
{
|
|
"entropy": 5.414823818206787,
|
|
"epoch": 1.6953445274330319,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004721334034842836,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.1954530030488968,
|
|
"num_tokens": 33675504.0,
|
|
"step": 15095
|
|
},
|
|
{
|
|
"entropy": 5.590618324279785,
|
|
"epoch": 1.6959061043409895,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004721140470027238,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18265432119369507,
|
|
"num_tokens": 33686505.0,
|
|
"step": 15100
|
|
},
|
|
{
|
|
"entropy": 5.6272969245910645,
|
|
"epoch": 1.6964676812489472,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.00047209468424497627,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.1850193604826927,
|
|
"num_tokens": 33698752.0,
|
|
"step": 15105
|
|
},
|
|
{
|
|
"entropy": 5.691330623626709,
|
|
"epoch": 1.6970292581569046,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004720753152116576,
|
|
"loss": 5.4691,
|
|
"mean_token_accuracy": 0.1778954118490219,
|
|
"num_tokens": 33710323.0,
|
|
"step": 15110
|
|
},
|
|
{
|
|
"entropy": 5.661396455764771,
|
|
"epoch": 1.697590835064862,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00047205593990338443,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.17385683506727218,
|
|
"num_tokens": 33721875.0,
|
|
"step": 15115
|
|
},
|
|
{
|
|
"entropy": 5.504017877578735,
|
|
"epoch": 1.6981524119728197,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004720365583207737,
|
|
"loss": 5.2253,
|
|
"mean_token_accuracy": 0.19767348766326903,
|
|
"num_tokens": 33731520.0,
|
|
"step": 15120
|
|
},
|
|
{
|
|
"entropy": 5.6268226146698,
|
|
"epoch": 1.6987139888807772,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004720171704644425,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.18229078650474548,
|
|
"num_tokens": 33743351.0,
|
|
"step": 15125
|
|
},
|
|
{
|
|
"entropy": 5.635243558883667,
|
|
"epoch": 1.6992755657887346,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004719977763350083,
|
|
"loss": 5.4076,
|
|
"mean_token_accuracy": 0.18609412759542465,
|
|
"num_tokens": 33754879.0,
|
|
"step": 15130
|
|
},
|
|
{
|
|
"entropy": 5.500914096832275,
|
|
"epoch": 1.6998371426966923,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00047197837593308833,
|
|
"loss": 5.3491,
|
|
"mean_token_accuracy": 0.18206062614917756,
|
|
"num_tokens": 33766671.0,
|
|
"step": 15135
|
|
},
|
|
{
|
|
"entropy": 5.587838363647461,
|
|
"epoch": 1.70039871960465,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004719589692593006,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.18447351455688477,
|
|
"num_tokens": 33778236.0,
|
|
"step": 15140
|
|
},
|
|
{
|
|
"entropy": 5.554403829574585,
|
|
"epoch": 1.7009602965126074,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004719395563142629,
|
|
"loss": 5.2906,
|
|
"mean_token_accuracy": 0.1885974273085594,
|
|
"num_tokens": 33788898.0,
|
|
"step": 15145
|
|
},
|
|
{
|
|
"entropy": 5.573729801177978,
|
|
"epoch": 1.7015218734205648,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004719201370985933,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.17930941581726073,
|
|
"num_tokens": 33800641.0,
|
|
"step": 15150
|
|
},
|
|
{
|
|
"entropy": 5.620885753631592,
|
|
"epoch": 1.7020834503285225,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00047190071161291007,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.1887860879302025,
|
|
"num_tokens": 33812581.0,
|
|
"step": 15155
|
|
},
|
|
{
|
|
"entropy": 5.546499109268188,
|
|
"epoch": 1.7026450272364801,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047188127985783195,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.1963081330060959,
|
|
"num_tokens": 33823378.0,
|
|
"step": 15160
|
|
},
|
|
{
|
|
"entropy": 5.540398788452149,
|
|
"epoch": 1.7032066041444376,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00047186184183397754,
|
|
"loss": 5.4183,
|
|
"mean_token_accuracy": 0.1868310108780861,
|
|
"num_tokens": 33834804.0,
|
|
"step": 15165
|
|
},
|
|
{
|
|
"entropy": 5.50910587310791,
|
|
"epoch": 1.703768181052395,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00047184239754196564,
|
|
"loss": 5.3727,
|
|
"mean_token_accuracy": 0.18303461819887162,
|
|
"num_tokens": 33847044.0,
|
|
"step": 15170
|
|
},
|
|
{
|
|
"entropy": 5.581722974777222,
|
|
"epoch": 1.7043297579603527,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004718229469824155,
|
|
"loss": 5.3331,
|
|
"mean_token_accuracy": 0.1800563395023346,
|
|
"num_tokens": 33858077.0,
|
|
"step": 15175
|
|
},
|
|
{
|
|
"entropy": 5.572086572647095,
|
|
"epoch": 1.7048913348683103,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00047180349015594634,
|
|
"loss": 5.3694,
|
|
"mean_token_accuracy": 0.1854755088686943,
|
|
"num_tokens": 33868765.0,
|
|
"step": 15180
|
|
},
|
|
{
|
|
"entropy": 5.52621021270752,
|
|
"epoch": 1.7054529117762678,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004717840270631778,
|
|
"loss": 5.3426,
|
|
"mean_token_accuracy": 0.18994404077529908,
|
|
"num_tokens": 33880415.0,
|
|
"step": 15185
|
|
},
|
|
{
|
|
"entropy": 5.533231019973755,
|
|
"epoch": 1.7060144886842252,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047176455770472946,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.18573530167341232,
|
|
"num_tokens": 33892081.0,
|
|
"step": 15190
|
|
},
|
|
{
|
|
"entropy": 5.631167316436768,
|
|
"epoch": 1.706576065592183,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00047174508208122135,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.179116652905941,
|
|
"num_tokens": 33903433.0,
|
|
"step": 15195
|
|
},
|
|
{
|
|
"entropy": 5.632302951812744,
|
|
"epoch": 1.7071376425001406,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004717256001932735,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.18265377581119538,
|
|
"num_tokens": 33914706.0,
|
|
"step": 15200
|
|
},
|
|
{
|
|
"entropy": 5.52523102760315,
|
|
"epoch": 1.707699219408098,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00047170611204150624,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.1813989460468292,
|
|
"num_tokens": 33927195.0,
|
|
"step": 15205
|
|
},
|
|
{
|
|
"entropy": 5.571352910995484,
|
|
"epoch": 1.7082607963160554,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004716866176265401,
|
|
"loss": 5.3643,
|
|
"mean_token_accuracy": 0.1884804368019104,
|
|
"num_tokens": 33938422.0,
|
|
"step": 15210
|
|
},
|
|
{
|
|
"entropy": 5.6760234355926515,
|
|
"epoch": 1.708822373224013,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00047166711694899573,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.18883152455091476,
|
|
"num_tokens": 33949775.0,
|
|
"step": 15215
|
|
},
|
|
{
|
|
"entropy": 5.5512501239776615,
|
|
"epoch": 1.7093839501319705,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047164761000949404,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.18902892172336577,
|
|
"num_tokens": 33960371.0,
|
|
"step": 15220
|
|
},
|
|
{
|
|
"entropy": 5.480539131164551,
|
|
"epoch": 1.709945527039928,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004716280968086563,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.1846398815512657,
|
|
"num_tokens": 33971326.0,
|
|
"step": 15225
|
|
},
|
|
{
|
|
"entropy": 5.617764568328857,
|
|
"epoch": 1.7105071039478856,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004716085773471036,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.180968801677227,
|
|
"num_tokens": 33982744.0,
|
|
"step": 15230
|
|
},
|
|
{
|
|
"entropy": 5.612250566482544,
|
|
"epoch": 1.7110686808558433,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00047158905162545756,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.1778939411044121,
|
|
"num_tokens": 33993647.0,
|
|
"step": 15235
|
|
},
|
|
{
|
|
"entropy": 5.538938379287719,
|
|
"epoch": 1.7116302577638007,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00047156951964433984,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.18366360813379287,
|
|
"num_tokens": 34004026.0,
|
|
"step": 15240
|
|
},
|
|
{
|
|
"entropy": 5.557793188095093,
|
|
"epoch": 1.7121918346717582,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047154998140437246,
|
|
"loss": 5.3882,
|
|
"mean_token_accuracy": 0.19072677046060563,
|
|
"num_tokens": 34014882.0,
|
|
"step": 15245
|
|
},
|
|
{
|
|
"entropy": 5.539154958724976,
|
|
"epoch": 1.7127534115797158,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00047153043690617737,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.1863025575876236,
|
|
"num_tokens": 34026548.0,
|
|
"step": 15250
|
|
},
|
|
{
|
|
"entropy": 5.529127931594848,
|
|
"epoch": 1.7133149884876735,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000471510886150377,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.18546749353408815,
|
|
"num_tokens": 34038393.0,
|
|
"step": 15255
|
|
},
|
|
{
|
|
"entropy": 5.608902359008789,
|
|
"epoch": 1.713876565395631,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004714913291375938,
|
|
"loss": 5.4338,
|
|
"mean_token_accuracy": 0.18306043297052382,
|
|
"num_tokens": 34050257.0,
|
|
"step": 15260
|
|
},
|
|
{
|
|
"entropy": 5.5992039203643795,
|
|
"epoch": 1.7144381423035884,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00047147176586845036,
|
|
"loss": 5.3756,
|
|
"mean_token_accuracy": 0.18563131839036942,
|
|
"num_tokens": 34061860.0,
|
|
"step": 15265
|
|
},
|
|
{
|
|
"entropy": 5.605739688873291,
|
|
"epoch": 1.714999719211546,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004714521963435698,
|
|
"loss": 5.4397,
|
|
"mean_token_accuracy": 0.18367208689451217,
|
|
"num_tokens": 34075247.0,
|
|
"step": 15270
|
|
},
|
|
{
|
|
"entropy": 5.596637868881226,
|
|
"epoch": 1.7155612961195037,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047143262056357506,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.18529912680387498,
|
|
"num_tokens": 34085801.0,
|
|
"step": 15275
|
|
},
|
|
{
|
|
"entropy": 5.570083284378052,
|
|
"epoch": 1.7161228730274611,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047141303852908965,
|
|
"loss": 5.4005,
|
|
"mean_token_accuracy": 0.18426835536956787,
|
|
"num_tokens": 34095686.0,
|
|
"step": 15280
|
|
},
|
|
{
|
|
"entropy": 5.517567586898804,
|
|
"epoch": 1.7166844499354186,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004713934502407367,
|
|
"loss": 5.3307,
|
|
"mean_token_accuracy": 0.19200510233640672,
|
|
"num_tokens": 34106518.0,
|
|
"step": 15285
|
|
},
|
|
{
|
|
"entropy": 5.623777866363525,
|
|
"epoch": 1.7172460268433762,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004713738556991402,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.1906556099653244,
|
|
"num_tokens": 34117793.0,
|
|
"step": 15290
|
|
},
|
|
{
|
|
"entropy": 5.579408788681031,
|
|
"epoch": 1.717807603751334,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000471354254904924,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.18860941976308823,
|
|
"num_tokens": 34128748.0,
|
|
"step": 15295
|
|
},
|
|
{
|
|
"entropy": 5.542307615280151,
|
|
"epoch": 1.7183691806592913,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00047133464785871216,
|
|
"loss": 5.3736,
|
|
"mean_token_accuracy": 0.1913885399699211,
|
|
"num_tokens": 34140597.0,
|
|
"step": 15300
|
|
},
|
|
{
|
|
"entropy": 5.608665132522583,
|
|
"epoch": 1.7189307575672488,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000471315034561129,
|
|
"loss": 5.377,
|
|
"mean_token_accuracy": 0.17972454577684402,
|
|
"num_tokens": 34151823.0,
|
|
"step": 15305
|
|
},
|
|
{
|
|
"entropy": 5.5218363285064695,
|
|
"epoch": 1.7194923344752064,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00047129541501279897,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19515182077884674,
|
|
"num_tokens": 34163697.0,
|
|
"step": 15310
|
|
},
|
|
{
|
|
"entropy": 5.583692741394043,
|
|
"epoch": 1.7200539113831639,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004712757892143468,
|
|
"loss": 5.3191,
|
|
"mean_token_accuracy": 0.18973155468702316,
|
|
"num_tokens": 34175058.0,
|
|
"step": 15315
|
|
},
|
|
{
|
|
"entropy": 5.585815715789795,
|
|
"epoch": 1.7206154882911213,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00047125615716639744,
|
|
"loss": 5.4787,
|
|
"mean_token_accuracy": 0.18608225286006927,
|
|
"num_tokens": 34186883.0,
|
|
"step": 15320
|
|
},
|
|
{
|
|
"entropy": 5.573738622665405,
|
|
"epoch": 1.721177065199079,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004712365188695758,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.189610455930233,
|
|
"num_tokens": 34198103.0,
|
|
"step": 15325
|
|
},
|
|
{
|
|
"entropy": 5.557200241088867,
|
|
"epoch": 1.7217386421070366,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004712168743245074,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.189980947971344,
|
|
"num_tokens": 34208747.0,
|
|
"step": 15330
|
|
},
|
|
{
|
|
"entropy": 5.600449419021606,
|
|
"epoch": 1.722300219014994,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00047119722353181754,
|
|
"loss": 5.4496,
|
|
"mean_token_accuracy": 0.18518861532211303,
|
|
"num_tokens": 34220775.0,
|
|
"step": 15335
|
|
},
|
|
{
|
|
"entropy": 5.626360559463501,
|
|
"epoch": 1.7228617959229515,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047117756649213204,
|
|
"loss": 5.3107,
|
|
"mean_token_accuracy": 0.18701462745666503,
|
|
"num_tokens": 34231031.0,
|
|
"step": 15340
|
|
},
|
|
{
|
|
"entropy": 5.550365304946899,
|
|
"epoch": 1.7234233728309092,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004711579032060767,
|
|
"loss": 5.433,
|
|
"mean_token_accuracy": 0.18697787672281266,
|
|
"num_tokens": 34241850.0,
|
|
"step": 15345
|
|
},
|
|
{
|
|
"entropy": 5.560673236846924,
|
|
"epoch": 1.7239849497388668,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004711382336742777,
|
|
"loss": 5.3268,
|
|
"mean_token_accuracy": 0.18711521923542024,
|
|
"num_tokens": 34252732.0,
|
|
"step": 15350
|
|
},
|
|
{
|
|
"entropy": 5.535443353652954,
|
|
"epoch": 1.7245465266468243,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004711185578973612,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.18295160681009293,
|
|
"num_tokens": 34264066.0,
|
|
"step": 15355
|
|
},
|
|
{
|
|
"entropy": 5.619380712509155,
|
|
"epoch": 1.7251081035547817,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004710988758759538,
|
|
"loss": 5.4418,
|
|
"mean_token_accuracy": 0.1772791251540184,
|
|
"num_tokens": 34275239.0,
|
|
"step": 15360
|
|
},
|
|
{
|
|
"entropy": 5.487407588958741,
|
|
"epoch": 1.7256696804627394,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004710791876106821,
|
|
"loss": 5.3068,
|
|
"mean_token_accuracy": 0.1854541689157486,
|
|
"num_tokens": 34285723.0,
|
|
"step": 15365
|
|
},
|
|
{
|
|
"entropy": 5.557523965835571,
|
|
"epoch": 1.726231257370697,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047105949310217304,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.19106273204088212,
|
|
"num_tokens": 34296292.0,
|
|
"step": 15370
|
|
},
|
|
{
|
|
"entropy": 5.530762147903443,
|
|
"epoch": 1.7267928342786545,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004710397923510537,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.1919559121131897,
|
|
"num_tokens": 34307232.0,
|
|
"step": 15375
|
|
},
|
|
{
|
|
"entropy": 5.562787437438965,
|
|
"epoch": 1.727354411186612,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00047102008535795134,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.19594061225652695,
|
|
"num_tokens": 34318933.0,
|
|
"step": 15380
|
|
},
|
|
{
|
|
"entropy": 5.594544839859009,
|
|
"epoch": 1.7279159880945696,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004710003721234934,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.1941317543387413,
|
|
"num_tokens": 34330431.0,
|
|
"step": 15385
|
|
},
|
|
{
|
|
"entropy": 5.571100091934204,
|
|
"epoch": 1.7284775650025272,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00047098065264830754,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.1825042486190796,
|
|
"num_tokens": 34342006.0,
|
|
"step": 15390
|
|
},
|
|
{
|
|
"entropy": 5.581746578216553,
|
|
"epoch": 1.7290391419104847,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00047096092693302174,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18516589254140853,
|
|
"num_tokens": 34353390.0,
|
|
"step": 15395
|
|
},
|
|
{
|
|
"entropy": 5.49395227432251,
|
|
"epoch": 1.7296007188184421,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047094119497826406,
|
|
"loss": 5.3206,
|
|
"mean_token_accuracy": 0.18705826997756958,
|
|
"num_tokens": 34364211.0,
|
|
"step": 15400
|
|
},
|
|
{
|
|
"entropy": 5.570211696624756,
|
|
"epoch": 1.7301622957263998,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00047092145678466273,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.18623632043600083,
|
|
"num_tokens": 34375362.0,
|
|
"step": 15405
|
|
},
|
|
{
|
|
"entropy": 5.504240226745606,
|
|
"epoch": 1.7307238726343572,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004709017123528462,
|
|
"loss": 5.2165,
|
|
"mean_token_accuracy": 0.1975977212190628,
|
|
"num_tokens": 34385511.0,
|
|
"step": 15410
|
|
},
|
|
{
|
|
"entropy": 5.501073408126831,
|
|
"epoch": 1.7312854495423147,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00047088196168344315,
|
|
"loss": 5.4528,
|
|
"mean_token_accuracy": 0.1857527270913124,
|
|
"num_tokens": 34397060.0,
|
|
"step": 15415
|
|
},
|
|
{
|
|
"entropy": 5.540259790420532,
|
|
"epoch": 1.7318470264502723,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047086220477708256,
|
|
"loss": 5.349,
|
|
"mean_token_accuracy": 0.1881771683692932,
|
|
"num_tokens": 34407703.0,
|
|
"step": 15420
|
|
},
|
|
{
|
|
"entropy": 5.578450441360474,
|
|
"epoch": 1.73240860335823,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00047084244163439335,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.19347355365753174,
|
|
"num_tokens": 34418929.0,
|
|
"step": 15425
|
|
},
|
|
{
|
|
"entropy": 5.504177284240723,
|
|
"epoch": 1.7329701802661874,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004708226722560049,
|
|
"loss": 5.2886,
|
|
"mean_token_accuracy": 0.18959824740886688,
|
|
"num_tokens": 34430693.0,
|
|
"step": 15430
|
|
},
|
|
{
|
|
"entropy": 5.519720506668091,
|
|
"epoch": 1.7335317571741449,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004708028966425465,
|
|
"loss": 5.3326,
|
|
"mean_token_accuracy": 0.18788740783929825,
|
|
"num_tokens": 34442299.0,
|
|
"step": 15435
|
|
},
|
|
{
|
|
"entropy": 5.570750761032104,
|
|
"epoch": 1.7340933340821025,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047078311479464797,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.1888814777135849,
|
|
"num_tokens": 34453426.0,
|
|
"step": 15440
|
|
},
|
|
{
|
|
"entropy": 5.514104413986206,
|
|
"epoch": 1.7346549109900602,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00047076332671293917,
|
|
"loss": 5.3429,
|
|
"mean_token_accuracy": 0.18930372595787048,
|
|
"num_tokens": 34463601.0,
|
|
"step": 15445
|
|
},
|
|
{
|
|
"entropy": 5.603073644638061,
|
|
"epoch": 1.7352164878980176,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00047074353239805005,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.1890818551182747,
|
|
"num_tokens": 34474938.0,
|
|
"step": 15450
|
|
},
|
|
{
|
|
"entropy": 5.509182071685791,
|
|
"epoch": 1.735778064805975,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004707237318506111,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.19393603652715682,
|
|
"num_tokens": 34485244.0,
|
|
"step": 15455
|
|
},
|
|
{
|
|
"entropy": 5.426490831375122,
|
|
"epoch": 1.7363396417139327,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00047070392507125245,
|
|
"loss": 5.2749,
|
|
"mean_token_accuracy": 0.19548602104187013,
|
|
"num_tokens": 34496912.0,
|
|
"step": 15460
|
|
},
|
|
{
|
|
"entropy": 5.489939117431641,
|
|
"epoch": 1.7369012186218904,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000470684112060605,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18912530094385147,
|
|
"num_tokens": 34508122.0,
|
|
"step": 15465
|
|
},
|
|
{
|
|
"entropy": 5.585915517807007,
|
|
"epoch": 1.7374627955298478,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047066429281929944,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.19040192812681198,
|
|
"num_tokens": 34519522.0,
|
|
"step": 15470
|
|
},
|
|
{
|
|
"entropy": 5.5331458568573,
|
|
"epoch": 1.7380243724378053,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000470644467347967,
|
|
"loss": 5.3546,
|
|
"mean_token_accuracy": 0.18848609030246735,
|
|
"num_tokens": 34532832.0,
|
|
"step": 15475
|
|
},
|
|
{
|
|
"entropy": 5.556308698654175,
|
|
"epoch": 1.738585949345763,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00047062463564723884,
|
|
"loss": 5.462,
|
|
"mean_token_accuracy": 0.19003038555383683,
|
|
"num_tokens": 34544817.0,
|
|
"step": 15480
|
|
},
|
|
{
|
|
"entropy": 5.534857749938965,
|
|
"epoch": 1.7391475262537206,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004706047977177464,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.18761374354362487,
|
|
"num_tokens": 34555391.0,
|
|
"step": 15485
|
|
},
|
|
{
|
|
"entropy": 5.4741428852081295,
|
|
"epoch": 1.739709103161678,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00047058495356012135,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.1882957398891449,
|
|
"num_tokens": 34567531.0,
|
|
"step": 15490
|
|
},
|
|
{
|
|
"entropy": 5.483543634414673,
|
|
"epoch": 1.7402706800696355,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047056510317499545,
|
|
"loss": 5.3591,
|
|
"mean_token_accuracy": 0.18920887559652327,
|
|
"num_tokens": 34578212.0,
|
|
"step": 15495
|
|
},
|
|
{
|
|
"entropy": 5.473145484924316,
|
|
"epoch": 1.7408322569775931,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00047054524656300087,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.19606369286775588,
|
|
"num_tokens": 34589331.0,
|
|
"step": 15500
|
|
},
|
|
{
|
|
"entropy": 5.4805131435394285,
|
|
"epoch": 1.7413938338855506,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00047052538372476985,
|
|
"loss": 5.3407,
|
|
"mean_token_accuracy": 0.19138521701097488,
|
|
"num_tokens": 34601467.0,
|
|
"step": 15505
|
|
},
|
|
{
|
|
"entropy": 5.530508613586425,
|
|
"epoch": 1.741955410793508,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.00047050551466093466,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.19271543025970458,
|
|
"num_tokens": 34611608.0,
|
|
"step": 15510
|
|
},
|
|
{
|
|
"entropy": 5.585846662521362,
|
|
"epoch": 1.7425169877014657,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004704856393721281,
|
|
"loss": 5.2805,
|
|
"mean_token_accuracy": 0.19657255113124847,
|
|
"num_tokens": 34622495.0,
|
|
"step": 15515
|
|
},
|
|
{
|
|
"entropy": 5.626529312133789,
|
|
"epoch": 1.7430785646094233,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00047046575785898297,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.1835566908121109,
|
|
"num_tokens": 34633279.0,
|
|
"step": 15520
|
|
},
|
|
{
|
|
"entropy": 5.504169654846192,
|
|
"epoch": 1.7436401415173808,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004704458701221323,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.19207601398229598,
|
|
"num_tokens": 34644030.0,
|
|
"step": 15525
|
|
},
|
|
{
|
|
"entropy": 5.622911262512207,
|
|
"epoch": 1.7442017184253382,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004704259761622094,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.1748870074748993,
|
|
"num_tokens": 34655540.0,
|
|
"step": 15530
|
|
},
|
|
{
|
|
"entropy": 5.5763397216796875,
|
|
"epoch": 1.7447632953332959,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00047040607597984745,
|
|
"loss": 5.3692,
|
|
"mean_token_accuracy": 0.18535261005163192,
|
|
"num_tokens": 34666752.0,
|
|
"step": 15535
|
|
},
|
|
{
|
|
"entropy": 5.580453300476075,
|
|
"epoch": 1.7453248722412535,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004703861695756804,
|
|
"loss": 5.3741,
|
|
"mean_token_accuracy": 0.1819029375910759,
|
|
"num_tokens": 34678670.0,
|
|
"step": 15540
|
|
},
|
|
{
|
|
"entropy": 5.581053972244263,
|
|
"epoch": 1.745886449149211,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004703662569503419,
|
|
"loss": 5.3812,
|
|
"mean_token_accuracy": 0.18425812870264052,
|
|
"num_tokens": 34690848.0,
|
|
"step": 15545
|
|
},
|
|
{
|
|
"entropy": 5.576274871826172,
|
|
"epoch": 1.7464480260571684,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00047034633810446604,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.17964570522308348,
|
|
"num_tokens": 34703135.0,
|
|
"step": 15550
|
|
},
|
|
{
|
|
"entropy": 5.570422744750976,
|
|
"epoch": 1.747009602965126,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004703264130386869,
|
|
"loss": 5.3434,
|
|
"mean_token_accuracy": 0.19045388996601104,
|
|
"num_tokens": 34714329.0,
|
|
"step": 15555
|
|
},
|
|
{
|
|
"entropy": 5.539223957061767,
|
|
"epoch": 1.7475711798730837,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00047030648175363913,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.1793899193406105,
|
|
"num_tokens": 34727032.0,
|
|
"step": 15560
|
|
},
|
|
{
|
|
"entropy": 5.584348726272583,
|
|
"epoch": 1.7481327567810412,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004702865442499572,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.1828996628522873,
|
|
"num_tokens": 34738600.0,
|
|
"step": 15565
|
|
},
|
|
{
|
|
"entropy": 5.646577262878418,
|
|
"epoch": 1.7486943336889986,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004702666005282759,
|
|
"loss": 5.4411,
|
|
"mean_token_accuracy": 0.1821493536233902,
|
|
"num_tokens": 34749810.0,
|
|
"step": 15570
|
|
},
|
|
{
|
|
"entropy": 5.783751440048218,
|
|
"epoch": 1.7492559105969563,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004702466505892304,
|
|
"loss": 5.6074,
|
|
"mean_token_accuracy": 0.1706284061074257,
|
|
"num_tokens": 34762029.0,
|
|
"step": 15575
|
|
},
|
|
{
|
|
"entropy": 5.570149230957031,
|
|
"epoch": 1.749817487504914,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00047022669443345575,
|
|
"loss": 5.4278,
|
|
"mean_token_accuracy": 0.18540889173746108,
|
|
"num_tokens": 34773160.0,
|
|
"step": 15580
|
|
},
|
|
{
|
|
"entropy": 5.4772313117980955,
|
|
"epoch": 1.7503790644128714,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00047020673206158743,
|
|
"loss": 5.3943,
|
|
"mean_token_accuracy": 0.18494369238615035,
|
|
"num_tokens": 34784659.0,
|
|
"step": 15585
|
|
},
|
|
{
|
|
"entropy": 5.663392829895019,
|
|
"epoch": 1.7509406413208288,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000470186763474261,
|
|
"loss": 5.3792,
|
|
"mean_token_accuracy": 0.18774221539497377,
|
|
"num_tokens": 34796976.0,
|
|
"step": 15590
|
|
},
|
|
{
|
|
"entropy": 5.540497350692749,
|
|
"epoch": 1.7515022182287865,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004701667886721125,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.1866961508989334,
|
|
"num_tokens": 34809271.0,
|
|
"step": 15595
|
|
},
|
|
{
|
|
"entropy": 5.555431938171386,
|
|
"epoch": 1.752063795136744,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004701468076557776,
|
|
"loss": 5.397,
|
|
"mean_token_accuracy": 0.18635219633579253,
|
|
"num_tokens": 34820291.0,
|
|
"step": 15600
|
|
},
|
|
{
|
|
"entropy": 5.490622282028198,
|
|
"epoch": 1.7526253720447014,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00047012682042589277,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.19393441081047058,
|
|
"num_tokens": 34831224.0,
|
|
"step": 15605
|
|
},
|
|
{
|
|
"entropy": 5.639893341064453,
|
|
"epoch": 1.753186948952659,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00047010682698309423,
|
|
"loss": 5.3883,
|
|
"mean_token_accuracy": 0.18732714653015137,
|
|
"num_tokens": 34842947.0,
|
|
"step": 15610
|
|
},
|
|
{
|
|
"entropy": 5.553979587554932,
|
|
"epoch": 1.7537485258606167,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004700868273280186,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.19574182629585266,
|
|
"num_tokens": 34853422.0,
|
|
"step": 15615
|
|
},
|
|
{
|
|
"entropy": 5.490517807006836,
|
|
"epoch": 1.7543101027685741,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.00047006682146130273,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.18289577215909958,
|
|
"num_tokens": 34864082.0,
|
|
"step": 15620
|
|
},
|
|
{
|
|
"entropy": 5.513972234725952,
|
|
"epoch": 1.7548716796765316,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004700468093835837,
|
|
"loss": 5.3295,
|
|
"mean_token_accuracy": 0.1938301518559456,
|
|
"num_tokens": 34874094.0,
|
|
"step": 15625
|
|
},
|
|
{
|
|
"entropy": 5.492033338546753,
|
|
"epoch": 1.7554332565844892,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00047002679109549864,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.19001140743494033,
|
|
"num_tokens": 34884597.0,
|
|
"step": 15630
|
|
},
|
|
{
|
|
"entropy": 5.4309392929077145,
|
|
"epoch": 1.755994833492447,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00047000676659768477,
|
|
"loss": 5.2212,
|
|
"mean_token_accuracy": 0.197855706512928,
|
|
"num_tokens": 34894746.0,
|
|
"step": 15635
|
|
},
|
|
{
|
|
"entropy": 5.5205765724182125,
|
|
"epoch": 1.7565564104004043,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004699867358907799,
|
|
"loss": 5.2533,
|
|
"mean_token_accuracy": 0.19430377334356308,
|
|
"num_tokens": 34906250.0,
|
|
"step": 15640
|
|
},
|
|
{
|
|
"entropy": 5.617281484603882,
|
|
"epoch": 1.7571179873083618,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004699666989754217,
|
|
"loss": 5.518,
|
|
"mean_token_accuracy": 0.17946161180734635,
|
|
"num_tokens": 34917772.0,
|
|
"step": 15645
|
|
},
|
|
{
|
|
"entropy": 5.58783917427063,
|
|
"epoch": 1.7576795642163194,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004699466558522482,
|
|
"loss": 5.3465,
|
|
"mean_token_accuracy": 0.19344176799058915,
|
|
"num_tokens": 34930243.0,
|
|
"step": 15650
|
|
},
|
|
{
|
|
"entropy": 5.515490341186523,
|
|
"epoch": 1.758241141124277,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046992660652189755,
|
|
"loss": 5.3711,
|
|
"mean_token_accuracy": 0.18888648599386215,
|
|
"num_tokens": 34941357.0,
|
|
"step": 15655
|
|
},
|
|
{
|
|
"entropy": 5.68783860206604,
|
|
"epoch": 1.7588027180322345,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046990655098500824,
|
|
"loss": 5.4917,
|
|
"mean_token_accuracy": 0.17438853085041045,
|
|
"num_tokens": 34952116.0,
|
|
"step": 15660
|
|
},
|
|
{
|
|
"entropy": 5.572920417785644,
|
|
"epoch": 1.759364294940192,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046988648924221866,
|
|
"loss": 5.3776,
|
|
"mean_token_accuracy": 0.18735404461622238,
|
|
"num_tokens": 34963707.0,
|
|
"step": 15665
|
|
},
|
|
{
|
|
"entropy": 5.591964197158814,
|
|
"epoch": 1.7599258718481496,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004698664212941677,
|
|
"loss": 5.4903,
|
|
"mean_token_accuracy": 0.1865868628025055,
|
|
"num_tokens": 34974376.0,
|
|
"step": 15670
|
|
},
|
|
{
|
|
"entropy": 5.56675443649292,
|
|
"epoch": 1.7604874487561073,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046984634714149437,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.18472738265991212,
|
|
"num_tokens": 34986183.0,
|
|
"step": 15675
|
|
},
|
|
{
|
|
"entropy": 5.661499881744385,
|
|
"epoch": 1.7610490256640647,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004698262667848377,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.19106657952070236,
|
|
"num_tokens": 34997137.0,
|
|
"step": 15680
|
|
},
|
|
{
|
|
"entropy": 5.673861789703369,
|
|
"epoch": 1.7616106025720222,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046980618022483714,
|
|
"loss": 5.5377,
|
|
"mean_token_accuracy": 0.17761271595954894,
|
|
"num_tokens": 35008944.0,
|
|
"step": 15685
|
|
},
|
|
{
|
|
"entropy": 5.585244464874267,
|
|
"epoch": 1.7621721794799798,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046978608746213224,
|
|
"loss": 5.4294,
|
|
"mean_token_accuracy": 0.18042032569646835,
|
|
"num_tokens": 35019972.0,
|
|
"step": 15690
|
|
},
|
|
{
|
|
"entropy": 5.52788348197937,
|
|
"epoch": 1.7627337563879373,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004697659884973628,
|
|
"loss": 5.312,
|
|
"mean_token_accuracy": 0.19038559794425963,
|
|
"num_tokens": 35031285.0,
|
|
"step": 15695
|
|
},
|
|
{
|
|
"entropy": 5.502678537368775,
|
|
"epoch": 1.7632953332958947,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004697458833311687,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.1871246799826622,
|
|
"num_tokens": 35042553.0,
|
|
"step": 15700
|
|
},
|
|
{
|
|
"entropy": 5.6457356929779055,
|
|
"epoch": 1.7638569102038524,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004697257719641902,
|
|
"loss": 5.5228,
|
|
"mean_token_accuracy": 0.17717983424663544,
|
|
"num_tokens": 35053637.0,
|
|
"step": 15705
|
|
},
|
|
{
|
|
"entropy": 5.619772911071777,
|
|
"epoch": 1.76441848711181,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004697056543970676,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.191217540204525,
|
|
"num_tokens": 35064754.0,
|
|
"step": 15710
|
|
},
|
|
{
|
|
"entropy": 5.62962760925293,
|
|
"epoch": 1.7649800640197675,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046968553063044146,
|
|
"loss": 5.3443,
|
|
"mean_token_accuracy": 0.18473501950502397,
|
|
"num_tokens": 35075816.0,
|
|
"step": 15715
|
|
},
|
|
{
|
|
"entropy": 5.596509647369385,
|
|
"epoch": 1.765541640927725,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046966540066495247,
|
|
"loss": 5.4568,
|
|
"mean_token_accuracy": 0.1858111098408699,
|
|
"num_tokens": 35088647.0,
|
|
"step": 15720
|
|
},
|
|
{
|
|
"entropy": 5.556439971923828,
|
|
"epoch": 1.7661032178356826,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.00046964526450124164,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.1902667373418808,
|
|
"num_tokens": 35099372.0,
|
|
"step": 15725
|
|
},
|
|
{
|
|
"entropy": 5.613338136672974,
|
|
"epoch": 1.7666647947436402,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046962512213995,
|
|
"loss": 5.4708,
|
|
"mean_token_accuracy": 0.17770947217941285,
|
|
"num_tokens": 35110663.0,
|
|
"step": 15730
|
|
},
|
|
{
|
|
"entropy": 5.741875314712525,
|
|
"epoch": 1.7672263716515977,
|
|
"grad_norm": 2.640625,
|
|
"learning_rate": 0.00046960497358171913,
|
|
"loss": 5.5694,
|
|
"mean_token_accuracy": 0.17378438115119935,
|
|
"num_tokens": 35122406.0,
|
|
"step": 15735
|
|
},
|
|
{
|
|
"entropy": 5.540828084945678,
|
|
"epoch": 1.7677879485595551,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046958481882719035,
|
|
"loss": 5.3321,
|
|
"mean_token_accuracy": 0.1855219706892967,
|
|
"num_tokens": 35133444.0,
|
|
"step": 15740
|
|
},
|
|
{
|
|
"entropy": 5.558192110061645,
|
|
"epoch": 1.7683495254675128,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00046956465787700554,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.18510175347328187,
|
|
"num_tokens": 35143840.0,
|
|
"step": 15745
|
|
},
|
|
{
|
|
"entropy": 5.629155921936035,
|
|
"epoch": 1.7689111023754704,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046954449073180644,
|
|
"loss": 5.5273,
|
|
"mean_token_accuracy": 0.1763617530465126,
|
|
"num_tokens": 35155050.0,
|
|
"step": 15750
|
|
},
|
|
{
|
|
"entropy": 5.674946022033692,
|
|
"epoch": 1.7694726792834279,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004695243173922354,
|
|
"loss": 5.4563,
|
|
"mean_token_accuracy": 0.1815337285399437,
|
|
"num_tokens": 35167649.0,
|
|
"step": 15755
|
|
},
|
|
{
|
|
"entropy": 5.590065813064575,
|
|
"epoch": 1.7700342561913853,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046950413785893465,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.18501245826482773,
|
|
"num_tokens": 35179238.0,
|
|
"step": 15760
|
|
},
|
|
{
|
|
"entropy": 5.587299394607544,
|
|
"epoch": 1.770595833099343,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046948395213254667,
|
|
"loss": 5.423,
|
|
"mean_token_accuracy": 0.1895361915230751,
|
|
"num_tokens": 35189510.0,
|
|
"step": 15765
|
|
},
|
|
{
|
|
"entropy": 5.627476501464844,
|
|
"epoch": 1.7711574100073006,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.0004694637602137143,
|
|
"loss": 5.4019,
|
|
"mean_token_accuracy": 0.18205129504203796,
|
|
"num_tokens": 35199727.0,
|
|
"step": 15770
|
|
},
|
|
{
|
|
"entropy": 5.543097496032715,
|
|
"epoch": 1.771718986915258,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004694435621030803,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.19201646596193314,
|
|
"num_tokens": 35210311.0,
|
|
"step": 15775
|
|
},
|
|
{
|
|
"entropy": 5.565152502059936,
|
|
"epoch": 1.7722805638232155,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046942335780128785,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.18896471112966537,
|
|
"num_tokens": 35222755.0,
|
|
"step": 15780
|
|
},
|
|
{
|
|
"entropy": 5.577018547058105,
|
|
"epoch": 1.7728421407311732,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046940314730898035,
|
|
"loss": 5.392,
|
|
"mean_token_accuracy": 0.18427122831344606,
|
|
"num_tokens": 35234337.0,
|
|
"step": 15785
|
|
},
|
|
{
|
|
"entropy": 5.561712837219238,
|
|
"epoch": 1.7734037176391306,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004693829306268012,
|
|
"loss": 5.375,
|
|
"mean_token_accuracy": 0.18425782918930053,
|
|
"num_tokens": 35245736.0,
|
|
"step": 15790
|
|
},
|
|
{
|
|
"entropy": 5.549394416809082,
|
|
"epoch": 1.773965294547088,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004693627077553942,
|
|
"loss": 5.313,
|
|
"mean_token_accuracy": 0.19118868112564086,
|
|
"num_tokens": 35256368.0,
|
|
"step": 15795
|
|
},
|
|
{
|
|
"entropy": 5.531165742874146,
|
|
"epoch": 1.7745268714550457,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004693424786954031,
|
|
"loss": 5.4077,
|
|
"mean_token_accuracy": 0.19057601541280747,
|
|
"num_tokens": 35267238.0,
|
|
"step": 15800
|
|
},
|
|
{
|
|
"entropy": 5.588297748565674,
|
|
"epoch": 1.7750884483630034,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046932224344747224,
|
|
"loss": 5.3301,
|
|
"mean_token_accuracy": 0.18491076081991195,
|
|
"num_tokens": 35277113.0,
|
|
"step": 15805
|
|
},
|
|
{
|
|
"entropy": 5.54120717048645,
|
|
"epoch": 1.7756500252709608,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046930200201224573,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.18561243265867233,
|
|
"num_tokens": 35288504.0,
|
|
"step": 15810
|
|
},
|
|
{
|
|
"entropy": 5.501207256317139,
|
|
"epoch": 1.7762116021789183,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004692817543903681,
|
|
"loss": 5.3211,
|
|
"mean_token_accuracy": 0.18900217711925507,
|
|
"num_tokens": 35301215.0,
|
|
"step": 15815
|
|
},
|
|
{
|
|
"entropy": 5.5304208278656,
|
|
"epoch": 1.776773179086876,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.000469261500582484,
|
|
"loss": 5.3157,
|
|
"mean_token_accuracy": 0.1854766219854355,
|
|
"num_tokens": 35311997.0,
|
|
"step": 15820
|
|
},
|
|
{
|
|
"entropy": 5.590717792510986,
|
|
"epoch": 1.7773347559948336,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046924124058923843,
|
|
"loss": 5.3933,
|
|
"mean_token_accuracy": 0.18797389268875123,
|
|
"num_tokens": 35323217.0,
|
|
"step": 15825
|
|
},
|
|
{
|
|
"entropy": 5.604794216156006,
|
|
"epoch": 1.777896332902791,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004692209744112765,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.19090602695941924,
|
|
"num_tokens": 35333102.0,
|
|
"step": 15830
|
|
},
|
|
{
|
|
"entropy": 5.6566074848175045,
|
|
"epoch": 1.7784579098107485,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004692007020492433,
|
|
"loss": 5.4539,
|
|
"mean_token_accuracy": 0.18121746331453323,
|
|
"num_tokens": 35346394.0,
|
|
"step": 15835
|
|
},
|
|
{
|
|
"entropy": 5.4409726619720455,
|
|
"epoch": 1.7790194867187061,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004691804235037845,
|
|
"loss": 5.2403,
|
|
"mean_token_accuracy": 0.19641357213258742,
|
|
"num_tokens": 35357827.0,
|
|
"step": 15840
|
|
},
|
|
{
|
|
"entropy": 5.504426956176758,
|
|
"epoch": 1.7795810636266638,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004691601387755456,
|
|
"loss": 5.3757,
|
|
"mean_token_accuracy": 0.1856133833527565,
|
|
"num_tokens": 35370517.0,
|
|
"step": 15845
|
|
},
|
|
{
|
|
"entropy": 5.642001581192017,
|
|
"epoch": 1.7801426405346212,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046913984786517275,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.18046326488256453,
|
|
"num_tokens": 35381830.0,
|
|
"step": 15850
|
|
},
|
|
{
|
|
"entropy": 5.697717666625977,
|
|
"epoch": 1.7807042174425787,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046911955077331177,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.1731054440140724,
|
|
"num_tokens": 35393161.0,
|
|
"step": 15855
|
|
},
|
|
{
|
|
"entropy": 5.599428796768189,
|
|
"epoch": 1.7812657943505363,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046909924750060893,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.19308048188686372,
|
|
"num_tokens": 35403338.0,
|
|
"step": 15860
|
|
},
|
|
{
|
|
"entropy": 5.599169588088989,
|
|
"epoch": 1.781827371258494,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004690789380477109,
|
|
"loss": 5.4309,
|
|
"mean_token_accuracy": 0.17985658645629882,
|
|
"num_tokens": 35415862.0,
|
|
"step": 15865
|
|
},
|
|
{
|
|
"entropy": 5.504052400588989,
|
|
"epoch": 1.7823889481664514,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004690586224152641,
|
|
"loss": 5.3192,
|
|
"mean_token_accuracy": 0.18855463862419128,
|
|
"num_tokens": 35426696.0,
|
|
"step": 15870
|
|
},
|
|
{
|
|
"entropy": 5.547023773193359,
|
|
"epoch": 1.7829505250744089,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004690383006039156,
|
|
"loss": 5.3708,
|
|
"mean_token_accuracy": 0.18854738026857376,
|
|
"num_tokens": 35438624.0,
|
|
"step": 15875
|
|
},
|
|
{
|
|
"entropy": 5.645945501327515,
|
|
"epoch": 1.7835121019823665,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004690179726143123,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.18324332386255265,
|
|
"num_tokens": 35449841.0,
|
|
"step": 15880
|
|
},
|
|
{
|
|
"entropy": 5.806521368026734,
|
|
"epoch": 1.784073678890324,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004689976384471014,
|
|
"loss": 5.6024,
|
|
"mean_token_accuracy": 0.1749742865562439,
|
|
"num_tokens": 35462081.0,
|
|
"step": 15885
|
|
},
|
|
{
|
|
"entropy": 5.492288398742676,
|
|
"epoch": 1.7846352557982814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004689772981029306,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.19096229076385499,
|
|
"num_tokens": 35472834.0,
|
|
"step": 15890
|
|
},
|
|
{
|
|
"entropy": 5.483275270462036,
|
|
"epoch": 1.785196832706239,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004689569515824473,
|
|
"loss": 5.2306,
|
|
"mean_token_accuracy": 0.19336001873016356,
|
|
"num_tokens": 35482975.0,
|
|
"step": 15895
|
|
},
|
|
{
|
|
"entropy": 5.46476411819458,
|
|
"epoch": 1.7857584096141967,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004689365988862995,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.1841615468263626,
|
|
"num_tokens": 35494470.0,
|
|
"step": 15900
|
|
},
|
|
{
|
|
"entropy": 5.484210443496704,
|
|
"epoch": 1.7863199865221542,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046891624001513515,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.18654714226722718,
|
|
"num_tokens": 35505464.0,
|
|
"step": 15905
|
|
},
|
|
{
|
|
"entropy": 5.519054889678955,
|
|
"epoch": 1.7868815634301116,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046889587496960257,
|
|
"loss": 5.3609,
|
|
"mean_token_accuracy": 0.18699045181274415,
|
|
"num_tokens": 35517609.0,
|
|
"step": 15910
|
|
},
|
|
{
|
|
"entropy": 5.535554218292236,
|
|
"epoch": 1.7874431403380693,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046887550375034997,
|
|
"loss": 5.2723,
|
|
"mean_token_accuracy": 0.19254475980997085,
|
|
"num_tokens": 35528994.0,
|
|
"step": 15915
|
|
},
|
|
{
|
|
"entropy": 5.544394063949585,
|
|
"epoch": 1.788004717246027,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046885512635802627,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.17600288093090058,
|
|
"num_tokens": 35541044.0,
|
|
"step": 15920
|
|
},
|
|
{
|
|
"entropy": 5.546467065811157,
|
|
"epoch": 1.7885662941539844,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004688347427932801,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.19480267465114592,
|
|
"num_tokens": 35552660.0,
|
|
"step": 15925
|
|
},
|
|
{
|
|
"entropy": 5.639483213424683,
|
|
"epoch": 1.7891278710619418,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046881435305676055,
|
|
"loss": 5.4037,
|
|
"mean_token_accuracy": 0.1806935966014862,
|
|
"num_tokens": 35565144.0,
|
|
"step": 15930
|
|
},
|
|
{
|
|
"entropy": 5.573234605789184,
|
|
"epoch": 1.7896894479698995,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046879395714911686,
|
|
"loss": 5.3582,
|
|
"mean_token_accuracy": 0.1856307253241539,
|
|
"num_tokens": 35577067.0,
|
|
"step": 15935
|
|
},
|
|
{
|
|
"entropy": 5.480866718292236,
|
|
"epoch": 1.7902510248778571,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046877355507099846,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.1896669551730156,
|
|
"num_tokens": 35588712.0,
|
|
"step": 15940
|
|
},
|
|
{
|
|
"entropy": 5.5005041599273685,
|
|
"epoch": 1.7908126017858146,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004687531468230549,
|
|
"loss": 5.2888,
|
|
"mean_token_accuracy": 0.185869762301445,
|
|
"num_tokens": 35599212.0,
|
|
"step": 15945
|
|
},
|
|
{
|
|
"entropy": 5.5777387619018555,
|
|
"epoch": 1.791374178693772,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004687327324059359,
|
|
"loss": 5.3444,
|
|
"mean_token_accuracy": 0.18815338164567946,
|
|
"num_tokens": 35609397.0,
|
|
"step": 15950
|
|
},
|
|
{
|
|
"entropy": 5.581180047988892,
|
|
"epoch": 1.7919357556017297,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004687123118202916,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.184771266579628,
|
|
"num_tokens": 35620615.0,
|
|
"step": 15955
|
|
},
|
|
{
|
|
"entropy": 5.629911661148071,
|
|
"epoch": 1.7924973325096873,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004686918850667722,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.1877639338374138,
|
|
"num_tokens": 35632684.0,
|
|
"step": 15960
|
|
},
|
|
{
|
|
"entropy": 5.550001716613769,
|
|
"epoch": 1.7930589094176448,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000468671452146028,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.18706910759210588,
|
|
"num_tokens": 35643896.0,
|
|
"step": 15965
|
|
},
|
|
{
|
|
"entropy": 5.571665620803833,
|
|
"epoch": 1.7936204863256022,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046865101305870965,
|
|
"loss": 5.347,
|
|
"mean_token_accuracy": 0.19187052249908448,
|
|
"num_tokens": 35655752.0,
|
|
"step": 15970
|
|
},
|
|
{
|
|
"entropy": 5.460735845565796,
|
|
"epoch": 1.7941820632335599,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000468630567805468,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.18869236558675767,
|
|
"num_tokens": 35665870.0,
|
|
"step": 15975
|
|
},
|
|
{
|
|
"entropy": 5.528667259216308,
|
|
"epoch": 1.7947436401415173,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000468610116386954,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1825406700372696,
|
|
"num_tokens": 35677792.0,
|
|
"step": 15980
|
|
},
|
|
{
|
|
"entropy": 5.546282482147217,
|
|
"epoch": 1.7953052170494748,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004685896588038187,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.187219101190567,
|
|
"num_tokens": 35689059.0,
|
|
"step": 15985
|
|
},
|
|
{
|
|
"entropy": 5.561834621429443,
|
|
"epoch": 1.7958667939574324,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004685691950567136,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.180425526201725,
|
|
"num_tokens": 35699953.0,
|
|
"step": 15990
|
|
},
|
|
{
|
|
"entropy": 5.603364276885986,
|
|
"epoch": 1.79642837086539,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046854872514629035,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.18564161509275437,
|
|
"num_tokens": 35710894.0,
|
|
"step": 15995
|
|
},
|
|
{
|
|
"entropy": 5.523373460769653,
|
|
"epoch": 1.7969899477733475,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004685282490732005,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.18250859826803206,
|
|
"num_tokens": 35722440.0,
|
|
"step": 16000
|
|
},
|
|
{
|
|
"entropy": 5.492196273803711,
|
|
"epoch": 1.797551524681305,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00046850776683809623,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.1913005918264389,
|
|
"num_tokens": 35733768.0,
|
|
"step": 16005
|
|
},
|
|
{
|
|
"entropy": 5.599816846847534,
|
|
"epoch": 1.7981131015892626,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004684872784416295,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.18957294523715973,
|
|
"num_tokens": 35744211.0,
|
|
"step": 16010
|
|
},
|
|
{
|
|
"entropy": 5.522316741943359,
|
|
"epoch": 1.7986746784972203,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004684667838844529,
|
|
"loss": 5.3785,
|
|
"mean_token_accuracy": 0.18913964182138443,
|
|
"num_tokens": 35755498.0,
|
|
"step": 16015
|
|
},
|
|
{
|
|
"entropy": 5.590417671203613,
|
|
"epoch": 1.7992362554051777,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004684462831672188,
|
|
"loss": 5.396,
|
|
"mean_token_accuracy": 0.18859418034553527,
|
|
"num_tokens": 35767442.0,
|
|
"step": 16020
|
|
},
|
|
{
|
|
"entropy": 5.517408227920532,
|
|
"epoch": 1.7997978323131352,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046842577629058006,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.19182632118463516,
|
|
"num_tokens": 35778040.0,
|
|
"step": 16025
|
|
},
|
|
{
|
|
"entropy": 5.5260649681091305,
|
|
"epoch": 1.8003594092210928,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004684052632551896,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.19448763281106948,
|
|
"num_tokens": 35788139.0,
|
|
"step": 16030
|
|
},
|
|
{
|
|
"entropy": 5.525516414642334,
|
|
"epoch": 1.8009209861290505,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046838474406170046,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.18789254277944564,
|
|
"num_tokens": 35799077.0,
|
|
"step": 16035
|
|
},
|
|
{
|
|
"entropy": 5.555387830734253,
|
|
"epoch": 1.801482563037008,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046836421871076616,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.18327100276947023,
|
|
"num_tokens": 35809748.0,
|
|
"step": 16040
|
|
},
|
|
{
|
|
"entropy": 5.620476818084716,
|
|
"epoch": 1.8020441399449654,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004683436872030401,
|
|
"loss": 5.4143,
|
|
"mean_token_accuracy": 0.18668506890535355,
|
|
"num_tokens": 35821621.0,
|
|
"step": 16045
|
|
},
|
|
{
|
|
"entropy": 5.574615573883056,
|
|
"epoch": 1.802605716852923,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00046832314953917605,
|
|
"loss": 5.3402,
|
|
"mean_token_accuracy": 0.189327409863472,
|
|
"num_tokens": 35833497.0,
|
|
"step": 16050
|
|
},
|
|
{
|
|
"entropy": 5.649515771865845,
|
|
"epoch": 1.8031672937608807,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046830260571982795,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.18848424702882766,
|
|
"num_tokens": 35844266.0,
|
|
"step": 16055
|
|
},
|
|
{
|
|
"entropy": 5.654657030105591,
|
|
"epoch": 1.8037288706688381,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004682820557456499,
|
|
"loss": 5.4692,
|
|
"mean_token_accuracy": 0.18158279955387116,
|
|
"num_tokens": 35855260.0,
|
|
"step": 16060
|
|
},
|
|
{
|
|
"entropy": 5.586683559417724,
|
|
"epoch": 1.8042904475767956,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046826149961729625,
|
|
"loss": 5.3908,
|
|
"mean_token_accuracy": 0.1884553089737892,
|
|
"num_tokens": 35865950.0,
|
|
"step": 16065
|
|
},
|
|
{
|
|
"entropy": 5.5849017143249515,
|
|
"epoch": 1.8048520244847532,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00046824093733542144,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.1796557068824768,
|
|
"num_tokens": 35877028.0,
|
|
"step": 16070
|
|
},
|
|
{
|
|
"entropy": 5.564942026138306,
|
|
"epoch": 1.8054136013927107,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00046822036890068033,
|
|
"loss": 5.3832,
|
|
"mean_token_accuracy": 0.18363112062215806,
|
|
"num_tokens": 35887831.0,
|
|
"step": 16075
|
|
},
|
|
{
|
|
"entropy": 5.590927505493164,
|
|
"epoch": 1.8059751783006681,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046819979431372773,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.19229669570922853,
|
|
"num_tokens": 35897946.0,
|
|
"step": 16080
|
|
},
|
|
{
|
|
"entropy": 5.672337436676026,
|
|
"epoch": 1.8065367552086258,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046817921357521865,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.1830137401819229,
|
|
"num_tokens": 35910973.0,
|
|
"step": 16085
|
|
},
|
|
{
|
|
"entropy": 5.620429563522339,
|
|
"epoch": 1.8070983321165834,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046815862668580854,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.17881544381380082,
|
|
"num_tokens": 35921478.0,
|
|
"step": 16090
|
|
},
|
|
{
|
|
"entropy": 5.582594919204712,
|
|
"epoch": 1.8076599090245409,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004681380336461528,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.19607065469026566,
|
|
"num_tokens": 35932211.0,
|
|
"step": 16095
|
|
},
|
|
{
|
|
"entropy": 5.469005584716797,
|
|
"epoch": 1.8082214859324983,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046811743445690724,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.18346918523311614,
|
|
"num_tokens": 35944350.0,
|
|
"step": 16100
|
|
},
|
|
{
|
|
"entropy": 5.623713064193725,
|
|
"epoch": 1.808783062840456,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004680968291187276,
|
|
"loss": 5.4631,
|
|
"mean_token_accuracy": 0.18263631463050842,
|
|
"num_tokens": 35955590.0,
|
|
"step": 16105
|
|
},
|
|
{
|
|
"entropy": 5.527838087081909,
|
|
"epoch": 1.8093446397484136,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004680762176322701,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19768508821725844,
|
|
"num_tokens": 35965872.0,
|
|
"step": 16110
|
|
},
|
|
{
|
|
"entropy": 5.491130065917969,
|
|
"epoch": 1.809906216656371,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046805559999819093,
|
|
"loss": 5.3406,
|
|
"mean_token_accuracy": 0.1876350909471512,
|
|
"num_tokens": 35976851.0,
|
|
"step": 16115
|
|
},
|
|
{
|
|
"entropy": 5.573330354690552,
|
|
"epoch": 1.8104677935643285,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004680349762171465,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.18497663736343384,
|
|
"num_tokens": 35986984.0,
|
|
"step": 16120
|
|
},
|
|
{
|
|
"entropy": 5.572206926345825,
|
|
"epoch": 1.8110293704722862,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004680143462897936,
|
|
"loss": 5.3964,
|
|
"mean_token_accuracy": 0.18287460654973983,
|
|
"num_tokens": 35999349.0,
|
|
"step": 16125
|
|
},
|
|
{
|
|
"entropy": 5.57323203086853,
|
|
"epoch": 1.8115909473802438,
|
|
"grad_norm": 1.890625,
|
|
"learning_rate": 0.0004679937102167891,
|
|
"loss": 5.4072,
|
|
"mean_token_accuracy": 0.1872829779982567,
|
|
"num_tokens": 36011122.0,
|
|
"step": 16130
|
|
},
|
|
{
|
|
"entropy": 5.616017198562622,
|
|
"epoch": 1.8121525242882013,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046797306799879,
|
|
"loss": 5.3342,
|
|
"mean_token_accuracy": 0.19002778083086014,
|
|
"num_tokens": 36022729.0,
|
|
"step": 16135
|
|
},
|
|
{
|
|
"entropy": 5.47162880897522,
|
|
"epoch": 1.8127141011961587,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046795241963645356,
|
|
"loss": 5.321,
|
|
"mean_token_accuracy": 0.18759965449571608,
|
|
"num_tokens": 36034042.0,
|
|
"step": 16140
|
|
},
|
|
{
|
|
"entropy": 5.539858770370484,
|
|
"epoch": 1.8132756781041164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004679317651304373,
|
|
"loss": 5.3714,
|
|
"mean_token_accuracy": 0.1838579222559929,
|
|
"num_tokens": 36045357.0,
|
|
"step": 16145
|
|
},
|
|
{
|
|
"entropy": 5.4432172775268555,
|
|
"epoch": 1.813837255012074,
|
|
"grad_norm": 2.515625,
|
|
"learning_rate": 0.0004679111044813987,
|
|
"loss": 5.1253,
|
|
"mean_token_accuracy": 0.19835015535354614,
|
|
"num_tokens": 36055180.0,
|
|
"step": 16150
|
|
},
|
|
{
|
|
"entropy": 5.489971685409546,
|
|
"epoch": 1.8143988319200315,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046789043768999573,
|
|
"loss": 5.2725,
|
|
"mean_token_accuracy": 0.19322363436222076,
|
|
"num_tokens": 36065574.0,
|
|
"step": 16155
|
|
},
|
|
{
|
|
"entropy": 5.510469579696656,
|
|
"epoch": 1.814960408827989,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004678697647568865,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.18765803426504135,
|
|
"num_tokens": 36077316.0,
|
|
"step": 16160
|
|
},
|
|
{
|
|
"entropy": 5.523150253295898,
|
|
"epoch": 1.8155219857359466,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046784908568272903,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.18998877406120301,
|
|
"num_tokens": 36088735.0,
|
|
"step": 16165
|
|
},
|
|
{
|
|
"entropy": 5.533297109603882,
|
|
"epoch": 1.8160835626439042,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000467828400468182,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.1888634294271469,
|
|
"num_tokens": 36098806.0,
|
|
"step": 16170
|
|
},
|
|
{
|
|
"entropy": 5.589130115509033,
|
|
"epoch": 1.8166451395518615,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00046780770911390387,
|
|
"loss": 5.4131,
|
|
"mean_token_accuracy": 0.18185719549655915,
|
|
"num_tokens": 36110333.0,
|
|
"step": 16175
|
|
},
|
|
{
|
|
"entropy": 5.646198463439942,
|
|
"epoch": 1.8172067164598191,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004677870116205534,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.18725590854883195,
|
|
"num_tokens": 36121719.0,
|
|
"step": 16180
|
|
},
|
|
{
|
|
"entropy": 5.538517951965332,
|
|
"epoch": 1.8177682933677768,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046776630798878985,
|
|
"loss": 5.2564,
|
|
"mean_token_accuracy": 0.19654612243175507,
|
|
"num_tokens": 36132129.0,
|
|
"step": 16185
|
|
},
|
|
{
|
|
"entropy": 5.619850540161133,
|
|
"epoch": 1.8183298702757342,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004677455982192723,
|
|
"loss": 5.5641,
|
|
"mean_token_accuracy": 0.18335972130298614,
|
|
"num_tokens": 36145189.0,
|
|
"step": 16190
|
|
},
|
|
{
|
|
"entropy": 5.583048391342163,
|
|
"epoch": 1.8188914471836917,
|
|
"grad_norm": 2.875,
|
|
"learning_rate": 0.00046772488231266004,
|
|
"loss": 5.3038,
|
|
"mean_token_accuracy": 0.18865644931793213,
|
|
"num_tokens": 36157896.0,
|
|
"step": 16195
|
|
},
|
|
{
|
|
"entropy": 5.608990430831909,
|
|
"epoch": 1.8194530240916493,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046770416026961284,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.18688480108976363,
|
|
"num_tokens": 36168842.0,
|
|
"step": 16200
|
|
},
|
|
{
|
|
"entropy": 5.43107590675354,
|
|
"epoch": 1.820014600999607,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004676834320907904,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.190485979616642,
|
|
"num_tokens": 36180075.0,
|
|
"step": 16205
|
|
},
|
|
{
|
|
"entropy": 5.476920318603516,
|
|
"epoch": 1.8205761779075644,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004676626977768528,
|
|
"loss": 5.2997,
|
|
"mean_token_accuracy": 0.19336915910243987,
|
|
"num_tokens": 36190589.0,
|
|
"step": 16210
|
|
},
|
|
{
|
|
"entropy": 5.445828580856324,
|
|
"epoch": 1.8211377548155219,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046764195732846013,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.19461333751678467,
|
|
"num_tokens": 36201145.0,
|
|
"step": 16215
|
|
},
|
|
{
|
|
"entropy": 5.525165796279907,
|
|
"epoch": 1.8216993317234795,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.00046762121074627285,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.18935733735561372,
|
|
"num_tokens": 36213243.0,
|
|
"step": 16220
|
|
},
|
|
{
|
|
"entropy": 5.437792634963989,
|
|
"epoch": 1.8222609086314372,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00046760045803095153,
|
|
"loss": 5.2863,
|
|
"mean_token_accuracy": 0.19440049231052398,
|
|
"num_tokens": 36224491.0,
|
|
"step": 16225
|
|
},
|
|
{
|
|
"entropy": 5.494497346878052,
|
|
"epoch": 1.8228224855393946,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004675796991831569,
|
|
"loss": 5.3388,
|
|
"mean_token_accuracy": 0.18706730008125305,
|
|
"num_tokens": 36236006.0,
|
|
"step": 16230
|
|
},
|
|
{
|
|
"entropy": 5.712548160552979,
|
|
"epoch": 1.823384062447352,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046755893420355,
|
|
"loss": 5.4417,
|
|
"mean_token_accuracy": 0.18242204934358597,
|
|
"num_tokens": 36246925.0,
|
|
"step": 16235
|
|
},
|
|
{
|
|
"entropy": 5.563034200668335,
|
|
"epoch": 1.8239456393553097,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004675381630927919,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.18443493098020552,
|
|
"num_tokens": 36258449.0,
|
|
"step": 16240
|
|
},
|
|
{
|
|
"entropy": 5.538782167434692,
|
|
"epoch": 1.8245072162632674,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046751738585154405,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.18277619630098343,
|
|
"num_tokens": 36270820.0,
|
|
"step": 16245
|
|
},
|
|
{
|
|
"entropy": 5.672790098190307,
|
|
"epoch": 1.8250687931712248,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00046749660248046794,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.18669208884239197,
|
|
"num_tokens": 36282346.0,
|
|
"step": 16250
|
|
},
|
|
{
|
|
"entropy": 5.605333566665649,
|
|
"epoch": 1.8256303700791823,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046747581298022537,
|
|
"loss": 5.4515,
|
|
"mean_token_accuracy": 0.17685943841934204,
|
|
"num_tokens": 36294111.0,
|
|
"step": 16255
|
|
},
|
|
{
|
|
"entropy": 5.480431413650512,
|
|
"epoch": 1.82619194698714,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004674550173514782,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.1893106371164322,
|
|
"num_tokens": 36304899.0,
|
|
"step": 16260
|
|
},
|
|
{
|
|
"entropy": 5.5797313213348385,
|
|
"epoch": 1.8267535238950976,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00046743421559488875,
|
|
"loss": 5.4565,
|
|
"mean_token_accuracy": 0.18013825863599778,
|
|
"num_tokens": 36316272.0,
|
|
"step": 16265
|
|
},
|
|
{
|
|
"entropy": 5.566914081573486,
|
|
"epoch": 1.8273151008030548,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046741340771111917,
|
|
"loss": 5.2578,
|
|
"mean_token_accuracy": 0.19387683719396592,
|
|
"num_tokens": 36326624.0,
|
|
"step": 16270
|
|
},
|
|
{
|
|
"entropy": 5.512542104721069,
|
|
"epoch": 1.8278766777110125,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046739259370083205,
|
|
"loss": 5.2759,
|
|
"mean_token_accuracy": 0.1949551746249199,
|
|
"num_tokens": 36338178.0,
|
|
"step": 16275
|
|
},
|
|
{
|
|
"entropy": 5.640486335754394,
|
|
"epoch": 1.8284382546189701,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004673717735646902,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.18785100877285005,
|
|
"num_tokens": 36349993.0,
|
|
"step": 16280
|
|
},
|
|
{
|
|
"entropy": 5.630641984939575,
|
|
"epoch": 1.8289998315269276,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004673509473033564,
|
|
"loss": 5.4369,
|
|
"mean_token_accuracy": 0.18203034102916718,
|
|
"num_tokens": 36361002.0,
|
|
"step": 16285
|
|
},
|
|
{
|
|
"entropy": 5.556751489639282,
|
|
"epoch": 1.829561408434885,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046733011491749383,
|
|
"loss": 5.3607,
|
|
"mean_token_accuracy": 0.1891090378165245,
|
|
"num_tokens": 36371688.0,
|
|
"step": 16290
|
|
},
|
|
{
|
|
"entropy": 5.487711811065674,
|
|
"epoch": 1.8301229853428427,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004673092764077658,
|
|
"loss": 5.307,
|
|
"mean_token_accuracy": 0.19521596878767014,
|
|
"num_tokens": 36382683.0,
|
|
"step": 16295
|
|
},
|
|
{
|
|
"entropy": 5.610037326812744,
|
|
"epoch": 1.8306845622508003,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004672884317748359,
|
|
"loss": 5.4621,
|
|
"mean_token_accuracy": 0.18013550192117692,
|
|
"num_tokens": 36394170.0,
|
|
"step": 16300
|
|
},
|
|
{
|
|
"entropy": 5.638150024414062,
|
|
"epoch": 1.8312461391587578,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004672675810193677,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.18480715155601501,
|
|
"num_tokens": 36405613.0,
|
|
"step": 16305
|
|
},
|
|
{
|
|
"entropy": 5.655437421798706,
|
|
"epoch": 1.8318077160667152,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00046724672414202514,
|
|
"loss": 5.4266,
|
|
"mean_token_accuracy": 0.18558551520109176,
|
|
"num_tokens": 36416282.0,
|
|
"step": 16310
|
|
},
|
|
{
|
|
"entropy": 5.634707260131836,
|
|
"epoch": 1.8323692929746729,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004672258611434724,
|
|
"loss": 5.4509,
|
|
"mean_token_accuracy": 0.17985614389181137,
|
|
"num_tokens": 36427624.0,
|
|
"step": 16315
|
|
},
|
|
{
|
|
"entropy": 5.528849172592163,
|
|
"epoch": 1.8329308698826305,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046720499202437354,
|
|
"loss": 5.2419,
|
|
"mean_token_accuracy": 0.20107460767030716,
|
|
"num_tokens": 36438230.0,
|
|
"step": 16320
|
|
},
|
|
{
|
|
"entropy": 5.591752767562866,
|
|
"epoch": 1.833492446790588,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004671841167853933,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.1863241508603096,
|
|
"num_tokens": 36448854.0,
|
|
"step": 16325
|
|
},
|
|
{
|
|
"entropy": 5.53044376373291,
|
|
"epoch": 1.8340540236985454,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004671632354271962,
|
|
"loss": 5.3773,
|
|
"mean_token_accuracy": 0.18363479673862457,
|
|
"num_tokens": 36460426.0,
|
|
"step": 16330
|
|
},
|
|
{
|
|
"entropy": 5.618747568130493,
|
|
"epoch": 1.834615600606503,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046714234795044724,
|
|
"loss": 5.3684,
|
|
"mean_token_accuracy": 0.18348488956689835,
|
|
"num_tokens": 36470914.0,
|
|
"step": 16335
|
|
},
|
|
{
|
|
"entropy": 5.540546703338623,
|
|
"epoch": 1.8351771775144607,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004671214543558113,
|
|
"loss": 5.2828,
|
|
"mean_token_accuracy": 0.19130490124225616,
|
|
"num_tokens": 36480753.0,
|
|
"step": 16340
|
|
},
|
|
{
|
|
"entropy": 5.5322356700897215,
|
|
"epoch": 1.8357387544224182,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004671005546439538,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.1919824331998825,
|
|
"num_tokens": 36492858.0,
|
|
"step": 16345
|
|
},
|
|
{
|
|
"entropy": 5.476413679122925,
|
|
"epoch": 1.8363003313303756,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046707964881554005,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.19456968307495118,
|
|
"num_tokens": 36503912.0,
|
|
"step": 16350
|
|
},
|
|
{
|
|
"entropy": 5.4944082736969,
|
|
"epoch": 1.8368619082383333,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046705873687123586,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.18888866305351257,
|
|
"num_tokens": 36515410.0,
|
|
"step": 16355
|
|
},
|
|
{
|
|
"entropy": 5.542603206634522,
|
|
"epoch": 1.837423485146291,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00046703781881170703,
|
|
"loss": 5.2669,
|
|
"mean_token_accuracy": 0.1883430689573288,
|
|
"num_tokens": 36526310.0,
|
|
"step": 16360
|
|
},
|
|
{
|
|
"entropy": 5.48847599029541,
|
|
"epoch": 1.8379850620542482,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.00046701689463761947,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1896289050579071,
|
|
"num_tokens": 36537081.0,
|
|
"step": 16365
|
|
},
|
|
{
|
|
"entropy": 5.500782012939453,
|
|
"epoch": 1.8385466389622058,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046699596434963953,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.1886397421360016,
|
|
"num_tokens": 36549419.0,
|
|
"step": 16370
|
|
},
|
|
{
|
|
"entropy": 5.462937688827514,
|
|
"epoch": 1.8391082158701635,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004669750279484337,
|
|
"loss": 5.3053,
|
|
"mean_token_accuracy": 0.19588281959295273,
|
|
"num_tokens": 36560842.0,
|
|
"step": 16375
|
|
},
|
|
{
|
|
"entropy": 5.540846300125122,
|
|
"epoch": 1.839669792778121,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004669540854346685,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.19223497360944747,
|
|
"num_tokens": 36571717.0,
|
|
"step": 16380
|
|
},
|
|
{
|
|
"entropy": 5.5494654178619385,
|
|
"epoch": 1.8402313696860784,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046693313680901073,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.1912903755903244,
|
|
"num_tokens": 36581709.0,
|
|
"step": 16385
|
|
},
|
|
{
|
|
"entropy": 5.4772059440612795,
|
|
"epoch": 1.840792946594036,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046691218207212744,
|
|
"loss": 5.3421,
|
|
"mean_token_accuracy": 0.18470590710639953,
|
|
"num_tokens": 36593033.0,
|
|
"step": 16390
|
|
},
|
|
{
|
|
"entropy": 5.578347063064575,
|
|
"epoch": 1.8413545235019937,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004668912212246859,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.18642119318246841,
|
|
"num_tokens": 36603605.0,
|
|
"step": 16395
|
|
},
|
|
{
|
|
"entropy": 5.636160516738892,
|
|
"epoch": 1.8419161004099511,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046687025426735335,
|
|
"loss": 5.4519,
|
|
"mean_token_accuracy": 0.1835762158036232,
|
|
"num_tokens": 36616219.0,
|
|
"step": 16400
|
|
},
|
|
{
|
|
"entropy": 5.610563802719116,
|
|
"epoch": 1.8424776773179086,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004668492812007976,
|
|
"loss": 5.3925,
|
|
"mean_token_accuracy": 0.18824509233236314,
|
|
"num_tokens": 36627777.0,
|
|
"step": 16405
|
|
},
|
|
{
|
|
"entropy": 5.5810723304748535,
|
|
"epoch": 1.8430392542258662,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004668283020256863,
|
|
"loss": 5.343,
|
|
"mean_token_accuracy": 0.18585171103477477,
|
|
"num_tokens": 36638792.0,
|
|
"step": 16410
|
|
},
|
|
{
|
|
"entropy": 5.539824533462524,
|
|
"epoch": 1.843600831133824,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.00046680731674268744,
|
|
"loss": 5.3578,
|
|
"mean_token_accuracy": 0.19007993191480638,
|
|
"num_tokens": 36650218.0,
|
|
"step": 16415
|
|
},
|
|
{
|
|
"entropy": 5.554005861282349,
|
|
"epoch": 1.8441624080417813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004667863253524692,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.18815506845712662,
|
|
"num_tokens": 36660987.0,
|
|
"step": 16420
|
|
},
|
|
{
|
|
"entropy": 5.505265617370606,
|
|
"epoch": 1.8447239849497388,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046676532785569995,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1836427703499794,
|
|
"num_tokens": 36671270.0,
|
|
"step": 16425
|
|
},
|
|
{
|
|
"entropy": 5.550834274291992,
|
|
"epoch": 1.8452855618576964,
|
|
"grad_norm": 2.015625,
|
|
"learning_rate": 0.0004667443242530484,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.19693876802921295,
|
|
"num_tokens": 36682484.0,
|
|
"step": 16430
|
|
},
|
|
{
|
|
"entropy": 5.544925594329834,
|
|
"epoch": 1.845847138765654,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046672331454518314,
|
|
"loss": 5.4023,
|
|
"mean_token_accuracy": 0.18727923184633255,
|
|
"num_tokens": 36693723.0,
|
|
"step": 16435
|
|
},
|
|
{
|
|
"entropy": 5.438486576080322,
|
|
"epoch": 1.8464087156736115,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004667022987327732,
|
|
"loss": 5.1992,
|
|
"mean_token_accuracy": 0.1977972447872162,
|
|
"num_tokens": 36704166.0,
|
|
"step": 16440
|
|
},
|
|
{
|
|
"entropy": 5.493281126022339,
|
|
"epoch": 1.846970292581569,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004666812768164877,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.1943044513463974,
|
|
"num_tokens": 36714139.0,
|
|
"step": 16445
|
|
},
|
|
{
|
|
"entropy": 5.560811567306518,
|
|
"epoch": 1.8475318694895266,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00046666024879699606,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.19593967348337174,
|
|
"num_tokens": 36724273.0,
|
|
"step": 16450
|
|
},
|
|
{
|
|
"entropy": 5.527120590209961,
|
|
"epoch": 1.8480934463974843,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046663921467496766,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.18444978594779968,
|
|
"num_tokens": 36735176.0,
|
|
"step": 16455
|
|
},
|
|
{
|
|
"entropy": 5.438452100753784,
|
|
"epoch": 1.8486550233054415,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004666181744510724,
|
|
"loss": 5.2855,
|
|
"mean_token_accuracy": 0.19109829962253572,
|
|
"num_tokens": 36746170.0,
|
|
"step": 16460
|
|
},
|
|
{
|
|
"entropy": 5.60580530166626,
|
|
"epoch": 1.8492166002133992,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00046659712812598017,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.18250878900289536,
|
|
"num_tokens": 36756969.0,
|
|
"step": 16465
|
|
},
|
|
{
|
|
"entropy": 5.690599012374878,
|
|
"epoch": 1.8497781771213568,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046657607570036103,
|
|
"loss": 5.322,
|
|
"mean_token_accuracy": 0.1903391644358635,
|
|
"num_tokens": 36767892.0,
|
|
"step": 16470
|
|
},
|
|
{
|
|
"entropy": 5.508238983154297,
|
|
"epoch": 1.8503397540293143,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046655501717488533,
|
|
"loss": 5.3193,
|
|
"mean_token_accuracy": 0.1926638275384903,
|
|
"num_tokens": 36778967.0,
|
|
"step": 16475
|
|
},
|
|
{
|
|
"entropy": 5.419472026824951,
|
|
"epoch": 1.8509013309372717,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004665339525502236,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.18942113369703292,
|
|
"num_tokens": 36789204.0,
|
|
"step": 16480
|
|
},
|
|
{
|
|
"entropy": 5.4896093845367435,
|
|
"epoch": 1.8514629078452294,
|
|
"grad_norm": 1.8359375,
|
|
"learning_rate": 0.00046651288182704653,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.19748687446117402,
|
|
"num_tokens": 36798990.0,
|
|
"step": 16485
|
|
},
|
|
{
|
|
"entropy": 5.58982400894165,
|
|
"epoch": 1.852024484753187,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004664918050060251,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.18887744396924971,
|
|
"num_tokens": 36809988.0,
|
|
"step": 16490
|
|
},
|
|
{
|
|
"entropy": 5.510670232772827,
|
|
"epoch": 1.8525860616611445,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004664707220878302,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.2002943843603134,
|
|
"num_tokens": 36821579.0,
|
|
"step": 16495
|
|
},
|
|
{
|
|
"entropy": 5.628005266189575,
|
|
"epoch": 1.853147638569102,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004664496330731334,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.18711163997650146,
|
|
"num_tokens": 36833141.0,
|
|
"step": 16500
|
|
},
|
|
{
|
|
"entropy": 5.587767934799194,
|
|
"epoch": 1.8537092154770596,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004664285379626059,
|
|
"loss": 5.4287,
|
|
"mean_token_accuracy": 0.18868701308965682,
|
|
"num_tokens": 36843347.0,
|
|
"step": 16505
|
|
},
|
|
{
|
|
"entropy": 5.583380556106567,
|
|
"epoch": 1.8542707923850172,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00046640743675691954,
|
|
"loss": 5.4489,
|
|
"mean_token_accuracy": 0.17965279370546341,
|
|
"num_tokens": 36854459.0,
|
|
"step": 16510
|
|
},
|
|
{
|
|
"entropy": 5.484674119949341,
|
|
"epoch": 1.8548323692929747,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004663863294567462,
|
|
"loss": 5.1682,
|
|
"mean_token_accuracy": 0.18858336806297302,
|
|
"num_tokens": 36864761.0,
|
|
"step": 16515
|
|
},
|
|
{
|
|
"entropy": 5.645143175125122,
|
|
"epoch": 1.8553939462009321,
|
|
"grad_norm": 2.25,
|
|
"learning_rate": 0.0004663652160627579,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.18329710364341736,
|
|
"num_tokens": 36875413.0,
|
|
"step": 16520
|
|
},
|
|
{
|
|
"entropy": 5.544934558868408,
|
|
"epoch": 1.8559555231088898,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00046634409657562683,
|
|
"loss": 5.3563,
|
|
"mean_token_accuracy": 0.18826665133237838,
|
|
"num_tokens": 36885350.0,
|
|
"step": 16525
|
|
},
|
|
{
|
|
"entropy": 5.508081722259521,
|
|
"epoch": 1.8565171000168474,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004663229709960255,
|
|
"loss": 5.2461,
|
|
"mean_token_accuracy": 0.19512075185775757,
|
|
"num_tokens": 36895355.0,
|
|
"step": 16530
|
|
},
|
|
{
|
|
"entropy": 5.553179788589477,
|
|
"epoch": 1.8570786769248049,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.00046630183932462664,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.1899194061756134,
|
|
"num_tokens": 36907454.0,
|
|
"step": 16535
|
|
},
|
|
{
|
|
"entropy": 5.504468727111816,
|
|
"epoch": 1.8576402538327623,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004662807015621031,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.18382397890090943,
|
|
"num_tokens": 36919199.0,
|
|
"step": 16540
|
|
},
|
|
{
|
|
"entropy": 5.65816559791565,
|
|
"epoch": 1.85820183074072,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00046625955770912764,
|
|
"loss": 5.4373,
|
|
"mean_token_accuracy": 0.18306384682655336,
|
|
"num_tokens": 36930499.0,
|
|
"step": 16545
|
|
},
|
|
{
|
|
"entropy": 5.591771984100342,
|
|
"epoch": 1.8587634076486776,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046623840776637384,
|
|
"loss": 5.3683,
|
|
"mean_token_accuracy": 0.18520331233739853,
|
|
"num_tokens": 36943082.0,
|
|
"step": 16550
|
|
},
|
|
{
|
|
"entropy": 5.4489147663116455,
|
|
"epoch": 1.859324984556635,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004662172517345149,
|
|
"loss": 5.2681,
|
|
"mean_token_accuracy": 0.1908291056752205,
|
|
"num_tokens": 36954591.0,
|
|
"step": 16555
|
|
},
|
|
{
|
|
"entropy": 5.479098653793335,
|
|
"epoch": 1.8598865614645925,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004661960896142245,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.19094809293746948,
|
|
"num_tokens": 36967028.0,
|
|
"step": 16560
|
|
},
|
|
{
|
|
"entropy": 5.54519624710083,
|
|
"epoch": 1.8604481383725502,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046617492140617654,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.1847678914666176,
|
|
"num_tokens": 36978716.0,
|
|
"step": 16565
|
|
},
|
|
{
|
|
"entropy": 5.555908060073852,
|
|
"epoch": 1.8610097152805076,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004661537471110448,
|
|
"loss": 5.2763,
|
|
"mean_token_accuracy": 0.19336800426244735,
|
|
"num_tokens": 36989416.0,
|
|
"step": 16570
|
|
},
|
|
{
|
|
"entropy": 5.578537178039551,
|
|
"epoch": 1.861571292188465,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004661325667295037,
|
|
"loss": 5.3394,
|
|
"mean_token_accuracy": 0.19259405732154847,
|
|
"num_tokens": 37002197.0,
|
|
"step": 16575
|
|
},
|
|
{
|
|
"entropy": 5.671295118331909,
|
|
"epoch": 1.8621328690964227,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004661113802622275,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.17447530031204223,
|
|
"num_tokens": 37012977.0,
|
|
"step": 16580
|
|
},
|
|
{
|
|
"entropy": 5.548588609695434,
|
|
"epoch": 1.8626944460043804,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004660901877098908,
|
|
"loss": 5.3596,
|
|
"mean_token_accuracy": 0.1864728808403015,
|
|
"num_tokens": 37024141.0,
|
|
"step": 16585
|
|
},
|
|
{
|
|
"entropy": 5.482138967514038,
|
|
"epoch": 1.8632560229123378,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004660689890731685,
|
|
"loss": 5.2757,
|
|
"mean_token_accuracy": 0.19443291574716567,
|
|
"num_tokens": 37034471.0,
|
|
"step": 16590
|
|
},
|
|
{
|
|
"entropy": 5.556358575820923,
|
|
"epoch": 1.8638175998202953,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00046604778435273546,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.1903866708278656,
|
|
"num_tokens": 37046375.0,
|
|
"step": 16595
|
|
},
|
|
{
|
|
"entropy": 5.577647876739502,
|
|
"epoch": 1.864379176728253,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00046602657354926686,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.19433042258024216,
|
|
"num_tokens": 37056617.0,
|
|
"step": 16600
|
|
},
|
|
{
|
|
"entropy": 5.469070196151733,
|
|
"epoch": 1.8649407536362106,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000466005356663438,
|
|
"loss": 5.1792,
|
|
"mean_token_accuracy": 0.19848380386829376,
|
|
"num_tokens": 37066477.0,
|
|
"step": 16605
|
|
},
|
|
{
|
|
"entropy": 5.518620872497559,
|
|
"epoch": 1.865502330544168,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046598413369592463,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.1845397397875786,
|
|
"num_tokens": 37077150.0,
|
|
"step": 16610
|
|
},
|
|
{
|
|
"entropy": 5.627141857147217,
|
|
"epoch": 1.8660639074521255,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004659629046474023,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.18467328250408171,
|
|
"num_tokens": 37089961.0,
|
|
"step": 16615
|
|
},
|
|
{
|
|
"entropy": 5.643972587585449,
|
|
"epoch": 1.8666254843600831,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000465941669518547,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.1841304361820221,
|
|
"num_tokens": 37100779.0,
|
|
"step": 16620
|
|
},
|
|
{
|
|
"entropy": 5.550005626678467,
|
|
"epoch": 1.8671870612680408,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004659204283100349,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.19424606263637542,
|
|
"num_tokens": 37111293.0,
|
|
"step": 16625
|
|
},
|
|
{
|
|
"entropy": 5.550073909759521,
|
|
"epoch": 1.8677486381759982,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046589918102254237,
|
|
"loss": 5.3834,
|
|
"mean_token_accuracy": 0.1909703478217125,
|
|
"num_tokens": 37123087.0,
|
|
"step": 16630
|
|
},
|
|
{
|
|
"entropy": 5.521503162384033,
|
|
"epoch": 1.8683102150839557,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004658779276567458,
|
|
"loss": 5.3555,
|
|
"mean_token_accuracy": 0.189847494661808,
|
|
"num_tokens": 37135227.0,
|
|
"step": 16635
|
|
},
|
|
{
|
|
"entropy": 5.554212331771851,
|
|
"epoch": 1.8688717919919133,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00046585666821332203,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.18797996491193772,
|
|
"num_tokens": 37146970.0,
|
|
"step": 16640
|
|
},
|
|
{
|
|
"entropy": 5.583242273330688,
|
|
"epoch": 1.869433368899871,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046583540269294794,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.1878607377409935,
|
|
"num_tokens": 37158144.0,
|
|
"step": 16645
|
|
},
|
|
{
|
|
"entropy": 5.5672338008880615,
|
|
"epoch": 1.8699949458078284,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004658141310963006,
|
|
"loss": 5.4428,
|
|
"mean_token_accuracy": 0.1881876543164253,
|
|
"num_tokens": 37169265.0,
|
|
"step": 16650
|
|
},
|
|
{
|
|
"entropy": 5.575741100311279,
|
|
"epoch": 1.8705565227157859,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004657928534240573,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.18534027487039567,
|
|
"num_tokens": 37179186.0,
|
|
"step": 16655
|
|
},
|
|
{
|
|
"entropy": 5.615464735031128,
|
|
"epoch": 1.8711180996237435,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004657715696768955,
|
|
"loss": 5.3253,
|
|
"mean_token_accuracy": 0.19169517904520034,
|
|
"num_tokens": 37188906.0,
|
|
"step": 16660
|
|
},
|
|
{
|
|
"entropy": 5.462756586074829,
|
|
"epoch": 1.871679676531701,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000465750279855493,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1957893118262291,
|
|
"num_tokens": 37200879.0,
|
|
"step": 16665
|
|
},
|
|
{
|
|
"entropy": 5.506002759933471,
|
|
"epoch": 1.8722412534396584,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004657289839605276,
|
|
"loss": 5.2715,
|
|
"mean_token_accuracy": 0.19352867901325227,
|
|
"num_tokens": 37211648.0,
|
|
"step": 16670
|
|
},
|
|
{
|
|
"entropy": 5.701457500457764,
|
|
"epoch": 1.872802830347616,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004657076819926774,
|
|
"loss": 5.4624,
|
|
"mean_token_accuracy": 0.1890949472784996,
|
|
"num_tokens": 37223164.0,
|
|
"step": 16675
|
|
},
|
|
{
|
|
"entropy": 5.554787683486938,
|
|
"epoch": 1.8733644072555737,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.0004656863739526206,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.19128381311893464,
|
|
"num_tokens": 37233860.0,
|
|
"step": 16680
|
|
},
|
|
{
|
|
"entropy": 5.572649192810059,
|
|
"epoch": 1.8739259841635312,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046566505984103575,
|
|
"loss": 5.2864,
|
|
"mean_token_accuracy": 0.18871597647666932,
|
|
"num_tokens": 37245431.0,
|
|
"step": 16685
|
|
},
|
|
{
|
|
"entropy": 5.555394458770752,
|
|
"epoch": 1.8744875610714886,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004656437396586014,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.184270641207695,
|
|
"num_tokens": 37256394.0,
|
|
"step": 16690
|
|
},
|
|
{
|
|
"entropy": 5.542269945144653,
|
|
"epoch": 1.8750491379794463,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004656224134059964,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.18762631714344025,
|
|
"num_tokens": 37268367.0,
|
|
"step": 16695
|
|
},
|
|
{
|
|
"entropy": 5.575541687011719,
|
|
"epoch": 1.875610714887404,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046560108108389985,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.19120696783065796,
|
|
"num_tokens": 37279019.0,
|
|
"step": 16700
|
|
},
|
|
{
|
|
"entropy": 5.614797353744507,
|
|
"epoch": 1.8761722917953614,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000465579742692991,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.18774400055408477,
|
|
"num_tokens": 37289806.0,
|
|
"step": 16705
|
|
},
|
|
{
|
|
"entropy": 5.503408479690552,
|
|
"epoch": 1.8767338687033188,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004655583982339492,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.1851000264286995,
|
|
"num_tokens": 37300607.0,
|
|
"step": 16710
|
|
},
|
|
{
|
|
"entropy": 5.582626056671143,
|
|
"epoch": 1.8772954456112765,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004655370477074541,
|
|
"loss": 5.4008,
|
|
"mean_token_accuracy": 0.18489654660224913,
|
|
"num_tokens": 37311966.0,
|
|
"step": 16715
|
|
},
|
|
{
|
|
"entropy": 5.4730767726898195,
|
|
"epoch": 1.8778570225192341,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004655156911141855,
|
|
"loss": 5.3289,
|
|
"mean_token_accuracy": 0.18872059434652327,
|
|
"num_tokens": 37324459.0,
|
|
"step": 16720
|
|
},
|
|
{
|
|
"entropy": 5.54251537322998,
|
|
"epoch": 1.8784185994271916,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004654943284548234,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.18824678361415864,
|
|
"num_tokens": 37335276.0,
|
|
"step": 16725
|
|
},
|
|
{
|
|
"entropy": 5.571168088912964,
|
|
"epoch": 1.878980176335149,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00046547295973004807,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.1914811834692955,
|
|
"num_tokens": 37347274.0,
|
|
"step": 16730
|
|
},
|
|
{
|
|
"entropy": 5.546994829177857,
|
|
"epoch": 1.8795417532431067,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046545158494053966,
|
|
"loss": 5.3755,
|
|
"mean_token_accuracy": 0.18126369267702103,
|
|
"num_tokens": 37359789.0,
|
|
"step": 16735
|
|
},
|
|
{
|
|
"entropy": 5.538412046432495,
|
|
"epoch": 1.8801033301510643,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00046543020408697905,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.19285972267389298,
|
|
"num_tokens": 37369851.0,
|
|
"step": 16740
|
|
},
|
|
{
|
|
"entropy": 5.637153387069702,
|
|
"epoch": 1.8806649070590218,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046540881717004685,
|
|
"loss": 5.4866,
|
|
"mean_token_accuracy": 0.1827334225177765,
|
|
"num_tokens": 37381008.0,
|
|
"step": 16745
|
|
},
|
|
{
|
|
"entropy": 5.5416699886322025,
|
|
"epoch": 1.8812264839669792,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004653874241904241,
|
|
"loss": 5.3128,
|
|
"mean_token_accuracy": 0.18703739196062089,
|
|
"num_tokens": 37392110.0,
|
|
"step": 16750
|
|
},
|
|
{
|
|
"entropy": 5.622640085220337,
|
|
"epoch": 1.8817880608749369,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004653660251487919,
|
|
"loss": 5.3473,
|
|
"mean_token_accuracy": 0.19627908170223235,
|
|
"num_tokens": 37402995.0,
|
|
"step": 16755
|
|
},
|
|
{
|
|
"entropy": 5.585756111145019,
|
|
"epoch": 1.8823496377828943,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046534462004583154,
|
|
"loss": 5.3505,
|
|
"mean_token_accuracy": 0.18679337352514266,
|
|
"num_tokens": 37415072.0,
|
|
"step": 16760
|
|
},
|
|
{
|
|
"entropy": 5.638362407684326,
|
|
"epoch": 1.8829112146908518,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004653232088822248,
|
|
"loss": 5.495,
|
|
"mean_token_accuracy": 0.1807260826230049,
|
|
"num_tokens": 37427375.0,
|
|
"step": 16765
|
|
},
|
|
{
|
|
"entropy": 5.475346612930298,
|
|
"epoch": 1.8834727915988094,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004653017916586532,
|
|
"loss": 5.269,
|
|
"mean_token_accuracy": 0.1959826171398163,
|
|
"num_tokens": 37436829.0,
|
|
"step": 16770
|
|
},
|
|
{
|
|
"entropy": 5.593945503234863,
|
|
"epoch": 1.884034368506767,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004652803683757987,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.17825179547071457,
|
|
"num_tokens": 37447875.0,
|
|
"step": 16775
|
|
},
|
|
{
|
|
"entropy": 5.4862525939941404,
|
|
"epoch": 1.8845959454147245,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004652589390343436,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19161031693220137,
|
|
"num_tokens": 37458408.0,
|
|
"step": 16780
|
|
},
|
|
{
|
|
"entropy": 5.525433826446533,
|
|
"epoch": 1.885157522322682,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046523750363497,
|
|
"loss": 5.3196,
|
|
"mean_token_accuracy": 0.187734891474247,
|
|
"num_tokens": 37468437.0,
|
|
"step": 16785
|
|
},
|
|
{
|
|
"entropy": 5.639262437820435,
|
|
"epoch": 1.8857190992306396,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004652160621783605,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.19055986255407334,
|
|
"num_tokens": 37479359.0,
|
|
"step": 16790
|
|
},
|
|
{
|
|
"entropy": 5.52949333190918,
|
|
"epoch": 1.8862806761385973,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00046519461466519785,
|
|
"loss": 5.3416,
|
|
"mean_token_accuracy": 0.1894940882921219,
|
|
"num_tokens": 37491321.0,
|
|
"step": 16795
|
|
},
|
|
{
|
|
"entropy": 5.57505841255188,
|
|
"epoch": 1.8868422530465547,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004651731610961649,
|
|
"loss": 5.3608,
|
|
"mean_token_accuracy": 0.18788401633501053,
|
|
"num_tokens": 37501828.0,
|
|
"step": 16800
|
|
},
|
|
{
|
|
"entropy": 5.683385896682739,
|
|
"epoch": 1.8874038299545122,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004651517014719446,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.1801801174879074,
|
|
"num_tokens": 37514525.0,
|
|
"step": 16805
|
|
},
|
|
{
|
|
"entropy": 5.5657752513885494,
|
|
"epoch": 1.8879654068624698,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004651302357932206,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.18999105393886567,
|
|
"num_tokens": 37525588.0,
|
|
"step": 16810
|
|
},
|
|
{
|
|
"entropy": 5.509109449386597,
|
|
"epoch": 1.8885269837704275,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000465108764060676,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18761055618524553,
|
|
"num_tokens": 37537941.0,
|
|
"step": 16815
|
|
},
|
|
{
|
|
"entropy": 5.53486385345459,
|
|
"epoch": 1.889088560678385,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046508728627499464,
|
|
"loss": 5.3585,
|
|
"mean_token_accuracy": 0.18559655398130417,
|
|
"num_tokens": 37549663.0,
|
|
"step": 16820
|
|
},
|
|
{
|
|
"entropy": 5.628708600997925,
|
|
"epoch": 1.8896501375863424,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004650658024368604,
|
|
"loss": 5.4039,
|
|
"mean_token_accuracy": 0.18834484815597535,
|
|
"num_tokens": 37559793.0,
|
|
"step": 16825
|
|
},
|
|
{
|
|
"entropy": 5.518650531768799,
|
|
"epoch": 1.8902117144943,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004650443125469573,
|
|
"loss": 5.2597,
|
|
"mean_token_accuracy": 0.1900397002696991,
|
|
"num_tokens": 37570203.0,
|
|
"step": 16830
|
|
},
|
|
{
|
|
"entropy": 5.49616641998291,
|
|
"epoch": 1.8907732914022577,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004650228166059695,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.18863515555858612,
|
|
"num_tokens": 37581858.0,
|
|
"step": 16835
|
|
},
|
|
{
|
|
"entropy": 5.588530111312866,
|
|
"epoch": 1.8913348683102151,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004650013146145816,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.1901543766260147,
|
|
"num_tokens": 37592311.0,
|
|
"step": 16840
|
|
},
|
|
{
|
|
"entropy": 5.641404247283935,
|
|
"epoch": 1.8918964452181726,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004649798065734781,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.17920273542404175,
|
|
"num_tokens": 37604721.0,
|
|
"step": 16845
|
|
},
|
|
{
|
|
"entropy": 5.64134669303894,
|
|
"epoch": 1.8924580221261302,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046495829248334393,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.17941076159477234,
|
|
"num_tokens": 37616044.0,
|
|
"step": 16850
|
|
},
|
|
{
|
|
"entropy": 5.562013864517212,
|
|
"epoch": 1.8930195990340877,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004649367723448641,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.19128530025482177,
|
|
"num_tokens": 37626501.0,
|
|
"step": 16855
|
|
},
|
|
{
|
|
"entropy": 5.665068197250366,
|
|
"epoch": 1.8935811759420451,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046491524615872366,
|
|
"loss": 5.3843,
|
|
"mean_token_accuracy": 0.18378467857837677,
|
|
"num_tokens": 37637861.0,
|
|
"step": 16860
|
|
},
|
|
{
|
|
"entropy": 5.502087926864624,
|
|
"epoch": 1.8941427528500028,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00046489371392560816,
|
|
"loss": 5.2346,
|
|
"mean_token_accuracy": 0.1925298184156418,
|
|
"num_tokens": 37649288.0,
|
|
"step": 16865
|
|
},
|
|
{
|
|
"entropy": 5.4675586223602295,
|
|
"epoch": 1.8947043297579604,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046487217564620317,
|
|
"loss": 5.2391,
|
|
"mean_token_accuracy": 0.1927187532186508,
|
|
"num_tokens": 37659700.0,
|
|
"step": 16870
|
|
},
|
|
{
|
|
"entropy": 5.59060378074646,
|
|
"epoch": 1.8952659066659179,
|
|
"grad_norm": 3.234375,
|
|
"learning_rate": 0.0004648506313211945,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.18239943832159042,
|
|
"num_tokens": 37671739.0,
|
|
"step": 16875
|
|
},
|
|
{
|
|
"entropy": 5.587790775299072,
|
|
"epoch": 1.8958274835738753,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00046482908095126803,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.1989983633160591,
|
|
"num_tokens": 37682250.0,
|
|
"step": 16880
|
|
},
|
|
{
|
|
"entropy": 5.542448043823242,
|
|
"epoch": 1.896389060481833,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046480752453711,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.19146676808595658,
|
|
"num_tokens": 37694052.0,
|
|
"step": 16885
|
|
},
|
|
{
|
|
"entropy": 5.625333070755005,
|
|
"epoch": 1.8969506373897906,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004647859620794068,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.18763629645109176,
|
|
"num_tokens": 37704818.0,
|
|
"step": 16890
|
|
},
|
|
{
|
|
"entropy": 5.64872407913208,
|
|
"epoch": 1.897512214297748,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.00046476439357884497,
|
|
"loss": 5.5017,
|
|
"mean_token_accuracy": 0.17706990689039231,
|
|
"num_tokens": 37717679.0,
|
|
"step": 16895
|
|
},
|
|
{
|
|
"entropy": 5.5432963371276855,
|
|
"epoch": 1.8980737912057055,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046474281903611126,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.1889132410287857,
|
|
"num_tokens": 37728711.0,
|
|
"step": 16900
|
|
},
|
|
{
|
|
"entropy": 5.55089111328125,
|
|
"epoch": 1.8986353681136632,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046472123845189253,
|
|
"loss": 5.3252,
|
|
"mean_token_accuracy": 0.1860739842057228,
|
|
"num_tokens": 37740082.0,
|
|
"step": 16905
|
|
},
|
|
{
|
|
"entropy": 5.627832412719727,
|
|
"epoch": 1.8991969450216208,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000464699651826876,
|
|
"loss": 5.4481,
|
|
"mean_token_accuracy": 0.18166497200727463,
|
|
"num_tokens": 37750715.0,
|
|
"step": 16910
|
|
},
|
|
{
|
|
"entropy": 5.615968561172485,
|
|
"epoch": 1.8997585219295783,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046467805916174907,
|
|
"loss": 5.4249,
|
|
"mean_token_accuracy": 0.18018938452005387,
|
|
"num_tokens": 37763230.0,
|
|
"step": 16915
|
|
},
|
|
{
|
|
"entropy": 5.523409748077393,
|
|
"epoch": 1.9003200988375357,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046465646045719915,
|
|
"loss": 5.3005,
|
|
"mean_token_accuracy": 0.18863568753004073,
|
|
"num_tokens": 37773621.0,
|
|
"step": 16920
|
|
},
|
|
{
|
|
"entropy": 5.581793260574341,
|
|
"epoch": 1.9008816757454934,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004646348557139139,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.1867442399263382,
|
|
"num_tokens": 37785068.0,
|
|
"step": 16925
|
|
},
|
|
{
|
|
"entropy": 5.570795297622681,
|
|
"epoch": 1.901443252653451,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046461324493258133,
|
|
"loss": 5.38,
|
|
"mean_token_accuracy": 0.1871982604265213,
|
|
"num_tokens": 37796925.0,
|
|
"step": 16930
|
|
},
|
|
{
|
|
"entropy": 5.514643239974975,
|
|
"epoch": 1.9020048295614085,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046459162811388955,
|
|
"loss": 5.3779,
|
|
"mean_token_accuracy": 0.1877373620867729,
|
|
"num_tokens": 37808291.0,
|
|
"step": 16935
|
|
},
|
|
{
|
|
"entropy": 5.504942226409912,
|
|
"epoch": 1.902566406469366,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004645700052585267,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.2041929170489311,
|
|
"num_tokens": 37819337.0,
|
|
"step": 16940
|
|
},
|
|
{
|
|
"entropy": 5.598858737945557,
|
|
"epoch": 1.9031279833773236,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004645483763671815,
|
|
"loss": 5.4239,
|
|
"mean_token_accuracy": 0.18608152121305466,
|
|
"num_tokens": 37831832.0,
|
|
"step": 16945
|
|
},
|
|
{
|
|
"entropy": 5.550009822845459,
|
|
"epoch": 1.903689560285281,
|
|
"grad_norm": 2.078125,
|
|
"learning_rate": 0.00046452674144054236,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.19405739307403563,
|
|
"num_tokens": 37842586.0,
|
|
"step": 16950
|
|
},
|
|
{
|
|
"entropy": 5.4988868713378904,
|
|
"epoch": 1.9042511371932385,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00046450510047929826,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.19844567626714707,
|
|
"num_tokens": 37852198.0,
|
|
"step": 16955
|
|
},
|
|
{
|
|
"entropy": 5.532628107070923,
|
|
"epoch": 1.9048127141011961,
|
|
"grad_norm": 2.3125,
|
|
"learning_rate": 0.00046448345348413833,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.192024265229702,
|
|
"num_tokens": 37862967.0,
|
|
"step": 16960
|
|
},
|
|
{
|
|
"entropy": 5.543120098114014,
|
|
"epoch": 1.9053742910091538,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004644618004557517,
|
|
"loss": 5.4324,
|
|
"mean_token_accuracy": 0.183971007168293,
|
|
"num_tokens": 37874501.0,
|
|
"step": 16965
|
|
},
|
|
{
|
|
"entropy": 5.591376924514771,
|
|
"epoch": 1.9059358679171112,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004644401413948279,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.19970332384109496,
|
|
"num_tokens": 37886404.0,
|
|
"step": 16970
|
|
},
|
|
{
|
|
"entropy": 5.583517551422119,
|
|
"epoch": 1.9064974448250687,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004644184763020565,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.1829296812415123,
|
|
"num_tokens": 37897344.0,
|
|
"step": 16975
|
|
},
|
|
{
|
|
"entropy": 5.465759420394898,
|
|
"epoch": 1.9070590217330263,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004643968051781273,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.1973785489797592,
|
|
"num_tokens": 37909226.0,
|
|
"step": 16980
|
|
},
|
|
{
|
|
"entropy": 5.626458406448364,
|
|
"epoch": 1.907620598640984,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004643751280237305,
|
|
"loss": 5.3809,
|
|
"mean_token_accuracy": 0.18722111433744432,
|
|
"num_tokens": 37920578.0,
|
|
"step": 16985
|
|
},
|
|
{
|
|
"entropy": 5.574364566802979,
|
|
"epoch": 1.9081821755489414,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004643534448395561,
|
|
"loss": 5.2964,
|
|
"mean_token_accuracy": 0.18628410696983339,
|
|
"num_tokens": 37931814.0,
|
|
"step": 16990
|
|
},
|
|
{
|
|
"entropy": 5.4980494499206545,
|
|
"epoch": 1.9087437524568989,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004643317556262946,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.18958449214696885,
|
|
"num_tokens": 37942345.0,
|
|
"step": 16995
|
|
},
|
|
{
|
|
"entropy": 5.514918422698974,
|
|
"epoch": 1.9093053293648565,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046431006038463653,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19243414998054503,
|
|
"num_tokens": 37953027.0,
|
|
"step": 17000
|
|
},
|
|
{
|
|
"entropy": 5.573061800003051,
|
|
"epoch": 1.9098669062728142,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004642883591152727,
|
|
"loss": 5.3774,
|
|
"mean_token_accuracy": 0.1869850128889084,
|
|
"num_tokens": 37963290.0,
|
|
"step": 17005
|
|
},
|
|
{
|
|
"entropy": 5.57389726638794,
|
|
"epoch": 1.9104284831807716,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004642666518188942,
|
|
"loss": 5.4935,
|
|
"mean_token_accuracy": 0.1782187357544899,
|
|
"num_tokens": 37974424.0,
|
|
"step": 17010
|
|
},
|
|
{
|
|
"entropy": 5.673620700836182,
|
|
"epoch": 1.910990060088729,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00046424493849619205,
|
|
"loss": 5.4823,
|
|
"mean_token_accuracy": 0.1817783609032631,
|
|
"num_tokens": 37987993.0,
|
|
"step": 17015
|
|
},
|
|
{
|
|
"entropy": 5.580899572372436,
|
|
"epoch": 1.9115516369966867,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00046422321914785757,
|
|
"loss": 5.2667,
|
|
"mean_token_accuracy": 0.19043606519699097,
|
|
"num_tokens": 37999340.0,
|
|
"step": 17020
|
|
},
|
|
{
|
|
"entropy": 5.498477602005005,
|
|
"epoch": 1.9121132139046444,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00046420149377458255,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.18639178872108458,
|
|
"num_tokens": 38009737.0,
|
|
"step": 17025
|
|
},
|
|
{
|
|
"entropy": 5.507870769500732,
|
|
"epoch": 1.9126747908126018,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00046417976237705846,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.18807660937309265,
|
|
"num_tokens": 38021283.0,
|
|
"step": 17030
|
|
},
|
|
{
|
|
"entropy": 5.685011959075927,
|
|
"epoch": 1.9132363677205593,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046415802495597744,
|
|
"loss": 5.442,
|
|
"mean_token_accuracy": 0.18164873719215394,
|
|
"num_tokens": 38034044.0,
|
|
"step": 17035
|
|
},
|
|
{
|
|
"entropy": 5.535062408447265,
|
|
"epoch": 1.913797944628517,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046413628151203154,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.19163980484008789,
|
|
"num_tokens": 38044585.0,
|
|
"step": 17040
|
|
},
|
|
{
|
|
"entropy": 5.462966775894165,
|
|
"epoch": 1.9143595215364744,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046411453204591303,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.18797462582588195,
|
|
"num_tokens": 38055771.0,
|
|
"step": 17045
|
|
},
|
|
{
|
|
"entropy": 5.497290515899659,
|
|
"epoch": 1.9149210984444318,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046409277655831455,
|
|
"loss": 5.3357,
|
|
"mean_token_accuracy": 0.18783791959285737,
|
|
"num_tokens": 38066344.0,
|
|
"step": 17050
|
|
},
|
|
{
|
|
"entropy": 5.562441110610962,
|
|
"epoch": 1.9154826753523895,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004640710150499287,
|
|
"loss": 5.2773,
|
|
"mean_token_accuracy": 0.19176914542913437,
|
|
"num_tokens": 38077785.0,
|
|
"step": 17055
|
|
},
|
|
{
|
|
"entropy": 5.52891354560852,
|
|
"epoch": 1.9160442522603471,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046404924752144834,
|
|
"loss": 5.3914,
|
|
"mean_token_accuracy": 0.18672641664743422,
|
|
"num_tokens": 38089023.0,
|
|
"step": 17060
|
|
},
|
|
{
|
|
"entropy": 5.545773649215699,
|
|
"epoch": 1.9166058291683046,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046402747397356666,
|
|
"loss": 5.2467,
|
|
"mean_token_accuracy": 0.1955689385533333,
|
|
"num_tokens": 38099428.0,
|
|
"step": 17065
|
|
},
|
|
{
|
|
"entropy": 5.523291397094726,
|
|
"epoch": 1.917167406076262,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004640056944069768,
|
|
"loss": 5.2812,
|
|
"mean_token_accuracy": 0.18789494931697845,
|
|
"num_tokens": 38110757.0,
|
|
"step": 17070
|
|
},
|
|
{
|
|
"entropy": 5.575390005111695,
|
|
"epoch": 1.9177289829842197,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004639839088223725,
|
|
"loss": 5.3483,
|
|
"mean_token_accuracy": 0.1862165719270706,
|
|
"num_tokens": 38121442.0,
|
|
"step": 17075
|
|
},
|
|
{
|
|
"entropy": 5.577487230300903,
|
|
"epoch": 1.9182905598921773,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046396211722044716,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.1903044819831848,
|
|
"num_tokens": 38132917.0,
|
|
"step": 17080
|
|
},
|
|
{
|
|
"entropy": 5.463597249984741,
|
|
"epoch": 1.9188521368001348,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046394031960189473,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.18787554800510406,
|
|
"num_tokens": 38143188.0,
|
|
"step": 17085
|
|
},
|
|
{
|
|
"entropy": 5.616248273849488,
|
|
"epoch": 1.9194137137080922,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004639185159674093,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.18439114838838577,
|
|
"num_tokens": 38154300.0,
|
|
"step": 17090
|
|
},
|
|
{
|
|
"entropy": 5.620881509780884,
|
|
"epoch": 1.9199752906160499,
|
|
"grad_norm": 3.296875,
|
|
"learning_rate": 0.00046389670631768494,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.18610019087791443,
|
|
"num_tokens": 38165697.0,
|
|
"step": 17095
|
|
},
|
|
{
|
|
"entropy": 5.581836557388305,
|
|
"epoch": 1.9205368675240075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004638748906534162,
|
|
"loss": 5.3304,
|
|
"mean_token_accuracy": 0.19115062803030014,
|
|
"num_tokens": 38176601.0,
|
|
"step": 17100
|
|
},
|
|
{
|
|
"entropy": 5.6303528308868405,
|
|
"epoch": 1.921098444431965,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004638530689752977,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.1896706148982048,
|
|
"num_tokens": 38188334.0,
|
|
"step": 17105
|
|
},
|
|
{
|
|
"entropy": 5.62305965423584,
|
|
"epoch": 1.9216600213399224,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046383124128402433,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1895851030945778,
|
|
"num_tokens": 38199483.0,
|
|
"step": 17110
|
|
},
|
|
{
|
|
"entropy": 5.592094564437867,
|
|
"epoch": 1.92222159824788,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00046380940758029095,
|
|
"loss": 5.4402,
|
|
"mean_token_accuracy": 0.18754971474409105,
|
|
"num_tokens": 38211391.0,
|
|
"step": 17115
|
|
},
|
|
{
|
|
"entropy": 5.546466636657715,
|
|
"epoch": 1.9227831751558377,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046378756786479274,
|
|
"loss": 5.3151,
|
|
"mean_token_accuracy": 0.18852895498275757,
|
|
"num_tokens": 38223415.0,
|
|
"step": 17120
|
|
},
|
|
{
|
|
"entropy": 5.510998821258545,
|
|
"epoch": 1.9233447520637952,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004637657221382252,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19193917363882065,
|
|
"num_tokens": 38235093.0,
|
|
"step": 17125
|
|
},
|
|
{
|
|
"entropy": 5.587700748443604,
|
|
"epoch": 1.9239063289717526,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00046374387040128384,
|
|
"loss": 5.4153,
|
|
"mean_token_accuracy": 0.18143144845962525,
|
|
"num_tokens": 38247192.0,
|
|
"step": 17130
|
|
},
|
|
{
|
|
"entropy": 5.643863773345947,
|
|
"epoch": 1.9244679058797103,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046372201265466444,
|
|
"loss": 5.3897,
|
|
"mean_token_accuracy": 0.1838589146733284,
|
|
"num_tokens": 38257965.0,
|
|
"step": 17135
|
|
},
|
|
{
|
|
"entropy": 5.630653190612793,
|
|
"epoch": 1.9250294827876677,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000463700148899063,
|
|
"loss": 5.4753,
|
|
"mean_token_accuracy": 0.18052055090665817,
|
|
"num_tokens": 38268529.0,
|
|
"step": 17140
|
|
},
|
|
{
|
|
"entropy": 5.51701717376709,
|
|
"epoch": 1.9255910596956252,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004636782791351756,
|
|
"loss": 5.327,
|
|
"mean_token_accuracy": 0.18572959005832673,
|
|
"num_tokens": 38279480.0,
|
|
"step": 17145
|
|
},
|
|
{
|
|
"entropy": 5.615934658050537,
|
|
"epoch": 1.9261526366035828,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004636564033636987,
|
|
"loss": 5.4195,
|
|
"mean_token_accuracy": 0.18547072559595107,
|
|
"num_tokens": 38291670.0,
|
|
"step": 17150
|
|
},
|
|
{
|
|
"entropy": 5.495688772201538,
|
|
"epoch": 1.9267142135115405,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046363452158532857,
|
|
"loss": 5.1923,
|
|
"mean_token_accuracy": 0.2034456506371498,
|
|
"num_tokens": 38303073.0,
|
|
"step": 17155
|
|
},
|
|
{
|
|
"entropy": 5.571677303314209,
|
|
"epoch": 1.927275790419498,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004636126338007622,
|
|
"loss": 5.37,
|
|
"mean_token_accuracy": 0.1807766929268837,
|
|
"num_tokens": 38313915.0,
|
|
"step": 17160
|
|
},
|
|
{
|
|
"entropy": 5.4969405174255375,
|
|
"epoch": 1.9278373673274554,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 0.0004635907400106965,
|
|
"loss": 5.3194,
|
|
"mean_token_accuracy": 0.18252474516630174,
|
|
"num_tokens": 38324845.0,
|
|
"step": 17165
|
|
},
|
|
{
|
|
"entropy": 5.5207854270935055,
|
|
"epoch": 1.928398944235413,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004635688402158285,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.19524409621953964,
|
|
"num_tokens": 38335096.0,
|
|
"step": 17170
|
|
},
|
|
{
|
|
"entropy": 5.572595405578613,
|
|
"epoch": 1.9289605211433707,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046354693441685537,
|
|
"loss": 5.329,
|
|
"mean_token_accuracy": 0.1887124851346016,
|
|
"num_tokens": 38345559.0,
|
|
"step": 17175
|
|
},
|
|
{
|
|
"entropy": 5.465444707870484,
|
|
"epoch": 1.9295220980513281,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046352502261447475,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.20006259381771088,
|
|
"num_tokens": 38356318.0,
|
|
"step": 17180
|
|
},
|
|
{
|
|
"entropy": 5.472886419296264,
|
|
"epoch": 1.9300836749592856,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004635031048093843,
|
|
"loss": 5.3077,
|
|
"mean_token_accuracy": 0.19038204252719879,
|
|
"num_tokens": 38367246.0,
|
|
"step": 17185
|
|
},
|
|
{
|
|
"entropy": 5.533672666549682,
|
|
"epoch": 1.9306452518672432,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004634811810022819,
|
|
"loss": 5.344,
|
|
"mean_token_accuracy": 0.18472021371126174,
|
|
"num_tokens": 38378767.0,
|
|
"step": 17190
|
|
},
|
|
{
|
|
"entropy": 5.575577735900879,
|
|
"epoch": 1.931206828775201,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046345925119386556,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.192129385471344,
|
|
"num_tokens": 38390414.0,
|
|
"step": 17195
|
|
},
|
|
{
|
|
"entropy": 5.54867992401123,
|
|
"epoch": 1.9317684056831583,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004634373153848336,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.1899900332093239,
|
|
"num_tokens": 38401569.0,
|
|
"step": 17200
|
|
},
|
|
{
|
|
"entropy": 5.59572114944458,
|
|
"epoch": 1.9323299825911158,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004634153735758845,
|
|
"loss": 5.4256,
|
|
"mean_token_accuracy": 0.18327434211969376,
|
|
"num_tokens": 38413561.0,
|
|
"step": 17205
|
|
},
|
|
{
|
|
"entropy": 5.577825212478638,
|
|
"epoch": 1.9328915594990734,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004633934257677167,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.1945035770535469,
|
|
"num_tokens": 38423965.0,
|
|
"step": 17210
|
|
},
|
|
{
|
|
"entropy": 5.485685920715332,
|
|
"epoch": 1.933453136407031,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004633714719610292,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.1893720433115959,
|
|
"num_tokens": 38434158.0,
|
|
"step": 17215
|
|
},
|
|
{
|
|
"entropy": 5.496278142929077,
|
|
"epoch": 1.9340147133149885,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00046334951215652097,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.19285691082477568,
|
|
"num_tokens": 38445449.0,
|
|
"step": 17220
|
|
},
|
|
{
|
|
"entropy": 5.619433307647705,
|
|
"epoch": 1.934576290222946,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046332754635489126,
|
|
"loss": 5.4218,
|
|
"mean_token_accuracy": 0.19061725735664367,
|
|
"num_tokens": 38457601.0,
|
|
"step": 17225
|
|
},
|
|
{
|
|
"entropy": 5.586219358444214,
|
|
"epoch": 1.9351378671309036,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004633055745568394,
|
|
"loss": 5.2981,
|
|
"mean_token_accuracy": 0.19171446263790132,
|
|
"num_tokens": 38468631.0,
|
|
"step": 17230
|
|
},
|
|
{
|
|
"entropy": 5.50202488899231,
|
|
"epoch": 1.935699444038861,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046328359676306506,
|
|
"loss": 5.3499,
|
|
"mean_token_accuracy": 0.18947120904922485,
|
|
"num_tokens": 38479567.0,
|
|
"step": 17235
|
|
},
|
|
{
|
|
"entropy": 5.485712718963623,
|
|
"epoch": 1.9362610209468185,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000463261612974268,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.190141761302948,
|
|
"num_tokens": 38489934.0,
|
|
"step": 17240
|
|
},
|
|
{
|
|
"entropy": 5.6858001232147215,
|
|
"epoch": 1.9368225978547762,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004632396231911481,
|
|
"loss": 5.5095,
|
|
"mean_token_accuracy": 0.18102382719516755,
|
|
"num_tokens": 38502214.0,
|
|
"step": 17245
|
|
},
|
|
{
|
|
"entropy": 5.615298700332642,
|
|
"epoch": 1.9373841747627338,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004632176274144056,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18850194811820983,
|
|
"num_tokens": 38513915.0,
|
|
"step": 17250
|
|
},
|
|
{
|
|
"entropy": 5.500184106826782,
|
|
"epoch": 1.9379457516706913,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046319562564474083,
|
|
"loss": 5.2861,
|
|
"mean_token_accuracy": 0.19257685989141465,
|
|
"num_tokens": 38525039.0,
|
|
"step": 17255
|
|
},
|
|
{
|
|
"entropy": 5.510066175460816,
|
|
"epoch": 1.9385073285786487,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00046317361788285436,
|
|
"loss": 5.2915,
|
|
"mean_token_accuracy": 0.19501728117465972,
|
|
"num_tokens": 38537264.0,
|
|
"step": 17260
|
|
},
|
|
{
|
|
"entropy": 5.639313077926635,
|
|
"epoch": 1.9390689054866064,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004631516041294469,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.18950749933719635,
|
|
"num_tokens": 38547926.0,
|
|
"step": 17265
|
|
},
|
|
{
|
|
"entropy": 5.508912992477417,
|
|
"epoch": 1.939630482394564,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004631295843852194,
|
|
"loss": 5.3409,
|
|
"mean_token_accuracy": 0.1873542845249176,
|
|
"num_tokens": 38558745.0,
|
|
"step": 17270
|
|
},
|
|
{
|
|
"entropy": 5.5051459789276125,
|
|
"epoch": 1.9401920593025215,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000463107558650873,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.19321348369121552,
|
|
"num_tokens": 38568190.0,
|
|
"step": 17275
|
|
},
|
|
{
|
|
"entropy": 5.639883375167846,
|
|
"epoch": 1.940753636210479,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00046308552692710895,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.18747277408838273,
|
|
"num_tokens": 38578932.0,
|
|
"step": 17280
|
|
},
|
|
{
|
|
"entropy": 5.515133190155029,
|
|
"epoch": 1.9413152131184366,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00046306348921462876,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.18797391653060913,
|
|
"num_tokens": 38590501.0,
|
|
"step": 17285
|
|
},
|
|
{
|
|
"entropy": 5.540187644958496,
|
|
"epoch": 1.9418767900263942,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004630414455141342,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19491633921861648,
|
|
"num_tokens": 38600498.0,
|
|
"step": 17290
|
|
},
|
|
{
|
|
"entropy": 5.512134790420532,
|
|
"epoch": 1.9424383669343517,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000463019395826327,
|
|
"loss": 5.2664,
|
|
"mean_token_accuracy": 0.19038528203964233,
|
|
"num_tokens": 38611991.0,
|
|
"step": 17295
|
|
},
|
|
{
|
|
"entropy": 5.446357870101929,
|
|
"epoch": 1.9429999438423091,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046299734015190934,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.1925743341445923,
|
|
"num_tokens": 38622284.0,
|
|
"step": 17300
|
|
},
|
|
{
|
|
"entropy": 5.5922283172607425,
|
|
"epoch": 1.9435615207502668,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046297527849158344,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.18569293171167373,
|
|
"num_tokens": 38633777.0,
|
|
"step": 17305
|
|
},
|
|
{
|
|
"entropy": 5.667721128463745,
|
|
"epoch": 1.9441230976582244,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004629532108460519,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.1815524861216545,
|
|
"num_tokens": 38644360.0,
|
|
"step": 17310
|
|
},
|
|
{
|
|
"entropy": 5.498967170715332,
|
|
"epoch": 1.9446846745661819,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00046293113721601706,
|
|
"loss": 5.3352,
|
|
"mean_token_accuracy": 0.18982650190591813,
|
|
"num_tokens": 38655242.0,
|
|
"step": 17315
|
|
},
|
|
{
|
|
"entropy": 5.5009317874908445,
|
|
"epoch": 1.9452462514741393,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00046290905760218193,
|
|
"loss": 5.2457,
|
|
"mean_token_accuracy": 0.197038871049881,
|
|
"num_tokens": 38667792.0,
|
|
"step": 17320
|
|
},
|
|
{
|
|
"entropy": 5.43487548828125,
|
|
"epoch": 1.945807828382097,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046288697200524964,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.19577704966068268,
|
|
"num_tokens": 38677735.0,
|
|
"step": 17325
|
|
},
|
|
{
|
|
"entropy": 5.5649580478668215,
|
|
"epoch": 1.9463694052900544,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046286488042592325,
|
|
"loss": 5.3277,
|
|
"mean_token_accuracy": 0.18976116925477982,
|
|
"num_tokens": 38689556.0,
|
|
"step": 17330
|
|
},
|
|
{
|
|
"entropy": 5.505726671218872,
|
|
"epoch": 1.9469309821980119,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004628427828649062,
|
|
"loss": 5.3138,
|
|
"mean_token_accuracy": 0.1946387067437172,
|
|
"num_tokens": 38700556.0,
|
|
"step": 17335
|
|
},
|
|
{
|
|
"entropy": 5.491486358642578,
|
|
"epoch": 1.9474925591059695,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00046282067932290204,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.19257644712924957,
|
|
"num_tokens": 38711019.0,
|
|
"step": 17340
|
|
},
|
|
{
|
|
"entropy": 5.525941181182861,
|
|
"epoch": 1.9480541360139272,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004627985698006146,
|
|
"loss": 5.3218,
|
|
"mean_token_accuracy": 0.1890546515583992,
|
|
"num_tokens": 38722228.0,
|
|
"step": 17345
|
|
},
|
|
{
|
|
"entropy": 5.440960311889649,
|
|
"epoch": 1.9486157129218846,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000462776454298748,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.1978791818022728,
|
|
"num_tokens": 38732183.0,
|
|
"step": 17350
|
|
},
|
|
{
|
|
"entropy": 5.474621677398682,
|
|
"epoch": 1.949177289829842,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00046275433281800613,
|
|
"loss": 5.2364,
|
|
"mean_token_accuracy": 0.19507492631673812,
|
|
"num_tokens": 38743659.0,
|
|
"step": 17355
|
|
},
|
|
{
|
|
"entropy": 5.61534276008606,
|
|
"epoch": 1.9497388667377997,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004627322053590935,
|
|
"loss": 5.3919,
|
|
"mean_token_accuracy": 0.18703874200582504,
|
|
"num_tokens": 38755032.0,
|
|
"step": 17360
|
|
},
|
|
{
|
|
"entropy": 5.56540093421936,
|
|
"epoch": 1.9503004436457574,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004627100719227147,
|
|
"loss": 5.2781,
|
|
"mean_token_accuracy": 0.19505268484354019,
|
|
"num_tokens": 38766126.0,
|
|
"step": 17365
|
|
},
|
|
{
|
|
"entropy": 5.606506729125977,
|
|
"epoch": 1.9508620205537148,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046268793250957437,
|
|
"loss": 5.4316,
|
|
"mean_token_accuracy": 0.18807401806116103,
|
|
"num_tokens": 38776921.0,
|
|
"step": 17370
|
|
},
|
|
{
|
|
"entropy": 5.492905712127685,
|
|
"epoch": 1.9514235974616723,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00046266578712037747,
|
|
"loss": 5.3006,
|
|
"mean_token_accuracy": 0.18932364135980606,
|
|
"num_tokens": 38788884.0,
|
|
"step": 17375
|
|
},
|
|
{
|
|
"entropy": 5.663022041320801,
|
|
"epoch": 1.95198517436963,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046264363575582916,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.18174161314964293,
|
|
"num_tokens": 38800505.0,
|
|
"step": 17380
|
|
},
|
|
{
|
|
"entropy": 5.546361446380615,
|
|
"epoch": 1.9525467512775876,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004626214784166347,
|
|
"loss": 5.2596,
|
|
"mean_token_accuracy": 0.18877926766872405,
|
|
"num_tokens": 38811132.0,
|
|
"step": 17385
|
|
},
|
|
{
|
|
"entropy": 5.558654832839966,
|
|
"epoch": 1.953108328185545,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004625993151034995,
|
|
"loss": 5.3415,
|
|
"mean_token_accuracy": 0.19733828604221343,
|
|
"num_tokens": 38821349.0,
|
|
"step": 17390
|
|
},
|
|
{
|
|
"entropy": 5.551306819915771,
|
|
"epoch": 1.9536699050935025,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004625771458171294,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.18589753210544585,
|
|
"num_tokens": 38832970.0,
|
|
"step": 17395
|
|
},
|
|
{
|
|
"entropy": 5.495958852767944,
|
|
"epoch": 1.9542314820014601,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046255497055823025,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.19042533487081528,
|
|
"num_tokens": 38844220.0,
|
|
"step": 17400
|
|
},
|
|
{
|
|
"entropy": 5.484007024765015,
|
|
"epoch": 1.9547930589094178,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004625327893275082,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.185167333483696,
|
|
"num_tokens": 38854848.0,
|
|
"step": 17405
|
|
},
|
|
{
|
|
"entropy": 5.581478548049927,
|
|
"epoch": 1.9553546358173752,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00046251060212566927,
|
|
"loss": 5.4253,
|
|
"mean_token_accuracy": 0.18208504021167754,
|
|
"num_tokens": 38864827.0,
|
|
"step": 17410
|
|
},
|
|
{
|
|
"entropy": 5.577907371520996,
|
|
"epoch": 1.9559162127253327,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004624884089534201,
|
|
"loss": 5.2924,
|
|
"mean_token_accuracy": 0.18757234513759613,
|
|
"num_tokens": 38875914.0,
|
|
"step": 17415
|
|
},
|
|
{
|
|
"entropy": 5.436034727096557,
|
|
"epoch": 1.9564777896332903,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004624662098114672,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.19371898770332335,
|
|
"num_tokens": 38886565.0,
|
|
"step": 17420
|
|
},
|
|
{
|
|
"entropy": 5.574147415161133,
|
|
"epoch": 1.9570393665412478,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046244400470051754,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.1811410129070282,
|
|
"num_tokens": 38897319.0,
|
|
"step": 17425
|
|
},
|
|
{
|
|
"entropy": 5.564211845397949,
|
|
"epoch": 1.9576009434492052,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000462421793621278,
|
|
"loss": 5.2813,
|
|
"mean_token_accuracy": 0.19070397019386293,
|
|
"num_tokens": 38908824.0,
|
|
"step": 17430
|
|
},
|
|
{
|
|
"entropy": 5.527219438552857,
|
|
"epoch": 1.9581625203571629,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000462399576574456,
|
|
"loss": 5.3886,
|
|
"mean_token_accuracy": 0.1887141689658165,
|
|
"num_tokens": 38921800.0,
|
|
"step": 17435
|
|
},
|
|
{
|
|
"entropy": 5.54549880027771,
|
|
"epoch": 1.9587240972651205,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004623773535607587,
|
|
"loss": 5.3126,
|
|
"mean_token_accuracy": 0.19318063110113143,
|
|
"num_tokens": 38932284.0,
|
|
"step": 17440
|
|
},
|
|
{
|
|
"entropy": 5.533887720108032,
|
|
"epoch": 1.959285674173078,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004623551245808938,
|
|
"loss": 5.332,
|
|
"mean_token_accuracy": 0.19330756962299347,
|
|
"num_tokens": 38943632.0,
|
|
"step": 17445
|
|
},
|
|
{
|
|
"entropy": 5.544536781311035,
|
|
"epoch": 1.9598472510810354,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004623328896355691,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1925597980618477,
|
|
"num_tokens": 38954701.0,
|
|
"step": 17450
|
|
},
|
|
{
|
|
"entropy": 5.6430089473724365,
|
|
"epoch": 1.960408827988993,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.00046231064872549244,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.18744004219770433,
|
|
"num_tokens": 38965625.0,
|
|
"step": 17455
|
|
},
|
|
{
|
|
"entropy": 5.556644248962402,
|
|
"epoch": 1.9609704048969507,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046228840185137215,
|
|
"loss": 5.3257,
|
|
"mean_token_accuracy": 0.19070612341165544,
|
|
"num_tokens": 38976989.0,
|
|
"step": 17460
|
|
},
|
|
{
|
|
"entropy": 5.506419563293457,
|
|
"epoch": 1.9615319818049082,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004622661490139165,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.19591319411993027,
|
|
"num_tokens": 38987661.0,
|
|
"step": 17465
|
|
},
|
|
{
|
|
"entropy": 5.500600814819336,
|
|
"epoch": 1.9620935587128656,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004622438902138341,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.19333523362874985,
|
|
"num_tokens": 38998014.0,
|
|
"step": 17470
|
|
},
|
|
{
|
|
"entropy": 5.492684459686279,
|
|
"epoch": 1.9626551356208233,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046222162545183357,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.19574263393878938,
|
|
"num_tokens": 39008843.0,
|
|
"step": 17475
|
|
},
|
|
{
|
|
"entropy": 5.571174430847168,
|
|
"epoch": 1.963216712528781,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046219935472862386,
|
|
"loss": 5.3713,
|
|
"mean_token_accuracy": 0.18617331683635713,
|
|
"num_tokens": 39020173.0,
|
|
"step": 17480
|
|
},
|
|
{
|
|
"entropy": 5.546753072738648,
|
|
"epoch": 1.9637782894367384,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00046217707804491404,
|
|
"loss": 5.4012,
|
|
"mean_token_accuracy": 0.18166946917772292,
|
|
"num_tokens": 39033087.0,
|
|
"step": 17485
|
|
},
|
|
{
|
|
"entropy": 5.611722946166992,
|
|
"epoch": 1.9643398663446958,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004621547954014135,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.1936030611395836,
|
|
"num_tokens": 39045252.0,
|
|
"step": 17490
|
|
},
|
|
{
|
|
"entropy": 5.5866844177246096,
|
|
"epoch": 1.9649014432526535,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004621325067988317,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.1837921842932701,
|
|
"num_tokens": 39056755.0,
|
|
"step": 17495
|
|
},
|
|
{
|
|
"entropy": 5.517789506912232,
|
|
"epoch": 1.9654630201606111,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00046211021223787827,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.195296448469162,
|
|
"num_tokens": 39066993.0,
|
|
"step": 17500
|
|
},
|
|
{
|
|
"entropy": 5.5415940284729,
|
|
"epoch": 1.9660245970685686,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00046208791171926315,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.19446637034416198,
|
|
"num_tokens": 39078671.0,
|
|
"step": 17505
|
|
},
|
|
{
|
|
"entropy": 5.587452030181884,
|
|
"epoch": 1.966586173976526,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046206560524369636,
|
|
"loss": 5.3202,
|
|
"mean_token_accuracy": 0.18873273134231566,
|
|
"num_tokens": 39089563.0,
|
|
"step": 17510
|
|
},
|
|
{
|
|
"entropy": 5.602343654632568,
|
|
"epoch": 1.9671477508844837,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046204329281188816,
|
|
"loss": 5.3702,
|
|
"mean_token_accuracy": 0.18672167062759398,
|
|
"num_tokens": 39099837.0,
|
|
"step": 17515
|
|
},
|
|
{
|
|
"entropy": 5.598878288269043,
|
|
"epoch": 1.9677093277924411,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004620209744245489,
|
|
"loss": 5.3603,
|
|
"mean_token_accuracy": 0.18496621698141097,
|
|
"num_tokens": 39112061.0,
|
|
"step": 17520
|
|
},
|
|
{
|
|
"entropy": 5.520508527755737,
|
|
"epoch": 1.9682709047003986,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00046199865008238937,
|
|
"loss": 5.3037,
|
|
"mean_token_accuracy": 0.1947123110294342,
|
|
"num_tokens": 39122777.0,
|
|
"step": 17525
|
|
},
|
|
{
|
|
"entropy": 5.448798131942749,
|
|
"epoch": 1.9688324816083562,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004619763197861203,
|
|
"loss": 5.2666,
|
|
"mean_token_accuracy": 0.1930849775671959,
|
|
"num_tokens": 39134827.0,
|
|
"step": 17530
|
|
},
|
|
{
|
|
"entropy": 5.532231760025025,
|
|
"epoch": 1.9693940585163139,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00046195398353645256,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.19254703372716903,
|
|
"num_tokens": 39144352.0,
|
|
"step": 17535
|
|
},
|
|
{
|
|
"entropy": 5.487201356887818,
|
|
"epoch": 1.9699556354242713,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004619316413340976,
|
|
"loss": 5.2432,
|
|
"mean_token_accuracy": 0.19358502179384232,
|
|
"num_tokens": 39155610.0,
|
|
"step": 17540
|
|
},
|
|
{
|
|
"entropy": 5.448001432418823,
|
|
"epoch": 1.9705172123322288,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046190929317976664,
|
|
"loss": 5.324,
|
|
"mean_token_accuracy": 0.19106620103120803,
|
|
"num_tokens": 39167058.0,
|
|
"step": 17545
|
|
},
|
|
{
|
|
"entropy": 5.571168041229248,
|
|
"epoch": 1.9710787892401864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004618869390741713,
|
|
"loss": 5.4228,
|
|
"mean_token_accuracy": 0.18453103303909302,
|
|
"num_tokens": 39178797.0,
|
|
"step": 17550
|
|
},
|
|
{
|
|
"entropy": 5.566341972351074,
|
|
"epoch": 1.971640366148144,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004618645790180233,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.19480976909399034,
|
|
"num_tokens": 39188980.0,
|
|
"step": 17555
|
|
},
|
|
{
|
|
"entropy": 5.5040453433990475,
|
|
"epoch": 1.9722019430561015,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004618422130120347,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.1880178764462471,
|
|
"num_tokens": 39200058.0,
|
|
"step": 17560
|
|
},
|
|
{
|
|
"entropy": 5.520547199249267,
|
|
"epoch": 1.972763519964059,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004618198410569175,
|
|
"loss": 5.36,
|
|
"mean_token_accuracy": 0.19431740790605545,
|
|
"num_tokens": 39211369.0,
|
|
"step": 17565
|
|
},
|
|
{
|
|
"entropy": 5.5720113754272464,
|
|
"epoch": 1.9733250968720166,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00046179746315338414,
|
|
"loss": 5.3825,
|
|
"mean_token_accuracy": 0.18746374249458314,
|
|
"num_tokens": 39222438.0,
|
|
"step": 17570
|
|
},
|
|
{
|
|
"entropy": 5.588553619384766,
|
|
"epoch": 1.9738866737799743,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046177507930214714,
|
|
"loss": 5.3638,
|
|
"mean_token_accuracy": 0.18315080553293228,
|
|
"num_tokens": 39233047.0,
|
|
"step": 17575
|
|
},
|
|
{
|
|
"entropy": 5.549322557449341,
|
|
"epoch": 1.9744482506879317,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004617526895039191,
|
|
"loss": 5.3039,
|
|
"mean_token_accuracy": 0.19158487766981125,
|
|
"num_tokens": 39244547.0,
|
|
"step": 17580
|
|
},
|
|
{
|
|
"entropy": 5.5426994323730465,
|
|
"epoch": 1.9750098275958892,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046173029375941305,
|
|
"loss": 5.2504,
|
|
"mean_token_accuracy": 0.1924957111477852,
|
|
"num_tokens": 39255549.0,
|
|
"step": 17585
|
|
},
|
|
{
|
|
"entropy": 5.463155126571655,
|
|
"epoch": 1.9755714045038468,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000461707892069342,
|
|
"loss": 5.2575,
|
|
"mean_token_accuracy": 0.18853694051504136,
|
|
"num_tokens": 39266527.0,
|
|
"step": 17590
|
|
},
|
|
{
|
|
"entropy": 5.523002767562867,
|
|
"epoch": 1.9761329814118045,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046168548443441926,
|
|
"loss": 5.3432,
|
|
"mean_token_accuracy": 0.19041741639375687,
|
|
"num_tokens": 39278013.0,
|
|
"step": 17595
|
|
},
|
|
{
|
|
"entropy": 5.566499948501587,
|
|
"epoch": 1.976694558319762,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004616630708553583,
|
|
"loss": 5.3139,
|
|
"mean_token_accuracy": 0.19020363241434096,
|
|
"num_tokens": 39289349.0,
|
|
"step": 17600
|
|
},
|
|
{
|
|
"entropy": 5.504770994186401,
|
|
"epoch": 1.9772561352277194,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046164065133287276,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.19242658615112304,
|
|
"num_tokens": 39301213.0,
|
|
"step": 17605
|
|
},
|
|
{
|
|
"entropy": 5.51604323387146,
|
|
"epoch": 1.977817712135677,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004616182258676765,
|
|
"loss": 5.1989,
|
|
"mean_token_accuracy": 0.20135003924369813,
|
|
"num_tokens": 39310960.0,
|
|
"step": 17610
|
|
},
|
|
{
|
|
"entropy": 5.549459409713745,
|
|
"epoch": 1.9783792890436345,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004615957944604835,
|
|
"loss": 5.3679,
|
|
"mean_token_accuracy": 0.18817516714334487,
|
|
"num_tokens": 39322603.0,
|
|
"step": 17615
|
|
},
|
|
{
|
|
"entropy": 5.5214653491973875,
|
|
"epoch": 1.978940865951592,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004615733571120081,
|
|
"loss": 5.3102,
|
|
"mean_token_accuracy": 0.18803376257419585,
|
|
"num_tokens": 39333811.0,
|
|
"step": 17620
|
|
},
|
|
{
|
|
"entropy": 5.585570001602173,
|
|
"epoch": 1.9795024428595496,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004615509138229646,
|
|
"loss": 5.359,
|
|
"mean_token_accuracy": 0.188025563955307,
|
|
"num_tokens": 39345218.0,
|
|
"step": 17625
|
|
},
|
|
{
|
|
"entropy": 5.483640146255493,
|
|
"epoch": 1.9800640197675072,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00046152846459406765,
|
|
"loss": 5.1789,
|
|
"mean_token_accuracy": 0.19236330837011337,
|
|
"num_tokens": 39356777.0,
|
|
"step": 17630
|
|
},
|
|
{
|
|
"entropy": 5.4884449481964115,
|
|
"epoch": 1.9806255966754647,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004615060094260321,
|
|
"loss": 5.2977,
|
|
"mean_token_accuracy": 0.19279973208904266,
|
|
"num_tokens": 39368288.0,
|
|
"step": 17635
|
|
},
|
|
{
|
|
"entropy": 5.590827131271363,
|
|
"epoch": 1.9811871735834221,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046148354831957285,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.1948817104101181,
|
|
"num_tokens": 39379398.0,
|
|
"step": 17640
|
|
},
|
|
{
|
|
"entropy": 5.483453893661499,
|
|
"epoch": 1.9817487504913798,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00046146108127540506,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.1921989306807518,
|
|
"num_tokens": 39391129.0,
|
|
"step": 17645
|
|
},
|
|
{
|
|
"entropy": 5.528729629516602,
|
|
"epoch": 1.9823103273993374,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004614386082942442,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.18335050195455552,
|
|
"num_tokens": 39402442.0,
|
|
"step": 17650
|
|
},
|
|
{
|
|
"entropy": 5.651702499389648,
|
|
"epoch": 1.9828719043072949,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004614161293768057,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.19544869512319565,
|
|
"num_tokens": 39413044.0,
|
|
"step": 17655
|
|
},
|
|
{
|
|
"entropy": 5.545426321029663,
|
|
"epoch": 1.9834334812152523,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00046139364452380536,
|
|
"loss": 5.3013,
|
|
"mean_token_accuracy": 0.1957097664475441,
|
|
"num_tokens": 39423739.0,
|
|
"step": 17660
|
|
},
|
|
{
|
|
"entropy": 5.514121150970459,
|
|
"epoch": 1.98399505812321,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.000461371153735959,
|
|
"loss": 5.4483,
|
|
"mean_token_accuracy": 0.18452351093292235,
|
|
"num_tokens": 39436199.0,
|
|
"step": 17665
|
|
},
|
|
{
|
|
"entropy": 5.56049656867981,
|
|
"epoch": 1.9845566350311676,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00046134865701398287,
|
|
"loss": 5.3349,
|
|
"mean_token_accuracy": 0.19470758885145187,
|
|
"num_tokens": 39449302.0,
|
|
"step": 17670
|
|
},
|
|
{
|
|
"entropy": 5.584875106811523,
|
|
"epoch": 1.985118211939125,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046132615435859326,
|
|
"loss": 5.3734,
|
|
"mean_token_accuracy": 0.18695272952318193,
|
|
"num_tokens": 39460723.0,
|
|
"step": 17675
|
|
},
|
|
{
|
|
"entropy": 5.518227386474609,
|
|
"epoch": 1.9856797888470825,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00046130364577050655,
|
|
"loss": 5.2973,
|
|
"mean_token_accuracy": 0.1952237606048584,
|
|
"num_tokens": 39471251.0,
|
|
"step": 17680
|
|
},
|
|
{
|
|
"entropy": 5.559889554977417,
|
|
"epoch": 1.9862413657550402,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00046128113125043957,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.196956567466259,
|
|
"num_tokens": 39482613.0,
|
|
"step": 17685
|
|
},
|
|
{
|
|
"entropy": 5.498400402069092,
|
|
"epoch": 1.9868029426629978,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00046125861079910913,
|
|
"loss": 5.3127,
|
|
"mean_token_accuracy": 0.20265943109989165,
|
|
"num_tokens": 39494626.0,
|
|
"step": 17690
|
|
},
|
|
{
|
|
"entropy": 5.46189136505127,
|
|
"epoch": 1.9873645195709553,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004612360844172322,
|
|
"loss": 5.2459,
|
|
"mean_token_accuracy": 0.1906777173280716,
|
|
"num_tokens": 39505302.0,
|
|
"step": 17695
|
|
},
|
|
{
|
|
"entropy": 5.505736398696899,
|
|
"epoch": 1.9879260964789127,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046121355210552626,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.18999366462230682,
|
|
"num_tokens": 39515854.0,
|
|
"step": 17700
|
|
},
|
|
{
|
|
"entropy": 5.587160062789917,
|
|
"epoch": 1.9884876733868704,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004611910138647085,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.1850861981511116,
|
|
"num_tokens": 39527504.0,
|
|
"step": 17705
|
|
},
|
|
{
|
|
"entropy": 5.5862733840942385,
|
|
"epoch": 1.989049250294828,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046116846969549666,
|
|
"loss": 5.2947,
|
|
"mean_token_accuracy": 0.19199934154748916,
|
|
"num_tokens": 39538885.0,
|
|
"step": 17710
|
|
},
|
|
{
|
|
"entropy": 5.4966072082519535,
|
|
"epoch": 1.9896108272027853,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004611459195986085,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.19710191786289216,
|
|
"num_tokens": 39549401.0,
|
|
"step": 17715
|
|
},
|
|
{
|
|
"entropy": 5.49089412689209,
|
|
"epoch": 1.990172404110743,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046112336357476217,
|
|
"loss": 5.3463,
|
|
"mean_token_accuracy": 0.18749746084213256,
|
|
"num_tokens": 39560814.0,
|
|
"step": 17720
|
|
},
|
|
{
|
|
"entropy": 5.519908237457275,
|
|
"epoch": 1.9907339810187006,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004611008016246757,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.18880258053541182,
|
|
"num_tokens": 39571490.0,
|
|
"step": 17725
|
|
},
|
|
{
|
|
"entropy": 5.45294451713562,
|
|
"epoch": 1.991295557926658,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00046107823374906754,
|
|
"loss": 5.2305,
|
|
"mean_token_accuracy": 0.19622138291597366,
|
|
"num_tokens": 39582815.0,
|
|
"step": 17730
|
|
},
|
|
{
|
|
"entropy": 5.52000937461853,
|
|
"epoch": 1.9918571348346155,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046105565994865614,
|
|
"loss": 5.3247,
|
|
"mean_token_accuracy": 0.19269051849842073,
|
|
"num_tokens": 39593712.0,
|
|
"step": 17735
|
|
},
|
|
{
|
|
"entropy": 5.536560726165772,
|
|
"epoch": 1.9924187117425731,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004610330802241605,
|
|
"loss": 5.3136,
|
|
"mean_token_accuracy": 0.19450237601995468,
|
|
"num_tokens": 39604504.0,
|
|
"step": 17740
|
|
},
|
|
{
|
|
"entropy": 5.588315391540528,
|
|
"epoch": 1.9929802886505308,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004610104945762994,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19023960530757905,
|
|
"num_tokens": 39614971.0,
|
|
"step": 17745
|
|
},
|
|
{
|
|
"entropy": 5.533897781372071,
|
|
"epoch": 1.9935418655584882,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.000460987903005792,
|
|
"loss": 5.2662,
|
|
"mean_token_accuracy": 0.193694007396698,
|
|
"num_tokens": 39626647.0,
|
|
"step": 17750
|
|
},
|
|
{
|
|
"entropy": 5.526335525512695,
|
|
"epoch": 1.9941034424664457,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004609653055133576,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.1857160359621048,
|
|
"num_tokens": 39636432.0,
|
|
"step": 17755
|
|
},
|
|
{
|
|
"entropy": 5.609818649291992,
|
|
"epoch": 1.9946650193744033,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00046094270209971576,
|
|
"loss": 5.3376,
|
|
"mean_token_accuracy": 0.19454389661550522,
|
|
"num_tokens": 39647055.0,
|
|
"step": 17760
|
|
},
|
|
{
|
|
"entropy": 5.580824518203736,
|
|
"epoch": 1.995226596282361,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004609200927655862,
|
|
"loss": 5.3219,
|
|
"mean_token_accuracy": 0.19362181872129441,
|
|
"num_tokens": 39657891.0,
|
|
"step": 17765
|
|
},
|
|
{
|
|
"entropy": 5.464189100265503,
|
|
"epoch": 1.9957881731903184,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004608974775116888,
|
|
"loss": 5.1847,
|
|
"mean_token_accuracy": 0.20182872265577317,
|
|
"num_tokens": 39668023.0,
|
|
"step": 17770
|
|
},
|
|
{
|
|
"entropy": 5.499495506286621,
|
|
"epoch": 1.9963497500982759,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004608748563387436,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.19311403334140778,
|
|
"num_tokens": 39678398.0,
|
|
"step": 17775
|
|
},
|
|
{
|
|
"entropy": 5.4978173732757565,
|
|
"epoch": 1.9969113270062335,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004608522292474708,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.1886007860302925,
|
|
"num_tokens": 39690619.0,
|
|
"step": 17780
|
|
},
|
|
{
|
|
"entropy": 5.462996578216552,
|
|
"epoch": 1.9974729039141912,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004608295962385911,
|
|
"loss": 5.2356,
|
|
"mean_token_accuracy": 0.19487352371215821,
|
|
"num_tokens": 39701690.0,
|
|
"step": 17785
|
|
},
|
|
{
|
|
"entropy": 5.53607029914856,
|
|
"epoch": 1.9980344808221486,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046080695731282484,
|
|
"loss": 5.3677,
|
|
"mean_token_accuracy": 0.18609132319688798,
|
|
"num_tokens": 39713878.0,
|
|
"step": 17790
|
|
},
|
|
{
|
|
"entropy": 5.596540927886963,
|
|
"epoch": 1.998596057730106,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000460784312470893,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.1875539630651474,
|
|
"num_tokens": 39725164.0,
|
|
"step": 17795
|
|
},
|
|
{
|
|
"entropy": 5.5487510681152346,
|
|
"epoch": 1.9991576346380637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00046076166171351673,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.19201114624738694,
|
|
"num_tokens": 39735354.0,
|
|
"step": 17800
|
|
},
|
|
{
|
|
"entropy": 5.5840130805969235,
|
|
"epoch": 1.9997192115460214,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000460739005041417,
|
|
"loss": 5.3889,
|
|
"mean_token_accuracy": 0.18856875002384185,
|
|
"num_tokens": 39746618.0,
|
|
"step": 17805
|
|
},
|
|
{
|
|
"entropy": 5.5555883513556585,
|
|
"epoch": 2.000224630763183,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004607163424553153,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.18889539274904463,
|
|
"num_tokens": 39755697.0,
|
|
"step": 17810
|
|
},
|
|
{
|
|
"entropy": 5.454597473144531,
|
|
"epoch": 2.0007862076711405,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00046069367395593325,
|
|
"loss": 5.2428,
|
|
"mean_token_accuracy": 0.18863409906625747,
|
|
"num_tokens": 39766311.0,
|
|
"step": 17815
|
|
},
|
|
{
|
|
"entropy": 5.554361772537232,
|
|
"epoch": 2.001347784579098,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004606709995439926,
|
|
"loss": 5.3539,
|
|
"mean_token_accuracy": 0.1868020549416542,
|
|
"num_tokens": 39777504.0,
|
|
"step": 17820
|
|
},
|
|
{
|
|
"entropy": 5.573062562942505,
|
|
"epoch": 2.001909361487056,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046064831922021534,
|
|
"loss": 5.2341,
|
|
"mean_token_accuracy": 0.18842247724533082,
|
|
"num_tokens": 39789190.0,
|
|
"step": 17825
|
|
},
|
|
{
|
|
"entropy": 5.506485176086426,
|
|
"epoch": 2.002470938395013,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004606256329853235,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.1892597809433937,
|
|
"num_tokens": 39801534.0,
|
|
"step": 17830
|
|
},
|
|
{
|
|
"entropy": 5.529390001296997,
|
|
"epoch": 2.0030325153029707,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004606029408400396,
|
|
"loss": 5.2914,
|
|
"mean_token_accuracy": 0.19076294749975203,
|
|
"num_tokens": 39812353.0,
|
|
"step": 17835
|
|
},
|
|
{
|
|
"entropy": 5.503262901306153,
|
|
"epoch": 2.0035940922109283,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004605802427850861,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.19502460658550264,
|
|
"num_tokens": 39823313.0,
|
|
"step": 17840
|
|
},
|
|
{
|
|
"entropy": 5.408044815063477,
|
|
"epoch": 2.004155669118886,
|
|
"grad_norm": 1.8984375,
|
|
"learning_rate": 0.00046055753882118564,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.20279876440763472,
|
|
"num_tokens": 39833966.0,
|
|
"step": 17845
|
|
},
|
|
{
|
|
"entropy": 5.477755117416382,
|
|
"epoch": 2.004717246026843,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004605348289490611,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.18888578116893767,
|
|
"num_tokens": 39843963.0,
|
|
"step": 17850
|
|
},
|
|
{
|
|
"entropy": 5.609683179855347,
|
|
"epoch": 2.005278822934801,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004605121131694358,
|
|
"loss": 5.2748,
|
|
"mean_token_accuracy": 0.19626229256391525,
|
|
"num_tokens": 39855237.0,
|
|
"step": 17855
|
|
},
|
|
{
|
|
"entropy": 5.546237468719482,
|
|
"epoch": 2.0058403998427585,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004604893914830328,
|
|
"loss": 5.4021,
|
|
"mean_token_accuracy": 0.18805417269468308,
|
|
"num_tokens": 39867270.0,
|
|
"step": 17860
|
|
},
|
|
{
|
|
"entropy": 5.572856664657593,
|
|
"epoch": 2.006401976750716,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00046046666389057563,
|
|
"loss": 5.3246,
|
|
"mean_token_accuracy": 0.18787772506475447,
|
|
"num_tokens": 39878103.0,
|
|
"step": 17865
|
|
},
|
|
{
|
|
"entropy": 5.532306098937989,
|
|
"epoch": 2.0069635536586734,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.000460443930392788,
|
|
"loss": 5.2291,
|
|
"mean_token_accuracy": 0.19136196374893188,
|
|
"num_tokens": 39888945.0,
|
|
"step": 17870
|
|
},
|
|
{
|
|
"entropy": 5.607737016677857,
|
|
"epoch": 2.007525130566631,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00046042119099039367,
|
|
"loss": 5.4288,
|
|
"mean_token_accuracy": 0.1860394671559334,
|
|
"num_tokens": 39899848.0,
|
|
"step": 17875
|
|
},
|
|
{
|
|
"entropy": 5.53341498374939,
|
|
"epoch": 2.0080867074745887,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00046039844568411667,
|
|
"loss": 5.287,
|
|
"mean_token_accuracy": 0.18746174722909928,
|
|
"num_tokens": 39911824.0,
|
|
"step": 17880
|
|
},
|
|
{
|
|
"entropy": 5.532930850982666,
|
|
"epoch": 2.0086482843825464,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004603756944746813,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.1945131778717041,
|
|
"num_tokens": 39923257.0,
|
|
"step": 17885
|
|
},
|
|
{
|
|
"entropy": 5.484224939346314,
|
|
"epoch": 2.0092098612905036,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00046035293736281185,
|
|
"loss": 5.2014,
|
|
"mean_token_accuracy": 0.2003853902220726,
|
|
"num_tokens": 39935312.0,
|
|
"step": 17890
|
|
},
|
|
{
|
|
"entropy": 5.4659960746765135,
|
|
"epoch": 2.0097714381984613,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004603301743492331,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.19483893513679504,
|
|
"num_tokens": 39946468.0,
|
|
"step": 17895
|
|
},
|
|
{
|
|
"entropy": 5.415630197525024,
|
|
"epoch": 2.010333015106419,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004603074054346696,
|
|
"loss": 5.0812,
|
|
"mean_token_accuracy": 0.2052256405353546,
|
|
"num_tokens": 39957517.0,
|
|
"step": 17900
|
|
},
|
|
{
|
|
"entropy": 5.397453880310058,
|
|
"epoch": 2.0108945920143766,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004602846306198465,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.1908474251627922,
|
|
"num_tokens": 39968385.0,
|
|
"step": 17905
|
|
},
|
|
{
|
|
"entropy": 5.46295166015625,
|
|
"epoch": 2.011456168922334,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004602618499054889,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.1978897660970688,
|
|
"num_tokens": 39979393.0,
|
|
"step": 17910
|
|
},
|
|
{
|
|
"entropy": 5.540377855300903,
|
|
"epoch": 2.0120177458302915,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004602390632923221,
|
|
"loss": 5.242,
|
|
"mean_token_accuracy": 0.18853503167629243,
|
|
"num_tokens": 39989709.0,
|
|
"step": 17915
|
|
},
|
|
{
|
|
"entropy": 5.521611452102661,
|
|
"epoch": 2.012579322738249,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00046021627078107177,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.1898085966706276,
|
|
"num_tokens": 40000472.0,
|
|
"step": 17920
|
|
},
|
|
{
|
|
"entropy": 5.381340551376343,
|
|
"epoch": 2.0131408996462063,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00046019347237246343,
|
|
"loss": 5.0599,
|
|
"mean_token_accuracy": 0.20139837265014648,
|
|
"num_tokens": 40011062.0,
|
|
"step": 17925
|
|
},
|
|
{
|
|
"entropy": 5.560047578811646,
|
|
"epoch": 2.013702476554164,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004601706680672232,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.17890087366104127,
|
|
"num_tokens": 40022430.0,
|
|
"step": 17930
|
|
},
|
|
{
|
|
"entropy": 5.434284448623657,
|
|
"epoch": 2.0142640534621217,
|
|
"grad_norm": 9.0625,
|
|
"learning_rate": 0.0004601478578660771,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.19185888171195983,
|
|
"num_tokens": 40033077.0,
|
|
"step": 17935
|
|
},
|
|
{
|
|
"entropy": 5.545168352127075,
|
|
"epoch": 2.0148256303700793,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004601250417697513,
|
|
"loss": 5.2535,
|
|
"mean_token_accuracy": 0.1987096220254898,
|
|
"num_tokens": 40044258.0,
|
|
"step": 17940
|
|
},
|
|
{
|
|
"entropy": 5.582378387451172,
|
|
"epoch": 2.0153872072780366,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004601022197789724,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1885640263557434,
|
|
"num_tokens": 40055876.0,
|
|
"step": 17945
|
|
},
|
|
{
|
|
"entropy": 5.481734275817871,
|
|
"epoch": 2.015948784185994,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004600793918944671,
|
|
"loss": 5.172,
|
|
"mean_token_accuracy": 0.201020285487175,
|
|
"num_tokens": 40066691.0,
|
|
"step": 17950
|
|
},
|
|
{
|
|
"entropy": 5.464176654815674,
|
|
"epoch": 2.016510361093952,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004600565581169621,
|
|
"loss": 5.1621,
|
|
"mean_token_accuracy": 0.19045062512159347,
|
|
"num_tokens": 40077335.0,
|
|
"step": 17955
|
|
},
|
|
{
|
|
"entropy": 5.504922485351562,
|
|
"epoch": 2.0170719380019095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00046003371844718455,
|
|
"loss": 5.2995,
|
|
"mean_token_accuracy": 0.18814326971769332,
|
|
"num_tokens": 40089053.0,
|
|
"step": 17960
|
|
},
|
|
{
|
|
"entropy": 5.4639795303344725,
|
|
"epoch": 2.0176335149098668,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00046001087288586164,
|
|
"loss": 5.1819,
|
|
"mean_token_accuracy": 0.20264505594968796,
|
|
"num_tokens": 40099371.0,
|
|
"step": 17965
|
|
},
|
|
{
|
|
"entropy": 5.54316463470459,
|
|
"epoch": 2.0181950918178244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004599880214337208,
|
|
"loss": 5.3162,
|
|
"mean_token_accuracy": 0.18868902921676636,
|
|
"num_tokens": 40110274.0,
|
|
"step": 17970
|
|
},
|
|
{
|
|
"entropy": 5.542514085769653,
|
|
"epoch": 2.018756668725782,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004599651640914896,
|
|
"loss": 5.3111,
|
|
"mean_token_accuracy": 0.19235458076000214,
|
|
"num_tokens": 40120364.0,
|
|
"step": 17975
|
|
},
|
|
{
|
|
"entropy": 5.517283630371094,
|
|
"epoch": 2.0193182456337397,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004599423008598957,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.19336242973804474,
|
|
"num_tokens": 40132400.0,
|
|
"step": 17980
|
|
},
|
|
{
|
|
"entropy": 5.550892686843872,
|
|
"epoch": 2.019879822541697,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045991943173966744,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.1920643001794815,
|
|
"num_tokens": 40142820.0,
|
|
"step": 17985
|
|
},
|
|
{
|
|
"entropy": 5.575599670410156,
|
|
"epoch": 2.0204413994496546,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004598965567315326,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.19057406783103942,
|
|
"num_tokens": 40153620.0,
|
|
"step": 17990
|
|
},
|
|
{
|
|
"entropy": 5.5233378410339355,
|
|
"epoch": 2.0210029763576123,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004598736758362198,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.19531966298818587,
|
|
"num_tokens": 40164250.0,
|
|
"step": 17995
|
|
},
|
|
{
|
|
"entropy": 5.499700880050659,
|
|
"epoch": 2.02156455326557,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045985078905445734,
|
|
"loss": 5.1877,
|
|
"mean_token_accuracy": 0.19329770505428315,
|
|
"num_tokens": 40175809.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"epoch": 2.02156455326557,
|
|
"eval_entropy": 5.430442132745664,
|
|
"eval_loss": 5.401913166046143,
|
|
"eval_mean_token_accuracy": 0.19447472008069613,
|
|
"eval_num_tokens": 40175809.0,
|
|
"eval_runtime": 23.932,
|
|
"eval_samples_per_second": 1295.878,
|
|
"eval_steps_per_second": 162.0,
|
|
"step": 18000
|
|
},
|
|
{
|
|
"entropy": 5.43562502861023,
|
|
"epoch": 2.022126130173527,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00045982789638697414,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.20144463330507278,
|
|
"num_tokens": 40187855.0,
|
|
"step": 18005
|
|
},
|
|
{
|
|
"entropy": 5.483263683319092,
|
|
"epoch": 2.022687707081485,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00045980499783449897,
|
|
"loss": 5.2082,
|
|
"mean_token_accuracy": 0.19980223178863527,
|
|
"num_tokens": 40198802.0,
|
|
"step": 18010
|
|
},
|
|
{
|
|
"entropy": 5.601558542251587,
|
|
"epoch": 2.0232492839894425,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045978209339776104,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.18342294096946715,
|
|
"num_tokens": 40210636.0,
|
|
"step": 18015
|
|
},
|
|
{
|
|
"entropy": 5.6208508014678955,
|
|
"epoch": 2.0238108608973997,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.00045975918307748965,
|
|
"loss": 5.2992,
|
|
"mean_token_accuracy": 0.19374825656414033,
|
|
"num_tokens": 40221216.0,
|
|
"step": 18020
|
|
},
|
|
{
|
|
"entropy": 5.4381969451904295,
|
|
"epoch": 2.0243724378053574,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004597362668744141,
|
|
"loss": 5.13,
|
|
"mean_token_accuracy": 0.20454993546009065,
|
|
"num_tokens": 40231988.0,
|
|
"step": 18025
|
|
},
|
|
{
|
|
"entropy": 5.556275177001953,
|
|
"epoch": 2.024934014713315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004597133447892642,
|
|
"loss": 5.4413,
|
|
"mean_token_accuracy": 0.18252910524606705,
|
|
"num_tokens": 40243789.0,
|
|
"step": 18030
|
|
},
|
|
{
|
|
"entropy": 5.517597246170044,
|
|
"epoch": 2.0254955916212727,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004596904168227698,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.20015547722578048,
|
|
"num_tokens": 40254771.0,
|
|
"step": 18035
|
|
},
|
|
{
|
|
"entropy": 5.517310905456543,
|
|
"epoch": 2.02605716852923,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045966748297566085,
|
|
"loss": 5.2124,
|
|
"mean_token_accuracy": 0.19584814310073853,
|
|
"num_tokens": 40265444.0,
|
|
"step": 18040
|
|
},
|
|
{
|
|
"entropy": 5.4731873035430905,
|
|
"epoch": 2.0266187454371876,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045964454324866767,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.1907760754227638,
|
|
"num_tokens": 40277146.0,
|
|
"step": 18045
|
|
},
|
|
{
|
|
"entropy": 5.513115406036377,
|
|
"epoch": 2.0271803223451452,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045962159764252055,
|
|
"loss": 5.2938,
|
|
"mean_token_accuracy": 0.19861688017845153,
|
|
"num_tokens": 40286493.0,
|
|
"step": 18050
|
|
},
|
|
{
|
|
"entropy": 5.554102659225464,
|
|
"epoch": 2.027741899253103,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004595986461579502,
|
|
"loss": 5.2482,
|
|
"mean_token_accuracy": 0.19470311403274537,
|
|
"num_tokens": 40297209.0,
|
|
"step": 18055
|
|
},
|
|
{
|
|
"entropy": 5.40962061882019,
|
|
"epoch": 2.02830347616106,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045957568879568736,
|
|
"loss": 5.2134,
|
|
"mean_token_accuracy": 0.19514864236116408,
|
|
"num_tokens": 40308666.0,
|
|
"step": 18060
|
|
},
|
|
{
|
|
"entropy": 5.557152271270752,
|
|
"epoch": 2.0288650530690178,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045955272555646306,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.183411668241024,
|
|
"num_tokens": 40321145.0,
|
|
"step": 18065
|
|
},
|
|
{
|
|
"entropy": 5.579719734191895,
|
|
"epoch": 2.0294266299769754,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004595297564410083,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.19108631014823912,
|
|
"num_tokens": 40332418.0,
|
|
"step": 18070
|
|
},
|
|
{
|
|
"entropy": 5.46156587600708,
|
|
"epoch": 2.029988206884933,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045950678145005456,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.19553135633468627,
|
|
"num_tokens": 40342838.0,
|
|
"step": 18075
|
|
},
|
|
{
|
|
"entropy": 5.473635578155518,
|
|
"epoch": 2.0305497837928903,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004594838005843333,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.19873646646738052,
|
|
"num_tokens": 40352940.0,
|
|
"step": 18080
|
|
},
|
|
{
|
|
"entropy": 5.599057197570801,
|
|
"epoch": 2.031111360700848,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045946081384457633,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.1886255756020546,
|
|
"num_tokens": 40364273.0,
|
|
"step": 18085
|
|
},
|
|
{
|
|
"entropy": 5.489436101913452,
|
|
"epoch": 2.0316729376088056,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045943782123151556,
|
|
"loss": 5.1756,
|
|
"mean_token_accuracy": 0.20638324916362763,
|
|
"num_tokens": 40374617.0,
|
|
"step": 18090
|
|
},
|
|
{
|
|
"entropy": 5.474668264389038,
|
|
"epoch": 2.0322345145167633,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004594148227458829,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.18950777798891066,
|
|
"num_tokens": 40385398.0,
|
|
"step": 18095
|
|
},
|
|
{
|
|
"entropy": 5.657859182357788,
|
|
"epoch": 2.0327960914247205,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004593918183884108,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.18432430773973466,
|
|
"num_tokens": 40397030.0,
|
|
"step": 18100
|
|
},
|
|
{
|
|
"entropy": 5.588179349899292,
|
|
"epoch": 2.033357668332678,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004593688081598318,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.19219240099191665,
|
|
"num_tokens": 40408027.0,
|
|
"step": 18105
|
|
},
|
|
{
|
|
"entropy": 5.559434795379639,
|
|
"epoch": 2.033919245240636,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045934579206087837,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18770513981580733,
|
|
"num_tokens": 40418755.0,
|
|
"step": 18110
|
|
},
|
|
{
|
|
"entropy": 5.5804801940917965,
|
|
"epoch": 2.034480822148593,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045932277009228336,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.1941789373755455,
|
|
"num_tokens": 40430694.0,
|
|
"step": 18115
|
|
},
|
|
{
|
|
"entropy": 5.556963300704956,
|
|
"epoch": 2.0350423990565507,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045929974225477986,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.1908900946378708,
|
|
"num_tokens": 40442019.0,
|
|
"step": 18120
|
|
},
|
|
{
|
|
"entropy": 5.566839981079101,
|
|
"epoch": 2.0356039759645084,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045927670854910117,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.1816680312156677,
|
|
"num_tokens": 40454120.0,
|
|
"step": 18125
|
|
},
|
|
{
|
|
"entropy": 5.557280874252319,
|
|
"epoch": 2.036165552872466,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004592536689759806,
|
|
"loss": 5.3863,
|
|
"mean_token_accuracy": 0.188648621737957,
|
|
"num_tokens": 40467445.0,
|
|
"step": 18130
|
|
},
|
|
{
|
|
"entropy": 5.472263288497925,
|
|
"epoch": 2.0367271297804233,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045923062353615167,
|
|
"loss": 5.1757,
|
|
"mean_token_accuracy": 0.1936883047223091,
|
|
"num_tokens": 40477512.0,
|
|
"step": 18135
|
|
},
|
|
{
|
|
"entropy": 5.422986745834351,
|
|
"epoch": 2.037288706688381,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045920757223034833,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19667674601078033,
|
|
"num_tokens": 40488209.0,
|
|
"step": 18140
|
|
},
|
|
{
|
|
"entropy": 5.560288810729981,
|
|
"epoch": 2.0378502835963386,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004591845150593044,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.19317319691181184,
|
|
"num_tokens": 40499793.0,
|
|
"step": 18145
|
|
},
|
|
{
|
|
"entropy": 5.590615844726562,
|
|
"epoch": 2.0384118605042962,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045916145202375407,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.183689446747303,
|
|
"num_tokens": 40510598.0,
|
|
"step": 18150
|
|
},
|
|
{
|
|
"entropy": 5.639198446273804,
|
|
"epoch": 2.0389734374122535,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004591383831244317,
|
|
"loss": 5.2833,
|
|
"mean_token_accuracy": 0.19449755400419236,
|
|
"num_tokens": 40521289.0,
|
|
"step": 18155
|
|
},
|
|
{
|
|
"entropy": 5.5510488986969,
|
|
"epoch": 2.039535014320211,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045911530836207173,
|
|
"loss": 5.3306,
|
|
"mean_token_accuracy": 0.19127672016620637,
|
|
"num_tokens": 40532048.0,
|
|
"step": 18160
|
|
},
|
|
{
|
|
"entropy": 5.497428464889526,
|
|
"epoch": 2.0400965912281688,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045909222773740904,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.19055402725934983,
|
|
"num_tokens": 40543699.0,
|
|
"step": 18165
|
|
},
|
|
{
|
|
"entropy": 5.629912900924682,
|
|
"epoch": 2.0406581681361264,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045906914125117833,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.19135082066059111,
|
|
"num_tokens": 40554626.0,
|
|
"step": 18170
|
|
},
|
|
{
|
|
"entropy": 5.5587749004364015,
|
|
"epoch": 2.0412197450440837,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045904604890411476,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.189820696413517,
|
|
"num_tokens": 40567046.0,
|
|
"step": 18175
|
|
},
|
|
{
|
|
"entropy": 5.6338794231414795,
|
|
"epoch": 2.0417813219520413,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045902295069695373,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.1831135019659996,
|
|
"num_tokens": 40578472.0,
|
|
"step": 18180
|
|
},
|
|
{
|
|
"entropy": 5.514951276779175,
|
|
"epoch": 2.042342898859999,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004589998466304305,
|
|
"loss": 5.286,
|
|
"mean_token_accuracy": 0.19058227986097337,
|
|
"num_tokens": 40589012.0,
|
|
"step": 18185
|
|
},
|
|
{
|
|
"entropy": 5.453519487380982,
|
|
"epoch": 2.0429044757679566,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045897673670528086,
|
|
"loss": 5.2071,
|
|
"mean_token_accuracy": 0.19679352194070815,
|
|
"num_tokens": 40600807.0,
|
|
"step": 18190
|
|
},
|
|
{
|
|
"entropy": 5.603279304504395,
|
|
"epoch": 2.043466052675914,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004589536209222404,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.19140677005052567,
|
|
"num_tokens": 40612578.0,
|
|
"step": 18195
|
|
},
|
|
{
|
|
"entropy": 5.490720272064209,
|
|
"epoch": 2.0440276295838715,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004589304992820454,
|
|
"loss": 5.1182,
|
|
"mean_token_accuracy": 0.19947428554296492,
|
|
"num_tokens": 40623504.0,
|
|
"step": 18200
|
|
},
|
|
{
|
|
"entropy": 5.581281900405884,
|
|
"epoch": 2.044589206491829,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000458907371785432,
|
|
"loss": 5.294,
|
|
"mean_token_accuracy": 0.19634150117635726,
|
|
"num_tokens": 40633676.0,
|
|
"step": 18205
|
|
},
|
|
{
|
|
"entropy": 5.5334169387817385,
|
|
"epoch": 2.0451507833997864,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004588842384331366,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.18979279994964598,
|
|
"num_tokens": 40645991.0,
|
|
"step": 18210
|
|
},
|
|
{
|
|
"entropy": 5.472150802612305,
|
|
"epoch": 2.045712360307744,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045886109922589564,
|
|
"loss": 5.1725,
|
|
"mean_token_accuracy": 0.19602841585874559,
|
|
"num_tokens": 40656617.0,
|
|
"step": 18215
|
|
},
|
|
{
|
|
"entropy": 5.550579404830932,
|
|
"epoch": 2.0462739372157017,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045883795416444594,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.19196162223815919,
|
|
"num_tokens": 40669708.0,
|
|
"step": 18220
|
|
},
|
|
{
|
|
"entropy": 5.525010871887207,
|
|
"epoch": 2.0468355141236594,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045881480324952455,
|
|
"loss": 5.2643,
|
|
"mean_token_accuracy": 0.1869907185435295,
|
|
"num_tokens": 40680248.0,
|
|
"step": 18225
|
|
},
|
|
{
|
|
"entropy": 5.608124685287476,
|
|
"epoch": 2.0473970910316166,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045879164648186853,
|
|
"loss": 5.3631,
|
|
"mean_token_accuracy": 0.18750502318143844,
|
|
"num_tokens": 40692704.0,
|
|
"step": 18230
|
|
},
|
|
{
|
|
"entropy": 5.555899620056152,
|
|
"epoch": 2.0479586679395743,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045876848386221513,
|
|
"loss": 5.2499,
|
|
"mean_token_accuracy": 0.19667329341173173,
|
|
"num_tokens": 40703156.0,
|
|
"step": 18235
|
|
},
|
|
{
|
|
"entropy": 5.515176010131836,
|
|
"epoch": 2.048520244847532,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045874531539130204,
|
|
"loss": 5.2316,
|
|
"mean_token_accuracy": 0.19667380899190903,
|
|
"num_tokens": 40713996.0,
|
|
"step": 18240
|
|
},
|
|
{
|
|
"entropy": 5.509386730194092,
|
|
"epoch": 2.0490818217554896,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045872214106986684,
|
|
"loss": 5.1557,
|
|
"mean_token_accuracy": 0.19499629288911818,
|
|
"num_tokens": 40724532.0,
|
|
"step": 18245
|
|
},
|
|
{
|
|
"entropy": 5.530002403259277,
|
|
"epoch": 2.049643398663447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045869896089864733,
|
|
"loss": 5.361,
|
|
"mean_token_accuracy": 0.18603706061840058,
|
|
"num_tokens": 40736045.0,
|
|
"step": 18250
|
|
},
|
|
{
|
|
"entropy": 5.376283836364746,
|
|
"epoch": 2.0502049755714045,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004586757748783817,
|
|
"loss": 5.1399,
|
|
"mean_token_accuracy": 0.19179279506206512,
|
|
"num_tokens": 40747398.0,
|
|
"step": 18255
|
|
},
|
|
{
|
|
"entropy": 5.406632280349731,
|
|
"epoch": 2.050766552479362,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045865258300980817,
|
|
"loss": 5.1045,
|
|
"mean_token_accuracy": 0.2068891167640686,
|
|
"num_tokens": 40758219.0,
|
|
"step": 18260
|
|
},
|
|
{
|
|
"entropy": 5.550711345672608,
|
|
"epoch": 2.05132812938732,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.00045862938529366514,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.19745828062295914,
|
|
"num_tokens": 40770002.0,
|
|
"step": 18265
|
|
},
|
|
{
|
|
"entropy": 5.446154165267944,
|
|
"epoch": 2.051889706295277,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004586061817306913,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.19960326701402664,
|
|
"num_tokens": 40780087.0,
|
|
"step": 18270
|
|
},
|
|
{
|
|
"entropy": 5.478053569793701,
|
|
"epoch": 2.0524512832032347,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045858297232162536,
|
|
"loss": 5.331,
|
|
"mean_token_accuracy": 0.18704583942890168,
|
|
"num_tokens": 40792225.0,
|
|
"step": 18275
|
|
},
|
|
{
|
|
"entropy": 5.563996028900147,
|
|
"epoch": 2.0530128601111923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045855975706720644,
|
|
"loss": 5.3842,
|
|
"mean_token_accuracy": 0.1867034465074539,
|
|
"num_tokens": 40804437.0,
|
|
"step": 18280
|
|
},
|
|
{
|
|
"entropy": 5.480005502700806,
|
|
"epoch": 2.05357443701915,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004585365359681736,
|
|
"loss": 5.1271,
|
|
"mean_token_accuracy": 0.20917608737945556,
|
|
"num_tokens": 40814625.0,
|
|
"step": 18285
|
|
},
|
|
{
|
|
"entropy": 5.431245946884156,
|
|
"epoch": 2.054136013927107,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045851330902526633,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19912341982126236,
|
|
"num_tokens": 40825843.0,
|
|
"step": 18290
|
|
},
|
|
{
|
|
"entropy": 5.518029832839966,
|
|
"epoch": 2.054697590835065,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045849007623922406,
|
|
"loss": 5.3642,
|
|
"mean_token_accuracy": 0.1842258781194687,
|
|
"num_tokens": 40837146.0,
|
|
"step": 18295
|
|
},
|
|
{
|
|
"entropy": 5.622282314300537,
|
|
"epoch": 2.0552591677430225,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004584668376107867,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.1810385450720787,
|
|
"num_tokens": 40849109.0,
|
|
"step": 18300
|
|
},
|
|
{
|
|
"entropy": 5.529095554351807,
|
|
"epoch": 2.0558207446509797,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000458443593140694,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.19003740549087525,
|
|
"num_tokens": 40861168.0,
|
|
"step": 18305
|
|
},
|
|
{
|
|
"entropy": 5.551097822189331,
|
|
"epoch": 2.0563823215589374,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045842034282968615,
|
|
"loss": 5.3156,
|
|
"mean_token_accuracy": 0.19156729578971862,
|
|
"num_tokens": 40873403.0,
|
|
"step": 18310
|
|
},
|
|
{
|
|
"entropy": 5.496070289611817,
|
|
"epoch": 2.056943898466895,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004583970866785035,
|
|
"loss": 5.2036,
|
|
"mean_token_accuracy": 0.1933010995388031,
|
|
"num_tokens": 40883434.0,
|
|
"step": 18315
|
|
},
|
|
{
|
|
"entropy": 5.512556743621826,
|
|
"epoch": 2.0575054753748527,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045837382468788643,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.19306977093219757,
|
|
"num_tokens": 40894742.0,
|
|
"step": 18320
|
|
},
|
|
{
|
|
"entropy": 5.434591341018677,
|
|
"epoch": 2.05806705228281,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004583505568585757,
|
|
"loss": 5.2138,
|
|
"mean_token_accuracy": 0.19950427114963531,
|
|
"num_tokens": 40905233.0,
|
|
"step": 18325
|
|
},
|
|
{
|
|
"entropy": 5.485489845275879,
|
|
"epoch": 2.0586286291907676,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045832728319131205,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.2027534008026123,
|
|
"num_tokens": 40915897.0,
|
|
"step": 18330
|
|
},
|
|
{
|
|
"entropy": 5.4939717769622805,
|
|
"epoch": 2.0591902060987253,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004583040036868367,
|
|
"loss": 5.2154,
|
|
"mean_token_accuracy": 0.19084835946559905,
|
|
"num_tokens": 40928178.0,
|
|
"step": 18335
|
|
},
|
|
{
|
|
"entropy": 5.491255092620849,
|
|
"epoch": 2.059751783006683,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004582807183458907,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.18976717293262482,
|
|
"num_tokens": 40938988.0,
|
|
"step": 18340
|
|
},
|
|
{
|
|
"entropy": 5.463309907913208,
|
|
"epoch": 2.06031335991464,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045825742716921553,
|
|
"loss": 5.1704,
|
|
"mean_token_accuracy": 0.1970521554350853,
|
|
"num_tokens": 40949671.0,
|
|
"step": 18345
|
|
},
|
|
{
|
|
"entropy": 5.409510469436645,
|
|
"epoch": 2.060874936822598,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004582341301575529,
|
|
"loss": 5.1377,
|
|
"mean_token_accuracy": 0.19255294501781464,
|
|
"num_tokens": 40960818.0,
|
|
"step": 18350
|
|
},
|
|
{
|
|
"entropy": 5.635234403610229,
|
|
"epoch": 2.0614365137305555,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045821082731164445,
|
|
"loss": 5.3934,
|
|
"mean_token_accuracy": 0.18197961896657944,
|
|
"num_tokens": 40973866.0,
|
|
"step": 18355
|
|
},
|
|
{
|
|
"entropy": 5.491624879837036,
|
|
"epoch": 2.061998090638513,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004581875186322322,
|
|
"loss": 5.2424,
|
|
"mean_token_accuracy": 0.19408725053071976,
|
|
"num_tokens": 40983355.0,
|
|
"step": 18360
|
|
},
|
|
{
|
|
"entropy": 5.4358165740966795,
|
|
"epoch": 2.0625596675464704,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045816420412005826,
|
|
"loss": 5.1268,
|
|
"mean_token_accuracy": 0.1962583467364311,
|
|
"num_tokens": 40994045.0,
|
|
"step": 18365
|
|
},
|
|
{
|
|
"entropy": 5.448887920379638,
|
|
"epoch": 2.063121244454428,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045814088377586505,
|
|
"loss": 5.1615,
|
|
"mean_token_accuracy": 0.20176758170127868,
|
|
"num_tokens": 41003974.0,
|
|
"step": 18370
|
|
},
|
|
{
|
|
"entropy": 5.490361881256104,
|
|
"epoch": 2.0636828213623857,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045811755760039513,
|
|
"loss": 5.3158,
|
|
"mean_token_accuracy": 0.1916757270693779,
|
|
"num_tokens": 41015262.0,
|
|
"step": 18375
|
|
},
|
|
{
|
|
"entropy": 5.5723623752594,
|
|
"epoch": 2.0642443982703433,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00045809422559439113,
|
|
"loss": 5.3557,
|
|
"mean_token_accuracy": 0.18970409482717515,
|
|
"num_tokens": 41027103.0,
|
|
"step": 18380
|
|
},
|
|
{
|
|
"entropy": 5.550037479400634,
|
|
"epoch": 2.0648059751783006,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00045807088775859595,
|
|
"loss": 5.2361,
|
|
"mean_token_accuracy": 0.19692100584506989,
|
|
"num_tokens": 41037240.0,
|
|
"step": 18385
|
|
},
|
|
{
|
|
"entropy": 5.581348323822022,
|
|
"epoch": 2.065367552086258,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004580475440937527,
|
|
"loss": 5.2614,
|
|
"mean_token_accuracy": 0.19321570843458175,
|
|
"num_tokens": 41048258.0,
|
|
"step": 18390
|
|
},
|
|
{
|
|
"entropy": 5.55000319480896,
|
|
"epoch": 2.065929128994216,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045802419460060464,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.19045539945363998,
|
|
"num_tokens": 41058204.0,
|
|
"step": 18395
|
|
},
|
|
{
|
|
"entropy": 5.600442266464233,
|
|
"epoch": 2.066490705902173,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004580008392798953,
|
|
"loss": 5.3286,
|
|
"mean_token_accuracy": 0.18861439526081086,
|
|
"num_tokens": 41070019.0,
|
|
"step": 18400
|
|
},
|
|
{
|
|
"entropy": 5.568366479873657,
|
|
"epoch": 2.0670522828101308,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045797747813236815,
|
|
"loss": 5.3081,
|
|
"mean_token_accuracy": 0.1952594593167305,
|
|
"num_tokens": 41081503.0,
|
|
"step": 18405
|
|
},
|
|
{
|
|
"entropy": 5.522409677505493,
|
|
"epoch": 2.0676138597180884,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045795411115876725,
|
|
"loss": 5.2604,
|
|
"mean_token_accuracy": 0.1867133304476738,
|
|
"num_tokens": 41091959.0,
|
|
"step": 18410
|
|
},
|
|
{
|
|
"entropy": 5.567802381515503,
|
|
"epoch": 2.068175436626046,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00045793073835983644,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.18891976326704024,
|
|
"num_tokens": 41103193.0,
|
|
"step": 18415
|
|
},
|
|
{
|
|
"entropy": 5.597355031967163,
|
|
"epoch": 2.0687370135340033,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045790735973631996,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.19679370522499084,
|
|
"num_tokens": 41115886.0,
|
|
"step": 18420
|
|
},
|
|
{
|
|
"entropy": 5.502266597747803,
|
|
"epoch": 2.069298590441961,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045788397528896224,
|
|
"loss": 5.2318,
|
|
"mean_token_accuracy": 0.1901304915547371,
|
|
"num_tokens": 41126868.0,
|
|
"step": 18425
|
|
},
|
|
{
|
|
"entropy": 5.5831990242004395,
|
|
"epoch": 2.0698601673499186,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045786058501850774,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.1980134904384613,
|
|
"num_tokens": 41136417.0,
|
|
"step": 18430
|
|
},
|
|
{
|
|
"entropy": 5.535528135299683,
|
|
"epoch": 2.0704217442578763,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00045783718892570136,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.18714429438114166,
|
|
"num_tokens": 41149515.0,
|
|
"step": 18435
|
|
},
|
|
{
|
|
"entropy": 5.572864389419555,
|
|
"epoch": 2.0709833211658335,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000457813787011288,
|
|
"loss": 5.3441,
|
|
"mean_token_accuracy": 0.19737367033958436,
|
|
"num_tokens": 41160023.0,
|
|
"step": 18440
|
|
},
|
|
{
|
|
"entropy": 5.423291921615601,
|
|
"epoch": 2.071544898073791,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004577903792760127,
|
|
"loss": 5.1299,
|
|
"mean_token_accuracy": 0.20345488637685777,
|
|
"num_tokens": 41170909.0,
|
|
"step": 18445
|
|
},
|
|
{
|
|
"entropy": 5.577049922943115,
|
|
"epoch": 2.072106474981749,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004577669657206209,
|
|
"loss": 5.3433,
|
|
"mean_token_accuracy": 0.19078997820615767,
|
|
"num_tokens": 41181960.0,
|
|
"step": 18450
|
|
},
|
|
{
|
|
"entropy": 5.620526456832886,
|
|
"epoch": 2.0726680518897065,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004577435463458579,
|
|
"loss": 5.3401,
|
|
"mean_token_accuracy": 0.1875019669532776,
|
|
"num_tokens": 41192292.0,
|
|
"step": 18455
|
|
},
|
|
{
|
|
"entropy": 5.584227991104126,
|
|
"epoch": 2.0732296287976637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004577201211524696,
|
|
"loss": 5.2847,
|
|
"mean_token_accuracy": 0.19283845275640488,
|
|
"num_tokens": 41203826.0,
|
|
"step": 18460
|
|
},
|
|
{
|
|
"entropy": 5.458957624435425,
|
|
"epoch": 2.0737912057056214,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004576966901412018,
|
|
"loss": 5.2998,
|
|
"mean_token_accuracy": 0.19395221918821334,
|
|
"num_tokens": 41215095.0,
|
|
"step": 18465
|
|
},
|
|
{
|
|
"entropy": 5.492665863037109,
|
|
"epoch": 2.074352782613579,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045767325331280044,
|
|
"loss": 5.1811,
|
|
"mean_token_accuracy": 0.19702965766191483,
|
|
"num_tokens": 41224953.0,
|
|
"step": 18470
|
|
},
|
|
{
|
|
"entropy": 5.544835567474365,
|
|
"epoch": 2.0749143595215367,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004576498106680119,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.1845150277018547,
|
|
"num_tokens": 41235479.0,
|
|
"step": 18475
|
|
},
|
|
{
|
|
"entropy": 5.5399524688720705,
|
|
"epoch": 2.075475936429494,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004576263622075826,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.18817681223154067,
|
|
"num_tokens": 41248520.0,
|
|
"step": 18480
|
|
},
|
|
{
|
|
"entropy": 5.60011625289917,
|
|
"epoch": 2.0760375133374516,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000457602907932259,
|
|
"loss": 5.4001,
|
|
"mean_token_accuracy": 0.18569980412721634,
|
|
"num_tokens": 41259112.0,
|
|
"step": 18485
|
|
},
|
|
{
|
|
"entropy": 5.548983144760132,
|
|
"epoch": 2.0765990902454092,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045757944784278803,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.1937241330742836,
|
|
"num_tokens": 41269554.0,
|
|
"step": 18490
|
|
},
|
|
{
|
|
"entropy": 5.534727001190186,
|
|
"epoch": 2.0771606671533664,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004575559819399166,
|
|
"loss": 5.288,
|
|
"mean_token_accuracy": 0.19030659645795822,
|
|
"num_tokens": 41281339.0,
|
|
"step": 18495
|
|
},
|
|
{
|
|
"entropy": 5.46879472732544,
|
|
"epoch": 2.077722244061324,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045753251022439195,
|
|
"loss": 5.1796,
|
|
"mean_token_accuracy": 0.20162457078695298,
|
|
"num_tokens": 41291629.0,
|
|
"step": 18500
|
|
},
|
|
{
|
|
"entropy": 5.592170715332031,
|
|
"epoch": 2.0782838209692818,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004575090326969614,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.19290124922990798,
|
|
"num_tokens": 41302162.0,
|
|
"step": 18505
|
|
},
|
|
{
|
|
"entropy": 5.532966423034668,
|
|
"epoch": 2.0788453978772394,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004574855493583723,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.19383668750524521,
|
|
"num_tokens": 41313667.0,
|
|
"step": 18510
|
|
},
|
|
{
|
|
"entropy": 5.48036527633667,
|
|
"epoch": 2.0794069747851966,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045746206020937276,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.19088611751794815,
|
|
"num_tokens": 41325063.0,
|
|
"step": 18515
|
|
},
|
|
{
|
|
"entropy": 5.5291173458099365,
|
|
"epoch": 2.0799685516931543,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045743856525071034,
|
|
"loss": 5.2909,
|
|
"mean_token_accuracy": 0.19512646049261093,
|
|
"num_tokens": 41335974.0,
|
|
"step": 18520
|
|
},
|
|
{
|
|
"entropy": 5.510433673858643,
|
|
"epoch": 2.080530128601112,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045741506448313327,
|
|
"loss": 5.2427,
|
|
"mean_token_accuracy": 0.19161279648542404,
|
|
"num_tokens": 41347469.0,
|
|
"step": 18525
|
|
},
|
|
{
|
|
"entropy": 5.578920841217041,
|
|
"epoch": 2.0810917055090696,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00045739155790738975,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19464484453201295,
|
|
"num_tokens": 41358418.0,
|
|
"step": 18530
|
|
},
|
|
{
|
|
"entropy": 5.548485946655274,
|
|
"epoch": 2.081653282417027,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045736804552422836,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.19568856358528136,
|
|
"num_tokens": 41368859.0,
|
|
"step": 18535
|
|
},
|
|
{
|
|
"entropy": 5.553003120422363,
|
|
"epoch": 2.0822148593249845,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004573445273343976,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.18351247906684875,
|
|
"num_tokens": 41380929.0,
|
|
"step": 18540
|
|
},
|
|
{
|
|
"entropy": 5.503594589233399,
|
|
"epoch": 2.082776436232942,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004573210033386464,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.1968427613377571,
|
|
"num_tokens": 41392190.0,
|
|
"step": 18545
|
|
},
|
|
{
|
|
"entropy": 5.584130144119262,
|
|
"epoch": 2.0833380131409,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004572974735377238,
|
|
"loss": 5.2319,
|
|
"mean_token_accuracy": 0.20184319615364074,
|
|
"num_tokens": 41402646.0,
|
|
"step": 18550
|
|
},
|
|
{
|
|
"entropy": 5.4544947147369385,
|
|
"epoch": 2.083899590048857,
|
|
"grad_norm": 1.828125,
|
|
"learning_rate": 0.0004572739379323788,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.1867653325200081,
|
|
"num_tokens": 41415179.0,
|
|
"step": 18555
|
|
},
|
|
{
|
|
"entropy": 5.5243510723114015,
|
|
"epoch": 2.0844611669568147,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045725039652336105,
|
|
"loss": 5.3116,
|
|
"mean_token_accuracy": 0.18787004947662353,
|
|
"num_tokens": 41426695.0,
|
|
"step": 18560
|
|
},
|
|
{
|
|
"entropy": 5.5220081329345705,
|
|
"epoch": 2.0850227438647724,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004572268493114199,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.19355572760105133,
|
|
"num_tokens": 41438078.0,
|
|
"step": 18565
|
|
},
|
|
{
|
|
"entropy": 5.547357654571533,
|
|
"epoch": 2.08558432077273,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004572032962973052,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.18998038321733474,
|
|
"num_tokens": 41448862.0,
|
|
"step": 18570
|
|
},
|
|
{
|
|
"entropy": 5.452404260635376,
|
|
"epoch": 2.0861458976806873,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045717973748176695,
|
|
"loss": 5.0881,
|
|
"mean_token_accuracy": 0.20200226157903672,
|
|
"num_tokens": 41458528.0,
|
|
"step": 18575
|
|
},
|
|
{
|
|
"entropy": 5.4530195713043215,
|
|
"epoch": 2.086707474588645,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045715617286555516,
|
|
"loss": 5.2091,
|
|
"mean_token_accuracy": 0.1893178328871727,
|
|
"num_tokens": 41469553.0,
|
|
"step": 18580
|
|
},
|
|
{
|
|
"entropy": 5.602101039886475,
|
|
"epoch": 2.0872690514966026,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045713260244942017,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.19021859765052795,
|
|
"num_tokens": 41482327.0,
|
|
"step": 18585
|
|
},
|
|
{
|
|
"entropy": 5.464052152633667,
|
|
"epoch": 2.08783062840456,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004571090262341125,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.2081007793545723,
|
|
"num_tokens": 41493126.0,
|
|
"step": 18590
|
|
},
|
|
{
|
|
"entropy": 5.518912839889526,
|
|
"epoch": 2.0883922053125175,
|
|
"grad_norm": 1.78125,
|
|
"learning_rate": 0.00045708544422038284,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.1842724159359932,
|
|
"num_tokens": 41505597.0,
|
|
"step": 18595
|
|
},
|
|
{
|
|
"entropy": 5.568154001235962,
|
|
"epoch": 2.088953782220475,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004570618564089819,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.18787640929222107,
|
|
"num_tokens": 41517296.0,
|
|
"step": 18600
|
|
},
|
|
{
|
|
"entropy": 5.563290071487427,
|
|
"epoch": 2.089515359128433,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045703826280066095,
|
|
"loss": 5.2577,
|
|
"mean_token_accuracy": 0.19719821959733963,
|
|
"num_tokens": 41529900.0,
|
|
"step": 18605
|
|
},
|
|
{
|
|
"entropy": 5.517068099975586,
|
|
"epoch": 2.09007693603639,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004570146633961711,
|
|
"loss": 5.2854,
|
|
"mean_token_accuracy": 0.19486710131168367,
|
|
"num_tokens": 41540641.0,
|
|
"step": 18610
|
|
},
|
|
{
|
|
"entropy": 5.458851146697998,
|
|
"epoch": 2.0906385129443477,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045699105819626374,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.18909004628658294,
|
|
"num_tokens": 41551335.0,
|
|
"step": 18615
|
|
},
|
|
{
|
|
"entropy": 5.528979349136352,
|
|
"epoch": 2.0912000898523053,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004569674472016904,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.19515670835971832,
|
|
"num_tokens": 41562265.0,
|
|
"step": 18620
|
|
},
|
|
{
|
|
"entropy": 5.549470663070679,
|
|
"epoch": 2.091761666760263,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004569438304132031,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.19890174120664597,
|
|
"num_tokens": 41574758.0,
|
|
"step": 18625
|
|
},
|
|
{
|
|
"entropy": 5.405692625045776,
|
|
"epoch": 2.09232324366822,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045692020783155376,
|
|
"loss": 5.1284,
|
|
"mean_token_accuracy": 0.1987699404358864,
|
|
"num_tokens": 41585007.0,
|
|
"step": 18630
|
|
},
|
|
{
|
|
"entropy": 5.419830226898194,
|
|
"epoch": 2.092884820576178,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004568965794574943,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.19426818639039994,
|
|
"num_tokens": 41596026.0,
|
|
"step": 18635
|
|
},
|
|
{
|
|
"entropy": 5.573201465606689,
|
|
"epoch": 2.0934463974841355,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004568729452917772,
|
|
"loss": 5.3265,
|
|
"mean_token_accuracy": 0.19361858069896698,
|
|
"num_tokens": 41608440.0,
|
|
"step": 18640
|
|
},
|
|
{
|
|
"entropy": 5.5410181999206545,
|
|
"epoch": 2.094007974392093,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045684930533515506,
|
|
"loss": 5.2231,
|
|
"mean_token_accuracy": 0.19025521278381347,
|
|
"num_tokens": 41620467.0,
|
|
"step": 18645
|
|
},
|
|
{
|
|
"entropy": 5.446234560012817,
|
|
"epoch": 2.0945695513000504,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045682565958838045,
|
|
"loss": 5.212,
|
|
"mean_token_accuracy": 0.1939581260085106,
|
|
"num_tokens": 41630918.0,
|
|
"step": 18650
|
|
},
|
|
{
|
|
"entropy": 5.502481317520141,
|
|
"epoch": 2.095131128208008,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004568020080522063,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.19510465115308762,
|
|
"num_tokens": 41641148.0,
|
|
"step": 18655
|
|
},
|
|
{
|
|
"entropy": 5.568475675582886,
|
|
"epoch": 2.0956927051159657,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004567783507273858,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.1957976385951042,
|
|
"num_tokens": 41652148.0,
|
|
"step": 18660
|
|
},
|
|
{
|
|
"entropy": 5.453569984436035,
|
|
"epoch": 2.0962542820239234,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045675468761467204,
|
|
"loss": 5.2473,
|
|
"mean_token_accuracy": 0.19199995696544647,
|
|
"num_tokens": 41662275.0,
|
|
"step": 18665
|
|
},
|
|
{
|
|
"entropy": 5.566884326934814,
|
|
"epoch": 2.0968158589318806,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045673101871481853,
|
|
"loss": 5.2948,
|
|
"mean_token_accuracy": 0.1896268457174301,
|
|
"num_tokens": 41673141.0,
|
|
"step": 18670
|
|
},
|
|
{
|
|
"entropy": 5.644404363632202,
|
|
"epoch": 2.0973774358398383,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004567073440285789,
|
|
"loss": 5.3972,
|
|
"mean_token_accuracy": 0.18449253886938094,
|
|
"num_tokens": 41683473.0,
|
|
"step": 18675
|
|
},
|
|
{
|
|
"entropy": 5.4291088581085205,
|
|
"epoch": 2.097939012747796,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045668366355670697,
|
|
"loss": 5.0503,
|
|
"mean_token_accuracy": 0.201994326710701,
|
|
"num_tokens": 41693847.0,
|
|
"step": 18680
|
|
},
|
|
{
|
|
"entropy": 5.493892574310303,
|
|
"epoch": 2.098500589655753,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004566599772999567,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.19080937653779984,
|
|
"num_tokens": 41705810.0,
|
|
"step": 18685
|
|
},
|
|
{
|
|
"entropy": 5.472356081008911,
|
|
"epoch": 2.099062166563711,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045663628525908237,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.19318359941244126,
|
|
"num_tokens": 41717160.0,
|
|
"step": 18690
|
|
},
|
|
{
|
|
"entropy": 5.569525194168091,
|
|
"epoch": 2.0996237434716685,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004566125874348382,
|
|
"loss": 5.3312,
|
|
"mean_token_accuracy": 0.1916143611073494,
|
|
"num_tokens": 41728631.0,
|
|
"step": 18695
|
|
},
|
|
{
|
|
"entropy": 5.61010217666626,
|
|
"epoch": 2.100185320379626,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045658888382797886,
|
|
"loss": 5.3551,
|
|
"mean_token_accuracy": 0.1856017142534256,
|
|
"num_tokens": 41738933.0,
|
|
"step": 18700
|
|
},
|
|
{
|
|
"entropy": 5.65227198600769,
|
|
"epoch": 2.1007468972875833,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045656517443925897,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.19532966911792754,
|
|
"num_tokens": 41750386.0,
|
|
"step": 18705
|
|
},
|
|
{
|
|
"entropy": 5.497491025924683,
|
|
"epoch": 2.101308474195541,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004565414592694336,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.19657013714313507,
|
|
"num_tokens": 41760711.0,
|
|
"step": 18710
|
|
},
|
|
{
|
|
"entropy": 5.477353143692016,
|
|
"epoch": 2.1018700511034987,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004565177383192577,
|
|
"loss": 5.3315,
|
|
"mean_token_accuracy": 0.184172560274601,
|
|
"num_tokens": 41772147.0,
|
|
"step": 18715
|
|
},
|
|
{
|
|
"entropy": 5.587006330490112,
|
|
"epoch": 2.1024316280114563,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045649401158948664,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19914837926626205,
|
|
"num_tokens": 41783265.0,
|
|
"step": 18720
|
|
},
|
|
{
|
|
"entropy": 5.516242790222168,
|
|
"epoch": 2.1029932049194136,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004564702790808758,
|
|
"loss": 5.1858,
|
|
"mean_token_accuracy": 0.19953457564115523,
|
|
"num_tokens": 41793977.0,
|
|
"step": 18725
|
|
},
|
|
{
|
|
"entropy": 5.502975511550903,
|
|
"epoch": 2.103554781827371,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004564465407941809,
|
|
"loss": 5.1984,
|
|
"mean_token_accuracy": 0.2001998707652092,
|
|
"num_tokens": 41804790.0,
|
|
"step": 18730
|
|
},
|
|
{
|
|
"entropy": 5.4702671527862545,
|
|
"epoch": 2.104116358735329,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045642279673015787,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.192343170940876,
|
|
"num_tokens": 41815611.0,
|
|
"step": 18735
|
|
},
|
|
{
|
|
"entropy": 5.421444845199585,
|
|
"epoch": 2.1046779356432865,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004563990468895625,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.189383827149868,
|
|
"num_tokens": 41826935.0,
|
|
"step": 18740
|
|
},
|
|
{
|
|
"entropy": 5.449337577819824,
|
|
"epoch": 2.1052395125512438,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004563752912731512,
|
|
"loss": 5.1855,
|
|
"mean_token_accuracy": 0.19496824443340302,
|
|
"num_tokens": 41838932.0,
|
|
"step": 18745
|
|
},
|
|
{
|
|
"entropy": 5.426710414886474,
|
|
"epoch": 2.1058010894592014,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004563515298816803,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.19172888845205308,
|
|
"num_tokens": 41850771.0,
|
|
"step": 18750
|
|
},
|
|
{
|
|
"entropy": 5.521370792388916,
|
|
"epoch": 2.106362666367159,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045632776271590624,
|
|
"loss": 5.1782,
|
|
"mean_token_accuracy": 0.20007923245429993,
|
|
"num_tokens": 41861515.0,
|
|
"step": 18755
|
|
},
|
|
{
|
|
"entropy": 5.475457763671875,
|
|
"epoch": 2.1069242432751167,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004563039897765859,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.2080126866698265,
|
|
"num_tokens": 41872195.0,
|
|
"step": 18760
|
|
},
|
|
{
|
|
"entropy": 5.370282745361328,
|
|
"epoch": 2.107485820183074,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004562802110644764,
|
|
"loss": 5.2106,
|
|
"mean_token_accuracy": 0.2016306385397911,
|
|
"num_tokens": 41882496.0,
|
|
"step": 18765
|
|
},
|
|
{
|
|
"entropy": 5.60964560508728,
|
|
"epoch": 2.1080473970910316,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045625642658033447,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.18533518463373183,
|
|
"num_tokens": 41893078.0,
|
|
"step": 18770
|
|
},
|
|
{
|
|
"entropy": 5.58244948387146,
|
|
"epoch": 2.1086089739989893,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045623263632491766,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.18813737034797667,
|
|
"num_tokens": 41905062.0,
|
|
"step": 18775
|
|
},
|
|
{
|
|
"entropy": 5.456647968292236,
|
|
"epoch": 2.1091705509069465,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045620884029898344,
|
|
"loss": 5.2458,
|
|
"mean_token_accuracy": 0.19331082105636596,
|
|
"num_tokens": 41916086.0,
|
|
"step": 18780
|
|
},
|
|
{
|
|
"entropy": 5.538427019119263,
|
|
"epoch": 2.109732127814904,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045618503850328954,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.19885223954916,
|
|
"num_tokens": 41925466.0,
|
|
"step": 18785
|
|
},
|
|
{
|
|
"entropy": 5.571448707580567,
|
|
"epoch": 2.110293704722862,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004561612309385936,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18774051517248153,
|
|
"num_tokens": 41936567.0,
|
|
"step": 18790
|
|
},
|
|
{
|
|
"entropy": 5.488919019699097,
|
|
"epoch": 2.1108552816308195,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045613741760565385,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.19824633598327637,
|
|
"num_tokens": 41947021.0,
|
|
"step": 18795
|
|
},
|
|
{
|
|
"entropy": 5.561722230911255,
|
|
"epoch": 2.1114168585387767,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004561135985052285,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.19321614056825637,
|
|
"num_tokens": 41957929.0,
|
|
"step": 18800
|
|
},
|
|
{
|
|
"entropy": 5.462351608276367,
|
|
"epoch": 2.1119784354467344,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000456089773638076,
|
|
"loss": 5.1617,
|
|
"mean_token_accuracy": 0.19819309562444687,
|
|
"num_tokens": 41968677.0,
|
|
"step": 18805
|
|
},
|
|
{
|
|
"entropy": 5.515204572677613,
|
|
"epoch": 2.112540012354692,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004560659430049548,
|
|
"loss": 5.3197,
|
|
"mean_token_accuracy": 0.1953011229634285,
|
|
"num_tokens": 41980330.0,
|
|
"step": 18810
|
|
},
|
|
{
|
|
"entropy": 5.524660396575928,
|
|
"epoch": 2.1131015892626497,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004560421066066237,
|
|
"loss": 5.2372,
|
|
"mean_token_accuracy": 0.1975623995065689,
|
|
"num_tokens": 41991258.0,
|
|
"step": 18815
|
|
},
|
|
{
|
|
"entropy": 5.577877998352051,
|
|
"epoch": 2.113663166170607,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045601826444384175,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.19632827043533324,
|
|
"num_tokens": 42002679.0,
|
|
"step": 18820
|
|
},
|
|
{
|
|
"entropy": 5.448603391647339,
|
|
"epoch": 2.1142247430785646,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045599441651736805,
|
|
"loss": 5.1887,
|
|
"mean_token_accuracy": 0.19818733781576156,
|
|
"num_tokens": 42012845.0,
|
|
"step": 18825
|
|
},
|
|
{
|
|
"entropy": 5.5551344871521,
|
|
"epoch": 2.1147863199865222,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00045597056282796196,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.18872618675231934,
|
|
"num_tokens": 42024461.0,
|
|
"step": 18830
|
|
},
|
|
{
|
|
"entropy": 5.5335471630096436,
|
|
"epoch": 2.11534789689448,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004559467033763829,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1917546808719635,
|
|
"num_tokens": 42036996.0,
|
|
"step": 18835
|
|
},
|
|
{
|
|
"entropy": 5.562220239639283,
|
|
"epoch": 2.115909473802437,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004559228381633907,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.19196655005216598,
|
|
"num_tokens": 42048731.0,
|
|
"step": 18840
|
|
},
|
|
{
|
|
"entropy": 5.589961290359497,
|
|
"epoch": 2.1164710507103948,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00045589896718974517,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.19407839328050613,
|
|
"num_tokens": 42060396.0,
|
|
"step": 18845
|
|
},
|
|
{
|
|
"entropy": 5.425152254104614,
|
|
"epoch": 2.1170326276183524,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004558750904562063,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.1964937314391136,
|
|
"num_tokens": 42072037.0,
|
|
"step": 18850
|
|
},
|
|
{
|
|
"entropy": 5.464056062698364,
|
|
"epoch": 2.11759420452631,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004558512079635345,
|
|
"loss": 5.1436,
|
|
"mean_token_accuracy": 0.20330312699079514,
|
|
"num_tokens": 42082577.0,
|
|
"step": 18855
|
|
},
|
|
{
|
|
"entropy": 5.404180574417114,
|
|
"epoch": 2.1181557814342673,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004558273197124899,
|
|
"loss": 5.1525,
|
|
"mean_token_accuracy": 0.20355821251869202,
|
|
"num_tokens": 42093978.0,
|
|
"step": 18860
|
|
},
|
|
{
|
|
"entropy": 5.510999870300293,
|
|
"epoch": 2.118717358342225,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00045580342570383347,
|
|
"loss": 5.3673,
|
|
"mean_token_accuracy": 0.18738407790660858,
|
|
"num_tokens": 42105773.0,
|
|
"step": 18865
|
|
},
|
|
{
|
|
"entropy": 5.520964670181274,
|
|
"epoch": 2.1192789352501826,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004557795259383258,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.19446599930524827,
|
|
"num_tokens": 42116232.0,
|
|
"step": 18870
|
|
},
|
|
{
|
|
"entropy": 5.479474353790283,
|
|
"epoch": 2.11984051215814,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045575562041672794,
|
|
"loss": 5.292,
|
|
"mean_token_accuracy": 0.19202446043491364,
|
|
"num_tokens": 42127813.0,
|
|
"step": 18875
|
|
},
|
|
{
|
|
"entropy": 5.4732810974121096,
|
|
"epoch": 2.1204020890660975,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045573170913980094,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.19381166994571686,
|
|
"num_tokens": 42138054.0,
|
|
"step": 18880
|
|
},
|
|
{
|
|
"entropy": 5.579210329055786,
|
|
"epoch": 2.120963665974055,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045570779210830627,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.18862388134002686,
|
|
"num_tokens": 42149575.0,
|
|
"step": 18885
|
|
},
|
|
{
|
|
"entropy": 5.474399280548096,
|
|
"epoch": 2.121525242882013,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004556838693230054,
|
|
"loss": 5.2918,
|
|
"mean_token_accuracy": 0.19200508296489716,
|
|
"num_tokens": 42160824.0,
|
|
"step": 18890
|
|
},
|
|
{
|
|
"entropy": 5.493786764144898,
|
|
"epoch": 2.12208681978997,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045565994078466005,
|
|
"loss": 5.3164,
|
|
"mean_token_accuracy": 0.19644628316164017,
|
|
"num_tokens": 42171088.0,
|
|
"step": 18895
|
|
},
|
|
{
|
|
"entropy": 5.498514413833618,
|
|
"epoch": 2.1226483966979277,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045563600649403213,
|
|
"loss": 5.2673,
|
|
"mean_token_accuracy": 0.19039820730686188,
|
|
"num_tokens": 42182112.0,
|
|
"step": 18900
|
|
},
|
|
{
|
|
"entropy": 5.5605250835418705,
|
|
"epoch": 2.1232099736058854,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004556120664518838,
|
|
"loss": 5.1559,
|
|
"mean_token_accuracy": 0.20501697957515716,
|
|
"num_tokens": 42193563.0,
|
|
"step": 18905
|
|
},
|
|
{
|
|
"entropy": 5.476816272735595,
|
|
"epoch": 2.123771550513843,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004555881206589771,
|
|
"loss": 5.2206,
|
|
"mean_token_accuracy": 0.19590689986944199,
|
|
"num_tokens": 42204891.0,
|
|
"step": 18910
|
|
},
|
|
{
|
|
"entropy": 5.499167108535767,
|
|
"epoch": 2.1243331274218002,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004555641691160746,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.19857258200645447,
|
|
"num_tokens": 42217226.0,
|
|
"step": 18915
|
|
},
|
|
{
|
|
"entropy": 5.5570038795471195,
|
|
"epoch": 2.124894704329758,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000455540211823939,
|
|
"loss": 5.2767,
|
|
"mean_token_accuracy": 0.18805427849292755,
|
|
"num_tokens": 42228134.0,
|
|
"step": 18920
|
|
},
|
|
{
|
|
"entropy": 5.549654912948609,
|
|
"epoch": 2.1254562812377156,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045551624878333296,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.1880549281835556,
|
|
"num_tokens": 42239868.0,
|
|
"step": 18925
|
|
},
|
|
{
|
|
"entropy": 5.5306213855743405,
|
|
"epoch": 2.1260178581456732,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045549227999501957,
|
|
"loss": 5.3199,
|
|
"mean_token_accuracy": 0.19649683237075805,
|
|
"num_tokens": 42250297.0,
|
|
"step": 18930
|
|
},
|
|
{
|
|
"entropy": 5.4999772071838375,
|
|
"epoch": 2.1265794350536305,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045546830545976203,
|
|
"loss": 5.0308,
|
|
"mean_token_accuracy": 0.2116914361715317,
|
|
"num_tokens": 42261263.0,
|
|
"step": 18935
|
|
},
|
|
{
|
|
"entropy": 5.516724300384522,
|
|
"epoch": 2.127141011961588,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045544432517832356,
|
|
"loss": 5.3097,
|
|
"mean_token_accuracy": 0.1959936037659645,
|
|
"num_tokens": 42272357.0,
|
|
"step": 18940
|
|
},
|
|
{
|
|
"entropy": 5.5358238697052,
|
|
"epoch": 2.1277025888695458,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045542033915146787,
|
|
"loss": 5.3384,
|
|
"mean_token_accuracy": 0.1926393985748291,
|
|
"num_tokens": 42283630.0,
|
|
"step": 18945
|
|
},
|
|
{
|
|
"entropy": 5.513246011734009,
|
|
"epoch": 2.1282641657775034,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00045539634737995857,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.17850194424390792,
|
|
"num_tokens": 42294981.0,
|
|
"step": 18950
|
|
},
|
|
{
|
|
"entropy": 5.510193824768066,
|
|
"epoch": 2.1288257426854607,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045537234986455964,
|
|
"loss": 5.2216,
|
|
"mean_token_accuracy": 0.1941283866763115,
|
|
"num_tokens": 42304877.0,
|
|
"step": 18955
|
|
},
|
|
{
|
|
"entropy": 5.522894620895386,
|
|
"epoch": 2.1293873195934183,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004553483466060351,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.18936374336481093,
|
|
"num_tokens": 42316325.0,
|
|
"step": 18960
|
|
},
|
|
{
|
|
"entropy": 5.50593786239624,
|
|
"epoch": 2.129948896501376,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00045532433760514925,
|
|
"loss": 5.2537,
|
|
"mean_token_accuracy": 0.19228193163871765,
|
|
"num_tokens": 42327437.0,
|
|
"step": 18965
|
|
},
|
|
{
|
|
"entropy": 5.417781209945678,
|
|
"epoch": 2.130510473409333,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004553003228626665,
|
|
"loss": 5.1608,
|
|
"mean_token_accuracy": 0.20140596032142638,
|
|
"num_tokens": 42337742.0,
|
|
"step": 18970
|
|
},
|
|
{
|
|
"entropy": 5.481891870498657,
|
|
"epoch": 2.131072050317291,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004552763023793517,
|
|
"loss": 5.2415,
|
|
"mean_token_accuracy": 0.19514294862747192,
|
|
"num_tokens": 42348511.0,
|
|
"step": 18975
|
|
},
|
|
{
|
|
"entropy": 5.497203683853149,
|
|
"epoch": 2.1316336272252485,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004552522761559694,
|
|
"loss": 5.2144,
|
|
"mean_token_accuracy": 0.19798169136047364,
|
|
"num_tokens": 42358977.0,
|
|
"step": 18980
|
|
},
|
|
{
|
|
"entropy": 5.550813913345337,
|
|
"epoch": 2.132195204133206,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00045522824419328475,
|
|
"loss": 5.3398,
|
|
"mean_token_accuracy": 0.1870965003967285,
|
|
"num_tokens": 42371609.0,
|
|
"step": 18985
|
|
},
|
|
{
|
|
"entropy": 5.569743967056274,
|
|
"epoch": 2.1327567810411634,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045520420649206283,
|
|
"loss": 5.2638,
|
|
"mean_token_accuracy": 0.19838677048683168,
|
|
"num_tokens": 42383150.0,
|
|
"step": 18990
|
|
},
|
|
{
|
|
"entropy": 5.466172885894776,
|
|
"epoch": 2.133318357949121,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004551801630530692,
|
|
"loss": 5.2089,
|
|
"mean_token_accuracy": 0.1918472483754158,
|
|
"num_tokens": 42395150.0,
|
|
"step": 18995
|
|
},
|
|
{
|
|
"entropy": 5.507394647598266,
|
|
"epoch": 2.1338799348570787,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004551561138770693,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.19413267225027084,
|
|
"num_tokens": 42406348.0,
|
|
"step": 19000
|
|
},
|
|
{
|
|
"entropy": 5.560656356811523,
|
|
"epoch": 2.1344415117650364,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00045513205896482875,
|
|
"loss": 5.2683,
|
|
"mean_token_accuracy": 0.18529891222715378,
|
|
"num_tokens": 42417183.0,
|
|
"step": 19005
|
|
},
|
|
{
|
|
"entropy": 5.538243293762207,
|
|
"epoch": 2.1350030886729936,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045510799831711366,
|
|
"loss": 5.2147,
|
|
"mean_token_accuracy": 0.2042955592274666,
|
|
"num_tokens": 42427805.0,
|
|
"step": 19010
|
|
},
|
|
{
|
|
"entropy": 5.532821226119995,
|
|
"epoch": 2.1355646655809513,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045508393193469,
|
|
"loss": 5.2233,
|
|
"mean_token_accuracy": 0.1936241418123245,
|
|
"num_tokens": 42439521.0,
|
|
"step": 19015
|
|
},
|
|
{
|
|
"entropy": 5.57507061958313,
|
|
"epoch": 2.136126242488909,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004550598598183241,
|
|
"loss": 5.3526,
|
|
"mean_token_accuracy": 0.1906222313642502,
|
|
"num_tokens": 42451201.0,
|
|
"step": 19020
|
|
},
|
|
{
|
|
"entropy": 5.539993476867676,
|
|
"epoch": 2.1366878193968666,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004550357819687825,
|
|
"loss": 5.2187,
|
|
"mean_token_accuracy": 0.1934363752603531,
|
|
"num_tokens": 42462315.0,
|
|
"step": 19025
|
|
},
|
|
{
|
|
"entropy": 5.655513906478882,
|
|
"epoch": 2.137249396304824,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004550116983868317,
|
|
"loss": 5.4185,
|
|
"mean_token_accuracy": 0.17984108924865722,
|
|
"num_tokens": 42473993.0,
|
|
"step": 19030
|
|
},
|
|
{
|
|
"entropy": 5.640888357162476,
|
|
"epoch": 2.1378109732127815,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004549876090732386,
|
|
"loss": 5.4136,
|
|
"mean_token_accuracy": 0.1858449950814247,
|
|
"num_tokens": 42484307.0,
|
|
"step": 19035
|
|
},
|
|
{
|
|
"entropy": 5.531917715072632,
|
|
"epoch": 2.138372550120739,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004549635140287703,
|
|
"loss": 5.3089,
|
|
"mean_token_accuracy": 0.19185017347335814,
|
|
"num_tokens": 42497305.0,
|
|
"step": 19040
|
|
},
|
|
{
|
|
"entropy": 5.570801687240601,
|
|
"epoch": 2.138934127028697,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045493941325419385,
|
|
"loss": 5.3044,
|
|
"mean_token_accuracy": 0.18875210881233215,
|
|
"num_tokens": 42508307.0,
|
|
"step": 19045
|
|
},
|
|
{
|
|
"entropy": 5.551884269714355,
|
|
"epoch": 2.139495703936654,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004549153067502768,
|
|
"loss": 5.3686,
|
|
"mean_token_accuracy": 0.1851409688591957,
|
|
"num_tokens": 42519946.0,
|
|
"step": 19050
|
|
},
|
|
{
|
|
"entropy": 5.4671406745910645,
|
|
"epoch": 2.1400572808446117,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045489119451778645,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.19710457921028138,
|
|
"num_tokens": 42530737.0,
|
|
"step": 19055
|
|
},
|
|
{
|
|
"entropy": 5.4123481750488285,
|
|
"epoch": 2.1406188577525693,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004548670765574908,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1971597343683243,
|
|
"num_tokens": 42542184.0,
|
|
"step": 19060
|
|
},
|
|
{
|
|
"entropy": 5.524309492111206,
|
|
"epoch": 2.1411804346605265,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00045484295287015757,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.1880420833826065,
|
|
"num_tokens": 42553816.0,
|
|
"step": 19065
|
|
},
|
|
{
|
|
"entropy": 5.61602520942688,
|
|
"epoch": 2.141742011568484,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004548188234565551,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.19569503366947175,
|
|
"num_tokens": 42564685.0,
|
|
"step": 19070
|
|
},
|
|
{
|
|
"entropy": 5.462467384338379,
|
|
"epoch": 2.142303588476442,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045479468831745144,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.18870755583047866,
|
|
"num_tokens": 42574864.0,
|
|
"step": 19075
|
|
},
|
|
{
|
|
"entropy": 5.475771570205689,
|
|
"epoch": 2.1428651653843995,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004547705474536152,
|
|
"loss": 5.2084,
|
|
"mean_token_accuracy": 0.19171673357486724,
|
|
"num_tokens": 42585214.0,
|
|
"step": 19080
|
|
},
|
|
{
|
|
"entropy": 5.536476182937622,
|
|
"epoch": 2.1434267422923567,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045474640086581506,
|
|
"loss": 5.3437,
|
|
"mean_token_accuracy": 0.19134631603956223,
|
|
"num_tokens": 42596017.0,
|
|
"step": 19085
|
|
},
|
|
{
|
|
"entropy": 5.508374929428101,
|
|
"epoch": 2.1439883192003144,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045472224855481975,
|
|
"loss": 5.2369,
|
|
"mean_token_accuracy": 0.18744268715381623,
|
|
"num_tokens": 42607903.0,
|
|
"step": 19090
|
|
},
|
|
{
|
|
"entropy": 5.512581253051758,
|
|
"epoch": 2.144549896108272,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045469809052139844,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.19229879677295686,
|
|
"num_tokens": 42618690.0,
|
|
"step": 19095
|
|
},
|
|
{
|
|
"entropy": 5.4738856792449955,
|
|
"epoch": 2.1451114730162297,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045467392676632016,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.1934794843196869,
|
|
"num_tokens": 42629655.0,
|
|
"step": 19100
|
|
},
|
|
{
|
|
"entropy": 5.519936275482178,
|
|
"epoch": 2.145673049924187,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004546497572903543,
|
|
"loss": 5.3241,
|
|
"mean_token_accuracy": 0.19361717253923416,
|
|
"num_tokens": 42641214.0,
|
|
"step": 19105
|
|
},
|
|
{
|
|
"entropy": 5.5499999046325685,
|
|
"epoch": 2.1462346268321446,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004546255820942706,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.18788168728351592,
|
|
"num_tokens": 42653829.0,
|
|
"step": 19110
|
|
},
|
|
{
|
|
"entropy": 5.569335269927978,
|
|
"epoch": 2.1467962037401023,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004546014011788386,
|
|
"loss": 5.2966,
|
|
"mean_token_accuracy": 0.1884668603539467,
|
|
"num_tokens": 42665245.0,
|
|
"step": 19115
|
|
},
|
|
{
|
|
"entropy": 5.488518857955933,
|
|
"epoch": 2.14735778064806,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004545772145448284,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.1907670259475708,
|
|
"num_tokens": 42676409.0,
|
|
"step": 19120
|
|
},
|
|
{
|
|
"entropy": 5.425270986557007,
|
|
"epoch": 2.147919357556017,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045455302219301,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.2023534059524536,
|
|
"num_tokens": 42686586.0,
|
|
"step": 19125
|
|
},
|
|
{
|
|
"entropy": 5.3874410629272464,
|
|
"epoch": 2.148480934463975,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004545288241241538,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.20010867714881897,
|
|
"num_tokens": 42696597.0,
|
|
"step": 19130
|
|
},
|
|
{
|
|
"entropy": 5.571540498733521,
|
|
"epoch": 2.1490425113719325,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004545046203390302,
|
|
"loss": 5.3509,
|
|
"mean_token_accuracy": 0.1936986654996872,
|
|
"num_tokens": 42707447.0,
|
|
"step": 19135
|
|
},
|
|
{
|
|
"entropy": 5.671237516403198,
|
|
"epoch": 2.14960408827989,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045448041083840973,
|
|
"loss": 5.3601,
|
|
"mean_token_accuracy": 0.18586227744817735,
|
|
"num_tokens": 42717533.0,
|
|
"step": 19140
|
|
},
|
|
{
|
|
"entropy": 5.59612627029419,
|
|
"epoch": 2.1501656651878474,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045445619562306354,
|
|
"loss": 5.3625,
|
|
"mean_token_accuracy": 0.1886406198143959,
|
|
"num_tokens": 42730563.0,
|
|
"step": 19145
|
|
},
|
|
{
|
|
"entropy": 5.48083815574646,
|
|
"epoch": 2.150727242095805,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045443197469376243,
|
|
"loss": 5.2256,
|
|
"mean_token_accuracy": 0.19888278245925903,
|
|
"num_tokens": 42740301.0,
|
|
"step": 19150
|
|
},
|
|
{
|
|
"entropy": 5.520439720153808,
|
|
"epoch": 2.1512888190037627,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004544077480512776,
|
|
"loss": 5.2719,
|
|
"mean_token_accuracy": 0.1885919228196144,
|
|
"num_tokens": 42752296.0,
|
|
"step": 19155
|
|
},
|
|
{
|
|
"entropy": 5.469354438781738,
|
|
"epoch": 2.15185039591172,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045438351569638055,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.20027718245983123,
|
|
"num_tokens": 42762530.0,
|
|
"step": 19160
|
|
},
|
|
{
|
|
"entropy": 5.454477405548095,
|
|
"epoch": 2.1524119728196776,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045435927762984277,
|
|
"loss": 5.1854,
|
|
"mean_token_accuracy": 0.1981496974825859,
|
|
"num_tokens": 42773059.0,
|
|
"step": 19165
|
|
},
|
|
{
|
|
"entropy": 5.476218032836914,
|
|
"epoch": 2.152973549727635,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000454335033852436,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.19704461693763733,
|
|
"num_tokens": 42783832.0,
|
|
"step": 19170
|
|
},
|
|
{
|
|
"entropy": 5.540331506729126,
|
|
"epoch": 2.153535126635593,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004543107843649322,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.19597008377313613,
|
|
"num_tokens": 42794565.0,
|
|
"step": 19175
|
|
},
|
|
{
|
|
"entropy": 5.568393802642822,
|
|
"epoch": 2.15409670354355,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004542865291681035,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.1866248294711113,
|
|
"num_tokens": 42805536.0,
|
|
"step": 19180
|
|
},
|
|
{
|
|
"entropy": 5.54846715927124,
|
|
"epoch": 2.1546582804515078,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045426226826272213,
|
|
"loss": 5.3009,
|
|
"mean_token_accuracy": 0.190846186876297,
|
|
"num_tokens": 42816718.0,
|
|
"step": 19185
|
|
},
|
|
{
|
|
"entropy": 5.569717836380005,
|
|
"epoch": 2.1552198573594654,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004542380016495607,
|
|
"loss": 5.2637,
|
|
"mean_token_accuracy": 0.19321095794439316,
|
|
"num_tokens": 42830183.0,
|
|
"step": 19190
|
|
},
|
|
{
|
|
"entropy": 5.463938808441162,
|
|
"epoch": 2.155781434267423,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045421372932939177,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.19771068543195724,
|
|
"num_tokens": 42841241.0,
|
|
"step": 19195
|
|
},
|
|
{
|
|
"entropy": 5.6381090641021725,
|
|
"epoch": 2.1563430111753803,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004541894513029881,
|
|
"loss": 5.3395,
|
|
"mean_token_accuracy": 0.1875772923231125,
|
|
"num_tokens": 42852775.0,
|
|
"step": 19200
|
|
},
|
|
{
|
|
"entropy": 5.660023307800293,
|
|
"epoch": 2.156904588083338,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.00045416516757112286,
|
|
"loss": 5.4577,
|
|
"mean_token_accuracy": 0.18079446852207184,
|
|
"num_tokens": 42863947.0,
|
|
"step": 19205
|
|
},
|
|
{
|
|
"entropy": 5.459608554840088,
|
|
"epoch": 2.1574661649912956,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045414087813456925,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.19575498700141908,
|
|
"num_tokens": 42874794.0,
|
|
"step": 19210
|
|
},
|
|
{
|
|
"entropy": 5.533738899230957,
|
|
"epoch": 2.1580277418992533,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004541165829941006,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.19114741086959838,
|
|
"num_tokens": 42886038.0,
|
|
"step": 19215
|
|
},
|
|
{
|
|
"entropy": 5.511582946777343,
|
|
"epoch": 2.1585893188072105,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004540922821504904,
|
|
"loss": 5.279,
|
|
"mean_token_accuracy": 0.1903168573975563,
|
|
"num_tokens": 42897243.0,
|
|
"step": 19220
|
|
},
|
|
{
|
|
"entropy": 5.490894365310669,
|
|
"epoch": 2.159150895715168,
|
|
"grad_norm": 1.9609375,
|
|
"learning_rate": 0.0004540679756045125,
|
|
"loss": 5.1826,
|
|
"mean_token_accuracy": 0.19556958824396134,
|
|
"num_tokens": 42908802.0,
|
|
"step": 19225
|
|
},
|
|
{
|
|
"entropy": 5.600104951858521,
|
|
"epoch": 2.159712472623126,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004540436633569407,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.18784704953432083,
|
|
"num_tokens": 42921156.0,
|
|
"step": 19230
|
|
},
|
|
{
|
|
"entropy": 5.43752384185791,
|
|
"epoch": 2.1602740495310835,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045401934540854937,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.19973911195993424,
|
|
"num_tokens": 42931336.0,
|
|
"step": 19235
|
|
},
|
|
{
|
|
"entropy": 5.489972400665283,
|
|
"epoch": 2.1608356264390407,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004539950217601127,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.19738709032535554,
|
|
"num_tokens": 42942312.0,
|
|
"step": 19240
|
|
},
|
|
{
|
|
"entropy": 5.499950790405274,
|
|
"epoch": 2.1613972033469984,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00045397069241240497,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.1949955254793167,
|
|
"num_tokens": 42953429.0,
|
|
"step": 19245
|
|
},
|
|
{
|
|
"entropy": 5.496206569671631,
|
|
"epoch": 2.161958780254956,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000453946357366201,
|
|
"loss": 5.1666,
|
|
"mean_token_accuracy": 0.19721957445144653,
|
|
"num_tokens": 42963354.0,
|
|
"step": 19250
|
|
},
|
|
{
|
|
"entropy": 5.586715173721314,
|
|
"epoch": 2.1625203571629132,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045392201662227565,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.19171375334262847,
|
|
"num_tokens": 42974643.0,
|
|
"step": 19255
|
|
},
|
|
{
|
|
"entropy": 5.5110002040863035,
|
|
"epoch": 2.163081934070871,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00045389767018140395,
|
|
"loss": 5.3123,
|
|
"mean_token_accuracy": 0.1921856164932251,
|
|
"num_tokens": 42985821.0,
|
|
"step": 19260
|
|
},
|
|
{
|
|
"entropy": 5.607332754135132,
|
|
"epoch": 2.1636435109788286,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045387331804436096,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.18711835592985154,
|
|
"num_tokens": 42998258.0,
|
|
"step": 19265
|
|
},
|
|
{
|
|
"entropy": 5.514812088012695,
|
|
"epoch": 2.1642050878867862,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004538489602119222,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.1955517679452896,
|
|
"num_tokens": 43009117.0,
|
|
"step": 19270
|
|
},
|
|
{
|
|
"entropy": 5.4097008228302,
|
|
"epoch": 2.1647666647947434,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004538245966848632,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.1948957175016403,
|
|
"num_tokens": 43020437.0,
|
|
"step": 19275
|
|
},
|
|
{
|
|
"entropy": 5.503125238418579,
|
|
"epoch": 2.165328241702701,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045380022746395953,
|
|
"loss": 5.3003,
|
|
"mean_token_accuracy": 0.1911396414041519,
|
|
"num_tokens": 43031722.0,
|
|
"step": 19280
|
|
},
|
|
{
|
|
"entropy": 5.509203100204468,
|
|
"epoch": 2.1658898186106588,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045377585254998743,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.20103756636381148,
|
|
"num_tokens": 43042957.0,
|
|
"step": 19285
|
|
},
|
|
{
|
|
"entropy": 5.470944452285766,
|
|
"epoch": 2.1664513955186164,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004537514719437228,
|
|
"loss": 5.2944,
|
|
"mean_token_accuracy": 0.19165925234556197,
|
|
"num_tokens": 43054086.0,
|
|
"step": 19290
|
|
},
|
|
{
|
|
"entropy": 5.583723497390747,
|
|
"epoch": 2.1670129724265736,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045372708564594196,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.18191485852003098,
|
|
"num_tokens": 43066259.0,
|
|
"step": 19295
|
|
},
|
|
{
|
|
"entropy": 5.432868719100952,
|
|
"epoch": 2.1675745493345313,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045370269365742143,
|
|
"loss": 5.1016,
|
|
"mean_token_accuracy": 0.20136747658252716,
|
|
"num_tokens": 43076837.0,
|
|
"step": 19300
|
|
},
|
|
{
|
|
"entropy": 5.442494010925293,
|
|
"epoch": 2.168136126242489,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045367829597893776,
|
|
"loss": 5.1727,
|
|
"mean_token_accuracy": 0.1988733783364296,
|
|
"num_tokens": 43087802.0,
|
|
"step": 19305
|
|
},
|
|
{
|
|
"entropy": 5.486414289474487,
|
|
"epoch": 2.1686977031504466,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045365389261126793,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.19589099287986755,
|
|
"num_tokens": 43097562.0,
|
|
"step": 19310
|
|
},
|
|
{
|
|
"entropy": 5.418877029418946,
|
|
"epoch": 2.169259280058404,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045362948355518883,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.19900362491607665,
|
|
"num_tokens": 43107973.0,
|
|
"step": 19315
|
|
},
|
|
{
|
|
"entropy": 5.440433740615845,
|
|
"epoch": 2.1698208569663615,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004536050688114777,
|
|
"loss": 5.1474,
|
|
"mean_token_accuracy": 0.20337087213993071,
|
|
"num_tokens": 43118923.0,
|
|
"step": 19320
|
|
},
|
|
{
|
|
"entropy": 5.461760520935059,
|
|
"epoch": 2.170382433874319,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045358064838091187,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.1974421501159668,
|
|
"num_tokens": 43130904.0,
|
|
"step": 19325
|
|
},
|
|
{
|
|
"entropy": 5.497675275802612,
|
|
"epoch": 2.170944010782277,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045355622226426903,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.19141136705875397,
|
|
"num_tokens": 43142293.0,
|
|
"step": 19330
|
|
},
|
|
{
|
|
"entropy": 5.531115007400513,
|
|
"epoch": 2.171505587690234,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00045353179046232674,
|
|
"loss": 5.2829,
|
|
"mean_token_accuracy": 0.20002973824739456,
|
|
"num_tokens": 43154340.0,
|
|
"step": 19335
|
|
},
|
|
{
|
|
"entropy": 5.520700836181641,
|
|
"epoch": 2.1720671645981917,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000453507352975863,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.19967207610607146,
|
|
"num_tokens": 43165924.0,
|
|
"step": 19340
|
|
},
|
|
{
|
|
"entropy": 5.470547342300415,
|
|
"epoch": 2.1726287415061494,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00045348290980565595,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.19395306706428528,
|
|
"num_tokens": 43177394.0,
|
|
"step": 19345
|
|
},
|
|
{
|
|
"entropy": 5.513988780975342,
|
|
"epoch": 2.1731903184141066,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045345846095248376,
|
|
"loss": 5.1899,
|
|
"mean_token_accuracy": 0.19490053206682206,
|
|
"num_tokens": 43188043.0,
|
|
"step": 19350
|
|
},
|
|
{
|
|
"entropy": 5.550333547592163,
|
|
"epoch": 2.1737518953220643,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045343400641712503,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.18655454069375993,
|
|
"num_tokens": 43199466.0,
|
|
"step": 19355
|
|
},
|
|
{
|
|
"entropy": 5.431333065032959,
|
|
"epoch": 2.174313472230022,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045340954620035827,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19705199748277663,
|
|
"num_tokens": 43210673.0,
|
|
"step": 19360
|
|
},
|
|
{
|
|
"entropy": 5.45861554145813,
|
|
"epoch": 2.1748750491379796,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00045338508030296246,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.18874214887619017,
|
|
"num_tokens": 43221263.0,
|
|
"step": 19365
|
|
},
|
|
{
|
|
"entropy": 5.535444211959839,
|
|
"epoch": 2.175436626045937,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00045336060872571646,
|
|
"loss": 5.3007,
|
|
"mean_token_accuracy": 0.19756841361522676,
|
|
"num_tokens": 43232590.0,
|
|
"step": 19370
|
|
},
|
|
{
|
|
"entropy": 5.618987369537353,
|
|
"epoch": 2.1759982029538945,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004533361314693994,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.19326794147491455,
|
|
"num_tokens": 43243693.0,
|
|
"step": 19375
|
|
},
|
|
{
|
|
"entropy": 5.516409158706665,
|
|
"epoch": 2.176559779861852,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045331164853479084,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.19515128880739213,
|
|
"num_tokens": 43254526.0,
|
|
"step": 19380
|
|
},
|
|
{
|
|
"entropy": 5.606832695007324,
|
|
"epoch": 2.17712135676981,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00045328715992267024,
|
|
"loss": 5.3047,
|
|
"mean_token_accuracy": 0.1921565815806389,
|
|
"num_tokens": 43264490.0,
|
|
"step": 19385
|
|
},
|
|
{
|
|
"entropy": 5.521264505386353,
|
|
"epoch": 2.177682933677767,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00045326266563381734,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.19472699761390685,
|
|
"num_tokens": 43275012.0,
|
|
"step": 19390
|
|
},
|
|
{
|
|
"entropy": 5.489199495315551,
|
|
"epoch": 2.1782445105857247,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045323816566901205,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.20028526932001114,
|
|
"num_tokens": 43285194.0,
|
|
"step": 19395
|
|
},
|
|
{
|
|
"entropy": 5.509725761413574,
|
|
"epoch": 2.1788060874936823,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004532136600290343,
|
|
"loss": 5.306,
|
|
"mean_token_accuracy": 0.1950877621769905,
|
|
"num_tokens": 43298159.0,
|
|
"step": 19400
|
|
},
|
|
{
|
|
"entropy": 5.560087728500366,
|
|
"epoch": 2.17936766440164,
|
|
"grad_norm": 2.15625,
|
|
"learning_rate": 0.0004531891487146646,
|
|
"loss": 5.3359,
|
|
"mean_token_accuracy": 0.18851345926523208,
|
|
"num_tokens": 43309664.0,
|
|
"step": 19405
|
|
},
|
|
{
|
|
"entropy": 5.526108598709106,
|
|
"epoch": 2.179929241309597,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004531646317266833,
|
|
"loss": 5.291,
|
|
"mean_token_accuracy": 0.18711543083190918,
|
|
"num_tokens": 43320399.0,
|
|
"step": 19410
|
|
},
|
|
{
|
|
"entropy": 5.47673397064209,
|
|
"epoch": 2.180490818217555,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045314010906587096,
|
|
"loss": 5.1047,
|
|
"mean_token_accuracy": 0.19840316623449325,
|
|
"num_tokens": 43331510.0,
|
|
"step": 19415
|
|
},
|
|
{
|
|
"entropy": 5.575441932678222,
|
|
"epoch": 2.1810523951255125,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00045311558073300853,
|
|
"loss": 5.3461,
|
|
"mean_token_accuracy": 0.193733911216259,
|
|
"num_tokens": 43342844.0,
|
|
"step": 19420
|
|
},
|
|
{
|
|
"entropy": 5.428063011169433,
|
|
"epoch": 2.18161397203347,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004530910467288769,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.1935359552502632,
|
|
"num_tokens": 43352556.0,
|
|
"step": 19425
|
|
},
|
|
{
|
|
"entropy": 5.471925878524781,
|
|
"epoch": 2.1821755489414274,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045306650705425727,
|
|
"loss": 5.1764,
|
|
"mean_token_accuracy": 0.19876355677843094,
|
|
"num_tokens": 43363357.0,
|
|
"step": 19430
|
|
},
|
|
{
|
|
"entropy": 5.593633699417114,
|
|
"epoch": 2.182737125849385,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045304196170993093,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.19072336107492446,
|
|
"num_tokens": 43374697.0,
|
|
"step": 19435
|
|
},
|
|
{
|
|
"entropy": 5.5405669689178465,
|
|
"epoch": 2.1832987027573427,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004530174106966795,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.18887477964162827,
|
|
"num_tokens": 43386826.0,
|
|
"step": 19440
|
|
},
|
|
{
|
|
"entropy": 5.496645164489746,
|
|
"epoch": 2.1838602796653,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045299285401528475,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.1911118134856224,
|
|
"num_tokens": 43398352.0,
|
|
"step": 19445
|
|
},
|
|
{
|
|
"entropy": 5.566546201705933,
|
|
"epoch": 2.1844218565732576,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004529682916665285,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19878541976213454,
|
|
"num_tokens": 43409509.0,
|
|
"step": 19450
|
|
},
|
|
{
|
|
"entropy": 5.418567562103272,
|
|
"epoch": 2.1849834334812153,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00045294372365119276,
|
|
"loss": 5.1977,
|
|
"mean_token_accuracy": 0.19314952045679093,
|
|
"num_tokens": 43420195.0,
|
|
"step": 19455
|
|
},
|
|
{
|
|
"entropy": 5.5031538009643555,
|
|
"epoch": 2.185545010389173,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004529191499700598,
|
|
"loss": 5.2968,
|
|
"mean_token_accuracy": 0.19530758559703826,
|
|
"num_tokens": 43430599.0,
|
|
"step": 19460
|
|
},
|
|
{
|
|
"entropy": 5.454104900360107,
|
|
"epoch": 2.18610658729713,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004528945706239122,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.19396157264709474,
|
|
"num_tokens": 43442212.0,
|
|
"step": 19465
|
|
},
|
|
{
|
|
"entropy": 5.438224935531617,
|
|
"epoch": 2.186668164205088,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045286998561353236,
|
|
"loss": 5.1951,
|
|
"mean_token_accuracy": 0.19524122923612594,
|
|
"num_tokens": 43452631.0,
|
|
"step": 19470
|
|
},
|
|
{
|
|
"entropy": 5.497567462921142,
|
|
"epoch": 2.1872297411130455,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004528453949397033,
|
|
"loss": 5.2396,
|
|
"mean_token_accuracy": 0.19558241665363313,
|
|
"num_tokens": 43463323.0,
|
|
"step": 19475
|
|
},
|
|
{
|
|
"entropy": 5.4938756942749025,
|
|
"epoch": 2.187791318021003,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045282079860320786,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.18554661870002748,
|
|
"num_tokens": 43474451.0,
|
|
"step": 19480
|
|
},
|
|
{
|
|
"entropy": 5.474974775314331,
|
|
"epoch": 2.1883528949289603,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00045279619660482925,
|
|
"loss": 5.1535,
|
|
"mean_token_accuracy": 0.19738832861185074,
|
|
"num_tokens": 43485948.0,
|
|
"step": 19485
|
|
},
|
|
{
|
|
"entropy": 5.556434488296508,
|
|
"epoch": 2.188914471836918,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045277158894535075,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.19789569675922394,
|
|
"num_tokens": 43498955.0,
|
|
"step": 19490
|
|
},
|
|
{
|
|
"entropy": 5.523875617980957,
|
|
"epoch": 2.1894760487448757,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045274697562555584,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.20008499473333358,
|
|
"num_tokens": 43509416.0,
|
|
"step": 19495
|
|
},
|
|
{
|
|
"entropy": 5.497178459167481,
|
|
"epoch": 2.1900376256528333,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004527223566462284,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.19794540256261825,
|
|
"num_tokens": 43520387.0,
|
|
"step": 19500
|
|
},
|
|
{
|
|
"entropy": 5.439568519592285,
|
|
"epoch": 2.1905992025607905,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004526977320081522,
|
|
"loss": 5.2522,
|
|
"mean_token_accuracy": 0.19643547534942626,
|
|
"num_tokens": 43532006.0,
|
|
"step": 19505
|
|
},
|
|
{
|
|
"entropy": 5.453122282028199,
|
|
"epoch": 2.191160779468748,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004526731017121111,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.19948485642671585,
|
|
"num_tokens": 43542303.0,
|
|
"step": 19510
|
|
},
|
|
{
|
|
"entropy": 5.568586301803589,
|
|
"epoch": 2.191722356376706,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00045264846575888973,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.1867700070142746,
|
|
"num_tokens": 43553711.0,
|
|
"step": 19515
|
|
},
|
|
{
|
|
"entropy": 5.445711946487426,
|
|
"epoch": 2.1922839332846635,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00045262382414927235,
|
|
"loss": 5.1976,
|
|
"mean_token_accuracy": 0.19183768779039384,
|
|
"num_tokens": 43564488.0,
|
|
"step": 19520
|
|
},
|
|
{
|
|
"entropy": 5.499575853347778,
|
|
"epoch": 2.1928455101926208,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00045259917688404336,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.19436590522527694,
|
|
"num_tokens": 43575414.0,
|
|
"step": 19525
|
|
},
|
|
{
|
|
"entropy": 5.4387829303741455,
|
|
"epoch": 2.1934070871005784,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004525745239639877,
|
|
"loss": 5.1906,
|
|
"mean_token_accuracy": 0.19729645997285844,
|
|
"num_tokens": 43586789.0,
|
|
"step": 19530
|
|
},
|
|
{
|
|
"entropy": 5.473733568191529,
|
|
"epoch": 2.193968664008536,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045254986538989045,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.20643625855445863,
|
|
"num_tokens": 43597423.0,
|
|
"step": 19535
|
|
},
|
|
{
|
|
"entropy": 5.497912168502808,
|
|
"epoch": 2.1945302409164933,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004525252011625366,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.1951088696718216,
|
|
"num_tokens": 43606703.0,
|
|
"step": 19540
|
|
},
|
|
{
|
|
"entropy": 5.543766975402832,
|
|
"epoch": 2.195091817824451,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004525005312827114,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.1938612475991249,
|
|
"num_tokens": 43617869.0,
|
|
"step": 19545
|
|
},
|
|
{
|
|
"entropy": 5.615937232971191,
|
|
"epoch": 2.1956533947324086,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004524758557512005,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.19136435389518738,
|
|
"num_tokens": 43629102.0,
|
|
"step": 19550
|
|
},
|
|
{
|
|
"entropy": 5.539566469192505,
|
|
"epoch": 2.1962149716403663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004524511745687895,
|
|
"loss": 5.2913,
|
|
"mean_token_accuracy": 0.19395723044872284,
|
|
"num_tokens": 43640421.0,
|
|
"step": 19555
|
|
},
|
|
{
|
|
"entropy": 5.493241024017334,
|
|
"epoch": 2.1967765485483235,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004524264877362643,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.19754767119884492,
|
|
"num_tokens": 43650516.0,
|
|
"step": 19560
|
|
},
|
|
{
|
|
"entropy": 5.4920916080474855,
|
|
"epoch": 2.197338125456281,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045240179525441094,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.2046605795621872,
|
|
"num_tokens": 43661439.0,
|
|
"step": 19565
|
|
},
|
|
{
|
|
"entropy": 5.506431341171265,
|
|
"epoch": 2.197899702364239,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004523770971240156,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.1933336928486824,
|
|
"num_tokens": 43672137.0,
|
|
"step": 19570
|
|
},
|
|
{
|
|
"entropy": 5.5327348709106445,
|
|
"epoch": 2.1984612792721965,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004523523933458647,
|
|
"loss": 5.2817,
|
|
"mean_token_accuracy": 0.18862942159175872,
|
|
"num_tokens": 43683612.0,
|
|
"step": 19575
|
|
},
|
|
{
|
|
"entropy": 5.478109550476074,
|
|
"epoch": 2.1990228561801537,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004523276839207448,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.19586929827928543,
|
|
"num_tokens": 43694331.0,
|
|
"step": 19580
|
|
},
|
|
{
|
|
"entropy": 5.5471395492553714,
|
|
"epoch": 2.1995844330881114,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045230296884944264,
|
|
"loss": 5.338,
|
|
"mean_token_accuracy": 0.19031967967748642,
|
|
"num_tokens": 43706572.0,
|
|
"step": 19585
|
|
},
|
|
{
|
|
"entropy": 5.450369071960449,
|
|
"epoch": 2.200146009996069,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045227824813274517,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.20296715050935746,
|
|
"num_tokens": 43718472.0,
|
|
"step": 19590
|
|
},
|
|
{
|
|
"entropy": 5.494547653198242,
|
|
"epoch": 2.2007075869040267,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004522535217714396,
|
|
"loss": 5.3067,
|
|
"mean_token_accuracy": 0.19363166391849518,
|
|
"num_tokens": 43729642.0,
|
|
"step": 19595
|
|
},
|
|
{
|
|
"entropy": 5.520801830291748,
|
|
"epoch": 2.201269163811984,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004522287897663131,
|
|
"loss": 5.304,
|
|
"mean_token_accuracy": 0.1923475444316864,
|
|
"num_tokens": 43739846.0,
|
|
"step": 19600
|
|
},
|
|
{
|
|
"entropy": 5.466316080093383,
|
|
"epoch": 2.2018307407199416,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045220405211815327,
|
|
"loss": 5.1382,
|
|
"mean_token_accuracy": 0.1978936329483986,
|
|
"num_tokens": 43750265.0,
|
|
"step": 19605
|
|
},
|
|
{
|
|
"entropy": 5.513313579559326,
|
|
"epoch": 2.202392317627899,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045217930882774754,
|
|
"loss": 5.2471,
|
|
"mean_token_accuracy": 0.19193320870399475,
|
|
"num_tokens": 43761245.0,
|
|
"step": 19610
|
|
},
|
|
{
|
|
"entropy": 5.529033565521241,
|
|
"epoch": 2.202953894535857,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045215455989588396,
|
|
"loss": 5.271,
|
|
"mean_token_accuracy": 0.19590318202972412,
|
|
"num_tokens": 43772677.0,
|
|
"step": 19615
|
|
},
|
|
{
|
|
"entropy": 5.501026296615601,
|
|
"epoch": 2.203515471443814,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045212980532335055,
|
|
"loss": 5.3188,
|
|
"mean_token_accuracy": 0.19151580184698105,
|
|
"num_tokens": 43783128.0,
|
|
"step": 19620
|
|
},
|
|
{
|
|
"entropy": 5.482798004150391,
|
|
"epoch": 2.2040770483517718,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00045210504511093534,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.1953653186559677,
|
|
"num_tokens": 43795323.0,
|
|
"step": 19625
|
|
},
|
|
{
|
|
"entropy": 5.612522077560425,
|
|
"epoch": 2.2046386252597294,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004520802792594269,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.19093612134456633,
|
|
"num_tokens": 43806917.0,
|
|
"step": 19630
|
|
},
|
|
{
|
|
"entropy": 5.631438159942627,
|
|
"epoch": 2.2052002021676866,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045205550776961366,
|
|
"loss": 5.3323,
|
|
"mean_token_accuracy": 0.19230648130178452,
|
|
"num_tokens": 43818963.0,
|
|
"step": 19635
|
|
},
|
|
{
|
|
"entropy": 5.444922590255738,
|
|
"epoch": 2.2057617790756443,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004520307306422844,
|
|
"loss": 5.1856,
|
|
"mean_token_accuracy": 0.19695780724287032,
|
|
"num_tokens": 43830163.0,
|
|
"step": 19640
|
|
},
|
|
{
|
|
"entropy": 5.444924974441529,
|
|
"epoch": 2.206323355983602,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045200594787822795,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.2006937876343727,
|
|
"num_tokens": 43840434.0,
|
|
"step": 19645
|
|
},
|
|
{
|
|
"entropy": 5.400426721572876,
|
|
"epoch": 2.2068849328915596,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004519811594782335,
|
|
"loss": 5.0625,
|
|
"mean_token_accuracy": 0.20271401554346086,
|
|
"num_tokens": 43851086.0,
|
|
"step": 19650
|
|
},
|
|
{
|
|
"entropy": 5.4808117866516115,
|
|
"epoch": 2.207446509799517,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045195636544309033,
|
|
"loss": 5.2869,
|
|
"mean_token_accuracy": 0.18854305744171143,
|
|
"num_tokens": 43862834.0,
|
|
"step": 19655
|
|
},
|
|
{
|
|
"entropy": 5.4795389652252195,
|
|
"epoch": 2.2080080867074745,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00045193156577358784,
|
|
"loss": 5.2768,
|
|
"mean_token_accuracy": 0.1896281659603119,
|
|
"num_tokens": 43874868.0,
|
|
"step": 19660
|
|
},
|
|
{
|
|
"entropy": 5.545945501327514,
|
|
"epoch": 2.208569663615432,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004519067604705157,
|
|
"loss": 5.2603,
|
|
"mean_token_accuracy": 0.19784044474363327,
|
|
"num_tokens": 43886175.0,
|
|
"step": 19665
|
|
},
|
|
{
|
|
"entropy": 5.464400672912598,
|
|
"epoch": 2.20913124052339,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045188194953466363,
|
|
"loss": 5.2178,
|
|
"mean_token_accuracy": 0.20125861167907716,
|
|
"num_tokens": 43896489.0,
|
|
"step": 19670
|
|
},
|
|
{
|
|
"entropy": 5.478315114974976,
|
|
"epoch": 2.209692817431347,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045185713296682175,
|
|
"loss": 5.2217,
|
|
"mean_token_accuracy": 0.19694866389036178,
|
|
"num_tokens": 43907759.0,
|
|
"step": 19675
|
|
},
|
|
{
|
|
"entropy": 5.508592987060547,
|
|
"epoch": 2.2102543943393047,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045183231076778005,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.19697954803705214,
|
|
"num_tokens": 43918136.0,
|
|
"step": 19680
|
|
},
|
|
{
|
|
"entropy": 5.504892492294312,
|
|
"epoch": 2.2108159712472624,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045180748293832906,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.18995241522789003,
|
|
"num_tokens": 43929662.0,
|
|
"step": 19685
|
|
},
|
|
{
|
|
"entropy": 5.459499263763428,
|
|
"epoch": 2.21137754815522,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045178264947925924,
|
|
"loss": 5.2449,
|
|
"mean_token_accuracy": 0.20057935416698455,
|
|
"num_tokens": 43939599.0,
|
|
"step": 19690
|
|
},
|
|
{
|
|
"entropy": 5.453392839431762,
|
|
"epoch": 2.2119391250631772,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00045175781039136133,
|
|
"loss": 5.2072,
|
|
"mean_token_accuracy": 0.19645652770996094,
|
|
"num_tokens": 43949728.0,
|
|
"step": 19695
|
|
},
|
|
{
|
|
"entropy": 5.569979476928711,
|
|
"epoch": 2.212500701971135,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004517329656754261,
|
|
"loss": 5.3143,
|
|
"mean_token_accuracy": 0.19562138468027115,
|
|
"num_tokens": 43961147.0,
|
|
"step": 19700
|
|
},
|
|
{
|
|
"entropy": 5.578468751907349,
|
|
"epoch": 2.2130622788790926,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004517081153322448,
|
|
"loss": 5.285,
|
|
"mean_token_accuracy": 0.1989368364214897,
|
|
"num_tokens": 43972541.0,
|
|
"step": 19705
|
|
},
|
|
{
|
|
"entropy": 5.477407646179199,
|
|
"epoch": 2.2136238557870502,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004516832593626085,
|
|
"loss": 5.3055,
|
|
"mean_token_accuracy": 0.19043268263339996,
|
|
"num_tokens": 43983540.0,
|
|
"step": 19710
|
|
},
|
|
{
|
|
"entropy": 5.493157863616943,
|
|
"epoch": 2.2141854326950074,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004516583977673087,
|
|
"loss": 5.1905,
|
|
"mean_token_accuracy": 0.2007892370223999,
|
|
"num_tokens": 43994255.0,
|
|
"step": 19715
|
|
},
|
|
{
|
|
"entropy": 5.612482213973999,
|
|
"epoch": 2.214747009602965,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045163353054713704,
|
|
"loss": 5.3581,
|
|
"mean_token_accuracy": 0.19203052371740342,
|
|
"num_tokens": 44004364.0,
|
|
"step": 19720
|
|
},
|
|
{
|
|
"entropy": 5.520586633682251,
|
|
"epoch": 2.2153085865109228,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004516086577028852,
|
|
"loss": 5.3183,
|
|
"mean_token_accuracy": 0.19553358256816863,
|
|
"num_tokens": 44015487.0,
|
|
"step": 19725
|
|
},
|
|
{
|
|
"entropy": 5.600929594039917,
|
|
"epoch": 2.21587016341888,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004515837792353453,
|
|
"loss": 5.2945,
|
|
"mean_token_accuracy": 0.19795719683170318,
|
|
"num_tokens": 44026974.0,
|
|
"step": 19730
|
|
},
|
|
{
|
|
"entropy": 5.529708576202393,
|
|
"epoch": 2.2164317403268377,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004515588951453093,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.1935240089893341,
|
|
"num_tokens": 44038718.0,
|
|
"step": 19735
|
|
},
|
|
{
|
|
"entropy": 5.474417448043823,
|
|
"epoch": 2.2169933172347953,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004515340054335696,
|
|
"loss": 5.1741,
|
|
"mean_token_accuracy": 0.19929495602846145,
|
|
"num_tokens": 44048821.0,
|
|
"step": 19740
|
|
},
|
|
{
|
|
"entropy": 5.536909437179565,
|
|
"epoch": 2.217554894142753,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004515091101009188,
|
|
"loss": 5.3393,
|
|
"mean_token_accuracy": 0.186346372961998,
|
|
"num_tokens": 44060973.0,
|
|
"step": 19745
|
|
},
|
|
{
|
|
"entropy": 5.658418750762939,
|
|
"epoch": 2.21811647105071,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004514842091481493,
|
|
"loss": 5.3137,
|
|
"mean_token_accuracy": 0.19731849282979966,
|
|
"num_tokens": 44073595.0,
|
|
"step": 19750
|
|
},
|
|
{
|
|
"entropy": 5.421954584121704,
|
|
"epoch": 2.218678047958668,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004514593025760543,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1981503263115883,
|
|
"num_tokens": 44084860.0,
|
|
"step": 19755
|
|
},
|
|
{
|
|
"entropy": 5.483652496337891,
|
|
"epoch": 2.2192396248666255,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045143439038542653,
|
|
"loss": 5.3131,
|
|
"mean_token_accuracy": 0.18987174481153488,
|
|
"num_tokens": 44096026.0,
|
|
"step": 19760
|
|
},
|
|
{
|
|
"entropy": 5.554149341583252,
|
|
"epoch": 2.219801201774583,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004514094725770594,
|
|
"loss": 5.2527,
|
|
"mean_token_accuracy": 0.19425288885831832,
|
|
"num_tokens": 44107981.0,
|
|
"step": 19765
|
|
},
|
|
{
|
|
"entropy": 5.491306591033935,
|
|
"epoch": 2.2203627786825404,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00045138454915174625,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19135937690734864,
|
|
"num_tokens": 44119589.0,
|
|
"step": 19770
|
|
},
|
|
{
|
|
"entropy": 5.479271078109742,
|
|
"epoch": 2.220924355590498,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00045135962011028064,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.19367558062076567,
|
|
"num_tokens": 44131094.0,
|
|
"step": 19775
|
|
},
|
|
{
|
|
"entropy": 5.553167009353638,
|
|
"epoch": 2.2214859324984557,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004513346854534564,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.1923410639166832,
|
|
"num_tokens": 44141348.0,
|
|
"step": 19780
|
|
},
|
|
{
|
|
"entropy": 5.605989551544189,
|
|
"epoch": 2.2220475094064134,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004513097451820673,
|
|
"loss": 5.3945,
|
|
"mean_token_accuracy": 0.191645248234272,
|
|
"num_tokens": 44152085.0,
|
|
"step": 19785
|
|
},
|
|
{
|
|
"entropy": 5.468550777435302,
|
|
"epoch": 2.2226090863143706,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045128479929690756,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.20539649724960327,
|
|
"num_tokens": 44163518.0,
|
|
"step": 19790
|
|
},
|
|
{
|
|
"entropy": 5.4756872177124025,
|
|
"epoch": 2.2231706632223283,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004512598477987714,
|
|
"loss": 5.2352,
|
|
"mean_token_accuracy": 0.19212053567171097,
|
|
"num_tokens": 44175513.0,
|
|
"step": 19795
|
|
},
|
|
{
|
|
"entropy": 5.556610012054444,
|
|
"epoch": 2.223732240130286,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045123489068845334,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19452006071805955,
|
|
"num_tokens": 44186660.0,
|
|
"step": 19800
|
|
},
|
|
{
|
|
"entropy": 5.523863983154297,
|
|
"epoch": 2.2242938170382436,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045120992796674804,
|
|
"loss": 5.3179,
|
|
"mean_token_accuracy": 0.19211677610874175,
|
|
"num_tokens": 44197613.0,
|
|
"step": 19805
|
|
},
|
|
{
|
|
"entropy": 5.469563293457031,
|
|
"epoch": 2.224855393946201,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004511849596344503,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.1884819582104683,
|
|
"num_tokens": 44209469.0,
|
|
"step": 19810
|
|
},
|
|
{
|
|
"entropy": 5.521347236633301,
|
|
"epoch": 2.2254169708541585,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00045115998569235507,
|
|
"loss": 5.2462,
|
|
"mean_token_accuracy": 0.19255650341510772,
|
|
"num_tokens": 44220672.0,
|
|
"step": 19815
|
|
},
|
|
{
|
|
"entropy": 5.51177487373352,
|
|
"epoch": 2.225978547762116,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045113500614125756,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.18700440376996993,
|
|
"num_tokens": 44232867.0,
|
|
"step": 19820
|
|
},
|
|
{
|
|
"entropy": 5.5368400573730465,
|
|
"epoch": 2.2265401246700733,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004511100209819532,
|
|
"loss": 5.2794,
|
|
"mean_token_accuracy": 0.1937655508518219,
|
|
"num_tokens": 44245567.0,
|
|
"step": 19825
|
|
},
|
|
{
|
|
"entropy": 5.514059114456177,
|
|
"epoch": 2.227101701578031,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00045108503021523737,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.19872262477874755,
|
|
"num_tokens": 44257449.0,
|
|
"step": 19830
|
|
},
|
|
{
|
|
"entropy": 5.500395727157593,
|
|
"epoch": 2.2276632784859887,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00045106003384190604,
|
|
"loss": 5.3076,
|
|
"mean_token_accuracy": 0.19075843393802644,
|
|
"num_tokens": 44268890.0,
|
|
"step": 19835
|
|
},
|
|
{
|
|
"entropy": 5.597168016433716,
|
|
"epoch": 2.2282248553939463,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045103503186275486,
|
|
"loss": 5.2856,
|
|
"mean_token_accuracy": 0.18729943931102752,
|
|
"num_tokens": 44280719.0,
|
|
"step": 19840
|
|
},
|
|
{
|
|
"entropy": 5.598517942428589,
|
|
"epoch": 2.2287864323019035,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00045101002427857997,
|
|
"loss": 5.3654,
|
|
"mean_token_accuracy": 0.1855131983757019,
|
|
"num_tokens": 44292567.0,
|
|
"step": 19845
|
|
},
|
|
{
|
|
"entropy": 5.501662683486939,
|
|
"epoch": 2.229348009209861,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00045098501109017765,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.18550007045269012,
|
|
"num_tokens": 44304177.0,
|
|
"step": 19850
|
|
},
|
|
{
|
|
"entropy": 5.486387729644775,
|
|
"epoch": 2.229909586117819,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00045095999229834437,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19794696867465972,
|
|
"num_tokens": 44315142.0,
|
|
"step": 19855
|
|
},
|
|
{
|
|
"entropy": 5.513644456863403,
|
|
"epoch": 2.2304711630257765,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004509349679038767,
|
|
"loss": 5.3522,
|
|
"mean_token_accuracy": 0.19155416190624236,
|
|
"num_tokens": 44327457.0,
|
|
"step": 19860
|
|
},
|
|
{
|
|
"entropy": 5.602671957015991,
|
|
"epoch": 2.2310327399337337,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00045090993790757137,
|
|
"loss": 5.3391,
|
|
"mean_token_accuracy": 0.18533536344766616,
|
|
"num_tokens": 44338978.0,
|
|
"step": 19865
|
|
},
|
|
{
|
|
"entropy": 5.535648536682129,
|
|
"epoch": 2.2315943168416914,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004508849023102253,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.1953305646777153,
|
|
"num_tokens": 44349121.0,
|
|
"step": 19870
|
|
},
|
|
{
|
|
"entropy": 5.472658443450928,
|
|
"epoch": 2.232155893749649,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004508598611126359,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.19956895411014558,
|
|
"num_tokens": 44360753.0,
|
|
"step": 19875
|
|
},
|
|
{
|
|
"entropy": 5.579345989227295,
|
|
"epoch": 2.2327174706576067,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004508348143156002,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.19559334963560104,
|
|
"num_tokens": 44371977.0,
|
|
"step": 19880
|
|
},
|
|
{
|
|
"entropy": 5.482034635543823,
|
|
"epoch": 2.233279047565564,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045080976191991587,
|
|
"loss": 5.198,
|
|
"mean_token_accuracy": 0.19075107127428054,
|
|
"num_tokens": 44383077.0,
|
|
"step": 19885
|
|
},
|
|
{
|
|
"entropy": 5.477060174942016,
|
|
"epoch": 2.2338406244735216,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004507847039263805,
|
|
"loss": 5.225,
|
|
"mean_token_accuracy": 0.19522584825754166,
|
|
"num_tokens": 44394827.0,
|
|
"step": 19890
|
|
},
|
|
{
|
|
"entropy": 5.478492879867554,
|
|
"epoch": 2.2344022013814793,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.000450759640335792,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.1976567268371582,
|
|
"num_tokens": 44406594.0,
|
|
"step": 19895
|
|
},
|
|
{
|
|
"entropy": 5.430236291885376,
|
|
"epoch": 2.234963778289437,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004507345711489484,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.19809218794107436,
|
|
"num_tokens": 44417842.0,
|
|
"step": 19900
|
|
},
|
|
{
|
|
"entropy": 5.530806350708008,
|
|
"epoch": 2.235525355197394,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045070949636664785,
|
|
"loss": 5.2098,
|
|
"mean_token_accuracy": 0.19266771227121354,
|
|
"num_tokens": 44428234.0,
|
|
"step": 19905
|
|
},
|
|
{
|
|
"entropy": 5.418927717208862,
|
|
"epoch": 2.236086932105352,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004506844159896888,
|
|
"loss": 5.1774,
|
|
"mean_token_accuracy": 0.20012435913085938,
|
|
"num_tokens": 44437504.0,
|
|
"step": 19910
|
|
},
|
|
{
|
|
"entropy": 5.497668361663818,
|
|
"epoch": 2.2366485090133095,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004506593300188698,
|
|
"loss": 5.2381,
|
|
"mean_token_accuracy": 0.1999306857585907,
|
|
"num_tokens": 44447873.0,
|
|
"step": 19915
|
|
},
|
|
{
|
|
"entropy": 5.549439191818237,
|
|
"epoch": 2.2372100859212667,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004506342384549897,
|
|
"loss": 5.3308,
|
|
"mean_token_accuracy": 0.19824532568454742,
|
|
"num_tokens": 44458990.0,
|
|
"step": 19920
|
|
},
|
|
{
|
|
"entropy": 5.513254117965698,
|
|
"epoch": 2.2377716628292244,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004506091412988472,
|
|
"loss": 5.2055,
|
|
"mean_token_accuracy": 0.19924843013286592,
|
|
"num_tokens": 44469374.0,
|
|
"step": 19925
|
|
},
|
|
{
|
|
"entropy": 5.466969585418701,
|
|
"epoch": 2.238333239737182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045058403855124165,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.19920733720064163,
|
|
"num_tokens": 44479629.0,
|
|
"step": 19930
|
|
},
|
|
{
|
|
"entropy": 5.577469682693481,
|
|
"epoch": 2.2388948166451397,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004505589302129721,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.19169560819864273,
|
|
"num_tokens": 44490603.0,
|
|
"step": 19935
|
|
},
|
|
{
|
|
"entropy": 5.424192476272583,
|
|
"epoch": 2.239456393553097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004505338162848382,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.20130681097507477,
|
|
"num_tokens": 44501527.0,
|
|
"step": 19940
|
|
},
|
|
{
|
|
"entropy": 5.550575399398804,
|
|
"epoch": 2.2400179704610546,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004505086967676395,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.19086854159832,
|
|
"num_tokens": 44512619.0,
|
|
"step": 19945
|
|
},
|
|
{
|
|
"entropy": 5.661468076705932,
|
|
"epoch": 2.240579547369012,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004504835716621757,
|
|
"loss": 5.388,
|
|
"mean_token_accuracy": 0.1864039793610573,
|
|
"num_tokens": 44524639.0,
|
|
"step": 19950
|
|
},
|
|
{
|
|
"entropy": 5.491331100463867,
|
|
"epoch": 2.24114112427697,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004504584409692471,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.2038565456867218,
|
|
"num_tokens": 44535013.0,
|
|
"step": 19955
|
|
},
|
|
{
|
|
"entropy": 5.663964176177979,
|
|
"epoch": 2.241702701184927,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00045043330468965364,
|
|
"loss": 5.348,
|
|
"mean_token_accuracy": 0.1870020717382431,
|
|
"num_tokens": 44546838.0,
|
|
"step": 19960
|
|
},
|
|
{
|
|
"entropy": 5.497413158416748,
|
|
"epoch": 2.2422642780928848,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045040816282419566,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.19940431863069535,
|
|
"num_tokens": 44557984.0,
|
|
"step": 19965
|
|
},
|
|
{
|
|
"entropy": 5.453099775314331,
|
|
"epoch": 2.2428258550008424,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.00045038301537367374,
|
|
"loss": 5.203,
|
|
"mean_token_accuracy": 0.19811960011720658,
|
|
"num_tokens": 44569029.0,
|
|
"step": 19970
|
|
},
|
|
{
|
|
"entropy": 5.507169961929321,
|
|
"epoch": 2.2433874319088,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045035786233888864,
|
|
"loss": 5.2832,
|
|
"mean_token_accuracy": 0.19503084123134612,
|
|
"num_tokens": 44578804.0,
|
|
"step": 19975
|
|
},
|
|
{
|
|
"entropy": 5.526713752746582,
|
|
"epoch": 2.2439490088167573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045033270372064123,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.1958169534802437,
|
|
"num_tokens": 44589362.0,
|
|
"step": 19980
|
|
},
|
|
{
|
|
"entropy": 5.533536100387574,
|
|
"epoch": 2.244510585724715,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045030753951973243,
|
|
"loss": 5.2774,
|
|
"mean_token_accuracy": 0.19348324239253997,
|
|
"num_tokens": 44600137.0,
|
|
"step": 19985
|
|
},
|
|
{
|
|
"entropy": 5.55185112953186,
|
|
"epoch": 2.2450721626326726,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00045028236973696363,
|
|
"loss": 5.2583,
|
|
"mean_token_accuracy": 0.20266866236925124,
|
|
"num_tokens": 44611707.0,
|
|
"step": 19990
|
|
},
|
|
{
|
|
"entropy": 5.502388954162598,
|
|
"epoch": 2.2456337395406303,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004502571943731362,
|
|
"loss": 5.2339,
|
|
"mean_token_accuracy": 0.19850484430789947,
|
|
"num_tokens": 44621141.0,
|
|
"step": 19995
|
|
},
|
|
{
|
|
"entropy": 5.504114580154419,
|
|
"epoch": 2.2461953164485875,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004502320134290517,
|
|
"loss": 5.3209,
|
|
"mean_token_accuracy": 0.1940768763422966,
|
|
"num_tokens": 44632043.0,
|
|
"step": 20000
|
|
},
|
|
{
|
|
"entropy": 5.540633487701416,
|
|
"epoch": 2.246756893356545,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045020682690551203,
|
|
"loss": 5.3118,
|
|
"mean_token_accuracy": 0.19313785582780837,
|
|
"num_tokens": 44643905.0,
|
|
"step": 20005
|
|
},
|
|
{
|
|
"entropy": 5.4738945960998535,
|
|
"epoch": 2.247318470264503,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045018163480331887,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.18852509111166,
|
|
"num_tokens": 44655105.0,
|
|
"step": 20010
|
|
},
|
|
{
|
|
"entropy": 5.497313785552978,
|
|
"epoch": 2.24788004717246,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045015643712327465,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.19500139802694322,
|
|
"num_tokens": 44667096.0,
|
|
"step": 20015
|
|
},
|
|
{
|
|
"entropy": 5.54805006980896,
|
|
"epoch": 2.2484416240804177,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004501312338661815,
|
|
"loss": 5.2743,
|
|
"mean_token_accuracy": 0.19380559176206588,
|
|
"num_tokens": 44678206.0,
|
|
"step": 20020
|
|
},
|
|
{
|
|
"entropy": 5.4583539962768555,
|
|
"epoch": 2.2490032009883754,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004501060250328419,
|
|
"loss": 5.1799,
|
|
"mean_token_accuracy": 0.19859344512224197,
|
|
"num_tokens": 44688619.0,
|
|
"step": 20025
|
|
},
|
|
{
|
|
"entropy": 5.48807373046875,
|
|
"epoch": 2.249564777896333,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004500808106240586,
|
|
"loss": 5.2488,
|
|
"mean_token_accuracy": 0.18839554488658905,
|
|
"num_tokens": 44700757.0,
|
|
"step": 20030
|
|
},
|
|
{
|
|
"entropy": 5.388700866699219,
|
|
"epoch": 2.2501263548042907,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004500555906406343,
|
|
"loss": 5.1064,
|
|
"mean_token_accuracy": 0.2022954523563385,
|
|
"num_tokens": 44710822.0,
|
|
"step": 20035
|
|
},
|
|
{
|
|
"entropy": 5.3746583461761475,
|
|
"epoch": 2.250687931712248,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004500303650833722,
|
|
"loss": 5.1067,
|
|
"mean_token_accuracy": 0.2057414323091507,
|
|
"num_tokens": 44722163.0,
|
|
"step": 20040
|
|
},
|
|
{
|
|
"entropy": 5.597979307174683,
|
|
"epoch": 2.2512495086202056,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004500051339530754,
|
|
"loss": 5.3152,
|
|
"mean_token_accuracy": 0.1869124576449394,
|
|
"num_tokens": 44734271.0,
|
|
"step": 20045
|
|
},
|
|
{
|
|
"entropy": 5.584524726867675,
|
|
"epoch": 2.2518110855281632,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004499798972505472,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19652804732322693,
|
|
"num_tokens": 44745345.0,
|
|
"step": 20050
|
|
},
|
|
{
|
|
"entropy": 5.409156465530396,
|
|
"epoch": 2.2523726624361204,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044995465497659127,
|
|
"loss": 5.2485,
|
|
"mean_token_accuracy": 0.18872489780187607,
|
|
"num_tokens": 44756986.0,
|
|
"step": 20055
|
|
},
|
|
{
|
|
"entropy": 5.382010650634766,
|
|
"epoch": 2.252934239344078,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004499294071320112,
|
|
"loss": 5.165,
|
|
"mean_token_accuracy": 0.20011703968048095,
|
|
"num_tokens": 44767259.0,
|
|
"step": 20060
|
|
},
|
|
{
|
|
"entropy": 5.4575605392456055,
|
|
"epoch": 2.2534958162520358,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000449904153717611,
|
|
"loss": 5.2789,
|
|
"mean_token_accuracy": 0.1890398919582367,
|
|
"num_tokens": 44778884.0,
|
|
"step": 20065
|
|
},
|
|
{
|
|
"entropy": 5.5230919361114506,
|
|
"epoch": 2.2540573931599934,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004498788947341947,
|
|
"loss": 5.1643,
|
|
"mean_token_accuracy": 0.20161470174789428,
|
|
"num_tokens": 44789216.0,
|
|
"step": 20070
|
|
},
|
|
{
|
|
"entropy": 5.37495265007019,
|
|
"epoch": 2.2546189700679506,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004498536301825665,
|
|
"loss": 5.1311,
|
|
"mean_token_accuracy": 0.20338324159383775,
|
|
"num_tokens": 44799357.0,
|
|
"step": 20075
|
|
},
|
|
{
|
|
"entropy": 5.422207975387574,
|
|
"epoch": 2.2551805469759083,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000449828360063531,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.19773583561182023,
|
|
"num_tokens": 44811040.0,
|
|
"step": 20080
|
|
},
|
|
{
|
|
"entropy": 5.5648767948150635,
|
|
"epoch": 2.255742123883866,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044980308437789267,
|
|
"loss": 5.3372,
|
|
"mean_token_accuracy": 0.18334406316280366,
|
|
"num_tokens": 44822103.0,
|
|
"step": 20085
|
|
},
|
|
{
|
|
"entropy": 5.52035493850708,
|
|
"epoch": 2.2563037007918236,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004497778031264564,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19108399003744125,
|
|
"num_tokens": 44834712.0,
|
|
"step": 20090
|
|
},
|
|
{
|
|
"entropy": 5.503679275512695,
|
|
"epoch": 2.256865277699781,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044975251631002694,
|
|
"loss": 5.1815,
|
|
"mean_token_accuracy": 0.1932123377919197,
|
|
"num_tokens": 44845412.0,
|
|
"step": 20095
|
|
},
|
|
{
|
|
"entropy": 5.486463022232056,
|
|
"epoch": 2.2574268546077385,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004497272239294097,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.19525197446346282,
|
|
"num_tokens": 44857720.0,
|
|
"step": 20100
|
|
},
|
|
{
|
|
"entropy": 5.504539203643799,
|
|
"epoch": 2.257988431515696,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004497019259854099,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.2011688083410263,
|
|
"num_tokens": 44868253.0,
|
|
"step": 20105
|
|
},
|
|
{
|
|
"entropy": 5.4910304069519045,
|
|
"epoch": 2.2585500084236534,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044967662247883295,
|
|
"loss": 5.2025,
|
|
"mean_token_accuracy": 0.19663511961698532,
|
|
"num_tokens": 44878525.0,
|
|
"step": 20110
|
|
},
|
|
{
|
|
"entropy": 5.381030130386352,
|
|
"epoch": 2.259111585331611,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044965131341048454,
|
|
"loss": 5.1737,
|
|
"mean_token_accuracy": 0.20292484313249587,
|
|
"num_tokens": 44889565.0,
|
|
"step": 20115
|
|
},
|
|
{
|
|
"entropy": 5.427085018157959,
|
|
"epoch": 2.2596731622395687,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004496259987811707,
|
|
"loss": 5.169,
|
|
"mean_token_accuracy": 0.1964082732796669,
|
|
"num_tokens": 44901191.0,
|
|
"step": 20120
|
|
},
|
|
{
|
|
"entropy": 5.468226909637451,
|
|
"epoch": 2.2602347391475264,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004496006785916973,
|
|
"loss": 5.1456,
|
|
"mean_token_accuracy": 0.2060801774263382,
|
|
"num_tokens": 44911483.0,
|
|
"step": 20125
|
|
},
|
|
{
|
|
"entropy": 5.584434366226196,
|
|
"epoch": 2.260796316055484,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044957535284287055,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.19299978166818618,
|
|
"num_tokens": 44923537.0,
|
|
"step": 20130
|
|
},
|
|
{
|
|
"entropy": 5.585608673095703,
|
|
"epoch": 2.2613578929634413,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044955002153549686,
|
|
"loss": 5.2881,
|
|
"mean_token_accuracy": 0.18915970176458358,
|
|
"num_tokens": 44935780.0,
|
|
"step": 20135
|
|
},
|
|
{
|
|
"entropy": 5.510671806335449,
|
|
"epoch": 2.261919469871399,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004495246846703828,
|
|
"loss": 5.2708,
|
|
"mean_token_accuracy": 0.19299889504909515,
|
|
"num_tokens": 44946879.0,
|
|
"step": 20140
|
|
},
|
|
{
|
|
"entropy": 5.550481796264648,
|
|
"epoch": 2.2624810467793566,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00044949934224833505,
|
|
"loss": 5.257,
|
|
"mean_token_accuracy": 0.19787415415048598,
|
|
"num_tokens": 44958385.0,
|
|
"step": 20145
|
|
},
|
|
{
|
|
"entropy": 5.515612030029297,
|
|
"epoch": 2.263042623687314,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004494739942701606,
|
|
"loss": 5.3485,
|
|
"mean_token_accuracy": 0.18720245808362962,
|
|
"num_tokens": 44970597.0,
|
|
"step": 20150
|
|
},
|
|
{
|
|
"entropy": 5.513953971862793,
|
|
"epoch": 2.2636042005952715,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044944864073666655,
|
|
"loss": 5.2911,
|
|
"mean_token_accuracy": 0.1973385140299797,
|
|
"num_tokens": 44983123.0,
|
|
"step": 20155
|
|
},
|
|
{
|
|
"entropy": 5.505777597427368,
|
|
"epoch": 2.264165777503229,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044942328164866,
|
|
"loss": 5.1889,
|
|
"mean_token_accuracy": 0.19418008178472518,
|
|
"num_tokens": 44993378.0,
|
|
"step": 20160
|
|
},
|
|
{
|
|
"entropy": 5.462815570831299,
|
|
"epoch": 2.2647273544111868,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004493979170069486,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.18503458350896834,
|
|
"num_tokens": 45004905.0,
|
|
"step": 20165
|
|
},
|
|
{
|
|
"entropy": 5.407270193099976,
|
|
"epoch": 2.265288931319144,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044937254681233984,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.19390511363744736,
|
|
"num_tokens": 45016640.0,
|
|
"step": 20170
|
|
},
|
|
{
|
|
"entropy": 5.5511411190032955,
|
|
"epoch": 2.2658505082271017,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044934717106564164,
|
|
"loss": 5.3649,
|
|
"mean_token_accuracy": 0.18685738742351532,
|
|
"num_tokens": 45028285.0,
|
|
"step": 20175
|
|
},
|
|
{
|
|
"entropy": 5.59020767211914,
|
|
"epoch": 2.2664120851350593,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044932178976766183,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.1922583505511284,
|
|
"num_tokens": 45038924.0,
|
|
"step": 20180
|
|
},
|
|
{
|
|
"entropy": 5.509301805496216,
|
|
"epoch": 2.266973662043017,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044929640291920865,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.19345965087413788,
|
|
"num_tokens": 45050483.0,
|
|
"step": 20185
|
|
},
|
|
{
|
|
"entropy": 5.5611302852630615,
|
|
"epoch": 2.267535238950974,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004492710105210904,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.18559971451759338,
|
|
"num_tokens": 45063242.0,
|
|
"step": 20190
|
|
},
|
|
{
|
|
"entropy": 5.503766012191773,
|
|
"epoch": 2.268096815858932,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044924561257411554,
|
|
"loss": 5.2409,
|
|
"mean_token_accuracy": 0.19339527785778046,
|
|
"num_tokens": 45074057.0,
|
|
"step": 20195
|
|
},
|
|
{
|
|
"entropy": 5.460871076583862,
|
|
"epoch": 2.2686583927668895,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004492202090790928,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.1844407305121422,
|
|
"num_tokens": 45085488.0,
|
|
"step": 20200
|
|
},
|
|
{
|
|
"entropy": 5.586784029006958,
|
|
"epoch": 2.2692199696748467,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004491948000368311,
|
|
"loss": 5.3616,
|
|
"mean_token_accuracy": 0.1919145405292511,
|
|
"num_tokens": 45096303.0,
|
|
"step": 20205
|
|
},
|
|
{
|
|
"entropy": 5.561692619323731,
|
|
"epoch": 2.2697815465828044,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044916938544813936,
|
|
"loss": 5.1264,
|
|
"mean_token_accuracy": 0.19595620036125183,
|
|
"num_tokens": 45106411.0,
|
|
"step": 20210
|
|
},
|
|
{
|
|
"entropy": 5.456285095214843,
|
|
"epoch": 2.270343123490762,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00044914396531382686,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.1950817421078682,
|
|
"num_tokens": 45117355.0,
|
|
"step": 20215
|
|
},
|
|
{
|
|
"entropy": 5.454509449005127,
|
|
"epoch": 2.2709047003987197,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044911853963470295,
|
|
"loss": 5.1808,
|
|
"mean_token_accuracy": 0.20187862515449523,
|
|
"num_tokens": 45127612.0,
|
|
"step": 20220
|
|
},
|
|
{
|
|
"entropy": 5.54796872138977,
|
|
"epoch": 2.2714662773066774,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004490931084115772,
|
|
"loss": 5.3538,
|
|
"mean_token_accuracy": 0.1942208006978035,
|
|
"num_tokens": 45138495.0,
|
|
"step": 20225
|
|
},
|
|
{
|
|
"entropy": 5.4929811477661135,
|
|
"epoch": 2.2720278542146346,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044906767164525936,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.20373067259788513,
|
|
"num_tokens": 45149727.0,
|
|
"step": 20230
|
|
},
|
|
{
|
|
"entropy": 5.490101861953735,
|
|
"epoch": 2.2725894311225923,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004490422293365594,
|
|
"loss": 5.2572,
|
|
"mean_token_accuracy": 0.19031398445367814,
|
|
"num_tokens": 45160921.0,
|
|
"step": 20235
|
|
},
|
|
{
|
|
"entropy": 5.40823712348938,
|
|
"epoch": 2.27315100803055,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004490167814862872,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.20218690037727355,
|
|
"num_tokens": 45172607.0,
|
|
"step": 20240
|
|
},
|
|
{
|
|
"entropy": 5.610833311080933,
|
|
"epoch": 2.273712584938507,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004489913280952533,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.1915770500898361,
|
|
"num_tokens": 45186330.0,
|
|
"step": 20245
|
|
},
|
|
{
|
|
"entropy": 5.416332244873047,
|
|
"epoch": 2.274274161846465,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004489658691642681,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.20174629986286163,
|
|
"num_tokens": 45198239.0,
|
|
"step": 20250
|
|
},
|
|
{
|
|
"entropy": 5.342674207687378,
|
|
"epoch": 2.2748357387544225,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044894040469414207,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20407681316137313,
|
|
"num_tokens": 45209295.0,
|
|
"step": 20255
|
|
},
|
|
{
|
|
"entropy": 5.4958991527557375,
|
|
"epoch": 2.27539731566238,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044891493468568607,
|
|
"loss": 5.2465,
|
|
"mean_token_accuracy": 0.19792570769786835,
|
|
"num_tokens": 45220210.0,
|
|
"step": 20260
|
|
},
|
|
{
|
|
"entropy": 5.502053260803223,
|
|
"epoch": 2.2759588925703373,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044888945913971106,
|
|
"loss": 5.2646,
|
|
"mean_token_accuracy": 0.19268529564142228,
|
|
"num_tokens": 45231809.0,
|
|
"step": 20265
|
|
},
|
|
{
|
|
"entropy": 5.466073226928711,
|
|
"epoch": 2.276520469478295,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044886397805702835,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.20378606915473937,
|
|
"num_tokens": 45242847.0,
|
|
"step": 20270
|
|
},
|
|
{
|
|
"entropy": 5.415965366363525,
|
|
"epoch": 2.2770820463862527,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00044883849143844914,
|
|
"loss": 5.1893,
|
|
"mean_token_accuracy": 0.20552432537078857,
|
|
"num_tokens": 45253357.0,
|
|
"step": 20275
|
|
},
|
|
{
|
|
"entropy": 5.432175350189209,
|
|
"epoch": 2.2776436232942103,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004488129992847848,
|
|
"loss": 5.0928,
|
|
"mean_token_accuracy": 0.20207509100437165,
|
|
"num_tokens": 45264607.0,
|
|
"step": 20280
|
|
},
|
|
{
|
|
"entropy": 5.561496162414551,
|
|
"epoch": 2.2782052002021675,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004487875015968473,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.194337198138237,
|
|
"num_tokens": 45275211.0,
|
|
"step": 20285
|
|
},
|
|
{
|
|
"entropy": 5.491414308547974,
|
|
"epoch": 2.278766777110125,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004487619983754483,
|
|
"loss": 5.1524,
|
|
"mean_token_accuracy": 0.20208866745233536,
|
|
"num_tokens": 45286665.0,
|
|
"step": 20290
|
|
},
|
|
{
|
|
"entropy": 5.477858257293701,
|
|
"epoch": 2.279328354018083,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00044873648962139983,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.19548479914665223,
|
|
"num_tokens": 45298066.0,
|
|
"step": 20295
|
|
},
|
|
{
|
|
"entropy": 5.461922359466553,
|
|
"epoch": 2.27988993092604,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004487109753355142,
|
|
"loss": 5.2477,
|
|
"mean_token_accuracy": 0.1936965987086296,
|
|
"num_tokens": 45308799.0,
|
|
"step": 20300
|
|
},
|
|
{
|
|
"entropy": 5.471404790878296,
|
|
"epoch": 2.2804515078339977,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004486854555186037,
|
|
"loss": 5.1187,
|
|
"mean_token_accuracy": 0.20425757765769958,
|
|
"num_tokens": 45319932.0,
|
|
"step": 20305
|
|
},
|
|
{
|
|
"entropy": 5.523519563674927,
|
|
"epoch": 2.2810130847419554,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004486599301714809,
|
|
"loss": 5.2714,
|
|
"mean_token_accuracy": 0.19466557800769807,
|
|
"num_tokens": 45330008.0,
|
|
"step": 20310
|
|
},
|
|
{
|
|
"entropy": 5.509019136428833,
|
|
"epoch": 2.281574661649913,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004486343992949587,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.19150369614362717,
|
|
"num_tokens": 45340877.0,
|
|
"step": 20315
|
|
},
|
|
{
|
|
"entropy": 5.442544889450073,
|
|
"epoch": 2.2821362385578707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044860886288984977,
|
|
"loss": 5.2349,
|
|
"mean_token_accuracy": 0.19698913991451264,
|
|
"num_tokens": 45351956.0,
|
|
"step": 20320
|
|
},
|
|
{
|
|
"entropy": 5.526035118103027,
|
|
"epoch": 2.282697815465828,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004485833209569674,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.19227344989776612,
|
|
"num_tokens": 45363133.0,
|
|
"step": 20325
|
|
},
|
|
{
|
|
"entropy": 5.462725448608398,
|
|
"epoch": 2.2832593923737856,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004485577734971247,
|
|
"loss": 5.1743,
|
|
"mean_token_accuracy": 0.19781951308250428,
|
|
"num_tokens": 45373917.0,
|
|
"step": 20330
|
|
},
|
|
{
|
|
"entropy": 5.5639630317687985,
|
|
"epoch": 2.2838209692817433,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044853222051113525,
|
|
"loss": 5.3004,
|
|
"mean_token_accuracy": 0.19448948949575423,
|
|
"num_tokens": 45385575.0,
|
|
"step": 20335
|
|
},
|
|
{
|
|
"entropy": 5.519522285461425,
|
|
"epoch": 2.2843825461897005,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044850666199981244,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19502506107091905,
|
|
"num_tokens": 45396615.0,
|
|
"step": 20340
|
|
},
|
|
{
|
|
"entropy": 5.458017301559448,
|
|
"epoch": 2.284944123097658,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00044848109796397035,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.19171172529459,
|
|
"num_tokens": 45408931.0,
|
|
"step": 20345
|
|
},
|
|
{
|
|
"entropy": 5.506092739105225,
|
|
"epoch": 2.285505700005616,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044845552840442276,
|
|
"loss": 5.2747,
|
|
"mean_token_accuracy": 0.19238129556179046,
|
|
"num_tokens": 45419993.0,
|
|
"step": 20350
|
|
},
|
|
{
|
|
"entropy": 5.542658138275146,
|
|
"epoch": 2.2860672769135735,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044842995332198393,
|
|
"loss": 5.3204,
|
|
"mean_token_accuracy": 0.18513930588960648,
|
|
"num_tokens": 45431889.0,
|
|
"step": 20355
|
|
},
|
|
{
|
|
"entropy": 5.441732788085938,
|
|
"epoch": 2.2866288538215307,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044840437271746807,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.19629255533218384,
|
|
"num_tokens": 45444233.0,
|
|
"step": 20360
|
|
},
|
|
{
|
|
"entropy": 5.449062204360962,
|
|
"epoch": 2.2871904307294884,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004483787865916898,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.19557869285345078,
|
|
"num_tokens": 45455743.0,
|
|
"step": 20365
|
|
},
|
|
{
|
|
"entropy": 5.458435440063477,
|
|
"epoch": 2.287752007637446,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044835319494546366,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.1936202362179756,
|
|
"num_tokens": 45466272.0,
|
|
"step": 20370
|
|
},
|
|
{
|
|
"entropy": 5.538595533370971,
|
|
"epoch": 2.2883135845454037,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00044832759777960456,
|
|
"loss": 5.205,
|
|
"mean_token_accuracy": 0.1956723928451538,
|
|
"num_tokens": 45477828.0,
|
|
"step": 20375
|
|
},
|
|
{
|
|
"entropy": 5.475883340835571,
|
|
"epoch": 2.288875161453361,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004483019950949276,
|
|
"loss": 5.2313,
|
|
"mean_token_accuracy": 0.19177326411008835,
|
|
"num_tokens": 45489315.0,
|
|
"step": 20380
|
|
},
|
|
{
|
|
"entropy": 5.395002269744873,
|
|
"epoch": 2.2894367383613186,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004482763868922478,
|
|
"loss": 5.1496,
|
|
"mean_token_accuracy": 0.20631805956363677,
|
|
"num_tokens": 45499836.0,
|
|
"step": 20385
|
|
},
|
|
{
|
|
"entropy": 5.522030210494995,
|
|
"epoch": 2.289998315269276,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004482507731723807,
|
|
"loss": 5.2731,
|
|
"mean_token_accuracy": 0.19067671298980712,
|
|
"num_tokens": 45511106.0,
|
|
"step": 20390
|
|
},
|
|
{
|
|
"entropy": 5.495359706878662,
|
|
"epoch": 2.2905598921772334,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004482251539361418,
|
|
"loss": 5.2067,
|
|
"mean_token_accuracy": 0.19410201162099838,
|
|
"num_tokens": 45521314.0,
|
|
"step": 20395
|
|
},
|
|
{
|
|
"entropy": 5.529042673110962,
|
|
"epoch": 2.291121469085191,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004481995291843467,
|
|
"loss": 5.261,
|
|
"mean_token_accuracy": 0.20009034425020217,
|
|
"num_tokens": 45531675.0,
|
|
"step": 20400
|
|
},
|
|
{
|
|
"entropy": 5.529282951354981,
|
|
"epoch": 2.2916830459931488,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004481738989178115,
|
|
"loss": 5.2899,
|
|
"mean_token_accuracy": 0.19630020409822463,
|
|
"num_tokens": 45542064.0,
|
|
"step": 20405
|
|
},
|
|
{
|
|
"entropy": 5.487805652618408,
|
|
"epoch": 2.2922446229011064,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004481482631373522,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.19990842938423156,
|
|
"num_tokens": 45553764.0,
|
|
"step": 20410
|
|
},
|
|
{
|
|
"entropy": 5.575030088424683,
|
|
"epoch": 2.292806199809064,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044812262184378503,
|
|
"loss": 5.3084,
|
|
"mean_token_accuracy": 0.194069766998291,
|
|
"num_tokens": 45565302.0,
|
|
"step": 20415
|
|
},
|
|
{
|
|
"entropy": 5.405620098114014,
|
|
"epoch": 2.2933677767170213,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044809697503792647,
|
|
"loss": 5.1356,
|
|
"mean_token_accuracy": 0.20320552587509155,
|
|
"num_tokens": 45577165.0,
|
|
"step": 20420
|
|
},
|
|
{
|
|
"entropy": 5.483516359329224,
|
|
"epoch": 2.293929353624979,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044807132272059306,
|
|
"loss": 5.1801,
|
|
"mean_token_accuracy": 0.20040037631988525,
|
|
"num_tokens": 45587771.0,
|
|
"step": 20425
|
|
},
|
|
{
|
|
"entropy": 5.45260591506958,
|
|
"epoch": 2.2944909305329366,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004480456648926016,
|
|
"loss": 5.2213,
|
|
"mean_token_accuracy": 0.2051618903875351,
|
|
"num_tokens": 45598815.0,
|
|
"step": 20430
|
|
},
|
|
{
|
|
"entropy": 5.457582664489746,
|
|
"epoch": 2.295052507440894,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004480200015547691,
|
|
"loss": 5.1729,
|
|
"mean_token_accuracy": 0.2023330271244049,
|
|
"num_tokens": 45609007.0,
|
|
"step": 20435
|
|
},
|
|
{
|
|
"entropy": 5.514306449890137,
|
|
"epoch": 2.2956140843488515,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00044799433270791255,
|
|
"loss": 5.3165,
|
|
"mean_token_accuracy": 0.1910293370485306,
|
|
"num_tokens": 45621323.0,
|
|
"step": 20440
|
|
},
|
|
{
|
|
"entropy": 5.445145893096924,
|
|
"epoch": 2.296175661256809,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004479686583528494,
|
|
"loss": 5.0512,
|
|
"mean_token_accuracy": 0.20401570051908494,
|
|
"num_tokens": 45631895.0,
|
|
"step": 20445
|
|
},
|
|
{
|
|
"entropy": 5.477041006088257,
|
|
"epoch": 2.296737238164767,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004479429784903971,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.1992275446653366,
|
|
"num_tokens": 45643204.0,
|
|
"step": 20450
|
|
},
|
|
{
|
|
"entropy": 5.476336097717285,
|
|
"epoch": 2.297298815072724,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004479172931213733,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.19647954255342484,
|
|
"num_tokens": 45654607.0,
|
|
"step": 20455
|
|
},
|
|
{
|
|
"entropy": 5.424917984008789,
|
|
"epoch": 2.2978603919806817,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004478916022465958,
|
|
"loss": 5.1667,
|
|
"mean_token_accuracy": 0.19767047464847565,
|
|
"num_tokens": 45666746.0,
|
|
"step": 20460
|
|
},
|
|
{
|
|
"entropy": 5.452603197097778,
|
|
"epoch": 2.2984219688886394,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004478659058668827,
|
|
"loss": 5.1226,
|
|
"mean_token_accuracy": 0.20131931453943253,
|
|
"num_tokens": 45676663.0,
|
|
"step": 20465
|
|
},
|
|
{
|
|
"entropy": 5.445347690582276,
|
|
"epoch": 2.298983545796597,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044784020398305204,
|
|
"loss": 5.1724,
|
|
"mean_token_accuracy": 0.1966598942875862,
|
|
"num_tokens": 45688746.0,
|
|
"step": 20470
|
|
},
|
|
{
|
|
"entropy": 5.580845546722412,
|
|
"epoch": 2.2995451227045542,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004478144965959222,
|
|
"loss": 5.3804,
|
|
"mean_token_accuracy": 0.1894101843237877,
|
|
"num_tokens": 45700199.0,
|
|
"step": 20475
|
|
},
|
|
{
|
|
"entropy": 5.479755020141601,
|
|
"epoch": 2.300106699612512,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044778878370631183,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19110425859689711,
|
|
"num_tokens": 45710771.0,
|
|
"step": 20480
|
|
},
|
|
{
|
|
"entropy": 5.507200813293457,
|
|
"epoch": 2.3006682765204696,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044776306531503957,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.19257741272449494,
|
|
"num_tokens": 45721957.0,
|
|
"step": 20485
|
|
},
|
|
{
|
|
"entropy": 5.515151023864746,
|
|
"epoch": 2.301229853428427,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044773734142292425,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.19508351981639863,
|
|
"num_tokens": 45733904.0,
|
|
"step": 20490
|
|
},
|
|
{
|
|
"entropy": 5.532930946350097,
|
|
"epoch": 2.3017914303363844,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004477116120307851,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.19844147115945815,
|
|
"num_tokens": 45744004.0,
|
|
"step": 20495
|
|
},
|
|
{
|
|
"entropy": 5.460457229614258,
|
|
"epoch": 2.302353007244342,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004476858771394412,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.2073976770043373,
|
|
"num_tokens": 45755130.0,
|
|
"step": 20500
|
|
},
|
|
{
|
|
"entropy": 5.4642860889434814,
|
|
"epoch": 2.3029145841522998,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004476601367497119,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.19005354791879653,
|
|
"num_tokens": 45767353.0,
|
|
"step": 20505
|
|
},
|
|
{
|
|
"entropy": 5.566329908370972,
|
|
"epoch": 2.3034761610602574,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000447634390862417,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.1791055753827095,
|
|
"num_tokens": 45779266.0,
|
|
"step": 20510
|
|
},
|
|
{
|
|
"entropy": 5.589048671722412,
|
|
"epoch": 2.3040377379682146,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00044760863947837607,
|
|
"loss": 5.3575,
|
|
"mean_token_accuracy": 0.19195362776517869,
|
|
"num_tokens": 45790601.0,
|
|
"step": 20515
|
|
},
|
|
{
|
|
"entropy": 5.513338375091553,
|
|
"epoch": 2.3045993148761723,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044758288259840904,
|
|
"loss": 5.2176,
|
|
"mean_token_accuracy": 0.19610059261322021,
|
|
"num_tokens": 45801449.0,
|
|
"step": 20520
|
|
},
|
|
{
|
|
"entropy": 5.4006000518798825,
|
|
"epoch": 2.30516089178413,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004475571202233363,
|
|
"loss": 5.1472,
|
|
"mean_token_accuracy": 0.20121243745088577,
|
|
"num_tokens": 45811737.0,
|
|
"step": 20525
|
|
},
|
|
{
|
|
"entropy": 5.452383136749267,
|
|
"epoch": 2.305722468692087,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004475313523539778,
|
|
"loss": 5.2185,
|
|
"mean_token_accuracy": 0.20134832859039306,
|
|
"num_tokens": 45822955.0,
|
|
"step": 20530
|
|
},
|
|
{
|
|
"entropy": 5.512687635421753,
|
|
"epoch": 2.306284045600045,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044750557899115407,
|
|
"loss": 5.2885,
|
|
"mean_token_accuracy": 0.1988004893064499,
|
|
"num_tokens": 45834697.0,
|
|
"step": 20535
|
|
},
|
|
{
|
|
"entropy": 5.453501224517822,
|
|
"epoch": 2.3068456225080025,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004474798001356859,
|
|
"loss": 5.2211,
|
|
"mean_token_accuracy": 0.1922624319791794,
|
|
"num_tokens": 45846869.0,
|
|
"step": 20540
|
|
},
|
|
{
|
|
"entropy": 5.4645631313323975,
|
|
"epoch": 2.30740719941596,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000447454015788394,
|
|
"loss": 5.2058,
|
|
"mean_token_accuracy": 0.19926741421222688,
|
|
"num_tokens": 45858171.0,
|
|
"step": 20545
|
|
},
|
|
{
|
|
"entropy": 5.487905836105346,
|
|
"epoch": 2.3079687763239174,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004474282259500992,
|
|
"loss": 5.1971,
|
|
"mean_token_accuracy": 0.19392701089382172,
|
|
"num_tokens": 45868715.0,
|
|
"step": 20550
|
|
},
|
|
{
|
|
"entropy": 5.468223762512207,
|
|
"epoch": 2.308530353231875,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000447402430621623,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.2021302953362465,
|
|
"num_tokens": 45880569.0,
|
|
"step": 20555
|
|
},
|
|
{
|
|
"entropy": 5.486944770812988,
|
|
"epoch": 2.3090919301398327,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004473766298037865,
|
|
"loss": 5.2011,
|
|
"mean_token_accuracy": 0.19763137996196747,
|
|
"num_tokens": 45890452.0,
|
|
"step": 20560
|
|
},
|
|
{
|
|
"entropy": 5.594872903823853,
|
|
"epoch": 2.3096535070477904,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044735082349741116,
|
|
"loss": 5.3046,
|
|
"mean_token_accuracy": 0.18926722109317778,
|
|
"num_tokens": 45903125.0,
|
|
"step": 20565
|
|
},
|
|
{
|
|
"entropy": 5.456194972991943,
|
|
"epoch": 2.3102150839557476,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044732501170331886,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.1987733393907547,
|
|
"num_tokens": 45914961.0,
|
|
"step": 20570
|
|
},
|
|
{
|
|
"entropy": 5.555016279220581,
|
|
"epoch": 2.3107766608637053,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004472991944223313,
|
|
"loss": 5.3378,
|
|
"mean_token_accuracy": 0.19245805889368056,
|
|
"num_tokens": 45927198.0,
|
|
"step": 20575
|
|
},
|
|
{
|
|
"entropy": 5.54108772277832,
|
|
"epoch": 2.311338237771663,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044727337165527056,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.19966366589069368,
|
|
"num_tokens": 45937937.0,
|
|
"step": 20580
|
|
},
|
|
{
|
|
"entropy": 5.55788221359253,
|
|
"epoch": 2.31189981467962,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044724754340295887,
|
|
"loss": 5.2713,
|
|
"mean_token_accuracy": 0.18861729502677918,
|
|
"num_tokens": 45948983.0,
|
|
"step": 20585
|
|
},
|
|
{
|
|
"entropy": 5.457464790344238,
|
|
"epoch": 2.312461391587578,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004472217096662186,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.18854102045297622,
|
|
"num_tokens": 45960674.0,
|
|
"step": 20590
|
|
},
|
|
{
|
|
"entropy": 5.4817986488342285,
|
|
"epoch": 2.3130229684955355,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004471958704458723,
|
|
"loss": 5.2024,
|
|
"mean_token_accuracy": 0.19684194326400756,
|
|
"num_tokens": 45971260.0,
|
|
"step": 20595
|
|
},
|
|
{
|
|
"entropy": 5.582309675216675,
|
|
"epoch": 2.313584545403493,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044717002574274267,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.1962347224354744,
|
|
"num_tokens": 45983942.0,
|
|
"step": 20600
|
|
},
|
|
{
|
|
"entropy": 5.512586069107056,
|
|
"epoch": 2.314146122311451,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004471441755576527,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.18981710970401763,
|
|
"num_tokens": 45995983.0,
|
|
"step": 20605
|
|
},
|
|
{
|
|
"entropy": 5.4869225025177,
|
|
"epoch": 2.314707699219408,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044711831989142534,
|
|
"loss": 5.2094,
|
|
"mean_token_accuracy": 0.19439781010150908,
|
|
"num_tokens": 46007074.0,
|
|
"step": 20610
|
|
},
|
|
{
|
|
"entropy": 5.547431230545044,
|
|
"epoch": 2.3152692761273657,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044709245874488405,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1979259356856346,
|
|
"num_tokens": 46018376.0,
|
|
"step": 20615
|
|
},
|
|
{
|
|
"entropy": 5.45595645904541,
|
|
"epoch": 2.3158308530353233,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004470665921188519,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.19550760984420776,
|
|
"num_tokens": 46029192.0,
|
|
"step": 20620
|
|
},
|
|
{
|
|
"entropy": 5.440639209747315,
|
|
"epoch": 2.3163924299432805,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044704072001415285,
|
|
"loss": 5.2753,
|
|
"mean_token_accuracy": 0.1992657244205475,
|
|
"num_tokens": 46040735.0,
|
|
"step": 20625
|
|
},
|
|
{
|
|
"entropy": 5.4766770362854,
|
|
"epoch": 2.316954006851238,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00044701484243161055,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.20483722537755966,
|
|
"num_tokens": 46050859.0,
|
|
"step": 20630
|
|
},
|
|
{
|
|
"entropy": 5.386773252487183,
|
|
"epoch": 2.317515583759196,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000446988959372049,
|
|
"loss": 5.181,
|
|
"mean_token_accuracy": 0.20264114886522294,
|
|
"num_tokens": 46060704.0,
|
|
"step": 20635
|
|
},
|
|
{
|
|
"entropy": 5.407052850723266,
|
|
"epoch": 2.3180771606671535,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004469630708362922,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.19639850854873658,
|
|
"num_tokens": 46072317.0,
|
|
"step": 20640
|
|
},
|
|
{
|
|
"entropy": 5.583427906036377,
|
|
"epoch": 2.3186387375751107,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004469371768251646,
|
|
"loss": 5.3507,
|
|
"mean_token_accuracy": 0.1896985501050949,
|
|
"num_tokens": 46083823.0,
|
|
"step": 20645
|
|
},
|
|
{
|
|
"entropy": 5.579678201675415,
|
|
"epoch": 2.3192003144830684,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004469112773394906,
|
|
"loss": 5.2704,
|
|
"mean_token_accuracy": 0.19577296823263168,
|
|
"num_tokens": 46093920.0,
|
|
"step": 20650
|
|
},
|
|
{
|
|
"entropy": 5.422857570648193,
|
|
"epoch": 2.319761891391026,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004468853723800948,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.19964059740304946,
|
|
"num_tokens": 46104618.0,
|
|
"step": 20655
|
|
},
|
|
{
|
|
"entropy": 5.45638632774353,
|
|
"epoch": 2.3203234682989837,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004468594619478021,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.20293244272470473,
|
|
"num_tokens": 46114748.0,
|
|
"step": 20660
|
|
},
|
|
{
|
|
"entropy": 5.505843639373779,
|
|
"epoch": 2.320885045206941,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004468335460434375,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.20009017139673232,
|
|
"num_tokens": 46125125.0,
|
|
"step": 20665
|
|
},
|
|
{
|
|
"entropy": 5.336104917526245,
|
|
"epoch": 2.3214466221148986,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004468076246678261,
|
|
"loss": 5.1675,
|
|
"mean_token_accuracy": 0.1908090204000473,
|
|
"num_tokens": 46135877.0,
|
|
"step": 20670
|
|
},
|
|
{
|
|
"entropy": 5.534953022003174,
|
|
"epoch": 2.3220081990228563,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044678169782179334,
|
|
"loss": 5.3553,
|
|
"mean_token_accuracy": 0.19203379154205322,
|
|
"num_tokens": 46146769.0,
|
|
"step": 20675
|
|
},
|
|
{
|
|
"entropy": 5.487344551086426,
|
|
"epoch": 2.3225697759308135,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044675576550616466,
|
|
"loss": 5.2238,
|
|
"mean_token_accuracy": 0.20019155740737915,
|
|
"num_tokens": 46158408.0,
|
|
"step": 20680
|
|
},
|
|
{
|
|
"entropy": 5.5948151588439945,
|
|
"epoch": 2.323131352838771,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044672982772176584,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.1879815563559532,
|
|
"num_tokens": 46169961.0,
|
|
"step": 20685
|
|
},
|
|
{
|
|
"entropy": 5.575778436660767,
|
|
"epoch": 2.323692929746729,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004467038844694227,
|
|
"loss": 5.3011,
|
|
"mean_token_accuracy": 0.19506117552518845,
|
|
"num_tokens": 46181750.0,
|
|
"step": 20690
|
|
},
|
|
{
|
|
"entropy": 5.4993890762329105,
|
|
"epoch": 2.3242545066546865,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004466779357499612,
|
|
"loss": 5.1698,
|
|
"mean_token_accuracy": 0.20466341078281403,
|
|
"num_tokens": 46192745.0,
|
|
"step": 20695
|
|
},
|
|
{
|
|
"entropy": 5.495275449752808,
|
|
"epoch": 2.324816083562644,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044665198156420774,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.19710493087768555,
|
|
"num_tokens": 46203267.0,
|
|
"step": 20700
|
|
},
|
|
{
|
|
"entropy": 5.474107837677002,
|
|
"epoch": 2.3253776604706013,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044662602191298856,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.20042662769556047,
|
|
"num_tokens": 46214966.0,
|
|
"step": 20705
|
|
},
|
|
{
|
|
"entropy": 5.412426900863648,
|
|
"epoch": 2.325939237378559,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044660005679713027,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.1992228403687477,
|
|
"num_tokens": 46225755.0,
|
|
"step": 20710
|
|
},
|
|
{
|
|
"entropy": 5.50371561050415,
|
|
"epoch": 2.3265008142865167,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044657408621745964,
|
|
"loss": 5.2745,
|
|
"mean_token_accuracy": 0.19571999311447144,
|
|
"num_tokens": 46237091.0,
|
|
"step": 20715
|
|
},
|
|
{
|
|
"entropy": 5.549902248382568,
|
|
"epoch": 2.327062391194474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004465481101748036,
|
|
"loss": 5.2661,
|
|
"mean_token_accuracy": 0.1911383628845215,
|
|
"num_tokens": 46249250.0,
|
|
"step": 20720
|
|
},
|
|
{
|
|
"entropy": 5.480843019485474,
|
|
"epoch": 2.3276239681024316,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044652212866998914,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.19388830959796904,
|
|
"num_tokens": 46259866.0,
|
|
"step": 20725
|
|
},
|
|
{
|
|
"entropy": 5.438033676147461,
|
|
"epoch": 2.328185545010389,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044649614170384354,
|
|
"loss": 5.1576,
|
|
"mean_token_accuracy": 0.20644867569208145,
|
|
"num_tokens": 46270888.0,
|
|
"step": 20730
|
|
},
|
|
{
|
|
"entropy": 5.458058881759643,
|
|
"epoch": 2.328747121918347,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044647014927719436,
|
|
"loss": 5.2237,
|
|
"mean_token_accuracy": 0.1946951448917389,
|
|
"num_tokens": 46281109.0,
|
|
"step": 20735
|
|
},
|
|
{
|
|
"entropy": 5.5181926727294925,
|
|
"epoch": 2.329308698826304,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044644415139086913,
|
|
"loss": 5.1196,
|
|
"mean_token_accuracy": 0.2072390228509903,
|
|
"num_tokens": 46292171.0,
|
|
"step": 20740
|
|
},
|
|
{
|
|
"entropy": 5.472347211837769,
|
|
"epoch": 2.3298702757342618,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004464181480456955,
|
|
"loss": 5.1972,
|
|
"mean_token_accuracy": 0.1948470503091812,
|
|
"num_tokens": 46302919.0,
|
|
"step": 20745
|
|
},
|
|
{
|
|
"entropy": 5.3546772480010985,
|
|
"epoch": 2.3304318526422194,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004463921392425017,
|
|
"loss": 5.1093,
|
|
"mean_token_accuracy": 0.2069597363471985,
|
|
"num_tokens": 46313199.0,
|
|
"step": 20750
|
|
},
|
|
{
|
|
"entropy": 5.532437515258789,
|
|
"epoch": 2.330993429550177,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00044636612498211566,
|
|
"loss": 5.2534,
|
|
"mean_token_accuracy": 0.19960334599018098,
|
|
"num_tokens": 46324316.0,
|
|
"step": 20755
|
|
},
|
|
{
|
|
"entropy": 5.430422639846801,
|
|
"epoch": 2.3315550064581343,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044634010526536575,
|
|
"loss": 5.2328,
|
|
"mean_token_accuracy": 0.19044245779514313,
|
|
"num_tokens": 46335767.0,
|
|
"step": 20760
|
|
},
|
|
{
|
|
"entropy": 5.428646850585937,
|
|
"epoch": 2.332116583366092,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004463140800930804,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.1928640455007553,
|
|
"num_tokens": 46347840.0,
|
|
"step": 20765
|
|
},
|
|
{
|
|
"entropy": 5.486501264572143,
|
|
"epoch": 2.3326781602740496,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004462880494660883,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.1896778389811516,
|
|
"num_tokens": 46359766.0,
|
|
"step": 20770
|
|
},
|
|
{
|
|
"entropy": 5.581293296813965,
|
|
"epoch": 2.333239737182007,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.00044626201338521834,
|
|
"loss": 5.2222,
|
|
"mean_token_accuracy": 0.2051137313246727,
|
|
"num_tokens": 46371426.0,
|
|
"step": 20775
|
|
},
|
|
{
|
|
"entropy": 5.529552841186524,
|
|
"epoch": 2.3338013140899645,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004462359718512993,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.1937130257487297,
|
|
"num_tokens": 46382257.0,
|
|
"step": 20780
|
|
},
|
|
{
|
|
"entropy": 5.515810823440551,
|
|
"epoch": 2.334362890997922,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00044620992486516073,
|
|
"loss": 5.2546,
|
|
"mean_token_accuracy": 0.19325234442949296,
|
|
"num_tokens": 46393689.0,
|
|
"step": 20785
|
|
},
|
|
{
|
|
"entropy": 5.4853262424469,
|
|
"epoch": 2.33492446790588,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004461838724276316,
|
|
"loss": 5.283,
|
|
"mean_token_accuracy": 0.19145442992448808,
|
|
"num_tokens": 46404856.0,
|
|
"step": 20790
|
|
},
|
|
{
|
|
"entropy": 5.62254147529602,
|
|
"epoch": 2.3354860448138375,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044615781453954164,
|
|
"loss": 5.2724,
|
|
"mean_token_accuracy": 0.19046712517738343,
|
|
"num_tokens": 46415395.0,
|
|
"step": 20795
|
|
},
|
|
{
|
|
"entropy": 5.579497861862182,
|
|
"epoch": 2.3360476217217947,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044613175120172035,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.19241973906755447,
|
|
"num_tokens": 46426773.0,
|
|
"step": 20800
|
|
},
|
|
{
|
|
"entropy": 5.418494367599488,
|
|
"epoch": 2.3366091986297524,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004461056824149979,
|
|
"loss": 5.1538,
|
|
"mean_token_accuracy": 0.1969577342271805,
|
|
"num_tokens": 46438206.0,
|
|
"step": 20805
|
|
},
|
|
{
|
|
"entropy": 5.531554412841797,
|
|
"epoch": 2.33717077553771,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000446079608180204,
|
|
"loss": 5.2565,
|
|
"mean_token_accuracy": 0.1963140994310379,
|
|
"num_tokens": 46449922.0,
|
|
"step": 20810
|
|
},
|
|
{
|
|
"entropy": 5.491814470291137,
|
|
"epoch": 2.3377323524456672,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004460535284981692,
|
|
"loss": 5.1878,
|
|
"mean_token_accuracy": 0.19918892085552214,
|
|
"num_tokens": 46461715.0,
|
|
"step": 20815
|
|
},
|
|
{
|
|
"entropy": 5.450894355773926,
|
|
"epoch": 2.338293929353625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004460274433697235,
|
|
"loss": 5.2028,
|
|
"mean_token_accuracy": 0.19470690190792084,
|
|
"num_tokens": 46473136.0,
|
|
"step": 20820
|
|
},
|
|
{
|
|
"entropy": 5.436090135574341,
|
|
"epoch": 2.3388555062615826,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044600135279569784,
|
|
"loss": 5.1006,
|
|
"mean_token_accuracy": 0.20262417197227478,
|
|
"num_tokens": 46483644.0,
|
|
"step": 20825
|
|
},
|
|
{
|
|
"entropy": 5.530288410186768,
|
|
"epoch": 2.3394170831695402,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044597525677692273,
|
|
"loss": 5.2639,
|
|
"mean_token_accuracy": 0.19475924372673034,
|
|
"num_tokens": 46494896.0,
|
|
"step": 20830
|
|
},
|
|
{
|
|
"entropy": 5.517976760864258,
|
|
"epoch": 2.3399786600774974,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004459491553142291,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.19440987408161164,
|
|
"num_tokens": 46505415.0,
|
|
"step": 20835
|
|
},
|
|
{
|
|
"entropy": 5.489750003814697,
|
|
"epoch": 2.340540236985455,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044592304840844813,
|
|
"loss": 5.2142,
|
|
"mean_token_accuracy": 0.19895916134119035,
|
|
"num_tokens": 46516280.0,
|
|
"step": 20840
|
|
},
|
|
{
|
|
"entropy": 5.407734203338623,
|
|
"epoch": 2.3411018138934128,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000445896936060411,
|
|
"loss": 5.1117,
|
|
"mean_token_accuracy": 0.19886795729398726,
|
|
"num_tokens": 46526456.0,
|
|
"step": 20845
|
|
},
|
|
{
|
|
"entropy": 5.481870555877686,
|
|
"epoch": 2.3416633908013704,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044587081827094906,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.198627245426178,
|
|
"num_tokens": 46537547.0,
|
|
"step": 20850
|
|
},
|
|
{
|
|
"entropy": 5.432827806472778,
|
|
"epoch": 2.3422249677093276,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044584469504089407,
|
|
"loss": 5.1639,
|
|
"mean_token_accuracy": 0.1990901365876198,
|
|
"num_tokens": 46549424.0,
|
|
"step": 20855
|
|
},
|
|
{
|
|
"entropy": 5.501176595687866,
|
|
"epoch": 2.3427865446172853,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004458185663710777,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.19921982288360596,
|
|
"num_tokens": 46560234.0,
|
|
"step": 20860
|
|
},
|
|
{
|
|
"entropy": 5.468033027648926,
|
|
"epoch": 2.343348121525243,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004457924322623319,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.19499204456806182,
|
|
"num_tokens": 46570847.0,
|
|
"step": 20865
|
|
},
|
|
{
|
|
"entropy": 5.3699875831604,
|
|
"epoch": 2.3439096984332,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044576629271548884,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.1958999902009964,
|
|
"num_tokens": 46582379.0,
|
|
"step": 20870
|
|
},
|
|
{
|
|
"entropy": 5.480055856704712,
|
|
"epoch": 2.344471275341158,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004457401477313808,
|
|
"loss": 5.2153,
|
|
"mean_token_accuracy": 0.1895243391394615,
|
|
"num_tokens": 46594669.0,
|
|
"step": 20875
|
|
},
|
|
{
|
|
"entropy": 5.398187828063965,
|
|
"epoch": 2.3450328522491155,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004457139973108403,
|
|
"loss": 5.0753,
|
|
"mean_token_accuracy": 0.20904066860675813,
|
|
"num_tokens": 46605834.0,
|
|
"step": 20880
|
|
},
|
|
{
|
|
"entropy": 5.437838411331176,
|
|
"epoch": 2.345594429157073,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004456878414546998,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.19901249259710313,
|
|
"num_tokens": 46616684.0,
|
|
"step": 20885
|
|
},
|
|
{
|
|
"entropy": 5.498946571350098,
|
|
"epoch": 2.346156006065031,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044566168016379234,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.1991828739643097,
|
|
"num_tokens": 46628045.0,
|
|
"step": 20890
|
|
},
|
|
{
|
|
"entropy": 5.470038557052613,
|
|
"epoch": 2.346717582972988,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004456355134389507,
|
|
"loss": 5.1979,
|
|
"mean_token_accuracy": 0.1997692972421646,
|
|
"num_tokens": 46639455.0,
|
|
"step": 20895
|
|
},
|
|
{
|
|
"entropy": 5.574736022949219,
|
|
"epoch": 2.3472791598809457,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044560934128100814,
|
|
"loss": 5.4271,
|
|
"mean_token_accuracy": 0.18692221045494078,
|
|
"num_tokens": 46651025.0,
|
|
"step": 20900
|
|
},
|
|
{
|
|
"entropy": 5.521283769607544,
|
|
"epoch": 2.3478407367889034,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00044558316369079805,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.19479753077030182,
|
|
"num_tokens": 46661859.0,
|
|
"step": 20905
|
|
},
|
|
{
|
|
"entropy": 5.523563957214355,
|
|
"epoch": 2.3484023136968606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044555698066915385,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.1956808790564537,
|
|
"num_tokens": 46673441.0,
|
|
"step": 20910
|
|
},
|
|
{
|
|
"entropy": 5.526943254470825,
|
|
"epoch": 2.3489638906048182,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004455307922169092,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1883349135518074,
|
|
"num_tokens": 46684959.0,
|
|
"step": 20915
|
|
},
|
|
{
|
|
"entropy": 5.5232288360595705,
|
|
"epoch": 2.349525467512776,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004455045983348979,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.2013918176293373,
|
|
"num_tokens": 46694940.0,
|
|
"step": 20920
|
|
},
|
|
{
|
|
"entropy": 5.481256341934204,
|
|
"epoch": 2.3500870444207336,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004454783990239542,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.19920895099639893,
|
|
"num_tokens": 46706184.0,
|
|
"step": 20925
|
|
},
|
|
{
|
|
"entropy": 5.536126232147216,
|
|
"epoch": 2.350648621328691,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044545219428491215,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.20401808023452758,
|
|
"num_tokens": 46718267.0,
|
|
"step": 20930
|
|
},
|
|
{
|
|
"entropy": 5.491634511947632,
|
|
"epoch": 2.3512101982366485,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044542598411860605,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19750663489103318,
|
|
"num_tokens": 46729293.0,
|
|
"step": 20935
|
|
},
|
|
{
|
|
"entropy": 5.430654764175415,
|
|
"epoch": 2.351771775144606,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004453997685258706,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.19901665598154067,
|
|
"num_tokens": 46740214.0,
|
|
"step": 20940
|
|
},
|
|
{
|
|
"entropy": 5.537059164047241,
|
|
"epoch": 2.3523333520525638,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044537354750754033,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.19459071904420852,
|
|
"num_tokens": 46751269.0,
|
|
"step": 20945
|
|
},
|
|
{
|
|
"entropy": 5.443349599838257,
|
|
"epoch": 2.352894928960521,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004453473210644503,
|
|
"loss": 5.0443,
|
|
"mean_token_accuracy": 0.20772076696157454,
|
|
"num_tokens": 46761851.0,
|
|
"step": 20950
|
|
},
|
|
{
|
|
"entropy": 5.418603754043579,
|
|
"epoch": 2.3534565058684787,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004453210891974355,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.1993235543370247,
|
|
"num_tokens": 46773441.0,
|
|
"step": 20955
|
|
},
|
|
{
|
|
"entropy": 5.41632571220398,
|
|
"epoch": 2.3540180827764363,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044529485190733113,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.1993184432387352,
|
|
"num_tokens": 46785016.0,
|
|
"step": 20960
|
|
},
|
|
{
|
|
"entropy": 5.474235105514526,
|
|
"epoch": 2.3545796596843935,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004452686091949727,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19116518944501876,
|
|
"num_tokens": 46796059.0,
|
|
"step": 20965
|
|
},
|
|
{
|
|
"entropy": 5.4062761783599855,
|
|
"epoch": 2.355141236592351,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044524236106119563,
|
|
"loss": 5.1544,
|
|
"mean_token_accuracy": 0.19984563440084457,
|
|
"num_tokens": 46805725.0,
|
|
"step": 20970
|
|
},
|
|
{
|
|
"entropy": 5.486260080337525,
|
|
"epoch": 2.355702813500309,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044521610750683586,
|
|
"loss": 5.1644,
|
|
"mean_token_accuracy": 0.20142922550439835,
|
|
"num_tokens": 46816300.0,
|
|
"step": 20975
|
|
},
|
|
{
|
|
"entropy": 5.411049175262451,
|
|
"epoch": 2.3562643904082665,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004451898485327291,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.1925427421927452,
|
|
"num_tokens": 46827498.0,
|
|
"step": 20980
|
|
},
|
|
{
|
|
"entropy": 5.502156448364258,
|
|
"epoch": 2.356825967316224,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004451635841397116,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.19362266957759858,
|
|
"num_tokens": 46838416.0,
|
|
"step": 20985
|
|
},
|
|
{
|
|
"entropy": 5.533211994171142,
|
|
"epoch": 2.3573875442241814,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004451373143286195,
|
|
"loss": 5.2985,
|
|
"mean_token_accuracy": 0.19522613734006883,
|
|
"num_tokens": 46849371.0,
|
|
"step": 20990
|
|
},
|
|
{
|
|
"entropy": 5.410873079299927,
|
|
"epoch": 2.357949121132139,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044511103910028945,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.19861335754394532,
|
|
"num_tokens": 46860095.0,
|
|
"step": 20995
|
|
},
|
|
{
|
|
"entropy": 5.533935403823852,
|
|
"epoch": 2.3585106980400967,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004450847584555579,
|
|
"loss": 5.3238,
|
|
"mean_token_accuracy": 0.18904694616794587,
|
|
"num_tokens": 46871217.0,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"epoch": 2.3585106980400967,
|
|
"eval_entropy": 5.364048132307295,
|
|
"eval_loss": 5.346198081970215,
|
|
"eval_mean_token_accuracy": 0.19883857124891283,
|
|
"eval_num_tokens": 46871217.0,
|
|
"eval_runtime": 24.0413,
|
|
"eval_samples_per_second": 1289.99,
|
|
"eval_steps_per_second": 161.264,
|
|
"step": 21000
|
|
},
|
|
{
|
|
"entropy": 5.4957421779632565,
|
|
"epoch": 2.359072274948054,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004450584723952617,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.20097206085920333,
|
|
"num_tokens": 46881224.0,
|
|
"step": 21005
|
|
},
|
|
{
|
|
"entropy": 5.464086866378784,
|
|
"epoch": 2.3596338518560116,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004450321809202377,
|
|
"loss": 5.2225,
|
|
"mean_token_accuracy": 0.19491785615682602,
|
|
"num_tokens": 46892673.0,
|
|
"step": 21010
|
|
},
|
|
{
|
|
"entropy": 5.61196813583374,
|
|
"epoch": 2.3601954287639693,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004450058840313232,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.19576784521341323,
|
|
"num_tokens": 46902753.0,
|
|
"step": 21015
|
|
},
|
|
{
|
|
"entropy": 5.3899736404418945,
|
|
"epoch": 2.360757005671927,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044497958172935536,
|
|
"loss": 5.141,
|
|
"mean_token_accuracy": 0.20177498012781142,
|
|
"num_tokens": 46914093.0,
|
|
"step": 21020
|
|
},
|
|
{
|
|
"entropy": 5.43114595413208,
|
|
"epoch": 2.361318582579884,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004449532740151717,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.20172757655382156,
|
|
"num_tokens": 46924946.0,
|
|
"step": 21025
|
|
},
|
|
{
|
|
"entropy": 5.520503854751587,
|
|
"epoch": 2.361880159487842,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044492696088960985,
|
|
"loss": 5.2408,
|
|
"mean_token_accuracy": 0.18819108009338378,
|
|
"num_tokens": 46936756.0,
|
|
"step": 21030
|
|
},
|
|
{
|
|
"entropy": 5.565401363372803,
|
|
"epoch": 2.3624417363957995,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004449006423535078,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.1940055474638939,
|
|
"num_tokens": 46948552.0,
|
|
"step": 21035
|
|
},
|
|
{
|
|
"entropy": 5.5664534091949465,
|
|
"epoch": 2.363003313303757,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044487431840770325,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.19424073547124862,
|
|
"num_tokens": 46960926.0,
|
|
"step": 21040
|
|
},
|
|
{
|
|
"entropy": 5.513043975830078,
|
|
"epoch": 2.3635648902117143,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004448479890530347,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.1908382549881935,
|
|
"num_tokens": 46972657.0,
|
|
"step": 21045
|
|
},
|
|
{
|
|
"entropy": 5.507877779006958,
|
|
"epoch": 2.364126467119672,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044482165429034014,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19810487627983092,
|
|
"num_tokens": 46984585.0,
|
|
"step": 21050
|
|
},
|
|
{
|
|
"entropy": 5.448917198181152,
|
|
"epoch": 2.3646880440276297,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004447953141204583,
|
|
"loss": 5.2843,
|
|
"mean_token_accuracy": 0.19562765061855317,
|
|
"num_tokens": 46996052.0,
|
|
"step": 21055
|
|
},
|
|
{
|
|
"entropy": 5.554747438430786,
|
|
"epoch": 2.365249620935587,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044476896854422785,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.20150172263383864,
|
|
"num_tokens": 47006185.0,
|
|
"step": 21060
|
|
},
|
|
{
|
|
"entropy": 5.413349342346192,
|
|
"epoch": 2.3658111978435445,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044474261756248745,
|
|
"loss": 5.2366,
|
|
"mean_token_accuracy": 0.19687468260526658,
|
|
"num_tokens": 47016647.0,
|
|
"step": 21065
|
|
},
|
|
{
|
|
"entropy": 5.519910430908203,
|
|
"epoch": 2.366372774751502,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004447162611760764,
|
|
"loss": 5.2657,
|
|
"mean_token_accuracy": 0.19417359679937363,
|
|
"num_tokens": 47026847.0,
|
|
"step": 21070
|
|
},
|
|
{
|
|
"entropy": 5.518534469604492,
|
|
"epoch": 2.36693435165946,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004446898993858338,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.1910597026348114,
|
|
"num_tokens": 47037948.0,
|
|
"step": 21075
|
|
},
|
|
{
|
|
"entropy": 5.5010590076446535,
|
|
"epoch": 2.3674959285674175,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044466353219259884,
|
|
"loss": 5.1818,
|
|
"mean_token_accuracy": 0.20189837962388993,
|
|
"num_tokens": 47047751.0,
|
|
"step": 21080
|
|
},
|
|
{
|
|
"entropy": 5.451937675476074,
|
|
"epoch": 2.3680575054753747,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004446371595972114,
|
|
"loss": 5.2221,
|
|
"mean_token_accuracy": 0.19829000681638717,
|
|
"num_tokens": 47059589.0,
|
|
"step": 21085
|
|
},
|
|
{
|
|
"entropy": 5.447256231307984,
|
|
"epoch": 2.3686190823833324,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004446107816005109,
|
|
"loss": 5.2236,
|
|
"mean_token_accuracy": 0.18885500729084015,
|
|
"num_tokens": 47070060.0,
|
|
"step": 21090
|
|
},
|
|
{
|
|
"entropy": 5.600105905532837,
|
|
"epoch": 2.36918065929129,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004445843982033373,
|
|
"loss": 5.2675,
|
|
"mean_token_accuracy": 0.19616807848215104,
|
|
"num_tokens": 47081419.0,
|
|
"step": 21095
|
|
},
|
|
{
|
|
"entropy": 5.453194284439087,
|
|
"epoch": 2.3697422361992473,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004445580094065307,
|
|
"loss": 5.2262,
|
|
"mean_token_accuracy": 0.18790048360824585,
|
|
"num_tokens": 47093701.0,
|
|
"step": 21100
|
|
},
|
|
{
|
|
"entropy": 5.475658750534057,
|
|
"epoch": 2.370303813107205,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004445316152109313,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.1958961546421051,
|
|
"num_tokens": 47104930.0,
|
|
"step": 21105
|
|
},
|
|
{
|
|
"entropy": 5.491491508483887,
|
|
"epoch": 2.3708653900151626,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004445052156173796,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.1942133992910385,
|
|
"num_tokens": 47115109.0,
|
|
"step": 21110
|
|
},
|
|
{
|
|
"entropy": 5.445060586929321,
|
|
"epoch": 2.3714269669231203,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004444788106267161,
|
|
"loss": 5.1488,
|
|
"mean_token_accuracy": 0.19880614578723907,
|
|
"num_tokens": 47125386.0,
|
|
"step": 21115
|
|
},
|
|
{
|
|
"entropy": 5.477118968963623,
|
|
"epoch": 2.3719885438310775,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004444524002397815,
|
|
"loss": 5.2392,
|
|
"mean_token_accuracy": 0.19693440049886704,
|
|
"num_tokens": 47136066.0,
|
|
"step": 21120
|
|
},
|
|
{
|
|
"entropy": 5.481480121612549,
|
|
"epoch": 2.372550120739035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004444259844574167,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.1978976771235466,
|
|
"num_tokens": 47147551.0,
|
|
"step": 21125
|
|
},
|
|
{
|
|
"entropy": 5.536519575119018,
|
|
"epoch": 2.373111697646993,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044439956328046296,
|
|
"loss": 5.196,
|
|
"mean_token_accuracy": 0.2009076178073883,
|
|
"num_tokens": 47158798.0,
|
|
"step": 21130
|
|
},
|
|
{
|
|
"entropy": 5.563368082046509,
|
|
"epoch": 2.3736732745549505,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004443731367097613,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.1924091637134552,
|
|
"num_tokens": 47169519.0,
|
|
"step": 21135
|
|
},
|
|
{
|
|
"entropy": 5.464848375320434,
|
|
"epoch": 2.3742348514629077,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044434670474615334,
|
|
"loss": 5.2433,
|
|
"mean_token_accuracy": 0.19366192817687988,
|
|
"num_tokens": 47180147.0,
|
|
"step": 21140
|
|
},
|
|
{
|
|
"entropy": 5.56273307800293,
|
|
"epoch": 2.3747964283708654,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044432026739048064,
|
|
"loss": 5.2836,
|
|
"mean_token_accuracy": 0.1994415670633316,
|
|
"num_tokens": 47191832.0,
|
|
"step": 21145
|
|
},
|
|
{
|
|
"entropy": 5.4514607906341555,
|
|
"epoch": 2.375358005278823,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000444293824643585,
|
|
"loss": 5.1385,
|
|
"mean_token_accuracy": 0.20346022844314576,
|
|
"num_tokens": 47201979.0,
|
|
"step": 21150
|
|
},
|
|
{
|
|
"entropy": 5.4264881134033205,
|
|
"epoch": 2.3759195821867802,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004442673765063082,
|
|
"loss": 5.3065,
|
|
"mean_token_accuracy": 0.19660840332508087,
|
|
"num_tokens": 47212271.0,
|
|
"step": 21155
|
|
},
|
|
{
|
|
"entropy": 5.463030529022217,
|
|
"epoch": 2.376481159094738,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004442409229794925,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.1955336034297943,
|
|
"num_tokens": 47223412.0,
|
|
"step": 21160
|
|
},
|
|
{
|
|
"entropy": 5.59325385093689,
|
|
"epoch": 2.3770427360026956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004442144640639803,
|
|
"loss": 5.3547,
|
|
"mean_token_accuracy": 0.18378935754299164,
|
|
"num_tokens": 47235919.0,
|
|
"step": 21165
|
|
},
|
|
{
|
|
"entropy": 5.493078899383545,
|
|
"epoch": 2.377604312910653,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004441879997606138,
|
|
"loss": 5.2292,
|
|
"mean_token_accuracy": 0.19536023437976838,
|
|
"num_tokens": 47246568.0,
|
|
"step": 21170
|
|
},
|
|
{
|
|
"entropy": 5.541056442260742,
|
|
"epoch": 2.378165889818611,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004441615300702358,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.19025035351514816,
|
|
"num_tokens": 47259474.0,
|
|
"step": 21175
|
|
},
|
|
{
|
|
"entropy": 5.520383024215699,
|
|
"epoch": 2.378727466726568,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004441350549936891,
|
|
"loss": 5.2434,
|
|
"mean_token_accuracy": 0.19505607187747956,
|
|
"num_tokens": 47270906.0,
|
|
"step": 21180
|
|
},
|
|
{
|
|
"entropy": 5.474784994125367,
|
|
"epoch": 2.3792890436345258,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004441085745318167,
|
|
"loss": 5.3072,
|
|
"mean_token_accuracy": 0.17993776947259904,
|
|
"num_tokens": 47283341.0,
|
|
"step": 21185
|
|
},
|
|
{
|
|
"entropy": 5.5422303676605225,
|
|
"epoch": 2.3798506205424834,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044408208868546164,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.1891882225871086,
|
|
"num_tokens": 47294590.0,
|
|
"step": 21190
|
|
},
|
|
{
|
|
"entropy": 5.425589656829834,
|
|
"epoch": 2.3804121974504406,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004440555974554673,
|
|
"loss": 5.0541,
|
|
"mean_token_accuracy": 0.20189134180545806,
|
|
"num_tokens": 47305111.0,
|
|
"step": 21195
|
|
},
|
|
{
|
|
"entropy": 5.454580688476563,
|
|
"epoch": 2.3809737743583983,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044402910084267717,
|
|
"loss": 5.2398,
|
|
"mean_token_accuracy": 0.19540555626153946,
|
|
"num_tokens": 47316145.0,
|
|
"step": 21200
|
|
},
|
|
{
|
|
"entropy": 5.450255393981934,
|
|
"epoch": 2.381535351266356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004440025988479349,
|
|
"loss": 5.1566,
|
|
"mean_token_accuracy": 0.19667960107326507,
|
|
"num_tokens": 47327085.0,
|
|
"step": 21205
|
|
},
|
|
{
|
|
"entropy": 5.585201215744019,
|
|
"epoch": 2.3820969281743136,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044397609147208436,
|
|
"loss": 5.3458,
|
|
"mean_token_accuracy": 0.19394553899765016,
|
|
"num_tokens": 47338308.0,
|
|
"step": 21210
|
|
},
|
|
{
|
|
"entropy": 5.519719839096069,
|
|
"epoch": 2.382658505082271,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004439495787159695,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.19742756634950637,
|
|
"num_tokens": 47348717.0,
|
|
"step": 21215
|
|
},
|
|
{
|
|
"entropy": 5.526262712478638,
|
|
"epoch": 2.3832200819902285,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00044392306058043453,
|
|
"loss": 5.1645,
|
|
"mean_token_accuracy": 0.20380304902791976,
|
|
"num_tokens": 47359804.0,
|
|
"step": 21220
|
|
},
|
|
{
|
|
"entropy": 5.500253343582154,
|
|
"epoch": 2.383781658898186,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004438965370663238,
|
|
"loss": 5.2141,
|
|
"mean_token_accuracy": 0.18839587569236754,
|
|
"num_tokens": 47370589.0,
|
|
"step": 21225
|
|
},
|
|
{
|
|
"entropy": 5.473827648162842,
|
|
"epoch": 2.384343235806144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004438700081744819,
|
|
"loss": 5.1692,
|
|
"mean_token_accuracy": 0.20114551931619645,
|
|
"num_tokens": 47381586.0,
|
|
"step": 21230
|
|
},
|
|
{
|
|
"entropy": 5.396011638641357,
|
|
"epoch": 2.384904812714101,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044384347390575337,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.20993277281522751,
|
|
"num_tokens": 47394064.0,
|
|
"step": 21235
|
|
},
|
|
{
|
|
"entropy": 5.427327871322632,
|
|
"epoch": 2.3854663896220587,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004438169342609831,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.19744872599840163,
|
|
"num_tokens": 47405371.0,
|
|
"step": 21240
|
|
},
|
|
{
|
|
"entropy": 5.3775166988372805,
|
|
"epoch": 2.3860279665300164,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00044379038924101627,
|
|
"loss": 5.2162,
|
|
"mean_token_accuracy": 0.2044070690870285,
|
|
"num_tokens": 47416446.0,
|
|
"step": 21245
|
|
},
|
|
{
|
|
"entropy": 5.421408796310425,
|
|
"epoch": 2.3865895434379736,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004437638388466979,
|
|
"loss": 5.0799,
|
|
"mean_token_accuracy": 0.20556101351976394,
|
|
"num_tokens": 47426588.0,
|
|
"step": 21250
|
|
},
|
|
{
|
|
"entropy": 5.522669935226441,
|
|
"epoch": 2.3871511203459312,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044373728307887353,
|
|
"loss": 5.3249,
|
|
"mean_token_accuracy": 0.18979761749505997,
|
|
"num_tokens": 47438015.0,
|
|
"step": 21255
|
|
},
|
|
{
|
|
"entropy": 5.602527618408203,
|
|
"epoch": 2.387712697253889,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044371072193838857,
|
|
"loss": 5.3857,
|
|
"mean_token_accuracy": 0.18218739330768585,
|
|
"num_tokens": 47448953.0,
|
|
"step": 21260
|
|
},
|
|
{
|
|
"entropy": 5.542633724212647,
|
|
"epoch": 2.3882742741618466,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044368415542608874,
|
|
"loss": 5.2199,
|
|
"mean_token_accuracy": 0.19530655741691588,
|
|
"num_tokens": 47459669.0,
|
|
"step": 21265
|
|
},
|
|
{
|
|
"entropy": 5.576962089538574,
|
|
"epoch": 2.3888358510698042,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044365758354282005,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19372000694274902,
|
|
"num_tokens": 47471018.0,
|
|
"step": 21270
|
|
},
|
|
{
|
|
"entropy": 5.529295492172241,
|
|
"epoch": 2.3893974279777614,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004436310062894285,
|
|
"loss": 5.2385,
|
|
"mean_token_accuracy": 0.1929918959736824,
|
|
"num_tokens": 47481613.0,
|
|
"step": 21275
|
|
},
|
|
{
|
|
"entropy": 5.423281192779541,
|
|
"epoch": 2.389959004885719,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004436044236667603,
|
|
"loss": 5.1115,
|
|
"mean_token_accuracy": 0.2011592611670494,
|
|
"num_tokens": 47491245.0,
|
|
"step": 21280
|
|
},
|
|
{
|
|
"entropy": 5.464746570587158,
|
|
"epoch": 2.3905205817936768,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004435778356756618,
|
|
"loss": 5.1837,
|
|
"mean_token_accuracy": 0.20272973626852037,
|
|
"num_tokens": 47502308.0,
|
|
"step": 21285
|
|
},
|
|
{
|
|
"entropy": 5.405542612075806,
|
|
"epoch": 2.391082158701634,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044355124231697967,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.2052757441997528,
|
|
"num_tokens": 47512799.0,
|
|
"step": 21290
|
|
},
|
|
{
|
|
"entropy": 5.539104223251343,
|
|
"epoch": 2.3916437356095916,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004435246435915607,
|
|
"loss": 5.2895,
|
|
"mean_token_accuracy": 0.19562687277793883,
|
|
"num_tokens": 47524740.0,
|
|
"step": 21295
|
|
},
|
|
{
|
|
"entropy": 5.589418554306031,
|
|
"epoch": 2.3922053125175493,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004434980395002516,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.194909031689167,
|
|
"num_tokens": 47535785.0,
|
|
"step": 21300
|
|
},
|
|
{
|
|
"entropy": 5.420190477371216,
|
|
"epoch": 2.392766889425507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044347143004389955,
|
|
"loss": 5.0861,
|
|
"mean_token_accuracy": 0.20854365676641465,
|
|
"num_tokens": 47545698.0,
|
|
"step": 21305
|
|
},
|
|
{
|
|
"entropy": 5.450634098052978,
|
|
"epoch": 2.393328466333464,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004434448152233519,
|
|
"loss": 5.2823,
|
|
"mean_token_accuracy": 0.19875526279211045,
|
|
"num_tokens": 47559786.0,
|
|
"step": 21310
|
|
},
|
|
{
|
|
"entropy": 5.5024724960327145,
|
|
"epoch": 2.393890043241422,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044341819503945594,
|
|
"loss": 5.2219,
|
|
"mean_token_accuracy": 0.1948492109775543,
|
|
"num_tokens": 47570267.0,
|
|
"step": 21315
|
|
},
|
|
{
|
|
"entropy": 5.56357364654541,
|
|
"epoch": 2.3944516201493795,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004433915694930594,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.1879332423210144,
|
|
"num_tokens": 47580462.0,
|
|
"step": 21320
|
|
},
|
|
{
|
|
"entropy": 5.444331264495849,
|
|
"epoch": 2.395013197057337,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004433649385850099,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.19509102255105973,
|
|
"num_tokens": 47590651.0,
|
|
"step": 21325
|
|
},
|
|
{
|
|
"entropy": 5.599223375320435,
|
|
"epoch": 2.3955747739652944,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004433383023161555,
|
|
"loss": 5.3816,
|
|
"mean_token_accuracy": 0.19591774195432662,
|
|
"num_tokens": 47602263.0,
|
|
"step": 21330
|
|
},
|
|
{
|
|
"entropy": 5.548493528366089,
|
|
"epoch": 2.396136350873252,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004433116606873443,
|
|
"loss": 5.1901,
|
|
"mean_token_accuracy": 0.19945676922798156,
|
|
"num_tokens": 47613570.0,
|
|
"step": 21335
|
|
},
|
|
{
|
|
"entropy": 5.457400751113892,
|
|
"epoch": 2.3966979277812097,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044328501369942454,
|
|
"loss": 5.3033,
|
|
"mean_token_accuracy": 0.2000881925225258,
|
|
"num_tokens": 47624915.0,
|
|
"step": 21340
|
|
},
|
|
{
|
|
"entropy": 5.5206516742706295,
|
|
"epoch": 2.3972595046891674,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004432583613532446,
|
|
"loss": 5.1748,
|
|
"mean_token_accuracy": 0.19605326652526855,
|
|
"num_tokens": 47635974.0,
|
|
"step": 21345
|
|
},
|
|
{
|
|
"entropy": 5.46282205581665,
|
|
"epoch": 2.3978210815971246,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004432317036496533,
|
|
"loss": 5.1961,
|
|
"mean_token_accuracy": 0.19931937754154205,
|
|
"num_tokens": 47647312.0,
|
|
"step": 21350
|
|
},
|
|
{
|
|
"entropy": 5.3955224514007565,
|
|
"epoch": 2.3983826585050823,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044320504058949916,
|
|
"loss": 5.0953,
|
|
"mean_token_accuracy": 0.20052715986967087,
|
|
"num_tokens": 47659224.0,
|
|
"step": 21355
|
|
},
|
|
{
|
|
"entropy": 5.486252737045288,
|
|
"epoch": 2.39894423541304,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004431783721736314,
|
|
"loss": 5.2569,
|
|
"mean_token_accuracy": 0.19538401812314987,
|
|
"num_tokens": 47670720.0,
|
|
"step": 21360
|
|
},
|
|
{
|
|
"entropy": 5.534076833724976,
|
|
"epoch": 2.3995058123209976,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044315169840289896,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.19581218361854552,
|
|
"num_tokens": 47680646.0,
|
|
"step": 21365
|
|
},
|
|
{
|
|
"entropy": 5.573084878921509,
|
|
"epoch": 2.400067389228955,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004431250192781513,
|
|
"loss": 5.2351,
|
|
"mean_token_accuracy": 0.19655300825834274,
|
|
"num_tokens": 47692155.0,
|
|
"step": 21370
|
|
},
|
|
{
|
|
"entropy": 5.607345008850098,
|
|
"epoch": 2.4006289661369125,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004430983348002378,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.18527810722589494,
|
|
"num_tokens": 47703662.0,
|
|
"step": 21375
|
|
},
|
|
{
|
|
"entropy": 5.462613201141357,
|
|
"epoch": 2.40119054304487,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044307164497000813,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.20424878746271133,
|
|
"num_tokens": 47713617.0,
|
|
"step": 21380
|
|
},
|
|
{
|
|
"entropy": 5.422450971603394,
|
|
"epoch": 2.4017521199528273,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044304494978831204,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.2031406044960022,
|
|
"num_tokens": 47725051.0,
|
|
"step": 21385
|
|
},
|
|
{
|
|
"entropy": 5.386803388595581,
|
|
"epoch": 2.402313696860785,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004430182492559997,
|
|
"loss": 5.1121,
|
|
"mean_token_accuracy": 0.20550687462091446,
|
|
"num_tokens": 47735023.0,
|
|
"step": 21390
|
|
},
|
|
{
|
|
"entropy": 5.499993515014649,
|
|
"epoch": 2.4028752737687427,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000442991543373921,
|
|
"loss": 5.159,
|
|
"mean_token_accuracy": 0.20314977318048477,
|
|
"num_tokens": 47746252.0,
|
|
"step": 21395
|
|
},
|
|
{
|
|
"entropy": 5.453688430786133,
|
|
"epoch": 2.4034368506767003,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004429648321429264,
|
|
"loss": 5.2876,
|
|
"mean_token_accuracy": 0.1956836014986038,
|
|
"num_tokens": 47756980.0,
|
|
"step": 21400
|
|
},
|
|
{
|
|
"entropy": 5.510166168212891,
|
|
"epoch": 2.4039984275846575,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00044293811556386656,
|
|
"loss": 5.2466,
|
|
"mean_token_accuracy": 0.20114626437425615,
|
|
"num_tokens": 47767633.0,
|
|
"step": 21405
|
|
},
|
|
{
|
|
"entropy": 5.415795707702637,
|
|
"epoch": 2.404560004492615,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004429113936375918,
|
|
"loss": 5.1779,
|
|
"mean_token_accuracy": 0.19742095470428467,
|
|
"num_tokens": 47779346.0,
|
|
"step": 21410
|
|
},
|
|
{
|
|
"entropy": 5.595906972885132,
|
|
"epoch": 2.405121581400573,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00044288466636495323,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.1909156009554863,
|
|
"num_tokens": 47791039.0,
|
|
"step": 21415
|
|
},
|
|
{
|
|
"entropy": 5.510268640518189,
|
|
"epoch": 2.4056831583085305,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044285793374680184,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19424779266119002,
|
|
"num_tokens": 47802096.0,
|
|
"step": 21420
|
|
},
|
|
{
|
|
"entropy": 5.497237730026245,
|
|
"epoch": 2.4062447352164877,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044283119578398866,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.18867555409669876,
|
|
"num_tokens": 47814087.0,
|
|
"step": 21425
|
|
},
|
|
{
|
|
"entropy": 5.484153604507446,
|
|
"epoch": 2.4068063121244454,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004428044524773651,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.19594870656728744,
|
|
"num_tokens": 47824656.0,
|
|
"step": 21430
|
|
},
|
|
{
|
|
"entropy": 5.506374454498291,
|
|
"epoch": 2.407367889032403,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004427777038277827,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.2062274008989334,
|
|
"num_tokens": 47836045.0,
|
|
"step": 21435
|
|
},
|
|
{
|
|
"entropy": 5.517376136779785,
|
|
"epoch": 2.4079294659403607,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00044275094983609313,
|
|
"loss": 5.2116,
|
|
"mean_token_accuracy": 0.20062740743160248,
|
|
"num_tokens": 47846494.0,
|
|
"step": 21440
|
|
},
|
|
{
|
|
"entropy": 5.522729587554932,
|
|
"epoch": 2.408491042848318,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00044272419050314833,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19619073569774628,
|
|
"num_tokens": 47858689.0,
|
|
"step": 21445
|
|
},
|
|
{
|
|
"entropy": 5.413524580001831,
|
|
"epoch": 2.4090526197562756,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00044269742582980017,
|
|
"loss": 5.1728,
|
|
"mean_token_accuracy": 0.20289859622716905,
|
|
"num_tokens": 47870534.0,
|
|
"step": 21450
|
|
},
|
|
{
|
|
"entropy": 5.48097038269043,
|
|
"epoch": 2.4096141966642333,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000442670655816901,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.20013128966093063,
|
|
"num_tokens": 47880354.0,
|
|
"step": 21455
|
|
},
|
|
{
|
|
"entropy": 5.514699840545655,
|
|
"epoch": 2.410175773572191,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044264388046530304,
|
|
"loss": 5.2591,
|
|
"mean_token_accuracy": 0.19355914741754532,
|
|
"num_tokens": 47892528.0,
|
|
"step": 21460
|
|
},
|
|
{
|
|
"entropy": 5.56632432937622,
|
|
"epoch": 2.410737350480148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044261709977585893,
|
|
"loss": 5.3001,
|
|
"mean_token_accuracy": 0.19924210011959076,
|
|
"num_tokens": 47904653.0,
|
|
"step": 21465
|
|
},
|
|
{
|
|
"entropy": 5.561650323867798,
|
|
"epoch": 2.411298927388106,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004425903137494214,
|
|
"loss": 5.3367,
|
|
"mean_token_accuracy": 0.1930277481675148,
|
|
"num_tokens": 47916452.0,
|
|
"step": 21470
|
|
},
|
|
{
|
|
"entropy": 5.515548467636108,
|
|
"epoch": 2.4118605042960635,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004425635223868433,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.1925035908818245,
|
|
"num_tokens": 47927746.0,
|
|
"step": 21475
|
|
},
|
|
{
|
|
"entropy": 5.476244306564331,
|
|
"epoch": 2.4124220812040207,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044253672568897754,
|
|
"loss": 5.2492,
|
|
"mean_token_accuracy": 0.1888311192393303,
|
|
"num_tokens": 47941057.0,
|
|
"step": 21480
|
|
},
|
|
{
|
|
"entropy": 5.553148889541626,
|
|
"epoch": 2.4129836581119783,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004425099236566775,
|
|
"loss": 5.3057,
|
|
"mean_token_accuracy": 0.19358752965927123,
|
|
"num_tokens": 47951912.0,
|
|
"step": 21485
|
|
},
|
|
{
|
|
"entropy": 5.530198812484741,
|
|
"epoch": 2.413545235019936,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00044248311629079657,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.19864861220121383,
|
|
"num_tokens": 47963483.0,
|
|
"step": 21490
|
|
},
|
|
{
|
|
"entropy": 5.540597677230835,
|
|
"epoch": 2.4141068119278937,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004424563035921882,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.19131122082471846,
|
|
"num_tokens": 47975047.0,
|
|
"step": 21495
|
|
},
|
|
{
|
|
"entropy": 5.491515970230102,
|
|
"epoch": 2.414668388835851,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00044242948556170634,
|
|
"loss": 5.2733,
|
|
"mean_token_accuracy": 0.18972691595554353,
|
|
"num_tokens": 47986432.0,
|
|
"step": 21500
|
|
},
|
|
{
|
|
"entropy": 5.5090508460998535,
|
|
"epoch": 2.4152299657438085,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044240266220020455,
|
|
"loss": 5.1838,
|
|
"mean_token_accuracy": 0.20027952790260314,
|
|
"num_tokens": 47997283.0,
|
|
"step": 21505
|
|
},
|
|
{
|
|
"entropy": 5.485702848434448,
|
|
"epoch": 2.415791542651766,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004423758335085371,
|
|
"loss": 5.2019,
|
|
"mean_token_accuracy": 0.19218785017728807,
|
|
"num_tokens": 48008353.0,
|
|
"step": 21510
|
|
},
|
|
{
|
|
"entropy": 5.457153701782227,
|
|
"epoch": 2.416353119559724,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00044234899948755827,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.19480863064527512,
|
|
"num_tokens": 48020065.0,
|
|
"step": 21515
|
|
},
|
|
{
|
|
"entropy": 5.498120260238648,
|
|
"epoch": 2.416914696467681,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00044232216013812226,
|
|
"loss": 5.2557,
|
|
"mean_token_accuracy": 0.1956646963953972,
|
|
"num_tokens": 48030062.0,
|
|
"step": 21520
|
|
},
|
|
{
|
|
"entropy": 5.4554990291595455,
|
|
"epoch": 2.4174762733756388,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004422953154610838,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19674865156412125,
|
|
"num_tokens": 48039639.0,
|
|
"step": 21525
|
|
},
|
|
{
|
|
"entropy": 5.4476526260375975,
|
|
"epoch": 2.4180378502835964,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004422684654572977,
|
|
"loss": 5.2623,
|
|
"mean_token_accuracy": 0.19530128836631774,
|
|
"num_tokens": 48050428.0,
|
|
"step": 21530
|
|
},
|
|
{
|
|
"entropy": 5.519549036026001,
|
|
"epoch": 2.418599427191554,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044224161012761874,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.19438917487859725,
|
|
"num_tokens": 48061214.0,
|
|
"step": 21535
|
|
},
|
|
{
|
|
"entropy": 5.448067378997803,
|
|
"epoch": 2.4191610040995113,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044221474947290205,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.20043330192565917,
|
|
"num_tokens": 48071983.0,
|
|
"step": 21540
|
|
},
|
|
{
|
|
"entropy": 5.426343011856079,
|
|
"epoch": 2.419722581007469,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004421878834940029,
|
|
"loss": 5.1417,
|
|
"mean_token_accuracy": 0.2005408450961113,
|
|
"num_tokens": 48083411.0,
|
|
"step": 21545
|
|
},
|
|
{
|
|
"entropy": 5.5195025444030765,
|
|
"epoch": 2.4202841579154266,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044216101219177667,
|
|
"loss": 5.2333,
|
|
"mean_token_accuracy": 0.19034329652786255,
|
|
"num_tokens": 48094718.0,
|
|
"step": 21550
|
|
},
|
|
{
|
|
"entropy": 5.530328702926636,
|
|
"epoch": 2.4208457348233843,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00044213413556707905,
|
|
"loss": 5.2538,
|
|
"mean_token_accuracy": 0.19498222321271896,
|
|
"num_tokens": 48106663.0,
|
|
"step": 21555
|
|
},
|
|
{
|
|
"entropy": 5.518128871917725,
|
|
"epoch": 2.4214073117313415,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004421072536207656,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.19572851359844207,
|
|
"num_tokens": 48117232.0,
|
|
"step": 21560
|
|
},
|
|
{
|
|
"entropy": 5.5183123588562015,
|
|
"epoch": 2.421968888639299,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044208036635369247,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.19860711991786956,
|
|
"num_tokens": 48128817.0,
|
|
"step": 21565
|
|
},
|
|
{
|
|
"entropy": 5.493495988845825,
|
|
"epoch": 2.422530465547257,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004420534737667157,
|
|
"loss": 5.2104,
|
|
"mean_token_accuracy": 0.20324168652296065,
|
|
"num_tokens": 48140893.0,
|
|
"step": 21570
|
|
},
|
|
{
|
|
"entropy": 5.402607107162476,
|
|
"epoch": 2.423092042455214,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044202657586069153,
|
|
"loss": 5.0877,
|
|
"mean_token_accuracy": 0.19762112498283385,
|
|
"num_tokens": 48152661.0,
|
|
"step": 21575
|
|
},
|
|
{
|
|
"entropy": 5.460731887817383,
|
|
"epoch": 2.4236536193631717,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044199967263647635,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.20158560425043107,
|
|
"num_tokens": 48163342.0,
|
|
"step": 21580
|
|
},
|
|
{
|
|
"entropy": 5.507939004898072,
|
|
"epoch": 2.4242151962711294,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004419727640949268,
|
|
"loss": 5.2503,
|
|
"mean_token_accuracy": 0.19469637274742127,
|
|
"num_tokens": 48175321.0,
|
|
"step": 21585
|
|
},
|
|
{
|
|
"entropy": 5.5556775569915775,
|
|
"epoch": 2.424776773179087,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004419458502368998,
|
|
"loss": 5.2779,
|
|
"mean_token_accuracy": 0.19253599643707275,
|
|
"num_tokens": 48186847.0,
|
|
"step": 21590
|
|
},
|
|
{
|
|
"entropy": 5.559316158294678,
|
|
"epoch": 2.4253383500870442,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044191893106325207,
|
|
"loss": 5.358,
|
|
"mean_token_accuracy": 0.1967461735010147,
|
|
"num_tokens": 48198840.0,
|
|
"step": 21595
|
|
},
|
|
{
|
|
"entropy": 5.556084632873535,
|
|
"epoch": 2.425899926995002,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004418920065748409,
|
|
"loss": 5.3298,
|
|
"mean_token_accuracy": 0.18928238451480867,
|
|
"num_tokens": 48209948.0,
|
|
"step": 21600
|
|
},
|
|
{
|
|
"entropy": 5.502374172210693,
|
|
"epoch": 2.4264615039029596,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00044186507677252345,
|
|
"loss": 5.2266,
|
|
"mean_token_accuracy": 0.19897107928991317,
|
|
"num_tokens": 48220125.0,
|
|
"step": 21605
|
|
},
|
|
{
|
|
"entropy": 5.425529432296753,
|
|
"epoch": 2.427023080810917,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004418381416571573,
|
|
"loss": 5.2105,
|
|
"mean_token_accuracy": 0.19947573840618132,
|
|
"num_tokens": 48230736.0,
|
|
"step": 21610
|
|
},
|
|
{
|
|
"entropy": 5.368519067764282,
|
|
"epoch": 2.4275846577188744,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004418112012296,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.20598108619451522,
|
|
"num_tokens": 48241387.0,
|
|
"step": 21615
|
|
},
|
|
{
|
|
"entropy": 5.50252480506897,
|
|
"epoch": 2.428146234626832,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044178425549070934,
|
|
"loss": 5.2166,
|
|
"mean_token_accuracy": 0.19301272928714752,
|
|
"num_tokens": 48252279.0,
|
|
"step": 21620
|
|
},
|
|
{
|
|
"entropy": 5.524114513397217,
|
|
"epoch": 2.4287078115347898,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044175730444134326,
|
|
"loss": 5.2425,
|
|
"mean_token_accuracy": 0.20094775706529616,
|
|
"num_tokens": 48264235.0,
|
|
"step": 21625
|
|
},
|
|
{
|
|
"entropy": 5.456684589385986,
|
|
"epoch": 2.4292693884427474,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044173034808236,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20560645014047624,
|
|
"num_tokens": 48276194.0,
|
|
"step": 21630
|
|
},
|
|
{
|
|
"entropy": 5.516948175430298,
|
|
"epoch": 2.4298309653507046,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004417033864146177,
|
|
"loss": 5.2848,
|
|
"mean_token_accuracy": 0.1990938276052475,
|
|
"num_tokens": 48287129.0,
|
|
"step": 21635
|
|
},
|
|
{
|
|
"entropy": 5.4332022190094,
|
|
"epoch": 2.4303925422586623,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004416764194389751,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.19491759091615676,
|
|
"num_tokens": 48298850.0,
|
|
"step": 21640
|
|
},
|
|
{
|
|
"entropy": 5.5072966575622555,
|
|
"epoch": 2.43095411916662,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004416494471562904,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.19354665130376816,
|
|
"num_tokens": 48309968.0,
|
|
"step": 21645
|
|
},
|
|
{
|
|
"entropy": 5.532361745834351,
|
|
"epoch": 2.4315156960745776,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004416224695674229,
|
|
"loss": 5.2045,
|
|
"mean_token_accuracy": 0.1981761321425438,
|
|
"num_tokens": 48320419.0,
|
|
"step": 21650
|
|
},
|
|
{
|
|
"entropy": 5.492864370346069,
|
|
"epoch": 2.432077272982535,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044159548667323126,
|
|
"loss": 5.263,
|
|
"mean_token_accuracy": 0.19223702996969222,
|
|
"num_tokens": 48332611.0,
|
|
"step": 21655
|
|
},
|
|
{
|
|
"entropy": 5.422542572021484,
|
|
"epoch": 2.4326388498904925,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004415684984745747,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.20083368718624114,
|
|
"num_tokens": 48344551.0,
|
|
"step": 21660
|
|
},
|
|
{
|
|
"entropy": 5.560600900650025,
|
|
"epoch": 2.43320042679845,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004415415049723126,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.19467189460992812,
|
|
"num_tokens": 48355142.0,
|
|
"step": 21665
|
|
},
|
|
{
|
|
"entropy": 5.484954690933227,
|
|
"epoch": 2.4337620037064074,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004415145061673043,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.20208345651626586,
|
|
"num_tokens": 48367342.0,
|
|
"step": 21670
|
|
},
|
|
{
|
|
"entropy": 5.536007976531982,
|
|
"epoch": 2.434323580614365,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004414875020604096,
|
|
"loss": 5.2734,
|
|
"mean_token_accuracy": 0.1955319434404373,
|
|
"num_tokens": 48378608.0,
|
|
"step": 21675
|
|
},
|
|
{
|
|
"entropy": 5.528318786621094,
|
|
"epoch": 2.4348851575223227,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004414604926524882,
|
|
"loss": 5.2618,
|
|
"mean_token_accuracy": 0.1972230389714241,
|
|
"num_tokens": 48390455.0,
|
|
"step": 21680
|
|
},
|
|
{
|
|
"entropy": 5.520149040222168,
|
|
"epoch": 2.4354467344302804,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004414334779444002,
|
|
"loss": 5.2264,
|
|
"mean_token_accuracy": 0.19478745460510255,
|
|
"num_tokens": 48401723.0,
|
|
"step": 21685
|
|
},
|
|
{
|
|
"entropy": 5.464621114730835,
|
|
"epoch": 2.4360083113382376,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044140645793700573,
|
|
"loss": 5.2518,
|
|
"mean_token_accuracy": 0.19090061038732528,
|
|
"num_tokens": 48414208.0,
|
|
"step": 21690
|
|
},
|
|
{
|
|
"entropy": 5.455954694747925,
|
|
"epoch": 2.4365698882461952,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00044137943263116515,
|
|
"loss": 5.2406,
|
|
"mean_token_accuracy": 0.19552295356988908,
|
|
"num_tokens": 48425978.0,
|
|
"step": 21695
|
|
},
|
|
{
|
|
"entropy": 5.474641990661621,
|
|
"epoch": 2.437131465154153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004413524020277388,
|
|
"loss": 5.1171,
|
|
"mean_token_accuracy": 0.20493845492601395,
|
|
"num_tokens": 48435988.0,
|
|
"step": 21700
|
|
},
|
|
{
|
|
"entropy": 5.513007259368896,
|
|
"epoch": 2.4376930420621106,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004413253661275875,
|
|
"loss": 5.2081,
|
|
"mean_token_accuracy": 0.1943923771381378,
|
|
"num_tokens": 48447217.0,
|
|
"step": 21705
|
|
},
|
|
{
|
|
"entropy": 5.420240354537964,
|
|
"epoch": 2.438254618970068,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044129832493157195,
|
|
"loss": 5.2651,
|
|
"mean_token_accuracy": 0.19560905247926713,
|
|
"num_tokens": 48458597.0,
|
|
"step": 21710
|
|
},
|
|
{
|
|
"entropy": 5.433232212066651,
|
|
"epoch": 2.4388161958780255,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044127127844055335,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.19780569523572922,
|
|
"num_tokens": 48470601.0,
|
|
"step": 21715
|
|
},
|
|
{
|
|
"entropy": 5.518121957778931,
|
|
"epoch": 2.439377772785983,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00044124422665539273,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.19458672553300857,
|
|
"num_tokens": 48481570.0,
|
|
"step": 21720
|
|
},
|
|
{
|
|
"entropy": 5.5503076076507565,
|
|
"epoch": 2.4399393496939408,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004412171695769515,
|
|
"loss": 5.3561,
|
|
"mean_token_accuracy": 0.19012211114168168,
|
|
"num_tokens": 48492146.0,
|
|
"step": 21725
|
|
},
|
|
{
|
|
"entropy": 5.504344654083252,
|
|
"epoch": 2.440500926601898,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044119010720609106,
|
|
"loss": 5.2371,
|
|
"mean_token_accuracy": 0.19248204082250595,
|
|
"num_tokens": 48504644.0,
|
|
"step": 21730
|
|
},
|
|
{
|
|
"entropy": 5.431183099746704,
|
|
"epoch": 2.4410625035098557,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044116303954367314,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.19745306223630904,
|
|
"num_tokens": 48516405.0,
|
|
"step": 21735
|
|
},
|
|
{
|
|
"entropy": 5.454683303833008,
|
|
"epoch": 2.4416240804178133,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004411359665905596,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.19344245344400407,
|
|
"num_tokens": 48528759.0,
|
|
"step": 21740
|
|
},
|
|
{
|
|
"entropy": 5.619750022888184,
|
|
"epoch": 2.442185657325771,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004411088883476125,
|
|
"loss": 5.3474,
|
|
"mean_token_accuracy": 0.18947906345129012,
|
|
"num_tokens": 48540731.0,
|
|
"step": 21745
|
|
},
|
|
{
|
|
"entropy": 5.5042966365814205,
|
|
"epoch": 2.442747234233728,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044108180481569387,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.19606222957372665,
|
|
"num_tokens": 48553642.0,
|
|
"step": 21750
|
|
},
|
|
{
|
|
"entropy": 5.585408496856689,
|
|
"epoch": 2.443308811141686,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00044105471599566626,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.19546174108982087,
|
|
"num_tokens": 48564596.0,
|
|
"step": 21755
|
|
},
|
|
{
|
|
"entropy": 5.53160548210144,
|
|
"epoch": 2.4438703880496435,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000441027621888392,
|
|
"loss": 5.282,
|
|
"mean_token_accuracy": 0.19303430169820784,
|
|
"num_tokens": 48574521.0,
|
|
"step": 21760
|
|
},
|
|
{
|
|
"entropy": 5.49158034324646,
|
|
"epoch": 2.4444319649576007,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044100052249473393,
|
|
"loss": 5.1375,
|
|
"mean_token_accuracy": 0.1974743753671646,
|
|
"num_tokens": 48586299.0,
|
|
"step": 21765
|
|
},
|
|
{
|
|
"entropy": 5.520669460296631,
|
|
"epoch": 2.4449935418655584,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004409734178155548,
|
|
"loss": 5.293,
|
|
"mean_token_accuracy": 0.1982475608587265,
|
|
"num_tokens": 48598366.0,
|
|
"step": 21770
|
|
},
|
|
{
|
|
"entropy": 5.451089477539062,
|
|
"epoch": 2.445555118773516,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004409463078517178,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.19114981591701508,
|
|
"num_tokens": 48609659.0,
|
|
"step": 21775
|
|
},
|
|
{
|
|
"entropy": 5.440776395797729,
|
|
"epoch": 2.4461166956814737,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00044091919260408585,
|
|
"loss": 5.1755,
|
|
"mean_token_accuracy": 0.20494567602872849,
|
|
"num_tokens": 48621623.0,
|
|
"step": 21780
|
|
},
|
|
{
|
|
"entropy": 5.443853855133057,
|
|
"epoch": 2.446678272589431,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004408920720735225,
|
|
"loss": 5.1328,
|
|
"mean_token_accuracy": 0.1953444629907608,
|
|
"num_tokens": 48632711.0,
|
|
"step": 21785
|
|
},
|
|
{
|
|
"entropy": 5.446401357650757,
|
|
"epoch": 2.4472398494973886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044086494626089127,
|
|
"loss": 5.2388,
|
|
"mean_token_accuracy": 0.19931987673044205,
|
|
"num_tokens": 48644518.0,
|
|
"step": 21790
|
|
},
|
|
{
|
|
"entropy": 5.503153371810913,
|
|
"epoch": 2.4478014264053463,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004408378151670558,
|
|
"loss": 5.234,
|
|
"mean_token_accuracy": 0.1950480595231056,
|
|
"num_tokens": 48655261.0,
|
|
"step": 21795
|
|
},
|
|
{
|
|
"entropy": 5.4616669654846195,
|
|
"epoch": 2.448363003313304,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044081067879288,
|
|
"loss": 5.182,
|
|
"mean_token_accuracy": 0.20600211769342422,
|
|
"num_tokens": 48666701.0,
|
|
"step": 21800
|
|
},
|
|
{
|
|
"entropy": 5.393737173080444,
|
|
"epoch": 2.448924580221261,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004407835371392279,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.2042812541127205,
|
|
"num_tokens": 48677919.0,
|
|
"step": 21805
|
|
},
|
|
{
|
|
"entropy": 5.437156534194946,
|
|
"epoch": 2.449486157129219,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004407563902069636,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.20266277641057967,
|
|
"num_tokens": 48688680.0,
|
|
"step": 21810
|
|
},
|
|
{
|
|
"entropy": 5.581361913681031,
|
|
"epoch": 2.4500477340371765,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004407292379969515,
|
|
"loss": 5.2321,
|
|
"mean_token_accuracy": 0.19590559005737304,
|
|
"num_tokens": 48701149.0,
|
|
"step": 21815
|
|
},
|
|
{
|
|
"entropy": 5.481720590591431,
|
|
"epoch": 2.450609310945134,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004407020805100563,
|
|
"loss": 5.1986,
|
|
"mean_token_accuracy": 0.19855584055185319,
|
|
"num_tokens": 48712236.0,
|
|
"step": 21820
|
|
},
|
|
{
|
|
"entropy": 5.429324436187744,
|
|
"epoch": 2.4511708878530913,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004406749177471425,
|
|
"loss": 5.1781,
|
|
"mean_token_accuracy": 0.2043123722076416,
|
|
"num_tokens": 48723923.0,
|
|
"step": 21825
|
|
},
|
|
{
|
|
"entropy": 5.401499509811401,
|
|
"epoch": 2.451732464761049,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00044064774970907516,
|
|
"loss": 5.1662,
|
|
"mean_token_accuracy": 0.2007371261715889,
|
|
"num_tokens": 48734925.0,
|
|
"step": 21830
|
|
},
|
|
{
|
|
"entropy": 5.448246908187866,
|
|
"epoch": 2.4522940416690067,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004406205763967193,
|
|
"loss": 5.1414,
|
|
"mean_token_accuracy": 0.20274387747049333,
|
|
"num_tokens": 48745758.0,
|
|
"step": 21835
|
|
},
|
|
{
|
|
"entropy": 5.3940142631530765,
|
|
"epoch": 2.4528556185769643,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004405933978109398,
|
|
"loss": 5.1548,
|
|
"mean_token_accuracy": 0.19916909784078599,
|
|
"num_tokens": 48756899.0,
|
|
"step": 21840
|
|
},
|
|
{
|
|
"entropy": 5.549937057495117,
|
|
"epoch": 2.4534171954849215,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00044056621395260247,
|
|
"loss": 5.2053,
|
|
"mean_token_accuracy": 0.19821321666240693,
|
|
"num_tokens": 48766805.0,
|
|
"step": 21845
|
|
},
|
|
{
|
|
"entropy": 5.526492357254028,
|
|
"epoch": 2.453978772392879,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044053902482257265,
|
|
"loss": 5.2509,
|
|
"mean_token_accuracy": 0.19965972155332565,
|
|
"num_tokens": 48779360.0,
|
|
"step": 21850
|
|
},
|
|
{
|
|
"entropy": 5.402393865585327,
|
|
"epoch": 2.454540349300837,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000440511830421716,
|
|
"loss": 5.1938,
|
|
"mean_token_accuracy": 0.19895824939012527,
|
|
"num_tokens": 48789836.0,
|
|
"step": 21855
|
|
},
|
|
{
|
|
"entropy": 5.456653165817261,
|
|
"epoch": 2.455101926208794,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004404846307508985,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.19544985592365266,
|
|
"num_tokens": 48801327.0,
|
|
"step": 21860
|
|
},
|
|
{
|
|
"entropy": 5.4749589443206785,
|
|
"epoch": 2.4556635031167517,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044045742581098624,
|
|
"loss": 5.1676,
|
|
"mean_token_accuracy": 0.2029585748910904,
|
|
"num_tokens": 48812521.0,
|
|
"step": 21865
|
|
},
|
|
{
|
|
"entropy": 5.440296220779419,
|
|
"epoch": 2.4562250800247094,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004404302156028453,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19861945807933806,
|
|
"num_tokens": 48824068.0,
|
|
"step": 21870
|
|
},
|
|
{
|
|
"entropy": 5.455506658554077,
|
|
"epoch": 2.456786656932667,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00044040300012734217,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19641304910182952,
|
|
"num_tokens": 48835183.0,
|
|
"step": 21875
|
|
},
|
|
{
|
|
"entropy": 5.503249216079712,
|
|
"epoch": 2.4573482338406243,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004403757793853434,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.1993090346455574,
|
|
"num_tokens": 48846616.0,
|
|
"step": 21880
|
|
},
|
|
{
|
|
"entropy": 5.474939203262329,
|
|
"epoch": 2.457909810748582,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004403485533777157,
|
|
"loss": 5.2493,
|
|
"mean_token_accuracy": 0.19547254145145415,
|
|
"num_tokens": 48858159.0,
|
|
"step": 21885
|
|
},
|
|
{
|
|
"entropy": 5.471838331222534,
|
|
"epoch": 2.4584713876565396,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004403213221053258,
|
|
"loss": 5.156,
|
|
"mean_token_accuracy": 0.19919808357954025,
|
|
"num_tokens": 48870363.0,
|
|
"step": 21890
|
|
},
|
|
{
|
|
"entropy": 5.5084303855896,
|
|
"epoch": 2.4590329645644973,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00044029408556904093,
|
|
"loss": 5.2841,
|
|
"mean_token_accuracy": 0.19388862252235411,
|
|
"num_tokens": 48882036.0,
|
|
"step": 21895
|
|
},
|
|
{
|
|
"entropy": 5.5480055809021,
|
|
"epoch": 2.4595945414724545,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004402668437697283,
|
|
"loss": 5.2374,
|
|
"mean_token_accuracy": 0.1989890679717064,
|
|
"num_tokens": 48893741.0,
|
|
"step": 21900
|
|
},
|
|
{
|
|
"entropy": 5.598579454421997,
|
|
"epoch": 2.460156118380412,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00044023959670825533,
|
|
"loss": 5.3272,
|
|
"mean_token_accuracy": 0.19219182282686234,
|
|
"num_tokens": 48906260.0,
|
|
"step": 21905
|
|
},
|
|
{
|
|
"entropy": 5.539308643341064,
|
|
"epoch": 2.46071769528837,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004402123443854894,
|
|
"loss": 5.2898,
|
|
"mean_token_accuracy": 0.1885729804635048,
|
|
"num_tokens": 48918078.0,
|
|
"step": 21910
|
|
},
|
|
{
|
|
"entropy": 5.5052672863006595,
|
|
"epoch": 2.4612792721963275,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004401850868022984,
|
|
"loss": 5.2218,
|
|
"mean_token_accuracy": 0.19678765535354614,
|
|
"num_tokens": 48928999.0,
|
|
"step": 21915
|
|
},
|
|
{
|
|
"entropy": 5.416975498199463,
|
|
"epoch": 2.4618408491042847,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004401578239595501,
|
|
"loss": 5.1742,
|
|
"mean_token_accuracy": 0.1949933648109436,
|
|
"num_tokens": 48940587.0,
|
|
"step": 21920
|
|
},
|
|
{
|
|
"entropy": 5.497702646255493,
|
|
"epoch": 2.4624024260122424,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044013055585811274,
|
|
"loss": 5.3201,
|
|
"mean_token_accuracy": 0.20022241175174713,
|
|
"num_tokens": 48951632.0,
|
|
"step": 21925
|
|
},
|
|
{
|
|
"entropy": 5.562156629562378,
|
|
"epoch": 2.4629640029202,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00044010328249885434,
|
|
"loss": 5.3822,
|
|
"mean_token_accuracy": 0.19013552814722062,
|
|
"num_tokens": 48963578.0,
|
|
"step": 21930
|
|
},
|
|
{
|
|
"entropy": 5.535305786132812,
|
|
"epoch": 2.4635255798281577,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004400760038826434,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.1952902689576149,
|
|
"num_tokens": 48974690.0,
|
|
"step": 21935
|
|
},
|
|
{
|
|
"entropy": 5.546695280075073,
|
|
"epoch": 2.464087156736115,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044004872001034856,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.19494616836309434,
|
|
"num_tokens": 48985871.0,
|
|
"step": 21940
|
|
},
|
|
{
|
|
"entropy": 5.396793842315674,
|
|
"epoch": 2.4646487336440726,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004400214308828384,
|
|
"loss": 5.1194,
|
|
"mean_token_accuracy": 0.20670516341924666,
|
|
"num_tokens": 48996475.0,
|
|
"step": 21945
|
|
},
|
|
{
|
|
"entropy": 5.518781328201294,
|
|
"epoch": 2.46521031055203,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043999413650098193,
|
|
"loss": 5.3228,
|
|
"mean_token_accuracy": 0.19987118542194365,
|
|
"num_tokens": 49008900.0,
|
|
"step": 21950
|
|
},
|
|
{
|
|
"entropy": 5.402926635742188,
|
|
"epoch": 2.4657718874599874,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004399668368656481,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.19909583330154418,
|
|
"num_tokens": 49020583.0,
|
|
"step": 21955
|
|
},
|
|
{
|
|
"entropy": 5.582782888412476,
|
|
"epoch": 2.466333464367945,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004399395319777062,
|
|
"loss": 5.3079,
|
|
"mean_token_accuracy": 0.18775818645954132,
|
|
"num_tokens": 49031363.0,
|
|
"step": 21960
|
|
},
|
|
{
|
|
"entropy": 5.449003887176514,
|
|
"epoch": 2.4668950412759028,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00043991222183802564,
|
|
"loss": 5.2699,
|
|
"mean_token_accuracy": 0.1990089401602745,
|
|
"num_tokens": 49043404.0,
|
|
"step": 21965
|
|
},
|
|
{
|
|
"entropy": 5.524685192108154,
|
|
"epoch": 2.4674566181838604,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000439884906447476,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.19461162090301515,
|
|
"num_tokens": 49054240.0,
|
|
"step": 21970
|
|
},
|
|
{
|
|
"entropy": 5.465969228744507,
|
|
"epoch": 2.4680181950918176,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000439857585806927,
|
|
"loss": 5.1123,
|
|
"mean_token_accuracy": 0.20583287477493287,
|
|
"num_tokens": 49064730.0,
|
|
"step": 21975
|
|
},
|
|
{
|
|
"entropy": 5.488947916030884,
|
|
"epoch": 2.4685797719997753,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043983025991724847,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.1950748696923256,
|
|
"num_tokens": 49075218.0,
|
|
"step": 21980
|
|
},
|
|
{
|
|
"entropy": 5.429767799377442,
|
|
"epoch": 2.469141348907733,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004398029287793106,
|
|
"loss": 5.1849,
|
|
"mean_token_accuracy": 0.20527995377779007,
|
|
"num_tokens": 49086182.0,
|
|
"step": 21985
|
|
},
|
|
{
|
|
"entropy": 5.512212419509888,
|
|
"epoch": 2.4697029258156906,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00043977559239398353,
|
|
"loss": 5.2979,
|
|
"mean_token_accuracy": 0.18575209975242615,
|
|
"num_tokens": 49099054.0,
|
|
"step": 21990
|
|
},
|
|
{
|
|
"entropy": 5.44070782661438,
|
|
"epoch": 2.470264502723648,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004397482507621376,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.202835313975811,
|
|
"num_tokens": 49110234.0,
|
|
"step": 21995
|
|
},
|
|
{
|
|
"entropy": 5.4816113948822025,
|
|
"epoch": 2.4708260796316055,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004397209038846436,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.1962631091475487,
|
|
"num_tokens": 49121884.0,
|
|
"step": 22000
|
|
},
|
|
{
|
|
"entropy": 5.457414340972901,
|
|
"epoch": 2.471387656539563,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00043969355176237207,
|
|
"loss": 5.162,
|
|
"mean_token_accuracy": 0.19944817572832108,
|
|
"num_tokens": 49133491.0,
|
|
"step": 22005
|
|
},
|
|
{
|
|
"entropy": 5.354421472549438,
|
|
"epoch": 2.471949233447521,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004396661943961941,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.19419801980257034,
|
|
"num_tokens": 49145895.0,
|
|
"step": 22010
|
|
},
|
|
{
|
|
"entropy": 5.5534432888031,
|
|
"epoch": 2.472510810355478,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004396388317869805,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.19617827087640763,
|
|
"num_tokens": 49157840.0,
|
|
"step": 22015
|
|
},
|
|
{
|
|
"entropy": 5.517497444152832,
|
|
"epoch": 2.4730723872634357,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004396114639356027,
|
|
"loss": 5.2347,
|
|
"mean_token_accuracy": 0.20043074786663057,
|
|
"num_tokens": 49170391.0,
|
|
"step": 22020
|
|
},
|
|
{
|
|
"entropy": 5.500590181350708,
|
|
"epoch": 2.4736339641713934,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000439584090842932,
|
|
"loss": 5.2043,
|
|
"mean_token_accuracy": 0.19255265295505525,
|
|
"num_tokens": 49181721.0,
|
|
"step": 22025
|
|
},
|
|
{
|
|
"entropy": 5.467894172668457,
|
|
"epoch": 2.474195541079351,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043955671250984005,
|
|
"loss": 5.2258,
|
|
"mean_token_accuracy": 0.20247261673212053,
|
|
"num_tokens": 49192137.0,
|
|
"step": 22030
|
|
},
|
|
{
|
|
"entropy": 5.551994466781617,
|
|
"epoch": 2.4747571179873082,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043952932893719847,
|
|
"loss": 5.2806,
|
|
"mean_token_accuracy": 0.1997486874461174,
|
|
"num_tokens": 49203260.0,
|
|
"step": 22035
|
|
},
|
|
{
|
|
"entropy": 5.4645326137542725,
|
|
"epoch": 2.475318694895266,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004395019401258794,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.20555262565612792,
|
|
"num_tokens": 49214799.0,
|
|
"step": 22040
|
|
},
|
|
{
|
|
"entropy": 5.408935832977295,
|
|
"epoch": 2.4758802718032236,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043947454607675464,
|
|
"loss": 5.1336,
|
|
"mean_token_accuracy": 0.20279794782400132,
|
|
"num_tokens": 49224595.0,
|
|
"step": 22045
|
|
},
|
|
{
|
|
"entropy": 5.476183938980102,
|
|
"epoch": 2.476441848711181,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004394471467906966,
|
|
"loss": 5.2192,
|
|
"mean_token_accuracy": 0.1996673434972763,
|
|
"num_tokens": 49235190.0,
|
|
"step": 22050
|
|
},
|
|
{
|
|
"entropy": 5.458039617538452,
|
|
"epoch": 2.4770034256191384,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043941974226857763,
|
|
"loss": 5.177,
|
|
"mean_token_accuracy": 0.20072853714227676,
|
|
"num_tokens": 49247103.0,
|
|
"step": 22055
|
|
},
|
|
{
|
|
"entropy": 5.536229753494263,
|
|
"epoch": 2.477565002527096,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004393923325112702,
|
|
"loss": 5.2737,
|
|
"mean_token_accuracy": 0.194827401638031,
|
|
"num_tokens": 49259874.0,
|
|
"step": 22060
|
|
},
|
|
{
|
|
"entropy": 5.355350112915039,
|
|
"epoch": 2.4781265794350538,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004393649175196472,
|
|
"loss": 5.1011,
|
|
"mean_token_accuracy": 0.20494270622730254,
|
|
"num_tokens": 49271059.0,
|
|
"step": 22065
|
|
},
|
|
{
|
|
"entropy": 5.435387372970581,
|
|
"epoch": 2.478688156343011,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004393374972945815,
|
|
"loss": 5.1023,
|
|
"mean_token_accuracy": 0.20523943603038788,
|
|
"num_tokens": 49283142.0,
|
|
"step": 22070
|
|
},
|
|
{
|
|
"entropy": 5.486760759353638,
|
|
"epoch": 2.4792497332509686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043931007183694616,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.19835471361875534,
|
|
"num_tokens": 49294022.0,
|
|
"step": 22075
|
|
},
|
|
{
|
|
"entropy": 5.4334940910339355,
|
|
"epoch": 2.4798113101589263,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00043928264114761437,
|
|
"loss": 5.2215,
|
|
"mean_token_accuracy": 0.19473174214363098,
|
|
"num_tokens": 49305849.0,
|
|
"step": 22080
|
|
},
|
|
{
|
|
"entropy": 5.467838001251221,
|
|
"epoch": 2.480372887066884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043925520522745953,
|
|
"loss": 5.2021,
|
|
"mean_token_accuracy": 0.1971364736557007,
|
|
"num_tokens": 49316957.0,
|
|
"step": 22085
|
|
},
|
|
{
|
|
"entropy": 5.497506999969483,
|
|
"epoch": 2.480934463974841,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004392277640773553,
|
|
"loss": 5.1946,
|
|
"mean_token_accuracy": 0.1969035178422928,
|
|
"num_tokens": 49329040.0,
|
|
"step": 22090
|
|
},
|
|
{
|
|
"entropy": 5.436862421035767,
|
|
"epoch": 2.481496040882799,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043920031769817543,
|
|
"loss": 5.2173,
|
|
"mean_token_accuracy": 0.2030940383672714,
|
|
"num_tokens": 49340037.0,
|
|
"step": 22095
|
|
},
|
|
{
|
|
"entropy": 5.427388000488281,
|
|
"epoch": 2.4820576177907565,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043917286609079364,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.19302205890417098,
|
|
"num_tokens": 49350059.0,
|
|
"step": 22100
|
|
},
|
|
{
|
|
"entropy": 5.444481039047242,
|
|
"epoch": 2.482619194698714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043914540925608426,
|
|
"loss": 5.1843,
|
|
"mean_token_accuracy": 0.2037918597459793,
|
|
"num_tokens": 49360880.0,
|
|
"step": 22105
|
|
},
|
|
{
|
|
"entropy": 5.5321861743927006,
|
|
"epoch": 2.4831807716066714,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004391179471949213,
|
|
"loss": 5.1575,
|
|
"mean_token_accuracy": 0.20265304446220397,
|
|
"num_tokens": 49370725.0,
|
|
"step": 22110
|
|
},
|
|
{
|
|
"entropy": 5.43274884223938,
|
|
"epoch": 2.483742348514629,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043909047990817917,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.19689952284097673,
|
|
"num_tokens": 49380991.0,
|
|
"step": 22115
|
|
},
|
|
{
|
|
"entropy": 5.361147928237915,
|
|
"epoch": 2.4843039254225867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043906300739673265,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.19945039600133896,
|
|
"num_tokens": 49390802.0,
|
|
"step": 22120
|
|
},
|
|
{
|
|
"entropy": 5.522245788574219,
|
|
"epoch": 2.4848655023305444,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043903552966145624,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.20141389816999436,
|
|
"num_tokens": 49401507.0,
|
|
"step": 22125
|
|
},
|
|
{
|
|
"entropy": 5.489225816726685,
|
|
"epoch": 2.4854270792385016,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000439008046703225,
|
|
"loss": 5.2764,
|
|
"mean_token_accuracy": 0.1951748862862587,
|
|
"num_tokens": 49412022.0,
|
|
"step": 22130
|
|
},
|
|
{
|
|
"entropy": 5.458759307861328,
|
|
"epoch": 2.4859886561464593,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000438980558522914,
|
|
"loss": 5.1626,
|
|
"mean_token_accuracy": 0.20547532588243483,
|
|
"num_tokens": 49423294.0,
|
|
"step": 22135
|
|
},
|
|
{
|
|
"entropy": 5.411266088485718,
|
|
"epoch": 2.486550233054417,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004389530651213983,
|
|
"loss": 5.1368,
|
|
"mean_token_accuracy": 0.1966401994228363,
|
|
"num_tokens": 49433915.0,
|
|
"step": 22140
|
|
},
|
|
{
|
|
"entropy": 5.377877187728882,
|
|
"epoch": 2.487111809962374,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043892556649955354,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.1969851329922676,
|
|
"num_tokens": 49445122.0,
|
|
"step": 22145
|
|
},
|
|
{
|
|
"entropy": 5.6347307682037355,
|
|
"epoch": 2.487673386870332,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004388980626582551,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.19468705505132675,
|
|
"num_tokens": 49456276.0,
|
|
"step": 22150
|
|
},
|
|
{
|
|
"entropy": 5.480639171600342,
|
|
"epoch": 2.4882349637782895,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004388705535983788,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.2016228586435318,
|
|
"num_tokens": 49467346.0,
|
|
"step": 22155
|
|
},
|
|
{
|
|
"entropy": 5.440138864517212,
|
|
"epoch": 2.488796540686247,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004388430393208005,
|
|
"loss": 5.1462,
|
|
"mean_token_accuracy": 0.2024841144680977,
|
|
"num_tokens": 49477635.0,
|
|
"step": 22160
|
|
},
|
|
{
|
|
"entropy": 5.462191438674926,
|
|
"epoch": 2.4893581175942043,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004388155198263963,
|
|
"loss": 5.2445,
|
|
"mean_token_accuracy": 0.1936072364449501,
|
|
"num_tokens": 49491060.0,
|
|
"step": 22165
|
|
},
|
|
{
|
|
"entropy": 5.516598653793335,
|
|
"epoch": 2.489919694502162,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004387879951160424,
|
|
"loss": 5.187,
|
|
"mean_token_accuracy": 0.20492628514766692,
|
|
"num_tokens": 49502551.0,
|
|
"step": 22170
|
|
},
|
|
{
|
|
"entropy": 5.466036319732666,
|
|
"epoch": 2.4904812714101197,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004387604651906152,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.19270135164260865,
|
|
"num_tokens": 49514505.0,
|
|
"step": 22175
|
|
},
|
|
{
|
|
"entropy": 5.381787586212158,
|
|
"epoch": 2.4910428483180773,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004387329300509913,
|
|
"loss": 5.1297,
|
|
"mean_token_accuracy": 0.1995222419500351,
|
|
"num_tokens": 49526301.0,
|
|
"step": 22180
|
|
},
|
|
{
|
|
"entropy": 5.447705268859863,
|
|
"epoch": 2.4916044252260345,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043870538969804733,
|
|
"loss": 5.1798,
|
|
"mean_token_accuracy": 0.20336931943893433,
|
|
"num_tokens": 49536546.0,
|
|
"step": 22185
|
|
},
|
|
{
|
|
"entropy": 5.5259675025939945,
|
|
"epoch": 2.492166002133992,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004386778441326603,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.19254212230443954,
|
|
"num_tokens": 49548046.0,
|
|
"step": 22190
|
|
},
|
|
{
|
|
"entropy": 5.4063385963439945,
|
|
"epoch": 2.49272757904195,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043865029335570725,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.20200827568769456,
|
|
"num_tokens": 49560001.0,
|
|
"step": 22195
|
|
},
|
|
{
|
|
"entropy": 5.442253828048706,
|
|
"epoch": 2.4932891559499075,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004386227373680655,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.20656651258468628,
|
|
"num_tokens": 49571111.0,
|
|
"step": 22200
|
|
},
|
|
{
|
|
"entropy": 5.391418886184693,
|
|
"epoch": 2.4938507328578647,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004385951761706122,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.20016490519046784,
|
|
"num_tokens": 49582888.0,
|
|
"step": 22205
|
|
},
|
|
{
|
|
"entropy": 5.417610549926758,
|
|
"epoch": 2.4944123097658224,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043856760976422506,
|
|
"loss": 5.1628,
|
|
"mean_token_accuracy": 0.20207063853740692,
|
|
"num_tokens": 49593710.0,
|
|
"step": 22210
|
|
},
|
|
{
|
|
"entropy": 5.488984251022339,
|
|
"epoch": 2.49497388667378,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043854003814978174,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.19924787431955338,
|
|
"num_tokens": 49604263.0,
|
|
"step": 22215
|
|
},
|
|
{
|
|
"entropy": 5.553605461120606,
|
|
"epoch": 2.4955354635817377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043851246132816025,
|
|
"loss": 5.3,
|
|
"mean_token_accuracy": 0.19588077813386917,
|
|
"num_tokens": 49615152.0,
|
|
"step": 22220
|
|
},
|
|
{
|
|
"entropy": 5.519556379318237,
|
|
"epoch": 2.496097040489695,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004384848793002385,
|
|
"loss": 5.3181,
|
|
"mean_token_accuracy": 0.19118940085172653,
|
|
"num_tokens": 49627778.0,
|
|
"step": 22225
|
|
},
|
|
{
|
|
"entropy": 5.472327661514282,
|
|
"epoch": 2.4966586173976526,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004384572920668949,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.19835316985845566,
|
|
"num_tokens": 49637701.0,
|
|
"step": 22230
|
|
},
|
|
{
|
|
"entropy": 5.400865602493286,
|
|
"epoch": 2.4972201943056103,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004384296996290076,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.20777858346700667,
|
|
"num_tokens": 49647680.0,
|
|
"step": 22235
|
|
},
|
|
{
|
|
"entropy": 5.5408929824829105,
|
|
"epoch": 2.4977817712135675,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043840210198745533,
|
|
"loss": 5.3146,
|
|
"mean_token_accuracy": 0.1990114375948906,
|
|
"num_tokens": 49659419.0,
|
|
"step": 22240
|
|
},
|
|
{
|
|
"entropy": 5.474949693679809,
|
|
"epoch": 2.498343348121525,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043837449914311676,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.20509854704141617,
|
|
"num_tokens": 49671131.0,
|
|
"step": 22245
|
|
},
|
|
{
|
|
"entropy": 5.428118419647217,
|
|
"epoch": 2.498904925029483,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043834689109687077,
|
|
"loss": 5.1759,
|
|
"mean_token_accuracy": 0.20144660621881486,
|
|
"num_tokens": 49681748.0,
|
|
"step": 22250
|
|
},
|
|
{
|
|
"entropy": 5.564125967025757,
|
|
"epoch": 2.4994665019374405,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004383192778495964,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.20369945466518402,
|
|
"num_tokens": 49693321.0,
|
|
"step": 22255
|
|
},
|
|
{
|
|
"entropy": 5.45250825881958,
|
|
"epoch": 2.500028078845398,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000438291659402173,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.20384441614151,
|
|
"num_tokens": 49704419.0,
|
|
"step": 22260
|
|
},
|
|
{
|
|
"entropy": 5.46245436668396,
|
|
"epoch": 2.5005896557533553,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043826403575547974,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.19631344676017762,
|
|
"num_tokens": 49715692.0,
|
|
"step": 22265
|
|
},
|
|
{
|
|
"entropy": 5.5674583435058596,
|
|
"epoch": 2.501151232661313,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004382364069103962,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.19193732142448425,
|
|
"num_tokens": 49726324.0,
|
|
"step": 22270
|
|
},
|
|
{
|
|
"entropy": 5.401347017288208,
|
|
"epoch": 2.5017128095692707,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043820877286780224,
|
|
"loss": 5.1502,
|
|
"mean_token_accuracy": 0.20821440517902373,
|
|
"num_tokens": 49737069.0,
|
|
"step": 22275
|
|
},
|
|
{
|
|
"entropy": 5.402892827987671,
|
|
"epoch": 2.502274386477228,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004381811336285776,
|
|
"loss": 5.17,
|
|
"mean_token_accuracy": 0.20197368711233138,
|
|
"num_tokens": 49748507.0,
|
|
"step": 22280
|
|
},
|
|
{
|
|
"entropy": 5.477514934539795,
|
|
"epoch": 2.5028359633851855,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004381534891936024,
|
|
"loss": 5.1702,
|
|
"mean_token_accuracy": 0.19761471301317216,
|
|
"num_tokens": 49759017.0,
|
|
"step": 22285
|
|
},
|
|
{
|
|
"entropy": 5.513065004348755,
|
|
"epoch": 2.503397540293143,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004381258395637568,
|
|
"loss": 5.2343,
|
|
"mean_token_accuracy": 0.19962990134954453,
|
|
"num_tokens": 49771353.0,
|
|
"step": 22290
|
|
},
|
|
{
|
|
"entropy": 5.537677526473999,
|
|
"epoch": 2.5039591172011004,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004380981847399212,
|
|
"loss": 5.3706,
|
|
"mean_token_accuracy": 0.18957899808883666,
|
|
"num_tokens": 49782337.0,
|
|
"step": 22295
|
|
},
|
|
{
|
|
"entropy": 5.494372272491455,
|
|
"epoch": 2.504520694109058,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043807052472297626,
|
|
"loss": 5.1313,
|
|
"mean_token_accuracy": 0.20252202600240707,
|
|
"num_tokens": 49794212.0,
|
|
"step": 22300
|
|
},
|
|
{
|
|
"entropy": 5.408016204833984,
|
|
"epoch": 2.5050822710170157,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004380428595138024,
|
|
"loss": 5.1793,
|
|
"mean_token_accuracy": 0.2043404161930084,
|
|
"num_tokens": 49804602.0,
|
|
"step": 22305
|
|
},
|
|
{
|
|
"entropy": 5.48831582069397,
|
|
"epoch": 2.5056438479249734,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043801518911328074,
|
|
"loss": 5.3467,
|
|
"mean_token_accuracy": 0.1861055999994278,
|
|
"num_tokens": 49816277.0,
|
|
"step": 22310
|
|
},
|
|
{
|
|
"entropy": 5.5418891429901125,
|
|
"epoch": 2.506205424832931,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043798751352229227,
|
|
"loss": 5.2121,
|
|
"mean_token_accuracy": 0.20059491842985153,
|
|
"num_tokens": 49827851.0,
|
|
"step": 22315
|
|
},
|
|
{
|
|
"entropy": 5.427427482604981,
|
|
"epoch": 2.5067670017408883,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043795983274171806,
|
|
"loss": 5.2289,
|
|
"mean_token_accuracy": 0.19419785290956498,
|
|
"num_tokens": 49840492.0,
|
|
"step": 22320
|
|
},
|
|
{
|
|
"entropy": 5.326941919326782,
|
|
"epoch": 2.507328578648846,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043793214677243967,
|
|
"loss": 5.0941,
|
|
"mean_token_accuracy": 0.2042275756597519,
|
|
"num_tokens": 49851427.0,
|
|
"step": 22325
|
|
},
|
|
{
|
|
"entropy": 5.44105167388916,
|
|
"epoch": 2.5078901555568036,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004379044556153384,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.19873884618282317,
|
|
"num_tokens": 49862883.0,
|
|
"step": 22330
|
|
},
|
|
{
|
|
"entropy": 5.503253078460693,
|
|
"epoch": 2.508451732464761,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043787675927129625,
|
|
"loss": 5.1749,
|
|
"mean_token_accuracy": 0.1951826825737953,
|
|
"num_tokens": 49874120.0,
|
|
"step": 22335
|
|
},
|
|
{
|
|
"entropy": 5.541385078430176,
|
|
"epoch": 2.5090133093727185,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043784905774119483,
|
|
"loss": 5.2507,
|
|
"mean_token_accuracy": 0.1966320425271988,
|
|
"num_tokens": 49885961.0,
|
|
"step": 22340
|
|
},
|
|
{
|
|
"entropy": 5.40331244468689,
|
|
"epoch": 2.509574886280676,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043782135102591626,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.2049578309059143,
|
|
"num_tokens": 49896821.0,
|
|
"step": 22345
|
|
},
|
|
{
|
|
"entropy": 5.366213464736939,
|
|
"epoch": 2.510136463188634,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004377936391263427,
|
|
"loss": 5.0587,
|
|
"mean_token_accuracy": 0.20414213985204696,
|
|
"num_tokens": 49908148.0,
|
|
"step": 22350
|
|
},
|
|
{
|
|
"entropy": 5.518667268753052,
|
|
"epoch": 2.5106980400965915,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043776592204335655,
|
|
"loss": 5.2232,
|
|
"mean_token_accuracy": 0.19924616813659668,
|
|
"num_tokens": 49919487.0,
|
|
"step": 22355
|
|
},
|
|
{
|
|
"entropy": 5.430217933654785,
|
|
"epoch": 2.5112596170045487,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004377381997778403,
|
|
"loss": 5.1746,
|
|
"mean_token_accuracy": 0.20421140938997268,
|
|
"num_tokens": 49930722.0,
|
|
"step": 22360
|
|
},
|
|
{
|
|
"entropy": 5.449837112426758,
|
|
"epoch": 2.5118211939125064,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004377104723306767,
|
|
"loss": 5.3019,
|
|
"mean_token_accuracy": 0.18949323147535324,
|
|
"num_tokens": 49941917.0,
|
|
"step": 22365
|
|
},
|
|
{
|
|
"entropy": 5.550791215896607,
|
|
"epoch": 2.512382770820464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004376827397027485,
|
|
"loss": 5.2413,
|
|
"mean_token_accuracy": 0.19173285961151124,
|
|
"num_tokens": 49952681.0,
|
|
"step": 22370
|
|
},
|
|
{
|
|
"entropy": 5.553361940383911,
|
|
"epoch": 2.5129443477284212,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004376550018949388,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.19720535725355148,
|
|
"num_tokens": 49965542.0,
|
|
"step": 22375
|
|
},
|
|
{
|
|
"entropy": 5.453121089935303,
|
|
"epoch": 2.513505924636379,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00043762725890813083,
|
|
"loss": 5.2703,
|
|
"mean_token_accuracy": 0.19595289826393128,
|
|
"num_tokens": 49977506.0,
|
|
"step": 22380
|
|
},
|
|
{
|
|
"entropy": 5.411323833465576,
|
|
"epoch": 2.5140675015443366,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004375995107432077,
|
|
"loss": 5.2329,
|
|
"mean_token_accuracy": 0.19535281509160995,
|
|
"num_tokens": 49988674.0,
|
|
"step": 22385
|
|
},
|
|
{
|
|
"entropy": 5.478612995147705,
|
|
"epoch": 2.5146290784522938,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043757175740105316,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19399542063474656,
|
|
"num_tokens": 50001618.0,
|
|
"step": 22390
|
|
},
|
|
{
|
|
"entropy": 5.484747505187988,
|
|
"epoch": 2.5151906553602514,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004375439988825508,
|
|
"loss": 5.1881,
|
|
"mean_token_accuracy": 0.1999855399131775,
|
|
"num_tokens": 50012556.0,
|
|
"step": 22395
|
|
},
|
|
{
|
|
"entropy": 5.502309274673462,
|
|
"epoch": 2.515752232268209,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004375162351885845,
|
|
"loss": 5.1528,
|
|
"mean_token_accuracy": 0.20436239391565322,
|
|
"num_tokens": 50023399.0,
|
|
"step": 22400
|
|
},
|
|
{
|
|
"entropy": 5.3912848949432375,
|
|
"epoch": 2.5163138091761668,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00043748846632003823,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.20284381955862046,
|
|
"num_tokens": 50035209.0,
|
|
"step": 22405
|
|
},
|
|
{
|
|
"entropy": 5.3960553169250485,
|
|
"epoch": 2.5168753860841244,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043746069227779615,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.1977429285645485,
|
|
"num_tokens": 50046383.0,
|
|
"step": 22410
|
|
},
|
|
{
|
|
"entropy": 5.456377601623535,
|
|
"epoch": 2.5174369629920816,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004374329130627427,
|
|
"loss": 5.2272,
|
|
"mean_token_accuracy": 0.2025247722864151,
|
|
"num_tokens": 50058785.0,
|
|
"step": 22415
|
|
},
|
|
{
|
|
"entropy": 5.52679328918457,
|
|
"epoch": 2.5179985399000393,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043740512867576224,
|
|
"loss": 5.2254,
|
|
"mean_token_accuracy": 0.19477398246526717,
|
|
"num_tokens": 50069629.0,
|
|
"step": 22420
|
|
},
|
|
{
|
|
"entropy": 5.53011269569397,
|
|
"epoch": 2.518560116807997,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004373773391177395,
|
|
"loss": 5.2148,
|
|
"mean_token_accuracy": 0.19921404123306274,
|
|
"num_tokens": 50080923.0,
|
|
"step": 22425
|
|
},
|
|
{
|
|
"entropy": 5.442033767700195,
|
|
"epoch": 2.519121693715954,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004373495443895593,
|
|
"loss": 5.1513,
|
|
"mean_token_accuracy": 0.20138380229473113,
|
|
"num_tokens": 50092133.0,
|
|
"step": 22430
|
|
},
|
|
{
|
|
"entropy": 5.34822793006897,
|
|
"epoch": 2.519683270623912,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004373217444921066,
|
|
"loss": 5.1494,
|
|
"mean_token_accuracy": 0.2052408680319786,
|
|
"num_tokens": 50104001.0,
|
|
"step": 22435
|
|
},
|
|
{
|
|
"entropy": 5.525723934173584,
|
|
"epoch": 2.5202448475318695,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043729393942626665,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.20314365923404692,
|
|
"num_tokens": 50115908.0,
|
|
"step": 22440
|
|
},
|
|
{
|
|
"entropy": 5.482291793823242,
|
|
"epoch": 2.520806424439827,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043726612919292476,
|
|
"loss": 5.235,
|
|
"mean_token_accuracy": 0.19285313189029693,
|
|
"num_tokens": 50127380.0,
|
|
"step": 22445
|
|
},
|
|
{
|
|
"entropy": 5.5117440700531,
|
|
"epoch": 2.521368001347785,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004372383137929663,
|
|
"loss": 5.1695,
|
|
"mean_token_accuracy": 0.20268419831991197,
|
|
"num_tokens": 50138458.0,
|
|
"step": 22450
|
|
},
|
|
{
|
|
"entropy": 5.548354768753052,
|
|
"epoch": 2.521929578255742,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043721049322727705,
|
|
"loss": 5.2975,
|
|
"mean_token_accuracy": 0.19436174035072326,
|
|
"num_tokens": 50148814.0,
|
|
"step": 22455
|
|
},
|
|
{
|
|
"entropy": 5.540166807174683,
|
|
"epoch": 2.5224911551636997,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004371826674967428,
|
|
"loss": 5.2941,
|
|
"mean_token_accuracy": 0.1902826577425003,
|
|
"num_tokens": 50159233.0,
|
|
"step": 22460
|
|
},
|
|
{
|
|
"entropy": 5.442757606506348,
|
|
"epoch": 2.5230527320716574,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043715483660224943,
|
|
"loss": 5.2088,
|
|
"mean_token_accuracy": 0.1965060204267502,
|
|
"num_tokens": 50170752.0,
|
|
"step": 22465
|
|
},
|
|
{
|
|
"entropy": 5.43938193321228,
|
|
"epoch": 2.5236143089796146,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004371270005446833,
|
|
"loss": 5.202,
|
|
"mean_token_accuracy": 0.19466197192668916,
|
|
"num_tokens": 50183759.0,
|
|
"step": 22470
|
|
},
|
|
{
|
|
"entropy": 5.493195581436157,
|
|
"epoch": 2.5241758858875722,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004370991593249305,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20323716402053832,
|
|
"num_tokens": 50194091.0,
|
|
"step": 22475
|
|
},
|
|
{
|
|
"entropy": 5.467813444137573,
|
|
"epoch": 2.52473746279553,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043707131294387766,
|
|
"loss": 5.1995,
|
|
"mean_token_accuracy": 0.2000100553035736,
|
|
"num_tokens": 50204591.0,
|
|
"step": 22480
|
|
},
|
|
{
|
|
"entropy": 5.404604864120484,
|
|
"epoch": 2.525299039703487,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004370434614024113,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20310093760490416,
|
|
"num_tokens": 50215809.0,
|
|
"step": 22485
|
|
},
|
|
{
|
|
"entropy": 5.428429317474365,
|
|
"epoch": 2.525860616611445,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043701560470141824,
|
|
"loss": 5.2365,
|
|
"mean_token_accuracy": 0.19854043126106263,
|
|
"num_tokens": 50227038.0,
|
|
"step": 22490
|
|
},
|
|
{
|
|
"entropy": 5.450902891159058,
|
|
"epoch": 2.5264221935194024,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004369877428417856,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.20390333384275436,
|
|
"num_tokens": 50237001.0,
|
|
"step": 22495
|
|
},
|
|
{
|
|
"entropy": 5.48543643951416,
|
|
"epoch": 2.52698377042736,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004369598758244003,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.2029763013124466,
|
|
"num_tokens": 50248389.0,
|
|
"step": 22500
|
|
},
|
|
{
|
|
"entropy": 5.441686487197876,
|
|
"epoch": 2.5275453473353178,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043693200365014985,
|
|
"loss": 5.1683,
|
|
"mean_token_accuracy": 0.2016885906457901,
|
|
"num_tokens": 50259676.0,
|
|
"step": 22505
|
|
},
|
|
{
|
|
"entropy": 5.548251390457153,
|
|
"epoch": 2.528106924243275,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043690412631992154,
|
|
"loss": 5.3094,
|
|
"mean_token_accuracy": 0.19789077192544938,
|
|
"num_tokens": 50270707.0,
|
|
"step": 22510
|
|
},
|
|
{
|
|
"entropy": 5.429886674880981,
|
|
"epoch": 2.5286685011512327,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00043687624383460306,
|
|
"loss": 5.0833,
|
|
"mean_token_accuracy": 0.20658133029937745,
|
|
"num_tokens": 50282187.0,
|
|
"step": 22515
|
|
},
|
|
{
|
|
"entropy": 5.481969785690308,
|
|
"epoch": 2.5292300780591903,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043684835619508215,
|
|
"loss": 5.2468,
|
|
"mean_token_accuracy": 0.19882859885692597,
|
|
"num_tokens": 50293672.0,
|
|
"step": 22520
|
|
},
|
|
{
|
|
"entropy": 5.445405340194702,
|
|
"epoch": 2.5297916549671475,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004368204634022469,
|
|
"loss": 5.0814,
|
|
"mean_token_accuracy": 0.20209303498268127,
|
|
"num_tokens": 50305235.0,
|
|
"step": 22525
|
|
},
|
|
{
|
|
"entropy": 5.474688863754272,
|
|
"epoch": 2.530353231875105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004367925654569852,
|
|
"loss": 5.2728,
|
|
"mean_token_accuracy": 0.19223947077989578,
|
|
"num_tokens": 50316178.0,
|
|
"step": 22530
|
|
},
|
|
{
|
|
"entropy": 5.411743879318237,
|
|
"epoch": 2.530914808783063,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004367646623601856,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20277856290340424,
|
|
"num_tokens": 50326713.0,
|
|
"step": 22535
|
|
},
|
|
{
|
|
"entropy": 5.457183361053467,
|
|
"epoch": 2.5314763856910205,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004367367541127364,
|
|
"loss": 5.3336,
|
|
"mean_token_accuracy": 0.19307427406311034,
|
|
"num_tokens": 50338648.0,
|
|
"step": 22540
|
|
},
|
|
{
|
|
"entropy": 5.513857507705689,
|
|
"epoch": 2.532037962598978,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004367088407155261,
|
|
"loss": 5.1761,
|
|
"mean_token_accuracy": 0.20217010378837585,
|
|
"num_tokens": 50350134.0,
|
|
"step": 22545
|
|
},
|
|
{
|
|
"entropy": 5.381488084793091,
|
|
"epoch": 2.5325995395069354,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004366809221694437,
|
|
"loss": 5.1323,
|
|
"mean_token_accuracy": 0.20723401010036469,
|
|
"num_tokens": 50361101.0,
|
|
"step": 22550
|
|
},
|
|
{
|
|
"entropy": 5.320346784591675,
|
|
"epoch": 2.533161116414893,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043665299847537805,
|
|
"loss": 5.1232,
|
|
"mean_token_accuracy": 0.19722621142864227,
|
|
"num_tokens": 50372376.0,
|
|
"step": 22555
|
|
},
|
|
{
|
|
"entropy": 5.473909616470337,
|
|
"epoch": 2.5337226933228507,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043662506963421815,
|
|
"loss": 5.1921,
|
|
"mean_token_accuracy": 0.20536231994628906,
|
|
"num_tokens": 50383494.0,
|
|
"step": 22560
|
|
},
|
|
{
|
|
"entropy": 5.4836921215057375,
|
|
"epoch": 2.534284270230808,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004365971356468534,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.19785553067922593,
|
|
"num_tokens": 50394720.0,
|
|
"step": 22565
|
|
},
|
|
{
|
|
"entropy": 5.541596937179565,
|
|
"epoch": 2.5348458471387656,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043656919651417314,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.19577511996030808,
|
|
"num_tokens": 50407109.0,
|
|
"step": 22570
|
|
},
|
|
{
|
|
"entropy": 5.602191209793091,
|
|
"epoch": 2.5354074240467233,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000436541252237067,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.1971014454960823,
|
|
"num_tokens": 50418664.0,
|
|
"step": 22575
|
|
},
|
|
{
|
|
"entropy": 5.433929395675659,
|
|
"epoch": 2.5359690009546805,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004365133028164248,
|
|
"loss": 5.1394,
|
|
"mean_token_accuracy": 0.2001485377550125,
|
|
"num_tokens": 50431069.0,
|
|
"step": 22580
|
|
},
|
|
{
|
|
"entropy": 5.433638668060302,
|
|
"epoch": 2.536530577862638,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004364853482531363,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.20226460546255112,
|
|
"num_tokens": 50441484.0,
|
|
"step": 22585
|
|
},
|
|
{
|
|
"entropy": 5.411719417572021,
|
|
"epoch": 2.537092154770596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043645738854809177,
|
|
"loss": 5.1343,
|
|
"mean_token_accuracy": 0.20645090490579604,
|
|
"num_tokens": 50452594.0,
|
|
"step": 22590
|
|
},
|
|
{
|
|
"entropy": 5.51454176902771,
|
|
"epoch": 2.5376537316785535,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004364294237021813,
|
|
"loss": 5.2652,
|
|
"mean_token_accuracy": 0.19244708269834518,
|
|
"num_tokens": 50463342.0,
|
|
"step": 22595
|
|
},
|
|
{
|
|
"entropy": 5.492631340026856,
|
|
"epoch": 2.538215308586511,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043640145371629544,
|
|
"loss": 5.2414,
|
|
"mean_token_accuracy": 0.19320266246795653,
|
|
"num_tokens": 50475164.0,
|
|
"step": 22600
|
|
},
|
|
{
|
|
"entropy": 5.528159093856812,
|
|
"epoch": 2.5387768854944683,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004363734785913246,
|
|
"loss": 5.2716,
|
|
"mean_token_accuracy": 0.19257901459932328,
|
|
"num_tokens": 50486793.0,
|
|
"step": 22605
|
|
},
|
|
{
|
|
"entropy": 5.425835800170899,
|
|
"epoch": 2.539338462402426,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004363454983281597,
|
|
"loss": 5.2039,
|
|
"mean_token_accuracy": 0.2040555015206337,
|
|
"num_tokens": 50499202.0,
|
|
"step": 22610
|
|
},
|
|
{
|
|
"entropy": 5.609098434448242,
|
|
"epoch": 2.5399000393103837,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004363175129276915,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.1864293709397316,
|
|
"num_tokens": 50511801.0,
|
|
"step": 22615
|
|
},
|
|
{
|
|
"entropy": 5.414378452301025,
|
|
"epoch": 2.540461616218341,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043628952239081113,
|
|
"loss": 5.1733,
|
|
"mean_token_accuracy": 0.19124306440353395,
|
|
"num_tokens": 50522918.0,
|
|
"step": 22620
|
|
},
|
|
{
|
|
"entropy": 5.4167030334472654,
|
|
"epoch": 2.5410231931262985,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043626152671840984,
|
|
"loss": 5.0956,
|
|
"mean_token_accuracy": 0.2008655622601509,
|
|
"num_tokens": 50534027.0,
|
|
"step": 22625
|
|
},
|
|
{
|
|
"entropy": 5.442627096176148,
|
|
"epoch": 2.541584770034256,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000436233525911379,
|
|
"loss": 5.145,
|
|
"mean_token_accuracy": 0.2036168172955513,
|
|
"num_tokens": 50543814.0,
|
|
"step": 22630
|
|
},
|
|
{
|
|
"entropy": 5.374173545837403,
|
|
"epoch": 2.542146346942214,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004362055199706101,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.2049317330121994,
|
|
"num_tokens": 50553818.0,
|
|
"step": 22635
|
|
},
|
|
{
|
|
"entropy": 5.5102996826171875,
|
|
"epoch": 2.5427079238501715,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043617750889699496,
|
|
"loss": 5.3061,
|
|
"mean_token_accuracy": 0.19148989170789718,
|
|
"num_tokens": 50564526.0,
|
|
"step": 22640
|
|
},
|
|
{
|
|
"entropy": 5.441617155075074,
|
|
"epoch": 2.5432695007581287,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043614949269142546,
|
|
"loss": 5.1303,
|
|
"mean_token_accuracy": 0.2054365247488022,
|
|
"num_tokens": 50576410.0,
|
|
"step": 22645
|
|
},
|
|
{
|
|
"entropy": 5.423891496658325,
|
|
"epoch": 2.5438310776660864,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043612147135479356,
|
|
"loss": 5.1564,
|
|
"mean_token_accuracy": 0.20463771224021912,
|
|
"num_tokens": 50586378.0,
|
|
"step": 22650
|
|
},
|
|
{
|
|
"entropy": 5.475130033493042,
|
|
"epoch": 2.544392654574044,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004360934448879916,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.19875438064336776,
|
|
"num_tokens": 50597157.0,
|
|
"step": 22655
|
|
},
|
|
{
|
|
"entropy": 5.431999826431275,
|
|
"epoch": 2.5449542314820013,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004360654132919118,
|
|
"loss": 5.1318,
|
|
"mean_token_accuracy": 0.20510659366846085,
|
|
"num_tokens": 50607390.0,
|
|
"step": 22660
|
|
},
|
|
{
|
|
"entropy": 5.369343519210815,
|
|
"epoch": 2.545515808389959,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004360373765674467,
|
|
"loss": 5.0959,
|
|
"mean_token_accuracy": 0.2093702033162117,
|
|
"num_tokens": 50618397.0,
|
|
"step": 22665
|
|
},
|
|
{
|
|
"entropy": 5.508790636062622,
|
|
"epoch": 2.5460773852979166,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043600933471548927,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.19242430329322815,
|
|
"num_tokens": 50631186.0,
|
|
"step": 22670
|
|
},
|
|
{
|
|
"entropy": 5.529711675643921,
|
|
"epoch": 2.546638962205874,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004359812877369321,
|
|
"loss": 5.2404,
|
|
"mean_token_accuracy": 0.2002548962831497,
|
|
"num_tokens": 50642761.0,
|
|
"step": 22675
|
|
},
|
|
{
|
|
"entropy": 5.39301438331604,
|
|
"epoch": 2.5472005391138315,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043595323563266815,
|
|
"loss": 5.0623,
|
|
"mean_token_accuracy": 0.20776823163032532,
|
|
"num_tokens": 50653374.0,
|
|
"step": 22680
|
|
},
|
|
{
|
|
"entropy": 5.410475063323974,
|
|
"epoch": 2.547762116021789,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00043592517840359093,
|
|
"loss": 5.1609,
|
|
"mean_token_accuracy": 0.20213131308555604,
|
|
"num_tokens": 50664331.0,
|
|
"step": 22685
|
|
},
|
|
{
|
|
"entropy": 5.5009101867675785,
|
|
"epoch": 2.548323692929747,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004358971160505936,
|
|
"loss": 5.2005,
|
|
"mean_token_accuracy": 0.19528648406267166,
|
|
"num_tokens": 50675011.0,
|
|
"step": 22690
|
|
},
|
|
{
|
|
"entropy": 5.351649188995362,
|
|
"epoch": 2.5488852698377045,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043586904857456963,
|
|
"loss": 5.0563,
|
|
"mean_token_accuracy": 0.20807598978281022,
|
|
"num_tokens": 50685139.0,
|
|
"step": 22695
|
|
},
|
|
{
|
|
"entropy": 5.480114603042603,
|
|
"epoch": 2.5494468467456617,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043584097597641275,
|
|
"loss": 5.1807,
|
|
"mean_token_accuracy": 0.20112843662500382,
|
|
"num_tokens": 50696610.0,
|
|
"step": 22700
|
|
},
|
|
{
|
|
"entropy": 5.429664230346679,
|
|
"epoch": 2.5500084236536193,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043581289825701683,
|
|
"loss": 5.188,
|
|
"mean_token_accuracy": 0.2002091035246849,
|
|
"num_tokens": 50708662.0,
|
|
"step": 22705
|
|
},
|
|
{
|
|
"entropy": 5.346069478988648,
|
|
"epoch": 2.550570000561577,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004357848154172759,
|
|
"loss": 5.1083,
|
|
"mean_token_accuracy": 0.20590364933013916,
|
|
"num_tokens": 50719457.0,
|
|
"step": 22710
|
|
},
|
|
{
|
|
"entropy": 5.437065601348877,
|
|
"epoch": 2.5511315774695342,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043575672745808404,
|
|
"loss": 5.1752,
|
|
"mean_token_accuracy": 0.20284862965345382,
|
|
"num_tokens": 50730038.0,
|
|
"step": 22715
|
|
},
|
|
{
|
|
"entropy": 5.494239044189453,
|
|
"epoch": 2.551693154377492,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043572863438033556,
|
|
"loss": 5.204,
|
|
"mean_token_accuracy": 0.1995227426290512,
|
|
"num_tokens": 50742327.0,
|
|
"step": 22720
|
|
},
|
|
{
|
|
"entropy": 5.539525890350342,
|
|
"epoch": 2.5522547312854496,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004357005361849251,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.19821358025074004,
|
|
"num_tokens": 50753056.0,
|
|
"step": 22725
|
|
},
|
|
{
|
|
"entropy": 5.436205863952637,
|
|
"epoch": 2.552816308193407,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00043567243287274726,
|
|
"loss": 5.2198,
|
|
"mean_token_accuracy": 0.20030268877744675,
|
|
"num_tokens": 50763961.0,
|
|
"step": 22730
|
|
},
|
|
{
|
|
"entropy": 5.426502370834351,
|
|
"epoch": 2.553377885101365,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043564432444469686,
|
|
"loss": 5.0939,
|
|
"mean_token_accuracy": 0.2098144546151161,
|
|
"num_tokens": 50774978.0,
|
|
"step": 22735
|
|
},
|
|
{
|
|
"entropy": 5.433435106277466,
|
|
"epoch": 2.553939462009322,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043561621090166885,
|
|
"loss": 5.219,
|
|
"mean_token_accuracy": 0.19730058014392854,
|
|
"num_tokens": 50786198.0,
|
|
"step": 22740
|
|
},
|
|
{
|
|
"entropy": 5.3961728572845455,
|
|
"epoch": 2.5545010389172798,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004355880922445584,
|
|
"loss": 5.1924,
|
|
"mean_token_accuracy": 0.19812019914388657,
|
|
"num_tokens": 50797685.0,
|
|
"step": 22745
|
|
},
|
|
{
|
|
"entropy": 5.335108089447021,
|
|
"epoch": 2.5550626158252374,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043555996847426077,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.21196724027395247,
|
|
"num_tokens": 50808518.0,
|
|
"step": 22750
|
|
},
|
|
{
|
|
"entropy": 5.459056615829468,
|
|
"epoch": 2.5556241927331946,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00043553183959167154,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.2000954732298851,
|
|
"num_tokens": 50819241.0,
|
|
"step": 22755
|
|
},
|
|
{
|
|
"entropy": 5.545576667785644,
|
|
"epoch": 2.5561857696411523,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043550370559768614,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.19117384999990464,
|
|
"num_tokens": 50830334.0,
|
|
"step": 22760
|
|
},
|
|
{
|
|
"entropy": 5.567694044113159,
|
|
"epoch": 2.55674734654911,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004354755664932006,
|
|
"loss": 5.2281,
|
|
"mean_token_accuracy": 0.2005622833967209,
|
|
"num_tokens": 50840738.0,
|
|
"step": 22765
|
|
},
|
|
{
|
|
"entropy": 5.506442928314209,
|
|
"epoch": 2.557308923457067,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043544742227911076,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.19021502286195754,
|
|
"num_tokens": 50853397.0,
|
|
"step": 22770
|
|
},
|
|
{
|
|
"entropy": 5.53231291770935,
|
|
"epoch": 2.557870500365025,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043541927295631276,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.19572806656360625,
|
|
"num_tokens": 50865786.0,
|
|
"step": 22775
|
|
},
|
|
{
|
|
"entropy": 5.490480756759643,
|
|
"epoch": 2.5584320772729825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043539111852570296,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.20291522592306138,
|
|
"num_tokens": 50876029.0,
|
|
"step": 22780
|
|
},
|
|
{
|
|
"entropy": 5.435733318328857,
|
|
"epoch": 2.55899365418094,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043536295898817767,
|
|
"loss": 5.1245,
|
|
"mean_token_accuracy": 0.20491679906845092,
|
|
"num_tokens": 50886941.0,
|
|
"step": 22785
|
|
},
|
|
{
|
|
"entropy": 5.441578006744384,
|
|
"epoch": 2.559555231088898,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004353347943446336,
|
|
"loss": 5.1582,
|
|
"mean_token_accuracy": 0.20094648599624634,
|
|
"num_tokens": 50898231.0,
|
|
"step": 22790
|
|
},
|
|
{
|
|
"entropy": 5.433730268478394,
|
|
"epoch": 2.560116807996855,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043530662459596744,
|
|
"loss": 5.2111,
|
|
"mean_token_accuracy": 0.19316208809614183,
|
|
"num_tokens": 50908282.0,
|
|
"step": 22795
|
|
},
|
|
{
|
|
"entropy": 5.458016109466553,
|
|
"epoch": 2.5606783849048127,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004352784497430762,
|
|
"loss": 5.0986,
|
|
"mean_token_accuracy": 0.20712638199329375,
|
|
"num_tokens": 50918462.0,
|
|
"step": 22800
|
|
},
|
|
{
|
|
"entropy": 5.431976318359375,
|
|
"epoch": 2.5612399618127704,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043525026978685706,
|
|
"loss": 5.1902,
|
|
"mean_token_accuracy": 0.20070159286260605,
|
|
"num_tokens": 50929160.0,
|
|
"step": 22805
|
|
},
|
|
{
|
|
"entropy": 5.510934972763062,
|
|
"epoch": 2.5618015387207276,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043522208472820706,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1902436211705208,
|
|
"num_tokens": 50943361.0,
|
|
"step": 22810
|
|
},
|
|
{
|
|
"entropy": 5.554844045639038,
|
|
"epoch": 2.5623631156286852,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004351938945680238,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.1988491892814636,
|
|
"num_tokens": 50954515.0,
|
|
"step": 22815
|
|
},
|
|
{
|
|
"entropy": 5.561653757095337,
|
|
"epoch": 2.562924692536643,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004351656993072048,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.19266541451215743,
|
|
"num_tokens": 50965237.0,
|
|
"step": 22820
|
|
},
|
|
{
|
|
"entropy": 5.4114494800567625,
|
|
"epoch": 2.5634862694446006,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004351374989466477,
|
|
"loss": 5.1423,
|
|
"mean_token_accuracy": 0.20329581797122956,
|
|
"num_tokens": 50976406.0,
|
|
"step": 22825
|
|
},
|
|
{
|
|
"entropy": 5.309348487854004,
|
|
"epoch": 2.5640478463525582,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043510929348725065,
|
|
"loss": 5.0886,
|
|
"mean_token_accuracy": 0.19816937446594238,
|
|
"num_tokens": 50987214.0,
|
|
"step": 22830
|
|
},
|
|
{
|
|
"entropy": 5.456770324707032,
|
|
"epoch": 2.5646094232605154,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043508108292991156,
|
|
"loss": 5.133,
|
|
"mean_token_accuracy": 0.20313860476016998,
|
|
"num_tokens": 50997668.0,
|
|
"step": 22835
|
|
},
|
|
{
|
|
"entropy": 5.510821294784546,
|
|
"epoch": 2.565171000168473,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004350528672755287,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.20532516092061998,
|
|
"num_tokens": 51008358.0,
|
|
"step": 22840
|
|
},
|
|
{
|
|
"entropy": 5.42626986503601,
|
|
"epoch": 2.5657325770764308,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004350246465250005,
|
|
"loss": 5.1717,
|
|
"mean_token_accuracy": 0.19925202131271363,
|
|
"num_tokens": 51019410.0,
|
|
"step": 22845
|
|
},
|
|
{
|
|
"entropy": 5.547534465789795,
|
|
"epoch": 2.566294153984388,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043499642067922544,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.19242394268512725,
|
|
"num_tokens": 51032307.0,
|
|
"step": 22850
|
|
},
|
|
{
|
|
"entropy": 5.548164939880371,
|
|
"epoch": 2.5668557308923456,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043496818973910235,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1967293366789818,
|
|
"num_tokens": 51043176.0,
|
|
"step": 22855
|
|
},
|
|
{
|
|
"entropy": 5.493961143493652,
|
|
"epoch": 2.5674173078003033,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043493995370553,
|
|
"loss": 5.2135,
|
|
"mean_token_accuracy": 0.1971124067902565,
|
|
"num_tokens": 51053977.0,
|
|
"step": 22860
|
|
},
|
|
{
|
|
"entropy": 5.431187582015991,
|
|
"epoch": 2.5679788847082605,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043491171257940755,
|
|
"loss": 5.1944,
|
|
"mean_token_accuracy": 0.20279388576745988,
|
|
"num_tokens": 51064801.0,
|
|
"step": 22865
|
|
},
|
|
{
|
|
"entropy": 5.480392217636108,
|
|
"epoch": 2.568540461616218,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00043488346636163405,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.20912546813488006,
|
|
"num_tokens": 51075400.0,
|
|
"step": 22870
|
|
},
|
|
{
|
|
"entropy": 5.475870895385742,
|
|
"epoch": 2.569102038524176,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004348552150531091,
|
|
"loss": 5.3159,
|
|
"mean_token_accuracy": 0.1912769556045532,
|
|
"num_tokens": 51087077.0,
|
|
"step": 22875
|
|
},
|
|
{
|
|
"entropy": 5.428199815750122,
|
|
"epoch": 2.5696636154321335,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043482695865473207,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.1973722368478775,
|
|
"num_tokens": 51099798.0,
|
|
"step": 22880
|
|
},
|
|
{
|
|
"entropy": 5.541248798370361,
|
|
"epoch": 2.570225192340091,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004347986971674026,
|
|
"loss": 5.3171,
|
|
"mean_token_accuracy": 0.19390056431293487,
|
|
"num_tokens": 51111880.0,
|
|
"step": 22885
|
|
},
|
|
{
|
|
"entropy": 5.46999340057373,
|
|
"epoch": 2.5707867692480484,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043477043059202077,
|
|
"loss": 5.1859,
|
|
"mean_token_accuracy": 0.20113180279731752,
|
|
"num_tokens": 51122358.0,
|
|
"step": 22890
|
|
},
|
|
{
|
|
"entropy": 5.456790399551392,
|
|
"epoch": 2.571348346156006,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004347421589294864,
|
|
"loss": 5.2158,
|
|
"mean_token_accuracy": 0.20488328784704207,
|
|
"num_tokens": 51132775.0,
|
|
"step": 22895
|
|
},
|
|
{
|
|
"entropy": 5.4839154243469235,
|
|
"epoch": 2.5719099230639637,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004347138821806997,
|
|
"loss": 5.275,
|
|
"mean_token_accuracy": 0.19473944902420043,
|
|
"num_tokens": 51144974.0,
|
|
"step": 22900
|
|
},
|
|
{
|
|
"entropy": 5.469318056106568,
|
|
"epoch": 2.572471499971921,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000434685600346561,
|
|
"loss": 5.1169,
|
|
"mean_token_accuracy": 0.20938941091299057,
|
|
"num_tokens": 51154700.0,
|
|
"step": 22905
|
|
},
|
|
{
|
|
"entropy": 5.529508399963379,
|
|
"epoch": 2.5730330768798786,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000434657313427971,
|
|
"loss": 5.2532,
|
|
"mean_token_accuracy": 0.19460317641496658,
|
|
"num_tokens": 51166910.0,
|
|
"step": 22910
|
|
},
|
|
{
|
|
"entropy": 5.432368612289428,
|
|
"epoch": 2.5735946537878363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004346290214258301,
|
|
"loss": 5.1043,
|
|
"mean_token_accuracy": 0.2010415479540825,
|
|
"num_tokens": 51177620.0,
|
|
"step": 22915
|
|
},
|
|
{
|
|
"entropy": 5.502174806594849,
|
|
"epoch": 2.574156230695794,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043460072434103934,
|
|
"loss": 5.1302,
|
|
"mean_token_accuracy": 0.20372734665870668,
|
|
"num_tokens": 51187894.0,
|
|
"step": 22920
|
|
},
|
|
{
|
|
"entropy": 5.401703405380249,
|
|
"epoch": 2.5747178076037516,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004345724221744996,
|
|
"loss": 5.2342,
|
|
"mean_token_accuracy": 0.19296132177114486,
|
|
"num_tokens": 51199625.0,
|
|
"step": 22925
|
|
},
|
|
{
|
|
"entropy": 5.385957431793213,
|
|
"epoch": 2.575279384511709,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043454411492711197,
|
|
"loss": 5.1707,
|
|
"mean_token_accuracy": 0.20146380215883256,
|
|
"num_tokens": 51211932.0,
|
|
"step": 22930
|
|
},
|
|
{
|
|
"entropy": 5.496762657165528,
|
|
"epoch": 2.5758409614196665,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043451580259977793,
|
|
"loss": 5.2456,
|
|
"mean_token_accuracy": 0.20146604776382446,
|
|
"num_tokens": 51223196.0,
|
|
"step": 22935
|
|
},
|
|
{
|
|
"entropy": 5.519961977005005,
|
|
"epoch": 2.576402538327624,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043448748519339875,
|
|
"loss": 5.2027,
|
|
"mean_token_accuracy": 0.1924605205655098,
|
|
"num_tokens": 51234246.0,
|
|
"step": 22940
|
|
},
|
|
{
|
|
"entropy": 5.511989402770996,
|
|
"epoch": 2.5769641152355813,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043445916270887626,
|
|
"loss": 5.1685,
|
|
"mean_token_accuracy": 0.20332323610782624,
|
|
"num_tokens": 51245056.0,
|
|
"step": 22945
|
|
},
|
|
{
|
|
"entropy": 5.474715662002564,
|
|
"epoch": 2.577525692143539,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004344308351471123,
|
|
"loss": 5.2049,
|
|
"mean_token_accuracy": 0.1981821447610855,
|
|
"num_tokens": 51256513.0,
|
|
"step": 22950
|
|
},
|
|
{
|
|
"entropy": 5.388407039642334,
|
|
"epoch": 2.5780872690514967,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043440250250900854,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.19886239916086196,
|
|
"num_tokens": 51267609.0,
|
|
"step": 22955
|
|
},
|
|
{
|
|
"entropy": 5.527415609359741,
|
|
"epoch": 2.578648845959454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004343741647954673,
|
|
"loss": 5.3074,
|
|
"mean_token_accuracy": 0.19608695805072784,
|
|
"num_tokens": 51277940.0,
|
|
"step": 22960
|
|
},
|
|
{
|
|
"entropy": 5.639070081710815,
|
|
"epoch": 2.5792104228674115,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004343458220073909,
|
|
"loss": 5.299,
|
|
"mean_token_accuracy": 0.1974821001291275,
|
|
"num_tokens": 51288853.0,
|
|
"step": 22965
|
|
},
|
|
{
|
|
"entropy": 5.495197439193726,
|
|
"epoch": 2.579771999775369,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004343174741456817,
|
|
"loss": 5.2972,
|
|
"mean_token_accuracy": 0.1934747576713562,
|
|
"num_tokens": 51299197.0,
|
|
"step": 22970
|
|
},
|
|
{
|
|
"entropy": 5.466072845458984,
|
|
"epoch": 2.580333576683327,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004342891212112423,
|
|
"loss": 5.3115,
|
|
"mean_token_accuracy": 0.18912968784570694,
|
|
"num_tokens": 51310821.0,
|
|
"step": 22975
|
|
},
|
|
{
|
|
"entropy": 5.5917792320251465,
|
|
"epoch": 2.5808951535912845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043426076320497557,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.1935696318745613,
|
|
"num_tokens": 51321805.0,
|
|
"step": 22980
|
|
},
|
|
{
|
|
"entropy": 5.411164665222168,
|
|
"epoch": 2.5814567304992417,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043423240012778437,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20404643714427947,
|
|
"num_tokens": 51332647.0,
|
|
"step": 22985
|
|
},
|
|
{
|
|
"entropy": 5.3848395347595215,
|
|
"epoch": 2.5820183074071994,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004342040319805717,
|
|
"loss": 5.109,
|
|
"mean_token_accuracy": 0.20321384370326995,
|
|
"num_tokens": 51344715.0,
|
|
"step": 22990
|
|
},
|
|
{
|
|
"entropy": 5.491957092285157,
|
|
"epoch": 2.582579884315157,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000434175658764241,
|
|
"loss": 5.3029,
|
|
"mean_token_accuracy": 0.19858656227588653,
|
|
"num_tokens": 51355481.0,
|
|
"step": 22995
|
|
},
|
|
{
|
|
"entropy": 5.530055713653565,
|
|
"epoch": 2.5831414612231143,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043414728047969553,
|
|
"loss": 5.1489,
|
|
"mean_token_accuracy": 0.20350098311901094,
|
|
"num_tokens": 51367098.0,
|
|
"step": 23000
|
|
},
|
|
{
|
|
"entropy": 5.49979600906372,
|
|
"epoch": 2.583703038131072,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043411889712783897,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.192843234539032,
|
|
"num_tokens": 51379948.0,
|
|
"step": 23005
|
|
},
|
|
{
|
|
"entropy": 5.3930503845214846,
|
|
"epoch": 2.5842646150390296,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00043409050870957505,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20281176269054413,
|
|
"num_tokens": 51391675.0,
|
|
"step": 23010
|
|
},
|
|
{
|
|
"entropy": 5.439097499847412,
|
|
"epoch": 2.5848261919469873,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004340621152258075,
|
|
"loss": 5.0725,
|
|
"mean_token_accuracy": 0.21035843938589097,
|
|
"num_tokens": 51401809.0,
|
|
"step": 23015
|
|
},
|
|
{
|
|
"entropy": 5.425943040847779,
|
|
"epoch": 2.585387768854945,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043403371667744055,
|
|
"loss": 5.1618,
|
|
"mean_token_accuracy": 0.20350307524204253,
|
|
"num_tokens": 51413184.0,
|
|
"step": 23020
|
|
},
|
|
{
|
|
"entropy": 5.451111507415772,
|
|
"epoch": 2.585949345762902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004340053130653785,
|
|
"loss": 5.2401,
|
|
"mean_token_accuracy": 0.19500567764043808,
|
|
"num_tokens": 51424751.0,
|
|
"step": 23025
|
|
},
|
|
{
|
|
"entropy": 5.42625789642334,
|
|
"epoch": 2.58651092267086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004339769043905255,
|
|
"loss": 5.157,
|
|
"mean_token_accuracy": 0.20028635561466218,
|
|
"num_tokens": 51436550.0,
|
|
"step": 23030
|
|
},
|
|
{
|
|
"entropy": 5.514390563964843,
|
|
"epoch": 2.5870724995788175,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043394849065378624,
|
|
"loss": 5.1828,
|
|
"mean_token_accuracy": 0.20010620206594468,
|
|
"num_tokens": 51447691.0,
|
|
"step": 23035
|
|
},
|
|
{
|
|
"entropy": 5.450367832183838,
|
|
"epoch": 2.5876340764867747,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043392007185606533,
|
|
"loss": 5.1802,
|
|
"mean_token_accuracy": 0.2015572264790535,
|
|
"num_tokens": 51459715.0,
|
|
"step": 23040
|
|
},
|
|
{
|
|
"entropy": 5.402326059341431,
|
|
"epoch": 2.5881956533947323,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004338916479982678,
|
|
"loss": 5.1162,
|
|
"mean_token_accuracy": 0.20762484520673752,
|
|
"num_tokens": 51470541.0,
|
|
"step": 23045
|
|
},
|
|
{
|
|
"entropy": 5.42541913986206,
|
|
"epoch": 2.58875723030269,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043386321908129856,
|
|
"loss": 5.0984,
|
|
"mean_token_accuracy": 0.21045170724391937,
|
|
"num_tokens": 51480724.0,
|
|
"step": 23050
|
|
},
|
|
{
|
|
"entropy": 5.5670877456665036,
|
|
"epoch": 2.589318807210647,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043383478510606276,
|
|
"loss": 5.3927,
|
|
"mean_token_accuracy": 0.19152320474386214,
|
|
"num_tokens": 51492204.0,
|
|
"step": 23055
|
|
},
|
|
{
|
|
"entropy": 5.49976954460144,
|
|
"epoch": 2.589880384118605,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004338063460734658,
|
|
"loss": 5.2101,
|
|
"mean_token_accuracy": 0.1916583865880966,
|
|
"num_tokens": 51503354.0,
|
|
"step": 23060
|
|
},
|
|
{
|
|
"entropy": 5.4599686622619625,
|
|
"epoch": 2.5904419610265625,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004337779019844132,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.20595337003469466,
|
|
"num_tokens": 51513563.0,
|
|
"step": 23065
|
|
},
|
|
{
|
|
"entropy": 5.489657306671143,
|
|
"epoch": 2.59100353793452,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043374945283981066,
|
|
"loss": 5.197,
|
|
"mean_token_accuracy": 0.19584972858428956,
|
|
"num_tokens": 51524996.0,
|
|
"step": 23070
|
|
},
|
|
{
|
|
"entropy": 5.367291593551636,
|
|
"epoch": 2.591565114842478,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004337209986405639,
|
|
"loss": 5.0911,
|
|
"mean_token_accuracy": 0.20955319106578826,
|
|
"num_tokens": 51536822.0,
|
|
"step": 23075
|
|
},
|
|
{
|
|
"entropy": 5.383330154418945,
|
|
"epoch": 2.592126691750435,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.000433692539387579,
|
|
"loss": 5.1332,
|
|
"mean_token_accuracy": 0.20628248900175095,
|
|
"num_tokens": 51547545.0,
|
|
"step": 23080
|
|
},
|
|
{
|
|
"entropy": 5.492537307739258,
|
|
"epoch": 2.5926882686583927,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004336640750817621,
|
|
"loss": 5.2169,
|
|
"mean_token_accuracy": 0.20161314755678178,
|
|
"num_tokens": 51560721.0,
|
|
"step": 23085
|
|
},
|
|
{
|
|
"entropy": 5.42164716720581,
|
|
"epoch": 2.5932498455663504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043363560572401953,
|
|
"loss": 5.0672,
|
|
"mean_token_accuracy": 0.2054253861308098,
|
|
"num_tokens": 51573226.0,
|
|
"step": 23090
|
|
},
|
|
{
|
|
"entropy": 5.423936462402343,
|
|
"epoch": 2.5938114224743076,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043360713131525774,
|
|
"loss": 5.1937,
|
|
"mean_token_accuracy": 0.20283742547035216,
|
|
"num_tokens": 51584338.0,
|
|
"step": 23095
|
|
},
|
|
{
|
|
"entropy": 5.4700006484985355,
|
|
"epoch": 2.5943729993822653,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004335786518563834,
|
|
"loss": 5.1967,
|
|
"mean_token_accuracy": 0.19860643297433853,
|
|
"num_tokens": 51593979.0,
|
|
"step": 23100
|
|
},
|
|
{
|
|
"entropy": 5.385732126235962,
|
|
"epoch": 2.594934576290223,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004335501673483033,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.20353750437498092,
|
|
"num_tokens": 51604713.0,
|
|
"step": 23105
|
|
},
|
|
{
|
|
"entropy": 5.438765525817871,
|
|
"epoch": 2.5954961531981806,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043352167779192423,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.20398078858852386,
|
|
"num_tokens": 51616034.0,
|
|
"step": 23110
|
|
},
|
|
{
|
|
"entropy": 5.343588876724243,
|
|
"epoch": 2.5960577301061383,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043349318318815363,
|
|
"loss": 5.094,
|
|
"mean_token_accuracy": 0.20045638531446458,
|
|
"num_tokens": 51627551.0,
|
|
"step": 23115
|
|
},
|
|
{
|
|
"entropy": 5.4696766376495365,
|
|
"epoch": 2.5966193070140955,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043346468353789853,
|
|
"loss": 5.1955,
|
|
"mean_token_accuracy": 0.20165563374757767,
|
|
"num_tokens": 51639625.0,
|
|
"step": 23120
|
|
},
|
|
{
|
|
"entropy": 5.4496232032775875,
|
|
"epoch": 2.597180883922053,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004334361788420664,
|
|
"loss": 5.1057,
|
|
"mean_token_accuracy": 0.20712644159793853,
|
|
"num_tokens": 51649918.0,
|
|
"step": 23125
|
|
},
|
|
{
|
|
"entropy": 5.34039716720581,
|
|
"epoch": 2.597742460830011,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00043340766910156497,
|
|
"loss": 5.1327,
|
|
"mean_token_accuracy": 0.21442865580320358,
|
|
"num_tokens": 51659527.0,
|
|
"step": 23130
|
|
},
|
|
{
|
|
"entropy": 5.410715484619141,
|
|
"epoch": 2.598304037737968,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043337915431730195,
|
|
"loss": 5.2686,
|
|
"mean_token_accuracy": 0.1951172485947609,
|
|
"num_tokens": 51670704.0,
|
|
"step": 23135
|
|
},
|
|
{
|
|
"entropy": 5.463361406326294,
|
|
"epoch": 2.5988656146459257,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043335063449018515,
|
|
"loss": 5.1723,
|
|
"mean_token_accuracy": 0.20300788581371307,
|
|
"num_tokens": 51681606.0,
|
|
"step": 23140
|
|
},
|
|
{
|
|
"entropy": 5.530260753631592,
|
|
"epoch": 2.5994271915538834,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004333221096211227,
|
|
"loss": 5.2658,
|
|
"mean_token_accuracy": 0.19512063413858413,
|
|
"num_tokens": 51692592.0,
|
|
"step": 23145
|
|
},
|
|
{
|
|
"entropy": 5.427650308609008,
|
|
"epoch": 2.599988768461841,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043329357971102296,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.19966524243354797,
|
|
"num_tokens": 51704990.0,
|
|
"step": 23150
|
|
},
|
|
{
|
|
"entropy": 5.452664947509765,
|
|
"epoch": 2.6005503453697982,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043326504476079425,
|
|
"loss": 5.1914,
|
|
"mean_token_accuracy": 0.20253764390945433,
|
|
"num_tokens": 51715934.0,
|
|
"step": 23155
|
|
},
|
|
{
|
|
"entropy": 5.472763252258301,
|
|
"epoch": 2.601111922277756,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004332365047713451,
|
|
"loss": 5.2949,
|
|
"mean_token_accuracy": 0.1914630800485611,
|
|
"num_tokens": 51727314.0,
|
|
"step": 23160
|
|
},
|
|
{
|
|
"entropy": 5.466134309768677,
|
|
"epoch": 2.6016734991857136,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004332079597435842,
|
|
"loss": 5.0915,
|
|
"mean_token_accuracy": 0.2080233946442604,
|
|
"num_tokens": 51738322.0,
|
|
"step": 23165
|
|
},
|
|
{
|
|
"entropy": 5.33489465713501,
|
|
"epoch": 2.602235076093671,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004331794096784206,
|
|
"loss": 5.1048,
|
|
"mean_token_accuracy": 0.2077830821275711,
|
|
"num_tokens": 51749221.0,
|
|
"step": 23170
|
|
},
|
|
{
|
|
"entropy": 5.381930208206176,
|
|
"epoch": 2.6027966530016284,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004331508545767633,
|
|
"loss": 5.1787,
|
|
"mean_token_accuracy": 0.19680433869361877,
|
|
"num_tokens": 51760568.0,
|
|
"step": 23175
|
|
},
|
|
{
|
|
"entropy": 5.484025764465332,
|
|
"epoch": 2.603358229909586,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004331222944395213,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.2042563021183014,
|
|
"num_tokens": 51772652.0,
|
|
"step": 23180
|
|
},
|
|
{
|
|
"entropy": 5.46460108757019,
|
|
"epoch": 2.6039198068175438,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004330937292676042,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.20381492972373963,
|
|
"num_tokens": 51783739.0,
|
|
"step": 23185
|
|
},
|
|
{
|
|
"entropy": 5.439929628372193,
|
|
"epoch": 2.604481383725501,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004330651590619214,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.20164480656385422,
|
|
"num_tokens": 51795521.0,
|
|
"step": 23190
|
|
},
|
|
{
|
|
"entropy": 5.3807573318481445,
|
|
"epoch": 2.6050429606334586,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004330365838233827,
|
|
"loss": 5.0215,
|
|
"mean_token_accuracy": 0.20409653335809708,
|
|
"num_tokens": 51805041.0,
|
|
"step": 23195
|
|
},
|
|
{
|
|
"entropy": 5.4696790218353275,
|
|
"epoch": 2.6056045375414163,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043300800355289786,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.19921782463788987,
|
|
"num_tokens": 51815157.0,
|
|
"step": 23200
|
|
},
|
|
{
|
|
"entropy": 5.50786395072937,
|
|
"epoch": 2.606166114449374,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043297941825137684,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.20174478590488434,
|
|
"num_tokens": 51826760.0,
|
|
"step": 23205
|
|
},
|
|
{
|
|
"entropy": 5.58562970161438,
|
|
"epoch": 2.6067276913573316,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043295082791972993,
|
|
"loss": 5.3877,
|
|
"mean_token_accuracy": 0.19258662611246108,
|
|
"num_tokens": 51838018.0,
|
|
"step": 23210
|
|
},
|
|
{
|
|
"entropy": 5.5503209114074705,
|
|
"epoch": 2.607289268265289,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00043292223255886737,
|
|
"loss": 5.2568,
|
|
"mean_token_accuracy": 0.19613364785909654,
|
|
"num_tokens": 51848217.0,
|
|
"step": 23215
|
|
},
|
|
{
|
|
"entropy": 5.452135038375855,
|
|
"epoch": 2.6078508451732465,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043289363216969973,
|
|
"loss": 5.1269,
|
|
"mean_token_accuracy": 0.20859239399433135,
|
|
"num_tokens": 51857537.0,
|
|
"step": 23220
|
|
},
|
|
{
|
|
"entropy": 5.453900003433228,
|
|
"epoch": 2.608412422081204,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043286502675313757,
|
|
"loss": 5.1657,
|
|
"mean_token_accuracy": 0.2028586372733116,
|
|
"num_tokens": 51867961.0,
|
|
"step": 23225
|
|
},
|
|
{
|
|
"entropy": 5.44667387008667,
|
|
"epoch": 2.6089739989891614,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004328364163100917,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.19203062057495118,
|
|
"num_tokens": 51879868.0,
|
|
"step": 23230
|
|
},
|
|
{
|
|
"entropy": 5.490435791015625,
|
|
"epoch": 2.609535575897119,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004328078008414731,
|
|
"loss": 5.2077,
|
|
"mean_token_accuracy": 0.1939200147986412,
|
|
"num_tokens": 51890849.0,
|
|
"step": 23235
|
|
},
|
|
{
|
|
"entropy": 5.4692870616912845,
|
|
"epoch": 2.6100971528050767,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000432779180348193,
|
|
"loss": 5.1777,
|
|
"mean_token_accuracy": 0.19702548384666443,
|
|
"num_tokens": 51901193.0,
|
|
"step": 23240
|
|
},
|
|
{
|
|
"entropy": 5.480481958389282,
|
|
"epoch": 2.6106587297130344,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043275055483116254,
|
|
"loss": 5.1776,
|
|
"mean_token_accuracy": 0.20156957507133483,
|
|
"num_tokens": 51912551.0,
|
|
"step": 23245
|
|
},
|
|
{
|
|
"entropy": 5.534122657775879,
|
|
"epoch": 2.6112203066209916,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004327219242912933,
|
|
"loss": 5.3672,
|
|
"mean_token_accuracy": 0.18527720123529434,
|
|
"num_tokens": 51923970.0,
|
|
"step": 23250
|
|
},
|
|
{
|
|
"entropy": 5.397737121582031,
|
|
"epoch": 2.6117818835289492,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004326932887294967,
|
|
"loss": 5.0448,
|
|
"mean_token_accuracy": 0.2042302593588829,
|
|
"num_tokens": 51936667.0,
|
|
"step": 23255
|
|
},
|
|
{
|
|
"entropy": 5.414308071136475,
|
|
"epoch": 2.612343460436907,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004326646481466848,
|
|
"loss": 5.0868,
|
|
"mean_token_accuracy": 0.20442045032978057,
|
|
"num_tokens": 51947479.0,
|
|
"step": 23260
|
|
},
|
|
{
|
|
"entropy": 5.3863883972167965,
|
|
"epoch": 2.6129050373448646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004326360025437692,
|
|
"loss": 5.244,
|
|
"mean_token_accuracy": 0.2054300382733345,
|
|
"num_tokens": 51958669.0,
|
|
"step": 23265
|
|
},
|
|
{
|
|
"entropy": 5.375784873962402,
|
|
"epoch": 2.613466614252822,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043260735192166217,
|
|
"loss": 5.0864,
|
|
"mean_token_accuracy": 0.20915568321943284,
|
|
"num_tokens": 51969273.0,
|
|
"step": 23270
|
|
},
|
|
{
|
|
"entropy": 5.532740926742553,
|
|
"epoch": 2.6140281911607794,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000432578696281276,
|
|
"loss": 5.2626,
|
|
"mean_token_accuracy": 0.19827527105808257,
|
|
"num_tokens": 51981220.0,
|
|
"step": 23275
|
|
},
|
|
{
|
|
"entropy": 5.454915571212768,
|
|
"epoch": 2.614589768068737,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000432550035623523,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.1979052171111107,
|
|
"num_tokens": 51992768.0,
|
|
"step": 23280
|
|
},
|
|
{
|
|
"entropy": 5.411095094680786,
|
|
"epoch": 2.6151513449766943,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004325213699493157,
|
|
"loss": 5.1471,
|
|
"mean_token_accuracy": 0.19316234141588212,
|
|
"num_tokens": 52002754.0,
|
|
"step": 23285
|
|
},
|
|
{
|
|
"entropy": 5.489265823364258,
|
|
"epoch": 2.615712921884652,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004324926992595669,
|
|
"loss": 5.1537,
|
|
"mean_token_accuracy": 0.20034459978342056,
|
|
"num_tokens": 52014503.0,
|
|
"step": 23290
|
|
},
|
|
{
|
|
"entropy": 5.4775584697723385,
|
|
"epoch": 2.6162744987926096,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004324640235551895,
|
|
"loss": 5.2189,
|
|
"mean_token_accuracy": 0.20189371109008789,
|
|
"num_tokens": 52026151.0,
|
|
"step": 23295
|
|
},
|
|
{
|
|
"entropy": 5.382840490341186,
|
|
"epoch": 2.6168360757005673,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004324353428370965,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.19594016075134277,
|
|
"num_tokens": 52037704.0,
|
|
"step": 23300
|
|
},
|
|
{
|
|
"entropy": 5.450302219390869,
|
|
"epoch": 2.617397652608525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004324066571062012,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.20234261304140091,
|
|
"num_tokens": 52049326.0,
|
|
"step": 23305
|
|
},
|
|
{
|
|
"entropy": 5.520052719116211,
|
|
"epoch": 2.617959229516482,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004323779663634168,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.2056918188929558,
|
|
"num_tokens": 52060030.0,
|
|
"step": 23310
|
|
},
|
|
{
|
|
"entropy": 5.558416509628296,
|
|
"epoch": 2.61852080642444,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000432349270609657,
|
|
"loss": 5.3469,
|
|
"mean_token_accuracy": 0.1961011067032814,
|
|
"num_tokens": 52071744.0,
|
|
"step": 23315
|
|
},
|
|
{
|
|
"entropy": 5.488220596313477,
|
|
"epoch": 2.6190823833323975,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00043232056984583527,
|
|
"loss": 5.1962,
|
|
"mean_token_accuracy": 0.19681306183338165,
|
|
"num_tokens": 52082443.0,
|
|
"step": 23320
|
|
},
|
|
{
|
|
"entropy": 5.426075649261475,
|
|
"epoch": 2.6196439602403547,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004322918640728656,
|
|
"loss": 5.154,
|
|
"mean_token_accuracy": 0.20221319049596786,
|
|
"num_tokens": 52094211.0,
|
|
"step": 23325
|
|
},
|
|
{
|
|
"entropy": 5.3940064907073975,
|
|
"epoch": 2.6202055371483124,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043226315329166203,
|
|
"loss": 5.1166,
|
|
"mean_token_accuracy": 0.20735709816217424,
|
|
"num_tokens": 52104802.0,
|
|
"step": 23330
|
|
},
|
|
{
|
|
"entropy": 5.524778699874878,
|
|
"epoch": 2.62076711405627,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043223443750313873,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.19766655713319778,
|
|
"num_tokens": 52115459.0,
|
|
"step": 23335
|
|
},
|
|
{
|
|
"entropy": 5.444881963729858,
|
|
"epoch": 2.6213286909642277,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004322057167082099,
|
|
"loss": 5.243,
|
|
"mean_token_accuracy": 0.19587359726428985,
|
|
"num_tokens": 52125572.0,
|
|
"step": 23340
|
|
},
|
|
{
|
|
"entropy": 5.400161600112915,
|
|
"epoch": 2.621890267872185,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043217699090779006,
|
|
"loss": 5.1678,
|
|
"mean_token_accuracy": 0.20162893682718278,
|
|
"num_tokens": 52137405.0,
|
|
"step": 23345
|
|
},
|
|
{
|
|
"entropy": 5.490806341171265,
|
|
"epoch": 2.6224518447801426,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00043214826010279383,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.1970750644803047,
|
|
"num_tokens": 52148131.0,
|
|
"step": 23350
|
|
},
|
|
{
|
|
"entropy": 5.480850028991699,
|
|
"epoch": 2.6230134216881003,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004321195242941361,
|
|
"loss": 5.1846,
|
|
"mean_token_accuracy": 0.19682349562644957,
|
|
"num_tokens": 52159361.0,
|
|
"step": 23355
|
|
},
|
|
{
|
|
"entropy": 5.371744012832641,
|
|
"epoch": 2.623574998596058,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043209078348273175,
|
|
"loss": 5.1732,
|
|
"mean_token_accuracy": 0.19548098742961884,
|
|
"num_tokens": 52170521.0,
|
|
"step": 23360
|
|
},
|
|
{
|
|
"entropy": 5.5385438919067385,
|
|
"epoch": 2.624136575504015,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004320620376694959,
|
|
"loss": 5.278,
|
|
"mean_token_accuracy": 0.20237941443920135,
|
|
"num_tokens": 52182069.0,
|
|
"step": 23365
|
|
},
|
|
{
|
|
"entropy": 5.408032989501953,
|
|
"epoch": 2.624698152411973,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043203328685534396,
|
|
"loss": 5.0818,
|
|
"mean_token_accuracy": 0.20961960256099701,
|
|
"num_tokens": 52191867.0,
|
|
"step": 23370
|
|
},
|
|
{
|
|
"entropy": 5.49868426322937,
|
|
"epoch": 2.6252597293199305,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004320045310411912,
|
|
"loss": 5.3588,
|
|
"mean_token_accuracy": 0.18307363539934157,
|
|
"num_tokens": 52204511.0,
|
|
"step": 23375
|
|
},
|
|
{
|
|
"entropy": 5.494802331924438,
|
|
"epoch": 2.6258213062278877,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043197577022795327,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.2041903778910637,
|
|
"num_tokens": 52214276.0,
|
|
"step": 23380
|
|
},
|
|
{
|
|
"entropy": 5.469472980499267,
|
|
"epoch": 2.6263828831358453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004319470044165459,
|
|
"loss": 5.18,
|
|
"mean_token_accuracy": 0.20590867549180986,
|
|
"num_tokens": 52225388.0,
|
|
"step": 23385
|
|
},
|
|
{
|
|
"entropy": 5.386995649337768,
|
|
"epoch": 2.626944460043803,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004319182336078852,
|
|
"loss": 5.0742,
|
|
"mean_token_accuracy": 0.2064932718873024,
|
|
"num_tokens": 52235300.0,
|
|
"step": 23390
|
|
},
|
|
{
|
|
"entropy": 5.489656686782837,
|
|
"epoch": 2.6275060369517607,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000431889457802887,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.18884073197841644,
|
|
"num_tokens": 52248392.0,
|
|
"step": 23395
|
|
},
|
|
{
|
|
"entropy": 5.498094844818115,
|
|
"epoch": 2.6280676138597183,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004318606770024675,
|
|
"loss": 5.1754,
|
|
"mean_token_accuracy": 0.19837892055511475,
|
|
"num_tokens": 52259839.0,
|
|
"step": 23400
|
|
},
|
|
{
|
|
"entropy": 5.493670701980591,
|
|
"epoch": 2.6286291907676755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004318318912075433,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.19171394109725953,
|
|
"num_tokens": 52271195.0,
|
|
"step": 23405
|
|
},
|
|
{
|
|
"entropy": 5.447798395156861,
|
|
"epoch": 2.629190767675633,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004318031004190308,
|
|
"loss": 5.161,
|
|
"mean_token_accuracy": 0.20423481464385987,
|
|
"num_tokens": 52282445.0,
|
|
"step": 23410
|
|
},
|
|
{
|
|
"entropy": 5.464029026031494,
|
|
"epoch": 2.629752344583591,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043177430463784685,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.19565656185150146,
|
|
"num_tokens": 52294144.0,
|
|
"step": 23415
|
|
},
|
|
{
|
|
"entropy": 5.377364778518677,
|
|
"epoch": 2.630313921491548,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043174550386490816,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.20269618630409242,
|
|
"num_tokens": 52304510.0,
|
|
"step": 23420
|
|
},
|
|
{
|
|
"entropy": 5.485373497009277,
|
|
"epoch": 2.6308754983995057,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004317166981011319,
|
|
"loss": 5.1229,
|
|
"mean_token_accuracy": 0.2028412789106369,
|
|
"num_tokens": 52314507.0,
|
|
"step": 23425
|
|
},
|
|
{
|
|
"entropy": 5.350175189971924,
|
|
"epoch": 2.6314370753074634,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043168788734743516,
|
|
"loss": 5.143,
|
|
"mean_token_accuracy": 0.20885964334011078,
|
|
"num_tokens": 52325104.0,
|
|
"step": 23430
|
|
},
|
|
{
|
|
"entropy": 5.471809911727905,
|
|
"epoch": 2.631998652215421,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043165907160473525,
|
|
"loss": 5.2418,
|
|
"mean_token_accuracy": 0.18996679037809372,
|
|
"num_tokens": 52336037.0,
|
|
"step": 23435
|
|
},
|
|
{
|
|
"entropy": 5.443579864501953,
|
|
"epoch": 2.6325602291233783,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004316302508739499,
|
|
"loss": 5.0969,
|
|
"mean_token_accuracy": 0.2032205045223236,
|
|
"num_tokens": 52346901.0,
|
|
"step": 23440
|
|
},
|
|
{
|
|
"entropy": 5.4770409107208256,
|
|
"epoch": 2.633121806031336,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004316014251559965,
|
|
"loss": 5.1886,
|
|
"mean_token_accuracy": 0.20187743455171586,
|
|
"num_tokens": 52359159.0,
|
|
"step": 23445
|
|
},
|
|
{
|
|
"entropy": 5.395916175842285,
|
|
"epoch": 2.6336833829392936,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00043157259445179304,
|
|
"loss": 5.0834,
|
|
"mean_token_accuracy": 0.20574690401554108,
|
|
"num_tokens": 52369274.0,
|
|
"step": 23450
|
|
},
|
|
{
|
|
"entropy": 5.331924057006836,
|
|
"epoch": 2.6342449598472513,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004315437587622574,
|
|
"loss": 5.1019,
|
|
"mean_token_accuracy": 0.20977938920259476,
|
|
"num_tokens": 52381360.0,
|
|
"step": 23455
|
|
},
|
|
{
|
|
"entropy": 5.4347740650177006,
|
|
"epoch": 2.6348065367552085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043151491808830777,
|
|
"loss": 5.1981,
|
|
"mean_token_accuracy": 0.19436035603284835,
|
|
"num_tokens": 52391550.0,
|
|
"step": 23460
|
|
},
|
|
{
|
|
"entropy": 5.429052019119263,
|
|
"epoch": 2.635368113663166,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043148607243086255,
|
|
"loss": 5.1146,
|
|
"mean_token_accuracy": 0.2012385442852974,
|
|
"num_tokens": 52401339.0,
|
|
"step": 23465
|
|
},
|
|
{
|
|
"entropy": 5.489598369598388,
|
|
"epoch": 2.635929690571124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004314572217908399,
|
|
"loss": 5.2022,
|
|
"mean_token_accuracy": 0.19932886511087416,
|
|
"num_tokens": 52412062.0,
|
|
"step": 23470
|
|
},
|
|
{
|
|
"entropy": 5.474435806274414,
|
|
"epoch": 2.636491267479081,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004314283661691587,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.20096951872110366,
|
|
"num_tokens": 52422524.0,
|
|
"step": 23475
|
|
},
|
|
{
|
|
"entropy": 5.531504774093628,
|
|
"epoch": 2.6370528443870387,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004313995055667377,
|
|
"loss": 5.2634,
|
|
"mean_token_accuracy": 0.19503721594810486,
|
|
"num_tokens": 52433422.0,
|
|
"step": 23480
|
|
},
|
|
{
|
|
"entropy": 5.5001177310943605,
|
|
"epoch": 2.6376144212949963,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004313706399844958,
|
|
"loss": 5.2588,
|
|
"mean_token_accuracy": 0.19336355328559876,
|
|
"num_tokens": 52443879.0,
|
|
"step": 23485
|
|
},
|
|
{
|
|
"entropy": 5.471763610839844,
|
|
"epoch": 2.638175998202954,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000431341769423352,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.19654588997364045,
|
|
"num_tokens": 52455610.0,
|
|
"step": 23490
|
|
},
|
|
{
|
|
"entropy": 5.504559803009033,
|
|
"epoch": 2.6387375751109117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004313128938842257,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.20162230283021926,
|
|
"num_tokens": 52467392.0,
|
|
"step": 23495
|
|
},
|
|
{
|
|
"entropy": 5.496713638305664,
|
|
"epoch": 2.639299152018869,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043128401336803616,
|
|
"loss": 5.114,
|
|
"mean_token_accuracy": 0.20307174623012542,
|
|
"num_tokens": 52478812.0,
|
|
"step": 23500
|
|
},
|
|
{
|
|
"entropy": 5.439522075653076,
|
|
"epoch": 2.6398607289268265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043125512787570305,
|
|
"loss": 5.2251,
|
|
"mean_token_accuracy": 0.20429726541042328,
|
|
"num_tokens": 52488837.0,
|
|
"step": 23505
|
|
},
|
|
{
|
|
"entropy": 5.447038459777832,
|
|
"epoch": 2.640422305834784,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004312262374081461,
|
|
"loss": 5.2902,
|
|
"mean_token_accuracy": 0.19265440851449966,
|
|
"num_tokens": 52501656.0,
|
|
"step": 23510
|
|
},
|
|
{
|
|
"entropy": 5.40860390663147,
|
|
"epoch": 2.6409838827427414,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00043119734196628507,
|
|
"loss": 5.1463,
|
|
"mean_token_accuracy": 0.19891251921653746,
|
|
"num_tokens": 52512280.0,
|
|
"step": 23515
|
|
},
|
|
{
|
|
"entropy": 5.425860929489136,
|
|
"epoch": 2.641545459650699,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00043116844155104025,
|
|
"loss": 5.1991,
|
|
"mean_token_accuracy": 0.2059519574046135,
|
|
"num_tokens": 52523664.0,
|
|
"step": 23520
|
|
},
|
|
{
|
|
"entropy": 5.479738712310791,
|
|
"epoch": 2.6421070365586568,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004311395361633316,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19505884796380996,
|
|
"num_tokens": 52534913.0,
|
|
"step": 23525
|
|
},
|
|
{
|
|
"entropy": 5.402557754516602,
|
|
"epoch": 2.6426686134666144,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004311106258040795,
|
|
"loss": 5.1225,
|
|
"mean_token_accuracy": 0.20670538246631623,
|
|
"num_tokens": 52545576.0,
|
|
"step": 23530
|
|
},
|
|
{
|
|
"entropy": 5.528948545455933,
|
|
"epoch": 2.643230190374572,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043108171047420463,
|
|
"loss": 5.224,
|
|
"mean_token_accuracy": 0.19745125621557236,
|
|
"num_tokens": 52556136.0,
|
|
"step": 23535
|
|
},
|
|
{
|
|
"entropy": 5.443972253799439,
|
|
"epoch": 2.6437917672825293,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004310527901746275,
|
|
"loss": 5.232,
|
|
"mean_token_accuracy": 0.19617877006530762,
|
|
"num_tokens": 52567425.0,
|
|
"step": 23540
|
|
},
|
|
{
|
|
"entropy": 5.446210861206055,
|
|
"epoch": 2.644353344190487,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000431023864906269,
|
|
"loss": 5.1482,
|
|
"mean_token_accuracy": 0.2038666382431984,
|
|
"num_tokens": 52578040.0,
|
|
"step": 23545
|
|
},
|
|
{
|
|
"entropy": 5.4122522354125975,
|
|
"epoch": 2.6449149210984446,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043099493467005015,
|
|
"loss": 5.0787,
|
|
"mean_token_accuracy": 0.20981689393520356,
|
|
"num_tokens": 52588261.0,
|
|
"step": 23550
|
|
},
|
|
{
|
|
"entropy": 5.339277982711792,
|
|
"epoch": 2.645476498006402,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000430965999466892,
|
|
"loss": 5.1478,
|
|
"mean_token_accuracy": 0.20336427837610244,
|
|
"num_tokens": 52599522.0,
|
|
"step": 23555
|
|
},
|
|
{
|
|
"entropy": 5.516213083267212,
|
|
"epoch": 2.6460380749143595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043093705929771604,
|
|
"loss": 5.3002,
|
|
"mean_token_accuracy": 0.1911569729447365,
|
|
"num_tokens": 52610244.0,
|
|
"step": 23560
|
|
},
|
|
{
|
|
"entropy": 5.637826299667358,
|
|
"epoch": 2.646599651822317,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004309081141634436,
|
|
"loss": 5.2777,
|
|
"mean_token_accuracy": 0.2008344918489456,
|
|
"num_tokens": 52621745.0,
|
|
"step": 23565
|
|
},
|
|
{
|
|
"entropy": 5.43931884765625,
|
|
"epoch": 2.6471612287302744,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043087916406499635,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.20266785025596618,
|
|
"num_tokens": 52633089.0,
|
|
"step": 23570
|
|
},
|
|
{
|
|
"entropy": 5.50287618637085,
|
|
"epoch": 2.647722805638232,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043085020900329604,
|
|
"loss": 5.2475,
|
|
"mean_token_accuracy": 0.19872048497200012,
|
|
"num_tokens": 52644911.0,
|
|
"step": 23575
|
|
},
|
|
{
|
|
"entropy": 5.421200942993164,
|
|
"epoch": 2.6482843825461897,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00043082124897926463,
|
|
"loss": 5.0309,
|
|
"mean_token_accuracy": 0.20765722095966338,
|
|
"num_tokens": 52656958.0,
|
|
"step": 23580
|
|
},
|
|
{
|
|
"entropy": 5.463959455490112,
|
|
"epoch": 2.6488459594541474,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004307922839938242,
|
|
"loss": 5.2517,
|
|
"mean_token_accuracy": 0.1970493331551552,
|
|
"num_tokens": 52668988.0,
|
|
"step": 23585
|
|
},
|
|
{
|
|
"entropy": 5.418364477157593,
|
|
"epoch": 2.649407536362105,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00043076331404789703,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.20075086057186126,
|
|
"num_tokens": 52679948.0,
|
|
"step": 23590
|
|
},
|
|
{
|
|
"entropy": 5.4857429504394535,
|
|
"epoch": 2.6499691132700622,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004307343391424055,
|
|
"loss": 5.1531,
|
|
"mean_token_accuracy": 0.20259717404842376,
|
|
"num_tokens": 52690249.0,
|
|
"step": 23595
|
|
},
|
|
{
|
|
"entropy": 5.466052532196045,
|
|
"epoch": 2.65053069017802,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004307053592782723,
|
|
"loss": 5.2599,
|
|
"mean_token_accuracy": 0.19687810391187668,
|
|
"num_tokens": 52702766.0,
|
|
"step": 23600
|
|
},
|
|
{
|
|
"entropy": 5.507641744613648,
|
|
"epoch": 2.6510922670859776,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043067637445642004,
|
|
"loss": 5.2193,
|
|
"mean_token_accuracy": 0.20140135586261748,
|
|
"num_tokens": 52714252.0,
|
|
"step": 23605
|
|
},
|
|
{
|
|
"entropy": 5.5219583988189695,
|
|
"epoch": 2.651653843993935,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043064738467777166,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.20015569776296616,
|
|
"num_tokens": 52724748.0,
|
|
"step": 23610
|
|
},
|
|
{
|
|
"entropy": 5.382074928283691,
|
|
"epoch": 2.6522154209018924,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00043061838994325007,
|
|
"loss": 5.2297,
|
|
"mean_token_accuracy": 0.20015106052160264,
|
|
"num_tokens": 52735636.0,
|
|
"step": 23615
|
|
},
|
|
{
|
|
"entropy": 5.588220453262329,
|
|
"epoch": 2.65277699780985,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043058939025377867,
|
|
"loss": 5.3802,
|
|
"mean_token_accuracy": 0.18982032239437102,
|
|
"num_tokens": 52747812.0,
|
|
"step": 23620
|
|
},
|
|
{
|
|
"entropy": 5.476462459564209,
|
|
"epoch": 2.6533385747178078,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004305603856102808,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.20483132004737853,
|
|
"num_tokens": 52759322.0,
|
|
"step": 23625
|
|
},
|
|
{
|
|
"entropy": 5.423488759994507,
|
|
"epoch": 2.6539001516257654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004305313760136799,
|
|
"loss": 5.1505,
|
|
"mean_token_accuracy": 0.20266229063272476,
|
|
"num_tokens": 52770238.0,
|
|
"step": 23630
|
|
},
|
|
{
|
|
"entropy": 5.495715951919555,
|
|
"epoch": 2.6544617285337226,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043050236146489955,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.19904519915580748,
|
|
"num_tokens": 52781243.0,
|
|
"step": 23635
|
|
},
|
|
{
|
|
"entropy": 5.468899202346802,
|
|
"epoch": 2.6550233054416803,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004304733419648638,
|
|
"loss": 5.1155,
|
|
"mean_token_accuracy": 0.20217693150043486,
|
|
"num_tokens": 52791341.0,
|
|
"step": 23640
|
|
},
|
|
{
|
|
"entropy": 5.466872596740723,
|
|
"epoch": 2.655584882349638,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00043044431751449656,
|
|
"loss": 5.2559,
|
|
"mean_token_accuracy": 0.1948439061641693,
|
|
"num_tokens": 52803322.0,
|
|
"step": 23645
|
|
},
|
|
{
|
|
"entropy": 5.309941911697388,
|
|
"epoch": 2.656146459257595,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004304152881147219,
|
|
"loss": 5.0509,
|
|
"mean_token_accuracy": 0.20588525384664536,
|
|
"num_tokens": 52813561.0,
|
|
"step": 23650
|
|
},
|
|
{
|
|
"entropy": 5.470542907714844,
|
|
"epoch": 2.656708036165553,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004303862537664642,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1986598938703537,
|
|
"num_tokens": 52824150.0,
|
|
"step": 23655
|
|
},
|
|
{
|
|
"entropy": 5.369553184509277,
|
|
"epoch": 2.6572696130735105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000430357214470648,
|
|
"loss": 5.037,
|
|
"mean_token_accuracy": 0.20996638089418412,
|
|
"num_tokens": 52835013.0,
|
|
"step": 23660
|
|
},
|
|
{
|
|
"entropy": 5.485597848892212,
|
|
"epoch": 2.6578311899814677,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004303281702281977,
|
|
"loss": 5.274,
|
|
"mean_token_accuracy": 0.2037332087755203,
|
|
"num_tokens": 52846682.0,
|
|
"step": 23665
|
|
},
|
|
{
|
|
"entropy": 5.354719161987305,
|
|
"epoch": 2.6583927668894254,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043029912104003827,
|
|
"loss": 5.1298,
|
|
"mean_token_accuracy": 0.19606436491012574,
|
|
"num_tokens": 52857561.0,
|
|
"step": 23670
|
|
},
|
|
{
|
|
"entropy": 5.461483144760132,
|
|
"epoch": 2.658954343797383,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043027006690709457,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.2042285367846489,
|
|
"num_tokens": 52868833.0,
|
|
"step": 23675
|
|
},
|
|
{
|
|
"entropy": 5.537949895858764,
|
|
"epoch": 2.6595159207053407,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004302410078302918,
|
|
"loss": 5.2581,
|
|
"mean_token_accuracy": 0.1963317260146141,
|
|
"num_tokens": 52879725.0,
|
|
"step": 23680
|
|
},
|
|
{
|
|
"entropy": 5.529873418807983,
|
|
"epoch": 2.6600774976132984,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043021194381055505,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.19189532101154327,
|
|
"num_tokens": 52890585.0,
|
|
"step": 23685
|
|
},
|
|
{
|
|
"entropy": 5.532176113128662,
|
|
"epoch": 2.6606390745212556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00043018287484880986,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.1902641087770462,
|
|
"num_tokens": 52902816.0,
|
|
"step": 23690
|
|
},
|
|
{
|
|
"entropy": 5.606956577301025,
|
|
"epoch": 2.6612006514292132,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004301538009459817,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.19303686320781707,
|
|
"num_tokens": 52914523.0,
|
|
"step": 23695
|
|
},
|
|
{
|
|
"entropy": 5.5087635040283205,
|
|
"epoch": 2.661762228337171,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004301247221029964,
|
|
"loss": 5.2234,
|
|
"mean_token_accuracy": 0.20332218706607819,
|
|
"num_tokens": 52924953.0,
|
|
"step": 23700
|
|
},
|
|
{
|
|
"entropy": 5.358062410354615,
|
|
"epoch": 2.662323805245128,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043009563832077977,
|
|
"loss": 5.0824,
|
|
"mean_token_accuracy": 0.20505772531032562,
|
|
"num_tokens": 52935435.0,
|
|
"step": 23705
|
|
},
|
|
{
|
|
"entropy": 5.440538024902343,
|
|
"epoch": 2.662885382153086,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004300665496002578,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.19805682450532913,
|
|
"num_tokens": 52946969.0,
|
|
"step": 23710
|
|
},
|
|
{
|
|
"entropy": 5.442613029479981,
|
|
"epoch": 2.6634469590610435,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043003745594235687,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.19808029532432556,
|
|
"num_tokens": 52958634.0,
|
|
"step": 23715
|
|
},
|
|
{
|
|
"entropy": 5.473411178588867,
|
|
"epoch": 2.664008535969001,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004300083573480031,
|
|
"loss": 5.1178,
|
|
"mean_token_accuracy": 0.2041054755449295,
|
|
"num_tokens": 52968412.0,
|
|
"step": 23720
|
|
},
|
|
{
|
|
"entropy": 5.361675691604614,
|
|
"epoch": 2.6645701128769588,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042997925381812313,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.19862494468688965,
|
|
"num_tokens": 52978653.0,
|
|
"step": 23725
|
|
},
|
|
{
|
|
"entropy": 5.423910188674927,
|
|
"epoch": 2.665131689784916,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042995014535364363,
|
|
"loss": 5.1526,
|
|
"mean_token_accuracy": 0.20615407526493074,
|
|
"num_tokens": 52988518.0,
|
|
"step": 23730
|
|
},
|
|
{
|
|
"entropy": 5.4081157684326175,
|
|
"epoch": 2.6656932666928737,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004299210319554914,
|
|
"loss": 5.122,
|
|
"mean_token_accuracy": 0.2010425642132759,
|
|
"num_tokens": 52999271.0,
|
|
"step": 23735
|
|
},
|
|
{
|
|
"entropy": 5.424631834030151,
|
|
"epoch": 2.6662548436008313,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042989191362459347,
|
|
"loss": 5.2277,
|
|
"mean_token_accuracy": 0.20586954802274704,
|
|
"num_tokens": 53010530.0,
|
|
"step": 23740
|
|
},
|
|
{
|
|
"entropy": 5.459703159332276,
|
|
"epoch": 2.6668164205087885,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004298627903618769,
|
|
"loss": 5.2157,
|
|
"mean_token_accuracy": 0.19880502969026564,
|
|
"num_tokens": 53021631.0,
|
|
"step": 23745
|
|
},
|
|
{
|
|
"entropy": 5.46162600517273,
|
|
"epoch": 2.667377997416746,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042983366216826907,
|
|
"loss": 5.1574,
|
|
"mean_token_accuracy": 0.2006342813372612,
|
|
"num_tokens": 53033763.0,
|
|
"step": 23750
|
|
},
|
|
{
|
|
"entropy": 5.439314317703247,
|
|
"epoch": 2.667939574324704,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004298045290446973,
|
|
"loss": 5.201,
|
|
"mean_token_accuracy": 0.1981994017958641,
|
|
"num_tokens": 53045839.0,
|
|
"step": 23755
|
|
},
|
|
{
|
|
"entropy": 5.473497486114502,
|
|
"epoch": 2.668501151232661,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00042977539099208937,
|
|
"loss": 5.2132,
|
|
"mean_token_accuracy": 0.19620386511087418,
|
|
"num_tokens": 53057295.0,
|
|
"step": 23760
|
|
},
|
|
{
|
|
"entropy": 5.620213317871094,
|
|
"epoch": 2.6690627281406187,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042974624801137283,
|
|
"loss": 5.4089,
|
|
"mean_token_accuracy": 0.18657888174057008,
|
|
"num_tokens": 53068595.0,
|
|
"step": 23765
|
|
},
|
|
{
|
|
"entropy": 5.4897346019744875,
|
|
"epoch": 2.6696243050485764,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042971710010347594,
|
|
"loss": 5.1634,
|
|
"mean_token_accuracy": 0.2015192076563835,
|
|
"num_tokens": 53080170.0,
|
|
"step": 23770
|
|
},
|
|
{
|
|
"entropy": 5.408882570266724,
|
|
"epoch": 2.670185881956534,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042968794726932634,
|
|
"loss": 5.1257,
|
|
"mean_token_accuracy": 0.2001305028796196,
|
|
"num_tokens": 53090894.0,
|
|
"step": 23775
|
|
},
|
|
{
|
|
"entropy": 5.444377088546753,
|
|
"epoch": 2.6707474588644917,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004296587895098527,
|
|
"loss": 5.2758,
|
|
"mean_token_accuracy": 0.19684267044067383,
|
|
"num_tokens": 53103732.0,
|
|
"step": 23780
|
|
},
|
|
{
|
|
"entropy": 5.55993390083313,
|
|
"epoch": 2.671309035772449,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042962962682598316,
|
|
"loss": 5.2012,
|
|
"mean_token_accuracy": 0.19872934222221375,
|
|
"num_tokens": 53115237.0,
|
|
"step": 23785
|
|
},
|
|
{
|
|
"entropy": 5.49130163192749,
|
|
"epoch": 2.6718706126804066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00042960045921864627,
|
|
"loss": 5.1493,
|
|
"mean_token_accuracy": 0.20115361213684083,
|
|
"num_tokens": 53125638.0,
|
|
"step": 23790
|
|
},
|
|
{
|
|
"entropy": 5.348725748062134,
|
|
"epoch": 2.6724321895883643,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004295712866887709,
|
|
"loss": 5.121,
|
|
"mean_token_accuracy": 0.20696690827608108,
|
|
"num_tokens": 53136153.0,
|
|
"step": 23795
|
|
},
|
|
{
|
|
"entropy": 5.454218149185181,
|
|
"epoch": 2.6729937664963215,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042954210923728565,
|
|
"loss": 5.2061,
|
|
"mean_token_accuracy": 0.20082892328500748,
|
|
"num_tokens": 53146562.0,
|
|
"step": 23800
|
|
},
|
|
{
|
|
"entropy": 5.60269603729248,
|
|
"epoch": 2.673555343404279,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004295129268651198,
|
|
"loss": 5.3095,
|
|
"mean_token_accuracy": 0.19268049746751786,
|
|
"num_tokens": 53158460.0,
|
|
"step": 23805
|
|
},
|
|
{
|
|
"entropy": 5.472504997253418,
|
|
"epoch": 2.674116920312237,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004294837395732025,
|
|
"loss": 5.1935,
|
|
"mean_token_accuracy": 0.20357325226068496,
|
|
"num_tokens": 53170576.0,
|
|
"step": 23810
|
|
},
|
|
{
|
|
"entropy": 5.426251173019409,
|
|
"epoch": 2.6746784972201945,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042945454736246293,
|
|
"loss": 5.113,
|
|
"mean_token_accuracy": 0.20715031325817107,
|
|
"num_tokens": 53181658.0,
|
|
"step": 23815
|
|
},
|
|
{
|
|
"entropy": 5.491357898712158,
|
|
"epoch": 2.675240074128152,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042942535023383075,
|
|
"loss": 5.24,
|
|
"mean_token_accuracy": 0.1936383068561554,
|
|
"num_tokens": 53193983.0,
|
|
"step": 23820
|
|
},
|
|
{
|
|
"entropy": 5.44902663230896,
|
|
"epoch": 2.6758016510361093,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042939614818823547,
|
|
"loss": 5.1629,
|
|
"mean_token_accuracy": 0.19764706790447234,
|
|
"num_tokens": 53205603.0,
|
|
"step": 23825
|
|
},
|
|
{
|
|
"entropy": 5.384964084625244,
|
|
"epoch": 2.676363227944067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004293669412266069,
|
|
"loss": 5.0823,
|
|
"mean_token_accuracy": 0.20538148432970046,
|
|
"num_tokens": 53216295.0,
|
|
"step": 23830
|
|
},
|
|
{
|
|
"entropy": 5.450446891784668,
|
|
"epoch": 2.6769248048520247,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004293377293498751,
|
|
"loss": 5.1693,
|
|
"mean_token_accuracy": 0.2076178401708603,
|
|
"num_tokens": 53227055.0,
|
|
"step": 23835
|
|
},
|
|
{
|
|
"entropy": 5.4947975158691404,
|
|
"epoch": 2.677486381759982,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00042930851255897014,
|
|
"loss": 5.1903,
|
|
"mean_token_accuracy": 0.20396430045366287,
|
|
"num_tokens": 53239050.0,
|
|
"step": 23840
|
|
},
|
|
{
|
|
"entropy": 5.396909618377686,
|
|
"epoch": 2.6780479586679395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004292792908548223,
|
|
"loss": 5.078,
|
|
"mean_token_accuracy": 0.20368672907352448,
|
|
"num_tokens": 53249551.0,
|
|
"step": 23845
|
|
},
|
|
{
|
|
"entropy": 5.472092390060425,
|
|
"epoch": 2.678609535575897,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00042925006423836197,
|
|
"loss": 5.2797,
|
|
"mean_token_accuracy": 0.19313735216856004,
|
|
"num_tokens": 53261645.0,
|
|
"step": 23850
|
|
},
|
|
{
|
|
"entropy": 5.536790657043457,
|
|
"epoch": 2.6791711124838544,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042922083271051975,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.19853435158729554,
|
|
"num_tokens": 53272601.0,
|
|
"step": 23855
|
|
},
|
|
{
|
|
"entropy": 5.490668439865113,
|
|
"epoch": 2.679732689391812,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004291915962722265,
|
|
"loss": 5.2004,
|
|
"mean_token_accuracy": 0.20072415322065354,
|
|
"num_tokens": 53283190.0,
|
|
"step": 23860
|
|
},
|
|
{
|
|
"entropy": 5.451309680938721,
|
|
"epoch": 2.6802942662997697,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004291623549244129,
|
|
"loss": 5.1592,
|
|
"mean_token_accuracy": 0.20290247052907945,
|
|
"num_tokens": 53294374.0,
|
|
"step": 23865
|
|
},
|
|
{
|
|
"entropy": 5.485828876495361,
|
|
"epoch": 2.6808558432077274,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042913310866801024,
|
|
"loss": 5.2978,
|
|
"mean_token_accuracy": 0.195500048995018,
|
|
"num_tokens": 53305609.0,
|
|
"step": 23870
|
|
},
|
|
{
|
|
"entropy": 5.339949131011963,
|
|
"epoch": 2.681417420115685,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042910385750394964,
|
|
"loss": 5.1163,
|
|
"mean_token_accuracy": 0.20789167433977127,
|
|
"num_tokens": 53316251.0,
|
|
"step": 23875
|
|
},
|
|
{
|
|
"entropy": 5.423102617263794,
|
|
"epoch": 2.6819789970236423,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004290746014331623,
|
|
"loss": 5.0828,
|
|
"mean_token_accuracy": 0.20478476732969284,
|
|
"num_tokens": 53326798.0,
|
|
"step": 23880
|
|
},
|
|
{
|
|
"entropy": 5.480163478851319,
|
|
"epoch": 2.6825405739316,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042904534045658,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.19889452010393144,
|
|
"num_tokens": 53337586.0,
|
|
"step": 23885
|
|
},
|
|
{
|
|
"entropy": 5.510830020904541,
|
|
"epoch": 2.6831021508395576,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004290160745751343,
|
|
"loss": 5.2442,
|
|
"mean_token_accuracy": 0.19539697617292404,
|
|
"num_tokens": 53348517.0,
|
|
"step": 23890
|
|
},
|
|
{
|
|
"entropy": 5.47496223449707,
|
|
"epoch": 2.683663727747515,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004289868037897571,
|
|
"loss": 5.1888,
|
|
"mean_token_accuracy": 0.20575479716062545,
|
|
"num_tokens": 53358937.0,
|
|
"step": 23895
|
|
},
|
|
{
|
|
"entropy": 5.399774360656738,
|
|
"epoch": 2.6842253046554725,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004289575281013802,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.2057294324040413,
|
|
"num_tokens": 53370007.0,
|
|
"step": 23900
|
|
},
|
|
{
|
|
"entropy": 5.377556610107422,
|
|
"epoch": 2.68478688156343,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000428928247510936,
|
|
"loss": 5.0459,
|
|
"mean_token_accuracy": 0.20521009862422943,
|
|
"num_tokens": 53380913.0,
|
|
"step": 23905
|
|
},
|
|
{
|
|
"entropy": 5.405971050262451,
|
|
"epoch": 2.685348458471388,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004288989620193567,
|
|
"loss": 5.1689,
|
|
"mean_token_accuracy": 0.19813993722200393,
|
|
"num_tokens": 53392526.0,
|
|
"step": 23910
|
|
},
|
|
{
|
|
"entropy": 5.463215732574463,
|
|
"epoch": 2.6859100353793455,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00042886967162757475,
|
|
"loss": 5.2133,
|
|
"mean_token_accuracy": 0.200523978471756,
|
|
"num_tokens": 53404522.0,
|
|
"step": 23915
|
|
},
|
|
{
|
|
"entropy": 5.460058498382568,
|
|
"epoch": 2.6864716122873027,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042884037633652276,
|
|
"loss": 5.1247,
|
|
"mean_token_accuracy": 0.20649925768375396,
|
|
"num_tokens": 53415156.0,
|
|
"step": 23920
|
|
},
|
|
{
|
|
"entropy": 5.479532909393311,
|
|
"epoch": 2.6870331891952604,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042881107614713355,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.19177641421556474,
|
|
"num_tokens": 53426297.0,
|
|
"step": 23925
|
|
},
|
|
{
|
|
"entropy": 5.582530498504639,
|
|
"epoch": 2.687594766103218,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042878177106034,
|
|
"loss": 5.309,
|
|
"mean_token_accuracy": 0.19136786460876465,
|
|
"num_tokens": 53438415.0,
|
|
"step": 23930
|
|
},
|
|
{
|
|
"entropy": 5.415176105499268,
|
|
"epoch": 2.6881563430111752,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004287524610770752,
|
|
"loss": 5.2542,
|
|
"mean_token_accuracy": 0.19446880966424943,
|
|
"num_tokens": 53450103.0,
|
|
"step": 23935
|
|
},
|
|
{
|
|
"entropy": 5.438649892807007,
|
|
"epoch": 2.688717919919133,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042872314619827234,
|
|
"loss": 5.1111,
|
|
"mean_token_accuracy": 0.20191027969121933,
|
|
"num_tokens": 53461440.0,
|
|
"step": 23940
|
|
},
|
|
{
|
|
"entropy": 5.590681457519532,
|
|
"epoch": 2.6892794968270906,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000428693826424865,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.19203422516584395,
|
|
"num_tokens": 53472369.0,
|
|
"step": 23945
|
|
},
|
|
{
|
|
"entropy": 5.455559396743775,
|
|
"epoch": 2.6898410737350478,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004286645017577866,
|
|
"loss": 5.2239,
|
|
"mean_token_accuracy": 0.20120565742254257,
|
|
"num_tokens": 53483739.0,
|
|
"step": 23950
|
|
},
|
|
{
|
|
"entropy": 5.493955039978028,
|
|
"epoch": 2.6904026506430054,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00042863517219797085,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19455630779266359,
|
|
"num_tokens": 53494131.0,
|
|
"step": 23955
|
|
},
|
|
{
|
|
"entropy": 5.5421349048614506,
|
|
"epoch": 2.690964227550963,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00042860583774635165,
|
|
"loss": 5.2448,
|
|
"mean_token_accuracy": 0.19452330023050307,
|
|
"num_tokens": 53504923.0,
|
|
"step": 23960
|
|
},
|
|
{
|
|
"entropy": 5.520519876480103,
|
|
"epoch": 2.6915258044589208,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000428576498403863,
|
|
"loss": 5.262,
|
|
"mean_token_accuracy": 0.1902679905295372,
|
|
"num_tokens": 53516660.0,
|
|
"step": 23965
|
|
},
|
|
{
|
|
"entropy": 5.374493360519409,
|
|
"epoch": 2.6920873813668784,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000428547154171439,
|
|
"loss": 5.0553,
|
|
"mean_token_accuracy": 0.21137415021657943,
|
|
"num_tokens": 53527617.0,
|
|
"step": 23970
|
|
},
|
|
{
|
|
"entropy": 5.437328481674195,
|
|
"epoch": 2.6926489582748356,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004285178050500142,
|
|
"loss": 5.1964,
|
|
"mean_token_accuracy": 0.19799984246492386,
|
|
"num_tokens": 53537830.0,
|
|
"step": 23975
|
|
},
|
|
{
|
|
"entropy": 5.590660810470581,
|
|
"epoch": 2.6932105351827933,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004284884510405228,
|
|
"loss": 5.3299,
|
|
"mean_token_accuracy": 0.19519096463918686,
|
|
"num_tokens": 53549981.0,
|
|
"step": 23980
|
|
},
|
|
{
|
|
"entropy": 5.501504230499267,
|
|
"epoch": 2.693772112090751,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004284590921438997,
|
|
"loss": 5.194,
|
|
"mean_token_accuracy": 0.19998874366283417,
|
|
"num_tokens": 53559941.0,
|
|
"step": 23985
|
|
},
|
|
{
|
|
"entropy": 5.36891918182373,
|
|
"epoch": 2.694333688998708,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00042842972836107954,
|
|
"loss": 5.076,
|
|
"mean_token_accuracy": 0.20204403549432753,
|
|
"num_tokens": 53571611.0,
|
|
"step": 23990
|
|
},
|
|
{
|
|
"entropy": 5.495262670516968,
|
|
"epoch": 2.694895265906666,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004284003596929973,
|
|
"loss": 5.1438,
|
|
"mean_token_accuracy": 0.19754309356212615,
|
|
"num_tokens": 53582425.0,
|
|
"step": 23995
|
|
},
|
|
{
|
|
"entropy": 5.529087686538697,
|
|
"epoch": 2.6954568428146235,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042837098614058815,
|
|
"loss": 5.276,
|
|
"mean_token_accuracy": 0.19742352664470672,
|
|
"num_tokens": 53593576.0,
|
|
"step": 24000
|
|
},
|
|
{
|
|
"epoch": 2.6954568428146235,
|
|
"eval_entropy": 5.253419952353221,
|
|
"eval_loss": 5.291341304779053,
|
|
"eval_mean_token_accuracy": 0.20357133003241443,
|
|
"eval_num_tokens": 53593576.0,
|
|
"eval_runtime": 23.8808,
|
|
"eval_samples_per_second": 1298.659,
|
|
"eval_steps_per_second": 162.348,
|
|
"step": 24000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 89030,
|
|
"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": 8.4013843534848e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|