380cd5d987
Model: fpadovani/swe-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
30090 lines
826 KiB
JSON
30090 lines
826 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.2601974375131275,
|
|
"eval_steps": 3000,
|
|
"global_step": 15000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 4.791903686523438,
|
|
"epoch": 0.0004200798151648813,
|
|
"grad_norm": 14.6875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 14.3853,
|
|
"mean_token_accuracy": 0.0001464128843508661,
|
|
"num_tokens": 8348.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 4.770248889923096,
|
|
"epoch": 0.0008401596303297626,
|
|
"grad_norm": 13.5,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 14.3427,
|
|
"mean_token_accuracy": 0.00011325028026476502,
|
|
"num_tokens": 17465.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 4.853783750534058,
|
|
"epoch": 0.001260239445494644,
|
|
"grad_norm": 19.875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 14.1261,
|
|
"mean_token_accuracy": 0.00010341261513531208,
|
|
"num_tokens": 26627.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 5.086610746383667,
|
|
"epoch": 0.0016803192606595252,
|
|
"grad_norm": 28.375,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 13.5157,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 36069.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.3999251365661625,
|
|
"epoch": 0.002100399075824407,
|
|
"grad_norm": 12.0625,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 11.7927,
|
|
"mean_token_accuracy": 0.0,
|
|
"num_tokens": 44967.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 10.45841064453125,
|
|
"epoch": 0.002520478890989288,
|
|
"grad_norm": 3.015625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 10.7852,
|
|
"mean_token_accuracy": 9.009009227156639e-05,
|
|
"num_tokens": 55132.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 10.697011375427246,
|
|
"epoch": 0.0029405587061541692,
|
|
"grad_norm": 2.75,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 10.5553,
|
|
"mean_token_accuracy": 0.006346415734151378,
|
|
"num_tokens": 65141.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 10.697507858276367,
|
|
"epoch": 0.0033606385213190504,
|
|
"grad_norm": 2.40625,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 10.2781,
|
|
"mean_token_accuracy": 0.039602359384298326,
|
|
"num_tokens": 74007.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 10.668922233581544,
|
|
"epoch": 0.003780718336483932,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 9.9863,
|
|
"mean_token_accuracy": 0.04357385709881782,
|
|
"num_tokens": 83736.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 10.582208251953125,
|
|
"epoch": 0.004200798151648814,
|
|
"grad_norm": 2.09375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 9.7817,
|
|
"mean_token_accuracy": 0.044408387318253514,
|
|
"num_tokens": 92525.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 10.561583709716796,
|
|
"epoch": 0.004620877966813695,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 9.6616,
|
|
"mean_token_accuracy": 0.042681990377604964,
|
|
"num_tokens": 102015.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 10.598667430877686,
|
|
"epoch": 0.005040957781978576,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 9.6152,
|
|
"mean_token_accuracy": 0.03954915180802345,
|
|
"num_tokens": 110887.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 10.602967929840087,
|
|
"epoch": 0.005461037597143457,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 9.5219,
|
|
"mean_token_accuracy": 0.04232911877334118,
|
|
"num_tokens": 120442.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 10.583982849121094,
|
|
"epoch": 0.0058811174123083385,
|
|
"grad_norm": 2.0625,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 9.4106,
|
|
"mean_token_accuracy": 0.041194649040699007,
|
|
"num_tokens": 129297.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 10.561800956726074,
|
|
"epoch": 0.00630119722747322,
|
|
"grad_norm": 1.921875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 9.3205,
|
|
"mean_token_accuracy": 0.04238409399986267,
|
|
"num_tokens": 138305.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 10.55169849395752,
|
|
"epoch": 0.006721277042638101,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 9.2587,
|
|
"mean_token_accuracy": 0.04415187537670136,
|
|
"num_tokens": 147640.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 10.53596887588501,
|
|
"epoch": 0.007141356857802983,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 9.156,
|
|
"mean_token_accuracy": 0.05057476349174976,
|
|
"num_tokens": 157633.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 10.498776817321778,
|
|
"epoch": 0.007561436672967864,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 9.1055,
|
|
"mean_token_accuracy": 0.043933939374983313,
|
|
"num_tokens": 167984.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 10.410062026977538,
|
|
"epoch": 0.007981516488132745,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 8.9796,
|
|
"mean_token_accuracy": 0.058869444206357,
|
|
"num_tokens": 176984.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 10.331822967529297,
|
|
"epoch": 0.008401596303297627,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 8.8274,
|
|
"mean_token_accuracy": 0.05482011772692204,
|
|
"num_tokens": 185931.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 10.239299774169922,
|
|
"epoch": 0.008821676118462508,
|
|
"grad_norm": 2.265625,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 8.7979,
|
|
"mean_token_accuracy": 0.05091267079114914,
|
|
"num_tokens": 195065.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 10.274462223052979,
|
|
"epoch": 0.00924175593362739,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 8.653,
|
|
"mean_token_accuracy": 0.053716998919844626,
|
|
"num_tokens": 203687.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 10.133169841766357,
|
|
"epoch": 0.00966183574879227,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 8.5503,
|
|
"mean_token_accuracy": 0.057077201455831526,
|
|
"num_tokens": 212847.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 10.040187549591064,
|
|
"epoch": 0.010081915563957152,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 8.4092,
|
|
"mean_token_accuracy": 0.05596162416040897,
|
|
"num_tokens": 222593.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 9.901103496551514,
|
|
"epoch": 0.010501995379122032,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 8.2565,
|
|
"mean_token_accuracy": 0.05481334701180458,
|
|
"num_tokens": 231174.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 9.70338020324707,
|
|
"epoch": 0.010922075194286915,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 8.1158,
|
|
"mean_token_accuracy": 0.058756759762763976,
|
|
"num_tokens": 239833.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 9.529671382904052,
|
|
"epoch": 0.011342155009451797,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 8.1187,
|
|
"mean_token_accuracy": 0.05617605000734329,
|
|
"num_tokens": 248794.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 9.257420444488526,
|
|
"epoch": 0.011762234824616677,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 8.0561,
|
|
"mean_token_accuracy": 0.056496378034353256,
|
|
"num_tokens": 257123.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 9.085350036621094,
|
|
"epoch": 0.012182314639781559,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.7656,
|
|
"mean_token_accuracy": 0.05573978051543236,
|
|
"num_tokens": 266088.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 8.806443977355958,
|
|
"epoch": 0.01260239445494644,
|
|
"grad_norm": 0.81640625,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 7.9249,
|
|
"mean_token_accuracy": 0.05259395204484463,
|
|
"num_tokens": 276074.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 8.64165735244751,
|
|
"epoch": 0.013022474270111321,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 7.8106,
|
|
"mean_token_accuracy": 0.0555482916533947,
|
|
"num_tokens": 285280.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 8.47070608139038,
|
|
"epoch": 0.013442554085276202,
|
|
"grad_norm": 0.80859375,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 7.8078,
|
|
"mean_token_accuracy": 0.05328563526272774,
|
|
"num_tokens": 296115.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 8.336323738098145,
|
|
"epoch": 0.013862633900441084,
|
|
"grad_norm": 0.83984375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 7.6742,
|
|
"mean_token_accuracy": 0.055481255799531934,
|
|
"num_tokens": 305483.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 8.235133361816406,
|
|
"epoch": 0.014282713715605966,
|
|
"grad_norm": 0.82421875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 7.6978,
|
|
"mean_token_accuracy": 0.05532576628029347,
|
|
"num_tokens": 314000.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 8.127510929107666,
|
|
"epoch": 0.014702793530770846,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 7.6891,
|
|
"mean_token_accuracy": 0.05845912620425224,
|
|
"num_tokens": 323667.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 8.085121822357177,
|
|
"epoch": 0.015122873345935728,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 7.6917,
|
|
"mean_token_accuracy": 0.05741722546517849,
|
|
"num_tokens": 332695.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 8.051828241348266,
|
|
"epoch": 0.015542953161100609,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 7.5384,
|
|
"mean_token_accuracy": 0.059001700952649117,
|
|
"num_tokens": 342428.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 8.029651880264282,
|
|
"epoch": 0.01596303297626549,
|
|
"grad_norm": 0.76953125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 7.6438,
|
|
"mean_token_accuracy": 0.05830682367086411,
|
|
"num_tokens": 353587.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 8.02134084701538,
|
|
"epoch": 0.01638311279143037,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 7.5846,
|
|
"mean_token_accuracy": 0.06251729987561702,
|
|
"num_tokens": 362997.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.912688684463501,
|
|
"epoch": 0.016803192606595255,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 7.6088,
|
|
"mean_token_accuracy": 0.06746274717152119,
|
|
"num_tokens": 372346.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 8.052432775497437,
|
|
"epoch": 0.017223272421760135,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000102,
|
|
"loss": 7.4944,
|
|
"mean_token_accuracy": 0.06457214206457138,
|
|
"num_tokens": 381575.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.941053867340088,
|
|
"epoch": 0.017643352236925015,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.561,
|
|
"mean_token_accuracy": 0.06631600968539715,
|
|
"num_tokens": 390706.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.876999855041504,
|
|
"epoch": 0.018063432052089896,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.000107,
|
|
"loss": 7.5529,
|
|
"mean_token_accuracy": 0.0665743712335825,
|
|
"num_tokens": 400000.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.916263389587402,
|
|
"epoch": 0.01848351186725478,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.5184,
|
|
"mean_token_accuracy": 0.06940894797444344,
|
|
"num_tokens": 409447.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.911146783828736,
|
|
"epoch": 0.01890359168241966,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 7.4837,
|
|
"mean_token_accuracy": 0.06915329694747925,
|
|
"num_tokens": 418417.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.839998531341553,
|
|
"epoch": 0.01932367149758454,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 7.4502,
|
|
"mean_token_accuracy": 0.06963084377348423,
|
|
"num_tokens": 427619.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.8366899490356445,
|
|
"epoch": 0.019743751312749424,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 7.5047,
|
|
"mean_token_accuracy": 0.06452232897281647,
|
|
"num_tokens": 437931.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.8866432189941404,
|
|
"epoch": 0.020163831127914304,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 7.546,
|
|
"mean_token_accuracy": 0.06933673955500126,
|
|
"num_tokens": 447595.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.882558917999267,
|
|
"epoch": 0.020583910943079185,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 7.4174,
|
|
"mean_token_accuracy": 0.06523367092013359,
|
|
"num_tokens": 457062.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.839541244506836,
|
|
"epoch": 0.021003990758244065,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 7.5086,
|
|
"mean_token_accuracy": 0.06696470156311989,
|
|
"num_tokens": 466191.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.8005016326904295,
|
|
"epoch": 0.02142407057340895,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 7.451,
|
|
"mean_token_accuracy": 0.06885578371584415,
|
|
"num_tokens": 475693.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.889404010772705,
|
|
"epoch": 0.02184415038857383,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 7.4804,
|
|
"mean_token_accuracy": 0.06973730027675629,
|
|
"num_tokens": 485173.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.815570974349976,
|
|
"epoch": 0.02226423020373871,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000132,
|
|
"loss": 7.3829,
|
|
"mean_token_accuracy": 0.07314893454313279,
|
|
"num_tokens": 493985.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.816596174240113,
|
|
"epoch": 0.022684310018903593,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 7.4224,
|
|
"mean_token_accuracy": 0.07099288031458854,
|
|
"num_tokens": 502837.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.785638856887817,
|
|
"epoch": 0.023104389834068473,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 7.3589,
|
|
"mean_token_accuracy": 0.07525993324816227,
|
|
"num_tokens": 511503.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.709826803207397,
|
|
"epoch": 0.023524469649233354,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 7.5429,
|
|
"mean_token_accuracy": 0.07307531610131264,
|
|
"num_tokens": 521499.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.790460062026978,
|
|
"epoch": 0.023944549464398234,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 7.3077,
|
|
"mean_token_accuracy": 0.07697631418704987,
|
|
"num_tokens": 530067.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.686764717102051,
|
|
"epoch": 0.024364629279563118,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 7.3034,
|
|
"mean_token_accuracy": 0.0773412711918354,
|
|
"num_tokens": 538559.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.772013425827026,
|
|
"epoch": 0.024784709094728,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 7.4929,
|
|
"mean_token_accuracy": 0.07045175209641456,
|
|
"num_tokens": 547288.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.7699915885925295,
|
|
"epoch": 0.02520478890989288,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 7.3747,
|
|
"mean_token_accuracy": 0.07021207436919212,
|
|
"num_tokens": 557269.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.7625007152557375,
|
|
"epoch": 0.025624868725057762,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 7.3902,
|
|
"mean_token_accuracy": 0.07074716240167618,
|
|
"num_tokens": 567280.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.732419967651367,
|
|
"epoch": 0.026044948540222643,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 7.2546,
|
|
"mean_token_accuracy": 0.07402584217488765,
|
|
"num_tokens": 576609.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.543032264709472,
|
|
"epoch": 0.026465028355387523,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000157,
|
|
"loss": 7.1466,
|
|
"mean_token_accuracy": 0.08402636647224426,
|
|
"num_tokens": 586053.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.557563781738281,
|
|
"epoch": 0.026885108170552403,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 7.353,
|
|
"mean_token_accuracy": 0.07976382523775101,
|
|
"num_tokens": 594649.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.672474765777588,
|
|
"epoch": 0.027305187985717287,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 7.299,
|
|
"mean_token_accuracy": 0.0721965666860342,
|
|
"num_tokens": 603445.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.649927425384521,
|
|
"epoch": 0.027725267800882167,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 7.3816,
|
|
"mean_token_accuracy": 0.07200038619339466,
|
|
"num_tokens": 613611.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.817860317230225,
|
|
"epoch": 0.028145347616047048,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 7.5608,
|
|
"mean_token_accuracy": 0.07428344339132309,
|
|
"num_tokens": 623024.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.615134525299072,
|
|
"epoch": 0.02856542743121193,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 7.241,
|
|
"mean_token_accuracy": 0.08163552284240723,
|
|
"num_tokens": 631624.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.6425103664398195,
|
|
"epoch": 0.028985507246376812,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 7.1878,
|
|
"mean_token_accuracy": 0.08015607595443726,
|
|
"num_tokens": 640473.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.680424308776855,
|
|
"epoch": 0.029405587061541692,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 7.3678,
|
|
"mean_token_accuracy": 0.07545013800263405,
|
|
"num_tokens": 649692.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.654160070419311,
|
|
"epoch": 0.029825666876706573,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.000177,
|
|
"loss": 7.319,
|
|
"mean_token_accuracy": 0.07563115619122981,
|
|
"num_tokens": 658236.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.521349573135376,
|
|
"epoch": 0.030245746691871456,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 7.1117,
|
|
"mean_token_accuracy": 0.08184256851673126,
|
|
"num_tokens": 667175.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.665167379379272,
|
|
"epoch": 0.030665826507036337,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 7.3978,
|
|
"mean_token_accuracy": 0.07722308114171028,
|
|
"num_tokens": 676456.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.747646379470825,
|
|
"epoch": 0.031085906322201217,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.3621,
|
|
"mean_token_accuracy": 0.07609389498829841,
|
|
"num_tokens": 686881.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.486468362808227,
|
|
"epoch": 0.0315059861373661,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 7.1472,
|
|
"mean_token_accuracy": 0.08116972967982292,
|
|
"num_tokens": 696045.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.507930612564087,
|
|
"epoch": 0.03192606595253098,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 7.1262,
|
|
"mean_token_accuracy": 0.08457142487168312,
|
|
"num_tokens": 704729.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.4088475704193115,
|
|
"epoch": 0.032346145767695865,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 7.1832,
|
|
"mean_token_accuracy": 0.07680457159876823,
|
|
"num_tokens": 714331.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.597209930419922,
|
|
"epoch": 0.03276622558286074,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 7.139,
|
|
"mean_token_accuracy": 0.08005330711603165,
|
|
"num_tokens": 722788.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.544012260437012,
|
|
"epoch": 0.033186305398025626,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 7.2038,
|
|
"mean_token_accuracy": 0.08137390315532685,
|
|
"num_tokens": 731417.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.463483619689941,
|
|
"epoch": 0.03360638521319051,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 7.1774,
|
|
"mean_token_accuracy": 0.08162600994110107,
|
|
"num_tokens": 741034.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.472280406951905,
|
|
"epoch": 0.034026465028355386,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000202,
|
|
"loss": 7.1863,
|
|
"mean_token_accuracy": 0.08051239103078842,
|
|
"num_tokens": 749596.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.539561700820923,
|
|
"epoch": 0.03444654484352027,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 7.1293,
|
|
"mean_token_accuracy": 0.08054611459374428,
|
|
"num_tokens": 758931.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.323099613189697,
|
|
"epoch": 0.03486662465868515,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 7.0321,
|
|
"mean_token_accuracy": 0.08574115931987762,
|
|
"num_tokens": 767534.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.436507081985473,
|
|
"epoch": 0.03528670447385003,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 7.1087,
|
|
"mean_token_accuracy": 0.0788518838584423,
|
|
"num_tokens": 776456.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.4387647151947025,
|
|
"epoch": 0.035706784289014915,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 7.1659,
|
|
"mean_token_accuracy": 0.07921701893210412,
|
|
"num_tokens": 786172.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.382072401046753,
|
|
"epoch": 0.03612686410417979,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 7.045,
|
|
"mean_token_accuracy": 0.08349293395876885,
|
|
"num_tokens": 795081.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.354331922531128,
|
|
"epoch": 0.036546943919344675,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 7.0961,
|
|
"mean_token_accuracy": 0.07894284576177597,
|
|
"num_tokens": 804259.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.416359519958496,
|
|
"epoch": 0.03696702373450956,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 7.1173,
|
|
"mean_token_accuracy": 0.08117417171597481,
|
|
"num_tokens": 813463.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.3510298252105715,
|
|
"epoch": 0.037387103549674436,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000222,
|
|
"loss": 7.0365,
|
|
"mean_token_accuracy": 0.08668158128857613,
|
|
"num_tokens": 823029.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.395490074157715,
|
|
"epoch": 0.03780718336483932,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 7.0882,
|
|
"mean_token_accuracy": 0.07999400310218334,
|
|
"num_tokens": 832902.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.301269912719727,
|
|
"epoch": 0.0382272631800042,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 7.0386,
|
|
"mean_token_accuracy": 0.08621552512049675,
|
|
"num_tokens": 842162.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.3866761207580565,
|
|
"epoch": 0.03864734299516908,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 7.0749,
|
|
"mean_token_accuracy": 0.08230168521404266,
|
|
"num_tokens": 852328.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.298245000839233,
|
|
"epoch": 0.039067422810333964,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 7.0332,
|
|
"mean_token_accuracy": 0.08720984831452369,
|
|
"num_tokens": 860929.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.339401197433472,
|
|
"epoch": 0.03948750262549885,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 7.1147,
|
|
"mean_token_accuracy": 0.07953860089182854,
|
|
"num_tokens": 869144.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.407509994506836,
|
|
"epoch": 0.039907582440663725,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 7.0553,
|
|
"mean_token_accuracy": 0.08522386401891709,
|
|
"num_tokens": 877447.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.326080799102783,
|
|
"epoch": 0.04032766225582861,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 7.0219,
|
|
"mean_token_accuracy": 0.07903883457183838,
|
|
"num_tokens": 887020.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.214662790298462,
|
|
"epoch": 0.040747742070993485,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 7.0658,
|
|
"mean_token_accuracy": 0.08200340047478676,
|
|
"num_tokens": 895937.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.282938385009766,
|
|
"epoch": 0.04116782188615837,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 7.0681,
|
|
"mean_token_accuracy": 0.07768266201019287,
|
|
"num_tokens": 905446.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.278123235702514,
|
|
"epoch": 0.04158790170132325,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.9754,
|
|
"mean_token_accuracy": 0.08815655037760735,
|
|
"num_tokens": 914547.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.246780204772949,
|
|
"epoch": 0.04200798151648813,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.971,
|
|
"mean_token_accuracy": 0.08642620444297791,
|
|
"num_tokens": 922900.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 7.250076103210449,
|
|
"epoch": 0.042428061331653014,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.9895,
|
|
"mean_token_accuracy": 0.09132884815335274,
|
|
"num_tokens": 930876.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.281206130981445,
|
|
"epoch": 0.0428481411468179,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 7.0298,
|
|
"mean_token_accuracy": 0.08785640895366668,
|
|
"num_tokens": 939871.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.217110443115234,
|
|
"epoch": 0.043268220961982774,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000257,
|
|
"loss": 7.0255,
|
|
"mean_token_accuracy": 0.08548255637288094,
|
|
"num_tokens": 948673.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.166579723358154,
|
|
"epoch": 0.04368830077714766,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.9755,
|
|
"mean_token_accuracy": 0.08237149193882942,
|
|
"num_tokens": 957603.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.258489608764648,
|
|
"epoch": 0.04410838059231254,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000262,
|
|
"loss": 7.0438,
|
|
"mean_token_accuracy": 0.08337677642703056,
|
|
"num_tokens": 967731.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 7.215053987503052,
|
|
"epoch": 0.04452846040747742,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 7.0538,
|
|
"mean_token_accuracy": 0.08425389714539051,
|
|
"num_tokens": 977427.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.323162364959717,
|
|
"epoch": 0.0449485402226423,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 7.0242,
|
|
"mean_token_accuracy": 0.0810987412929535,
|
|
"num_tokens": 986758.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 7.260653781890869,
|
|
"epoch": 0.045368620037807186,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 7.0153,
|
|
"mean_token_accuracy": 0.0921817146241665,
|
|
"num_tokens": 996377.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.14100399017334,
|
|
"epoch": 0.04578869985297206,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 7.0719,
|
|
"mean_token_accuracy": 0.07598314173519612,
|
|
"num_tokens": 1006483.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.1814124584198,
|
|
"epoch": 0.04620877966813695,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.9586,
|
|
"mean_token_accuracy": 0.08432785160839558,
|
|
"num_tokens": 1016132.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 7.212322998046875,
|
|
"epoch": 0.04662885948330183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.9099,
|
|
"mean_token_accuracy": 0.08570380732417107,
|
|
"num_tokens": 1024970.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.235566568374634,
|
|
"epoch": 0.04704893929846671,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.986,
|
|
"mean_token_accuracy": 0.08736011460423469,
|
|
"num_tokens": 1034335.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.172399663925171,
|
|
"epoch": 0.04746901911363159,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 7.0432,
|
|
"mean_token_accuracy": 0.09397755041718484,
|
|
"num_tokens": 1043954.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.211180973052978,
|
|
"epoch": 0.04788909892879647,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.9855,
|
|
"mean_token_accuracy": 0.08458798602223397,
|
|
"num_tokens": 1053554.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.182736825942993,
|
|
"epoch": 0.04830917874396135,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.9441,
|
|
"mean_token_accuracy": 0.0878808081150055,
|
|
"num_tokens": 1062008.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 7.098301124572754,
|
|
"epoch": 0.048729258559126236,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 7.0042,
|
|
"mean_token_accuracy": 0.09225907325744628,
|
|
"num_tokens": 1070740.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 7.182776641845703,
|
|
"epoch": 0.04914933837429111,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.9919,
|
|
"mean_token_accuracy": 0.08668612986803055,
|
|
"num_tokens": 1079681.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.184729337692261,
|
|
"epoch": 0.049569418189456,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.8713,
|
|
"mean_token_accuracy": 0.08976615592837334,
|
|
"num_tokens": 1088979.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 7.06590256690979,
|
|
"epoch": 0.04998949800462088,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.8795,
|
|
"mean_token_accuracy": 0.09069397076964378,
|
|
"num_tokens": 1097870.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 7.103166151046753,
|
|
"epoch": 0.05040957781978576,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.9879,
|
|
"mean_token_accuracy": 0.08688322901725769,
|
|
"num_tokens": 1107948.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 7.1195960521698,
|
|
"epoch": 0.05082965763495064,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.9085,
|
|
"mean_token_accuracy": 0.08996571898460388,
|
|
"num_tokens": 1117032.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.0409345626831055,
|
|
"epoch": 0.051249737450115525,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.8922,
|
|
"mean_token_accuracy": 0.09091109931468963,
|
|
"num_tokens": 1127834.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.202378034591675,
|
|
"epoch": 0.0516698172652804,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.9702,
|
|
"mean_token_accuracy": 0.10021311864256859,
|
|
"num_tokens": 1137382.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.999694728851319,
|
|
"epoch": 0.052089897080445285,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.8129,
|
|
"mean_token_accuracy": 0.09540090411901474,
|
|
"num_tokens": 1146095.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 7.04736361503601,
|
|
"epoch": 0.05250997689561017,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.8486,
|
|
"mean_token_accuracy": 0.09502546936273575,
|
|
"num_tokens": 1154981.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.99720253944397,
|
|
"epoch": 0.052930056710775046,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.8621,
|
|
"mean_token_accuracy": 0.09437942430377007,
|
|
"num_tokens": 1164939.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.151091146469116,
|
|
"epoch": 0.05335013652593993,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.9914,
|
|
"mean_token_accuracy": 0.0866759791970253,
|
|
"num_tokens": 1174991.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 7.180017423629761,
|
|
"epoch": 0.05377021634110481,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 7.0331,
|
|
"mean_token_accuracy": 0.0841725155711174,
|
|
"num_tokens": 1184885.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.973786115646362,
|
|
"epoch": 0.05419029615626969,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.9191,
|
|
"mean_token_accuracy": 0.08975687026977539,
|
|
"num_tokens": 1193637.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.9996246814727785,
|
|
"epoch": 0.054610375971434574,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.7105,
|
|
"mean_token_accuracy": 0.09813873320817948,
|
|
"num_tokens": 1202188.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 7.099790334701538,
|
|
"epoch": 0.05503045578659945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.8407,
|
|
"mean_token_accuracy": 0.08720196485519409,
|
|
"num_tokens": 1210768.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 7.041568231582642,
|
|
"epoch": 0.055450535601764335,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.8421,
|
|
"mean_token_accuracy": 0.0917449563741684,
|
|
"num_tokens": 1219819.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 7.046403980255127,
|
|
"epoch": 0.05587061541692922,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.8979,
|
|
"mean_token_accuracy": 0.08456902354955673,
|
|
"num_tokens": 1229703.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 7.123572778701782,
|
|
"epoch": 0.056290695232094096,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.9292,
|
|
"mean_token_accuracy": 0.08853036314249038,
|
|
"num_tokens": 1238942.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 7.159795522689819,
|
|
"epoch": 0.05671077504725898,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.9738,
|
|
"mean_token_accuracy": 0.08909042924642563,
|
|
"num_tokens": 1248943.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.958240079879761,
|
|
"epoch": 0.05713085486242386,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.8634,
|
|
"mean_token_accuracy": 0.09144520461559295,
|
|
"num_tokens": 1257761.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.8688782215118405,
|
|
"epoch": 0.05755093467758874,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7949,
|
|
"mean_token_accuracy": 0.08892206028103829,
|
|
"num_tokens": 1267216.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.068194055557251,
|
|
"epoch": 0.057971014492753624,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.8935,
|
|
"mean_token_accuracy": 0.0898799903690815,
|
|
"num_tokens": 1277210.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 7.016180753707886,
|
|
"epoch": 0.05839109430791851,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.818,
|
|
"mean_token_accuracy": 0.08777436465024949,
|
|
"num_tokens": 1285310.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.991688251495361,
|
|
"epoch": 0.058811174123083385,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.83,
|
|
"mean_token_accuracy": 0.09071314185857773,
|
|
"num_tokens": 1294421.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.878597545623779,
|
|
"epoch": 0.05923125393824827,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.6618,
|
|
"mean_token_accuracy": 0.09866252094507218,
|
|
"num_tokens": 1303281.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.936507320404052,
|
|
"epoch": 0.059651333753413145,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.824,
|
|
"mean_token_accuracy": 0.0997501090168953,
|
|
"num_tokens": 1312280.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.8826006889343265,
|
|
"epoch": 0.06007141356857803,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.7922,
|
|
"mean_token_accuracy": 0.09014676585793495,
|
|
"num_tokens": 1321243.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.928562927246094,
|
|
"epoch": 0.06049149338374291,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.8825,
|
|
"mean_token_accuracy": 0.09469160959124565,
|
|
"num_tokens": 1330324.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.990442323684692,
|
|
"epoch": 0.06091157319890779,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.7224,
|
|
"mean_token_accuracy": 0.09678644239902497,
|
|
"num_tokens": 1339485.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.953311347961426,
|
|
"epoch": 0.06133165301407267,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.8803,
|
|
"mean_token_accuracy": 0.08837029710412025,
|
|
"num_tokens": 1348640.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.882500171661377,
|
|
"epoch": 0.06175173282923756,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.7691,
|
|
"mean_token_accuracy": 0.09767747819423675,
|
|
"num_tokens": 1357581.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.97215313911438,
|
|
"epoch": 0.062171812644402434,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.8411,
|
|
"mean_token_accuracy": 0.0938787505030632,
|
|
"num_tokens": 1367883.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.919119882583618,
|
|
"epoch": 0.06259189245956731,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.7914,
|
|
"mean_token_accuracy": 0.09219447746872902,
|
|
"num_tokens": 1376936.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.825827884674072,
|
|
"epoch": 0.0630119722747322,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.7125,
|
|
"mean_token_accuracy": 0.09528392925858498,
|
|
"num_tokens": 1386359.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.892624235153198,
|
|
"epoch": 0.06343205208989708,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.7627,
|
|
"mean_token_accuracy": 0.09940937235951423,
|
|
"num_tokens": 1395223.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 7.047525787353516,
|
|
"epoch": 0.06385213190506196,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.9106,
|
|
"mean_token_accuracy": 0.09024005718529224,
|
|
"num_tokens": 1404917.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.961672592163086,
|
|
"epoch": 0.06427221172022685,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.8159,
|
|
"mean_token_accuracy": 0.10144984871149063,
|
|
"num_tokens": 1413348.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.793653059005737,
|
|
"epoch": 0.06469229153539173,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.7916,
|
|
"mean_token_accuracy": 0.09195128381252289,
|
|
"num_tokens": 1421726.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.895196437835693,
|
|
"epoch": 0.0651123713505566,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.7955,
|
|
"mean_token_accuracy": 0.09626475274562836,
|
|
"num_tokens": 1430686.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.93384485244751,
|
|
"epoch": 0.06553245116572148,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.7897,
|
|
"mean_token_accuracy": 0.09465737789869308,
|
|
"num_tokens": 1439499.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.955707168579101,
|
|
"epoch": 0.06595253098088637,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.7769,
|
|
"mean_token_accuracy": 0.09800057783722878,
|
|
"num_tokens": 1448220.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.76906795501709,
|
|
"epoch": 0.06637261079605125,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.7919,
|
|
"mean_token_accuracy": 0.08977739810943604,
|
|
"num_tokens": 1458217.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.814671993255615,
|
|
"epoch": 0.06679269061121614,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.7075,
|
|
"mean_token_accuracy": 0.09342081621289253,
|
|
"num_tokens": 1467422.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.887504005432129,
|
|
"epoch": 0.06721277042638102,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.6819,
|
|
"mean_token_accuracy": 0.10001382231712341,
|
|
"num_tokens": 1476152.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.807573080062866,
|
|
"epoch": 0.06763285024154589,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.7751,
|
|
"mean_token_accuracy": 0.09214248061180115,
|
|
"num_tokens": 1485248.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.854774427413941,
|
|
"epoch": 0.06805293005671077,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.7307,
|
|
"mean_token_accuracy": 0.09543775320053101,
|
|
"num_tokens": 1494248.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.848575687408447,
|
|
"epoch": 0.06847300987187566,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.8448,
|
|
"mean_token_accuracy": 0.0940382607281208,
|
|
"num_tokens": 1503565.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.988439130783081,
|
|
"epoch": 0.06889308968704054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.9384,
|
|
"mean_token_accuracy": 0.08889181464910507,
|
|
"num_tokens": 1513227.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.93678297996521,
|
|
"epoch": 0.06931316950220542,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.7217,
|
|
"mean_token_accuracy": 0.10070210471749305,
|
|
"num_tokens": 1522312.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.770338535308838,
|
|
"epoch": 0.0697332493173703,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.6784,
|
|
"mean_token_accuracy": 0.09791189730167389,
|
|
"num_tokens": 1531720.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.800765943527222,
|
|
"epoch": 0.07015332913253518,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.7521,
|
|
"mean_token_accuracy": 0.09716509580612183,
|
|
"num_tokens": 1541238.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.8829351425170895,
|
|
"epoch": 0.07057340894770006,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.8628,
|
|
"mean_token_accuracy": 0.09571778625249863,
|
|
"num_tokens": 1550875.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.7474853515625,
|
|
"epoch": 0.07099348876286495,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.7945,
|
|
"mean_token_accuracy": 0.09439405128359794,
|
|
"num_tokens": 1560287.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.8450279712677,
|
|
"epoch": 0.07141356857802983,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.6719,
|
|
"mean_token_accuracy": 0.10050797313451768,
|
|
"num_tokens": 1569043.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.72012848854065,
|
|
"epoch": 0.07183364839319471,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6946,
|
|
"mean_token_accuracy": 0.10327838435769081,
|
|
"num_tokens": 1578112.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.666503381729126,
|
|
"epoch": 0.07225372820835958,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.6083,
|
|
"mean_token_accuracy": 0.10177602767944335,
|
|
"num_tokens": 1586587.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.876049327850342,
|
|
"epoch": 0.07267380802352447,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.7715,
|
|
"mean_token_accuracy": 0.09597784802317619,
|
|
"num_tokens": 1595585.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.793572664260864,
|
|
"epoch": 0.07309388783868935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.7402,
|
|
"mean_token_accuracy": 0.09475546851754188,
|
|
"num_tokens": 1605355.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.829131984710694,
|
|
"epoch": 0.07351396765385423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.7645,
|
|
"mean_token_accuracy": 0.09627607688307763,
|
|
"num_tokens": 1613637.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.7632164478302,
|
|
"epoch": 0.07393404746901912,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.09899500831961631,
|
|
"num_tokens": 1622731.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.812683629989624,
|
|
"epoch": 0.074354127284184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.678,
|
|
"mean_token_accuracy": 0.09412262439727784,
|
|
"num_tokens": 1632098.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.743659448623657,
|
|
"epoch": 0.07477420709934887,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6765,
|
|
"mean_token_accuracy": 0.09482985511422157,
|
|
"num_tokens": 1641259.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.833035087585449,
|
|
"epoch": 0.07519428691451376,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.7498,
|
|
"mean_token_accuracy": 0.09258906096220017,
|
|
"num_tokens": 1651362.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.710019874572754,
|
|
"epoch": 0.07561436672967864,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.6731,
|
|
"mean_token_accuracy": 0.09449022710323333,
|
|
"num_tokens": 1660190.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.716372060775757,
|
|
"epoch": 0.07603444654484352,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.6958,
|
|
"mean_token_accuracy": 0.09791603237390518,
|
|
"num_tokens": 1669020.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.81228666305542,
|
|
"epoch": 0.0764545263600084,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.7321,
|
|
"mean_token_accuracy": 0.09860685616731643,
|
|
"num_tokens": 1678158.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.792080020904541,
|
|
"epoch": 0.07687460617517328,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.7306,
|
|
"mean_token_accuracy": 0.09886500239372253,
|
|
"num_tokens": 1687481.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.71827883720398,
|
|
"epoch": 0.07729468599033816,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.6994,
|
|
"mean_token_accuracy": 0.103325155377388,
|
|
"num_tokens": 1696782.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.721747827529907,
|
|
"epoch": 0.07771476580550304,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.7107,
|
|
"mean_token_accuracy": 0.10372448563575745,
|
|
"num_tokens": 1706153.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.703522777557373,
|
|
"epoch": 0.07813484562066793,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.7323,
|
|
"mean_token_accuracy": 0.10109473243355752,
|
|
"num_tokens": 1715585.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.9429340839385985,
|
|
"epoch": 0.07855492543583281,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.8552,
|
|
"mean_token_accuracy": 0.09585651680827141,
|
|
"num_tokens": 1724857.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.723682641983032,
|
|
"epoch": 0.0789750052509977,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.6587,
|
|
"mean_token_accuracy": 0.10578344613313675,
|
|
"num_tokens": 1733528.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.796629476547241,
|
|
"epoch": 0.07939508506616257,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.7839,
|
|
"mean_token_accuracy": 0.09946857616305352,
|
|
"num_tokens": 1742953.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.778720664978027,
|
|
"epoch": 0.07981516488132745,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.7418,
|
|
"mean_token_accuracy": 0.10183344334363938,
|
|
"num_tokens": 1752155.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.6747581481933596,
|
|
"epoch": 0.08023524469649233,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.6189,
|
|
"mean_token_accuracy": 0.10308177843689918,
|
|
"num_tokens": 1760562.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.6881184577941895,
|
|
"epoch": 0.08065532451165722,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.6407,
|
|
"mean_token_accuracy": 0.09682166650891304,
|
|
"num_tokens": 1769631.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.686205625534058,
|
|
"epoch": 0.0810754043268221,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.6737,
|
|
"mean_token_accuracy": 0.09623132348060608,
|
|
"num_tokens": 1779080.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.71329026222229,
|
|
"epoch": 0.08149548414198697,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.6501,
|
|
"mean_token_accuracy": 0.09797736331820488,
|
|
"num_tokens": 1787830.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.607724714279175,
|
|
"epoch": 0.08191556395715185,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.5762,
|
|
"mean_token_accuracy": 0.10056376829743385,
|
|
"num_tokens": 1796998.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.796718168258667,
|
|
"epoch": 0.08233564377231674,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.6548,
|
|
"mean_token_accuracy": 0.10055585950613022,
|
|
"num_tokens": 1806194.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.432325410842895,
|
|
"epoch": 0.08275572358748162,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.5356,
|
|
"mean_token_accuracy": 0.10625480636954307,
|
|
"num_tokens": 1815751.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.659997034072876,
|
|
"epoch": 0.0831758034026465,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.6207,
|
|
"mean_token_accuracy": 0.10119200572371483,
|
|
"num_tokens": 1825379.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.685537910461425,
|
|
"epoch": 0.08359588321781139,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5776,
|
|
"mean_token_accuracy": 0.10274154916405678,
|
|
"num_tokens": 1834158.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.586271667480469,
|
|
"epoch": 0.08401596303297626,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.5331,
|
|
"mean_token_accuracy": 0.1030009813606739,
|
|
"num_tokens": 1842724.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.606362009048462,
|
|
"epoch": 0.08443604284814114,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499999998724557,
|
|
"loss": 6.5511,
|
|
"mean_token_accuracy": 0.10277646854519844,
|
|
"num_tokens": 1852485.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.6398862361907955,
|
|
"epoch": 0.08485612266330603,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999999935430703,
|
|
"loss": 6.5824,
|
|
"mean_token_accuracy": 0.10646345019340515,
|
|
"num_tokens": 1861303.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.527065420150757,
|
|
"epoch": 0.08527620247847091,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999999843758243,
|
|
"loss": 6.5766,
|
|
"mean_token_accuracy": 0.1160741962492466,
|
|
"num_tokens": 1870859.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.720239210128784,
|
|
"epoch": 0.0856962822936358,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999712228196,
|
|
"loss": 6.7375,
|
|
"mean_token_accuracy": 0.09559379816055298,
|
|
"num_tokens": 1880295.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.755932474136353,
|
|
"epoch": 0.08611636210880068,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999999540840562,
|
|
"loss": 6.6322,
|
|
"mean_token_accuracy": 0.10711020082235337,
|
|
"num_tokens": 1889193.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.635529565811157,
|
|
"epoch": 0.08653644192396555,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004999999329595345,
|
|
"loss": 6.7369,
|
|
"mean_token_accuracy": 0.09584898650646209,
|
|
"num_tokens": 1899437.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.71239709854126,
|
|
"epoch": 0.08695652173913043,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999999078492548,
|
|
"loss": 6.6284,
|
|
"mean_token_accuracy": 0.10203150510787964,
|
|
"num_tokens": 1907882.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.588162136077881,
|
|
"epoch": 0.08737660155429532,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999998787532176,
|
|
"loss": 6.5411,
|
|
"mean_token_accuracy": 0.10083841383457184,
|
|
"num_tokens": 1916872.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.676869010925293,
|
|
"epoch": 0.0877966813694602,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999998456714234,
|
|
"loss": 6.7265,
|
|
"mean_token_accuracy": 0.09887873977422715,
|
|
"num_tokens": 1926636.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.626446390151978,
|
|
"epoch": 0.08821676118462508,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999998086038729,
|
|
"loss": 6.6125,
|
|
"mean_token_accuracy": 0.10665144100785255,
|
|
"num_tokens": 1935962.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.63335337638855,
|
|
"epoch": 0.08863684099978995,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999997675505665,
|
|
"loss": 6.5714,
|
|
"mean_token_accuracy": 0.10421753227710724,
|
|
"num_tokens": 1944600.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.66912956237793,
|
|
"epoch": 0.08905692081495484,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999997225115052,
|
|
"loss": 6.7618,
|
|
"mean_token_accuracy": 0.10299883931875228,
|
|
"num_tokens": 1954234.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.80169267654419,
|
|
"epoch": 0.08947700063011972,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999996734866896,
|
|
"loss": 6.7125,
|
|
"mean_token_accuracy": 0.10105927959084511,
|
|
"num_tokens": 1964499.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.4505407333374025,
|
|
"epoch": 0.0898970804452846,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999996204761206,
|
|
"loss": 6.4236,
|
|
"mean_token_accuracy": 0.1128264844417572,
|
|
"num_tokens": 1973635.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.56596827507019,
|
|
"epoch": 0.09031716026044949,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999995634797993,
|
|
"loss": 6.5739,
|
|
"mean_token_accuracy": 0.10490957424044609,
|
|
"num_tokens": 1983509.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.62415657043457,
|
|
"epoch": 0.09073724007561437,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999995024977265,
|
|
"loss": 6.5551,
|
|
"mean_token_accuracy": 0.11068339720368385,
|
|
"num_tokens": 1992336.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.581994724273682,
|
|
"epoch": 0.09115731989077924,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999994375299034,
|
|
"loss": 6.5937,
|
|
"mean_token_accuracy": 0.10452346429228783,
|
|
"num_tokens": 2001931.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.580089092254639,
|
|
"epoch": 0.09157739970594413,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499999368576331,
|
|
"loss": 6.4447,
|
|
"mean_token_accuracy": 0.11201497912406921,
|
|
"num_tokens": 2010935.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.511315250396729,
|
|
"epoch": 0.09199747952110901,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999992956370109,
|
|
"loss": 6.4995,
|
|
"mean_token_accuracy": 0.10933665409684182,
|
|
"num_tokens": 2020587.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.465148067474365,
|
|
"epoch": 0.0924175593362739,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499999218711944,
|
|
"loss": 6.5391,
|
|
"mean_token_accuracy": 0.10621756613254547,
|
|
"num_tokens": 2029743.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.62024712562561,
|
|
"epoch": 0.09283763915143878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999991378011317,
|
|
"loss": 6.5513,
|
|
"mean_token_accuracy": 0.11122238337993622,
|
|
"num_tokens": 2038468.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.526382637023926,
|
|
"epoch": 0.09325771896660366,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999990529045757,
|
|
"loss": 6.4773,
|
|
"mean_token_accuracy": 0.10901794061064721,
|
|
"num_tokens": 2047456.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.6758506298065186,
|
|
"epoch": 0.09367779878176853,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999989640222771,
|
|
"loss": 6.7907,
|
|
"mean_token_accuracy": 0.09581167250871658,
|
|
"num_tokens": 2056691.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.724249839782715,
|
|
"epoch": 0.09409787859693342,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000499998871154238,
|
|
"loss": 6.5726,
|
|
"mean_token_accuracy": 0.1056052066385746,
|
|
"num_tokens": 2066068.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.619223117828369,
|
|
"epoch": 0.0945179584120983,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999987743004597,
|
|
"loss": 6.5105,
|
|
"mean_token_accuracy": 0.10904356241226196,
|
|
"num_tokens": 2075113.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.579265213012695,
|
|
"epoch": 0.09493803822726318,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999986734609438,
|
|
"loss": 6.648,
|
|
"mean_token_accuracy": 0.10513966977596283,
|
|
"num_tokens": 2084557.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.630017042160034,
|
|
"epoch": 0.09535811804242807,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999985686356923,
|
|
"loss": 6.5466,
|
|
"mean_token_accuracy": 0.10622756630182266,
|
|
"num_tokens": 2093424.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.602306842803955,
|
|
"epoch": 0.09577819785759294,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499998459824707,
|
|
"loss": 6.6635,
|
|
"mean_token_accuracy": 0.10230447798967361,
|
|
"num_tokens": 2103066.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.612010765075683,
|
|
"epoch": 0.09619827767275782,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049999834702799,
|
|
"loss": 6.5355,
|
|
"mean_token_accuracy": 0.1076541669666767,
|
|
"num_tokens": 2112447.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.522880172729492,
|
|
"epoch": 0.0966183574879227,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999982302455431,
|
|
"loss": 6.5497,
|
|
"mean_token_accuracy": 0.10876928493380547,
|
|
"num_tokens": 2121949.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.574669218063354,
|
|
"epoch": 0.09703843730308759,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999981094773683,
|
|
"loss": 6.4538,
|
|
"mean_token_accuracy": 0.10955686494708061,
|
|
"num_tokens": 2130464.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.626054668426514,
|
|
"epoch": 0.09745851711825247,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499997984723468,
|
|
"loss": 6.6151,
|
|
"mean_token_accuracy": 0.10182780474424362,
|
|
"num_tokens": 2139577.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.2696503639221195,
|
|
"epoch": 0.09787859693341736,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999978559838441,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.10666822865605355,
|
|
"num_tokens": 2147919.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.4677763938903805,
|
|
"epoch": 0.09829867674858223,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999977232584991,
|
|
"loss": 6.5126,
|
|
"mean_token_accuracy": 0.10790005698800087,
|
|
"num_tokens": 2156936.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.619596195220947,
|
|
"epoch": 0.09871875656374711,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999975865474354,
|
|
"loss": 6.565,
|
|
"mean_token_accuracy": 0.1067568302154541,
|
|
"num_tokens": 2165362.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.488823509216308,
|
|
"epoch": 0.099138836378912,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999974458506551,
|
|
"loss": 6.4994,
|
|
"mean_token_accuracy": 0.105003522336483,
|
|
"num_tokens": 2173665.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.633204603195191,
|
|
"epoch": 0.09955891619407688,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499997301168161,
|
|
"loss": 6.4861,
|
|
"mean_token_accuracy": 0.10850023925304413,
|
|
"num_tokens": 2182222.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.550716543197632,
|
|
"epoch": 0.09997899600924176,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999971524999556,
|
|
"loss": 6.5724,
|
|
"mean_token_accuracy": 0.11284129321575165,
|
|
"num_tokens": 2192358.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.5804180145263675,
|
|
"epoch": 0.10039907582440663,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999969998460414,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.10514037609100342,
|
|
"num_tokens": 2201889.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.548522186279297,
|
|
"epoch": 0.10081915563957151,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004999968432064213,
|
|
"loss": 6.5442,
|
|
"mean_token_accuracy": 0.11475524455308914,
|
|
"num_tokens": 2211810.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.474522876739502,
|
|
"epoch": 0.1012392354547364,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999966825810979,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.10969577804207802,
|
|
"num_tokens": 2221123.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.482648086547852,
|
|
"epoch": 0.10165931526990128,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999965179700742,
|
|
"loss": 6.4233,
|
|
"mean_token_accuracy": 0.11192466542124749,
|
|
"num_tokens": 2230129.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.427746820449829,
|
|
"epoch": 0.10207939508506617,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.000499996349373353,
|
|
"loss": 6.4731,
|
|
"mean_token_accuracy": 0.11126175448298455,
|
|
"num_tokens": 2239929.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.540882635116577,
|
|
"epoch": 0.10249947490023105,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999961767909374,
|
|
"loss": 6.4503,
|
|
"mean_token_accuracy": 0.11326849237084388,
|
|
"num_tokens": 2248078.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.496834564208984,
|
|
"epoch": 0.10291955471539592,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999960002228303,
|
|
"loss": 6.5467,
|
|
"mean_token_accuracy": 0.11118405237793923,
|
|
"num_tokens": 2256975.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.528544092178345,
|
|
"epoch": 0.1033396345305608,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999958196690349,
|
|
"loss": 6.4084,
|
|
"mean_token_accuracy": 0.11252974197268487,
|
|
"num_tokens": 2265797.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.500071668624878,
|
|
"epoch": 0.10375971434572569,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999956351295545,
|
|
"loss": 6.4961,
|
|
"mean_token_accuracy": 0.11529959514737129,
|
|
"num_tokens": 2274099.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.427072525024414,
|
|
"epoch": 0.10417979416089057,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999954466043922,
|
|
"loss": 6.4331,
|
|
"mean_token_accuracy": 0.11734503880143166,
|
|
"num_tokens": 2282360.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.490129566192627,
|
|
"epoch": 0.10459987397605545,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999952540935514,
|
|
"loss": 6.5292,
|
|
"mean_token_accuracy": 0.10359383374452591,
|
|
"num_tokens": 2292714.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.519558954238891,
|
|
"epoch": 0.10501995379122034,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999950575970356,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.11484305784106255,
|
|
"num_tokens": 2301633.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.521380376815796,
|
|
"epoch": 0.10544003360638521,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999948571148482,
|
|
"loss": 6.4373,
|
|
"mean_token_accuracy": 0.1137208767235279,
|
|
"num_tokens": 2310067.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.447480583190918,
|
|
"epoch": 0.10586011342155009,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999946526469927,
|
|
"loss": 6.5213,
|
|
"mean_token_accuracy": 0.11123185902833939,
|
|
"num_tokens": 2320090.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.488873481750488,
|
|
"epoch": 0.10628019323671498,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999944441934728,
|
|
"loss": 6.474,
|
|
"mean_token_accuracy": 0.11672058925032616,
|
|
"num_tokens": 2329255.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.575503969192505,
|
|
"epoch": 0.10670027305187986,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999942317542922,
|
|
"loss": 6.5597,
|
|
"mean_token_accuracy": 0.11168134436011315,
|
|
"num_tokens": 2339535.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.4351553440094,
|
|
"epoch": 0.10712035286704474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999940153294546,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.11417224109172822,
|
|
"num_tokens": 2348948.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.516087198257447,
|
|
"epoch": 0.10754043268220961,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499993794918964,
|
|
"loss": 6.4852,
|
|
"mean_token_accuracy": 0.10800226852297783,
|
|
"num_tokens": 2359141.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.426724910736084,
|
|
"epoch": 0.1079605124973745,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999935705228241,
|
|
"loss": 6.5269,
|
|
"mean_token_accuracy": 0.10617210119962692,
|
|
"num_tokens": 2368906.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.60525369644165,
|
|
"epoch": 0.10838059231253938,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999933421410389,
|
|
"loss": 6.5118,
|
|
"mean_token_accuracy": 0.11492194160819054,
|
|
"num_tokens": 2377029.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.507741403579712,
|
|
"epoch": 0.10880067212770426,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004999931097736125,
|
|
"loss": 6.5731,
|
|
"mean_token_accuracy": 0.10368336364626884,
|
|
"num_tokens": 2387088.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.560735607147217,
|
|
"epoch": 0.10922075194286915,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999928734205492,
|
|
"loss": 6.4678,
|
|
"mean_token_accuracy": 0.11101854220032692,
|
|
"num_tokens": 2395596.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.4469006061553955,
|
|
"epoch": 0.10964083175803403,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999926330818528,
|
|
"loss": 6.4508,
|
|
"mean_token_accuracy": 0.11560385897755623,
|
|
"num_tokens": 2404506.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.50532808303833,
|
|
"epoch": 0.1100609115731989,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004999923887575278,
|
|
"loss": 6.4871,
|
|
"mean_token_accuracy": 0.1127387061715126,
|
|
"num_tokens": 2414342.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.511183404922486,
|
|
"epoch": 0.11048099138836379,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999921404475785,
|
|
"loss": 6.464,
|
|
"mean_token_accuracy": 0.11368927583098412,
|
|
"num_tokens": 2423076.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.4253387451171875,
|
|
"epoch": 0.11090107120352867,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999918881520093,
|
|
"loss": 6.415,
|
|
"mean_token_accuracy": 0.11362927556037902,
|
|
"num_tokens": 2432492.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.421670770645141,
|
|
"epoch": 0.11132115101869355,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999916318708246,
|
|
"loss": 6.3657,
|
|
"mean_token_accuracy": 0.11932958588004113,
|
|
"num_tokens": 2441916.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.4051666259765625,
|
|
"epoch": 0.11174123083385844,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999913716040291,
|
|
"loss": 6.4305,
|
|
"mean_token_accuracy": 0.11500561088323594,
|
|
"num_tokens": 2450932.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.410413789749145,
|
|
"epoch": 0.11216131064902331,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999911073516272,
|
|
"loss": 6.4353,
|
|
"mean_token_accuracy": 0.11533465534448624,
|
|
"num_tokens": 2460058.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.411908531188965,
|
|
"epoch": 0.11258139046418819,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999908391136237,
|
|
"loss": 6.3795,
|
|
"mean_token_accuracy": 0.11413594856858253,
|
|
"num_tokens": 2469607.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.480467748641968,
|
|
"epoch": 0.11300147027935308,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999905668900234,
|
|
"loss": 6.4206,
|
|
"mean_token_accuracy": 0.10967940241098403,
|
|
"num_tokens": 2478345.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.437506008148193,
|
|
"epoch": 0.11342155009451796,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499990290680831,
|
|
"loss": 6.3551,
|
|
"mean_token_accuracy": 0.11509306952357293,
|
|
"num_tokens": 2486662.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.440225267410279,
|
|
"epoch": 0.11384162990968284,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999900104860516,
|
|
"loss": 6.493,
|
|
"mean_token_accuracy": 0.10815305337309837,
|
|
"num_tokens": 2495392.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.476166391372681,
|
|
"epoch": 0.11426170972484773,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999897263056898,
|
|
"loss": 6.5134,
|
|
"mean_token_accuracy": 0.1084674522280693,
|
|
"num_tokens": 2505254.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.572962856292724,
|
|
"epoch": 0.1146817895400126,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499989438139751,
|
|
"loss": 6.3391,
|
|
"mean_token_accuracy": 0.11722229272127152,
|
|
"num_tokens": 2514096.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.320563554763794,
|
|
"epoch": 0.11510186935517748,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999891459882401,
|
|
"loss": 6.3415,
|
|
"mean_token_accuracy": 0.11798084080219269,
|
|
"num_tokens": 2523635.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.370605707168579,
|
|
"epoch": 0.11552194917034236,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999888498511624,
|
|
"loss": 6.4231,
|
|
"mean_token_accuracy": 0.11351286545395851,
|
|
"num_tokens": 2532528.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.42153754234314,
|
|
"epoch": 0.11594202898550725,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999885497285229,
|
|
"loss": 6.3223,
|
|
"mean_token_accuracy": 0.11377703249454499,
|
|
"num_tokens": 2541893.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.374641036987304,
|
|
"epoch": 0.11636210880067213,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999882456203273,
|
|
"loss": 6.3828,
|
|
"mean_token_accuracy": 0.11570416316390038,
|
|
"num_tokens": 2551551.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.409754896163941,
|
|
"epoch": 0.11678218861583702,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999879375265806,
|
|
"loss": 6.3397,
|
|
"mean_token_accuracy": 0.11345641836524009,
|
|
"num_tokens": 2560183.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.346025371551514,
|
|
"epoch": 0.11720226843100189,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999876254472886,
|
|
"loss": 6.244,
|
|
"mean_token_accuracy": 0.1259176701307297,
|
|
"num_tokens": 2568697.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.418486166000366,
|
|
"epoch": 0.11762234824616677,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999873093824565,
|
|
"loss": 6.4413,
|
|
"mean_token_accuracy": 0.11301257386803627,
|
|
"num_tokens": 2578151.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.546730661392212,
|
|
"epoch": 0.11804242806133165,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999869893320902,
|
|
"loss": 6.5711,
|
|
"mean_token_accuracy": 0.11398048102855682,
|
|
"num_tokens": 2585901.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.384084796905517,
|
|
"epoch": 0.11846250787649654,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999866652961952,
|
|
"loss": 6.3911,
|
|
"mean_token_accuracy": 0.1123290129005909,
|
|
"num_tokens": 2595655.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.452324104309082,
|
|
"epoch": 0.11888258769166142,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999863372747773,
|
|
"loss": 6.3493,
|
|
"mean_token_accuracy": 0.10948696061968803,
|
|
"num_tokens": 2604949.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.454392957687378,
|
|
"epoch": 0.11930266750682629,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999860052678423,
|
|
"loss": 6.4265,
|
|
"mean_token_accuracy": 0.11580813452601432,
|
|
"num_tokens": 2614260.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.358513355255127,
|
|
"epoch": 0.11972274732199117,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999856692753959,
|
|
"loss": 6.4088,
|
|
"mean_token_accuracy": 0.11651854142546654,
|
|
"num_tokens": 2623740.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.431614780426026,
|
|
"epoch": 0.12014282713715606,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999853292974444,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.119064449518919,
|
|
"num_tokens": 2631998.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.387428283691406,
|
|
"epoch": 0.12056290695232094,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999849853339936,
|
|
"loss": 6.4515,
|
|
"mean_token_accuracy": 0.11693638861179352,
|
|
"num_tokens": 2641169.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.461726379394531,
|
|
"epoch": 0.12098298676748583,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004999846373850497,
|
|
"loss": 6.3006,
|
|
"mean_token_accuracy": 0.11889183148741722,
|
|
"num_tokens": 2650576.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.285704851150513,
|
|
"epoch": 0.12140306658265071,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999842854506186,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.11337714865803719,
|
|
"num_tokens": 2660817.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.454374599456787,
|
|
"epoch": 0.12182314639781558,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999839295307069,
|
|
"loss": 6.3413,
|
|
"mean_token_accuracy": 0.11637749969959259,
|
|
"num_tokens": 2669338.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.4314216613769535,
|
|
"epoch": 0.12224322621298046,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999835696253206,
|
|
"loss": 6.3931,
|
|
"mean_token_accuracy": 0.1177656464278698,
|
|
"num_tokens": 2679108.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.414116144180298,
|
|
"epoch": 0.12266330602814535,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999832057344664,
|
|
"loss": 6.3513,
|
|
"mean_token_accuracy": 0.11523670107126235,
|
|
"num_tokens": 2688126.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.248635339736938,
|
|
"epoch": 0.12308338584331023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999828378581504,
|
|
"loss": 6.3207,
|
|
"mean_token_accuracy": 0.1255062073469162,
|
|
"num_tokens": 2697245.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.469296169281006,
|
|
"epoch": 0.12350346565847511,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999824659963793,
|
|
"loss": 6.3851,
|
|
"mean_token_accuracy": 0.12115937024354935,
|
|
"num_tokens": 2705934.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.348638343811035,
|
|
"epoch": 0.12392354547364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999820901491598,
|
|
"loss": 6.3102,
|
|
"mean_token_accuracy": 0.12247596234083176,
|
|
"num_tokens": 2714367.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.288274192810059,
|
|
"epoch": 0.12434362528880487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999817103164983,
|
|
"loss": 6.347,
|
|
"mean_token_accuracy": 0.120758505910635,
|
|
"num_tokens": 2724366.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.409024095535278,
|
|
"epoch": 0.12476370510396975,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999813264984017,
|
|
"loss": 6.3559,
|
|
"mean_token_accuracy": 0.11786462664604187,
|
|
"num_tokens": 2733980.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.405835437774658,
|
|
"epoch": 0.12518378491913462,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999809386948767,
|
|
"loss": 6.3447,
|
|
"mean_token_accuracy": 0.12095973119139672,
|
|
"num_tokens": 2744013.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.306218957901001,
|
|
"epoch": 0.12560386473429952,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999805469059302,
|
|
"loss": 6.409,
|
|
"mean_token_accuracy": 0.11885412856936454,
|
|
"num_tokens": 2753385.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.402831554412842,
|
|
"epoch": 0.1260239445494644,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999801511315693,
|
|
"loss": 6.2797,
|
|
"mean_token_accuracy": 0.11564093008637429,
|
|
"num_tokens": 2762875.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.413339233398437,
|
|
"epoch": 0.1264440243646293,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999797513718007,
|
|
"loss": 6.3316,
|
|
"mean_token_accuracy": 0.12512060776352882,
|
|
"num_tokens": 2772182.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.232090759277344,
|
|
"epoch": 0.12686410417979416,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999793476266317,
|
|
"loss": 6.2777,
|
|
"mean_token_accuracy": 0.1216270886361599,
|
|
"num_tokens": 2780814.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.62731146812439,
|
|
"epoch": 0.12728418399495905,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999789398960695,
|
|
"loss": 6.5737,
|
|
"mean_token_accuracy": 0.11791431680321693,
|
|
"num_tokens": 2791104.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.245316696166992,
|
|
"epoch": 0.12770426381012392,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999785281801212,
|
|
"loss": 6.2623,
|
|
"mean_token_accuracy": 0.12040979042649269,
|
|
"num_tokens": 2800081.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.359339189529419,
|
|
"epoch": 0.1281243436252888,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499978112478794,
|
|
"loss": 6.3902,
|
|
"mean_token_accuracy": 0.11980480477213859,
|
|
"num_tokens": 2809096.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.453446865081787,
|
|
"epoch": 0.1285444234404537,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999776927920955,
|
|
"loss": 6.3617,
|
|
"mean_token_accuracy": 0.12184310704469681,
|
|
"num_tokens": 2818857.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.291106510162353,
|
|
"epoch": 0.12896450325561856,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499977269120033,
|
|
"loss": 6.444,
|
|
"mean_token_accuracy": 0.11637230366468429,
|
|
"num_tokens": 2829332.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.427845621109009,
|
|
"epoch": 0.12938458307078346,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499976841462614,
|
|
"loss": 6.3583,
|
|
"mean_token_accuracy": 0.11303109228610993,
|
|
"num_tokens": 2839193.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.396592044830323,
|
|
"epoch": 0.12980466288594833,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 0.000499976409819846,
|
|
"loss": 6.34,
|
|
"mean_token_accuracy": 0.11379488185048103,
|
|
"num_tokens": 2848535.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.191351747512817,
|
|
"epoch": 0.1302247427011132,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999759741917369,
|
|
"loss": 6.2442,
|
|
"mean_token_accuracy": 0.1232595019042492,
|
|
"num_tokens": 2858090.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.410407018661499,
|
|
"epoch": 0.1306448225162781,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999755345782941,
|
|
"loss": 6.3942,
|
|
"mean_token_accuracy": 0.11326258555054665,
|
|
"num_tokens": 2866984.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.209921407699585,
|
|
"epoch": 0.13106490233144297,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004999750909795256,
|
|
"loss": 6.202,
|
|
"mean_token_accuracy": 0.12322057262063027,
|
|
"num_tokens": 2876550.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.351957511901856,
|
|
"epoch": 0.13148498214660786,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999746433954394,
|
|
"loss": 6.3062,
|
|
"mean_token_accuracy": 0.11787799671292305,
|
|
"num_tokens": 2885782.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.3278861999511715,
|
|
"epoch": 0.13190506196177273,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499974191826043,
|
|
"loss": 6.2833,
|
|
"mean_token_accuracy": 0.13189474642276763,
|
|
"num_tokens": 2894807.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.376989316940308,
|
|
"epoch": 0.1323251417769376,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999737362713448,
|
|
"loss": 6.3235,
|
|
"mean_token_accuracy": 0.12015982195734978,
|
|
"num_tokens": 2904076.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.2569879531860355,
|
|
"epoch": 0.1327452215921025,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999732767313527,
|
|
"loss": 6.2239,
|
|
"mean_token_accuracy": 0.12142896950244904,
|
|
"num_tokens": 2913761.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.479147958755493,
|
|
"epoch": 0.13316530140726737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999728132060746,
|
|
"loss": 6.4597,
|
|
"mean_token_accuracy": 0.1231887847185135,
|
|
"num_tokens": 2922848.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.33915228843689,
|
|
"epoch": 0.13358538122243227,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 0.0004999723456955192,
|
|
"loss": 6.3453,
|
|
"mean_token_accuracy": 0.12047107368707657,
|
|
"num_tokens": 2932718.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.313900423049927,
|
|
"epoch": 0.13400546103759714,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999718741996945,
|
|
"loss": 6.2846,
|
|
"mean_token_accuracy": 0.12055236473679543,
|
|
"num_tokens": 2942686.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.250068187713623,
|
|
"epoch": 0.13442554085276204,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499971398718609,
|
|
"loss": 6.2541,
|
|
"mean_token_accuracy": 0.12233499884605407,
|
|
"num_tokens": 2952096.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.400825262069702,
|
|
"epoch": 0.1348456206679269,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999709192522708,
|
|
"loss": 6.343,
|
|
"mean_token_accuracy": 0.12068295776844025,
|
|
"num_tokens": 2960660.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.373941278457641,
|
|
"epoch": 0.13526570048309178,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999704358006887,
|
|
"loss": 6.338,
|
|
"mean_token_accuracy": 0.11847807541489601,
|
|
"num_tokens": 2969834.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.3392332077026365,
|
|
"epoch": 0.13568578029825668,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999699483638712,
|
|
"loss": 6.3224,
|
|
"mean_token_accuracy": 0.11975563690066338,
|
|
"num_tokens": 2979023.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.312718057632447,
|
|
"epoch": 0.13610586011342155,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999694569418269,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.12105349376797676,
|
|
"num_tokens": 2988083.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.298077011108399,
|
|
"epoch": 0.13652593992858644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999689615345645,
|
|
"loss": 6.2407,
|
|
"mean_token_accuracy": 0.12377956956624984,
|
|
"num_tokens": 2997240.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.40955810546875,
|
|
"epoch": 0.1369460197437513,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999684621420928,
|
|
"loss": 6.325,
|
|
"mean_token_accuracy": 0.11809631884098053,
|
|
"num_tokens": 3007077.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.277155590057373,
|
|
"epoch": 0.13736609955891618,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999679587644205,
|
|
"loss": 6.3514,
|
|
"mean_token_accuracy": 0.117049939930439,
|
|
"num_tokens": 3015821.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.334466028213501,
|
|
"epoch": 0.13778617937408108,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999674514015568,
|
|
"loss": 6.27,
|
|
"mean_token_accuracy": 0.12460469976067542,
|
|
"num_tokens": 3025858.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.350087356567383,
|
|
"epoch": 0.13820625918924595,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999669400535105,
|
|
"loss": 6.246,
|
|
"mean_token_accuracy": 0.11693726480007172,
|
|
"num_tokens": 3035537.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.1635466575622555,
|
|
"epoch": 0.13862633900441085,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999664247202907,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.12513800859451293,
|
|
"num_tokens": 3044204.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.405851364135742,
|
|
"epoch": 0.13904641881957572,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999659054019066,
|
|
"loss": 6.3371,
|
|
"mean_token_accuracy": 0.12036163732409477,
|
|
"num_tokens": 3053111.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.243852519989014,
|
|
"epoch": 0.1394664986347406,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999653820983673,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.12018982619047165,
|
|
"num_tokens": 3062456.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.309187984466552,
|
|
"epoch": 0.13988657844990549,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499964854809682,
|
|
"loss": 6.2742,
|
|
"mean_token_accuracy": 0.12464778944849968,
|
|
"num_tokens": 3071132.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.253125143051148,
|
|
"epoch": 0.14030665826507036,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999643235358602,
|
|
"loss": 6.2296,
|
|
"mean_token_accuracy": 0.12636966705322267,
|
|
"num_tokens": 3080892.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.241448926925659,
|
|
"epoch": 0.14072673808023525,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999637882769112,
|
|
"loss": 6.166,
|
|
"mean_token_accuracy": 0.129159078001976,
|
|
"num_tokens": 3089874.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.321546411514282,
|
|
"epoch": 0.14114681789540012,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004999632490328447,
|
|
"loss": 6.3087,
|
|
"mean_token_accuracy": 0.12358235269784927,
|
|
"num_tokens": 3099535.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.297367906570434,
|
|
"epoch": 0.14156689771056502,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999627058036699,
|
|
"loss": 6.2544,
|
|
"mean_token_accuracy": 0.11949014514684678,
|
|
"num_tokens": 3108772.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.318113327026367,
|
|
"epoch": 0.1419869775257299,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999621585893966,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.11683647856116294,
|
|
"num_tokens": 3118333.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.319453144073487,
|
|
"epoch": 0.14240705734089476,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999616073900346,
|
|
"loss": 6.3252,
|
|
"mean_token_accuracy": 0.12005885392427444,
|
|
"num_tokens": 3127356.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.334293079376221,
|
|
"epoch": 0.14282713715605966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999610522055935,
|
|
"loss": 6.2875,
|
|
"mean_token_accuracy": 0.11621066182851791,
|
|
"num_tokens": 3136859.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.296079492568969,
|
|
"epoch": 0.14324721697122453,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999604930360832,
|
|
"loss": 6.3178,
|
|
"mean_token_accuracy": 0.11642780154943466,
|
|
"num_tokens": 3146607.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.24936580657959,
|
|
"epoch": 0.14366729678638943,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004999599298815136,
|
|
"loss": 6.2668,
|
|
"mean_token_accuracy": 0.12453223988413811,
|
|
"num_tokens": 3156327.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.249935483932495,
|
|
"epoch": 0.1440873766015543,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004999593627418947,
|
|
"loss": 6.203,
|
|
"mean_token_accuracy": 0.12521106824278833,
|
|
"num_tokens": 3165559.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.336143445968628,
|
|
"epoch": 0.14450745641671917,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999587916172365,
|
|
"loss": 6.3011,
|
|
"mean_token_accuracy": 0.1152021661400795,
|
|
"num_tokens": 3173850.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.285958003997803,
|
|
"epoch": 0.14492753623188406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999582165075492,
|
|
"loss": 6.2465,
|
|
"mean_token_accuracy": 0.115229881554842,
|
|
"num_tokens": 3182838.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.184572982788086,
|
|
"epoch": 0.14534761604704893,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999576374128429,
|
|
"loss": 6.237,
|
|
"mean_token_accuracy": 0.12389757782220841,
|
|
"num_tokens": 3191692.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.397026300430298,
|
|
"epoch": 0.14576769586221383,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999570543331279,
|
|
"loss": 6.2806,
|
|
"mean_token_accuracy": 0.12041986957192422,
|
|
"num_tokens": 3200069.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.260718488693238,
|
|
"epoch": 0.1461877756773787,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999564672684145,
|
|
"loss": 6.3438,
|
|
"mean_token_accuracy": 0.1193387195467949,
|
|
"num_tokens": 3209653.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.393806028366089,
|
|
"epoch": 0.14660785549254357,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999558762187131,
|
|
"loss": 6.217,
|
|
"mean_token_accuracy": 0.12818640992045402,
|
|
"num_tokens": 3218313.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.188047790527344,
|
|
"epoch": 0.14702793530770847,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999552811840342,
|
|
"loss": 6.1623,
|
|
"mean_token_accuracy": 0.12572802156209945,
|
|
"num_tokens": 3227525.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.254945421218872,
|
|
"epoch": 0.14744801512287334,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004999546821643884,
|
|
"loss": 6.275,
|
|
"mean_token_accuracy": 0.1252661019563675,
|
|
"num_tokens": 3237022.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.239528560638428,
|
|
"epoch": 0.14786809493803824,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999540791597861,
|
|
"loss": 6.1635,
|
|
"mean_token_accuracy": 0.1251967169344425,
|
|
"num_tokens": 3246605.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.140348815917969,
|
|
"epoch": 0.1482881747532031,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999534721702383,
|
|
"loss": 6.1328,
|
|
"mean_token_accuracy": 0.12913108766078948,
|
|
"num_tokens": 3255587.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.292690563201904,
|
|
"epoch": 0.148708254568368,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999528611957553,
|
|
"loss": 6.2117,
|
|
"mean_token_accuracy": 0.1271899625658989,
|
|
"num_tokens": 3265669.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.244245195388794,
|
|
"epoch": 0.14912833438353287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999522462363485,
|
|
"loss": 6.2107,
|
|
"mean_token_accuracy": 0.12735746875405313,
|
|
"num_tokens": 3275013.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.274697399139404,
|
|
"epoch": 0.14954841419869774,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004999516272920283,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.12256114035844803,
|
|
"num_tokens": 3284723.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.149048852920532,
|
|
"epoch": 0.14996849401386264,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499951004362806,
|
|
"loss": 6.148,
|
|
"mean_token_accuracy": 0.12680203318595887,
|
|
"num_tokens": 3293860.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.166975450515747,
|
|
"epoch": 0.1503885738290275,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999503774486924,
|
|
"loss": 6.1912,
|
|
"mean_token_accuracy": 0.12579060941934586,
|
|
"num_tokens": 3303158.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.141963243484497,
|
|
"epoch": 0.1508086536441924,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999497465496987,
|
|
"loss": 6.127,
|
|
"mean_token_accuracy": 0.11945450827479362,
|
|
"num_tokens": 3313068.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.272381019592285,
|
|
"epoch": 0.15122873345935728,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499949111665836,
|
|
"loss": 6.2113,
|
|
"mean_token_accuracy": 0.12545057907700538,
|
|
"num_tokens": 3321885.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.260741281509399,
|
|
"epoch": 0.15164881327452215,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999484727971158,
|
|
"loss": 6.2004,
|
|
"mean_token_accuracy": 0.1255272276699543,
|
|
"num_tokens": 3330924.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.217929172515869,
|
|
"epoch": 0.15206889308968705,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499947829943549,
|
|
"loss": 6.2325,
|
|
"mean_token_accuracy": 0.12151647359132767,
|
|
"num_tokens": 3340070.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.26392617225647,
|
|
"epoch": 0.15248897290485192,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999471831051474,
|
|
"loss": 6.2282,
|
|
"mean_token_accuracy": 0.1356467515230179,
|
|
"num_tokens": 3349870.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.306232357025147,
|
|
"epoch": 0.1529090527200168,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004999465322819222,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.12093094363808632,
|
|
"num_tokens": 3359573.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.253879976272583,
|
|
"epoch": 0.15332913253518168,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999458774738851,
|
|
"loss": 6.2008,
|
|
"mean_token_accuracy": 0.1337040476500988,
|
|
"num_tokens": 3368577.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.189093828201294,
|
|
"epoch": 0.15374921235034655,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999452186810476,
|
|
"loss": 6.1859,
|
|
"mean_token_accuracy": 0.12909814566373826,
|
|
"num_tokens": 3377801.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.290127277374268,
|
|
"epoch": 0.15416929216551145,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999445559034214,
|
|
"loss": 6.2251,
|
|
"mean_token_accuracy": 0.13048515170812608,
|
|
"num_tokens": 3386666.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.365573501586914,
|
|
"epoch": 0.15458937198067632,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999438891410181,
|
|
"loss": 6.364,
|
|
"mean_token_accuracy": 0.11682043001055717,
|
|
"num_tokens": 3396086.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.219829654693603,
|
|
"epoch": 0.15500945179584122,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999432183938496,
|
|
"loss": 6.2847,
|
|
"mean_token_accuracy": 0.12174131944775582,
|
|
"num_tokens": 3404894.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.1805830001831055,
|
|
"epoch": 0.1554295316110061,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999425436619279,
|
|
"loss": 6.2621,
|
|
"mean_token_accuracy": 0.119705418497324,
|
|
"num_tokens": 3414172.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.348053646087647,
|
|
"epoch": 0.15584961142617096,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.000499941864945265,
|
|
"loss": 6.2477,
|
|
"mean_token_accuracy": 0.11934950053691865,
|
|
"num_tokens": 3423409.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.174108409881592,
|
|
"epoch": 0.15626969124133586,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999411822438726,
|
|
"loss": 6.1935,
|
|
"mean_token_accuracy": 0.12505294382572174,
|
|
"num_tokens": 3433047.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.257612848281861,
|
|
"epoch": 0.15668977105650073,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499940495557763,
|
|
"loss": 6.178,
|
|
"mean_token_accuracy": 0.12779488489031793,
|
|
"num_tokens": 3442490.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.248907375335693,
|
|
"epoch": 0.15710985087166562,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999398048869485,
|
|
"loss": 6.2472,
|
|
"mean_token_accuracy": 0.12368729263544083,
|
|
"num_tokens": 3451804.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.3145753860473635,
|
|
"epoch": 0.1575299306868305,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499939110231441,
|
|
"loss": 6.2386,
|
|
"mean_token_accuracy": 0.1283128082752228,
|
|
"num_tokens": 3461481.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.25744366645813,
|
|
"epoch": 0.1579500105019954,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999384115912531,
|
|
"loss": 6.2722,
|
|
"mean_token_accuracy": 0.12746385112404823,
|
|
"num_tokens": 3471798.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.1273274421691895,
|
|
"epoch": 0.15837009031716026,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000499937708966397,
|
|
"loss": 6.1695,
|
|
"mean_token_accuracy": 0.1235118955373764,
|
|
"num_tokens": 3481386.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.278209686279297,
|
|
"epoch": 0.15879017013232513,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999370023568853,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.1265706330537796,
|
|
"num_tokens": 3489981.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.165022706985473,
|
|
"epoch": 0.15921024994749003,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999362917627304,
|
|
"loss": 6.1462,
|
|
"mean_token_accuracy": 0.12947175428271293,
|
|
"num_tokens": 3498551.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.203568363189698,
|
|
"epoch": 0.1596303297626549,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999355771839448,
|
|
"loss": 6.1261,
|
|
"mean_token_accuracy": 0.12978117987513543,
|
|
"num_tokens": 3507921.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.325990772247314,
|
|
"epoch": 0.1600504095778198,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999348586205414,
|
|
"loss": 6.3032,
|
|
"mean_token_accuracy": 0.1252683699131012,
|
|
"num_tokens": 3517570.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.316230726242066,
|
|
"epoch": 0.16047048939298467,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999341360725327,
|
|
"loss": 6.2873,
|
|
"mean_token_accuracy": 0.1217451848089695,
|
|
"num_tokens": 3526774.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.25418004989624,
|
|
"epoch": 0.16089056920814954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999334095399317,
|
|
"loss": 6.2253,
|
|
"mean_token_accuracy": 0.13255979344248772,
|
|
"num_tokens": 3535319.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.0919859409332275,
|
|
"epoch": 0.16131064902331443,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999326790227512,
|
|
"loss": 6.192,
|
|
"mean_token_accuracy": 0.12934273406863211,
|
|
"num_tokens": 3544468.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.13924469947815,
|
|
"epoch": 0.1617307288384793,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004999319445210041,
|
|
"loss": 6.0772,
|
|
"mean_token_accuracy": 0.1331401713192463,
|
|
"num_tokens": 3553529.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.140831708908081,
|
|
"epoch": 0.1621508086536442,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999312060347034,
|
|
"loss": 6.1169,
|
|
"mean_token_accuracy": 0.128947152197361,
|
|
"num_tokens": 3563053.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.201217079162598,
|
|
"epoch": 0.16257088846880907,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999304635638621,
|
|
"loss": 6.0724,
|
|
"mean_token_accuracy": 0.1313454084098339,
|
|
"num_tokens": 3571877.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.137188291549682,
|
|
"epoch": 0.16299096828397394,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 0.0004999297171084935,
|
|
"loss": 6.1144,
|
|
"mean_token_accuracy": 0.13178201764822006,
|
|
"num_tokens": 3581496.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.274984455108642,
|
|
"epoch": 0.16341104809913884,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004999289666686109,
|
|
"loss": 6.1397,
|
|
"mean_token_accuracy": 0.12548287436366082,
|
|
"num_tokens": 3590752.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.027514791488647,
|
|
"epoch": 0.1638311279143037,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004999282122442274,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.12893687859177588,
|
|
"num_tokens": 3599885.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.314913415908814,
|
|
"epoch": 0.1642512077294686,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999274538353564,
|
|
"loss": 6.225,
|
|
"mean_token_accuracy": 0.12287019938230515,
|
|
"num_tokens": 3610039.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.137080287933349,
|
|
"epoch": 0.16467128754463348,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999266914420114,
|
|
"loss": 6.1398,
|
|
"mean_token_accuracy": 0.12600617855787277,
|
|
"num_tokens": 3619954.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.19411187171936,
|
|
"epoch": 0.16509136735979837,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499925925064206,
|
|
"loss": 6.1087,
|
|
"mean_token_accuracy": 0.13167392686009408,
|
|
"num_tokens": 3628164.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.276717853546143,
|
|
"epoch": 0.16551144717496324,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999251547019535,
|
|
"loss": 6.2662,
|
|
"mean_token_accuracy": 0.12937605381011963,
|
|
"num_tokens": 3636778.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.321251440048218,
|
|
"epoch": 0.16593152699012811,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999243803552678,
|
|
"loss": 6.2031,
|
|
"mean_token_accuracy": 0.12865082323551177,
|
|
"num_tokens": 3647046.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.092304801940918,
|
|
"epoch": 0.166351606805293,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999236020241625,
|
|
"loss": 6.1208,
|
|
"mean_token_accuracy": 0.12650337740778922,
|
|
"num_tokens": 3656130.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.216774225234985,
|
|
"epoch": 0.16677168662045788,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999228197086514,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.11985883414745331,
|
|
"num_tokens": 3666145.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 6.222474908828735,
|
|
"epoch": 0.16719176643562278,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004999220334087484,
|
|
"loss": 6.2471,
|
|
"mean_token_accuracy": 0.1268869273364544,
|
|
"num_tokens": 3676722.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.2897861957550045,
|
|
"epoch": 0.16761184625078765,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004999212431244673,
|
|
"loss": 6.2493,
|
|
"mean_token_accuracy": 0.1202566534280777,
|
|
"num_tokens": 3685880.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.107799291610718,
|
|
"epoch": 0.16803192606595252,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999204488558222,
|
|
"loss": 6.0634,
|
|
"mean_token_accuracy": 0.13050426542758942,
|
|
"num_tokens": 3695167.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.197722768783569,
|
|
"epoch": 0.16845200588111742,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999196506028273,
|
|
"loss": 6.183,
|
|
"mean_token_accuracy": 0.1260111801326275,
|
|
"num_tokens": 3703700.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.235522031784058,
|
|
"epoch": 0.1688720856962823,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004999188483654965,
|
|
"loss": 6.1217,
|
|
"mean_token_accuracy": 0.1260783888399601,
|
|
"num_tokens": 3712825.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.099165439605713,
|
|
"epoch": 0.16929216551144718,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999180421438442,
|
|
"loss": 6.089,
|
|
"mean_token_accuracy": 0.12902323082089423,
|
|
"num_tokens": 3721807.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 6.248017930984497,
|
|
"epoch": 0.16971224532661205,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999172319378846,
|
|
"loss": 6.2757,
|
|
"mean_token_accuracy": 0.12072234824299813,
|
|
"num_tokens": 3730502.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.263659858703614,
|
|
"epoch": 0.17013232514177692,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004999164177476319,
|
|
"loss": 6.149,
|
|
"mean_token_accuracy": 0.12994196712970735,
|
|
"num_tokens": 3739696.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.063019037246704,
|
|
"epoch": 0.17055240495694182,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004999155995731009,
|
|
"loss": 6.1537,
|
|
"mean_token_accuracy": 0.13063850849866868,
|
|
"num_tokens": 3748675.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.347209215164185,
|
|
"epoch": 0.1709724847721067,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999147774143057,
|
|
"loss": 6.233,
|
|
"mean_token_accuracy": 0.12277846410870552,
|
|
"num_tokens": 3757714.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.09723424911499,
|
|
"epoch": 0.1713925645872716,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499913951271261,
|
|
"loss": 6.0474,
|
|
"mean_token_accuracy": 0.13144370764493943,
|
|
"num_tokens": 3767589.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.220744895935058,
|
|
"epoch": 0.17181264440243646,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999131211439816,
|
|
"loss": 6.1603,
|
|
"mean_token_accuracy": 0.12925415337085724,
|
|
"num_tokens": 3777261.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.157608842849731,
|
|
"epoch": 0.17223272421760136,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499912287032482,
|
|
"loss": 6.1136,
|
|
"mean_token_accuracy": 0.13876328021287918,
|
|
"num_tokens": 3786658.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 6.097555351257324,
|
|
"epoch": 0.17265280403276623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499911448936777,
|
|
"loss": 6.1039,
|
|
"mean_token_accuracy": 0.13591505512595176,
|
|
"num_tokens": 3794977.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.0962035179138185,
|
|
"epoch": 0.1730728838479311,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004999106068568816,
|
|
"loss": 6.1794,
|
|
"mean_token_accuracy": 0.12809087112545967,
|
|
"num_tokens": 3805138.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.231352376937866,
|
|
"epoch": 0.173492963663096,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999097607928106,
|
|
"loss": 6.1206,
|
|
"mean_token_accuracy": 0.1363896384835243,
|
|
"num_tokens": 3814444.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.190911483764649,
|
|
"epoch": 0.17391304347826086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004999089107445788,
|
|
"loss": 6.0912,
|
|
"mean_token_accuracy": 0.12825695872306825,
|
|
"num_tokens": 3822859.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.055686283111572,
|
|
"epoch": 0.17433312329342576,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004999080567122016,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.12722248658537866,
|
|
"num_tokens": 3833159.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.126674318313599,
|
|
"epoch": 0.17475320310859063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999071986956941,
|
|
"loss": 6.1145,
|
|
"mean_token_accuracy": 0.13205313310027122,
|
|
"num_tokens": 3842136.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.132652282714844,
|
|
"epoch": 0.1751732829237555,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999063366950713,
|
|
"loss": 6.1975,
|
|
"mean_token_accuracy": 0.12595101371407508,
|
|
"num_tokens": 3851406.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.16230001449585,
|
|
"epoch": 0.1755933627389204,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999054707103486,
|
|
"loss": 6.1031,
|
|
"mean_token_accuracy": 0.1279636099934578,
|
|
"num_tokens": 3861061.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.178242540359497,
|
|
"epoch": 0.17601344255408527,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004999046007415412,
|
|
"loss": 6.0821,
|
|
"mean_token_accuracy": 0.12796319127082825,
|
|
"num_tokens": 3870357.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.1904627799987795,
|
|
"epoch": 0.17643352236925017,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999037267886646,
|
|
"loss": 6.1006,
|
|
"mean_token_accuracy": 0.13064605742692947,
|
|
"num_tokens": 3879393.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.076858758926392,
|
|
"epoch": 0.17685360218441504,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999028488517343,
|
|
"loss": 6.1097,
|
|
"mean_token_accuracy": 0.1291967511177063,
|
|
"num_tokens": 3888030.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 6.22084493637085,
|
|
"epoch": 0.1772736819995799,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999019669307659,
|
|
"loss": 6.1189,
|
|
"mean_token_accuracy": 0.1333627261221409,
|
|
"num_tokens": 3897430.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.15262508392334,
|
|
"epoch": 0.1776937618147448,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004999010810257749,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.1225900873541832,
|
|
"num_tokens": 3907711.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.100615692138672,
|
|
"epoch": 0.17811384162990967,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004999001911367771,
|
|
"loss": 6.0784,
|
|
"mean_token_accuracy": 0.13617549166083337,
|
|
"num_tokens": 3915816.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.130948638916015,
|
|
"epoch": 0.17853392144507457,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998992972637883,
|
|
"loss": 6.2002,
|
|
"mean_token_accuracy": 0.12154756337404252,
|
|
"num_tokens": 3925162.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.210935020446778,
|
|
"epoch": 0.17895400126023944,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998983994068242,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.1311741665005684,
|
|
"num_tokens": 3934476.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.098375844955444,
|
|
"epoch": 0.17937408107540434,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998974975659006,
|
|
"loss": 6.1351,
|
|
"mean_token_accuracy": 0.12713489457964897,
|
|
"num_tokens": 3943501.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.198156356811523,
|
|
"epoch": 0.1797941608905692,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998965917410338,
|
|
"loss": 6.1279,
|
|
"mean_token_accuracy": 0.12831434607505798,
|
|
"num_tokens": 3953663.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.133723402023316,
|
|
"epoch": 0.18021424070573408,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998956819322397,
|
|
"loss": 6.088,
|
|
"mean_token_accuracy": 0.12946128249168395,
|
|
"num_tokens": 3962634.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.1390259742736815,
|
|
"epoch": 0.18063432052089898,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998947681395343,
|
|
"loss": 6.0855,
|
|
"mean_token_accuracy": 0.13397737592458725,
|
|
"num_tokens": 3972496.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.254479598999024,
|
|
"epoch": 0.18105440033606385,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499893850362934,
|
|
"loss": 6.3337,
|
|
"mean_token_accuracy": 0.12332669869065285,
|
|
"num_tokens": 3980724.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.2081263065338135,
|
|
"epoch": 0.18147448015122875,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998929286024548,
|
|
"loss": 6.1709,
|
|
"mean_token_accuracy": 0.12541203945875168,
|
|
"num_tokens": 3989842.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.17150354385376,
|
|
"epoch": 0.18189455996639362,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998920028581133,
|
|
"loss": 6.0848,
|
|
"mean_token_accuracy": 0.1349337212741375,
|
|
"num_tokens": 3998534.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.159293746948242,
|
|
"epoch": 0.18231463978155849,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998910731299258,
|
|
"loss": 6.0963,
|
|
"mean_token_accuracy": 0.12547213733196258,
|
|
"num_tokens": 4007677.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.151889276504517,
|
|
"epoch": 0.18273471959672338,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998901394179085,
|
|
"loss": 6.1632,
|
|
"mean_token_accuracy": 0.12913861274719238,
|
|
"num_tokens": 4016347.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.125647306442261,
|
|
"epoch": 0.18315479941188825,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998892017220784,
|
|
"loss": 6.0392,
|
|
"mean_token_accuracy": 0.13342646807432174,
|
|
"num_tokens": 4025199.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.153134059906006,
|
|
"epoch": 0.18357487922705315,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998882600424519,
|
|
"loss": 6.0961,
|
|
"mean_token_accuracy": 0.12564898803830146,
|
|
"num_tokens": 4033933.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.154629516601562,
|
|
"epoch": 0.18399495904221802,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998873143790455,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.13878689035773278,
|
|
"num_tokens": 4042891.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.129179048538208,
|
|
"epoch": 0.1844150388573829,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998863647318763,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.1272033281624317,
|
|
"num_tokens": 4051123.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.1010294437408445,
|
|
"epoch": 0.1848351186725478,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998854111009608,
|
|
"loss": 6.1152,
|
|
"mean_token_accuracy": 0.12936600148677826,
|
|
"num_tokens": 4060025.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.11760630607605,
|
|
"epoch": 0.18525519848771266,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998844534863161,
|
|
"loss": 6.0205,
|
|
"mean_token_accuracy": 0.12755625769495965,
|
|
"num_tokens": 4069363.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.150998878479004,
|
|
"epoch": 0.18567527830287756,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998834918879592,
|
|
"loss": 6.1697,
|
|
"mean_token_accuracy": 0.1331343524158001,
|
|
"num_tokens": 4078855.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.200693273544312,
|
|
"epoch": 0.18609535811804243,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499882526305907,
|
|
"loss": 6.1425,
|
|
"mean_token_accuracy": 0.12896015048027037,
|
|
"num_tokens": 4087801.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 6.137786483764648,
|
|
"epoch": 0.18651543793320732,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998815567401765,
|
|
"loss": 6.1525,
|
|
"mean_token_accuracy": 0.12895300164818763,
|
|
"num_tokens": 4096949.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.203073024749756,
|
|
"epoch": 0.1869355177483722,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998805831907851,
|
|
"loss": 6.1034,
|
|
"mean_token_accuracy": 0.1270811975002289,
|
|
"num_tokens": 4105399.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.1230597496032715,
|
|
"epoch": 0.18735559756353706,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998796056577501,
|
|
"loss": 6.0488,
|
|
"mean_token_accuracy": 0.12729625552892684,
|
|
"num_tokens": 4113873.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.073714399337769,
|
|
"epoch": 0.18777567737870196,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998786241410886,
|
|
"loss": 6.1026,
|
|
"mean_token_accuracy": 0.13166192471981047,
|
|
"num_tokens": 4123528.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.234827375411987,
|
|
"epoch": 0.18819575719386683,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499877638640818,
|
|
"loss": 6.1114,
|
|
"mean_token_accuracy": 0.12597778365015982,
|
|
"num_tokens": 4133370.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.071894741058349,
|
|
"epoch": 0.18861583700903173,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000499876649156956,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.1308871813118458,
|
|
"num_tokens": 4142370.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 6.07040696144104,
|
|
"epoch": 0.1890359168241966,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998756556895196,
|
|
"loss": 6.1178,
|
|
"mean_token_accuracy": 0.13069864958524705,
|
|
"num_tokens": 4152367.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.167872524261474,
|
|
"epoch": 0.18945599663936147,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499874658238527,
|
|
"loss": 6.1024,
|
|
"mean_token_accuracy": 0.13190473541617392,
|
|
"num_tokens": 4161126.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.139232063293457,
|
|
"epoch": 0.18987607645452637,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998736568039957,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.13119693994522094,
|
|
"num_tokens": 4169910.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.1185729026794435,
|
|
"epoch": 0.19029615626969124,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998726513859432,
|
|
"loss": 6.1461,
|
|
"mean_token_accuracy": 0.12717667669057847,
|
|
"num_tokens": 4179893.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.202062654495239,
|
|
"epoch": 0.19071623608485613,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004998716419843875,
|
|
"loss": 6.1633,
|
|
"mean_token_accuracy": 0.13450514376163483,
|
|
"num_tokens": 4190065.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.053268957138061,
|
|
"epoch": 0.191136315900021,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998706285993465,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.12834293991327286,
|
|
"num_tokens": 4198395.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 6.130187177658081,
|
|
"epoch": 0.19155639571518587,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998696112308381,
|
|
"loss": 6.0944,
|
|
"mean_token_accuracy": 0.12858275175094605,
|
|
"num_tokens": 4207555.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.074777889251709,
|
|
"epoch": 0.19197647553035077,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998685898788803,
|
|
"loss": 6.0485,
|
|
"mean_token_accuracy": 0.13106716349720954,
|
|
"num_tokens": 4216533.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.191452217102051,
|
|
"epoch": 0.19239655534551564,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998675645434914,
|
|
"loss": 6.1523,
|
|
"mean_token_accuracy": 0.13225150257349014,
|
|
"num_tokens": 4225575.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 6.0228188037872314,
|
|
"epoch": 0.19281663516068054,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998665352246891,
|
|
"loss": 5.9361,
|
|
"mean_token_accuracy": 0.13841283321380615,
|
|
"num_tokens": 4234306.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 6.043151473999023,
|
|
"epoch": 0.1932367149758454,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998655019224921,
|
|
"loss": 6.1283,
|
|
"mean_token_accuracy": 0.13190191760659217,
|
|
"num_tokens": 4243998.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.166877937316895,
|
|
"epoch": 0.19365679479101028,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998644646369185,
|
|
"loss": 6.0139,
|
|
"mean_token_accuracy": 0.12847840487957002,
|
|
"num_tokens": 4253653.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.034109115600586,
|
|
"epoch": 0.19407687460617518,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998634233679865,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.12612878382205964,
|
|
"num_tokens": 4263305.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.1194260597229,
|
|
"epoch": 0.19449695442134005,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499862378115715,
|
|
"loss": 5.9818,
|
|
"mean_token_accuracy": 0.13570686057209969,
|
|
"num_tokens": 4272212.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.182863759994507,
|
|
"epoch": 0.19491703423650494,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998613288801221,
|
|
"loss": 6.1959,
|
|
"mean_token_accuracy": 0.1276652343571186,
|
|
"num_tokens": 4281445.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 6.213861799240112,
|
|
"epoch": 0.1953371140516698,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004998602756612267,
|
|
"loss": 6.1058,
|
|
"mean_token_accuracy": 0.12670243680477142,
|
|
"num_tokens": 4290938.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 6.066101360321045,
|
|
"epoch": 0.1957571938668347,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998592184590471,
|
|
"loss": 6.1379,
|
|
"mean_token_accuracy": 0.12725966945290565,
|
|
"num_tokens": 4300022.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.080681276321411,
|
|
"epoch": 0.19617727368199958,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998581572736024,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.1344592235982418,
|
|
"num_tokens": 4308910.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.050167417526245,
|
|
"epoch": 0.19659735349716445,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998570921049112,
|
|
"loss": 5.9814,
|
|
"mean_token_accuracy": 0.13220275193452835,
|
|
"num_tokens": 4317136.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.09632978439331,
|
|
"epoch": 0.19701743331232935,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004998560229529924,
|
|
"loss": 6.0501,
|
|
"mean_token_accuracy": 0.1387757182121277,
|
|
"num_tokens": 4326163.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.229255342483521,
|
|
"epoch": 0.19743751312749422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998549498178649,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.12868764251470566,
|
|
"num_tokens": 4335837.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 6.126859140396118,
|
|
"epoch": 0.19785759294265912,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004998538726995477,
|
|
"loss": 6.1084,
|
|
"mean_token_accuracy": 0.13344382494688034,
|
|
"num_tokens": 4345108.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 6.168588161468506,
|
|
"epoch": 0.198277672757824,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049985279159806,
|
|
"loss": 6.119,
|
|
"mean_token_accuracy": 0.12684730514883996,
|
|
"num_tokens": 4353761.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.090028953552246,
|
|
"epoch": 0.19869775257298886,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998517065134208,
|
|
"loss": 6.0824,
|
|
"mean_token_accuracy": 0.13213628232479097,
|
|
"num_tokens": 4363244.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.138245010375977,
|
|
"epoch": 0.19911783238815375,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004998506174456494,
|
|
"loss": 6.0839,
|
|
"mean_token_accuracy": 0.12802947238087653,
|
|
"num_tokens": 4373034.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 6.12951922416687,
|
|
"epoch": 0.19953791220331862,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004998495243947653,
|
|
"loss": 6.0216,
|
|
"mean_token_accuracy": 0.1251508317887783,
|
|
"num_tokens": 4382554.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 6.1475914478302,
|
|
"epoch": 0.19995799201848352,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004998484273607875,
|
|
"loss": 6.0463,
|
|
"mean_token_accuracy": 0.136245708912611,
|
|
"num_tokens": 4391001.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.926258325576782,
|
|
"epoch": 0.2003780718336484,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998473263437356,
|
|
"loss": 5.9565,
|
|
"mean_token_accuracy": 0.13519108295440674,
|
|
"num_tokens": 4400632.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 6.048220825195313,
|
|
"epoch": 0.20079815164881326,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499846221343629,
|
|
"loss": 6.051,
|
|
"mean_token_accuracy": 0.13025175258517266,
|
|
"num_tokens": 4409565.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 6.0700782299041744,
|
|
"epoch": 0.20121823146397816,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998451123604875,
|
|
"loss": 5.9988,
|
|
"mean_token_accuracy": 0.14039506316184996,
|
|
"num_tokens": 4418384.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.146504878997803,
|
|
"epoch": 0.20163831127914303,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998439993943306,
|
|
"loss": 6.1232,
|
|
"mean_token_accuracy": 0.13494747802615165,
|
|
"num_tokens": 4427581.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.175554275512695,
|
|
"epoch": 0.20205839109430793,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998428824451779,
|
|
"loss": 6.1094,
|
|
"mean_token_accuracy": 0.1269066423177719,
|
|
"num_tokens": 4436572.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.086094999313355,
|
|
"epoch": 0.2024784709094728,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998417615130495,
|
|
"loss": 6.1156,
|
|
"mean_token_accuracy": 0.12977832332253456,
|
|
"num_tokens": 4445230.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 6.189484167098999,
|
|
"epoch": 0.2028985507246377,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998406365979649,
|
|
"loss": 6.1725,
|
|
"mean_token_accuracy": 0.13100939616560936,
|
|
"num_tokens": 4454251.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.080749225616455,
|
|
"epoch": 0.20331863053980256,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004998395076999443,
|
|
"loss": 6.0178,
|
|
"mean_token_accuracy": 0.13957264572381972,
|
|
"num_tokens": 4463949.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 6.179844999313355,
|
|
"epoch": 0.20373871035496743,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998383748190076,
|
|
"loss": 6.2136,
|
|
"mean_token_accuracy": 0.1258860044181347,
|
|
"num_tokens": 4473373.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 6.209265089035034,
|
|
"epoch": 0.20415879017013233,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998372379551748,
|
|
"loss": 6.0447,
|
|
"mean_token_accuracy": 0.13152522593736649,
|
|
"num_tokens": 4482303.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 6.047933959960938,
|
|
"epoch": 0.2045788699852972,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998360971084663,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.1300078108906746,
|
|
"num_tokens": 4491214.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.923014402389526,
|
|
"epoch": 0.2049989498004621,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998349522789019,
|
|
"loss": 5.9367,
|
|
"mean_token_accuracy": 0.13840087428689002,
|
|
"num_tokens": 4500099.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 6.065491151809693,
|
|
"epoch": 0.20541902961562697,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004998338034665021,
|
|
"loss": 6.0088,
|
|
"mean_token_accuracy": 0.14065721929073333,
|
|
"num_tokens": 4509893.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.0568382263183596,
|
|
"epoch": 0.20583910943079184,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998326506712872,
|
|
"loss": 5.9933,
|
|
"mean_token_accuracy": 0.13122306242585183,
|
|
"num_tokens": 4518606.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.102985429763794,
|
|
"epoch": 0.20625918924595674,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998314938932778,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.13163421601057052,
|
|
"num_tokens": 4528392.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.143069076538086,
|
|
"epoch": 0.2066792690611216,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998303331324943,
|
|
"loss": 6.0446,
|
|
"mean_token_accuracy": 0.13527958691120148,
|
|
"num_tokens": 4536983.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.983616924285888,
|
|
"epoch": 0.2070993488762865,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998291683889571,
|
|
"loss": 5.9545,
|
|
"mean_token_accuracy": 0.13531955927610398,
|
|
"num_tokens": 4544967.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 6.107338380813599,
|
|
"epoch": 0.20751942869145137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499827999662687,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.12663825750350952,
|
|
"num_tokens": 4554646.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 6.1525249004364015,
|
|
"epoch": 0.20793950850661624,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004998268269537046,
|
|
"loss": 6.0498,
|
|
"mean_token_accuracy": 0.13295727223157883,
|
|
"num_tokens": 4564040.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.977402019500732,
|
|
"epoch": 0.20835958832178114,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998256502620308,
|
|
"loss": 6.0631,
|
|
"mean_token_accuracy": 0.13584776520729064,
|
|
"num_tokens": 4573758.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 6.187655830383301,
|
|
"epoch": 0.208779668136946,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004998244695876864,
|
|
"loss": 6.0894,
|
|
"mean_token_accuracy": 0.12783714309334754,
|
|
"num_tokens": 4582097.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 6.000187587738037,
|
|
"epoch": 0.2091997479521109,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998232849306921,
|
|
"loss": 6.0587,
|
|
"mean_token_accuracy": 0.1367252618074417,
|
|
"num_tokens": 4590687.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 6.167983675003052,
|
|
"epoch": 0.20961982776727578,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004998220962910693,
|
|
"loss": 6.0418,
|
|
"mean_token_accuracy": 0.1291399121284485,
|
|
"num_tokens": 4599497.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 6.0570958137512205,
|
|
"epoch": 0.21003990758244068,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998209036688386,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.134087672829628,
|
|
"num_tokens": 4607958.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 6.154553699493408,
|
|
"epoch": 0.21045998739760555,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998197070640216,
|
|
"loss": 6.1436,
|
|
"mean_token_accuracy": 0.1265629693865776,
|
|
"num_tokens": 4617515.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 6.159878873825074,
|
|
"epoch": 0.21088006721277042,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998185064766391,
|
|
"loss": 6.029,
|
|
"mean_token_accuracy": 0.13321105763316154,
|
|
"num_tokens": 4627037.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.991772747039795,
|
|
"epoch": 0.21130014702793531,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004998173019067127,
|
|
"loss": 6.0263,
|
|
"mean_token_accuracy": 0.13551492914557456,
|
|
"num_tokens": 4637393.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 6.076245498657227,
|
|
"epoch": 0.21172022684310018,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004998160933542633,
|
|
"loss": 6.0656,
|
|
"mean_token_accuracy": 0.1218369334936142,
|
|
"num_tokens": 4646832.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 6.151754760742188,
|
|
"epoch": 0.21214030665826508,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998148808193128,
|
|
"loss": 6.0983,
|
|
"mean_token_accuracy": 0.13457245901226997,
|
|
"num_tokens": 4655719.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 6.129997682571411,
|
|
"epoch": 0.21256038647342995,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004998136643018823,
|
|
"loss": 6.0362,
|
|
"mean_token_accuracy": 0.13282962441444396,
|
|
"num_tokens": 4665364.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 6.060281705856323,
|
|
"epoch": 0.21298046628859482,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998124438019935,
|
|
"loss": 6.016,
|
|
"mean_token_accuracy": 0.1327340230345726,
|
|
"num_tokens": 4674760.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.969087028503418,
|
|
"epoch": 0.21340054610375972,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004998112193196681,
|
|
"loss": 5.9355,
|
|
"mean_token_accuracy": 0.1348019614815712,
|
|
"num_tokens": 4683900.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.984380483627319,
|
|
"epoch": 0.2138206259189246,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998099908549277,
|
|
"loss": 5.9913,
|
|
"mean_token_accuracy": 0.13222553506493567,
|
|
"num_tokens": 4693915.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.969556903839111,
|
|
"epoch": 0.2142407057340895,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499808758407794,
|
|
"loss": 5.8426,
|
|
"mean_token_accuracy": 0.14078716412186623,
|
|
"num_tokens": 4703102.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 6.0391675472259525,
|
|
"epoch": 0.21466078554925436,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998075219782889,
|
|
"loss": 6.076,
|
|
"mean_token_accuracy": 0.13493016585707665,
|
|
"num_tokens": 4712925.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 6.044742774963379,
|
|
"epoch": 0.21508086536441923,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998062815664344,
|
|
"loss": 6.0143,
|
|
"mean_token_accuracy": 0.1313328728079796,
|
|
"num_tokens": 4722641.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 6.006574583053589,
|
|
"epoch": 0.21550094517958412,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998050371722524,
|
|
"loss": 6.0658,
|
|
"mean_token_accuracy": 0.13319918289780616,
|
|
"num_tokens": 4732603.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.998908233642578,
|
|
"epoch": 0.215921024994749,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004998037887957649,
|
|
"loss": 5.91,
|
|
"mean_token_accuracy": 0.13604277446866037,
|
|
"num_tokens": 4742644.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 6.173721647262573,
|
|
"epoch": 0.2163411048099139,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004998025364369939,
|
|
"loss": 6.2348,
|
|
"mean_token_accuracy": 0.1272044688463211,
|
|
"num_tokens": 4751482.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 6.235174703598022,
|
|
"epoch": 0.21676118462507876,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998012800959619,
|
|
"loss": 6.0898,
|
|
"mean_token_accuracy": 0.13052162379026414,
|
|
"num_tokens": 4760593.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 6.111858797073364,
|
|
"epoch": 0.21718126444024366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004998000197726909,
|
|
"loss": 6.0859,
|
|
"mean_token_accuracy": 0.13651981949806213,
|
|
"num_tokens": 4769294.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 6.069575262069702,
|
|
"epoch": 0.21760134425540853,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997987554672033,
|
|
"loss": 5.9867,
|
|
"mean_token_accuracy": 0.13439425751566886,
|
|
"num_tokens": 4779239.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 6.047330856323242,
|
|
"epoch": 0.2180214240705734,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004997974871795215,
|
|
"loss": 6.0684,
|
|
"mean_token_accuracy": 0.1306284710764885,
|
|
"num_tokens": 4788211.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 6.074938344955444,
|
|
"epoch": 0.2184415038857383,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000499796214909668,
|
|
"loss": 6.0291,
|
|
"mean_token_accuracy": 0.13745831623673438,
|
|
"num_tokens": 4797921.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 6.087161684036255,
|
|
"epoch": 0.21886158370090317,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004997949386576653,
|
|
"loss": 6.0259,
|
|
"mean_token_accuracy": 0.13380660563707353,
|
|
"num_tokens": 4807772.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 6.045609188079834,
|
|
"epoch": 0.21928166351606806,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000499793658423536,
|
|
"loss": 6.053,
|
|
"mean_token_accuracy": 0.12916495203971862,
|
|
"num_tokens": 4817999.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 6.102342319488526,
|
|
"epoch": 0.21970174333123293,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997923742073028,
|
|
"loss": 6.0064,
|
|
"mean_token_accuracy": 0.14091803804039954,
|
|
"num_tokens": 4826679.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.991182327270508,
|
|
"epoch": 0.2201218231463978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997910860089884,
|
|
"loss": 6.0052,
|
|
"mean_token_accuracy": 0.13694314211606978,
|
|
"num_tokens": 4834998.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 6.100556564331055,
|
|
"epoch": 0.2205419029615627,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997897938286156,
|
|
"loss": 5.9615,
|
|
"mean_token_accuracy": 0.13899449855089188,
|
|
"num_tokens": 4843635.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 6.097274303436279,
|
|
"epoch": 0.22096198277672757,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004997884976662075,
|
|
"loss": 6.0782,
|
|
"mean_token_accuracy": 0.13321034833788872,
|
|
"num_tokens": 4852027.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 6.147892570495605,
|
|
"epoch": 0.22138206259189247,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997871975217868,
|
|
"loss": 5.997,
|
|
"mean_token_accuracy": 0.14202353730797768,
|
|
"num_tokens": 4861244.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.8932945251464846,
|
|
"epoch": 0.22180214240705734,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997858933953768,
|
|
"loss": 5.9307,
|
|
"mean_token_accuracy": 0.13638841062784196,
|
|
"num_tokens": 4869902.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.95978422164917,
|
|
"epoch": 0.2222222222222222,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997845852870004,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.1398716911673546,
|
|
"num_tokens": 4878502.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 6.00921368598938,
|
|
"epoch": 0.2226423020373871,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997832731966806,
|
|
"loss": 5.9483,
|
|
"mean_token_accuracy": 0.14096327498555183,
|
|
"num_tokens": 4888348.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.991452217102051,
|
|
"epoch": 0.22306238185255198,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997819571244411,
|
|
"loss": 6.0189,
|
|
"mean_token_accuracy": 0.1372461050748825,
|
|
"num_tokens": 4897302.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 6.012991952896118,
|
|
"epoch": 0.22348246166771688,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997806370703049,
|
|
"loss": 6.0444,
|
|
"mean_token_accuracy": 0.13569730073213576,
|
|
"num_tokens": 4907078.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.988911724090576,
|
|
"epoch": 0.22390254148288175,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004997793130342954,
|
|
"loss": 5.874,
|
|
"mean_token_accuracy": 0.13960873782634736,
|
|
"num_tokens": 4917489.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.930651092529297,
|
|
"epoch": 0.22432262129804661,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997779850164363,
|
|
"loss": 5.9779,
|
|
"mean_token_accuracy": 0.13561228066682815,
|
|
"num_tokens": 4927073.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 6.158057308197021,
|
|
"epoch": 0.2247427011132115,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004997766530167508,
|
|
"loss": 6.0815,
|
|
"mean_token_accuracy": 0.13055123686790465,
|
|
"num_tokens": 4935464.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 6.137771940231323,
|
|
"epoch": 0.22516278092837638,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997753170352627,
|
|
"loss": 6.1621,
|
|
"mean_token_accuracy": 0.12912468686699868,
|
|
"num_tokens": 4944718.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 6.082327508926392,
|
|
"epoch": 0.22558286074354128,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004997739770719955,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.13314241990447045,
|
|
"num_tokens": 4954223.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 6.058599901199341,
|
|
"epoch": 0.22600294055870615,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499772633126973,
|
|
"loss": 6.0734,
|
|
"mean_token_accuracy": 0.132587993144989,
|
|
"num_tokens": 4963371.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 6.008123540878296,
|
|
"epoch": 0.22642302037387105,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997712852002192,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.14214024171233178,
|
|
"num_tokens": 4972973.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.0829901695251465,
|
|
"epoch": 0.22684310018903592,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997699332917578,
|
|
"loss": 6.1705,
|
|
"mean_token_accuracy": 0.12515681982040405,
|
|
"num_tokens": 4982808.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 6.190164613723755,
|
|
"epoch": 0.2272631800042008,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997685774016127,
|
|
"loss": 6.0492,
|
|
"mean_token_accuracy": 0.13310236856341362,
|
|
"num_tokens": 4992427.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 6.118629407882691,
|
|
"epoch": 0.22768325981936569,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.000499767217529808,
|
|
"loss": 6.2194,
|
|
"mean_token_accuracy": 0.1233941525220871,
|
|
"num_tokens": 5003562.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 6.01776008605957,
|
|
"epoch": 0.22810333963453056,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004997658536763678,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.13683665543794632,
|
|
"num_tokens": 5013429.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 6.101313972473145,
|
|
"epoch": 0.22852341944969545,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004997644858413163,
|
|
"loss": 6.0303,
|
|
"mean_token_accuracy": 0.13920028880238533,
|
|
"num_tokens": 5022045.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.957802677154541,
|
|
"epoch": 0.22894349926486032,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004997631140246775,
|
|
"loss": 5.8742,
|
|
"mean_token_accuracy": 0.1393354929983616,
|
|
"num_tokens": 5032260.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 6.008182525634766,
|
|
"epoch": 0.2293635790800252,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499761738226476,
|
|
"loss": 5.9304,
|
|
"mean_token_accuracy": 0.13518433645367622,
|
|
"num_tokens": 5041688.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 6.007689189910889,
|
|
"epoch": 0.2297836588951901,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499760358446736,
|
|
"loss": 6.0285,
|
|
"mean_token_accuracy": 0.1302636370062828,
|
|
"num_tokens": 5051005.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 6.086931037902832,
|
|
"epoch": 0.23020373871035496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499758974685482,
|
|
"loss": 5.9683,
|
|
"mean_token_accuracy": 0.13642121478915215,
|
|
"num_tokens": 5060084.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 6.020289707183838,
|
|
"epoch": 0.23062381852551986,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997575869427385,
|
|
"loss": 5.9633,
|
|
"mean_token_accuracy": 0.14196947664022447,
|
|
"num_tokens": 5069081.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 6.004650115966797,
|
|
"epoch": 0.23104389834068473,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00049975619521853,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.12970962673425673,
|
|
"num_tokens": 5078597.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.982837867736817,
|
|
"epoch": 0.2314639781558496,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004997547995128814,
|
|
"loss": 6.0116,
|
|
"mean_token_accuracy": 0.13743849247694015,
|
|
"num_tokens": 5087607.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 6.052627325057983,
|
|
"epoch": 0.2318840579710145,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004997533998258171,
|
|
"loss": 6.0129,
|
|
"mean_token_accuracy": 0.13540438339114189,
|
|
"num_tokens": 5097412.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 6.117385768890381,
|
|
"epoch": 0.23230413778617937,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997519961573622,
|
|
"loss": 6.0833,
|
|
"mean_token_accuracy": 0.12936894744634628,
|
|
"num_tokens": 5105817.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 6.181453561782837,
|
|
"epoch": 0.23272421760134426,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997505885075414,
|
|
"loss": 6.1236,
|
|
"mean_token_accuracy": 0.131087327003479,
|
|
"num_tokens": 5114958.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 6.078393983840942,
|
|
"epoch": 0.23314429741650913,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997491768763795,
|
|
"loss": 6.0399,
|
|
"mean_token_accuracy": 0.13298976346850394,
|
|
"num_tokens": 5123728.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 6.067098140716553,
|
|
"epoch": 0.23356437723167403,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997477612639018,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.13075175881385803,
|
|
"num_tokens": 5134099.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 6.135926675796509,
|
|
"epoch": 0.2339844570468389,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997463416701332,
|
|
"loss": 6.0951,
|
|
"mean_token_accuracy": 0.12707924395799636,
|
|
"num_tokens": 5142934.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 6.010523986816406,
|
|
"epoch": 0.23440453686200377,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997449180950989,
|
|
"loss": 5.9263,
|
|
"mean_token_accuracy": 0.15269666612148286,
|
|
"num_tokens": 5151835.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.981678676605225,
|
|
"epoch": 0.23482461667716867,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004997434905388241,
|
|
"loss": 5.9711,
|
|
"mean_token_accuracy": 0.1440896660089493,
|
|
"num_tokens": 5161136.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 6.001285219192505,
|
|
"epoch": 0.23524469649233354,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000499742059001334,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.13934119418263435,
|
|
"num_tokens": 5170741.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 6.018690299987793,
|
|
"epoch": 0.23566477630749844,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997406234826541,
|
|
"loss": 5.9552,
|
|
"mean_token_accuracy": 0.14054046496748923,
|
|
"num_tokens": 5180549.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.938224172592163,
|
|
"epoch": 0.2360848561226633,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004997391839828098,
|
|
"loss": 5.9206,
|
|
"mean_token_accuracy": 0.14346935153007506,
|
|
"num_tokens": 5189486.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.992739534378051,
|
|
"epoch": 0.23650493593782818,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997377405018266,
|
|
"loss": 5.989,
|
|
"mean_token_accuracy": 0.13284722566604615,
|
|
"num_tokens": 5198525.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 6.092206192016602,
|
|
"epoch": 0.23692501575299307,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00049973629303973,
|
|
"loss": 6.0314,
|
|
"mean_token_accuracy": 0.13478757068514824,
|
|
"num_tokens": 5207124.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.945079660415649,
|
|
"epoch": 0.23734509556815794,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004997348415965457,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.13759657815098764,
|
|
"num_tokens": 5216529.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 6.023407697677612,
|
|
"epoch": 0.23776517538332284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997333861722995,
|
|
"loss": 6.0141,
|
|
"mean_token_accuracy": 0.13514548242092134,
|
|
"num_tokens": 5225796.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 6.10746054649353,
|
|
"epoch": 0.2381852551984877,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499731926767017,
|
|
"loss": 6.038,
|
|
"mean_token_accuracy": 0.13310380131006241,
|
|
"num_tokens": 5233876.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.989476442337036,
|
|
"epoch": 0.23860533501365258,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004997304633807242,
|
|
"loss": 6.0249,
|
|
"mean_token_accuracy": 0.13009608685970306,
|
|
"num_tokens": 5244782.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 6.030221557617187,
|
|
"epoch": 0.23902541482881748,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997289960134468,
|
|
"loss": 5.9703,
|
|
"mean_token_accuracy": 0.1368887707591057,
|
|
"num_tokens": 5253453.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.974435091018677,
|
|
"epoch": 0.23944549464398235,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997275246652111,
|
|
"loss": 5.9925,
|
|
"mean_token_accuracy": 0.13992664366960525,
|
|
"num_tokens": 5262355.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.960743093490601,
|
|
"epoch": 0.23986557445914725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499726049336043,
|
|
"loss": 5.9169,
|
|
"mean_token_accuracy": 0.13876279294490815,
|
|
"num_tokens": 5271959.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 6.026579475402832,
|
|
"epoch": 0.24028565427431212,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997245700259686,
|
|
"loss": 5.9378,
|
|
"mean_token_accuracy": 0.14501210153102875,
|
|
"num_tokens": 5281393.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 6.063703155517578,
|
|
"epoch": 0.240705734089477,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004997230867350141,
|
|
"loss": 6.0777,
|
|
"mean_token_accuracy": 0.13284969255328177,
|
|
"num_tokens": 5290979.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 6.101211261749268,
|
|
"epoch": 0.24112581390464188,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997215994632059,
|
|
"loss": 6.0262,
|
|
"mean_token_accuracy": 0.13758746907114983,
|
|
"num_tokens": 5300263.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 6.094251537322998,
|
|
"epoch": 0.24154589371980675,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997201082105704,
|
|
"loss": 6.0534,
|
|
"mean_token_accuracy": 0.13286127597093583,
|
|
"num_tokens": 5309522.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 6.022702550888061,
|
|
"epoch": 0.24196597353497165,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004997186129771338,
|
|
"loss": 6.0403,
|
|
"mean_token_accuracy": 0.13587599471211434,
|
|
"num_tokens": 5319770.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 6.158471012115479,
|
|
"epoch": 0.24238605335013652,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004997171137629226,
|
|
"loss": 6.0553,
|
|
"mean_token_accuracy": 0.13789832219481468,
|
|
"num_tokens": 5328400.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.906137275695801,
|
|
"epoch": 0.24280613316530142,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004997156105679636,
|
|
"loss": 5.8523,
|
|
"mean_token_accuracy": 0.1505324125289917,
|
|
"num_tokens": 5336338.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.937476301193238,
|
|
"epoch": 0.2432262129804663,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997141033922832,
|
|
"loss": 5.9567,
|
|
"mean_token_accuracy": 0.13674451038241386,
|
|
"num_tokens": 5345391.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 6.064019298553466,
|
|
"epoch": 0.24364629279563116,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004997125922359081,
|
|
"loss": 5.9792,
|
|
"mean_token_accuracy": 0.12863812744617462,
|
|
"num_tokens": 5354709.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 6.019229459762573,
|
|
"epoch": 0.24406637261079606,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004997110770988652,
|
|
"loss": 5.8953,
|
|
"mean_token_accuracy": 0.1387791097164154,
|
|
"num_tokens": 5363738.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 6.001317119598388,
|
|
"epoch": 0.24448645242596093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997095579811813,
|
|
"loss": 6.0193,
|
|
"mean_token_accuracy": 0.13423686176538469,
|
|
"num_tokens": 5373583.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 6.057038736343384,
|
|
"epoch": 0.24490653224112582,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004997080348828833,
|
|
"loss": 6.0731,
|
|
"mean_token_accuracy": 0.1342361442744732,
|
|
"num_tokens": 5383486.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 6.072895145416259,
|
|
"epoch": 0.2453266120562907,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997065078039981,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.13158463463187217,
|
|
"num_tokens": 5391974.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 6.060671615600586,
|
|
"epoch": 0.24574669187145556,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997049767445529,
|
|
"loss": 6.0206,
|
|
"mean_token_accuracy": 0.13064797297120095,
|
|
"num_tokens": 5400882.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 6.072234678268432,
|
|
"epoch": 0.24616677168662046,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004997034417045746,
|
|
"loss": 5.9808,
|
|
"mean_token_accuracy": 0.13372990265488624,
|
|
"num_tokens": 5410538.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.924702501296997,
|
|
"epoch": 0.24658685150178533,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004997019026840907,
|
|
"loss": 5.8715,
|
|
"mean_token_accuracy": 0.13977383449673653,
|
|
"num_tokens": 5419406.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.90452995300293,
|
|
"epoch": 0.24700693131695023,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997003596831282,
|
|
"loss": 5.9778,
|
|
"mean_token_accuracy": 0.1360274873673916,
|
|
"num_tokens": 5428817.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 6.072986078262329,
|
|
"epoch": 0.2474270111321151,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996988127017145,
|
|
"loss": 6.0065,
|
|
"mean_token_accuracy": 0.135275649279356,
|
|
"num_tokens": 5438277.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 6.042351722717285,
|
|
"epoch": 0.24784709094728,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996972617398772,
|
|
"loss": 6.0257,
|
|
"mean_token_accuracy": 0.1333914116024971,
|
|
"num_tokens": 5447440.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 6.086295413970947,
|
|
"epoch": 0.24826717076244487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996957067976435,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.1371552027761936,
|
|
"num_tokens": 5455988.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.992445421218872,
|
|
"epoch": 0.24868725057760974,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996941478750411,
|
|
"loss": 5.9653,
|
|
"mean_token_accuracy": 0.13751397803425788,
|
|
"num_tokens": 5464996.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 6.070774841308594,
|
|
"epoch": 0.24910733039277463,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004996925849720975,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.1302956260740757,
|
|
"num_tokens": 5474174.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 6.157161235809326,
|
|
"epoch": 0.2495274102079395,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996910180888405,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.13579627349972725,
|
|
"num_tokens": 5482838.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.956932163238525,
|
|
"epoch": 0.2499474900231044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996894472252977,
|
|
"loss": 6.0037,
|
|
"mean_token_accuracy": 0.13603818491101266,
|
|
"num_tokens": 5491616.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 6.029225301742554,
|
|
"epoch": 0.25036756983826924,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996878723814973,
|
|
"loss": 5.9869,
|
|
"mean_token_accuracy": 0.13199443742632866,
|
|
"num_tokens": 5500942.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 6.036972188949585,
|
|
"epoch": 0.25078764965343414,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996862935574667,
|
|
"loss": 5.9337,
|
|
"mean_token_accuracy": 0.12902862578630447,
|
|
"num_tokens": 5510078.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.945563459396363,
|
|
"epoch": 0.25120772946859904,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996847107532342,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.13469186648726464,
|
|
"num_tokens": 5518924.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 6.076007747650147,
|
|
"epoch": 0.25162780928376394,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996831239688277,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.13338077962398528,
|
|
"num_tokens": 5527385.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.917894792556763,
|
|
"epoch": 0.2520478890989288,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996815332042754,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.1404413752257824,
|
|
"num_tokens": 5536781.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 0.2520478890989288,
|
|
"eval_entropy": 5.782812329743307,
|
|
"eval_loss": 6.003105163574219,
|
|
"eval_mean_token_accuracy": 0.1416803571949664,
|
|
"eval_num_tokens": 5536781.0,
|
|
"eval_runtime": 27.3987,
|
|
"eval_samples_per_second": 1363.789,
|
|
"eval_steps_per_second": 170.483,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.977773952484131,
|
|
"epoch": 0.2524679689140937,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996799384596054,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.13907053023576738,
|
|
"num_tokens": 5545893.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 6.0576560497283936,
|
|
"epoch": 0.2528880487292586,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996783397348461,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.13274262547492982,
|
|
"num_tokens": 5555818.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 6.054492235183716,
|
|
"epoch": 0.2533081285444234,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004996767370300256,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.14041735008358955,
|
|
"num_tokens": 5565331.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 6.005804014205933,
|
|
"epoch": 0.2537282083595883,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996751303451724,
|
|
"loss": 5.9358,
|
|
"mean_token_accuracy": 0.14184233397245408,
|
|
"num_tokens": 5574003.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.961899328231811,
|
|
"epoch": 0.2541482881747532,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996735196803149,
|
|
"loss": 5.8439,
|
|
"mean_token_accuracy": 0.1449878543615341,
|
|
"num_tokens": 5582517.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 6.0015801906585695,
|
|
"epoch": 0.2545683679899181,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004996719050354818,
|
|
"loss": 6.056,
|
|
"mean_token_accuracy": 0.13052123561501502,
|
|
"num_tokens": 5591952.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 6.00065770149231,
|
|
"epoch": 0.25498844780508295,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004996702864107015,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.13981510698795319,
|
|
"num_tokens": 5601460.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 6.187022733688354,
|
|
"epoch": 0.25540852762024785,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996686638060028,
|
|
"loss": 6.0716,
|
|
"mean_token_accuracy": 0.13106706812977792,
|
|
"num_tokens": 5610776.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.974349451065064,
|
|
"epoch": 0.25582860743541275,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996670372214144,
|
|
"loss": 5.9846,
|
|
"mean_token_accuracy": 0.13845233097672463,
|
|
"num_tokens": 5619627.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.915146541595459,
|
|
"epoch": 0.2562486872505776,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996654066569651,
|
|
"loss": 5.8361,
|
|
"mean_token_accuracy": 0.14477361738681793,
|
|
"num_tokens": 5628969.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.960678625106811,
|
|
"epoch": 0.2566687670657425,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996637721126839,
|
|
"loss": 5.9181,
|
|
"mean_token_accuracy": 0.1386953629553318,
|
|
"num_tokens": 5638629.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.996072626113891,
|
|
"epoch": 0.2570888468809074,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004996621335885996,
|
|
"loss": 5.9879,
|
|
"mean_token_accuracy": 0.135421983897686,
|
|
"num_tokens": 5647571.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 6.034391689300537,
|
|
"epoch": 0.2575089266960722,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004996604910847413,
|
|
"loss": 5.8941,
|
|
"mean_token_accuracy": 0.14892763271927834,
|
|
"num_tokens": 5656709.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 6.000552320480347,
|
|
"epoch": 0.2579290065112371,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499658844601138,
|
|
"loss": 6.0898,
|
|
"mean_token_accuracy": 0.13416215255856515,
|
|
"num_tokens": 5665714.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 6.078448486328125,
|
|
"epoch": 0.258349086326402,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499657194137819,
|
|
"loss": 6.0433,
|
|
"mean_token_accuracy": 0.13601171597838402,
|
|
"num_tokens": 5675854.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 6.0375328540802,
|
|
"epoch": 0.2587691661415669,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004996555396948136,
|
|
"loss": 5.8646,
|
|
"mean_token_accuracy": 0.1391562268137932,
|
|
"num_tokens": 5685690.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.9128001689910885,
|
|
"epoch": 0.25918924595673176,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004996538812721509,
|
|
"loss": 5.9151,
|
|
"mean_token_accuracy": 0.14342632815241813,
|
|
"num_tokens": 5695766.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.95283260345459,
|
|
"epoch": 0.25960932577189666,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004996522188698603,
|
|
"loss": 5.983,
|
|
"mean_token_accuracy": 0.13854097425937653,
|
|
"num_tokens": 5704365.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 6.116002321243286,
|
|
"epoch": 0.26002940558706156,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996505524879714,
|
|
"loss": 6.0766,
|
|
"mean_token_accuracy": 0.13496588468551635,
|
|
"num_tokens": 5713345.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 6.015519475936889,
|
|
"epoch": 0.2604494854022264,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996488821265137,
|
|
"loss": 5.8806,
|
|
"mean_token_accuracy": 0.1452178031206131,
|
|
"num_tokens": 5722907.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.933816623687744,
|
|
"epoch": 0.2608695652173913,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996472077855166,
|
|
"loss": 5.9337,
|
|
"mean_token_accuracy": 0.14104732349514962,
|
|
"num_tokens": 5731589.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.977402830123902,
|
|
"epoch": 0.2612896450325562,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00049964552946501,
|
|
"loss": 5.9115,
|
|
"mean_token_accuracy": 0.13637820407748222,
|
|
"num_tokens": 5739922.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.934371995925903,
|
|
"epoch": 0.2617097248477211,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996438471650235,
|
|
"loss": 5.8288,
|
|
"mean_token_accuracy": 0.14435512721538543,
|
|
"num_tokens": 5749206.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.976166868209839,
|
|
"epoch": 0.26212980466288593,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004996421608855869,
|
|
"loss": 5.8863,
|
|
"mean_token_accuracy": 0.142840925604105,
|
|
"num_tokens": 5758803.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.948814392089844,
|
|
"epoch": 0.26254988447805083,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996404706267301,
|
|
"loss": 5.984,
|
|
"mean_token_accuracy": 0.13239931613206862,
|
|
"num_tokens": 5768368.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.966429710388184,
|
|
"epoch": 0.26296996429321573,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499638776388483,
|
|
"loss": 5.8325,
|
|
"mean_token_accuracy": 0.14922686219215392,
|
|
"num_tokens": 5776707.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.935250091552734,
|
|
"epoch": 0.26339004410838057,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004996370781708757,
|
|
"loss": 6.0176,
|
|
"mean_token_accuracy": 0.13138642013072968,
|
|
"num_tokens": 5787037.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 6.067586517333984,
|
|
"epoch": 0.26381012392354547,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004996353759739382,
|
|
"loss": 5.9517,
|
|
"mean_token_accuracy": 0.14147150069475173,
|
|
"num_tokens": 5796630.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.96584677696228,
|
|
"epoch": 0.26423020373871037,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996336697977007,
|
|
"loss": 5.9623,
|
|
"mean_token_accuracy": 0.13759462237358094,
|
|
"num_tokens": 5806402.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.93000898361206,
|
|
"epoch": 0.2646502835538752,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996319596421933,
|
|
"loss": 5.9198,
|
|
"mean_token_accuracy": 0.14076491743326186,
|
|
"num_tokens": 5815742.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.965633296966553,
|
|
"epoch": 0.2650703633690401,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996302455074466,
|
|
"loss": 5.9267,
|
|
"mean_token_accuracy": 0.13825056850910186,
|
|
"num_tokens": 5824915.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 6.006742715835571,
|
|
"epoch": 0.265490443184205,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004996285273934906,
|
|
"loss": 5.9521,
|
|
"mean_token_accuracy": 0.13590887412428856,
|
|
"num_tokens": 5834978.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 6.0410035133361815,
|
|
"epoch": 0.2659105229993699,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000499626805300356,
|
|
"loss": 6.1124,
|
|
"mean_token_accuracy": 0.13741038590669633,
|
|
"num_tokens": 5845684.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 6.130275392532349,
|
|
"epoch": 0.26633060281453474,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004996250792280732,
|
|
"loss": 5.9976,
|
|
"mean_token_accuracy": 0.1319746233522892,
|
|
"num_tokens": 5854905.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.999055051803589,
|
|
"epoch": 0.26675068262969964,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004996233491766727,
|
|
"loss": 5.9884,
|
|
"mean_token_accuracy": 0.13657371699810028,
|
|
"num_tokens": 5863654.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 6.02589430809021,
|
|
"epoch": 0.26717076244486454,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004996216151461854,
|
|
"loss": 6.0131,
|
|
"mean_token_accuracy": 0.13810913935303687,
|
|
"num_tokens": 5872442.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 6.0054370880126955,
|
|
"epoch": 0.2675908422600294,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996198771366417,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.14127852842211724,
|
|
"num_tokens": 5882372.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.776381587982177,
|
|
"epoch": 0.2680109220751943,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996181351480726,
|
|
"loss": 5.7292,
|
|
"mean_token_accuracy": 0.14581410139799117,
|
|
"num_tokens": 5891113.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.928227233886719,
|
|
"epoch": 0.2684310018903592,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996163891805089,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.14188458919525146,
|
|
"num_tokens": 5899582.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 6.024863529205322,
|
|
"epoch": 0.2688510817055241,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996146392339815,
|
|
"loss": 5.9231,
|
|
"mean_token_accuracy": 0.13705718368291855,
|
|
"num_tokens": 5908938.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.970179176330566,
|
|
"epoch": 0.2692711615206889,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004996128853085215,
|
|
"loss": 5.8847,
|
|
"mean_token_accuracy": 0.13865636065602302,
|
|
"num_tokens": 5918055.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 6.023169231414795,
|
|
"epoch": 0.2696912413358538,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004996111274041598,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.13727672547101974,
|
|
"num_tokens": 5926744.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.933250093460083,
|
|
"epoch": 0.2701113211510187,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.0004996093655209277,
|
|
"loss": 5.9569,
|
|
"mean_token_accuracy": 0.13804723769426347,
|
|
"num_tokens": 5936521.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 6.115011072158813,
|
|
"epoch": 0.27053140096618356,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004996075996588563,
|
|
"loss": 6.0278,
|
|
"mean_token_accuracy": 0.13099832609295844,
|
|
"num_tokens": 5945010.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.968009567260742,
|
|
"epoch": 0.27095148078134845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499605829817977,
|
|
"loss": 5.9283,
|
|
"mean_token_accuracy": 0.14273589625954627,
|
|
"num_tokens": 5953766.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.991914701461792,
|
|
"epoch": 0.27137156059651335,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499604055998321,
|
|
"loss": 5.854,
|
|
"mean_token_accuracy": 0.14187208637595178,
|
|
"num_tokens": 5962168.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.884540939331055,
|
|
"epoch": 0.2717916404116782,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996022781999198,
|
|
"loss": 5.8717,
|
|
"mean_token_accuracy": 0.14200249686837196,
|
|
"num_tokens": 5971627.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.9543530464172365,
|
|
"epoch": 0.2722117202268431,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499600496422805,
|
|
"loss": 5.9681,
|
|
"mean_token_accuracy": 0.13829579949378967,
|
|
"num_tokens": 5981775.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.955832004547119,
|
|
"epoch": 0.272631800042008,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499598710667008,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.13946632146835328,
|
|
"num_tokens": 5991097.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.936240339279175,
|
|
"epoch": 0.2730518798571729,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995969209325604,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.13132257238030434,
|
|
"num_tokens": 5999517.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.978598117828369,
|
|
"epoch": 0.2734719596723377,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995951272194941,
|
|
"loss": 5.9235,
|
|
"mean_token_accuracy": 0.13358060643076897,
|
|
"num_tokens": 6008545.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 6.072739219665527,
|
|
"epoch": 0.2738920394875026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995933295278407,
|
|
"loss": 5.9109,
|
|
"mean_token_accuracy": 0.1385839842259884,
|
|
"num_tokens": 6017366.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.855804061889648,
|
|
"epoch": 0.2743121193026675,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995915278576321,
|
|
"loss": 5.8665,
|
|
"mean_token_accuracy": 0.14388442635536194,
|
|
"num_tokens": 6025597.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 6.032962656021118,
|
|
"epoch": 0.27473219911783237,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004995897222089004,
|
|
"loss": 5.9639,
|
|
"mean_token_accuracy": 0.14044651240110398,
|
|
"num_tokens": 6034239.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 6.106841373443603,
|
|
"epoch": 0.27515227893299726,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995879125816772,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.13598284870386124,
|
|
"num_tokens": 6043837.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.915260076522827,
|
|
"epoch": 0.27557235874816216,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995860989759949,
|
|
"loss": 5.941,
|
|
"mean_token_accuracy": 0.14384470880031586,
|
|
"num_tokens": 6053217.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 6.076294040679931,
|
|
"epoch": 0.27599243856332706,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995842813918855,
|
|
"loss": 5.9613,
|
|
"mean_token_accuracy": 0.13819462284445763,
|
|
"num_tokens": 6061553.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.935478210449219,
|
|
"epoch": 0.2764125183784919,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995824598293812,
|
|
"loss": 5.8427,
|
|
"mean_token_accuracy": 0.14168552458286285,
|
|
"num_tokens": 6070080.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 6.007778882980347,
|
|
"epoch": 0.2768325981936568,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995806342885142,
|
|
"loss": 5.9809,
|
|
"mean_token_accuracy": 0.14499464854598046,
|
|
"num_tokens": 6078438.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 6.007369041442871,
|
|
"epoch": 0.2772526780088217,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499578804769317,
|
|
"loss": 5.9557,
|
|
"mean_token_accuracy": 0.1349240206182003,
|
|
"num_tokens": 6087794.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.998343896865845,
|
|
"epoch": 0.27767275782398654,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004995769712718218,
|
|
"loss": 5.9682,
|
|
"mean_token_accuracy": 0.13966120928525924,
|
|
"num_tokens": 6096709.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.972318410873413,
|
|
"epoch": 0.27809283763915144,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995751337960613,
|
|
"loss": 5.8993,
|
|
"mean_token_accuracy": 0.1387478418648243,
|
|
"num_tokens": 6105866.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.972552490234375,
|
|
"epoch": 0.27851291745431633,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995732923420679,
|
|
"loss": 5.8559,
|
|
"mean_token_accuracy": 0.14280831515789033,
|
|
"num_tokens": 6114882.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.830796527862549,
|
|
"epoch": 0.2789329972694812,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995714469098743,
|
|
"loss": 5.8455,
|
|
"mean_token_accuracy": 0.13632447943091391,
|
|
"num_tokens": 6123978.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.958771753311157,
|
|
"epoch": 0.2793530770846461,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499569597499513,
|
|
"loss": 5.9729,
|
|
"mean_token_accuracy": 0.13917672261595726,
|
|
"num_tokens": 6133246.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.980595827102661,
|
|
"epoch": 0.27977315689981097,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004995677441110172,
|
|
"loss": 5.8311,
|
|
"mean_token_accuracy": 0.14128057211637496,
|
|
"num_tokens": 6142865.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.997343969345093,
|
|
"epoch": 0.28019323671497587,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995658867444192,
|
|
"loss": 5.9328,
|
|
"mean_token_accuracy": 0.1337972767651081,
|
|
"num_tokens": 6152492.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.931694602966308,
|
|
"epoch": 0.2806133165301407,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995640253997523,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.13617469519376754,
|
|
"num_tokens": 6161953.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.863255500793457,
|
|
"epoch": 0.2810333963453056,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004995621600770492,
|
|
"loss": 5.7754,
|
|
"mean_token_accuracy": 0.14608248248696326,
|
|
"num_tokens": 6171467.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.920885229110718,
|
|
"epoch": 0.2814534761604705,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004995602907763431,
|
|
"loss": 5.8645,
|
|
"mean_token_accuracy": 0.13830695673823357,
|
|
"num_tokens": 6180646.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.936646366119385,
|
|
"epoch": 0.28187355597563535,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004995584174976672,
|
|
"loss": 5.8904,
|
|
"mean_token_accuracy": 0.13721169158816338,
|
|
"num_tokens": 6189832.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.9191412925720215,
|
|
"epoch": 0.28229363579080025,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995565402410544,
|
|
"loss": 5.7818,
|
|
"mean_token_accuracy": 0.148978391289711,
|
|
"num_tokens": 6198339.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.912237596511841,
|
|
"epoch": 0.28271371560596514,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004995546590065383,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.1437646083533764,
|
|
"num_tokens": 6207564.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.889131784439087,
|
|
"epoch": 0.28313379542113004,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995527737941518,
|
|
"loss": 5.9398,
|
|
"mean_token_accuracy": 0.13947484493255616,
|
|
"num_tokens": 6216056.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.946989393234253,
|
|
"epoch": 0.2835538752362949,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004995508846039287,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.14209089279174805,
|
|
"num_tokens": 6225573.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 6.02515664100647,
|
|
"epoch": 0.2839739550514598,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004995489914359023,
|
|
"loss": 6.0174,
|
|
"mean_token_accuracy": 0.1341426320374012,
|
|
"num_tokens": 6235057.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 6.066995286941529,
|
|
"epoch": 0.2843940348666247,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995470942901061,
|
|
"loss": 5.9375,
|
|
"mean_token_accuracy": 0.13986450731754302,
|
|
"num_tokens": 6244164.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.99746265411377,
|
|
"epoch": 0.2848141146817895,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995451931665738,
|
|
"loss": 5.9431,
|
|
"mean_token_accuracy": 0.1334978774189949,
|
|
"num_tokens": 6253095.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.890120506286621,
|
|
"epoch": 0.2852341944969544,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499543288065339,
|
|
"loss": 5.8901,
|
|
"mean_token_accuracy": 0.1397278554737568,
|
|
"num_tokens": 6261134.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.932734107971191,
|
|
"epoch": 0.2856542743121193,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004995413789864354,
|
|
"loss": 5.8767,
|
|
"mean_token_accuracy": 0.14287681505084038,
|
|
"num_tokens": 6270384.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.902149295806884,
|
|
"epoch": 0.28607435412728416,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004995394659298971,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14894422441720961,
|
|
"num_tokens": 6279702.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.952029037475586,
|
|
"epoch": 0.28649443394244906,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995375488957576,
|
|
"loss": 5.8642,
|
|
"mean_token_accuracy": 0.14061814397573472,
|
|
"num_tokens": 6288297.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.962431287765503,
|
|
"epoch": 0.28691451375761395,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499535627884051,
|
|
"loss": 5.9584,
|
|
"mean_token_accuracy": 0.13575505912303926,
|
|
"num_tokens": 6297288.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 6.059740591049194,
|
|
"epoch": 0.28733459357277885,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004995337028948115,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.1375635452568531,
|
|
"num_tokens": 6306719.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.898637819290161,
|
|
"epoch": 0.2877546733879437,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995317739280731,
|
|
"loss": 5.8103,
|
|
"mean_token_accuracy": 0.14930489808320999,
|
|
"num_tokens": 6316639.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.959413146972656,
|
|
"epoch": 0.2881747532031086,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004995298409838699,
|
|
"loss": 5.9312,
|
|
"mean_token_accuracy": 0.14022086784243584,
|
|
"num_tokens": 6326879.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.916826486587524,
|
|
"epoch": 0.2885948330182735,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.000499527904062236,
|
|
"loss": 5.8308,
|
|
"mean_token_accuracy": 0.14133042842149734,
|
|
"num_tokens": 6335729.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.9654303073883055,
|
|
"epoch": 0.28901491283343833,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004995259631632061,
|
|
"loss": 5.9046,
|
|
"mean_token_accuracy": 0.13657819852232933,
|
|
"num_tokens": 6345154.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.953763580322265,
|
|
"epoch": 0.28943499264860323,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004995240182868143,
|
|
"loss": 5.8628,
|
|
"mean_token_accuracy": 0.1393618740141392,
|
|
"num_tokens": 6354309.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.8329935550689695,
|
|
"epoch": 0.2898550724637681,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004995220694330951,
|
|
"loss": 5.8319,
|
|
"mean_token_accuracy": 0.1423378512263298,
|
|
"num_tokens": 6363389.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.91787896156311,
|
|
"epoch": 0.290275152278933,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004995201166020832,
|
|
"loss": 5.8932,
|
|
"mean_token_accuracy": 0.13977494835853577,
|
|
"num_tokens": 6372475.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 6.0139179706573485,
|
|
"epoch": 0.29069523209409787,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499518159793813,
|
|
"loss": 5.8548,
|
|
"mean_token_accuracy": 0.13958276361227034,
|
|
"num_tokens": 6380906.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.906954050064087,
|
|
"epoch": 0.29111531190926276,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000499516199008319,
|
|
"loss": 5.8626,
|
|
"mean_token_accuracy": 0.1415554866194725,
|
|
"num_tokens": 6390085.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.950432682037354,
|
|
"epoch": 0.29153539172442766,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995142342456364,
|
|
"loss": 5.9291,
|
|
"mean_token_accuracy": 0.1387101523578167,
|
|
"num_tokens": 6399441.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 6.014185523986816,
|
|
"epoch": 0.2919554715395925,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004995122655057997,
|
|
"loss": 5.9967,
|
|
"mean_token_accuracy": 0.1390436626970768,
|
|
"num_tokens": 6408995.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.861843252182007,
|
|
"epoch": 0.2923755513547574,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995102927888437,
|
|
"loss": 5.7559,
|
|
"mean_token_accuracy": 0.15259871631860733,
|
|
"num_tokens": 6418080.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.965292978286743,
|
|
"epoch": 0.2927956311699223,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004995083160948036,
|
|
"loss": 5.9191,
|
|
"mean_token_accuracy": 0.13854052796959876,
|
|
"num_tokens": 6426732.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.914570665359497,
|
|
"epoch": 0.29321571098508714,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004995063354237141,
|
|
"loss": 5.9308,
|
|
"mean_token_accuracy": 0.14200378581881523,
|
|
"num_tokens": 6435957.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.950191402435303,
|
|
"epoch": 0.29363579080025204,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004995043507756107,
|
|
"loss": 5.879,
|
|
"mean_token_accuracy": 0.138716172426939,
|
|
"num_tokens": 6445642.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.972989511489868,
|
|
"epoch": 0.29405587061541694,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995023621505282,
|
|
"loss": 5.9175,
|
|
"mean_token_accuracy": 0.13968884497880935,
|
|
"num_tokens": 6454664.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.872178792953491,
|
|
"epoch": 0.29447595043058183,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499500369548502,
|
|
"loss": 5.8333,
|
|
"mean_token_accuracy": 0.1440023772418499,
|
|
"num_tokens": 6463224.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 6.124553251266479,
|
|
"epoch": 0.2948960302457467,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004994983729695674,
|
|
"loss": 6.0621,
|
|
"mean_token_accuracy": 0.13571332320570945,
|
|
"num_tokens": 6473112.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.9443089962005615,
|
|
"epoch": 0.2953161100609116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994963724137595,
|
|
"loss": 5.902,
|
|
"mean_token_accuracy": 0.14207390323281288,
|
|
"num_tokens": 6482062.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.893982458114624,
|
|
"epoch": 0.29573618987607647,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994943678811142,
|
|
"loss": 5.8777,
|
|
"mean_token_accuracy": 0.1399894528090954,
|
|
"num_tokens": 6490568.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.980154275894165,
|
|
"epoch": 0.2961562696912413,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994923593716667,
|
|
"loss": 5.9442,
|
|
"mean_token_accuracy": 0.14206611216068268,
|
|
"num_tokens": 6500815.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.961334371566773,
|
|
"epoch": 0.2965763495064062,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994903468854527,
|
|
"loss": 5.8139,
|
|
"mean_token_accuracy": 0.1528165690600872,
|
|
"num_tokens": 6509529.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.880562591552734,
|
|
"epoch": 0.2969964293215711,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994883304225077,
|
|
"loss": 5.8963,
|
|
"mean_token_accuracy": 0.1385498009622097,
|
|
"num_tokens": 6517934.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.994669198989868,
|
|
"epoch": 0.297416509136736,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004994863099828675,
|
|
"loss": 5.8493,
|
|
"mean_token_accuracy": 0.1401224449276924,
|
|
"num_tokens": 6526098.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.8993443012237545,
|
|
"epoch": 0.29783658895190085,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000499484285566568,
|
|
"loss": 5.8767,
|
|
"mean_token_accuracy": 0.13881718441843988,
|
|
"num_tokens": 6535831.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.915220880508423,
|
|
"epoch": 0.29825666876706575,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994822571736449,
|
|
"loss": 5.797,
|
|
"mean_token_accuracy": 0.13917236104607583,
|
|
"num_tokens": 6545704.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.904978036880493,
|
|
"epoch": 0.29867674858223064,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994802248041342,
|
|
"loss": 5.8276,
|
|
"mean_token_accuracy": 0.1413833126425743,
|
|
"num_tokens": 6554423.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.953101110458374,
|
|
"epoch": 0.2990968283973955,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499478188458072,
|
|
"loss": 5.8845,
|
|
"mean_token_accuracy": 0.14304101467132568,
|
|
"num_tokens": 6563989.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.932208251953125,
|
|
"epoch": 0.2995169082125604,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004994761481354943,
|
|
"loss": 6.0148,
|
|
"mean_token_accuracy": 0.13859598264098166,
|
|
"num_tokens": 6572745.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 6.1440201759338375,
|
|
"epoch": 0.2999369880277253,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994741038364371,
|
|
"loss": 6.0089,
|
|
"mean_token_accuracy": 0.136870276927948,
|
|
"num_tokens": 6581723.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.866305208206176,
|
|
"epoch": 0.3003570678428901,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994720555609369,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.14511004835367203,
|
|
"num_tokens": 6590342.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.784994506835938,
|
|
"epoch": 0.300777147658055,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004994700033090297,
|
|
"loss": 5.7982,
|
|
"mean_token_accuracy": 0.1514626145362854,
|
|
"num_tokens": 6599206.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 6.044550800323487,
|
|
"epoch": 0.3011972274732199,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000499467947080752,
|
|
"loss": 6.1055,
|
|
"mean_token_accuracy": 0.13087693974375725,
|
|
"num_tokens": 6608947.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.973358917236328,
|
|
"epoch": 0.3016173072883848,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994658868761402,
|
|
"loss": 5.8986,
|
|
"mean_token_accuracy": 0.14760937988758088,
|
|
"num_tokens": 6618378.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 6.014848804473877,
|
|
"epoch": 0.30203738710354966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994638226952307,
|
|
"loss": 5.9391,
|
|
"mean_token_accuracy": 0.13312117457389833,
|
|
"num_tokens": 6627527.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 6.01325945854187,
|
|
"epoch": 0.30245746691871456,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994617545380604,
|
|
"loss": 5.8769,
|
|
"mean_token_accuracy": 0.14055330455303192,
|
|
"num_tokens": 6636964.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.821473407745361,
|
|
"epoch": 0.30287754673387945,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004994596824046656,
|
|
"loss": 5.8354,
|
|
"mean_token_accuracy": 0.14282228872179986,
|
|
"num_tokens": 6646074.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.973945283889771,
|
|
"epoch": 0.3032976265490443,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000499457606295083,
|
|
"loss": 5.9055,
|
|
"mean_token_accuracy": 0.13781704679131507,
|
|
"num_tokens": 6655027.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.746331119537354,
|
|
"epoch": 0.3037177063642092,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994555262093495,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.15337992906570436,
|
|
"num_tokens": 6663747.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 6.0847930908203125,
|
|
"epoch": 0.3041377861793741,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000499453442147502,
|
|
"loss": 6.0169,
|
|
"mean_token_accuracy": 0.1323746047914028,
|
|
"num_tokens": 6672922.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.927127981185913,
|
|
"epoch": 0.304557865994539,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004994513541095773,
|
|
"loss": 5.8436,
|
|
"mean_token_accuracy": 0.1500074289739132,
|
|
"num_tokens": 6682233.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.871771383285522,
|
|
"epoch": 0.30497794580970383,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994492620956126,
|
|
"loss": 5.8909,
|
|
"mean_token_accuracy": 0.14380869269371033,
|
|
"num_tokens": 6691593.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.89651346206665,
|
|
"epoch": 0.30539802562486873,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994471661056445,
|
|
"loss": 5.8834,
|
|
"mean_token_accuracy": 0.14558402746915816,
|
|
"num_tokens": 6701318.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 6.059045791625977,
|
|
"epoch": 0.3058181054400336,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994450661397106,
|
|
"loss": 5.8977,
|
|
"mean_token_accuracy": 0.14569492712616922,
|
|
"num_tokens": 6710059.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 6.073701477050781,
|
|
"epoch": 0.30623818525519847,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000499442962197848,
|
|
"loss": 5.9894,
|
|
"mean_token_accuracy": 0.1346615768969059,
|
|
"num_tokens": 6719811.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.866523504257202,
|
|
"epoch": 0.30665826507036337,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004994408542800937,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.14546327590942382,
|
|
"num_tokens": 6728789.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.874834203720093,
|
|
"epoch": 0.30707834488552826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994387423864855,
|
|
"loss": 5.8507,
|
|
"mean_token_accuracy": 0.13754900097846984,
|
|
"num_tokens": 6737706.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.860865497589112,
|
|
"epoch": 0.3074984247006931,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994366265170603,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.15615564733743667,
|
|
"num_tokens": 6746861.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 6.020911169052124,
|
|
"epoch": 0.307918504515858,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004994345066718558,
|
|
"loss": 6.0006,
|
|
"mean_token_accuracy": 0.1347304418683052,
|
|
"num_tokens": 6755242.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 6.019271802902222,
|
|
"epoch": 0.3083385843310229,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994323828509098,
|
|
"loss": 5.9331,
|
|
"mean_token_accuracy": 0.1355019263923168,
|
|
"num_tokens": 6764549.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.885806322097778,
|
|
"epoch": 0.3087586641461878,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004994302550542596,
|
|
"loss": 5.917,
|
|
"mean_token_accuracy": 0.1445144943892956,
|
|
"num_tokens": 6774123.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.832986640930176,
|
|
"epoch": 0.30917874396135264,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000499428123281943,
|
|
"loss": 5.6888,
|
|
"mean_token_accuracy": 0.150942887365818,
|
|
"num_tokens": 6782922.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.9098718643188475,
|
|
"epoch": 0.30959882377651754,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994259875339978,
|
|
"loss": 5.9422,
|
|
"mean_token_accuracy": 0.1405124768614769,
|
|
"num_tokens": 6792042.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 6.074847984313965,
|
|
"epoch": 0.31001890359168244,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004994238478104617,
|
|
"loss": 5.9376,
|
|
"mean_token_accuracy": 0.1440422020852566,
|
|
"num_tokens": 6800994.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.9522175788879395,
|
|
"epoch": 0.3104389834068473,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994217041113727,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.14600413292646408,
|
|
"num_tokens": 6809938.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.933554553985596,
|
|
"epoch": 0.3108590632220122,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004994195564367688,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.13622643798589706,
|
|
"num_tokens": 6820289.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.9958281993865965,
|
|
"epoch": 0.3112791430371771,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994174047866882,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.14527520388364792,
|
|
"num_tokens": 6830068.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.786840772628784,
|
|
"epoch": 0.3116992228523419,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004994152491611686,
|
|
"loss": 5.8625,
|
|
"mean_token_accuracy": 0.14006299674510955,
|
|
"num_tokens": 6838591.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.904484987258911,
|
|
"epoch": 0.3121193026675068,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994130895602485,
|
|
"loss": 5.8153,
|
|
"mean_token_accuracy": 0.14202122390270233,
|
|
"num_tokens": 6847796.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 6.0328771591186525,
|
|
"epoch": 0.3125393824826717,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000499410925983966,
|
|
"loss": 5.9232,
|
|
"mean_token_accuracy": 0.1450626164674759,
|
|
"num_tokens": 6856585.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.84233341217041,
|
|
"epoch": 0.3129594622978366,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994087584323596,
|
|
"loss": 5.8286,
|
|
"mean_token_accuracy": 0.1493520975112915,
|
|
"num_tokens": 6865757.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.8724321842193605,
|
|
"epoch": 0.31337954211300145,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004994065869054676,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.13832397535443305,
|
|
"num_tokens": 6875371.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.988558006286621,
|
|
"epoch": 0.31379962192816635,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004994044114033283,
|
|
"loss": 5.9369,
|
|
"mean_token_accuracy": 0.1350552909076214,
|
|
"num_tokens": 6884050.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.992891883850097,
|
|
"epoch": 0.31421970174333125,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004994022319259806,
|
|
"loss": 5.889,
|
|
"mean_token_accuracy": 0.14552320092916488,
|
|
"num_tokens": 6893079.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.952337551116943,
|
|
"epoch": 0.3146397815584961,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004994000484734629,
|
|
"loss": 5.995,
|
|
"mean_token_accuracy": 0.14312526509165763,
|
|
"num_tokens": 6903100.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.9438494682312015,
|
|
"epoch": 0.315059861373661,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993978610458137,
|
|
"loss": 5.8256,
|
|
"mean_token_accuracy": 0.14954894483089448,
|
|
"num_tokens": 6912164.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.8575239181518555,
|
|
"epoch": 0.3154799411888259,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993956696430721,
|
|
"loss": 5.8486,
|
|
"mean_token_accuracy": 0.14094497933983802,
|
|
"num_tokens": 6921183.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 6.00494794845581,
|
|
"epoch": 0.3159000210039908,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004993934742652768,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.1435340739786625,
|
|
"num_tokens": 6931325.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.935520792007447,
|
|
"epoch": 0.3163201008191556,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993912749124665,
|
|
"loss": 5.8321,
|
|
"mean_token_accuracy": 0.14375170618295668,
|
|
"num_tokens": 6940234.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.882375431060791,
|
|
"epoch": 0.3167401806343205,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993890715846804,
|
|
"loss": 5.9072,
|
|
"mean_token_accuracy": 0.14548940509557723,
|
|
"num_tokens": 6949067.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.975930404663086,
|
|
"epoch": 0.3171602604494854,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993868642819574,
|
|
"loss": 5.8933,
|
|
"mean_token_accuracy": 0.14246345758438111,
|
|
"num_tokens": 6959085.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.952158069610595,
|
|
"epoch": 0.31758034026465026,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993846530043367,
|
|
"loss": 5.9278,
|
|
"mean_token_accuracy": 0.13835494145750998,
|
|
"num_tokens": 6967392.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.894070625305176,
|
|
"epoch": 0.31800042007981516,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993824377518574,
|
|
"loss": 5.8551,
|
|
"mean_token_accuracy": 0.14527128487825394,
|
|
"num_tokens": 6976369.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.92194676399231,
|
|
"epoch": 0.31842049989498006,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993802185245587,
|
|
"loss": 5.8617,
|
|
"mean_token_accuracy": 0.14414689913392068,
|
|
"num_tokens": 6985889.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.896907377243042,
|
|
"epoch": 0.3188405797101449,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049937799532248,
|
|
"loss": 5.8865,
|
|
"mean_token_accuracy": 0.1328159935772419,
|
|
"num_tokens": 6995396.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 6.125208377838135,
|
|
"epoch": 0.3192606595253098,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993757681456607,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.1384855605661869,
|
|
"num_tokens": 7004666.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.907473802566528,
|
|
"epoch": 0.3196807393404747,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993735369941401,
|
|
"loss": 5.9629,
|
|
"mean_token_accuracy": 0.1332864873111248,
|
|
"num_tokens": 7014608.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.944202995300293,
|
|
"epoch": 0.3201008191556396,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004993713018679579,
|
|
"loss": 5.8458,
|
|
"mean_token_accuracy": 0.14125867262482644,
|
|
"num_tokens": 7023671.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.928729820251465,
|
|
"epoch": 0.32052089897080444,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004993690627671536,
|
|
"loss": 5.8973,
|
|
"mean_token_accuracy": 0.13645214289426805,
|
|
"num_tokens": 7033786.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.887518405914307,
|
|
"epoch": 0.32094097878596933,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993668196917669,
|
|
"loss": 5.8101,
|
|
"mean_token_accuracy": 0.14580376744270324,
|
|
"num_tokens": 7042162.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.971746206283569,
|
|
"epoch": 0.32136105860113423,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993645726418375,
|
|
"loss": 5.9551,
|
|
"mean_token_accuracy": 0.14017711579799652,
|
|
"num_tokens": 7051903.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.813205862045288,
|
|
"epoch": 0.3217811384162991,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004993623216174053,
|
|
"loss": 5.7747,
|
|
"mean_token_accuracy": 0.15284693986177444,
|
|
"num_tokens": 7060229.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.849071598052978,
|
|
"epoch": 0.32220121823146397,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00049936006661851,
|
|
"loss": 5.8722,
|
|
"mean_token_accuracy": 0.1437354326248169,
|
|
"num_tokens": 7069040.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.901387882232666,
|
|
"epoch": 0.32262129804662887,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004993578076451917,
|
|
"loss": 5.7592,
|
|
"mean_token_accuracy": 0.14521230906248092,
|
|
"num_tokens": 7078409.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.755710220336914,
|
|
"epoch": 0.32304137786179377,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993555446974903,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.13679178506135942,
|
|
"num_tokens": 7087983.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.907869100570679,
|
|
"epoch": 0.3234614576769586,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499353277775446,
|
|
"loss": 5.7939,
|
|
"mean_token_accuracy": 0.14731610864400863,
|
|
"num_tokens": 7097277.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.8764000415802,
|
|
"epoch": 0.3238815374921235,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004993510068790989,
|
|
"loss": 5.7001,
|
|
"mean_token_accuracy": 0.1560800179839134,
|
|
"num_tokens": 7105918.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.7582238674163815,
|
|
"epoch": 0.3243016173072884,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993487320084892,
|
|
"loss": 5.7782,
|
|
"mean_token_accuracy": 0.15001367256045342,
|
|
"num_tokens": 7115049.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.903066968917846,
|
|
"epoch": 0.32472169712245325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993464531636573,
|
|
"loss": 5.8538,
|
|
"mean_token_accuracy": 0.1425308421254158,
|
|
"num_tokens": 7124862.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.880357646942139,
|
|
"epoch": 0.32514177693761814,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993441703446435,
|
|
"loss": 5.7615,
|
|
"mean_token_accuracy": 0.15210687071084977,
|
|
"num_tokens": 7133280.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.987690162658692,
|
|
"epoch": 0.32556185675278304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993418835514882,
|
|
"loss": 5.9443,
|
|
"mean_token_accuracy": 0.14041659682989122,
|
|
"num_tokens": 7142446.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.899273204803467,
|
|
"epoch": 0.3259819365679479,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004993395927842321,
|
|
"loss": 5.8526,
|
|
"mean_token_accuracy": 0.13959464728832244,
|
|
"num_tokens": 7152143.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.969484949111939,
|
|
"epoch": 0.3264020163831128,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004993372980429155,
|
|
"loss": 5.9318,
|
|
"mean_token_accuracy": 0.13812349438667298,
|
|
"num_tokens": 7162046.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.943978548049927,
|
|
"epoch": 0.3268220961982777,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004993349993275792,
|
|
"loss": 5.8136,
|
|
"mean_token_accuracy": 0.14231757447123528,
|
|
"num_tokens": 7171557.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.693315172195435,
|
|
"epoch": 0.3272421760134426,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004993326966382639,
|
|
"loss": 5.72,
|
|
"mean_token_accuracy": 0.14861621260643004,
|
|
"num_tokens": 7180927.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.866424655914306,
|
|
"epoch": 0.3276622558286074,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004993303899750104,
|
|
"loss": 5.7842,
|
|
"mean_token_accuracy": 0.14696542471647261,
|
|
"num_tokens": 7189552.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.99456205368042,
|
|
"epoch": 0.3280823356437723,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993280793378595,
|
|
"loss": 5.8131,
|
|
"mean_token_accuracy": 0.14061524197459221,
|
|
"num_tokens": 7197857.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.852747583389283,
|
|
"epoch": 0.3285024154589372,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993257647268522,
|
|
"loss": 5.784,
|
|
"mean_token_accuracy": 0.1499074526131153,
|
|
"num_tokens": 7206785.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.897435235977173,
|
|
"epoch": 0.32892249527410206,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004993234461420295,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.14293809309601785,
|
|
"num_tokens": 7216360.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.796799039840698,
|
|
"epoch": 0.32934257508926695,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993211235834326,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.1605226844549179,
|
|
"num_tokens": 7224890.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.739530944824219,
|
|
"epoch": 0.32976265490443185,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004993187970511023,
|
|
"loss": 5.7395,
|
|
"mean_token_accuracy": 0.16714823096990586,
|
|
"num_tokens": 7234442.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.890788459777832,
|
|
"epoch": 0.33018273471959675,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993164665450801,
|
|
"loss": 5.8905,
|
|
"mean_token_accuracy": 0.14693281054496765,
|
|
"num_tokens": 7244023.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.90093765258789,
|
|
"epoch": 0.3306028145347616,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004993141320654072,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.15061969310045242,
|
|
"num_tokens": 7253548.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.896792697906494,
|
|
"epoch": 0.3310228943499265,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000499311793612125,
|
|
"loss": 5.7993,
|
|
"mean_token_accuracy": 0.14582014903426171,
|
|
"num_tokens": 7262962.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.883127927780151,
|
|
"epoch": 0.3314429741650914,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004993094511852748,
|
|
"loss": 5.8366,
|
|
"mean_token_accuracy": 0.14408671855926514,
|
|
"num_tokens": 7272234.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.896127986907959,
|
|
"epoch": 0.33186305398025623,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004993071047848983,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.14289655536413193,
|
|
"num_tokens": 7281524.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.824465751647949,
|
|
"epoch": 0.3322831337954211,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004993047544110368,
|
|
"loss": 5.7238,
|
|
"mean_token_accuracy": 0.1518530122935772,
|
|
"num_tokens": 7289601.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.694170951843262,
|
|
"epoch": 0.332703213610586,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004993024000637321,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15183946788311004,
|
|
"num_tokens": 7298508.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.792486143112183,
|
|
"epoch": 0.33312329342575087,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004993000417430259,
|
|
"loss": 5.8899,
|
|
"mean_token_accuracy": 0.14279956892132759,
|
|
"num_tokens": 7309065.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 6.024036836624146,
|
|
"epoch": 0.33354337324091576,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00049929767944896,
|
|
"loss": 5.9246,
|
|
"mean_token_accuracy": 0.14718690514564514,
|
|
"num_tokens": 7319669.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.950971412658691,
|
|
"epoch": 0.33396345305608066,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004992953131815761,
|
|
"loss": 5.8623,
|
|
"mean_token_accuracy": 0.14798057675361634,
|
|
"num_tokens": 7328425.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.795519065856934,
|
|
"epoch": 0.33438353287124556,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004992929429409164,
|
|
"loss": 5.7591,
|
|
"mean_token_accuracy": 0.15135881006717683,
|
|
"num_tokens": 7337369.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.837197399139404,
|
|
"epoch": 0.3348036126864104,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004992905687270225,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.14630376771092415,
|
|
"num_tokens": 7346829.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.964364957809448,
|
|
"epoch": 0.3352236925015753,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992881905399368,
|
|
"loss": 5.8666,
|
|
"mean_token_accuracy": 0.14199195429682732,
|
|
"num_tokens": 7355976.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.900812721252441,
|
|
"epoch": 0.3356437723167402,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992858083797013,
|
|
"loss": 5.8223,
|
|
"mean_token_accuracy": 0.1406247913837433,
|
|
"num_tokens": 7365210.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.871991872787476,
|
|
"epoch": 0.33606385213190504,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992834222463581,
|
|
"loss": 5.8811,
|
|
"mean_token_accuracy": 0.13051848039031028,
|
|
"num_tokens": 7374175.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.91477222442627,
|
|
"epoch": 0.33648393194706994,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992810321399496,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.13812239095568657,
|
|
"num_tokens": 7383302.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.950973415374756,
|
|
"epoch": 0.33690401176223483,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992786380605182,
|
|
"loss": 5.8954,
|
|
"mean_token_accuracy": 0.13927265778183937,
|
|
"num_tokens": 7392746.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.840262222290039,
|
|
"epoch": 0.33732409157739973,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992762400081062,
|
|
"loss": 5.7351,
|
|
"mean_token_accuracy": 0.1521330937743187,
|
|
"num_tokens": 7401604.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.792042589187622,
|
|
"epoch": 0.3377441713925646,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004992738379827559,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.1433362640440464,
|
|
"num_tokens": 7410594.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.919311571121216,
|
|
"epoch": 0.33816425120772947,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004992714319845101,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.15505423694849013,
|
|
"num_tokens": 7418831.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.792124700546265,
|
|
"epoch": 0.33858433102289437,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992690220134116,
|
|
"loss": 5.7874,
|
|
"mean_token_accuracy": 0.14773694202303886,
|
|
"num_tokens": 7427731.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.9903051376342775,
|
|
"epoch": 0.3390044108380592,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992666080695027,
|
|
"loss": 5.901,
|
|
"mean_token_accuracy": 0.14006555154919625,
|
|
"num_tokens": 7436447.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.859370946884155,
|
|
"epoch": 0.3394244906532241,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004992641901528262,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.14703143313527106,
|
|
"num_tokens": 7445352.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.9202173233032225,
|
|
"epoch": 0.339844570468389,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004992617682634252,
|
|
"loss": 5.8533,
|
|
"mean_token_accuracy": 0.14578376188874245,
|
|
"num_tokens": 7454298.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.925920295715332,
|
|
"epoch": 0.34026465028355385,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004992593424013424,
|
|
"loss": 5.8687,
|
|
"mean_token_accuracy": 0.14278641790151597,
|
|
"num_tokens": 7463543.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.906185626983643,
|
|
"epoch": 0.34068473009871875,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992569125666209,
|
|
"loss": 5.8916,
|
|
"mean_token_accuracy": 0.14117056503891945,
|
|
"num_tokens": 7472701.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.985479879379272,
|
|
"epoch": 0.34110480991388364,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992544787593037,
|
|
"loss": 5.877,
|
|
"mean_token_accuracy": 0.14191561043262482,
|
|
"num_tokens": 7481123.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.9610504627227785,
|
|
"epoch": 0.34152488972904854,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992520409794338,
|
|
"loss": 5.9189,
|
|
"mean_token_accuracy": 0.1452765129506588,
|
|
"num_tokens": 7490439.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.836852645874023,
|
|
"epoch": 0.3419449695442134,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992495992270544,
|
|
"loss": 5.7926,
|
|
"mean_token_accuracy": 0.14515199437737464,
|
|
"num_tokens": 7499326.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.891369199752807,
|
|
"epoch": 0.3423650493593783,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992471535022089,
|
|
"loss": 5.8635,
|
|
"mean_token_accuracy": 0.14169666543602943,
|
|
"num_tokens": 7509407.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.9069582462310795,
|
|
"epoch": 0.3427851291745432,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004992447038049405,
|
|
"loss": 5.8996,
|
|
"mean_token_accuracy": 0.14123916029930114,
|
|
"num_tokens": 7518443.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.812238025665283,
|
|
"epoch": 0.343205208989708,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992422501352927,
|
|
"loss": 5.7668,
|
|
"mean_token_accuracy": 0.15378406941890715,
|
|
"num_tokens": 7527609.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.93126916885376,
|
|
"epoch": 0.3436252888048729,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004992397924933089,
|
|
"loss": 5.8537,
|
|
"mean_token_accuracy": 0.1427117370069027,
|
|
"num_tokens": 7536890.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.9002909660339355,
|
|
"epoch": 0.3440453686200378,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992373308790325,
|
|
"loss": 5.8216,
|
|
"mean_token_accuracy": 0.14809030741453172,
|
|
"num_tokens": 7546509.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.803368282318115,
|
|
"epoch": 0.3444654484352027,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004992348652925074,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.14304676800966262,
|
|
"num_tokens": 7555336.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.942346906661987,
|
|
"epoch": 0.34488552825036756,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004992323957337771,
|
|
"loss": 5.791,
|
|
"mean_token_accuracy": 0.14322008267045022,
|
|
"num_tokens": 7565210.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.929241180419922,
|
|
"epoch": 0.34530560806553245,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004992299222028855,
|
|
"loss": 5.8774,
|
|
"mean_token_accuracy": 0.15235665440559387,
|
|
"num_tokens": 7574516.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.811958742141724,
|
|
"epoch": 0.34572568788069735,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004992274446998761,
|
|
"loss": 5.7417,
|
|
"mean_token_accuracy": 0.14640501961112024,
|
|
"num_tokens": 7583219.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.927424812316895,
|
|
"epoch": 0.3461457676958622,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004992249632247929,
|
|
"loss": 5.9848,
|
|
"mean_token_accuracy": 0.13824489042162896,
|
|
"num_tokens": 7592050.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.978273487091064,
|
|
"epoch": 0.3465658475110271,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004992224777776802,
|
|
"loss": 5.804,
|
|
"mean_token_accuracy": 0.14370897114276887,
|
|
"num_tokens": 7600718.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.832902526855468,
|
|
"epoch": 0.346985927326192,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004992199883585816,
|
|
"loss": 5.8337,
|
|
"mean_token_accuracy": 0.14620699509978294,
|
|
"num_tokens": 7609191.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.898161125183106,
|
|
"epoch": 0.34740600714135683,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004992174949675413,
|
|
"loss": 5.8663,
|
|
"mean_token_accuracy": 0.14224207326769828,
|
|
"num_tokens": 7618509.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.8946198463439945,
|
|
"epoch": 0.34782608695652173,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992149976046037,
|
|
"loss": 5.7879,
|
|
"mean_token_accuracy": 0.144022449105978,
|
|
"num_tokens": 7627851.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.815617799758911,
|
|
"epoch": 0.3482461667716866,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992124962698128,
|
|
"loss": 5.8457,
|
|
"mean_token_accuracy": 0.14384627863764762,
|
|
"num_tokens": 7636748.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.8924195766448975,
|
|
"epoch": 0.3486662465868515,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499209990963213,
|
|
"loss": 5.7665,
|
|
"mean_token_accuracy": 0.14772162735462188,
|
|
"num_tokens": 7645436.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.927510690689087,
|
|
"epoch": 0.34908632640201637,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004992074816848487,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.14214019924402238,
|
|
"num_tokens": 7655414.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.804220294952392,
|
|
"epoch": 0.34950640621718126,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992049684347642,
|
|
"loss": 5.6855,
|
|
"mean_token_accuracy": 0.1492043748497963,
|
|
"num_tokens": 7664295.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.893027591705322,
|
|
"epoch": 0.34992648603234616,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004992024512130042,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.14553705751895904,
|
|
"num_tokens": 7673295.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.80792088508606,
|
|
"epoch": 0.350346565847511,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004991999300196132,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.14397938475012778,
|
|
"num_tokens": 7682932.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.955667972564697,
|
|
"epoch": 0.3507666456626759,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004991974048546359,
|
|
"loss": 5.8403,
|
|
"mean_token_accuracy": 0.14294423833489417,
|
|
"num_tokens": 7692105.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.830784654617309,
|
|
"epoch": 0.3511867254778408,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000499194875718117,
|
|
"loss": 5.8283,
|
|
"mean_token_accuracy": 0.1480561077594757,
|
|
"num_tokens": 7701294.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.911309385299683,
|
|
"epoch": 0.3516068052930057,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991923426101013,
|
|
"loss": 5.8251,
|
|
"mean_token_accuracy": 0.14229920953512193,
|
|
"num_tokens": 7710964.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.952438926696777,
|
|
"epoch": 0.35202688510817054,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991898055306337,
|
|
"loss": 5.958,
|
|
"mean_token_accuracy": 0.13736522495746611,
|
|
"num_tokens": 7719938.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.8736350536346436,
|
|
"epoch": 0.35244696492333544,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004991872644797591,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.14402214288711548,
|
|
"num_tokens": 7729129.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.931869459152222,
|
|
"epoch": 0.35286704473850034,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004991847194575226,
|
|
"loss": 5.869,
|
|
"mean_token_accuracy": 0.1402227133512497,
|
|
"num_tokens": 7738506.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.974721908569336,
|
|
"epoch": 0.3532871245536652,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991821704639693,
|
|
"loss": 5.9687,
|
|
"mean_token_accuracy": 0.14027536809444427,
|
|
"num_tokens": 7749320.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 6.00723237991333,
|
|
"epoch": 0.3537072043688301,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991796174991443,
|
|
"loss": 5.8353,
|
|
"mean_token_accuracy": 0.14073035642504692,
|
|
"num_tokens": 7758735.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.794616985321045,
|
|
"epoch": 0.354127284183995,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004991770605630927,
|
|
"loss": 5.7909,
|
|
"mean_token_accuracy": 0.14388300105929375,
|
|
"num_tokens": 7767556.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.851093196868897,
|
|
"epoch": 0.3545473639991598,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991744996558599,
|
|
"loss": 5.8025,
|
|
"mean_token_accuracy": 0.14704317823052407,
|
|
"num_tokens": 7776615.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.890424919128418,
|
|
"epoch": 0.3549674438143247,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991719347774913,
|
|
"loss": 5.8605,
|
|
"mean_token_accuracy": 0.14900021702051164,
|
|
"num_tokens": 7785288.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.859505701065063,
|
|
"epoch": 0.3553875236294896,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991693659280324,
|
|
"loss": 5.7568,
|
|
"mean_token_accuracy": 0.14839265495538712,
|
|
"num_tokens": 7794381.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.84209361076355,
|
|
"epoch": 0.3558076034446545,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991667931075284,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.14752706736326218,
|
|
"num_tokens": 7803265.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.866020679473877,
|
|
"epoch": 0.35622768325981935,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004991642163160252,
|
|
"loss": 5.8504,
|
|
"mean_token_accuracy": 0.14277284890413283,
|
|
"num_tokens": 7812445.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.960299301147461,
|
|
"epoch": 0.35664776307498425,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004991616355535684,
|
|
"loss": 5.8377,
|
|
"mean_token_accuracy": 0.14702583178877832,
|
|
"num_tokens": 7822073.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.9013489246368405,
|
|
"epoch": 0.35706784289014915,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004991590508202036,
|
|
"loss": 5.8132,
|
|
"mean_token_accuracy": 0.1407523714005947,
|
|
"num_tokens": 7831193.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.895477247238159,
|
|
"epoch": 0.357487922705314,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991564621159766,
|
|
"loss": 5.8444,
|
|
"mean_token_accuracy": 0.14087399318814278,
|
|
"num_tokens": 7840311.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.826603794097901,
|
|
"epoch": 0.3579080025204789,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991538694409334,
|
|
"loss": 5.8748,
|
|
"mean_token_accuracy": 0.13955658972263335,
|
|
"num_tokens": 7849622.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.89751443862915,
|
|
"epoch": 0.3583280823356438,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004991512727951198,
|
|
"loss": 5.8243,
|
|
"mean_token_accuracy": 0.14570727497339248,
|
|
"num_tokens": 7859494.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 6.055752372741699,
|
|
"epoch": 0.3587481621508087,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991486721785818,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1410772293806076,
|
|
"num_tokens": 7868526.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.842230558395386,
|
|
"epoch": 0.3591682419659735,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004991460675913655,
|
|
"loss": 5.7697,
|
|
"mean_token_accuracy": 0.14887222051620483,
|
|
"num_tokens": 7877631.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.889631223678589,
|
|
"epoch": 0.3595883217811384,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000499143459033517,
|
|
"loss": 5.8122,
|
|
"mean_token_accuracy": 0.15351531505584717,
|
|
"num_tokens": 7886814.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.774262809753418,
|
|
"epoch": 0.3600084015963033,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991408465050825,
|
|
"loss": 5.6496,
|
|
"mean_token_accuracy": 0.15586639940738678,
|
|
"num_tokens": 7896337.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.794591951370239,
|
|
"epoch": 0.36042848141146816,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991382300061084,
|
|
"loss": 5.9096,
|
|
"mean_token_accuracy": 0.13906644135713578,
|
|
"num_tokens": 7906071.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.954898834228516,
|
|
"epoch": 0.36084856122663306,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004991356095366409,
|
|
"loss": 5.8891,
|
|
"mean_token_accuracy": 0.14360055327415466,
|
|
"num_tokens": 7915003.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.958932161331177,
|
|
"epoch": 0.36126864104179796,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004991329850967266,
|
|
"loss": 5.7565,
|
|
"mean_token_accuracy": 0.14655721336603164,
|
|
"num_tokens": 7924408.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.7926774501800535,
|
|
"epoch": 0.3616887208569628,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991303566864118,
|
|
"loss": 5.7071,
|
|
"mean_token_accuracy": 0.15100994557142258,
|
|
"num_tokens": 7934717.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.794317770004272,
|
|
"epoch": 0.3621088006721277,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991277243057431,
|
|
"loss": 5.7798,
|
|
"mean_token_accuracy": 0.14485913664102554,
|
|
"num_tokens": 7944278.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.806375885009766,
|
|
"epoch": 0.3625288804872926,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991250879547673,
|
|
"loss": 5.789,
|
|
"mean_token_accuracy": 0.14822428524494172,
|
|
"num_tokens": 7953344.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.846715068817138,
|
|
"epoch": 0.3629489603024575,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991224476335309,
|
|
"loss": 5.8149,
|
|
"mean_token_accuracy": 0.14335916191339493,
|
|
"num_tokens": 7962869.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.923276138305664,
|
|
"epoch": 0.36336904011762233,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991198033420807,
|
|
"loss": 5.8196,
|
|
"mean_token_accuracy": 0.14247879534959793,
|
|
"num_tokens": 7971981.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.807793760299683,
|
|
"epoch": 0.36378911993278723,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004991171550804636,
|
|
"loss": 5.7905,
|
|
"mean_token_accuracy": 0.1423468828201294,
|
|
"num_tokens": 7980979.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.894701766967773,
|
|
"epoch": 0.36420919974795213,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004991145028487266,
|
|
"loss": 5.8441,
|
|
"mean_token_accuracy": 0.14491954892873765,
|
|
"num_tokens": 7989607.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.807421636581421,
|
|
"epoch": 0.36462927956311697,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991118466469165,
|
|
"loss": 5.6743,
|
|
"mean_token_accuracy": 0.14987035244703292,
|
|
"num_tokens": 7998356.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.801383352279663,
|
|
"epoch": 0.36504935937828187,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004991091864750805,
|
|
"loss": 5.7912,
|
|
"mean_token_accuracy": 0.14811926037073136,
|
|
"num_tokens": 8007596.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.899381494522094,
|
|
"epoch": 0.36546943919344677,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991065223332655,
|
|
"loss": 5.8413,
|
|
"mean_token_accuracy": 0.13843609243631363,
|
|
"num_tokens": 8016493.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.873028373718261,
|
|
"epoch": 0.36588951900861166,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991038542215191,
|
|
"loss": 5.8016,
|
|
"mean_token_accuracy": 0.1431220918893814,
|
|
"num_tokens": 8025867.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.8522546768188475,
|
|
"epoch": 0.3663095988237765,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004991011821398882,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.1501036748290062,
|
|
"num_tokens": 8036251.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.921151638031006,
|
|
"epoch": 0.3667296786389414,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990985060884202,
|
|
"loss": 5.7996,
|
|
"mean_token_accuracy": 0.14999555051326752,
|
|
"num_tokens": 8045647.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.919665145874023,
|
|
"epoch": 0.3671497584541063,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990958260671627,
|
|
"loss": 5.8552,
|
|
"mean_token_accuracy": 0.13897678777575492,
|
|
"num_tokens": 8056025.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.852178335189819,
|
|
"epoch": 0.36756983826927114,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004990931420761629,
|
|
"loss": 5.7784,
|
|
"mean_token_accuracy": 0.15142176076769828,
|
|
"num_tokens": 8065029.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.9026415824890135,
|
|
"epoch": 0.36798991808443604,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990904541154685,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.1552293211221695,
|
|
"num_tokens": 8073249.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.88547682762146,
|
|
"epoch": 0.36840999789960094,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990877621851271,
|
|
"loss": 5.881,
|
|
"mean_token_accuracy": 0.14117127507925034,
|
|
"num_tokens": 8082039.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.770593690872192,
|
|
"epoch": 0.3688300777147658,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004990850662851863,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.15070880651474,
|
|
"num_tokens": 8090011.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.923220920562744,
|
|
"epoch": 0.3692501575299307,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990823664156941,
|
|
"loss": 5.8305,
|
|
"mean_token_accuracy": 0.1554453194141388,
|
|
"num_tokens": 8099934.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.9510838985443115,
|
|
"epoch": 0.3696702373450956,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004990796625766981,
|
|
"loss": 5.8418,
|
|
"mean_token_accuracy": 0.14417348951101303,
|
|
"num_tokens": 8108969.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.8232039451599125,
|
|
"epoch": 0.3700903171602605,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990769547682462,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.1469231814146042,
|
|
"num_tokens": 8117372.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.944585466384888,
|
|
"epoch": 0.3705103969754253,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004990742429903866,
|
|
"loss": 5.96,
|
|
"mean_token_accuracy": 0.1372426740825176,
|
|
"num_tokens": 8127108.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 6.011254787445068,
|
|
"epoch": 0.3709304767905902,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000499071527243167,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.1404549315571785,
|
|
"num_tokens": 8137392.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.8784748077392575,
|
|
"epoch": 0.3713505566057551,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990688075266357,
|
|
"loss": 5.7757,
|
|
"mean_token_accuracy": 0.1502571687102318,
|
|
"num_tokens": 8146257.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.852525138854981,
|
|
"epoch": 0.37177063642091995,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004990660838408409,
|
|
"loss": 5.7482,
|
|
"mean_token_accuracy": 0.1445622481405735,
|
|
"num_tokens": 8154952.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.867915201187134,
|
|
"epoch": 0.37219071623608485,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990633561858308,
|
|
"loss": 5.7956,
|
|
"mean_token_accuracy": 0.14470055550336838,
|
|
"num_tokens": 8164365.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.882321166992187,
|
|
"epoch": 0.37261079605124975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990606245616537,
|
|
"loss": 5.8081,
|
|
"mean_token_accuracy": 0.14612025395035744,
|
|
"num_tokens": 8172614.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.951104545593262,
|
|
"epoch": 0.37303087586641465,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990578889683579,
|
|
"loss": 5.8748,
|
|
"mean_token_accuracy": 0.14046685621142388,
|
|
"num_tokens": 8182445.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.873566579818726,
|
|
"epoch": 0.3734509556815795,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004990551494059921,
|
|
"loss": 5.7487,
|
|
"mean_token_accuracy": 0.14927588850259782,
|
|
"num_tokens": 8191871.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.879621505737305,
|
|
"epoch": 0.3738710354967444,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990524058746047,
|
|
"loss": 5.918,
|
|
"mean_token_accuracy": 0.1478033483028412,
|
|
"num_tokens": 8200658.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.87360520362854,
|
|
"epoch": 0.3742911153119093,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990496583742443,
|
|
"loss": 5.8291,
|
|
"mean_token_accuracy": 0.14281335473060608,
|
|
"num_tokens": 8209776.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.873605442047119,
|
|
"epoch": 0.3747111951270741,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004990469069049596,
|
|
"loss": 5.7478,
|
|
"mean_token_accuracy": 0.15005824714899063,
|
|
"num_tokens": 8219401.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.832020092010498,
|
|
"epoch": 0.375131274942239,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990441514667993,
|
|
"loss": 5.799,
|
|
"mean_token_accuracy": 0.15009642094373704,
|
|
"num_tokens": 8228762.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.921987819671631,
|
|
"epoch": 0.3755513547574039,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990413920598121,
|
|
"loss": 5.816,
|
|
"mean_token_accuracy": 0.14943203181028367,
|
|
"num_tokens": 8236612.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.8898248195648195,
|
|
"epoch": 0.37597143457256876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990386286840471,
|
|
"loss": 5.8002,
|
|
"mean_token_accuracy": 0.14471676647663118,
|
|
"num_tokens": 8245043.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.907721614837646,
|
|
"epoch": 0.37639151438773366,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990358613395532,
|
|
"loss": 5.9009,
|
|
"mean_token_accuracy": 0.14435933604836465,
|
|
"num_tokens": 8255270.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.959932088851929,
|
|
"epoch": 0.37681159420289856,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004990330900263792,
|
|
"loss": 5.8703,
|
|
"mean_token_accuracy": 0.13668696507811545,
|
|
"num_tokens": 8264761.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.932935667037964,
|
|
"epoch": 0.37723167401806346,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004990303147445745,
|
|
"loss": 5.8345,
|
|
"mean_token_accuracy": 0.14731877371668817,
|
|
"num_tokens": 8274308.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.771492147445679,
|
|
"epoch": 0.3776517538332283,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004990275354941881,
|
|
"loss": 5.7201,
|
|
"mean_token_accuracy": 0.1533718004822731,
|
|
"num_tokens": 8283323.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.900288772583008,
|
|
"epoch": 0.3780718336483932,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990247522752694,
|
|
"loss": 6.0389,
|
|
"mean_token_accuracy": 0.1318746455013752,
|
|
"num_tokens": 8293452.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.938249158859253,
|
|
"epoch": 0.3784919134635581,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004990219650878674,
|
|
"loss": 5.7189,
|
|
"mean_token_accuracy": 0.15227051973342895,
|
|
"num_tokens": 8302941.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.7787196159362795,
|
|
"epoch": 0.37891199327872294,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004990191739320318,
|
|
"loss": 5.7343,
|
|
"mean_token_accuracy": 0.14977421835064889,
|
|
"num_tokens": 8311811.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.729694271087647,
|
|
"epoch": 0.37933207309388783,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004990163788078117,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15700877755880355,
|
|
"num_tokens": 8321130.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.794627618789673,
|
|
"epoch": 0.37975215290905273,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004990135797152569,
|
|
"loss": 5.7616,
|
|
"mean_token_accuracy": 0.14539173543453215,
|
|
"num_tokens": 8330233.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.780507516860962,
|
|
"epoch": 0.3801722327242176,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004990107766544169,
|
|
"loss": 5.74,
|
|
"mean_token_accuracy": 0.1528162345290184,
|
|
"num_tokens": 8338585.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.822282552719116,
|
|
"epoch": 0.38059231253938247,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004990079696253413,
|
|
"loss": 5.7744,
|
|
"mean_token_accuracy": 0.15210666060447692,
|
|
"num_tokens": 8346618.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.853319835662842,
|
|
"epoch": 0.38101239235454737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004990051586280799,
|
|
"loss": 5.7773,
|
|
"mean_token_accuracy": 0.14609165936708451,
|
|
"num_tokens": 8356273.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.819488286972046,
|
|
"epoch": 0.38143247216971227,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004990023436626824,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.14789900034666062,
|
|
"num_tokens": 8366668.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.977391242980957,
|
|
"epoch": 0.3818525519848771,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004989995247291988,
|
|
"loss": 5.8693,
|
|
"mean_token_accuracy": 0.14475300461053847,
|
|
"num_tokens": 8375610.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.869308757781982,
|
|
"epoch": 0.382272631800042,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989967018276789,
|
|
"loss": 5.7532,
|
|
"mean_token_accuracy": 0.1510820835828781,
|
|
"num_tokens": 8384455.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.768916749954224,
|
|
"epoch": 0.3826927116152069,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004989938749581727,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14365579262375833,
|
|
"num_tokens": 8393868.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.859430313110352,
|
|
"epoch": 0.38311279143037175,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004989910441207305,
|
|
"loss": 5.8063,
|
|
"mean_token_accuracy": 0.14428819417953492,
|
|
"num_tokens": 8402916.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.804932451248169,
|
|
"epoch": 0.38353287124553664,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989882093154023,
|
|
"loss": 5.7313,
|
|
"mean_token_accuracy": 0.1530011385679245,
|
|
"num_tokens": 8411649.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.838339900970459,
|
|
"epoch": 0.38395295106070154,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004989853705422381,
|
|
"loss": 5.8416,
|
|
"mean_token_accuracy": 0.1406970351934433,
|
|
"num_tokens": 8420393.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.8445580959320065,
|
|
"epoch": 0.38437303087586644,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989825278012886,
|
|
"loss": 5.7338,
|
|
"mean_token_accuracy": 0.14734147042036055,
|
|
"num_tokens": 8429404.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.827604675292969,
|
|
"epoch": 0.3847931106910313,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498979681092604,
|
|
"loss": 5.7896,
|
|
"mean_token_accuracy": 0.1458117887377739,
|
|
"num_tokens": 8438299.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.774310302734375,
|
|
"epoch": 0.3852131905061962,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989768304162345,
|
|
"loss": 5.7287,
|
|
"mean_token_accuracy": 0.14704838395118713,
|
|
"num_tokens": 8447392.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.8903289318084715,
|
|
"epoch": 0.3856332703213611,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004989739757722308,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.1420938104391098,
|
|
"num_tokens": 8456361.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.8679603099822994,
|
|
"epoch": 0.3860533501365259,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989711171606436,
|
|
"loss": 5.7636,
|
|
"mean_token_accuracy": 0.1483553446829319,
|
|
"num_tokens": 8465548.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.890800905227661,
|
|
"epoch": 0.3864734299516908,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989682545815232,
|
|
"loss": 5.7864,
|
|
"mean_token_accuracy": 0.14626673310995103,
|
|
"num_tokens": 8474454.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.799082851409912,
|
|
"epoch": 0.3868935097668557,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004989653880349207,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.14468655437231065,
|
|
"num_tokens": 8482694.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.846567821502686,
|
|
"epoch": 0.38731358958202056,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004989625175208864,
|
|
"loss": 5.809,
|
|
"mean_token_accuracy": 0.14379870519042015,
|
|
"num_tokens": 8491162.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.696895551681519,
|
|
"epoch": 0.38773366939718545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989596430394717,
|
|
"loss": 5.663,
|
|
"mean_token_accuracy": 0.1604851856827736,
|
|
"num_tokens": 8500716.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.810876178741455,
|
|
"epoch": 0.38815374921235035,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498956764590727,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.14853276833891868,
|
|
"num_tokens": 8508871.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.960144567489624,
|
|
"epoch": 0.38857382902751525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989538821747037,
|
|
"loss": 5.9266,
|
|
"mean_token_accuracy": 0.1409666955471039,
|
|
"num_tokens": 8518450.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.916182136535644,
|
|
"epoch": 0.3889939088426801,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989509957914527,
|
|
"loss": 5.8179,
|
|
"mean_token_accuracy": 0.14130397886037827,
|
|
"num_tokens": 8528238.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.778582000732422,
|
|
"epoch": 0.389413988657845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004989481054410251,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.14815662652254105,
|
|
"num_tokens": 8537587.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.860828018188476,
|
|
"epoch": 0.3898340684730099,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989452111234721,
|
|
"loss": 5.8194,
|
|
"mean_token_accuracy": 0.14564207270741464,
|
|
"num_tokens": 8547703.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.833293724060058,
|
|
"epoch": 0.39025414828817473,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000498942312838845,
|
|
"loss": 5.7527,
|
|
"mean_token_accuracy": 0.1507646232843399,
|
|
"num_tokens": 8557001.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.812011241912842,
|
|
"epoch": 0.3906742281033396,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989394105871952,
|
|
"loss": 5.6446,
|
|
"mean_token_accuracy": 0.15711887776851655,
|
|
"num_tokens": 8565638.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.877040576934815,
|
|
"epoch": 0.3910943079185045,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000498936504368574,
|
|
"loss": 5.8199,
|
|
"mean_token_accuracy": 0.14237563014030458,
|
|
"num_tokens": 8574428.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.787962818145752,
|
|
"epoch": 0.3915143877336694,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004989335941830329,
|
|
"loss": 5.7797,
|
|
"mean_token_accuracy": 0.14808216989040374,
|
|
"num_tokens": 8583157.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.842103910446167,
|
|
"epoch": 0.39193446754883426,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004989306800306236,
|
|
"loss": 5.7493,
|
|
"mean_token_accuracy": 0.1453156664967537,
|
|
"num_tokens": 8592382.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.755923700332642,
|
|
"epoch": 0.39235454736399916,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989277619113975,
|
|
"loss": 5.7158,
|
|
"mean_token_accuracy": 0.15265436917543412,
|
|
"num_tokens": 8601058.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.874063444137573,
|
|
"epoch": 0.39277462717916406,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004989248398254065,
|
|
"loss": 5.8198,
|
|
"mean_token_accuracy": 0.14102344885468482,
|
|
"num_tokens": 8609479.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.8090002059936525,
|
|
"epoch": 0.3931947069943289,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004989219137727021,
|
|
"loss": 5.7837,
|
|
"mean_token_accuracy": 0.14906230419874192,
|
|
"num_tokens": 8618860.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.830205297470092,
|
|
"epoch": 0.3936147868094938,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004989189837533365,
|
|
"loss": 5.7182,
|
|
"mean_token_accuracy": 0.14967697113752365,
|
|
"num_tokens": 8627462.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.934653282165527,
|
|
"epoch": 0.3940348666246587,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004989160497673613,
|
|
"loss": 5.9021,
|
|
"mean_token_accuracy": 0.14029332622885704,
|
|
"num_tokens": 8637569.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.910148859024048,
|
|
"epoch": 0.39445494643982354,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004989131118148286,
|
|
"loss": 5.7088,
|
|
"mean_token_accuracy": 0.1493791311979294,
|
|
"num_tokens": 8645440.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.807815074920654,
|
|
"epoch": 0.39487502625498844,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004989101698957904,
|
|
"loss": 5.8673,
|
|
"mean_token_accuracy": 0.14714024513959884,
|
|
"num_tokens": 8655077.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.876171731948853,
|
|
"epoch": 0.39529510607015333,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989072240102988,
|
|
"loss": 5.783,
|
|
"mean_token_accuracy": 0.15092868655920028,
|
|
"num_tokens": 8663126.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.894665288925171,
|
|
"epoch": 0.39571518588531823,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989042741584061,
|
|
"loss": 5.7571,
|
|
"mean_token_accuracy": 0.14441050142049788,
|
|
"num_tokens": 8672386.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.667036533355713,
|
|
"epoch": 0.3961352657004831,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004989013203401645,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.15284878835082055,
|
|
"num_tokens": 8681930.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.86320013999939,
|
|
"epoch": 0.396555345515648,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988983625556264,
|
|
"loss": 5.7663,
|
|
"mean_token_accuracy": 0.14834155216813089,
|
|
"num_tokens": 8690993.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.822726678848267,
|
|
"epoch": 0.39697542533081287,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004988954008048438,
|
|
"loss": 5.7459,
|
|
"mean_token_accuracy": 0.15125422477722167,
|
|
"num_tokens": 8699497.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.943749618530274,
|
|
"epoch": 0.3973955051459777,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988924350878697,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.1371678613126278,
|
|
"num_tokens": 8709274.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.918771076202392,
|
|
"epoch": 0.3978155849611426,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988894654047563,
|
|
"loss": 5.7983,
|
|
"mean_token_accuracy": 0.14176035523414612,
|
|
"num_tokens": 8718158.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.741904830932617,
|
|
"epoch": 0.3982356647763075,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988864917555562,
|
|
"loss": 5.6785,
|
|
"mean_token_accuracy": 0.14662874788045882,
|
|
"num_tokens": 8727459.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.864354753494263,
|
|
"epoch": 0.3986557445914724,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004988835141403224,
|
|
"loss": 5.8222,
|
|
"mean_token_accuracy": 0.15272913128137589,
|
|
"num_tokens": 8737614.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.787281656265259,
|
|
"epoch": 0.39907582440663725,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004988805325591073,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.15006959736347197,
|
|
"num_tokens": 8746799.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.795963478088379,
|
|
"epoch": 0.39949590422180214,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004988775470119639,
|
|
"loss": 5.8349,
|
|
"mean_token_accuracy": 0.14210814163088797,
|
|
"num_tokens": 8756555.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.811279678344727,
|
|
"epoch": 0.39991598403696704,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004988745574989451,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14978650212287903,
|
|
"num_tokens": 8765849.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 6.0015599727630615,
|
|
"epoch": 0.4003360638521319,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988715640201036,
|
|
"loss": 5.904,
|
|
"mean_token_accuracy": 0.14214877486228944,
|
|
"num_tokens": 8775713.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.84947829246521,
|
|
"epoch": 0.4007561436672968,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988685665754928,
|
|
"loss": 5.7345,
|
|
"mean_token_accuracy": 0.1462959110736847,
|
|
"num_tokens": 8784717.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.768613386154175,
|
|
"epoch": 0.4011762234824617,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004988655651651656,
|
|
"loss": 5.7506,
|
|
"mean_token_accuracy": 0.1455540031194687,
|
|
"num_tokens": 8794388.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.7637909889221195,
|
|
"epoch": 0.4015963032976265,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988625597891751,
|
|
"loss": 5.7701,
|
|
"mean_token_accuracy": 0.14478957056999206,
|
|
"num_tokens": 8802436.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.9429168701171875,
|
|
"epoch": 0.4020163831127914,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004988595504475746,
|
|
"loss": 5.7261,
|
|
"mean_token_accuracy": 0.14802230298519134,
|
|
"num_tokens": 8811184.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.862749767303467,
|
|
"epoch": 0.4024364629279563,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988565371404175,
|
|
"loss": 5.8073,
|
|
"mean_token_accuracy": 0.1479243002831936,
|
|
"num_tokens": 8820525.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.766486692428589,
|
|
"epoch": 0.4028565427431212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988535198677571,
|
|
"loss": 5.6627,
|
|
"mean_token_accuracy": 0.15454638600349427,
|
|
"num_tokens": 8828928.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.870850229263306,
|
|
"epoch": 0.40327662255828606,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988504986296469,
|
|
"loss": 5.8718,
|
|
"mean_token_accuracy": 0.139602579921484,
|
|
"num_tokens": 8838615.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.950463771820068,
|
|
"epoch": 0.40369670237345096,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004988474734261404,
|
|
"loss": 5.856,
|
|
"mean_token_accuracy": 0.13832745403051377,
|
|
"num_tokens": 8848709.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.906767892837524,
|
|
"epoch": 0.40411678218861585,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988444442572911,
|
|
"loss": 5.7919,
|
|
"mean_token_accuracy": 0.1422821246087551,
|
|
"num_tokens": 8858277.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.770445251464844,
|
|
"epoch": 0.4045368620037807,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988414111231528,
|
|
"loss": 5.7716,
|
|
"mean_token_accuracy": 0.1510346472263336,
|
|
"num_tokens": 8868436.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.844740867614746,
|
|
"epoch": 0.4049569418189456,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000498838374023779,
|
|
"loss": 5.7534,
|
|
"mean_token_accuracy": 0.142206509411335,
|
|
"num_tokens": 8877740.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.885952091217041,
|
|
"epoch": 0.4053770216341105,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004988353329592239,
|
|
"loss": 5.7489,
|
|
"mean_token_accuracy": 0.14901506081223487,
|
|
"num_tokens": 8887408.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.8851417064666744,
|
|
"epoch": 0.4057971014492754,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988322879295409,
|
|
"loss": 5.9079,
|
|
"mean_token_accuracy": 0.1435435011982918,
|
|
"num_tokens": 8897141.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.849951601028442,
|
|
"epoch": 0.40621718126444023,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004988292389347844,
|
|
"loss": 5.6885,
|
|
"mean_token_accuracy": 0.15934282243251802,
|
|
"num_tokens": 8905747.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.889691162109375,
|
|
"epoch": 0.40663726107960513,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498826185975008,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.14562582597136497,
|
|
"num_tokens": 8914926.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.844784164428711,
|
|
"epoch": 0.40705734089477,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988231290502662,
|
|
"loss": 5.8302,
|
|
"mean_token_accuracy": 0.1439170941710472,
|
|
"num_tokens": 8923956.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.8658223152160645,
|
|
"epoch": 0.40747742070993487,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988200681606127,
|
|
"loss": 5.7062,
|
|
"mean_token_accuracy": 0.14471790790557862,
|
|
"num_tokens": 8932654.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.820353651046753,
|
|
"epoch": 0.40789750052509977,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498817003306102,
|
|
"loss": 5.7099,
|
|
"mean_token_accuracy": 0.153290569037199,
|
|
"num_tokens": 8941716.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.757675075531006,
|
|
"epoch": 0.40831758034026466,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004988139344867884,
|
|
"loss": 5.7752,
|
|
"mean_token_accuracy": 0.14610066637396812,
|
|
"num_tokens": 8950377.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.777942085266114,
|
|
"epoch": 0.4087376601554295,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004988108617027261,
|
|
"loss": 5.7374,
|
|
"mean_token_accuracy": 0.14812174588441848,
|
|
"num_tokens": 8959857.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.746048545837402,
|
|
"epoch": 0.4091577399705944,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988077849539698,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.15261283069849013,
|
|
"num_tokens": 8968272.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.8564534187316895,
|
|
"epoch": 0.4095778197857593,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004988047042405736,
|
|
"loss": 5.7535,
|
|
"mean_token_accuracy": 0.1546842411160469,
|
|
"num_tokens": 8977445.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.9273241519927975,
|
|
"epoch": 0.4099978996009242,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004988016195625924,
|
|
"loss": 5.8238,
|
|
"mean_token_accuracy": 0.1429767683148384,
|
|
"num_tokens": 8987315.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.859557819366455,
|
|
"epoch": 0.41041797941608904,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004987985309200807,
|
|
"loss": 5.8188,
|
|
"mean_token_accuracy": 0.14291241616010666,
|
|
"num_tokens": 8998119.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.789018440246582,
|
|
"epoch": 0.41083805923125394,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987954383130934,
|
|
"loss": 5.6925,
|
|
"mean_token_accuracy": 0.15540220364928245,
|
|
"num_tokens": 9007167.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.792231464385987,
|
|
"epoch": 0.41125813904641884,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498792341741685,
|
|
"loss": 5.7706,
|
|
"mean_token_accuracy": 0.14267298579216003,
|
|
"num_tokens": 9016690.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.932197856903076,
|
|
"epoch": 0.4116782188615837,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004987892412059106,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.1477791592478752,
|
|
"num_tokens": 9026117.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.7695259094238285,
|
|
"epoch": 0.4120982986767486,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987861367058251,
|
|
"loss": 5.7227,
|
|
"mean_token_accuracy": 0.14521004483103753,
|
|
"num_tokens": 9035754.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.844812536239624,
|
|
"epoch": 0.4125183784919135,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987830282414833,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15308188572525977,
|
|
"num_tokens": 9045453.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.901562261581421,
|
|
"epoch": 0.41293845830707837,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987799158129404,
|
|
"loss": 5.8435,
|
|
"mean_token_accuracy": 0.14217550978064536,
|
|
"num_tokens": 9056045.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.7665058135986325,
|
|
"epoch": 0.4133585381222432,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004987767994202516,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.14514194130897523,
|
|
"num_tokens": 9065728.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.8297545433044435,
|
|
"epoch": 0.4137786179374081,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004987736790634719,
|
|
"loss": 5.7584,
|
|
"mean_token_accuracy": 0.14594158828258513,
|
|
"num_tokens": 9075522.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.812106466293335,
|
|
"epoch": 0.414198697752573,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004987705547426568,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.14480755999684333,
|
|
"num_tokens": 9084412.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.854213285446167,
|
|
"epoch": 0.41461877756773785,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987674264578615,
|
|
"loss": 5.795,
|
|
"mean_token_accuracy": 0.14237734973430632,
|
|
"num_tokens": 9094289.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.794469690322876,
|
|
"epoch": 0.41503885738290275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004987642942091414,
|
|
"loss": 5.715,
|
|
"mean_token_accuracy": 0.14896973520517348,
|
|
"num_tokens": 9103124.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.814328575134278,
|
|
"epoch": 0.41545893719806765,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987611579965523,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.14823724925518036,
|
|
"num_tokens": 9112794.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.825801277160645,
|
|
"epoch": 0.4158790170132325,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004987580178201492,
|
|
"loss": 5.8176,
|
|
"mean_token_accuracy": 0.15566431283950805,
|
|
"num_tokens": 9122718.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.824101305007934,
|
|
"epoch": 0.4162990968283974,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004987548736799882,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.1412522651255131,
|
|
"num_tokens": 9131855.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.840525722503662,
|
|
"epoch": 0.4167191766435623,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987517255761248,
|
|
"loss": 5.6908,
|
|
"mean_token_accuracy": 0.15148798674345015,
|
|
"num_tokens": 9141102.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.813421249389648,
|
|
"epoch": 0.4171392564587272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987485735086148,
|
|
"loss": 5.7415,
|
|
"mean_token_accuracy": 0.14812534004449845,
|
|
"num_tokens": 9150552.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.857693719863891,
|
|
"epoch": 0.417559336273892,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000498745417477514,
|
|
"loss": 5.7528,
|
|
"mean_token_accuracy": 0.14549532830715178,
|
|
"num_tokens": 9160105.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.779812955856324,
|
|
"epoch": 0.4179794160890569,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987422574828784,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.14596971422433852,
|
|
"num_tokens": 9169367.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.743670463562012,
|
|
"epoch": 0.4183994959042218,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004987390935247639,
|
|
"loss": 5.6307,
|
|
"mean_token_accuracy": 0.15040962547063827,
|
|
"num_tokens": 9177872.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.8342043399810795,
|
|
"epoch": 0.41881957571938666,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004987359256032265,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.13960791900753974,
|
|
"num_tokens": 9187879.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.849059009552002,
|
|
"epoch": 0.41923965553455156,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987327537183225,
|
|
"loss": 5.7467,
|
|
"mean_token_accuracy": 0.1469127669930458,
|
|
"num_tokens": 9198281.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.84087119102478,
|
|
"epoch": 0.41965973534971646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004987295778701078,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.1467703640460968,
|
|
"num_tokens": 9207670.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.875102853775024,
|
|
"epoch": 0.42007981516488135,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000498726398058639,
|
|
"loss": 5.7467,
|
|
"mean_token_accuracy": 0.15389208644628524,
|
|
"num_tokens": 9216995.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.806438732147217,
|
|
"epoch": 0.4204998949800462,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004987232142839723,
|
|
"loss": 5.8226,
|
|
"mean_token_accuracy": 0.14448345750570296,
|
|
"num_tokens": 9227330.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.8239421367645265,
|
|
"epoch": 0.4209199747952111,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004987200265461638,
|
|
"loss": 5.7538,
|
|
"mean_token_accuracy": 0.15376091599464417,
|
|
"num_tokens": 9236666.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.837996959686279,
|
|
"epoch": 0.421340054610376,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004987168348452705,
|
|
"loss": 5.7491,
|
|
"mean_token_accuracy": 0.14361261576414108,
|
|
"num_tokens": 9246388.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.79644136428833,
|
|
"epoch": 0.42176013442554083,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004987136391813485,
|
|
"loss": 5.7039,
|
|
"mean_token_accuracy": 0.15708659887313842,
|
|
"num_tokens": 9255239.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.7528785228729244,
|
|
"epoch": 0.42218021424070573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004987104395544547,
|
|
"loss": 5.6738,
|
|
"mean_token_accuracy": 0.14564956724643707,
|
|
"num_tokens": 9264468.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.801192283630371,
|
|
"epoch": 0.42260029405587063,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004987072359646455,
|
|
"loss": 5.7502,
|
|
"mean_token_accuracy": 0.15197303295135497,
|
|
"num_tokens": 9274140.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.8728814125061035,
|
|
"epoch": 0.42302037387103547,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987040284119778,
|
|
"loss": 5.7389,
|
|
"mean_token_accuracy": 0.14780100136995317,
|
|
"num_tokens": 9283539.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.707630681991577,
|
|
"epoch": 0.42344045368620037,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987008168965087,
|
|
"loss": 5.7434,
|
|
"mean_token_accuracy": 0.14961520582437515,
|
|
"num_tokens": 9292664.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.886917591094971,
|
|
"epoch": 0.42386053350136527,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986976014182946,
|
|
"loss": 5.8367,
|
|
"mean_token_accuracy": 0.1453338533639908,
|
|
"num_tokens": 9302814.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.905004692077637,
|
|
"epoch": 0.42428061331653016,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986943819773927,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.15036008954048158,
|
|
"num_tokens": 9312654.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.895126533508301,
|
|
"epoch": 0.424700693131695,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00049869115857386,
|
|
"loss": 5.8318,
|
|
"mean_token_accuracy": 0.14068375900387764,
|
|
"num_tokens": 9322271.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.920522689819336,
|
|
"epoch": 0.4251207729468599,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986879312077536,
|
|
"loss": 5.7907,
|
|
"mean_token_accuracy": 0.14867359772324562,
|
|
"num_tokens": 9331341.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.782687711715698,
|
|
"epoch": 0.4255408527620248,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004986846998791308,
|
|
"loss": 5.7009,
|
|
"mean_token_accuracy": 0.1479552812874317,
|
|
"num_tokens": 9339863.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.761766624450684,
|
|
"epoch": 0.42596093257718964,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986814645880485,
|
|
"loss": 5.6913,
|
|
"mean_token_accuracy": 0.1528707779943943,
|
|
"num_tokens": 9349488.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.753648185729981,
|
|
"epoch": 0.42638101239235454,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004986782253345645,
|
|
"loss": 5.7015,
|
|
"mean_token_accuracy": 0.14424998313188553,
|
|
"num_tokens": 9357977.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.822470092773438,
|
|
"epoch": 0.42680109220751944,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986749821187358,
|
|
"loss": 5.8156,
|
|
"mean_token_accuracy": 0.1453898549079895,
|
|
"num_tokens": 9367449.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.918146848678589,
|
|
"epoch": 0.42722117202268434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00049867173494062,
|
|
"loss": 5.8163,
|
|
"mean_token_accuracy": 0.14584119468927384,
|
|
"num_tokens": 9377070.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.796223783493042,
|
|
"epoch": 0.4276412518378492,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004986684838002744,
|
|
"loss": 5.6173,
|
|
"mean_token_accuracy": 0.14928414672613144,
|
|
"num_tokens": 9385881.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.753831768035889,
|
|
"epoch": 0.4280613316530141,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986652286977569,
|
|
"loss": 5.7468,
|
|
"mean_token_accuracy": 0.14418202489614487,
|
|
"num_tokens": 9395159.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.829101705551148,
|
|
"epoch": 0.428481411468179,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004986619696331252,
|
|
"loss": 5.6932,
|
|
"mean_token_accuracy": 0.14958384707570077,
|
|
"num_tokens": 9404590.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.858063268661499,
|
|
"epoch": 0.4289014912833438,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986587066064367,
|
|
"loss": 5.726,
|
|
"mean_token_accuracy": 0.15162373185157776,
|
|
"num_tokens": 9414452.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.838721084594726,
|
|
"epoch": 0.4293215710985087,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986554396177494,
|
|
"loss": 5.8629,
|
|
"mean_token_accuracy": 0.14060329645872116,
|
|
"num_tokens": 9424004.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.8798810005187985,
|
|
"epoch": 0.4297416509136736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004986521686671212,
|
|
"loss": 5.7375,
|
|
"mean_token_accuracy": 0.15874141305685044,
|
|
"num_tokens": 9433487.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.820468187332153,
|
|
"epoch": 0.43016173072883845,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00049864889375461,
|
|
"loss": 5.8045,
|
|
"mean_token_accuracy": 0.14226291850209236,
|
|
"num_tokens": 9442742.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.823851108551025,
|
|
"epoch": 0.43058181054400335,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004986456148802738,
|
|
"loss": 5.8512,
|
|
"mean_token_accuracy": 0.1478380650281906,
|
|
"num_tokens": 9452550.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.949095916748047,
|
|
"epoch": 0.43100189035916825,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986423320441707,
|
|
"loss": 5.8028,
|
|
"mean_token_accuracy": 0.1422652445733547,
|
|
"num_tokens": 9461920.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.89138822555542,
|
|
"epoch": 0.43142197017433315,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004986390452463588,
|
|
"loss": 5.7321,
|
|
"mean_token_accuracy": 0.1446138709783554,
|
|
"num_tokens": 9470817.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.692741823196411,
|
|
"epoch": 0.431842049989498,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986357544868964,
|
|
"loss": 5.6781,
|
|
"mean_token_accuracy": 0.1526497036218643,
|
|
"num_tokens": 9479936.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.840050792694091,
|
|
"epoch": 0.4322621298046629,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986324597658418,
|
|
"loss": 5.7111,
|
|
"mean_token_accuracy": 0.15329033583402635,
|
|
"num_tokens": 9489818.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.679720258712768,
|
|
"epoch": 0.4326822096198278,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986291610832533,
|
|
"loss": 5.7152,
|
|
"mean_token_accuracy": 0.14663320183753967,
|
|
"num_tokens": 9499688.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.932486724853516,
|
|
"epoch": 0.4331022894349926,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004986258584391892,
|
|
"loss": 5.7743,
|
|
"mean_token_accuracy": 0.14935381412506105,
|
|
"num_tokens": 9509581.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.936005020141602,
|
|
"epoch": 0.4335223692501575,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004986225518337084,
|
|
"loss": 5.8499,
|
|
"mean_token_accuracy": 0.1452954113483429,
|
|
"num_tokens": 9518556.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.727261352539062,
|
|
"epoch": 0.4339424490653224,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986192412668692,
|
|
"loss": 5.7533,
|
|
"mean_token_accuracy": 0.1502923622727394,
|
|
"num_tokens": 9527612.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.777105236053467,
|
|
"epoch": 0.4343625288804873,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004986159267387302,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.15689545422792434,
|
|
"num_tokens": 9535882.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.798953247070313,
|
|
"epoch": 0.43478260869565216,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004986126082493502,
|
|
"loss": 5.7425,
|
|
"mean_token_accuracy": 0.15121322870254517,
|
|
"num_tokens": 9544799.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.757265424728393,
|
|
"epoch": 0.43520268851081706,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004986092857987881,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.15490222424268724,
|
|
"num_tokens": 9553805.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.7829601764678955,
|
|
"epoch": 0.43562276832598196,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004986059593871026,
|
|
"loss": 5.6988,
|
|
"mean_token_accuracy": 0.1475805327296257,
|
|
"num_tokens": 9563493.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.794771003723144,
|
|
"epoch": 0.4360428481411468,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004986026290143527,
|
|
"loss": 5.7871,
|
|
"mean_token_accuracy": 0.1461959660053253,
|
|
"num_tokens": 9572297.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.942814207077026,
|
|
"epoch": 0.4364629279563117,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004985992946805973,
|
|
"loss": 5.8966,
|
|
"mean_token_accuracy": 0.1419041596353054,
|
|
"num_tokens": 9581967.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.875198268890381,
|
|
"epoch": 0.4368830077714766,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004985959563858955,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.149876207113266,
|
|
"num_tokens": 9590885.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.878464889526367,
|
|
"epoch": 0.43730308758664144,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004985926141303066,
|
|
"loss": 5.7457,
|
|
"mean_token_accuracy": 0.14725576043128968,
|
|
"num_tokens": 9599247.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.793534898757935,
|
|
"epoch": 0.43772316740180633,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985892679138896,
|
|
"loss": 5.6742,
|
|
"mean_token_accuracy": 0.15613210648298265,
|
|
"num_tokens": 9608296.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.832571029663086,
|
|
"epoch": 0.43814324721697123,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004985859177367038,
|
|
"loss": 5.7225,
|
|
"mean_token_accuracy": 0.1492369145154953,
|
|
"num_tokens": 9616734.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.872725296020508,
|
|
"epoch": 0.43856332703213613,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985825635988087,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.14337899088859557,
|
|
"num_tokens": 9626246.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.748163080215454,
|
|
"epoch": 0.43898340684730097,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985792055002635,
|
|
"loss": 5.662,
|
|
"mean_token_accuracy": 0.1514718361198902,
|
|
"num_tokens": 9634963.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.872535848617554,
|
|
"epoch": 0.43940348666246587,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004985758434411278,
|
|
"loss": 5.7475,
|
|
"mean_token_accuracy": 0.15245552510023117,
|
|
"num_tokens": 9643615.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.807539796829223,
|
|
"epoch": 0.43982356647763077,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004985724774214613,
|
|
"loss": 5.7091,
|
|
"mean_token_accuracy": 0.1469217024743557,
|
|
"num_tokens": 9653306.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.8017144203186035,
|
|
"epoch": 0.4402436462927956,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004985691074413233,
|
|
"loss": 5.7408,
|
|
"mean_token_accuracy": 0.1475864641368389,
|
|
"num_tokens": 9662389.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.795043849945069,
|
|
"epoch": 0.4406637261079605,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004985657335007739,
|
|
"loss": 5.7409,
|
|
"mean_token_accuracy": 0.14567713364958762,
|
|
"num_tokens": 9671183.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.813223123550415,
|
|
"epoch": 0.4410838059231254,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004985623555998725,
|
|
"loss": 5.7139,
|
|
"mean_token_accuracy": 0.15571152418851852,
|
|
"num_tokens": 9680544.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.806698322296143,
|
|
"epoch": 0.4415038857382903,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004985589737386791,
|
|
"loss": 5.7474,
|
|
"mean_token_accuracy": 0.14870114251971245,
|
|
"num_tokens": 9690137.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.791662406921387,
|
|
"epoch": 0.44192396555345514,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004985555879172535,
|
|
"loss": 5.6861,
|
|
"mean_token_accuracy": 0.15161058008670808,
|
|
"num_tokens": 9699149.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.812884378433227,
|
|
"epoch": 0.44234404536862004,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498552198135656,
|
|
"loss": 5.763,
|
|
"mean_token_accuracy": 0.15164322704076766,
|
|
"num_tokens": 9709308.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.770615005493164,
|
|
"epoch": 0.44276412518378494,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004985488043939462,
|
|
"loss": 5.7076,
|
|
"mean_token_accuracy": 0.1522655814886093,
|
|
"num_tokens": 9718462.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.8054506301879885,
|
|
"epoch": 0.4431842049989498,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985454066921846,
|
|
"loss": 5.64,
|
|
"mean_token_accuracy": 0.14959139227867127,
|
|
"num_tokens": 9727626.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.665741491317749,
|
|
"epoch": 0.4436042848141147,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004985420050304312,
|
|
"loss": 5.6701,
|
|
"mean_token_accuracy": 0.14974095672369003,
|
|
"num_tokens": 9737091.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.7471333026885985,
|
|
"epoch": 0.4440243646292796,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004985385994087462,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.14873735308647157,
|
|
"num_tokens": 9746135.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.838712120056153,
|
|
"epoch": 0.4444444444444444,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004985351898271901,
|
|
"loss": 5.6731,
|
|
"mean_token_accuracy": 0.15403366982936859,
|
|
"num_tokens": 9754549.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.828793716430664,
|
|
"epoch": 0.4448645242596093,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985317762858231,
|
|
"loss": 5.8134,
|
|
"mean_token_accuracy": 0.1410953238606453,
|
|
"num_tokens": 9764219.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.79041018486023,
|
|
"epoch": 0.4452846040747742,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000498528358784706,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.15147143453359604,
|
|
"num_tokens": 9772234.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.761803770065308,
|
|
"epoch": 0.4457046838899391,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498524937323899,
|
|
"loss": 5.7143,
|
|
"mean_token_accuracy": 0.15045253187417984,
|
|
"num_tokens": 9781417.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.912419557571411,
|
|
"epoch": 0.44612476370510395,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004985215119034628,
|
|
"loss": 5.83,
|
|
"mean_token_accuracy": 0.13866035491228104,
|
|
"num_tokens": 9791286.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.829041481018066,
|
|
"epoch": 0.44654484352026885,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985180825234582,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.14558245986700058,
|
|
"num_tokens": 9802157.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.8994176387786865,
|
|
"epoch": 0.44696492333543375,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004985146491839459,
|
|
"loss": 5.8102,
|
|
"mean_token_accuracy": 0.13574059829115867,
|
|
"num_tokens": 9812646.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.954456853866577,
|
|
"epoch": 0.4473850031505986,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004985112118849865,
|
|
"loss": 5.819,
|
|
"mean_token_accuracy": 0.14093976765871047,
|
|
"num_tokens": 9822274.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.737771701812744,
|
|
"epoch": 0.4478050829657635,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985077706266412,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.14395610615611076,
|
|
"num_tokens": 9831337.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.7339942932128904,
|
|
"epoch": 0.4482251627809284,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004985043254089708,
|
|
"loss": 5.7586,
|
|
"mean_token_accuracy": 0.1422972373664379,
|
|
"num_tokens": 9840798.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.747358274459839,
|
|
"epoch": 0.44864524259609323,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985008762320364,
|
|
"loss": 5.7263,
|
|
"mean_token_accuracy": 0.14806412309408187,
|
|
"num_tokens": 9850117.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.791873502731323,
|
|
"epoch": 0.4490653224112581,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498497423095899,
|
|
"loss": 5.6724,
|
|
"mean_token_accuracy": 0.154633791744709,
|
|
"num_tokens": 9858227.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.7806925773620605,
|
|
"epoch": 0.449485402226423,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004984939660006199,
|
|
"loss": 5.7529,
|
|
"mean_token_accuracy": 0.14604211449623108,
|
|
"num_tokens": 9867157.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.769717884063721,
|
|
"epoch": 0.4499054820415879,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004984905049462602,
|
|
"loss": 5.6816,
|
|
"mean_token_accuracy": 0.14660602807998657,
|
|
"num_tokens": 9877045.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.902087068557739,
|
|
"epoch": 0.45032556185675277,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984870399328814,
|
|
"loss": 5.8208,
|
|
"mean_token_accuracy": 0.14698289036750795,
|
|
"num_tokens": 9886637.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.751916408538818,
|
|
"epoch": 0.45074564167191766,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004984835709605446,
|
|
"loss": 5.691,
|
|
"mean_token_accuracy": 0.1520322397351265,
|
|
"num_tokens": 9895601.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.830451345443725,
|
|
"epoch": 0.45116572148708256,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984800980293116,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.14870392084121703,
|
|
"num_tokens": 9904775.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.830691766738892,
|
|
"epoch": 0.4515858013022474,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004984766211392435,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.14393762201070787,
|
|
"num_tokens": 9913795.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.805560731887818,
|
|
"epoch": 0.4520058811174123,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004984731402904024,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.15417981371283532,
|
|
"num_tokens": 9922576.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.739026212692261,
|
|
"epoch": 0.4524259609325772,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004984696554828496,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1531780928373337,
|
|
"num_tokens": 9930971.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.801077175140381,
|
|
"epoch": 0.4528460407477421,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004984661667166468,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.15592064559459687,
|
|
"num_tokens": 9939628.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.807399845123291,
|
|
"epoch": 0.45326612056290694,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984626739918561,
|
|
"loss": 5.6836,
|
|
"mean_token_accuracy": 0.15975240394473075,
|
|
"num_tokens": 9948397.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.839657735824585,
|
|
"epoch": 0.45368620037807184,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004984591773085391,
|
|
"loss": 5.7721,
|
|
"mean_token_accuracy": 0.15158986151218415,
|
|
"num_tokens": 9957683.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.840809059143067,
|
|
"epoch": 0.45410628019323673,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984556766667578,
|
|
"loss": 5.7469,
|
|
"mean_token_accuracy": 0.14915718138217926,
|
|
"num_tokens": 9966756.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.824033927917481,
|
|
"epoch": 0.4545263600084016,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984521720665743,
|
|
"loss": 5.7479,
|
|
"mean_token_accuracy": 0.14859457165002823,
|
|
"num_tokens": 9976000.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.868662643432617,
|
|
"epoch": 0.4549464398235665,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004984486635080507,
|
|
"loss": 5.7537,
|
|
"mean_token_accuracy": 0.1539094254374504,
|
|
"num_tokens": 9985509.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.7345482349395756,
|
|
"epoch": 0.45536651963873137,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984451509912489,
|
|
"loss": 5.7046,
|
|
"mean_token_accuracy": 0.1475559502840042,
|
|
"num_tokens": 9994342.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.76420407295227,
|
|
"epoch": 0.4557865994538962,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984416345162315,
|
|
"loss": 5.7417,
|
|
"mean_token_accuracy": 0.1464938871562481,
|
|
"num_tokens": 10004249.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.827924537658691,
|
|
"epoch": 0.4562066792690611,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004984381140830605,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.1514168582856655,
|
|
"num_tokens": 10012430.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.84401159286499,
|
|
"epoch": 0.456626759084226,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004984345896917984,
|
|
"loss": 5.7136,
|
|
"mean_token_accuracy": 0.14923455715179443,
|
|
"num_tokens": 10021434.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.7987868309021,
|
|
"epoch": 0.4570468388993909,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004984310613425076,
|
|
"loss": 5.7086,
|
|
"mean_token_accuracy": 0.14991628527641296,
|
|
"num_tokens": 10030473.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.8427849292755125,
|
|
"epoch": 0.45746691871455575,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004984275290352506,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.15363647043704987,
|
|
"num_tokens": 10039057.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.887651014328003,
|
|
"epoch": 0.45788699852972065,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984239927700899,
|
|
"loss": 5.7915,
|
|
"mean_token_accuracy": 0.14603089392185212,
|
|
"num_tokens": 10047998.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.905976247787476,
|
|
"epoch": 0.45830707834488554,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984204525470883,
|
|
"loss": 5.7109,
|
|
"mean_token_accuracy": 0.14362944588065146,
|
|
"num_tokens": 10057479.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.703067064285278,
|
|
"epoch": 0.4587271581600504,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004984169083663084,
|
|
"loss": 5.6963,
|
|
"mean_token_accuracy": 0.14525847285985946,
|
|
"num_tokens": 10067754.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.800664043426513,
|
|
"epoch": 0.4591472379752153,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004984133602278129,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.1455842971801758,
|
|
"num_tokens": 10076815.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.94423246383667,
|
|
"epoch": 0.4595673177903802,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000498409808131665,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.15147839486598969,
|
|
"num_tokens": 10086300.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.747309446334839,
|
|
"epoch": 0.4599873976055451,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004984062520779272,
|
|
"loss": 5.6883,
|
|
"mean_token_accuracy": 0.1561483383178711,
|
|
"num_tokens": 10095383.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.73441481590271,
|
|
"epoch": 0.4604074774207099,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984026920666628,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.15058314353227614,
|
|
"num_tokens": 10103971.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.7511381149292,
|
|
"epoch": 0.4608275572358748,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004983991280979347,
|
|
"loss": 5.6601,
|
|
"mean_token_accuracy": 0.1518106997013092,
|
|
"num_tokens": 10113028.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.799294757843017,
|
|
"epoch": 0.4612476370510397,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983955601718061,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.14627908915281296,
|
|
"num_tokens": 10121890.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.870154333114624,
|
|
"epoch": 0.46166771686620456,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983919882883401,
|
|
"loss": 5.761,
|
|
"mean_token_accuracy": 0.14976027309894563,
|
|
"num_tokens": 10131655.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.851486492156982,
|
|
"epoch": 0.46208779668136946,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004983884124476,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.1464255526661873,
|
|
"num_tokens": 10140778.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.7697046279907225,
|
|
"epoch": 0.46250787649653435,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983848326496494,
|
|
"loss": 5.8037,
|
|
"mean_token_accuracy": 0.14742077738046647,
|
|
"num_tokens": 10150229.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.8817291259765625,
|
|
"epoch": 0.4629279563116992,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983812488945513,
|
|
"loss": 5.7155,
|
|
"mean_token_accuracy": 0.1507673218846321,
|
|
"num_tokens": 10158939.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.805754947662353,
|
|
"epoch": 0.4633480361268641,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004983776611823696,
|
|
"loss": 5.7042,
|
|
"mean_token_accuracy": 0.14701770842075348,
|
|
"num_tokens": 10168383.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.7591667652130125,
|
|
"epoch": 0.463768115942029,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004983740695131676,
|
|
"loss": 5.7041,
|
|
"mean_token_accuracy": 0.15164369344711304,
|
|
"num_tokens": 10178678.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.810311889648437,
|
|
"epoch": 0.4641881957571939,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000498370473887009,
|
|
"loss": 5.7131,
|
|
"mean_token_accuracy": 0.1485781654715538,
|
|
"num_tokens": 10188964.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.844456338882447,
|
|
"epoch": 0.46460827557235873,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983668743039573,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.15294503271579743,
|
|
"num_tokens": 10198333.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.732112169265747,
|
|
"epoch": 0.46502835538752363,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983632707640766,
|
|
"loss": 5.741,
|
|
"mean_token_accuracy": 0.1478828214108944,
|
|
"num_tokens": 10207876.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.762799310684204,
|
|
"epoch": 0.4654484352026885,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004983596632674306,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.1528876930475235,
|
|
"num_tokens": 10216822.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.89079327583313,
|
|
"epoch": 0.46586851501785337,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983560518140831,
|
|
"loss": 5.8051,
|
|
"mean_token_accuracy": 0.14096633195877076,
|
|
"num_tokens": 10226887.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.8007360935211185,
|
|
"epoch": 0.46628859483301827,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004983524364040982,
|
|
"loss": 5.6429,
|
|
"mean_token_accuracy": 0.154203137755394,
|
|
"num_tokens": 10235935.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.785525369644165,
|
|
"epoch": 0.46670867464818316,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004983488170375399,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.15314862504601479,
|
|
"num_tokens": 10245590.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.682972955703735,
|
|
"epoch": 0.46712875446334806,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004983451937144723,
|
|
"loss": 5.6887,
|
|
"mean_token_accuracy": 0.14980672895908356,
|
|
"num_tokens": 10255104.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.612952136993409,
|
|
"epoch": 0.4675488342785129,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983415664349595,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.1598246991634369,
|
|
"num_tokens": 10264236.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.829507875442505,
|
|
"epoch": 0.4679689140936778,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004983379351990659,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.15338489711284636,
|
|
"num_tokens": 10273335.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.7265605449676515,
|
|
"epoch": 0.4683889939088427,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004983343000068559,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.15400451123714448,
|
|
"num_tokens": 10282206.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.658405828475952,
|
|
"epoch": 0.46880907372400754,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004983306608583937,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.16081484854221345,
|
|
"num_tokens": 10290056.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.776408720016479,
|
|
"epoch": 0.46922915353917244,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004983270177537438,
|
|
"loss": 5.6587,
|
|
"mean_token_accuracy": 0.15047800838947295,
|
|
"num_tokens": 10299726.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.769086027145386,
|
|
"epoch": 0.46964923335433734,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004983233706929708,
|
|
"loss": 5.7277,
|
|
"mean_token_accuracy": 0.14831028133630753,
|
|
"num_tokens": 10308696.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.8635729312896725,
|
|
"epoch": 0.4700693131695022,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004983197196761392,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.14269383996725082,
|
|
"num_tokens": 10317845.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.799219799041748,
|
|
"epoch": 0.4704893929846671,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004983160647033139,
|
|
"loss": 5.7013,
|
|
"mean_token_accuracy": 0.1549665093421936,
|
|
"num_tokens": 10326563.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.832771301269531,
|
|
"epoch": 0.470909472799832,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004983124057745595,
|
|
"loss": 5.6801,
|
|
"mean_token_accuracy": 0.14922733306884767,
|
|
"num_tokens": 10335931.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.690406656265258,
|
|
"epoch": 0.47132955261499687,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004983087428899408,
|
|
"loss": 5.6809,
|
|
"mean_token_accuracy": 0.14426365718245507,
|
|
"num_tokens": 10344984.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.79549012184143,
|
|
"epoch": 0.4717496324301617,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004983050760495227,
|
|
"loss": 5.709,
|
|
"mean_token_accuracy": 0.1500493675470352,
|
|
"num_tokens": 10353522.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.866241216659546,
|
|
"epoch": 0.4721697122453266,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004983014052533702,
|
|
"loss": 5.7266,
|
|
"mean_token_accuracy": 0.15051157921552658,
|
|
"num_tokens": 10363527.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.768464851379394,
|
|
"epoch": 0.4725897920604915,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004982977305015481,
|
|
"loss": 5.6488,
|
|
"mean_token_accuracy": 0.1469082362949848,
|
|
"num_tokens": 10372040.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.791842842102051,
|
|
"epoch": 0.47300987187565635,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004982940517941219,
|
|
"loss": 5.6314,
|
|
"mean_token_accuracy": 0.14977569580078126,
|
|
"num_tokens": 10381279.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.833928823471069,
|
|
"epoch": 0.47342995169082125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982903691311564,
|
|
"loss": 5.8003,
|
|
"mean_token_accuracy": 0.14435067921876907,
|
|
"num_tokens": 10390608.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.762945175170898,
|
|
"epoch": 0.47385003150598615,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982866825127172,
|
|
"loss": 5.5751,
|
|
"mean_token_accuracy": 0.15733419954776764,
|
|
"num_tokens": 10399851.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.863043403625488,
|
|
"epoch": 0.47427011132115104,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982829919388692,
|
|
"loss": 5.876,
|
|
"mean_token_accuracy": 0.14255642220377923,
|
|
"num_tokens": 10410425.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.71831259727478,
|
|
"epoch": 0.4746901911363159,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004982792974096781,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.15793368965387344,
|
|
"num_tokens": 10418783.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.846996879577636,
|
|
"epoch": 0.4751102709514808,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000498275598925209,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.1399559460580349,
|
|
"num_tokens": 10427360.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.902381563186646,
|
|
"epoch": 0.4755303507666457,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004982718964855277,
|
|
"loss": 5.7724,
|
|
"mean_token_accuracy": 0.1477045461535454,
|
|
"num_tokens": 10436613.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.831106662750244,
|
|
"epoch": 0.4759504305818105,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004982681900907,
|
|
"loss": 5.8166,
|
|
"mean_token_accuracy": 0.14889360964298248,
|
|
"num_tokens": 10445055.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.788445329666137,
|
|
"epoch": 0.4763705103969754,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498264479740791,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.15863950699567794,
|
|
"num_tokens": 10454516.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.86628303527832,
|
|
"epoch": 0.4767905902121403,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982607654358668,
|
|
"loss": 5.7552,
|
|
"mean_token_accuracy": 0.1509106144309044,
|
|
"num_tokens": 10463771.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.709434938430786,
|
|
"epoch": 0.47721067002730516,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000498257047175993,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.14843147546052932,
|
|
"num_tokens": 10473783.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.726885223388672,
|
|
"epoch": 0.47763074984247006,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982533249612357,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1500977322459221,
|
|
"num_tokens": 10483424.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.7648450374603275,
|
|
"epoch": 0.47805082965763496,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004982495987916607,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.15635181814432145,
|
|
"num_tokens": 10492536.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.7842613697052006,
|
|
"epoch": 0.47847090947279985,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004982458686673339,
|
|
"loss": 5.7034,
|
|
"mean_token_accuracy": 0.14793817102909088,
|
|
"num_tokens": 10501616.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.839844703674316,
|
|
"epoch": 0.4788909892879647,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004982421345883217,
|
|
"loss": 5.7449,
|
|
"mean_token_accuracy": 0.147707599401474,
|
|
"num_tokens": 10511190.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.733095026016235,
|
|
"epoch": 0.4793110691031296,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982383965546898,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.14984251707792282,
|
|
"num_tokens": 10520310.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.840996932983399,
|
|
"epoch": 0.4797311489182945,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982346545665048,
|
|
"loss": 5.6688,
|
|
"mean_token_accuracy": 0.1559746041893959,
|
|
"num_tokens": 10528711.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.825336980819702,
|
|
"epoch": 0.48015122873345933,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982309086238328,
|
|
"loss": 5.7566,
|
|
"mean_token_accuracy": 0.1434244692325592,
|
|
"num_tokens": 10538484.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.79931492805481,
|
|
"epoch": 0.48057130854862423,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982271587267403,
|
|
"loss": 5.7018,
|
|
"mean_token_accuracy": 0.14842950850725173,
|
|
"num_tokens": 10547623.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.766378021240234,
|
|
"epoch": 0.48099138836378913,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982234048752935,
|
|
"loss": 5.6452,
|
|
"mean_token_accuracy": 0.15442409366369247,
|
|
"num_tokens": 10556234.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.838606309890747,
|
|
"epoch": 0.481411468178954,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000498219647069559,
|
|
"loss": 5.875,
|
|
"mean_token_accuracy": 0.14210818707942963,
|
|
"num_tokens": 10566308.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.902328968048096,
|
|
"epoch": 0.48183154799411887,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004982158853096035,
|
|
"loss": 5.8085,
|
|
"mean_token_accuracy": 0.1433735728263855,
|
|
"num_tokens": 10575212.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.795661878585816,
|
|
"epoch": 0.48225162780928377,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982121195954935,
|
|
"loss": 5.5791,
|
|
"mean_token_accuracy": 0.15854463130235671,
|
|
"num_tokens": 10584590.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.72941517829895,
|
|
"epoch": 0.48267170762444866,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004982083499272957,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.15250627547502518,
|
|
"num_tokens": 10593997.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.777765226364136,
|
|
"epoch": 0.4830917874396135,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004982045763050768,
|
|
"loss": 5.7716,
|
|
"mean_token_accuracy": 0.1511766344308853,
|
|
"num_tokens": 10603299.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.8095392227172855,
|
|
"epoch": 0.4835118672547784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004982007987289041,
|
|
"loss": 5.7159,
|
|
"mean_token_accuracy": 0.150531367957592,
|
|
"num_tokens": 10613546.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.776759195327759,
|
|
"epoch": 0.4839319470699433,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981970171988439,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.1606784962117672,
|
|
"num_tokens": 10622966.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.802293014526367,
|
|
"epoch": 0.48435202688510814,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004981932317149636,
|
|
"loss": 5.7643,
|
|
"mean_token_accuracy": 0.14677036479115485,
|
|
"num_tokens": 10633441.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.871302127838135,
|
|
"epoch": 0.48477210670027304,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00049818944227733,
|
|
"loss": 5.7431,
|
|
"mean_token_accuracy": 0.14571086168289185,
|
|
"num_tokens": 10643124.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.788599300384521,
|
|
"epoch": 0.48519218651543794,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981856488860105,
|
|
"loss": 5.7115,
|
|
"mean_token_accuracy": 0.14598402380943298,
|
|
"num_tokens": 10652517.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.782949590682984,
|
|
"epoch": 0.48561226633060284,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981818515410721,
|
|
"loss": 5.7367,
|
|
"mean_token_accuracy": 0.14545634835958482,
|
|
"num_tokens": 10663352.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.821159505844117,
|
|
"epoch": 0.4860323461457677,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981780502425821,
|
|
"loss": 5.7598,
|
|
"mean_token_accuracy": 0.15368367582559586,
|
|
"num_tokens": 10672430.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.822045946121216,
|
|
"epoch": 0.4864524259609326,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004981742449906079,
|
|
"loss": 5.6982,
|
|
"mean_token_accuracy": 0.1539619520306587,
|
|
"num_tokens": 10681908.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.846343612670898,
|
|
"epoch": 0.4868725057760975,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981704357852168,
|
|
"loss": 5.7077,
|
|
"mean_token_accuracy": 0.14915080666542052,
|
|
"num_tokens": 10691259.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.720254230499267,
|
|
"epoch": 0.4872925855912623,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004981666226264764,
|
|
"loss": 5.5932,
|
|
"mean_token_accuracy": 0.14788943082094191,
|
|
"num_tokens": 10699668.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.762866544723511,
|
|
"epoch": 0.4877126654064272,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004981628055144542,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.1536644384264946,
|
|
"num_tokens": 10709146.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.773292684555054,
|
|
"epoch": 0.4881327452215921,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981589844492177,
|
|
"loss": 5.7398,
|
|
"mean_token_accuracy": 0.14368562251329423,
|
|
"num_tokens": 10718724.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.741464710235595,
|
|
"epoch": 0.488552825036757,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004981551594308349,
|
|
"loss": 5.6811,
|
|
"mean_token_accuracy": 0.1533760130405426,
|
|
"num_tokens": 10728101.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.868719911575317,
|
|
"epoch": 0.48897290485192185,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004981513304593733,
|
|
"loss": 5.7116,
|
|
"mean_token_accuracy": 0.15002420991659166,
|
|
"num_tokens": 10736750.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.850791263580322,
|
|
"epoch": 0.48939298466708675,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004981474975349006,
|
|
"loss": 5.8999,
|
|
"mean_token_accuracy": 0.14523305892944335,
|
|
"num_tokens": 10746914.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.826296806335449,
|
|
"epoch": 0.48981306448225165,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000498143660657485,
|
|
"loss": 5.735,
|
|
"mean_token_accuracy": 0.15287000834941863,
|
|
"num_tokens": 10755786.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.693120765686035,
|
|
"epoch": 0.4902331442974165,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981398198271944,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.15199866890907288,
|
|
"num_tokens": 10764821.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.775625324249267,
|
|
"epoch": 0.4906532241125814,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004981359750440968,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.14958391785621644,
|
|
"num_tokens": 10773569.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.698379755020142,
|
|
"epoch": 0.4910733039277463,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981321263082603,
|
|
"loss": 5.6703,
|
|
"mean_token_accuracy": 0.14412777721881867,
|
|
"num_tokens": 10782298.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.716889905929565,
|
|
"epoch": 0.4914933837429111,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000498128273619753,
|
|
"loss": 5.6402,
|
|
"mean_token_accuracy": 0.15635652095079422,
|
|
"num_tokens": 10792087.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.834375047683716,
|
|
"epoch": 0.491913463558076,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004981244169786433,
|
|
"loss": 5.738,
|
|
"mean_token_accuracy": 0.14734297171235083,
|
|
"num_tokens": 10801641.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.87250828742981,
|
|
"epoch": 0.4923335433732409,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004981205563849994,
|
|
"loss": 5.8138,
|
|
"mean_token_accuracy": 0.1475193165242672,
|
|
"num_tokens": 10811612.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.749148321151734,
|
|
"epoch": 0.4927536231884058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004981166918388897,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.15407940298318862,
|
|
"num_tokens": 10821608.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.674514102935791,
|
|
"epoch": 0.49317370300357066,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004981128233403828,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.15862181633710862,
|
|
"num_tokens": 10830679.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.774006509780884,
|
|
"epoch": 0.49359378281873556,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498108950889547,
|
|
"loss": 5.6646,
|
|
"mean_token_accuracy": 0.15421441048383713,
|
|
"num_tokens": 10839669.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.764991903305054,
|
|
"epoch": 0.49401386263390046,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004981050744864512,
|
|
"loss": 5.6346,
|
|
"mean_token_accuracy": 0.15262162685394287,
|
|
"num_tokens": 10849666.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.72649884223938,
|
|
"epoch": 0.4944339424490653,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004981011941311638,
|
|
"loss": 5.5555,
|
|
"mean_token_accuracy": 0.16141532510519027,
|
|
"num_tokens": 10858225.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.66461033821106,
|
|
"epoch": 0.4948540222642302,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980973098237535,
|
|
"loss": 5.6584,
|
|
"mean_token_accuracy": 0.14741952568292618,
|
|
"num_tokens": 10867466.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.8419431209564205,
|
|
"epoch": 0.4952741020793951,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980934215642894,
|
|
"loss": 5.7012,
|
|
"mean_token_accuracy": 0.15556059777736664,
|
|
"num_tokens": 10875850.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.721167850494385,
|
|
"epoch": 0.49569418189456,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00049808952935284,
|
|
"loss": 5.6463,
|
|
"mean_token_accuracy": 0.15190516263246537,
|
|
"num_tokens": 10885154.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.701448440551758,
|
|
"epoch": 0.49611426170972484,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004980856331894747,
|
|
"loss": 5.7224,
|
|
"mean_token_accuracy": 0.14825090169906616,
|
|
"num_tokens": 10894080.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.78351993560791,
|
|
"epoch": 0.49653434152488973,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004980817330742621,
|
|
"loss": 5.7187,
|
|
"mean_token_accuracy": 0.14427882730960845,
|
|
"num_tokens": 10903248.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.805410528182984,
|
|
"epoch": 0.49695442134005463,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980778290072716,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.15272436887025834,
|
|
"num_tokens": 10912939.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.77779188156128,
|
|
"epoch": 0.4973745011552195,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004980739209885722,
|
|
"loss": 5.7101,
|
|
"mean_token_accuracy": 0.15421786904335022,
|
|
"num_tokens": 10921505.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.821563053131103,
|
|
"epoch": 0.49779458097038437,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980700090182331,
|
|
"loss": 5.7852,
|
|
"mean_token_accuracy": 0.15165787041187287,
|
|
"num_tokens": 10931861.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.8428229808807375,
|
|
"epoch": 0.49821466078554927,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980660930963238,
|
|
"loss": 5.7011,
|
|
"mean_token_accuracy": 0.15149710923433304,
|
|
"num_tokens": 10940810.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.702348804473877,
|
|
"epoch": 0.4986347406007141,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980621732229133,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.15044856518507005,
|
|
"num_tokens": 10949514.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.803748416900635,
|
|
"epoch": 0.499054820415879,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980582493980714,
|
|
"loss": 5.7968,
|
|
"mean_token_accuracy": 0.14371122792363167,
|
|
"num_tokens": 10959161.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.770447301864624,
|
|
"epoch": 0.4994749002310439,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980543216218674,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.1631261572241783,
|
|
"num_tokens": 10968983.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.808981323242188,
|
|
"epoch": 0.4998949800462088,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004980503898943711,
|
|
"loss": 5.8114,
|
|
"mean_token_accuracy": 0.15061289817094803,
|
|
"num_tokens": 10978044.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.788982200622558,
|
|
"epoch": 0.5003150598613737,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004980464542156519,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15479907542467117,
|
|
"num_tokens": 10986980.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.79339451789856,
|
|
"epoch": 0.5007351396765385,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004980425145857796,
|
|
"loss": 5.6394,
|
|
"mean_token_accuracy": 0.16022832095623016,
|
|
"num_tokens": 10995163.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.68665771484375,
|
|
"epoch": 0.5011552194917034,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000498038571004824,
|
|
"loss": 5.5686,
|
|
"mean_token_accuracy": 0.1633736938238144,
|
|
"num_tokens": 11003722.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.609031295776367,
|
|
"epoch": 0.5015752993068683,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980346234728549,
|
|
"loss": 5.6442,
|
|
"mean_token_accuracy": 0.1569686323404312,
|
|
"num_tokens": 11013176.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.7894915580749515,
|
|
"epoch": 0.5019953791220332,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004980306719899424,
|
|
"loss": 5.6952,
|
|
"mean_token_accuracy": 0.151578326523304,
|
|
"num_tokens": 11022636.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.776892518997192,
|
|
"epoch": 0.5024154589371981,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980267165561564,
|
|
"loss": 5.6302,
|
|
"mean_token_accuracy": 0.15875780060887337,
|
|
"num_tokens": 11031896.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.7132336616516115,
|
|
"epoch": 0.502835538752363,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004980227571715669,
|
|
"loss": 5.7054,
|
|
"mean_token_accuracy": 0.14930393695831298,
|
|
"num_tokens": 11040802.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.726763486862183,
|
|
"epoch": 0.5032556185675279,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004980187938362441,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.14617264419794082,
|
|
"num_tokens": 11049701.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.781429719924927,
|
|
"epoch": 0.5036756983826927,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004980148265502581,
|
|
"loss": 5.8043,
|
|
"mean_token_accuracy": 0.14090105295181274,
|
|
"num_tokens": 11059555.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.852024269104004,
|
|
"epoch": 0.5040957781978576,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980108553136795,
|
|
"loss": 5.7355,
|
|
"mean_token_accuracy": 0.1523468405008316,
|
|
"num_tokens": 11068940.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 0.5040957781978576,
|
|
"eval_entropy": 5.700179389446457,
|
|
"eval_loss": 5.713378429412842,
|
|
"eval_mean_token_accuracy": 0.15722168653683422,
|
|
"eval_num_tokens": 11068940.0,
|
|
"eval_runtime": 27.4743,
|
|
"eval_samples_per_second": 1360.037,
|
|
"eval_steps_per_second": 170.014,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.850462198257446,
|
|
"epoch": 0.5045158580130225,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980068801265783,
|
|
"loss": 5.6918,
|
|
"mean_token_accuracy": 0.15200575068593025,
|
|
"num_tokens": 11079014.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.7985584259033205,
|
|
"epoch": 0.5049359378281874,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004980029009890251,
|
|
"loss": 5.7794,
|
|
"mean_token_accuracy": 0.14995476454496384,
|
|
"num_tokens": 11089526.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.745014381408692,
|
|
"epoch": 0.5053560176433523,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979989179010904,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.15582752823829651,
|
|
"num_tokens": 11099156.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.753205490112305,
|
|
"epoch": 0.5057760974585171,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004979949308628445,
|
|
"loss": 5.6531,
|
|
"mean_token_accuracy": 0.1576333686709404,
|
|
"num_tokens": 11108242.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.7076881408691404,
|
|
"epoch": 0.506196177273682,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004979909398743584,
|
|
"loss": 5.6553,
|
|
"mean_token_accuracy": 0.15808477848768235,
|
|
"num_tokens": 11118076.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.797974157333374,
|
|
"epoch": 0.5066162570888468,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004979869449357026,
|
|
"loss": 5.7275,
|
|
"mean_token_accuracy": 0.16116174012422563,
|
|
"num_tokens": 11127265.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.756021356582641,
|
|
"epoch": 0.5070363369040117,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004979829460469478,
|
|
"loss": 5.6513,
|
|
"mean_token_accuracy": 0.15123417377471923,
|
|
"num_tokens": 11136429.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.746025085449219,
|
|
"epoch": 0.5074564167191766,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004979789432081649,
|
|
"loss": 5.6536,
|
|
"mean_token_accuracy": 0.15169408172369003,
|
|
"num_tokens": 11146201.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.7764967918396,
|
|
"epoch": 0.5078764965343415,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497974936419425,
|
|
"loss": 5.6814,
|
|
"mean_token_accuracy": 0.1552870064973831,
|
|
"num_tokens": 11154867.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.697817325592041,
|
|
"epoch": 0.5082965763495064,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004979709256807989,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1530693456530571,
|
|
"num_tokens": 11164092.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.767863702774048,
|
|
"epoch": 0.5087166561646713,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979669109923575,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.15086525678634644,
|
|
"num_tokens": 11173176.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.823122596740722,
|
|
"epoch": 0.5091367359798362,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004979628923541721,
|
|
"loss": 5.7074,
|
|
"mean_token_accuracy": 0.15153964161872863,
|
|
"num_tokens": 11182397.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.847384881973267,
|
|
"epoch": 0.509556815795001,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497958869766314,
|
|
"loss": 5.736,
|
|
"mean_token_accuracy": 0.15451715439558028,
|
|
"num_tokens": 11191790.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.775505256652832,
|
|
"epoch": 0.5099768956101659,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979548432288543,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.15639978721737863,
|
|
"num_tokens": 11201104.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.7940943241119385,
|
|
"epoch": 0.5103969754253308,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979508127418643,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.156558046489954,
|
|
"num_tokens": 11209578.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.7526520729064945,
|
|
"epoch": 0.5108170552404957,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004979467783054155,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.15932658165693284,
|
|
"num_tokens": 11218380.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.653487491607666,
|
|
"epoch": 0.5112371350556606,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004979427399195793,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.15166352689266205,
|
|
"num_tokens": 11227810.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.715474700927734,
|
|
"epoch": 0.5116572148708255,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979386975844274,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.1557892754673958,
|
|
"num_tokens": 11236631.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.7959397315979,
|
|
"epoch": 0.5120772946859904,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979346513000311,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.1493688315153122,
|
|
"num_tokens": 11247418.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.743378114700318,
|
|
"epoch": 0.5124973745011552,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004979306010664623,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15673113763332366,
|
|
"num_tokens": 11256246.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.6460973739624025,
|
|
"epoch": 0.5129174543163201,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004979265468837927,
|
|
"loss": 5.6109,
|
|
"mean_token_accuracy": 0.15803674310445787,
|
|
"num_tokens": 11265980.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.7585508823394775,
|
|
"epoch": 0.513337534131485,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497922488752094,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.15313291698694229,
|
|
"num_tokens": 11276158.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.75591721534729,
|
|
"epoch": 0.5137576139466499,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004979184266714383,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.1576843872666359,
|
|
"num_tokens": 11284957.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.691437435150147,
|
|
"epoch": 0.5141776937618148,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004979143606418974,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.15532443746924401,
|
|
"num_tokens": 11294340.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.817380475997925,
|
|
"epoch": 0.5145977735769797,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004979102906635435,
|
|
"loss": 5.8399,
|
|
"mean_token_accuracy": 0.14829942509531974,
|
|
"num_tokens": 11303344.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.825004005432129,
|
|
"epoch": 0.5150178533921445,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004979062167364486,
|
|
"loss": 5.7016,
|
|
"mean_token_accuracy": 0.15979470312595367,
|
|
"num_tokens": 11311338.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.708187103271484,
|
|
"epoch": 0.5154379332073094,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004979021388606847,
|
|
"loss": 5.5348,
|
|
"mean_token_accuracy": 0.15981798246502876,
|
|
"num_tokens": 11320194.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.763344478607178,
|
|
"epoch": 0.5158580130224742,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004978980570363243,
|
|
"loss": 5.7105,
|
|
"mean_token_accuracy": 0.15382457673549652,
|
|
"num_tokens": 11329952.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.736899137496948,
|
|
"epoch": 0.5162780928376391,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004978939712634396,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.15457842200994493,
|
|
"num_tokens": 11339384.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.811904716491699,
|
|
"epoch": 0.516698172652804,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004978898815421029,
|
|
"loss": 5.8281,
|
|
"mean_token_accuracy": 0.1484919786453247,
|
|
"num_tokens": 11348409.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.865073776245117,
|
|
"epoch": 0.5171182524679689,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004978857878723867,
|
|
"loss": 5.7251,
|
|
"mean_token_accuracy": 0.15440079271793367,
|
|
"num_tokens": 11357478.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.813732147216797,
|
|
"epoch": 0.5175383322831338,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978816902543636,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.15630923956632614,
|
|
"num_tokens": 11366379.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.804885578155518,
|
|
"epoch": 0.5179584120982986,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978775886881062,
|
|
"loss": 5.7586,
|
|
"mean_token_accuracy": 0.15422743335366249,
|
|
"num_tokens": 11376357.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.754732990264893,
|
|
"epoch": 0.5183784919134635,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497873483173687,
|
|
"loss": 5.6229,
|
|
"mean_token_accuracy": 0.15853857696056367,
|
|
"num_tokens": 11384995.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.748101091384887,
|
|
"epoch": 0.5187985717286284,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004978693737111787,
|
|
"loss": 5.635,
|
|
"mean_token_accuracy": 0.1528910756111145,
|
|
"num_tokens": 11395363.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.736073970794678,
|
|
"epoch": 0.5192186515437933,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004978652603006543,
|
|
"loss": 5.628,
|
|
"mean_token_accuracy": 0.15332882851362228,
|
|
"num_tokens": 11404511.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.778553915023804,
|
|
"epoch": 0.5196387313589582,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978611429421866,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.15048506557941438,
|
|
"num_tokens": 11413400.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.794227361679077,
|
|
"epoch": 0.5200588111741231,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978570216358485,
|
|
"loss": 5.7234,
|
|
"mean_token_accuracy": 0.14682584255933762,
|
|
"num_tokens": 11423693.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.818920612335205,
|
|
"epoch": 0.520478890989288,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000497852896381713,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1458378776907921,
|
|
"num_tokens": 11433195.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.760408115386963,
|
|
"epoch": 0.5208989708044528,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004978487671798531,
|
|
"loss": 5.8299,
|
|
"mean_token_accuracy": 0.141814424097538,
|
|
"num_tokens": 11443416.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.829377174377441,
|
|
"epoch": 0.5213190506196177,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978446340303422,
|
|
"loss": 5.6827,
|
|
"mean_token_accuracy": 0.1550835467875004,
|
|
"num_tokens": 11452487.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.777486085891724,
|
|
"epoch": 0.5217391304347826,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978404969332533,
|
|
"loss": 5.6976,
|
|
"mean_token_accuracy": 0.1613258346915245,
|
|
"num_tokens": 11461893.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.6914146900177,
|
|
"epoch": 0.5221592102499475,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004978363558886597,
|
|
"loss": 5.6347,
|
|
"mean_token_accuracy": 0.14582654014229773,
|
|
"num_tokens": 11471238.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.780894374847412,
|
|
"epoch": 0.5225792900651124,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978322108966348,
|
|
"loss": 5.7322,
|
|
"mean_token_accuracy": 0.14352654069662094,
|
|
"num_tokens": 11480571.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.752029228210449,
|
|
"epoch": 0.5229993698802773,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004978280619572521,
|
|
"loss": 5.7121,
|
|
"mean_token_accuracy": 0.15060520470142363,
|
|
"num_tokens": 11489552.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.808607912063598,
|
|
"epoch": 0.5234194496954422,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497823909070585,
|
|
"loss": 5.7575,
|
|
"mean_token_accuracy": 0.14814567118883132,
|
|
"num_tokens": 11498715.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.850186061859131,
|
|
"epoch": 0.523839529510607,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978197522367071,
|
|
"loss": 5.6975,
|
|
"mean_token_accuracy": 0.1479704961180687,
|
|
"num_tokens": 11508472.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.831798458099366,
|
|
"epoch": 0.5242596093257719,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004978155914556919,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15581255853176118,
|
|
"num_tokens": 11517620.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.682782220840454,
|
|
"epoch": 0.5246796891409368,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004978114267276134,
|
|
"loss": 5.6977,
|
|
"mean_token_accuracy": 0.15499856919050217,
|
|
"num_tokens": 11526106.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.819548797607422,
|
|
"epoch": 0.5250997689561017,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004978072580525451,
|
|
"loss": 5.7264,
|
|
"mean_token_accuracy": 0.15035497546195983,
|
|
"num_tokens": 11535840.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.8192667961120605,
|
|
"epoch": 0.5255198487712666,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000497803085430561,
|
|
"loss": 5.703,
|
|
"mean_token_accuracy": 0.1543534591794014,
|
|
"num_tokens": 11545110.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.857662773132324,
|
|
"epoch": 0.5259399285864315,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004977989088617349,
|
|
"loss": 5.7236,
|
|
"mean_token_accuracy": 0.1509743146598339,
|
|
"num_tokens": 11554382.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.714362955093383,
|
|
"epoch": 0.5263600084015964,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497794728346141,
|
|
"loss": 5.5827,
|
|
"mean_token_accuracy": 0.162162946164608,
|
|
"num_tokens": 11562821.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.852323722839356,
|
|
"epoch": 0.5267800882167611,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977905438838531,
|
|
"loss": 5.8009,
|
|
"mean_token_accuracy": 0.13918681740760802,
|
|
"num_tokens": 11571705.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.715672159194947,
|
|
"epoch": 0.527200168031926,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977863554749453,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.1484605222940445,
|
|
"num_tokens": 11580692.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.748901891708374,
|
|
"epoch": 0.5276202478470909,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004977821631194922,
|
|
"loss": 5.6336,
|
|
"mean_token_accuracy": 0.14991371780633928,
|
|
"num_tokens": 11589966.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.8247438907623295,
|
|
"epoch": 0.5280403276622558,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004977779668175677,
|
|
"loss": 5.6979,
|
|
"mean_token_accuracy": 0.15071138143539428,
|
|
"num_tokens": 11599627.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.786518621444702,
|
|
"epoch": 0.5284604074774207,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977737665692461,
|
|
"loss": 5.6958,
|
|
"mean_token_accuracy": 0.15588323771953583,
|
|
"num_tokens": 11608431.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.720681619644165,
|
|
"epoch": 0.5288804872925856,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977695623746021,
|
|
"loss": 5.5589,
|
|
"mean_token_accuracy": 0.156508731842041,
|
|
"num_tokens": 11617552.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.7268609523773195,
|
|
"epoch": 0.5293005671077504,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004977653542337099,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.15938956588506697,
|
|
"num_tokens": 11626828.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.753752660751343,
|
|
"epoch": 0.5297206469229153,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004977611421466443,
|
|
"loss": 5.6933,
|
|
"mean_token_accuracy": 0.14879160374403,
|
|
"num_tokens": 11635867.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.821589660644531,
|
|
"epoch": 0.5301407267380802,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004977569261134797,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.16307313442230226,
|
|
"num_tokens": 11644711.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.776092433929444,
|
|
"epoch": 0.5305608065532451,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004977527061342908,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.15243458598852158,
|
|
"num_tokens": 11653320.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.739018869400025,
|
|
"epoch": 0.53098088636841,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004977484822091524,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.1549768939614296,
|
|
"num_tokens": 11662753.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.790743827819824,
|
|
"epoch": 0.5314009661835749,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004977442543381394,
|
|
"loss": 5.6776,
|
|
"mean_token_accuracy": 0.14615621492266656,
|
|
"num_tokens": 11671622.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.81527943611145,
|
|
"epoch": 0.5318210459987398,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977400225213266,
|
|
"loss": 5.6697,
|
|
"mean_token_accuracy": 0.14917083755135535,
|
|
"num_tokens": 11679964.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.709684419631958,
|
|
"epoch": 0.5322411258139046,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497735786758789,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.1544922798871994,
|
|
"num_tokens": 11688700.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.761388683319092,
|
|
"epoch": 0.5326612056290695,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004977315470506016,
|
|
"loss": 5.7514,
|
|
"mean_token_accuracy": 0.15335165113210678,
|
|
"num_tokens": 11698425.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.918869924545288,
|
|
"epoch": 0.5330812854442344,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004977273033968397,
|
|
"loss": 5.7348,
|
|
"mean_token_accuracy": 0.14367725551128388,
|
|
"num_tokens": 11707705.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.790050745010376,
|
|
"epoch": 0.5335013652593993,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004977230557975782,
|
|
"loss": 5.6271,
|
|
"mean_token_accuracy": 0.1547234535217285,
|
|
"num_tokens": 11717079.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.737287473678589,
|
|
"epoch": 0.5339214450745642,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004977188042528923,
|
|
"loss": 5.6199,
|
|
"mean_token_accuracy": 0.15220877379179001,
|
|
"num_tokens": 11725504.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.763228845596314,
|
|
"epoch": 0.5343415248897291,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004977145487628576,
|
|
"loss": 5.7038,
|
|
"mean_token_accuracy": 0.14911844879388808,
|
|
"num_tokens": 11735282.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.766521883010864,
|
|
"epoch": 0.534761604704894,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004977102893275494,
|
|
"loss": 5.6834,
|
|
"mean_token_accuracy": 0.1509793907403946,
|
|
"num_tokens": 11744827.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.80914888381958,
|
|
"epoch": 0.5351816845200588,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000497706025947043,
|
|
"loss": 5.6602,
|
|
"mean_token_accuracy": 0.15433914735913276,
|
|
"num_tokens": 11753066.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.779637861251831,
|
|
"epoch": 0.5356017643352237,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004977017586214142,
|
|
"loss": 5.6734,
|
|
"mean_token_accuracy": 0.1484221376478672,
|
|
"num_tokens": 11761190.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.748640012741089,
|
|
"epoch": 0.5360218441503886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004976974873507382,
|
|
"loss": 5.6372,
|
|
"mean_token_accuracy": 0.1559848442673683,
|
|
"num_tokens": 11770321.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.738561058044434,
|
|
"epoch": 0.5364419239655535,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000497693212135091,
|
|
"loss": 5.699,
|
|
"mean_token_accuracy": 0.1514401003718376,
|
|
"num_tokens": 11778388.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.765327787399292,
|
|
"epoch": 0.5368620037807184,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004976889329745482,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.15486714467406273,
|
|
"num_tokens": 11786250.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.621909475326538,
|
|
"epoch": 0.5372820835958833,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976846498691857,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.15950624793767929,
|
|
"num_tokens": 11794831.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.68565411567688,
|
|
"epoch": 0.5377021634110482,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004976803628190792,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.16010595262050628,
|
|
"num_tokens": 11803550.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.74244441986084,
|
|
"epoch": 0.5381222432262129,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976760718243047,
|
|
"loss": 5.651,
|
|
"mean_token_accuracy": 0.15274949222803116,
|
|
"num_tokens": 11812478.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.778332471847534,
|
|
"epoch": 0.5385423230413778,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004976717768849383,
|
|
"loss": 5.6248,
|
|
"mean_token_accuracy": 0.14805713966488837,
|
|
"num_tokens": 11822463.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.742837858200073,
|
|
"epoch": 0.5389624028565427,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004976674780010561,
|
|
"loss": 5.6795,
|
|
"mean_token_accuracy": 0.14474959224462508,
|
|
"num_tokens": 11831853.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.798117733001709,
|
|
"epoch": 0.5393824826717076,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497663175172734,
|
|
"loss": 5.6862,
|
|
"mean_token_accuracy": 0.14788996651768685,
|
|
"num_tokens": 11841574.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.805143690109253,
|
|
"epoch": 0.5398025624868725,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976588684000486,
|
|
"loss": 5.7683,
|
|
"mean_token_accuracy": 0.13789285868406295,
|
|
"num_tokens": 11852489.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.778584146499634,
|
|
"epoch": 0.5402226423020374,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976545576830759,
|
|
"loss": 5.6469,
|
|
"mean_token_accuracy": 0.14674668833613397,
|
|
"num_tokens": 11861499.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.825410175323486,
|
|
"epoch": 0.5406427221172023,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976502430218924,
|
|
"loss": 5.7217,
|
|
"mean_token_accuracy": 0.14696074053645133,
|
|
"num_tokens": 11871685.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.72649827003479,
|
|
"epoch": 0.5410628019323671,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004976459244165744,
|
|
"loss": 5.6456,
|
|
"mean_token_accuracy": 0.15092769861221314,
|
|
"num_tokens": 11881340.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.727269411087036,
|
|
"epoch": 0.541482881747532,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004976416018671986,
|
|
"loss": 5.6649,
|
|
"mean_token_accuracy": 0.14953715354204178,
|
|
"num_tokens": 11890700.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.7685645580291744,
|
|
"epoch": 0.5419029615626969,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976372753738415,
|
|
"loss": 5.6509,
|
|
"mean_token_accuracy": 0.14911282658576966,
|
|
"num_tokens": 11900329.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.83752589225769,
|
|
"epoch": 0.5423230413778618,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004976329449365795,
|
|
"loss": 5.6857,
|
|
"mean_token_accuracy": 0.14632721096277237,
|
|
"num_tokens": 11909915.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.7468969345092775,
|
|
"epoch": 0.5427431211930267,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004976286105554897,
|
|
"loss": 5.6999,
|
|
"mean_token_accuracy": 0.15292935222387313,
|
|
"num_tokens": 11918302.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.746342515945434,
|
|
"epoch": 0.5431632010081916,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004976242722306487,
|
|
"loss": 5.6634,
|
|
"mean_token_accuracy": 0.1509156569838524,
|
|
"num_tokens": 11927794.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.770822763442993,
|
|
"epoch": 0.5435832808233564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976199299621333,
|
|
"loss": 5.6778,
|
|
"mean_token_accuracy": 0.15434709787368775,
|
|
"num_tokens": 11937701.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.691930055618286,
|
|
"epoch": 0.5440033606385213,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004976155837500205,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.15657489597797394,
|
|
"num_tokens": 11946106.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.728176116943359,
|
|
"epoch": 0.5444234404536862,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004976112335943872,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.15170824974775315,
|
|
"num_tokens": 11954604.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.6393060207366945,
|
|
"epoch": 0.5448435202688511,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004976068794953106,
|
|
"loss": 5.589,
|
|
"mean_token_accuracy": 0.15737116038799287,
|
|
"num_tokens": 11963664.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.765772342681885,
|
|
"epoch": 0.545263600084016,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004976025214528677,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.15527967661619185,
|
|
"num_tokens": 11973426.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.675690031051635,
|
|
"epoch": 0.5456836798991809,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004975981594671359,
|
|
"loss": 5.6445,
|
|
"mean_token_accuracy": 0.1517896443605423,
|
|
"num_tokens": 11982339.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.829104852676392,
|
|
"epoch": 0.5461037597143458,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975937935381921,
|
|
"loss": 5.6875,
|
|
"mean_token_accuracy": 0.15777059495449067,
|
|
"num_tokens": 11992016.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.725285243988037,
|
|
"epoch": 0.5465238395295106,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000497589423666114,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.1507769599556923,
|
|
"num_tokens": 12000616.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.61439094543457,
|
|
"epoch": 0.5469439193446755,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975850498509789,
|
|
"loss": 5.5739,
|
|
"mean_token_accuracy": 0.1537862613797188,
|
|
"num_tokens": 12009717.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.743680143356324,
|
|
"epoch": 0.5473639991598404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004975806720928642,
|
|
"loss": 5.6559,
|
|
"mean_token_accuracy": 0.15329572409391404,
|
|
"num_tokens": 12018020.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.767218780517578,
|
|
"epoch": 0.5477840789750053,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004975762903918475,
|
|
"loss": 5.652,
|
|
"mean_token_accuracy": 0.150393944978714,
|
|
"num_tokens": 12027119.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.75718412399292,
|
|
"epoch": 0.5482041587901701,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975719047480064,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.15850069671869277,
|
|
"num_tokens": 12035566.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.718412923812866,
|
|
"epoch": 0.548624238605335,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975675151614187,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.15670061558485032,
|
|
"num_tokens": 12044505.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.666616725921631,
|
|
"epoch": 0.5490443184204999,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000497563121632162,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.15498950183391572,
|
|
"num_tokens": 12053338.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.739244508743286,
|
|
"epoch": 0.5494643982356647,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004975587241603142,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.15466095507144928,
|
|
"num_tokens": 12063235.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.815131378173828,
|
|
"epoch": 0.5498844780508296,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004975543227459533,
|
|
"loss": 5.6884,
|
|
"mean_token_accuracy": 0.1545080229640007,
|
|
"num_tokens": 12072490.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.773799467086792,
|
|
"epoch": 0.5503045578659945,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975499173891571,
|
|
"loss": 5.755,
|
|
"mean_token_accuracy": 0.1480020761489868,
|
|
"num_tokens": 12081474.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.755259323120117,
|
|
"epoch": 0.5507246376811594,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004975455080900037,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.15658100992441176,
|
|
"num_tokens": 12090963.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.762655639648438,
|
|
"epoch": 0.5511447174963243,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975410948485713,
|
|
"loss": 5.621,
|
|
"mean_token_accuracy": 0.1500764697790146,
|
|
"num_tokens": 12099786.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.7010783672332765,
|
|
"epoch": 0.5515647973114892,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975366776649379,
|
|
"loss": 5.6427,
|
|
"mean_token_accuracy": 0.15350330322980882,
|
|
"num_tokens": 12108469.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.758830261230469,
|
|
"epoch": 0.5519848771266541,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004975322565391818,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.15436404794454575,
|
|
"num_tokens": 12118287.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.858336734771728,
|
|
"epoch": 0.5524049569418189,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004975278314713814,
|
|
"loss": 5.7823,
|
|
"mean_token_accuracy": 0.14279426410794258,
|
|
"num_tokens": 12127122.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.782270908355713,
|
|
"epoch": 0.5528250367569838,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975234024616152,
|
|
"loss": 5.6667,
|
|
"mean_token_accuracy": 0.15639008581638336,
|
|
"num_tokens": 12136395.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.687395429611206,
|
|
"epoch": 0.5532451165721487,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975189695099613,
|
|
"loss": 5.6468,
|
|
"mean_token_accuracy": 0.15870906561613082,
|
|
"num_tokens": 12145025.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.795616292953492,
|
|
"epoch": 0.5536651963873136,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004975145326164985,
|
|
"loss": 5.6945,
|
|
"mean_token_accuracy": 0.14933544173836708,
|
|
"num_tokens": 12154352.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.753207206726074,
|
|
"epoch": 0.5540852762024785,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004975100917813055,
|
|
"loss": 5.6076,
|
|
"mean_token_accuracy": 0.14919200241565705,
|
|
"num_tokens": 12163802.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.691126537322998,
|
|
"epoch": 0.5545053560176434,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004975056470044606,
|
|
"loss": 5.6249,
|
|
"mean_token_accuracy": 0.15280142724514006,
|
|
"num_tokens": 12173111.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.721021461486816,
|
|
"epoch": 0.5549254358328082,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004975011982860428,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.14891051650047302,
|
|
"num_tokens": 12182048.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.743900537490845,
|
|
"epoch": 0.5553455156479731,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004974967456261309,
|
|
"loss": 5.6508,
|
|
"mean_token_accuracy": 0.1532616786658764,
|
|
"num_tokens": 12191501.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.782261896133423,
|
|
"epoch": 0.555765595463138,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974922890248036,
|
|
"loss": 5.6774,
|
|
"mean_token_accuracy": 0.1570911407470703,
|
|
"num_tokens": 12201132.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.863410520553589,
|
|
"epoch": 0.5561856752783029,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049748782848214,
|
|
"loss": 5.8015,
|
|
"mean_token_accuracy": 0.14694183841347694,
|
|
"num_tokens": 12211082.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.847155141830444,
|
|
"epoch": 0.5566057550934678,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004974833639982192,
|
|
"loss": 5.6247,
|
|
"mean_token_accuracy": 0.15586238205432892,
|
|
"num_tokens": 12219946.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.8018636226654055,
|
|
"epoch": 0.5570258349086327,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00049747889557312,
|
|
"loss": 5.7296,
|
|
"mean_token_accuracy": 0.15069587752223015,
|
|
"num_tokens": 12229668.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.767895221710205,
|
|
"epoch": 0.5574459147237976,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004974744232069219,
|
|
"loss": 5.713,
|
|
"mean_token_accuracy": 0.15386377424001693,
|
|
"num_tokens": 12238750.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.755981302261352,
|
|
"epoch": 0.5578659945389624,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004974699468997038,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.15173935890197754,
|
|
"num_tokens": 12246825.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.728928136825561,
|
|
"epoch": 0.5582860743541272,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974654666515452,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.1545877903699875,
|
|
"num_tokens": 12256413.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.749405002593994,
|
|
"epoch": 0.5587061541692921,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004974609824625254,
|
|
"loss": 5.629,
|
|
"mean_token_accuracy": 0.16152739375829697,
|
|
"num_tokens": 12265458.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.596953678131103,
|
|
"epoch": 0.559126233984457,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004974564943327239,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.15982334166765214,
|
|
"num_tokens": 12274124.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.590590953826904,
|
|
"epoch": 0.5595463137996219,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049745200226222,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.16951307207345961,
|
|
"num_tokens": 12283513.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.7416705131530765,
|
|
"epoch": 0.5599663936147868,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004974475062510936,
|
|
"loss": 5.6747,
|
|
"mean_token_accuracy": 0.1532605156302452,
|
|
"num_tokens": 12292396.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.736781597137451,
|
|
"epoch": 0.5603864734299517,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004974430062994242,
|
|
"loss": 5.6779,
|
|
"mean_token_accuracy": 0.15212651938199998,
|
|
"num_tokens": 12301604.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.842722940444946,
|
|
"epoch": 0.5608065532451165,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004974385024072912,
|
|
"loss": 5.7193,
|
|
"mean_token_accuracy": 0.1500556856393814,
|
|
"num_tokens": 12310458.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.8713582992553714,
|
|
"epoch": 0.5612266330602814,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000497433994574775,
|
|
"loss": 5.716,
|
|
"mean_token_accuracy": 0.1482469394803047,
|
|
"num_tokens": 12319620.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.79235725402832,
|
|
"epoch": 0.5616467128754463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497429482801955,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.14732127711176873,
|
|
"num_tokens": 12329518.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.753377771377563,
|
|
"epoch": 0.5620667926906112,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974249670889111,
|
|
"loss": 5.5939,
|
|
"mean_token_accuracy": 0.15525755882263184,
|
|
"num_tokens": 12338244.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.862080144882202,
|
|
"epoch": 0.5624868725057761,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004974204474357237,
|
|
"loss": 5.7698,
|
|
"mean_token_accuracy": 0.15021772235631942,
|
|
"num_tokens": 12347962.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.7907792091369625,
|
|
"epoch": 0.562906952320941,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004974159238424723,
|
|
"loss": 5.6812,
|
|
"mean_token_accuracy": 0.15491234064102172,
|
|
"num_tokens": 12357020.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.760762023925781,
|
|
"epoch": 0.5633270321361059,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004974113963092376,
|
|
"loss": 5.6569,
|
|
"mean_token_accuracy": 0.1541620060801506,
|
|
"num_tokens": 12366108.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.802693128585815,
|
|
"epoch": 0.5637471119512707,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004974068648360995,
|
|
"loss": 5.5724,
|
|
"mean_token_accuracy": 0.16243264824151993,
|
|
"num_tokens": 12374508.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.705340957641601,
|
|
"epoch": 0.5641671917664356,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004974023294231383,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.16032086312770844,
|
|
"num_tokens": 12383555.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.718349361419678,
|
|
"epoch": 0.5645872715816005,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004973977900704342,
|
|
"loss": 5.6873,
|
|
"mean_token_accuracy": 0.1504265695810318,
|
|
"num_tokens": 12392680.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.824889087677002,
|
|
"epoch": 0.5650073513967654,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004973932467780679,
|
|
"loss": 5.7349,
|
|
"mean_token_accuracy": 0.14873759895563127,
|
|
"num_tokens": 12401881.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.804216718673706,
|
|
"epoch": 0.5654274312119303,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004973886995461197,
|
|
"loss": 5.7209,
|
|
"mean_token_accuracy": 0.1467141777276993,
|
|
"num_tokens": 12411487.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.693055963516235,
|
|
"epoch": 0.5658475110270952,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004973841483746703,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.16629059463739396,
|
|
"num_tokens": 12420376.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.600977802276612,
|
|
"epoch": 0.5662675908422601,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004973795932638001,
|
|
"loss": 5.582,
|
|
"mean_token_accuracy": 0.15954945236444473,
|
|
"num_tokens": 12429518.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.7596508979797365,
|
|
"epoch": 0.5666876706574249,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00049737503421359,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15875059515237808,
|
|
"num_tokens": 12438952.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.718114280700684,
|
|
"epoch": 0.5671077504725898,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004973704712241206,
|
|
"loss": 5.5653,
|
|
"mean_token_accuracy": 0.1561713308095932,
|
|
"num_tokens": 12448576.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.647132396697998,
|
|
"epoch": 0.5675278302877547,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973659042954729,
|
|
"loss": 5.607,
|
|
"mean_token_accuracy": 0.1554710254073143,
|
|
"num_tokens": 12458166.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.595485591888428,
|
|
"epoch": 0.5679479101029196,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004973613334277277,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.16030601412057877,
|
|
"num_tokens": 12467271.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.731112432479859,
|
|
"epoch": 0.5683679899180845,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004973567586209658,
|
|
"loss": 5.7021,
|
|
"mean_token_accuracy": 0.1484995201230049,
|
|
"num_tokens": 12476255.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.772892475128174,
|
|
"epoch": 0.5687880697332494,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004973521798752686,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.15195122808218003,
|
|
"num_tokens": 12485096.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.885549306869507,
|
|
"epoch": 0.5692081495484141,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000497347597190717,
|
|
"loss": 5.6869,
|
|
"mean_token_accuracy": 0.15596108734607697,
|
|
"num_tokens": 12494405.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.71028151512146,
|
|
"epoch": 0.569628229363579,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973430105673921,
|
|
"loss": 5.6126,
|
|
"mean_token_accuracy": 0.1530092716217041,
|
|
"num_tokens": 12503349.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.719080543518066,
|
|
"epoch": 0.5700483091787439,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973384200053754,
|
|
"loss": 5.7078,
|
|
"mean_token_accuracy": 0.15315269976854323,
|
|
"num_tokens": 12513122.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.743679618835449,
|
|
"epoch": 0.5704683889939088,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497333825504748,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.1548440471291542,
|
|
"num_tokens": 12523614.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.7131969928741455,
|
|
"epoch": 0.5708884688090737,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004973292270655914,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.14896309226751328,
|
|
"num_tokens": 12532031.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.802944564819336,
|
|
"epoch": 0.5713085486242386,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000497324624687987,
|
|
"loss": 5.7597,
|
|
"mean_token_accuracy": 0.14592752158641814,
|
|
"num_tokens": 12542239.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.848610973358154,
|
|
"epoch": 0.5717286284394035,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004973200183720164,
|
|
"loss": 5.6903,
|
|
"mean_token_accuracy": 0.1458892785012722,
|
|
"num_tokens": 12552608.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.62038254737854,
|
|
"epoch": 0.5721487082545683,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004973154081177611,
|
|
"loss": 5.5269,
|
|
"mean_token_accuracy": 0.15161003023386002,
|
|
"num_tokens": 12562020.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.707475709915161,
|
|
"epoch": 0.5725687880697332,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004973107939253027,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1621535986661911,
|
|
"num_tokens": 12570519.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.6555585861206055,
|
|
"epoch": 0.5729888678848981,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004973061757947233,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.15764508694410323,
|
|
"num_tokens": 12579324.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.704854106903076,
|
|
"epoch": 0.573408947700063,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004973015537261043,
|
|
"loss": 5.6644,
|
|
"mean_token_accuracy": 0.15810555219650269,
|
|
"num_tokens": 12588014.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.835838747024536,
|
|
"epoch": 0.5738290275152279,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004972969277195279,
|
|
"loss": 5.6713,
|
|
"mean_token_accuracy": 0.15615084320306777,
|
|
"num_tokens": 12596882.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.745213270187378,
|
|
"epoch": 0.5742491073303928,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004972922977750757,
|
|
"loss": 5.5888,
|
|
"mean_token_accuracy": 0.15589642524719238,
|
|
"num_tokens": 12606069.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.724167776107788,
|
|
"epoch": 0.5746691871455577,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.00049728766389283,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.1498618669807911,
|
|
"num_tokens": 12615167.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.698711585998535,
|
|
"epoch": 0.5750892669607225,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972830260728729,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.15492099523544312,
|
|
"num_tokens": 12624230.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.763922691345215,
|
|
"epoch": 0.5755093467758874,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004972783843152863,
|
|
"loss": 5.6375,
|
|
"mean_token_accuracy": 0.15997321605682374,
|
|
"num_tokens": 12633158.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.726704406738281,
|
|
"epoch": 0.5759294265910523,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004972737386201527,
|
|
"loss": 5.5934,
|
|
"mean_token_accuracy": 0.15616918057203294,
|
|
"num_tokens": 12641465.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.6682007789611815,
|
|
"epoch": 0.5763495064062172,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972690889875541,
|
|
"loss": 5.557,
|
|
"mean_token_accuracy": 0.15953669995069503,
|
|
"num_tokens": 12650437.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.859883642196655,
|
|
"epoch": 0.5767695862213821,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972644354175732,
|
|
"loss": 5.7609,
|
|
"mean_token_accuracy": 0.14930831044912338,
|
|
"num_tokens": 12660072.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.833072233200073,
|
|
"epoch": 0.577189666036547,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004972597779102922,
|
|
"loss": 5.7682,
|
|
"mean_token_accuracy": 0.14977988600730896,
|
|
"num_tokens": 12670405.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.733975601196289,
|
|
"epoch": 0.5776097458517119,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004972551164657937,
|
|
"loss": 5.6639,
|
|
"mean_token_accuracy": 0.15277623534202575,
|
|
"num_tokens": 12679992.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.823847150802612,
|
|
"epoch": 0.5780298256668767,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004972504510841602,
|
|
"loss": 5.7063,
|
|
"mean_token_accuracy": 0.1545391082763672,
|
|
"num_tokens": 12690289.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.863948345184326,
|
|
"epoch": 0.5784499054820416,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004972457817654745,
|
|
"loss": 5.7185,
|
|
"mean_token_accuracy": 0.15025423765182494,
|
|
"num_tokens": 12700518.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.788507699966431,
|
|
"epoch": 0.5788699852972065,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972411085098191,
|
|
"loss": 5.7685,
|
|
"mean_token_accuracy": 0.14289451837539674,
|
|
"num_tokens": 12710603.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.803801727294922,
|
|
"epoch": 0.5792900651123714,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000497236431317277,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.15858056545257568,
|
|
"num_tokens": 12719298.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.794863271713257,
|
|
"epoch": 0.5797101449275363,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000497231750187931,
|
|
"loss": 5.6389,
|
|
"mean_token_accuracy": 0.15869482904672622,
|
|
"num_tokens": 12728368.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.842878913879394,
|
|
"epoch": 0.5801302247427012,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004972270651218638,
|
|
"loss": 5.7213,
|
|
"mean_token_accuracy": 0.15775972306728364,
|
|
"num_tokens": 12737898.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.82655348777771,
|
|
"epoch": 0.580550304557866,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004972223761191587,
|
|
"loss": 5.6457,
|
|
"mean_token_accuracy": 0.15020321011543275,
|
|
"num_tokens": 12746761.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.683896875381469,
|
|
"epoch": 0.5809703843730308,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004972176831798986,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.1623480200767517,
|
|
"num_tokens": 12755128.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.7375232696533205,
|
|
"epoch": 0.5813904641881957,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004972129863041667,
|
|
"loss": 5.7634,
|
|
"mean_token_accuracy": 0.14732126891613007,
|
|
"num_tokens": 12764727.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.8072254180908205,
|
|
"epoch": 0.5818105440033606,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004972082854920462,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.15929616689682008,
|
|
"num_tokens": 12773557.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.735633420944214,
|
|
"epoch": 0.5822306238185255,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004972035807436203,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.16261496543884277,
|
|
"num_tokens": 12782525.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.823388385772705,
|
|
"epoch": 0.5826507036336904,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004971988720589723,
|
|
"loss": 5.7055,
|
|
"mean_token_accuracy": 0.1529671147465706,
|
|
"num_tokens": 12791534.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.790287637710572,
|
|
"epoch": 0.5830707834488553,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004971941594381858,
|
|
"loss": 5.6007,
|
|
"mean_token_accuracy": 0.15712943971157073,
|
|
"num_tokens": 12800662.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.758783388137817,
|
|
"epoch": 0.5834908632640201,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004971894428813441,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.1564931422472,
|
|
"num_tokens": 12809440.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.827863645553589,
|
|
"epoch": 0.583910943079185,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000497184722388531,
|
|
"loss": 5.7252,
|
|
"mean_token_accuracy": 0.15080841034650802,
|
|
"num_tokens": 12818560.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.824147796630859,
|
|
"epoch": 0.5843310228943499,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971799979598297,
|
|
"loss": 5.6712,
|
|
"mean_token_accuracy": 0.15087602585554122,
|
|
"num_tokens": 12827898.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.652761316299438,
|
|
"epoch": 0.5847511027095148,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004971752695953243,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.1591871291399002,
|
|
"num_tokens": 12837199.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.755173635482788,
|
|
"epoch": 0.5851711825246797,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004971705372950984,
|
|
"loss": 5.6386,
|
|
"mean_token_accuracy": 0.15210898518562316,
|
|
"num_tokens": 12846493.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.80136251449585,
|
|
"epoch": 0.5855912623398446,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004971658010592358,
|
|
"loss": 5.6393,
|
|
"mean_token_accuracy": 0.15254888236522673,
|
|
"num_tokens": 12855026.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.743722152709961,
|
|
"epoch": 0.5860113421550095,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004971610608878205,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.15148996114730834,
|
|
"num_tokens": 12864563.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.840014123916626,
|
|
"epoch": 0.5864314219701743,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971563167809363,
|
|
"loss": 5.6431,
|
|
"mean_token_accuracy": 0.15958610326051711,
|
|
"num_tokens": 12874358.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.7371094703674315,
|
|
"epoch": 0.5868515017853392,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004971515687386674,
|
|
"loss": 5.6661,
|
|
"mean_token_accuracy": 0.15151161104440689,
|
|
"num_tokens": 12883110.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.755078363418579,
|
|
"epoch": 0.5872715816005041,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004971468167610978,
|
|
"loss": 5.7166,
|
|
"mean_token_accuracy": 0.15706731230020524,
|
|
"num_tokens": 12892977.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.698009443283081,
|
|
"epoch": 0.587691661415669,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004971420608483117,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.16349953562021255,
|
|
"num_tokens": 12902327.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.649787044525146,
|
|
"epoch": 0.5881117412308339,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004971373010003936,
|
|
"loss": 5.5487,
|
|
"mean_token_accuracy": 0.16682940125465393,
|
|
"num_tokens": 12911957.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.733649349212646,
|
|
"epoch": 0.5885318210459988,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004971325372174274,
|
|
"loss": 5.6528,
|
|
"mean_token_accuracy": 0.15108825862407685,
|
|
"num_tokens": 12920380.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.750072050094604,
|
|
"epoch": 0.5889519008611637,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971277694994976,
|
|
"loss": 5.7134,
|
|
"mean_token_accuracy": 0.1527300551533699,
|
|
"num_tokens": 12929670.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.763653707504273,
|
|
"epoch": 0.5893719806763285,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000497122997846689,
|
|
"loss": 5.6119,
|
|
"mean_token_accuracy": 0.16422443389892577,
|
|
"num_tokens": 12938185.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.749804496765137,
|
|
"epoch": 0.5897920604914934,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004971182222590857,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.15942007005214692,
|
|
"num_tokens": 12947706.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.678315114974976,
|
|
"epoch": 0.5902121403066583,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004971134427367725,
|
|
"loss": 5.6385,
|
|
"mean_token_accuracy": 0.15062529146671294,
|
|
"num_tokens": 12957393.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.782941627502441,
|
|
"epoch": 0.5906322201218231,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000497108659279834,
|
|
"loss": 5.5173,
|
|
"mean_token_accuracy": 0.16111443936824799,
|
|
"num_tokens": 12967165.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.780286359786987,
|
|
"epoch": 0.591052299936988,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004971038718883551,
|
|
"loss": 5.6612,
|
|
"mean_token_accuracy": 0.14747030138969422,
|
|
"num_tokens": 12976490.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.7380303859710695,
|
|
"epoch": 0.5914723797521529,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970990805624203,
|
|
"loss": 5.6581,
|
|
"mean_token_accuracy": 0.14838391840457915,
|
|
"num_tokens": 12985423.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.707084608078003,
|
|
"epoch": 0.5918924595673178,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004970942853021147,
|
|
"loss": 5.5599,
|
|
"mean_token_accuracy": 0.1571175068616867,
|
|
"num_tokens": 12994510.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.783777189254761,
|
|
"epoch": 0.5923125393824826,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004970894861075232,
|
|
"loss": 5.6727,
|
|
"mean_token_accuracy": 0.15406235307455063,
|
|
"num_tokens": 13003383.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.771741485595703,
|
|
"epoch": 0.5927326191976475,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004970846829787309,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.15840743184089662,
|
|
"num_tokens": 13012550.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.776666688919067,
|
|
"epoch": 0.5931526990128124,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970798759158227,
|
|
"loss": 5.6561,
|
|
"mean_token_accuracy": 0.1523322269320488,
|
|
"num_tokens": 13022066.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.756951570510864,
|
|
"epoch": 0.5935727788279773,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970750649188839,
|
|
"loss": 5.6481,
|
|
"mean_token_accuracy": 0.15815414711833,
|
|
"num_tokens": 13031008.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.679452228546142,
|
|
"epoch": 0.5939928586431422,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004970702499879998,
|
|
"loss": 5.6268,
|
|
"mean_token_accuracy": 0.15596338957548142,
|
|
"num_tokens": 13040366.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.706829309463501,
|
|
"epoch": 0.5944129384583071,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004970654311232554,
|
|
"loss": 5.6516,
|
|
"mean_token_accuracy": 0.15320228338241576,
|
|
"num_tokens": 13051140.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.750200080871582,
|
|
"epoch": 0.594833018273472,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004970606083247362,
|
|
"loss": 5.5899,
|
|
"mean_token_accuracy": 0.15294858068227768,
|
|
"num_tokens": 13059835.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.651260042190552,
|
|
"epoch": 0.5952530980886368,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970557815925278,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1561323568224907,
|
|
"num_tokens": 13068909.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.683264064788818,
|
|
"epoch": 0.5956731779038017,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004970509509267155,
|
|
"loss": 5.5946,
|
|
"mean_token_accuracy": 0.15663747787475585,
|
|
"num_tokens": 13078380.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.806794452667236,
|
|
"epoch": 0.5960932577189666,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004970461163273849,
|
|
"loss": 5.6274,
|
|
"mean_token_accuracy": 0.15849297642707824,
|
|
"num_tokens": 13087774.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.651058006286621,
|
|
"epoch": 0.5965133375341315,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004970412777946219,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.1637790635228157,
|
|
"num_tokens": 13095938.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.640749740600586,
|
|
"epoch": 0.5969334173492964,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004970364353285117,
|
|
"loss": 5.6397,
|
|
"mean_token_accuracy": 0.1581492930650711,
|
|
"num_tokens": 13104661.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.792786121368408,
|
|
"epoch": 0.5973534971644613,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004970315889291405,
|
|
"loss": 5.5999,
|
|
"mean_token_accuracy": 0.15228829234838487,
|
|
"num_tokens": 13114505.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.620942783355713,
|
|
"epoch": 0.5977735769796261,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004970267385965941,
|
|
"loss": 5.5679,
|
|
"mean_token_accuracy": 0.15517654567956923,
|
|
"num_tokens": 13124590.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.6427405834197994,
|
|
"epoch": 0.598193656794791,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004970218843309583,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.16136947572231292,
|
|
"num_tokens": 13134026.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.7891843795776365,
|
|
"epoch": 0.5986137366099559,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004970170261323192,
|
|
"loss": 5.7066,
|
|
"mean_token_accuracy": 0.1564835265278816,
|
|
"num_tokens": 13142654.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.692693042755127,
|
|
"epoch": 0.5990338164251208,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970121640007627,
|
|
"loss": 5.6146,
|
|
"mean_token_accuracy": 0.15288418233394624,
|
|
"num_tokens": 13151177.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.707670879364014,
|
|
"epoch": 0.5994538962402857,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004970072979363751,
|
|
"loss": 5.6171,
|
|
"mean_token_accuracy": 0.15406128615140915,
|
|
"num_tokens": 13159689.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.676187992095947,
|
|
"epoch": 0.5998739760554506,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004970024279392425,
|
|
"loss": 5.6408,
|
|
"mean_token_accuracy": 0.15284743309020996,
|
|
"num_tokens": 13168601.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.714297485351563,
|
|
"epoch": 0.6002940558706155,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969975540094513,
|
|
"loss": 5.6171,
|
|
"mean_token_accuracy": 0.1539945885539055,
|
|
"num_tokens": 13177035.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.777990198135376,
|
|
"epoch": 0.6007141356857802,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004969926761470876,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.16266828924417495,
|
|
"num_tokens": 13185444.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.732035493850708,
|
|
"epoch": 0.6011342155009451,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496987794352238,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.16005024313926697,
|
|
"num_tokens": 13194987.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.668026494979858,
|
|
"epoch": 0.60155429531611,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969829086249889,
|
|
"loss": 5.6295,
|
|
"mean_token_accuracy": 0.15632065534591674,
|
|
"num_tokens": 13203807.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.78542275428772,
|
|
"epoch": 0.6019743751312749,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496978018965427,
|
|
"loss": 5.7228,
|
|
"mean_token_accuracy": 0.1500210165977478,
|
|
"num_tokens": 13214362.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.81239013671875,
|
|
"epoch": 0.6023944549464398,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004969731253736387,
|
|
"loss": 5.7303,
|
|
"mean_token_accuracy": 0.15099334120750427,
|
|
"num_tokens": 13224192.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.714849805831909,
|
|
"epoch": 0.6028145347616047,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969682278497109,
|
|
"loss": 5.694,
|
|
"mean_token_accuracy": 0.15593211725354195,
|
|
"num_tokens": 13234430.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.6827106952667235,
|
|
"epoch": 0.6032346145767696,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969633263937301,
|
|
"loss": 5.5785,
|
|
"mean_token_accuracy": 0.15635734647512436,
|
|
"num_tokens": 13243681.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.8973612785339355,
|
|
"epoch": 0.6036546943919344,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004969584210057832,
|
|
"loss": 5.8472,
|
|
"mean_token_accuracy": 0.14447207152843475,
|
|
"num_tokens": 13254334.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.908036136627198,
|
|
"epoch": 0.6040747742070993,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969535116859573,
|
|
"loss": 5.669,
|
|
"mean_token_accuracy": 0.1561342217028141,
|
|
"num_tokens": 13263781.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.671984529495239,
|
|
"epoch": 0.6044948540222642,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969485984343392,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.155980384349823,
|
|
"num_tokens": 13272831.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.727685928344727,
|
|
"epoch": 0.6049149338374291,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000496943681251016,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.15507230162620544,
|
|
"num_tokens": 13281621.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.654034233093261,
|
|
"epoch": 0.605335013652594,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004969387601360747,
|
|
"loss": 5.6026,
|
|
"mean_token_accuracy": 0.14952811896800994,
|
|
"num_tokens": 13291021.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.738556241989135,
|
|
"epoch": 0.6057550934677589,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004969338350896026,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.15897882282733916,
|
|
"num_tokens": 13299752.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.826848030090332,
|
|
"epoch": 0.6061751732829238,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004969289061116869,
|
|
"loss": 5.6755,
|
|
"mean_token_accuracy": 0.14820482730865478,
|
|
"num_tokens": 13309112.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.764469861984253,
|
|
"epoch": 0.6065952530980886,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004969239732024148,
|
|
"loss": 5.6566,
|
|
"mean_token_accuracy": 0.15721848756074905,
|
|
"num_tokens": 13318328.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.5925215721130375,
|
|
"epoch": 0.6070153329132535,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004969190363618739,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.1585030034184456,
|
|
"num_tokens": 13328940.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.665217399597168,
|
|
"epoch": 0.6074354127284184,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004969140955901516,
|
|
"loss": 5.5687,
|
|
"mean_token_accuracy": 0.16284290254116057,
|
|
"num_tokens": 13337829.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.850957870483398,
|
|
"epoch": 0.6078554925435833,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969091508873352,
|
|
"loss": 5.7334,
|
|
"mean_token_accuracy": 0.14851107820868492,
|
|
"num_tokens": 13348289.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.759013700485229,
|
|
"epoch": 0.6082755723587482,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004969042022535126,
|
|
"loss": 5.653,
|
|
"mean_token_accuracy": 0.15454121828079223,
|
|
"num_tokens": 13357292.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.779410743713379,
|
|
"epoch": 0.6086956521739131,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004968992496887713,
|
|
"loss": 5.687,
|
|
"mean_token_accuracy": 0.15323319733142854,
|
|
"num_tokens": 13366640.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.730707216262817,
|
|
"epoch": 0.609115731989078,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004968942931931989,
|
|
"loss": 5.5924,
|
|
"mean_token_accuracy": 0.16110291406512262,
|
|
"num_tokens": 13377509.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.706106567382813,
|
|
"epoch": 0.6095358118042428,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004968893327668835,
|
|
"loss": 5.6956,
|
|
"mean_token_accuracy": 0.14979534447193146,
|
|
"num_tokens": 13386573.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.660001468658447,
|
|
"epoch": 0.6099558916194077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004968843684099128,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.15726414173841477,
|
|
"num_tokens": 13395790.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.721255302429199,
|
|
"epoch": 0.6103759714345726,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968794001223747,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.15050944983959197,
|
|
"num_tokens": 13405265.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.687171363830567,
|
|
"epoch": 0.6107960512497375,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004968744279043574,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.1621822014451027,
|
|
"num_tokens": 13413796.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.776734972000122,
|
|
"epoch": 0.6112161310649024,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004968694517559488,
|
|
"loss": 5.6438,
|
|
"mean_token_accuracy": 0.15677839443087577,
|
|
"num_tokens": 13423299.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.688075065612793,
|
|
"epoch": 0.6116362108800673,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968644716772371,
|
|
"loss": 5.5675,
|
|
"mean_token_accuracy": 0.16029704958200455,
|
|
"num_tokens": 13432267.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.672435188293457,
|
|
"epoch": 0.612056290695232,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004968594876683105,
|
|
"loss": 5.6545,
|
|
"mean_token_accuracy": 0.151273912191391,
|
|
"num_tokens": 13442332.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.711434841156006,
|
|
"epoch": 0.6124763705103969,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968544997292572,
|
|
"loss": 5.6178,
|
|
"mean_token_accuracy": 0.15658531337976456,
|
|
"num_tokens": 13451700.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.742845582962036,
|
|
"epoch": 0.6128964503255618,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004968495078601659,
|
|
"loss": 5.7153,
|
|
"mean_token_accuracy": 0.14965228438377381,
|
|
"num_tokens": 13461009.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.795819425582886,
|
|
"epoch": 0.6133165301407267,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004968445120611247,
|
|
"loss": 5.7035,
|
|
"mean_token_accuracy": 0.1513729974627495,
|
|
"num_tokens": 13470341.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.769411659240722,
|
|
"epoch": 0.6137366099558916,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004968395123322223,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.15624384433031083,
|
|
"num_tokens": 13479898.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.633978939056396,
|
|
"epoch": 0.6141566897710565,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000496834508673547,
|
|
"loss": 5.5368,
|
|
"mean_token_accuracy": 0.1608336254954338,
|
|
"num_tokens": 13488116.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.718822479248047,
|
|
"epoch": 0.6145767695862214,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004968295010851877,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.15767939537763595,
|
|
"num_tokens": 13497814.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.695955896377564,
|
|
"epoch": 0.6149968494013862,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004968244895672331,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.15185445845127105,
|
|
"num_tokens": 13506617.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.676547336578369,
|
|
"epoch": 0.6154169292165511,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004968194741197718,
|
|
"loss": 5.7503,
|
|
"mean_token_accuracy": 0.14818976521492006,
|
|
"num_tokens": 13516632.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.856671953201294,
|
|
"epoch": 0.615837009031716,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004968144547428927,
|
|
"loss": 5.6583,
|
|
"mean_token_accuracy": 0.15702558159828187,
|
|
"num_tokens": 13526452.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.799902677536011,
|
|
"epoch": 0.6162570888468809,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004968094314366848,
|
|
"loss": 5.5676,
|
|
"mean_token_accuracy": 0.15817629396915436,
|
|
"num_tokens": 13535663.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.622874593734741,
|
|
"epoch": 0.6166771686620458,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000496804404201237,
|
|
"loss": 5.5007,
|
|
"mean_token_accuracy": 0.17091045528650284,
|
|
"num_tokens": 13544574.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.760069704055786,
|
|
"epoch": 0.6170972484772107,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004967993730366385,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.15604218244552612,
|
|
"num_tokens": 13553041.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.671512126922607,
|
|
"epoch": 0.6175173282923756,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004967943379429781,
|
|
"loss": 5.6417,
|
|
"mean_token_accuracy": 0.15232662558555604,
|
|
"num_tokens": 13562108.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.906947946548462,
|
|
"epoch": 0.6179374081075404,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967892989203454,
|
|
"loss": 5.7739,
|
|
"mean_token_accuracy": 0.14764633178710937,
|
|
"num_tokens": 13571500.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.8263520240783695,
|
|
"epoch": 0.6183574879227053,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967842559688295,
|
|
"loss": 5.6844,
|
|
"mean_token_accuracy": 0.1520024761557579,
|
|
"num_tokens": 13581304.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.683232069015503,
|
|
"epoch": 0.6187775677378702,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004967792090885195,
|
|
"loss": 5.5609,
|
|
"mean_token_accuracy": 0.16256952211260794,
|
|
"num_tokens": 13590734.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.66082911491394,
|
|
"epoch": 0.6191976475530351,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967741582795052,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.1554405942559242,
|
|
"num_tokens": 13600486.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.834723377227784,
|
|
"epoch": 0.6196177273682,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004967691035418758,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.14801207035779954,
|
|
"num_tokens": 13610542.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.717353200912475,
|
|
"epoch": 0.6200378071833649,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496764044875721,
|
|
"loss": 5.5897,
|
|
"mean_token_accuracy": 0.160822394490242,
|
|
"num_tokens": 13619431.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.72810926437378,
|
|
"epoch": 0.6204578869985298,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004967589822811303,
|
|
"loss": 5.6448,
|
|
"mean_token_accuracy": 0.15230367332696915,
|
|
"num_tokens": 13629930.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.810457468032837,
|
|
"epoch": 0.6208779668136946,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004967539157581934,
|
|
"loss": 5.7607,
|
|
"mean_token_accuracy": 0.1508558511734009,
|
|
"num_tokens": 13639439.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.810669803619385,
|
|
"epoch": 0.6212980466288595,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496748845307,
|
|
"loss": 5.681,
|
|
"mean_token_accuracy": 0.15527973473072051,
|
|
"num_tokens": 13648548.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.788920211791992,
|
|
"epoch": 0.6217181264440244,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004967437709276401,
|
|
"loss": 5.7221,
|
|
"mean_token_accuracy": 0.15710752308368683,
|
|
"num_tokens": 13657658.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.674347543716431,
|
|
"epoch": 0.6221382062591893,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004967386926202034,
|
|
"loss": 5.4981,
|
|
"mean_token_accuracy": 0.1621797114610672,
|
|
"num_tokens": 13666763.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.782182407379151,
|
|
"epoch": 0.6225582860743542,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00049673361038478,
|
|
"loss": 5.7373,
|
|
"mean_token_accuracy": 0.14591761454939842,
|
|
"num_tokens": 13676527.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.726846313476562,
|
|
"epoch": 0.622978365889519,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004967285242214599,
|
|
"loss": 5.711,
|
|
"mean_token_accuracy": 0.15441259145736694,
|
|
"num_tokens": 13685404.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.775293207168579,
|
|
"epoch": 0.6233984457046838,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000496723434130333,
|
|
"loss": 5.5312,
|
|
"mean_token_accuracy": 0.15585086047649382,
|
|
"num_tokens": 13693118.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.682599878311157,
|
|
"epoch": 0.6238185255198487,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004967183401114898,
|
|
"loss": 5.5973,
|
|
"mean_token_accuracy": 0.15298613160848618,
|
|
"num_tokens": 13702015.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.709433698654175,
|
|
"epoch": 0.6242386053350136,
|
|
"grad_norm": 1.96875,
|
|
"learning_rate": 0.0004967132421650203,
|
|
"loss": 5.6205,
|
|
"mean_token_accuracy": 0.1487925611436367,
|
|
"num_tokens": 13711658.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.640313625335693,
|
|
"epoch": 0.6246586851501785,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004967081402910149,
|
|
"loss": 5.6281,
|
|
"mean_token_accuracy": 0.15437382012605666,
|
|
"num_tokens": 13720718.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.696998929977417,
|
|
"epoch": 0.6250787649653434,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000496703034489564,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.16457302123308182,
|
|
"num_tokens": 13729364.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.812005949020386,
|
|
"epoch": 0.6254988447805083,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004966979247607579,
|
|
"loss": 5.7952,
|
|
"mean_token_accuracy": 0.1459818609058857,
|
|
"num_tokens": 13739436.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.809390115737915,
|
|
"epoch": 0.6259189245956732,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004966928111046873,
|
|
"loss": 5.7157,
|
|
"mean_token_accuracy": 0.1619449883699417,
|
|
"num_tokens": 13749196.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.722574186325073,
|
|
"epoch": 0.626339004410838,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004966876935214426,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.15739037543535234,
|
|
"num_tokens": 13758414.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.696356010437012,
|
|
"epoch": 0.6267590842260029,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004966825720111147,
|
|
"loss": 5.599,
|
|
"mean_token_accuracy": 0.15576763302087784,
|
|
"num_tokens": 13767496.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.731720113754273,
|
|
"epoch": 0.6271791640411678,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004966774465737942,
|
|
"loss": 5.7364,
|
|
"mean_token_accuracy": 0.15644533336162567,
|
|
"num_tokens": 13777033.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.762928485870361,
|
|
"epoch": 0.6275992438563327,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966723172095717,
|
|
"loss": 5.6998,
|
|
"mean_token_accuracy": 0.15392984971404075,
|
|
"num_tokens": 13786313.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.734139251708984,
|
|
"epoch": 0.6280193236714976,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004966671839185384,
|
|
"loss": 5.6214,
|
|
"mean_token_accuracy": 0.16077139377593994,
|
|
"num_tokens": 13795257.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.636916065216065,
|
|
"epoch": 0.6284394034866625,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004966620467007851,
|
|
"loss": 5.546,
|
|
"mean_token_accuracy": 0.16158626824617386,
|
|
"num_tokens": 13804582.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.686999893188476,
|
|
"epoch": 0.6288594833018274,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004966569055564027,
|
|
"loss": 5.5142,
|
|
"mean_token_accuracy": 0.1591956153512001,
|
|
"num_tokens": 13813248.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.8127374172210695,
|
|
"epoch": 0.6292795631169922,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004966517604854823,
|
|
"loss": 5.7932,
|
|
"mean_token_accuracy": 0.14702995121479034,
|
|
"num_tokens": 13823301.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.716786479949951,
|
|
"epoch": 0.6296996429321571,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966466114881152,
|
|
"loss": 5.527,
|
|
"mean_token_accuracy": 0.1616852879524231,
|
|
"num_tokens": 13832040.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.789406156539917,
|
|
"epoch": 0.630119722747322,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004966414585643925,
|
|
"loss": 5.708,
|
|
"mean_token_accuracy": 0.15371926724910737,
|
|
"num_tokens": 13841874.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.673316860198975,
|
|
"epoch": 0.6305398025624869,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004966363017144055,
|
|
"loss": 5.5343,
|
|
"mean_token_accuracy": 0.16494474560022354,
|
|
"num_tokens": 13850755.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.633390045166015,
|
|
"epoch": 0.6309598823776518,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966311409382455,
|
|
"loss": 5.6069,
|
|
"mean_token_accuracy": 0.1526731699705124,
|
|
"num_tokens": 13860009.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.645658397674561,
|
|
"epoch": 0.6313799621928167,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004966259762360039,
|
|
"loss": 5.5308,
|
|
"mean_token_accuracy": 0.15903031826019287,
|
|
"num_tokens": 13868476.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.6507611751556395,
|
|
"epoch": 0.6318000420079816,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004966208076077723,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.16062566936016082,
|
|
"num_tokens": 13877367.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.700343370437622,
|
|
"epoch": 0.6322201218231464,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004966156350536422,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.15362192541360856,
|
|
"num_tokens": 13885985.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.673612928390503,
|
|
"epoch": 0.6326402016383113,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004966104585737054,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.1552409939467907,
|
|
"num_tokens": 13895059.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.7044392108917235,
|
|
"epoch": 0.6330602814534761,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004966052781680534,
|
|
"loss": 5.6238,
|
|
"mean_token_accuracy": 0.15182910710573197,
|
|
"num_tokens": 13903789.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.762989282608032,
|
|
"epoch": 0.633480361268641,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004966000938367778,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.1539550706744194,
|
|
"num_tokens": 13913377.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.600185346603394,
|
|
"epoch": 0.6339004410838059,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004965949055799708,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.16593605130910874,
|
|
"num_tokens": 13922141.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.727922582626343,
|
|
"epoch": 0.6343205208989708,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004965897133977241,
|
|
"loss": 5.5956,
|
|
"mean_token_accuracy": 0.1511126011610031,
|
|
"num_tokens": 13930717.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.748683834075928,
|
|
"epoch": 0.6347406007141357,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004965845172901298,
|
|
"loss": 5.6662,
|
|
"mean_token_accuracy": 0.15031958371400833,
|
|
"num_tokens": 13940344.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.686314058303833,
|
|
"epoch": 0.6351606805293005,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004965793172572798,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.15951916426420212,
|
|
"num_tokens": 13948400.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.66354660987854,
|
|
"epoch": 0.6355807603444654,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004965741132992663,
|
|
"loss": 5.6187,
|
|
"mean_token_accuracy": 0.1530763328075409,
|
|
"num_tokens": 13957939.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.766050386428833,
|
|
"epoch": 0.6360008401596303,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004965689054161814,
|
|
"loss": 5.6048,
|
|
"mean_token_accuracy": 0.15733802318572998,
|
|
"num_tokens": 13966943.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.686775827407837,
|
|
"epoch": 0.6364209199747952,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004965636936081176,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1530359521508217,
|
|
"num_tokens": 13975850.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.774266147613526,
|
|
"epoch": 0.6368409997899601,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000496558477875167,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.16522209197282792,
|
|
"num_tokens": 13985059.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.737274599075318,
|
|
"epoch": 0.637261079605125,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496553258217422,
|
|
"loss": 5.6641,
|
|
"mean_token_accuracy": 0.1459086686372757,
|
|
"num_tokens": 13993571.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.7590330123901365,
|
|
"epoch": 0.6376811594202898,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004965480346349751,
|
|
"loss": 5.6473,
|
|
"mean_token_accuracy": 0.15470026284456254,
|
|
"num_tokens": 14002326.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.850418996810913,
|
|
"epoch": 0.6381012392354547,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496542807127919,
|
|
"loss": 5.7856,
|
|
"mean_token_accuracy": 0.14904989078640937,
|
|
"num_tokens": 14012002.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.688018846511841,
|
|
"epoch": 0.6385213190506196,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496537575696346,
|
|
"loss": 5.6618,
|
|
"mean_token_accuracy": 0.1517901375889778,
|
|
"num_tokens": 14022085.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.700750541687012,
|
|
"epoch": 0.6389413988657845,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004965323403403488,
|
|
"loss": 5.5531,
|
|
"mean_token_accuracy": 0.15710408240556717,
|
|
"num_tokens": 14030706.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.692938947677613,
|
|
"epoch": 0.6393614786809494,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004965271010600205,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.15845440477132797,
|
|
"num_tokens": 14039520.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.7362024784088135,
|
|
"epoch": 0.6397815584961143,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004965218578554535,
|
|
"loss": 5.6609,
|
|
"mean_token_accuracy": 0.1563500553369522,
|
|
"num_tokens": 14048407.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.681648254394531,
|
|
"epoch": 0.6402016383112792,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000496516610726741,
|
|
"loss": 5.5922,
|
|
"mean_token_accuracy": 0.16066278517246246,
|
|
"num_tokens": 14057534.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.708992671966553,
|
|
"epoch": 0.640621718126444,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004965113596739759,
|
|
"loss": 5.5528,
|
|
"mean_token_accuracy": 0.16508279591798783,
|
|
"num_tokens": 14065992.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.664807271957398,
|
|
"epoch": 0.6410417979416089,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004965061046972508,
|
|
"loss": 5.5339,
|
|
"mean_token_accuracy": 0.15689536631107331,
|
|
"num_tokens": 14074806.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.65765414237976,
|
|
"epoch": 0.6414618777567738,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004965008457966594,
|
|
"loss": 5.5964,
|
|
"mean_token_accuracy": 0.15954618155956268,
|
|
"num_tokens": 14083813.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.694348669052124,
|
|
"epoch": 0.6418819575719387,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004964955829722945,
|
|
"loss": 5.5392,
|
|
"mean_token_accuracy": 0.1576619863510132,
|
|
"num_tokens": 14092193.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.807347249984741,
|
|
"epoch": 0.6423020373871036,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004964903162242493,
|
|
"loss": 5.7404,
|
|
"mean_token_accuracy": 0.14879937767982482,
|
|
"num_tokens": 14102797.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.7141985416412355,
|
|
"epoch": 0.6427221172022685,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004964850455526173,
|
|
"loss": 5.611,
|
|
"mean_token_accuracy": 0.15806291848421097,
|
|
"num_tokens": 14112226.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.599700927734375,
|
|
"epoch": 0.6431421970174334,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004964797709574917,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.157790507376194,
|
|
"num_tokens": 14121775.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.666961145401001,
|
|
"epoch": 0.6435622768325981,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000496474492438966,
|
|
"loss": 5.5204,
|
|
"mean_token_accuracy": 0.16159009486436843,
|
|
"num_tokens": 14130415.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.703153944015503,
|
|
"epoch": 0.643982356647763,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004964692099971338,
|
|
"loss": 5.5545,
|
|
"mean_token_accuracy": 0.16274037957191467,
|
|
"num_tokens": 14140204.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.666165065765381,
|
|
"epoch": 0.6444024364629279,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004964639236320885,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.15845234841108322,
|
|
"num_tokens": 14149595.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.6308153629302975,
|
|
"epoch": 0.6448225162780928,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004964586333439239,
|
|
"loss": 5.5805,
|
|
"mean_token_accuracy": 0.15749624222517014,
|
|
"num_tokens": 14158865.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.667867422103882,
|
|
"epoch": 0.6452425960932577,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004964533391327335,
|
|
"loss": 5.5375,
|
|
"mean_token_accuracy": 0.16526372283697127,
|
|
"num_tokens": 14167962.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.699340200424194,
|
|
"epoch": 0.6456626759084226,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004964480409986113,
|
|
"loss": 5.5873,
|
|
"mean_token_accuracy": 0.16477292776107788,
|
|
"num_tokens": 14176479.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.758196306228638,
|
|
"epoch": 0.6460827557235875,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004964427389416512,
|
|
"loss": 5.5979,
|
|
"mean_token_accuracy": 0.1566400408744812,
|
|
"num_tokens": 14185408.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.606453227996826,
|
|
"epoch": 0.6465028355387523,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000496437432961947,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.15897119492292405,
|
|
"num_tokens": 14194155.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.640574026107788,
|
|
"epoch": 0.6469229153539172,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004964321230595925,
|
|
"loss": 5.6261,
|
|
"mean_token_accuracy": 0.1550075277686119,
|
|
"num_tokens": 14202779.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.836891317367554,
|
|
"epoch": 0.6473429951690821,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004964268092346821,
|
|
"loss": 5.8207,
|
|
"mean_token_accuracy": 0.146051287651062,
|
|
"num_tokens": 14212552.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.879545545578003,
|
|
"epoch": 0.647763074984247,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004964214914873098,
|
|
"loss": 5.6016,
|
|
"mean_token_accuracy": 0.15281028002500535,
|
|
"num_tokens": 14222783.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.548879718780517,
|
|
"epoch": 0.6481831547994119,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964161698175697,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.1592596337199211,
|
|
"num_tokens": 14232085.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.6611487865448,
|
|
"epoch": 0.6486032346145768,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004964108442255562,
|
|
"loss": 5.6532,
|
|
"mean_token_accuracy": 0.15136753022670746,
|
|
"num_tokens": 14241969.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.700356197357178,
|
|
"epoch": 0.6490233144297417,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004964055147113637,
|
|
"loss": 5.5627,
|
|
"mean_token_accuracy": 0.1610928788781166,
|
|
"num_tokens": 14251012.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.784811544418335,
|
|
"epoch": 0.6494433942449065,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004964001812750864,
|
|
"loss": 5.6746,
|
|
"mean_token_accuracy": 0.1543006032705307,
|
|
"num_tokens": 14261110.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.703812551498413,
|
|
"epoch": 0.6498634740600714,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000496394843916819,
|
|
"loss": 5.6434,
|
|
"mean_token_accuracy": 0.15608806014060975,
|
|
"num_tokens": 14270869.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.744104099273682,
|
|
"epoch": 0.6502835538752363,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963895026366558,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.15321880877017974,
|
|
"num_tokens": 14279607.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.670469808578491,
|
|
"epoch": 0.6507036336904012,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004963841574346917,
|
|
"loss": 5.584,
|
|
"mean_token_accuracy": 0.15689192116260528,
|
|
"num_tokens": 14289282.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.666816091537475,
|
|
"epoch": 0.6511237135055661,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004963788083110212,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.16109126657247544,
|
|
"num_tokens": 14298658.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.7850751876831055,
|
|
"epoch": 0.651543793320731,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000496373455265739,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.15321561843156814,
|
|
"num_tokens": 14307832.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.6633306503295895,
|
|
"epoch": 0.6519638731358958,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963680982989402,
|
|
"loss": 5.5331,
|
|
"mean_token_accuracy": 0.15990484803915023,
|
|
"num_tokens": 14317122.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.641975736618042,
|
|
"epoch": 0.6523839529510607,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004963627374107195,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.1605705052614212,
|
|
"num_tokens": 14326069.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.6536908626556395,
|
|
"epoch": 0.6528040327662256,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004963573726011717,
|
|
"loss": 5.5586,
|
|
"mean_token_accuracy": 0.15782028138637544,
|
|
"num_tokens": 14335260.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.781147193908692,
|
|
"epoch": 0.6532241125813905,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004963520038703922,
|
|
"loss": 5.6589,
|
|
"mean_token_accuracy": 0.14450628608465194,
|
|
"num_tokens": 14345823.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.680127048492432,
|
|
"epoch": 0.6536441923965554,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000496346631218476,
|
|
"loss": 5.5181,
|
|
"mean_token_accuracy": 0.15935117304325103,
|
|
"num_tokens": 14354316.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.658060073852539,
|
|
"epoch": 0.6540642722117203,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000496341254645518,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.1578880801796913,
|
|
"num_tokens": 14364539.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.6646044731140135,
|
|
"epoch": 0.6544843520268852,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004963358741516138,
|
|
"loss": 5.6768,
|
|
"mean_token_accuracy": 0.14892476946115493,
|
|
"num_tokens": 14374081.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.715250015258789,
|
|
"epoch": 0.6549044318420499,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004963304897368585,
|
|
"loss": 5.5744,
|
|
"mean_token_accuracy": 0.15301866233348846,
|
|
"num_tokens": 14383255.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.781266593933106,
|
|
"epoch": 0.6553245116572148,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004963251014013475,
|
|
"loss": 5.7162,
|
|
"mean_token_accuracy": 0.15105995386838914,
|
|
"num_tokens": 14392417.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.869361925125122,
|
|
"epoch": 0.6557445914723797,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004963197091451763,
|
|
"loss": 5.7623,
|
|
"mean_token_accuracy": 0.14551858603954315,
|
|
"num_tokens": 14401899.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.800676774978638,
|
|
"epoch": 0.6561646712875446,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004963143129684405,
|
|
"loss": 5.7137,
|
|
"mean_token_accuracy": 0.15205856338143348,
|
|
"num_tokens": 14411245.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.656564712524414,
|
|
"epoch": 0.6565847511027095,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004963089128712355,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.1596169352531433,
|
|
"num_tokens": 14419710.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.685669898986816,
|
|
"epoch": 0.6570048309178744,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004963035088536571,
|
|
"loss": 5.541,
|
|
"mean_token_accuracy": 0.16597671955823898,
|
|
"num_tokens": 14430266.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.71679105758667,
|
|
"epoch": 0.6574249107330393,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004962981009158012,
|
|
"loss": 5.5222,
|
|
"mean_token_accuracy": 0.15457252264022828,
|
|
"num_tokens": 14439515.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.671058607101441,
|
|
"epoch": 0.6578449905482041,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004962926890577632,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.15761883705854415,
|
|
"num_tokens": 14448091.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.678781509399414,
|
|
"epoch": 0.658265070363369,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000496287273279639,
|
|
"loss": 5.6241,
|
|
"mean_token_accuracy": 0.15393756926059723,
|
|
"num_tokens": 14457744.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.75106201171875,
|
|
"epoch": 0.6586851501785339,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000496281853581525,
|
|
"loss": 5.6013,
|
|
"mean_token_accuracy": 0.16268085986375808,
|
|
"num_tokens": 14467597.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.71776933670044,
|
|
"epoch": 0.6591052299936988,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004962764299635168,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.158500038087368,
|
|
"num_tokens": 14476662.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.780879735946655,
|
|
"epoch": 0.6595253098088637,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004962710024257105,
|
|
"loss": 5.6777,
|
|
"mean_token_accuracy": 0.15187399610877036,
|
|
"num_tokens": 14486583.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.816821718215943,
|
|
"epoch": 0.6599453896240286,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962655709682025,
|
|
"loss": 5.6847,
|
|
"mean_token_accuracy": 0.15380629003047944,
|
|
"num_tokens": 14496528.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.759185695648194,
|
|
"epoch": 0.6603654694391935,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004962601355910887,
|
|
"loss": 5.6504,
|
|
"mean_token_accuracy": 0.14890926629304885,
|
|
"num_tokens": 14507026.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.616134738922119,
|
|
"epoch": 0.6607855492543583,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004962546962944656,
|
|
"loss": 5.5158,
|
|
"mean_token_accuracy": 0.1625874564051628,
|
|
"num_tokens": 14516480.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.6247007846832275,
|
|
"epoch": 0.6612056290695232,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004962492530784295,
|
|
"loss": 5.4622,
|
|
"mean_token_accuracy": 0.16726566851139069,
|
|
"num_tokens": 14525068.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.687610340118408,
|
|
"epoch": 0.6616257088846881,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004962438059430768,
|
|
"loss": 5.5961,
|
|
"mean_token_accuracy": 0.15713810473680495,
|
|
"num_tokens": 14534441.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.733529424667358,
|
|
"epoch": 0.662045788699853,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004962383548885039,
|
|
"loss": 5.6936,
|
|
"mean_token_accuracy": 0.15146275758743286,
|
|
"num_tokens": 14543026.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.70049557685852,
|
|
"epoch": 0.6624658685150179,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962328999148075,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.162800632417202,
|
|
"num_tokens": 14552068.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.766546583175659,
|
|
"epoch": 0.6628859483301828,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004962274410220842,
|
|
"loss": 5.6896,
|
|
"mean_token_accuracy": 0.15465587973594666,
|
|
"num_tokens": 14561587.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.830715274810791,
|
|
"epoch": 0.6633060281453477,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004962219782104308,
|
|
"loss": 5.6782,
|
|
"mean_token_accuracy": 0.15767197906970978,
|
|
"num_tokens": 14571020.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.752756977081299,
|
|
"epoch": 0.6637261079605125,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004962165114799439,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.15070140063762666,
|
|
"num_tokens": 14580638.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.657642221450805,
|
|
"epoch": 0.6641461877756774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004962110408307204,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.1519331306219101,
|
|
"num_tokens": 14590173.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.627839040756226,
|
|
"epoch": 0.6645662675908423,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962055662628571,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.1591130867600441,
|
|
"num_tokens": 14598635.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.728003406524659,
|
|
"epoch": 0.6649863474060071,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004962000877764513,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.15895481109619142,
|
|
"num_tokens": 14607233.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.8495190143585205,
|
|
"epoch": 0.665406427221172,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004961946053715998,
|
|
"loss": 5.7522,
|
|
"mean_token_accuracy": 0.1442479744553566,
|
|
"num_tokens": 14617483.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.6968982219696045,
|
|
"epoch": 0.665826507036337,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004961891190483997,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.15327939689159392,
|
|
"num_tokens": 14625805.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.619145631790161,
|
|
"epoch": 0.6662465868515017,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004961836288069483,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.16205275803804398,
|
|
"num_tokens": 14634605.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.767789077758789,
|
|
"epoch": 0.6666666666666666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004961781346473428,
|
|
"loss": 5.6948,
|
|
"mean_token_accuracy": 0.1465153157711029,
|
|
"num_tokens": 14644970.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.756932115554809,
|
|
"epoch": 0.6670867464818315,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004961726365696805,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.15876282155513763,
|
|
"num_tokens": 14655043.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.705471324920654,
|
|
"epoch": 0.6675068262969964,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004961671345740589,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.15569487810134888,
|
|
"num_tokens": 14663994.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.643215370178223,
|
|
"epoch": 0.6679269061121613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961616286605753,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.1519337624311447,
|
|
"num_tokens": 14674101.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.652733421325683,
|
|
"epoch": 0.6683469859273262,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004961561188293273,
|
|
"loss": 5.6378,
|
|
"mean_token_accuracy": 0.15260846465826033,
|
|
"num_tokens": 14684156.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.650334310531616,
|
|
"epoch": 0.6687670657424911,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004961506050804126,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.16360556036233903,
|
|
"num_tokens": 14693223.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.747977447509766,
|
|
"epoch": 0.6691871455576559,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000496145087413929,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.1563424676656723,
|
|
"num_tokens": 14702959.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.758147382736206,
|
|
"epoch": 0.6696072253728208,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004961395658299737,
|
|
"loss": 5.6716,
|
|
"mean_token_accuracy": 0.15093171894550322,
|
|
"num_tokens": 14712146.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.668249607086182,
|
|
"epoch": 0.6700273051879857,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004961340403286451,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1509583607316017,
|
|
"num_tokens": 14721932.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.666338872909546,
|
|
"epoch": 0.6704473850031506,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004961285109100408,
|
|
"loss": 5.5256,
|
|
"mean_token_accuracy": 0.16514174044132232,
|
|
"num_tokens": 14731080.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.632850456237793,
|
|
"epoch": 0.6708674648183155,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004961229775742587,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.16417475491762162,
|
|
"num_tokens": 14740057.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.78202714920044,
|
|
"epoch": 0.6712875446334804,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000496117440321397,
|
|
"loss": 5.6093,
|
|
"mean_token_accuracy": 0.16053422838449477,
|
|
"num_tokens": 14748399.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.70674409866333,
|
|
"epoch": 0.6717076244486453,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004961118991515537,
|
|
"loss": 5.6082,
|
|
"mean_token_accuracy": 0.1542074903845787,
|
|
"num_tokens": 14757215.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.65750560760498,
|
|
"epoch": 0.6721277042638101,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000496106354064827,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.15751723647117616,
|
|
"num_tokens": 14766191.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.8624285697937015,
|
|
"epoch": 0.672547784078975,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004961008050613149,
|
|
"loss": 5.6822,
|
|
"mean_token_accuracy": 0.1490050807595253,
|
|
"num_tokens": 14775220.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.722703504562378,
|
|
"epoch": 0.6729678638941399,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004960952521411161,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.15520244240760803,
|
|
"num_tokens": 14784287.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.772007274627685,
|
|
"epoch": 0.6733879437093048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004960896953043287,
|
|
"loss": 5.7014,
|
|
"mean_token_accuracy": 0.15136762484908103,
|
|
"num_tokens": 14794219.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.756883382797241,
|
|
"epoch": 0.6738080235244697,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004960841345510511,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.15511505603790282,
|
|
"num_tokens": 14803324.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.709602546691895,
|
|
"epoch": 0.6742281033396346,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000496078569881382,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.15611841082572936,
|
|
"num_tokens": 14811963.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.684782934188843,
|
|
"epoch": 0.6746481831547995,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004960730012954198,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.1514737568795681,
|
|
"num_tokens": 14821903.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.651682996749878,
|
|
"epoch": 0.6750682629699643,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004960674287932634,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.15362193435430527,
|
|
"num_tokens": 14831215.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.724930715560913,
|
|
"epoch": 0.6754883427851291,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004960618523750111,
|
|
"loss": 5.4999,
|
|
"mean_token_accuracy": 0.15814183801412582,
|
|
"num_tokens": 14840354.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.705191946029663,
|
|
"epoch": 0.675908422600294,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000496056272040762,
|
|
"loss": 5.6671,
|
|
"mean_token_accuracy": 0.15655403584241867,
|
|
"num_tokens": 14849660.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.735822105407715,
|
|
"epoch": 0.6763285024154589,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004960506877906149,
|
|
"loss": 5.5847,
|
|
"mean_token_accuracy": 0.15051980167627335,
|
|
"num_tokens": 14859819.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.742122793197632,
|
|
"epoch": 0.6767485822306238,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004960450996246686,
|
|
"loss": 5.5912,
|
|
"mean_token_accuracy": 0.1597781151533127,
|
|
"num_tokens": 14869260.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.650514125823975,
|
|
"epoch": 0.6771686620457887,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004960395075430222,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.15572320222854613,
|
|
"num_tokens": 14878685.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.661490488052368,
|
|
"epoch": 0.6775887418609536,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004960339115457748,
|
|
"loss": 5.5594,
|
|
"mean_token_accuracy": 0.15551790744066238,
|
|
"num_tokens": 14888456.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.721035194396973,
|
|
"epoch": 0.6780088216761184,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004960283116330255,
|
|
"loss": 5.6613,
|
|
"mean_token_accuracy": 0.1521642178297043,
|
|
"num_tokens": 14897401.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.722047758102417,
|
|
"epoch": 0.6784289014912833,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004960227078048735,
|
|
"loss": 5.5854,
|
|
"mean_token_accuracy": 0.15904034078121185,
|
|
"num_tokens": 14906741.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.669973230361938,
|
|
"epoch": 0.6788489813064482,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004960171000614179,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16626458019018173,
|
|
"num_tokens": 14916002.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.575302028656006,
|
|
"epoch": 0.6792690611216131,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004960114884027583,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.17047906070947647,
|
|
"num_tokens": 14925247.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.6553647994995115,
|
|
"epoch": 0.679689140936778,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004960058728289939,
|
|
"loss": 5.542,
|
|
"mean_token_accuracy": 0.1531473934650421,
|
|
"num_tokens": 14933925.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.774356412887573,
|
|
"epoch": 0.6801092207519429,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004960002533402243,
|
|
"loss": 5.5971,
|
|
"mean_token_accuracy": 0.15796921104192735,
|
|
"num_tokens": 14943368.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.718150043487549,
|
|
"epoch": 0.6805293005671077,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004959946299365491,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.15140645951032639,
|
|
"num_tokens": 14953710.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.776417064666748,
|
|
"epoch": 0.6809493803822726,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004959890026180677,
|
|
"loss": 5.642,
|
|
"mean_token_accuracy": 0.15366872251033784,
|
|
"num_tokens": 14962814.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.610153675079346,
|
|
"epoch": 0.6813694601974375,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00049598337138488,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.16162641048431398,
|
|
"num_tokens": 14971631.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.704393625259399,
|
|
"epoch": 0.6817895400126024,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004959777362370855,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.15709181278944015,
|
|
"num_tokens": 14980528.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.752010297775269,
|
|
"epoch": 0.6822096198277673,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004959720971747843,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.15931246876716615,
|
|
"num_tokens": 14989331.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.641499423980713,
|
|
"epoch": 0.6826296996429322,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004959664541980762,
|
|
"loss": 5.5448,
|
|
"mean_token_accuracy": 0.16116672456264497,
|
|
"num_tokens": 14999403.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.716615200042725,
|
|
"epoch": 0.6830497794580971,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004959608073070612,
|
|
"loss": 5.6204,
|
|
"mean_token_accuracy": 0.15285489484667777,
|
|
"num_tokens": 15009388.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.761466312408447,
|
|
"epoch": 0.6834698592732619,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004959551565018392,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.1617701143026352,
|
|
"num_tokens": 15018586.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.675375652313233,
|
|
"epoch": 0.6838899390884268,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004959495017825104,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.1646643817424774,
|
|
"num_tokens": 15027982.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.645266532897949,
|
|
"epoch": 0.6843100189035917,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004959438431491749,
|
|
"loss": 5.5486,
|
|
"mean_token_accuracy": 0.16084384471178054,
|
|
"num_tokens": 15037103.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.652230548858642,
|
|
"epoch": 0.6847300987187566,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000495938180601933,
|
|
"loss": 5.6586,
|
|
"mean_token_accuracy": 0.15451920107007028,
|
|
"num_tokens": 15046739.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.771371221542358,
|
|
"epoch": 0.6851501785339215,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004959325141408851,
|
|
"loss": 5.6031,
|
|
"mean_token_accuracy": 0.15792788416147233,
|
|
"num_tokens": 15056586.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.683104991912842,
|
|
"epoch": 0.6855702583490864,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004959268437661313,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.15851471424102784,
|
|
"num_tokens": 15066622.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.7034577369689945,
|
|
"epoch": 0.6859903381642513,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004959211694777724,
|
|
"loss": 5.5704,
|
|
"mean_token_accuracy": 0.160592782497406,
|
|
"num_tokens": 15075415.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.628656339645386,
|
|
"epoch": 0.686410417979416,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004959154912759086,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16037230640649797,
|
|
"num_tokens": 15085087.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.674224853515625,
|
|
"epoch": 0.6868304977945809,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004959098091606406,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.1610500007867813,
|
|
"num_tokens": 15093580.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.649624395370483,
|
|
"epoch": 0.6872505776097458,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004959041231320692,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.16328124403953553,
|
|
"num_tokens": 15104033.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.689769697189331,
|
|
"epoch": 0.6876706574249107,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004958984331902951,
|
|
"loss": 5.6276,
|
|
"mean_token_accuracy": 0.15330591350793837,
|
|
"num_tokens": 15113164.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.6513279438018795,
|
|
"epoch": 0.6880907372400756,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004958927393354188,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.16279968321323396,
|
|
"num_tokens": 15122215.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.661105632781982,
|
|
"epoch": 0.6885108170552405,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004958870415675415,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.1579482913017273,
|
|
"num_tokens": 15130877.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.671978092193603,
|
|
"epoch": 0.6889308968704054,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004958813398867639,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16374406665563584,
|
|
"num_tokens": 15140227.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.849607276916504,
|
|
"epoch": 0.6893509766855702,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004958756342931872,
|
|
"loss": 5.6957,
|
|
"mean_token_accuracy": 0.14763638526201248,
|
|
"num_tokens": 15150006.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.712654685974121,
|
|
"epoch": 0.6897710565007351,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004958699247869122,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.15836212635040284,
|
|
"num_tokens": 15160032.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.662709379196167,
|
|
"epoch": 0.6901911363159,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004958642113680404,
|
|
"loss": 5.5373,
|
|
"mean_token_accuracy": 0.1649177625775337,
|
|
"num_tokens": 15168966.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.824816131591797,
|
|
"epoch": 0.6906112161310649,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004958584940366727,
|
|
"loss": 5.7236,
|
|
"mean_token_accuracy": 0.1509198695421219,
|
|
"num_tokens": 15179337.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.735790348052978,
|
|
"epoch": 0.6910312959462298,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004958527727929106,
|
|
"loss": 5.6149,
|
|
"mean_token_accuracy": 0.15628711581230165,
|
|
"num_tokens": 15188395.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.690367364883423,
|
|
"epoch": 0.6914513757613947,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004958470476368552,
|
|
"loss": 5.5466,
|
|
"mean_token_accuracy": 0.16225921884179115,
|
|
"num_tokens": 15198669.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.666697883605957,
|
|
"epoch": 0.6918714555765595,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004958413185686082,
|
|
"loss": 5.5682,
|
|
"mean_token_accuracy": 0.15779572129249572,
|
|
"num_tokens": 15207371.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.701167821884155,
|
|
"epoch": 0.6922915353917244,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004958355855882709,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.15898908376693727,
|
|
"num_tokens": 15215694.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.754236125946045,
|
|
"epoch": 0.6927116152068893,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000495829848695945,
|
|
"loss": 5.5756,
|
|
"mean_token_accuracy": 0.15326517820358276,
|
|
"num_tokens": 15224963.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.597766494750976,
|
|
"epoch": 0.6931316950220542,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000495824107891732,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.16624577939510346,
|
|
"num_tokens": 15233569.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.594980192184448,
|
|
"epoch": 0.6935517748372191,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004958183631757336,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.15748120099306107,
|
|
"num_tokens": 15242671.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.651359605789184,
|
|
"epoch": 0.693971854652384,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004958126145480517,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.16182665377855301,
|
|
"num_tokens": 15251698.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.7826704502105715,
|
|
"epoch": 0.6943919344675489,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004958068620087879,
|
|
"loss": 5.6492,
|
|
"mean_token_accuracy": 0.1562219113111496,
|
|
"num_tokens": 15260608.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.599528217315674,
|
|
"epoch": 0.6948120142827137,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004958011055580443,
|
|
"loss": 5.5184,
|
|
"mean_token_accuracy": 0.1627250775694847,
|
|
"num_tokens": 15268866.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.586710405349732,
|
|
"epoch": 0.6952320940978786,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957953451959229,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.1718572720885277,
|
|
"num_tokens": 15277600.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.653484869003296,
|
|
"epoch": 0.6956521739130435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004957895809225254,
|
|
"loss": 5.4978,
|
|
"mean_token_accuracy": 0.1609959051012993,
|
|
"num_tokens": 15286016.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.688267993927002,
|
|
"epoch": 0.6960722537282084,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004957838127379544,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.1622077226638794,
|
|
"num_tokens": 15294676.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.697055292129517,
|
|
"epoch": 0.6964923335433733,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004957780406423118,
|
|
"loss": 5.5451,
|
|
"mean_token_accuracy": 0.15666759461164476,
|
|
"num_tokens": 15304084.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.6490225315094,
|
|
"epoch": 0.6969124133585382,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957722646356999,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.15901953727006912,
|
|
"num_tokens": 15314182.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.695853900909424,
|
|
"epoch": 0.697332493173703,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004957664847182209,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.15351271778345107,
|
|
"num_tokens": 15324213.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.770386505126953,
|
|
"epoch": 0.6977525729888678,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004957607008899774,
|
|
"loss": 5.5987,
|
|
"mean_token_accuracy": 0.15388550460338593,
|
|
"num_tokens": 15333122.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.790099620819092,
|
|
"epoch": 0.6981726528040327,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004957549131510717,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.146911858022213,
|
|
"num_tokens": 15342199.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.784045934677124,
|
|
"epoch": 0.6985927326191976,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004957491215016065,
|
|
"loss": 5.6357,
|
|
"mean_token_accuracy": 0.14943675845861434,
|
|
"num_tokens": 15352463.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.574797677993774,
|
|
"epoch": 0.6990128124343625,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004957433259416841,
|
|
"loss": 5.4843,
|
|
"mean_token_accuracy": 0.15912050753831863,
|
|
"num_tokens": 15361815.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.761810731887818,
|
|
"epoch": 0.6994328922495274,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004957375264714075,
|
|
"loss": 5.5941,
|
|
"mean_token_accuracy": 0.14885254427790642,
|
|
"num_tokens": 15371773.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.640265989303589,
|
|
"epoch": 0.6998529720646923,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004957317230908792,
|
|
"loss": 5.5488,
|
|
"mean_token_accuracy": 0.15723545998334884,
|
|
"num_tokens": 15380881.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.614818906784057,
|
|
"epoch": 0.7002730518798572,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004957259158002022,
|
|
"loss": 5.4189,
|
|
"mean_token_accuracy": 0.1693311810493469,
|
|
"num_tokens": 15389310.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.604830265045166,
|
|
"epoch": 0.700693131695022,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957201045994791,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.16204681545495986,
|
|
"num_tokens": 15398584.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.675758123397827,
|
|
"epoch": 0.7011132115101869,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004957142894888131,
|
|
"loss": 5.5447,
|
|
"mean_token_accuracy": 0.1662557229399681,
|
|
"num_tokens": 15407208.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.706802701950073,
|
|
"epoch": 0.7015332913253518,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957084704683071,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.16073613464832306,
|
|
"num_tokens": 15416474.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.709591579437256,
|
|
"epoch": 0.7019533711405167,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004957026475380642,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.15872790813446044,
|
|
"num_tokens": 15426101.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.750075244903565,
|
|
"epoch": 0.7023734509556816,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956968206981875,
|
|
"loss": 5.6179,
|
|
"mean_token_accuracy": 0.15739136934280396,
|
|
"num_tokens": 15435910.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.7634851932525635,
|
|
"epoch": 0.7027935307708465,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004956909899487803,
|
|
"loss": 5.6603,
|
|
"mean_token_accuracy": 0.1546674281358719,
|
|
"num_tokens": 15445494.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.677435827255249,
|
|
"epoch": 0.7032136105860114,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956851552899459,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.1608722448348999,
|
|
"num_tokens": 15455332.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.684817934036255,
|
|
"epoch": 0.7036336904011762,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004956793167217874,
|
|
"loss": 5.6122,
|
|
"mean_token_accuracy": 0.1539962038397789,
|
|
"num_tokens": 15464241.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.77572021484375,
|
|
"epoch": 0.7040537702163411,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004956734742444087,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.156563501060009,
|
|
"num_tokens": 15473473.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.676117277145385,
|
|
"epoch": 0.704473850031506,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004956676278579129,
|
|
"loss": 5.4876,
|
|
"mean_token_accuracy": 0.16209144443273543,
|
|
"num_tokens": 15482494.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.5847352027893065,
|
|
"epoch": 0.7048939298466709,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004956617775624037,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.15996210426092147,
|
|
"num_tokens": 15491180.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.684952878952027,
|
|
"epoch": 0.7053140096618358,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956559233579848,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.1575160101056099,
|
|
"num_tokens": 15501035.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.660862255096435,
|
|
"epoch": 0.7057340894770007,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004956500652447598,
|
|
"loss": 5.5498,
|
|
"mean_token_accuracy": 0.15877256616950036,
|
|
"num_tokens": 15510191.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.616110467910767,
|
|
"epoch": 0.7061541692921655,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004956442032228324,
|
|
"loss": 5.6257,
|
|
"mean_token_accuracy": 0.1581491820514202,
|
|
"num_tokens": 15519253.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.665469741821289,
|
|
"epoch": 0.7065742491073304,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004956383372923067,
|
|
"loss": 5.5804,
|
|
"mean_token_accuracy": 0.15870503187179566,
|
|
"num_tokens": 15528348.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.852564477920533,
|
|
"epoch": 0.7069943289224953,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004956324674532864,
|
|
"loss": 5.6792,
|
|
"mean_token_accuracy": 0.15142991095781327,
|
|
"num_tokens": 15537557.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.765557336807251,
|
|
"epoch": 0.7074144087376601,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004956265937058757,
|
|
"loss": 5.5959,
|
|
"mean_token_accuracy": 0.15625424385070802,
|
|
"num_tokens": 15546745.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.6664046287536625,
|
|
"epoch": 0.707834488552825,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956207160501784,
|
|
"loss": 5.4974,
|
|
"mean_token_accuracy": 0.16058537662029265,
|
|
"num_tokens": 15555532.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.695961809158325,
|
|
"epoch": 0.70825456836799,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004956148344862987,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.16354536563158034,
|
|
"num_tokens": 15564189.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.604541540145874,
|
|
"epoch": 0.7086746481831548,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004956089490143408,
|
|
"loss": 5.5702,
|
|
"mean_token_accuracy": 0.15514277219772338,
|
|
"num_tokens": 15574116.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.74328932762146,
|
|
"epoch": 0.7090947279983196,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004956030596344089,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.15882139503955842,
|
|
"num_tokens": 15583031.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.730233430862427,
|
|
"epoch": 0.7095148078134845,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004955971663466075,
|
|
"loss": 5.7008,
|
|
"mean_token_accuracy": 0.1583823412656784,
|
|
"num_tokens": 15592576.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.7435754299163815,
|
|
"epoch": 0.7099348876286494,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955912691510407,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15949044972658158,
|
|
"num_tokens": 15601065.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.7207683563232425,
|
|
"epoch": 0.7103549674438143,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004955853680478134,
|
|
"loss": 5.5574,
|
|
"mean_token_accuracy": 0.1536167934536934,
|
|
"num_tokens": 15610112.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.724563407897949,
|
|
"epoch": 0.7107750472589792,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004955794630370297,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.1562636002898216,
|
|
"num_tokens": 15618890.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.628248786926269,
|
|
"epoch": 0.7111951270741441,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955735541187945,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1557060018181801,
|
|
"num_tokens": 15627678.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.7201728343963625,
|
|
"epoch": 0.711615206889309,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004955676412932124,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.1623851999640465,
|
|
"num_tokens": 15636833.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.690943670272827,
|
|
"epoch": 0.7120352867044738,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004955617245603881,
|
|
"loss": 5.587,
|
|
"mean_token_accuracy": 0.15263200998306276,
|
|
"num_tokens": 15646571.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.6829156398773195,
|
|
"epoch": 0.7124553665196387,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004955558039204263,
|
|
"loss": 5.6182,
|
|
"mean_token_accuracy": 0.16115371286869049,
|
|
"num_tokens": 15654907.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.7532580375671385,
|
|
"epoch": 0.7128754463348036,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955498793734321,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.1611197918653488,
|
|
"num_tokens": 15664336.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.745222282409668,
|
|
"epoch": 0.7132955261499685,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004955439509195103,
|
|
"loss": 5.6056,
|
|
"mean_token_accuracy": 0.16001220643520356,
|
|
"num_tokens": 15674000.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.7138604640960695,
|
|
"epoch": 0.7137156059651334,
|
|
"grad_norm": 1.875,
|
|
"learning_rate": 0.0004955380185587661,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15749419778585433,
|
|
"num_tokens": 15684214.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.710150194168091,
|
|
"epoch": 0.7141356857802983,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004955320822913043,
|
|
"loss": 5.6195,
|
|
"mean_token_accuracy": 0.15598317384719848,
|
|
"num_tokens": 15693546.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.677717828750611,
|
|
"epoch": 0.7145557655954632,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004955261421172302,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.15616966933012008,
|
|
"num_tokens": 15702310.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.698915433883667,
|
|
"epoch": 0.714975845410628,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955201980366493,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.1571685291826725,
|
|
"num_tokens": 15711544.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.5956744194030765,
|
|
"epoch": 0.7153959252257929,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004955142500496665,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.15791433602571486,
|
|
"num_tokens": 15720914.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.749522113800049,
|
|
"epoch": 0.7158160050409578,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004955082981563872,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.1538071796298027,
|
|
"num_tokens": 15729825.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.651506567001343,
|
|
"epoch": 0.7162360848561227,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000495502342356917,
|
|
"loss": 5.5774,
|
|
"mean_token_accuracy": 0.15711765587329865,
|
|
"num_tokens": 15739649.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.69700608253479,
|
|
"epoch": 0.7166561646712876,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004954963826513614,
|
|
"loss": 5.471,
|
|
"mean_token_accuracy": 0.15691360533237458,
|
|
"num_tokens": 15747805.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.759174013137818,
|
|
"epoch": 0.7170762444864525,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000495490419039826,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.15306852161884307,
|
|
"num_tokens": 15757267.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.656875848770142,
|
|
"epoch": 0.7174963243016174,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004954844515224162,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.16100525110960007,
|
|
"num_tokens": 15767412.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.617850732803345,
|
|
"epoch": 0.7179164041167821,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004954784800992379,
|
|
"loss": 5.5648,
|
|
"mean_token_accuracy": 0.15756135284900666,
|
|
"num_tokens": 15776813.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.7305539608001705,
|
|
"epoch": 0.718336483931947,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004954725047703969,
|
|
"loss": 5.619,
|
|
"mean_token_accuracy": 0.15379863306879998,
|
|
"num_tokens": 15786258.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.710029125213623,
|
|
"epoch": 0.7187565637471119,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000495466525535999,
|
|
"loss": 5.576,
|
|
"mean_token_accuracy": 0.15841218307614327,
|
|
"num_tokens": 15795673.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.743064737319946,
|
|
"epoch": 0.7191766435622768,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004954605423961501,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.15423453375697135,
|
|
"num_tokens": 15805050.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.599371862411499,
|
|
"epoch": 0.7195967233774417,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004954545553509562,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.16561046838760377,
|
|
"num_tokens": 15813347.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.735318899154663,
|
|
"epoch": 0.7200168031926066,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004954485644005235,
|
|
"loss": 5.6455,
|
|
"mean_token_accuracy": 0.15517944395542144,
|
|
"num_tokens": 15823528.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.804451417922974,
|
|
"epoch": 0.7204368830077714,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004954425695449578,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.15588821172714235,
|
|
"num_tokens": 15832727.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.727295684814453,
|
|
"epoch": 0.7208569628229363,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004954365707843657,
|
|
"loss": 5.6252,
|
|
"mean_token_accuracy": 0.1505603663623333,
|
|
"num_tokens": 15842402.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.609046983718872,
|
|
"epoch": 0.7212770426381012,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004954305681188531,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.15758911669254302,
|
|
"num_tokens": 15850886.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.874528598785401,
|
|
"epoch": 0.7216971224532661,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004954245615485265,
|
|
"loss": 5.775,
|
|
"mean_token_accuracy": 0.15257195830345155,
|
|
"num_tokens": 15860093.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.730541467666626,
|
|
"epoch": 0.722117202268431,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004954185510734924,
|
|
"loss": 5.4951,
|
|
"mean_token_accuracy": 0.16199183613061904,
|
|
"num_tokens": 15868681.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.63291220664978,
|
|
"epoch": 0.7225372820835959,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004954125366938571,
|
|
"loss": 5.5715,
|
|
"mean_token_accuracy": 0.1619466871023178,
|
|
"num_tokens": 15878041.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.672195911407471,
|
|
"epoch": 0.7229573618987608,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004954065184097271,
|
|
"loss": 5.5729,
|
|
"mean_token_accuracy": 0.15789103657007217,
|
|
"num_tokens": 15887562.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.6754150390625,
|
|
"epoch": 0.7233774417139256,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004954004962212092,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.17005416005849838,
|
|
"num_tokens": 15896480.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.799858427047729,
|
|
"epoch": 0.7237975215290905,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004953944701284101,
|
|
"loss": 5.7002,
|
|
"mean_token_accuracy": 0.15285454094409942,
|
|
"num_tokens": 15906743.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.687485456466675,
|
|
"epoch": 0.7242176013442554,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004953884401314363,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.14405350238084794,
|
|
"num_tokens": 15915981.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.668266773223877,
|
|
"epoch": 0.7246376811594203,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.0004953824062303949,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.15426170378923415,
|
|
"num_tokens": 15924117.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.691087102890014,
|
|
"epoch": 0.7250577609745852,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004953763684253926,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.16509582996368408,
|
|
"num_tokens": 15933124.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.6671497344970705,
|
|
"epoch": 0.7254778407897501,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004953703267165364,
|
|
"loss": 5.4093,
|
|
"mean_token_accuracy": 0.16131499111652375,
|
|
"num_tokens": 15942422.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.673836374282837,
|
|
"epoch": 0.725897920604915,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004953642811039332,
|
|
"loss": 5.6407,
|
|
"mean_token_accuracy": 0.1549506589770317,
|
|
"num_tokens": 15950989.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.6949738502502445,
|
|
"epoch": 0.7263180004200798,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004953582315876904,
|
|
"loss": 5.6403,
|
|
"mean_token_accuracy": 0.1533081702888012,
|
|
"num_tokens": 15959659.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.694576978683472,
|
|
"epoch": 0.7267380802352447,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000495352178167915,
|
|
"loss": 5.5041,
|
|
"mean_token_accuracy": 0.17099424004554747,
|
|
"num_tokens": 15968102.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.793760204315186,
|
|
"epoch": 0.7271581600504096,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004953461208447143,
|
|
"loss": 5.6391,
|
|
"mean_token_accuracy": 0.15256927609443666,
|
|
"num_tokens": 15977705.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.675874042510986,
|
|
"epoch": 0.7275782398655745,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004953400596181953,
|
|
"loss": 5.6382,
|
|
"mean_token_accuracy": 0.15347846299409867,
|
|
"num_tokens": 15986703.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.719884777069092,
|
|
"epoch": 0.7279983196807394,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004953339944884657,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1610653355717659,
|
|
"num_tokens": 15995672.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.578777265548706,
|
|
"epoch": 0.7284183994959043,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004953279254556329,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.16606825590133667,
|
|
"num_tokens": 16004437.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.646161603927612,
|
|
"epoch": 0.7288384793110692,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004953218525198043,
|
|
"loss": 5.5353,
|
|
"mean_token_accuracy": 0.15697001963853835,
|
|
"num_tokens": 16012847.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.735745191574097,
|
|
"epoch": 0.7292585591262339,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004953157756810876,
|
|
"loss": 5.5712,
|
|
"mean_token_accuracy": 0.15936386734247207,
|
|
"num_tokens": 16022213.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.667310523986816,
|
|
"epoch": 0.7296786389413988,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004953096949395902,
|
|
"loss": 5.6223,
|
|
"mean_token_accuracy": 0.16006928235292434,
|
|
"num_tokens": 16031411.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.7181422233581545,
|
|
"epoch": 0.7300987187565637,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004953036102954202,
|
|
"loss": 5.665,
|
|
"mean_token_accuracy": 0.1544424846768379,
|
|
"num_tokens": 16041227.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.656005573272705,
|
|
"epoch": 0.7305187985717286,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004952975217486852,
|
|
"loss": 5.4861,
|
|
"mean_token_accuracy": 0.16734187602996825,
|
|
"num_tokens": 16049777.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.685440540313721,
|
|
"epoch": 0.7309388783868935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004952914292994928,
|
|
"loss": 5.5849,
|
|
"mean_token_accuracy": 0.1611620768904686,
|
|
"num_tokens": 16059093.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.751390409469605,
|
|
"epoch": 0.7313589582020584,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004952853329479514,
|
|
"loss": 5.6066,
|
|
"mean_token_accuracy": 0.16480785459280015,
|
|
"num_tokens": 16068550.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.6971841812133786,
|
|
"epoch": 0.7317790380172233,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004952792326941686,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.15641499161720276,
|
|
"num_tokens": 16078286.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.731863737106323,
|
|
"epoch": 0.7321991178323881,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004952731285382527,
|
|
"loss": 5.5655,
|
|
"mean_token_accuracy": 0.15366139262914658,
|
|
"num_tokens": 16087560.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.676146841049194,
|
|
"epoch": 0.732619197647553,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004952670204803118,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.1664838597178459,
|
|
"num_tokens": 16097478.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.717540884017945,
|
|
"epoch": 0.7330392774627179,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004952609085204539,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.16377640068531035,
|
|
"num_tokens": 16106884.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.7192158699035645,
|
|
"epoch": 0.7334593572778828,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004952547926587876,
|
|
"loss": 5.5669,
|
|
"mean_token_accuracy": 0.15231358855962754,
|
|
"num_tokens": 16115689.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.7321789264678955,
|
|
"epoch": 0.7338794370930477,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004952486728954209,
|
|
"loss": 5.4923,
|
|
"mean_token_accuracy": 0.16603951752185822,
|
|
"num_tokens": 16125237.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.608639526367187,
|
|
"epoch": 0.7342995169082126,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004952425492304624,
|
|
"loss": 5.5186,
|
|
"mean_token_accuracy": 0.16192169040441512,
|
|
"num_tokens": 16133940.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.68213267326355,
|
|
"epoch": 0.7347195967233774,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004952364216640207,
|
|
"loss": 5.6094,
|
|
"mean_token_accuracy": 0.1565001666545868,
|
|
"num_tokens": 16143256.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.72492618560791,
|
|
"epoch": 0.7351396765385423,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000495230290196204,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1615516275167465,
|
|
"num_tokens": 16153259.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.719367265701294,
|
|
"epoch": 0.7355597563537072,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004952241548271212,
|
|
"loss": 5.7241,
|
|
"mean_token_accuracy": 0.15054681450128554,
|
|
"num_tokens": 16162125.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.750476121902466,
|
|
"epoch": 0.7359798361688721,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004952180155568809,
|
|
"loss": 5.6369,
|
|
"mean_token_accuracy": 0.15786453932523728,
|
|
"num_tokens": 16171680.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.760352325439453,
|
|
"epoch": 0.736399915984037,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004952118723855919,
|
|
"loss": 5.6384,
|
|
"mean_token_accuracy": 0.15803294628858566,
|
|
"num_tokens": 16181559.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.698783349990845,
|
|
"epoch": 0.7368199957992019,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004952057253133628,
|
|
"loss": 5.5916,
|
|
"mean_token_accuracy": 0.15793971419334413,
|
|
"num_tokens": 16190611.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.748305034637451,
|
|
"epoch": 0.7372400756143668,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951995743403028,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.1553585410118103,
|
|
"num_tokens": 16200156.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.690016174316407,
|
|
"epoch": 0.7376601554295316,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004951934194665208,
|
|
"loss": 5.5778,
|
|
"mean_token_accuracy": 0.15406155884265899,
|
|
"num_tokens": 16209808.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.6809381484985355,
|
|
"epoch": 0.7380802352446965,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004951872606921257,
|
|
"loss": 5.5356,
|
|
"mean_token_accuracy": 0.16181282997131347,
|
|
"num_tokens": 16219243.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.642398118972778,
|
|
"epoch": 0.7385003150598614,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004951810980172265,
|
|
"loss": 5.5469,
|
|
"mean_token_accuracy": 0.16897100061178208,
|
|
"num_tokens": 16228180.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.688885879516602,
|
|
"epoch": 0.7389203948750263,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004951749314419327,
|
|
"loss": 5.5564,
|
|
"mean_token_accuracy": 0.16285726577043533,
|
|
"num_tokens": 16237045.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.7178980827331545,
|
|
"epoch": 0.7393404746901912,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004951687609663533,
|
|
"loss": 5.4986,
|
|
"mean_token_accuracy": 0.16633692383766174,
|
|
"num_tokens": 16245307.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.6679950714111325,
|
|
"epoch": 0.739760554505356,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004951625865905977,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.1576075181365013,
|
|
"num_tokens": 16255047.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.619790697097779,
|
|
"epoch": 0.740180634320521,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004951564083147753,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.16550215929746628,
|
|
"num_tokens": 16264969.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.738697290420532,
|
|
"epoch": 0.7406007141356857,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004951502261389953,
|
|
"loss": 5.657,
|
|
"mean_token_accuracy": 0.15243045836687089,
|
|
"num_tokens": 16274757.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.708020639419556,
|
|
"epoch": 0.7410207939508506,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004951440400633677,
|
|
"loss": 5.5439,
|
|
"mean_token_accuracy": 0.17007714062929152,
|
|
"num_tokens": 16283409.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.637024974822998,
|
|
"epoch": 0.7414408737660155,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951378500880015,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.1615572139620781,
|
|
"num_tokens": 16293206.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.699015426635742,
|
|
"epoch": 0.7418609535811804,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004951316562130067,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.16240676045417785,
|
|
"num_tokens": 16303121.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.673394870758057,
|
|
"epoch": 0.7422810333963453,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000495125458438493,
|
|
"loss": 5.5209,
|
|
"mean_token_accuracy": 0.1677414059638977,
|
|
"num_tokens": 16312710.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.826586580276489,
|
|
"epoch": 0.7427011132115102,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004951192567645702,
|
|
"loss": 5.7156,
|
|
"mean_token_accuracy": 0.1540753185749054,
|
|
"num_tokens": 16322280.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.609132862091064,
|
|
"epoch": 0.7431211930266751,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004951130511913481,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.1609240397810936,
|
|
"num_tokens": 16331656.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.695055818557739,
|
|
"epoch": 0.7435412728418399,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004951068417189366,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.16215466409921647,
|
|
"num_tokens": 16341074.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.693843412399292,
|
|
"epoch": 0.7439613526570048,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004951006283474457,
|
|
"loss": 5.5714,
|
|
"mean_token_accuracy": 0.15623839199543,
|
|
"num_tokens": 16350097.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.533200073242187,
|
|
"epoch": 0.7443814324721697,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004950944110769856,
|
|
"loss": 5.4689,
|
|
"mean_token_accuracy": 0.16720343977212906,
|
|
"num_tokens": 16359274.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.591437864303589,
|
|
"epoch": 0.7448015122873346,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004950881899076663,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.17578994035720824,
|
|
"num_tokens": 16368445.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.731908941268921,
|
|
"epoch": 0.7452215921024995,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950819648395979,
|
|
"loss": 5.5514,
|
|
"mean_token_accuracy": 0.16629501432180405,
|
|
"num_tokens": 16377689.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.6472413539886475,
|
|
"epoch": 0.7456416719176644,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000495075735872891,
|
|
"loss": 5.5111,
|
|
"mean_token_accuracy": 0.15904580056667328,
|
|
"num_tokens": 16386713.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.683931541442871,
|
|
"epoch": 0.7460617517328293,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004950695030076557,
|
|
"loss": 5.5424,
|
|
"mean_token_accuracy": 0.15848269909620286,
|
|
"num_tokens": 16395390.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.741724491119385,
|
|
"epoch": 0.7464818315479941,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004950632662440027,
|
|
"loss": 5.6115,
|
|
"mean_token_accuracy": 0.159981369972229,
|
|
"num_tokens": 16404531.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.599276351928711,
|
|
"epoch": 0.746901911363159,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004950570255820419,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.16114450246095657,
|
|
"num_tokens": 16413649.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.629710292816162,
|
|
"epoch": 0.7473219911783239,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950507810218843,
|
|
"loss": 5.6315,
|
|
"mean_token_accuracy": 0.1517360143363476,
|
|
"num_tokens": 16423247.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.7457269668579105,
|
|
"epoch": 0.7477420709934888,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004950445325636405,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.15606946051120757,
|
|
"num_tokens": 16432190.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.723924207687378,
|
|
"epoch": 0.7481621508086537,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004950382802074211,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.1662849009037018,
|
|
"num_tokens": 16443091.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.593891191482544,
|
|
"epoch": 0.7485822306238186,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004950320239533369,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.16187762469053268,
|
|
"num_tokens": 16452077.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.766776895523071,
|
|
"epoch": 0.7490023104389834,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004950257638014986,
|
|
"loss": 5.6666,
|
|
"mean_token_accuracy": 0.1541683092713356,
|
|
"num_tokens": 16461893.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.725894832611084,
|
|
"epoch": 0.7494223902541483,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004950194997520172,
|
|
"loss": 5.5287,
|
|
"mean_token_accuracy": 0.15639800429344178,
|
|
"num_tokens": 16470904.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.652572441101074,
|
|
"epoch": 0.7498424700693131,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004950132318050037,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.15636360496282578,
|
|
"num_tokens": 16480130.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.686444091796875,
|
|
"epoch": 0.750262549884478,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004950069599605691,
|
|
"loss": 5.6189,
|
|
"mean_token_accuracy": 0.15773196816444396,
|
|
"num_tokens": 16489485.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.682436275482178,
|
|
"epoch": 0.750682629699643,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004950006842188245,
|
|
"loss": 5.5841,
|
|
"mean_token_accuracy": 0.16362835615873336,
|
|
"num_tokens": 16498529.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.676763725280762,
|
|
"epoch": 0.7511027095148078,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000494994404579881,
|
|
"loss": 5.4927,
|
|
"mean_token_accuracy": 0.15938565880060196,
|
|
"num_tokens": 16508094.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.751111745834351,
|
|
"epoch": 0.7515227893299727,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00049498812104385,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.15739443451166152,
|
|
"num_tokens": 16517620.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.664203453063965,
|
|
"epoch": 0.7519428691451375,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004949818336108425,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.15442595928907393,
|
|
"num_tokens": 16526720.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.672812128067017,
|
|
"epoch": 0.7523629489603024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004949755422809703,
|
|
"loss": 5.5558,
|
|
"mean_token_accuracy": 0.15813300311565398,
|
|
"num_tokens": 16535979.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.660897350311279,
|
|
"epoch": 0.7527830287754673,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004949692470543446,
|
|
"loss": 5.4598,
|
|
"mean_token_accuracy": 0.17246938049793242,
|
|
"num_tokens": 16544538.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.610929727554321,
|
|
"epoch": 0.7532031085906322,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004949629479310769,
|
|
"loss": 5.5282,
|
|
"mean_token_accuracy": 0.16230118721723558,
|
|
"num_tokens": 16553962.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.661597442626953,
|
|
"epoch": 0.7536231884057971,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004949566449112788,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.16285742372274398,
|
|
"num_tokens": 16562652.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.704653215408325,
|
|
"epoch": 0.754043268220962,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004949503379950621,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.15362354516983032,
|
|
"num_tokens": 16570887.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.722882509231567,
|
|
"epoch": 0.7544633480361269,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004949440271825385,
|
|
"loss": 5.6894,
|
|
"mean_token_accuracy": 0.1523263484239578,
|
|
"num_tokens": 16581469.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.761154270172119,
|
|
"epoch": 0.7548834278512917,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004949377124738196,
|
|
"loss": 5.5602,
|
|
"mean_token_accuracy": 0.15706332474946977,
|
|
"num_tokens": 16590213.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.696602058410645,
|
|
"epoch": 0.7553035076664566,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004949313938690174,
|
|
"loss": 5.5492,
|
|
"mean_token_accuracy": 0.1597098231315613,
|
|
"num_tokens": 16598384.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.6125421047210695,
|
|
"epoch": 0.7557235874816215,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004949250713682438,
|
|
"loss": 5.5277,
|
|
"mean_token_accuracy": 0.16421396732330323,
|
|
"num_tokens": 16607670.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.717169332504272,
|
|
"epoch": 0.7561436672967864,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004949187449716107,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15434789657592773,
|
|
"num_tokens": 16617560.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 0.7561436672967864,
|
|
"eval_entropy": 5.550903656885421,
|
|
"eval_loss": 5.585652828216553,
|
|
"eval_mean_token_accuracy": 0.1653114039517877,
|
|
"eval_num_tokens": 16617560.0,
|
|
"eval_runtime": 27.4853,
|
|
"eval_samples_per_second": 1359.488,
|
|
"eval_steps_per_second": 169.945,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.676779699325562,
|
|
"epoch": 0.7565637471119513,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004949124146792304,
|
|
"loss": 5.5309,
|
|
"mean_token_accuracy": 0.16354483962059022,
|
|
"num_tokens": 16626038.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.657222414016724,
|
|
"epoch": 0.7569838269271162,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004949060804912149,
|
|
"loss": 5.5512,
|
|
"mean_token_accuracy": 0.16051364243030547,
|
|
"num_tokens": 16636490.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.710636186599731,
|
|
"epoch": 0.7574039067422811,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004948997424076764,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.1557503804564476,
|
|
"num_tokens": 16645369.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.759248876571656,
|
|
"epoch": 0.7578239865574459,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004948934004287272,
|
|
"loss": 5.6124,
|
|
"mean_token_accuracy": 0.1579928658902645,
|
|
"num_tokens": 16654348.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.7791351795196535,
|
|
"epoch": 0.7582440663726108,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004948870545544796,
|
|
"loss": 5.6141,
|
|
"mean_token_accuracy": 0.1496404230594635,
|
|
"num_tokens": 16664009.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.709259700775147,
|
|
"epoch": 0.7586641461877757,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000494880704785046,
|
|
"loss": 5.6286,
|
|
"mean_token_accuracy": 0.15393585115671157,
|
|
"num_tokens": 16674079.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.69500150680542,
|
|
"epoch": 0.7590842260029406,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004948743511205392,
|
|
"loss": 5.559,
|
|
"mean_token_accuracy": 0.16091811507940293,
|
|
"num_tokens": 16683687.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.664481973648071,
|
|
"epoch": 0.7595043058181055,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004948679935610712,
|
|
"loss": 5.4712,
|
|
"mean_token_accuracy": 0.1736868515610695,
|
|
"num_tokens": 16693311.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.641069650650024,
|
|
"epoch": 0.7599243856332704,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000494861632106755,
|
|
"loss": 5.5108,
|
|
"mean_token_accuracy": 0.1594437539577484,
|
|
"num_tokens": 16702121.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.643872547149658,
|
|
"epoch": 0.7603444654484351,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004948552667577033,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.1581725984811783,
|
|
"num_tokens": 16711883.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.724424076080322,
|
|
"epoch": 0.7607645452636,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004948488975140286,
|
|
"loss": 5.612,
|
|
"mean_token_accuracy": 0.15874697566032409,
|
|
"num_tokens": 16721449.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.686666107177734,
|
|
"epoch": 0.7611846250787649,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000494842524375844,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.1576692521572113,
|
|
"num_tokens": 16730068.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.629677724838257,
|
|
"epoch": 0.7616047048939298,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004948361473432623,
|
|
"loss": 5.5526,
|
|
"mean_token_accuracy": 0.158638134598732,
|
|
"num_tokens": 16739970.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.772377395629883,
|
|
"epoch": 0.7620247847090947,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004948297664163964,
|
|
"loss": 5.6304,
|
|
"mean_token_accuracy": 0.15675289779901505,
|
|
"num_tokens": 16749461.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.757342672348022,
|
|
"epoch": 0.7624448645242596,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004948233815953593,
|
|
"loss": 5.6877,
|
|
"mean_token_accuracy": 0.1533423252403736,
|
|
"num_tokens": 16758747.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.6478190422058105,
|
|
"epoch": 0.7628649443394245,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004948169928802643,
|
|
"loss": 5.4186,
|
|
"mean_token_accuracy": 0.1680832475423813,
|
|
"num_tokens": 16767212.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.715030384063721,
|
|
"epoch": 0.7632850241545893,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004948106002712245,
|
|
"loss": 5.5782,
|
|
"mean_token_accuracy": 0.15843361914157866,
|
|
"num_tokens": 16776514.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.709997463226318,
|
|
"epoch": 0.7637051039697542,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004948042037683529,
|
|
"loss": 5.5506,
|
|
"mean_token_accuracy": 0.15640008747577666,
|
|
"num_tokens": 16786310.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.718139171600342,
|
|
"epoch": 0.7641251837849191,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004947978033717632,
|
|
"loss": 5.581,
|
|
"mean_token_accuracy": 0.15548551678657532,
|
|
"num_tokens": 16795551.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.7015400409698485,
|
|
"epoch": 0.764545263600084,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004947913990815684,
|
|
"loss": 5.5491,
|
|
"mean_token_accuracy": 0.15944830179214478,
|
|
"num_tokens": 16805099.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.720749711990356,
|
|
"epoch": 0.7649653434152489,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004947849908978824,
|
|
"loss": 5.5826,
|
|
"mean_token_accuracy": 0.15997215658426284,
|
|
"num_tokens": 16813963.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.7728959083557125,
|
|
"epoch": 0.7653854232304138,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004947785788208182,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.15642002671957017,
|
|
"num_tokens": 16822814.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.748675060272217,
|
|
"epoch": 0.7658055030455787,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004947721628504898,
|
|
"loss": 5.6506,
|
|
"mean_token_accuracy": 0.15549189746379852,
|
|
"num_tokens": 16831906.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.6409765720367435,
|
|
"epoch": 0.7662255828607435,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004947657429870108,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.1629703313112259,
|
|
"num_tokens": 16840050.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.592518949508667,
|
|
"epoch": 0.7666456626759084,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004947593192304946,
|
|
"loss": 5.4915,
|
|
"mean_token_accuracy": 0.16089494079351424,
|
|
"num_tokens": 16848404.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.62299108505249,
|
|
"epoch": 0.7670657424910733,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004947528915810554,
|
|
"loss": 5.4933,
|
|
"mean_token_accuracy": 0.1622912123799324,
|
|
"num_tokens": 16856568.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.6679102897644045,
|
|
"epoch": 0.7674858223062382,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004947464600388066,
|
|
"loss": 5.5196,
|
|
"mean_token_accuracy": 0.1620594307780266,
|
|
"num_tokens": 16864936.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.808090543746948,
|
|
"epoch": 0.7679059021214031,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004947400246038627,
|
|
"loss": 5.658,
|
|
"mean_token_accuracy": 0.15416733771562577,
|
|
"num_tokens": 16874504.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.572278261184692,
|
|
"epoch": 0.768325981936568,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004947335852763374,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.1646368309855461,
|
|
"num_tokens": 16883365.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.67635669708252,
|
|
"epoch": 0.7687460617517329,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004947271420563447,
|
|
"loss": 5.6623,
|
|
"mean_token_accuracy": 0.144975683093071,
|
|
"num_tokens": 16892701.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.678815221786499,
|
|
"epoch": 0.7691661415668977,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004947206949439989,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.15904399305582045,
|
|
"num_tokens": 16901864.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.71064567565918,
|
|
"epoch": 0.7695862213820626,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494714243939414,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.16552575305104256,
|
|
"num_tokens": 16910908.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.67052116394043,
|
|
"epoch": 0.7700063011972275,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004947077890427045,
|
|
"loss": 5.5671,
|
|
"mean_token_accuracy": 0.16161819100379943,
|
|
"num_tokens": 16920299.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.782629203796387,
|
|
"epoch": 0.7704263810123924,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004947013302539846,
|
|
"loss": 5.6819,
|
|
"mean_token_accuracy": 0.14940958172082902,
|
|
"num_tokens": 16930027.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.750628232955933,
|
|
"epoch": 0.7708464608275573,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004946948675733688,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.15798421204090118,
|
|
"num_tokens": 16939387.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.68762173652649,
|
|
"epoch": 0.7712665406427222,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004946884010009714,
|
|
"loss": 5.5436,
|
|
"mean_token_accuracy": 0.16124205887317658,
|
|
"num_tokens": 16950024.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.638156890869141,
|
|
"epoch": 0.771686620457887,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004946819305369073,
|
|
"loss": 5.4453,
|
|
"mean_token_accuracy": 0.16821138560771942,
|
|
"num_tokens": 16958219.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.6072611808776855,
|
|
"epoch": 0.7721067002730518,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004946754561812909,
|
|
"loss": 5.424,
|
|
"mean_token_accuracy": 0.16381552219390869,
|
|
"num_tokens": 16966829.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.621193552017212,
|
|
"epoch": 0.7725267800882167,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004946689779342367,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.16035796105861663,
|
|
"num_tokens": 16975585.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.625691366195679,
|
|
"epoch": 0.7729468599033816,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004946624957958599,
|
|
"loss": 5.5195,
|
|
"mean_token_accuracy": 0.16271020472049713,
|
|
"num_tokens": 16984848.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.610690355300903,
|
|
"epoch": 0.7733669397185465,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000494656009766275,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.16337853372097016,
|
|
"num_tokens": 16993179.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.62993860244751,
|
|
"epoch": 0.7737870195337114,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000494649519845597,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.1587835118174553,
|
|
"num_tokens": 17002563.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.708981704711914,
|
|
"epoch": 0.7742070993488763,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004946430260339409,
|
|
"loss": 5.5556,
|
|
"mean_token_accuracy": 0.15450216233730316,
|
|
"num_tokens": 17011805.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.677693319320679,
|
|
"epoch": 0.7746271791640411,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004946365283314216,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.15712636411190034,
|
|
"num_tokens": 17020398.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.605440521240235,
|
|
"epoch": 0.775047258979206,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004946300267381545,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.16217170357704164,
|
|
"num_tokens": 17030805.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.669513273239136,
|
|
"epoch": 0.7754673387943709,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004946235212542544,
|
|
"loss": 5.5344,
|
|
"mean_token_accuracy": 0.16208829283714293,
|
|
"num_tokens": 17040164.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.650531339645386,
|
|
"epoch": 0.7758874186095358,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004946170118798367,
|
|
"loss": 5.5906,
|
|
"mean_token_accuracy": 0.15611371397972107,
|
|
"num_tokens": 17049519.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.731847667694092,
|
|
"epoch": 0.7763074984247007,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004946104986150167,
|
|
"loss": 5.5354,
|
|
"mean_token_accuracy": 0.15955014228820802,
|
|
"num_tokens": 17058042.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.645770788192749,
|
|
"epoch": 0.7767275782398656,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004946039814599099,
|
|
"loss": 5.5463,
|
|
"mean_token_accuracy": 0.16279122084379197,
|
|
"num_tokens": 17067107.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.659356498718262,
|
|
"epoch": 0.7771476580550305,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004945974604146316,
|
|
"loss": 5.6383,
|
|
"mean_token_accuracy": 0.16182979196310043,
|
|
"num_tokens": 17076975.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.652160120010376,
|
|
"epoch": 0.7775677378701953,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004945909354792974,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.16177307814359665,
|
|
"num_tokens": 17086405.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.673442792892456,
|
|
"epoch": 0.7779878176853602,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004945844066540229,
|
|
"loss": 5.5607,
|
|
"mean_token_accuracy": 0.15728678107261657,
|
|
"num_tokens": 17095333.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.715294075012207,
|
|
"epoch": 0.7784078975005251,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004945778739389236,
|
|
"loss": 5.6047,
|
|
"mean_token_accuracy": 0.15702673196792602,
|
|
"num_tokens": 17103631.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.694115066528321,
|
|
"epoch": 0.77882797731569,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004945713373341152,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.1604058101773262,
|
|
"num_tokens": 17112612.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.704887533187867,
|
|
"epoch": 0.7792480571308549,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004945647968397139,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.1582975372672081,
|
|
"num_tokens": 17121592.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.646542644500732,
|
|
"epoch": 0.7796681369460198,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004945582524558352,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.16268820613622664,
|
|
"num_tokens": 17131003.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.76059775352478,
|
|
"epoch": 0.7800882167611847,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494551704182595,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.15795339047908782,
|
|
"num_tokens": 17140013.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.794629859924316,
|
|
"epoch": 0.7805082965763495,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004945451520201095,
|
|
"loss": 5.7168,
|
|
"mean_token_accuracy": 0.1471349537372589,
|
|
"num_tokens": 17150406.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.697279930114746,
|
|
"epoch": 0.7809283763915144,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004945385959684947,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.15653786659240723,
|
|
"num_tokens": 17159757.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.733369779586792,
|
|
"epoch": 0.7813484562066793,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004945320360278667,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.16423405855894088,
|
|
"num_tokens": 17169317.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.745339679718017,
|
|
"epoch": 0.7817685360218442,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004945254721983416,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.16655531898140907,
|
|
"num_tokens": 17178410.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.705344915390015,
|
|
"epoch": 0.782188615837009,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000494518904480036,
|
|
"loss": 5.5004,
|
|
"mean_token_accuracy": 0.15776502788066865,
|
|
"num_tokens": 17186922.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.664468145370483,
|
|
"epoch": 0.782608695652174,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004945123328730659,
|
|
"loss": 5.5965,
|
|
"mean_token_accuracy": 0.1562838301062584,
|
|
"num_tokens": 17197125.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.67675747871399,
|
|
"epoch": 0.7830287754673388,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000494505757377548,
|
|
"loss": 5.507,
|
|
"mean_token_accuracy": 0.15732436180114745,
|
|
"num_tokens": 17206169.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.616800355911255,
|
|
"epoch": 0.7834488552825036,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004944991779935985,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.16231919527053834,
|
|
"num_tokens": 17214607.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.607938623428344,
|
|
"epoch": 0.7838689350976685,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000494492594721334,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.16268193870782852,
|
|
"num_tokens": 17223616.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.702634334564209,
|
|
"epoch": 0.7842890149128334,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004944860075608715,
|
|
"loss": 5.5245,
|
|
"mean_token_accuracy": 0.1614809066057205,
|
|
"num_tokens": 17232729.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.658515548706054,
|
|
"epoch": 0.7847090947279983,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004944794165123272,
|
|
"loss": 5.5865,
|
|
"mean_token_accuracy": 0.16026565730571746,
|
|
"num_tokens": 17242128.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.650646591186524,
|
|
"epoch": 0.7851291745431632,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000494472821575818,
|
|
"loss": 5.4782,
|
|
"mean_token_accuracy": 0.16116299331188202,
|
|
"num_tokens": 17250806.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.776854419708252,
|
|
"epoch": 0.7855492543583281,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004944662227514609,
|
|
"loss": 5.722,
|
|
"mean_token_accuracy": 0.14963266700506211,
|
|
"num_tokens": 17260888.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.670192575454712,
|
|
"epoch": 0.785969334173493,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004944596200393726,
|
|
"loss": 5.4813,
|
|
"mean_token_accuracy": 0.16274381577968597,
|
|
"num_tokens": 17270387.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.671835851669312,
|
|
"epoch": 0.7863894139886578,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004944530134396702,
|
|
"loss": 5.5314,
|
|
"mean_token_accuracy": 0.16092900931835175,
|
|
"num_tokens": 17279866.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.621250009536743,
|
|
"epoch": 0.7868094938038227,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004944464029524707,
|
|
"loss": 5.5052,
|
|
"mean_token_accuracy": 0.161967870593071,
|
|
"num_tokens": 17289233.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.738542604446411,
|
|
"epoch": 0.7872295736189876,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000494439788577891,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.15567109882831573,
|
|
"num_tokens": 17298705.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.732174921035766,
|
|
"epoch": 0.7876496534341525,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004944331703160486,
|
|
"loss": 5.549,
|
|
"mean_token_accuracy": 0.1578393891453743,
|
|
"num_tokens": 17307793.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.651821613311768,
|
|
"epoch": 0.7880697332493174,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004944265481670605,
|
|
"loss": 5.6218,
|
|
"mean_token_accuracy": 0.15234800577163696,
|
|
"num_tokens": 17318248.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.704642677307129,
|
|
"epoch": 0.7884898130644823,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004944199221310441,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.15532419532537461,
|
|
"num_tokens": 17327281.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.700555324554443,
|
|
"epoch": 0.7889098928796471,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004944132922081168,
|
|
"loss": 5.5445,
|
|
"mean_token_accuracy": 0.16321972906589508,
|
|
"num_tokens": 17336805.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.66338005065918,
|
|
"epoch": 0.789329972694812,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004944066583983961,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.15633855164051055,
|
|
"num_tokens": 17346024.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.653223037719727,
|
|
"epoch": 0.7897500525099769,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004944000207019992,
|
|
"loss": 5.5732,
|
|
"mean_token_accuracy": 0.15641905665397643,
|
|
"num_tokens": 17355100.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.753649759292602,
|
|
"epoch": 0.7901701323251418,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004943933791190441,
|
|
"loss": 5.6113,
|
|
"mean_token_accuracy": 0.1497926726937294,
|
|
"num_tokens": 17364769.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.621674108505249,
|
|
"epoch": 0.7905902121403067,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004943867336496482,
|
|
"loss": 5.4727,
|
|
"mean_token_accuracy": 0.16464877128601074,
|
|
"num_tokens": 17374082.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.578705501556397,
|
|
"epoch": 0.7910102919554716,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004943800842939293,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16334666460752487,
|
|
"num_tokens": 17383570.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.728313684463501,
|
|
"epoch": 0.7914303717706365,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000494373431052005,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.1631974011659622,
|
|
"num_tokens": 17392105.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.636175203323364,
|
|
"epoch": 0.7918504515858013,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004943667739239935,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.15721355080604554,
|
|
"num_tokens": 17401363.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.671138334274292,
|
|
"epoch": 0.7922705314009661,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004943601129100125,
|
|
"loss": 5.4985,
|
|
"mean_token_accuracy": 0.16342997252941133,
|
|
"num_tokens": 17411333.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.735333776473999,
|
|
"epoch": 0.792690611216131,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004943534480101801,
|
|
"loss": 5.5707,
|
|
"mean_token_accuracy": 0.16346004083752633,
|
|
"num_tokens": 17421162.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.659286451339722,
|
|
"epoch": 0.793110691031296,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004943467792246142,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16254661232233047,
|
|
"num_tokens": 17430119.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.65619683265686,
|
|
"epoch": 0.7935307708464608,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943401065534332,
|
|
"loss": 5.5137,
|
|
"mean_token_accuracy": 0.15908659845590592,
|
|
"num_tokens": 17439617.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.591221809387207,
|
|
"epoch": 0.7939508506616257,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004943334299967551,
|
|
"loss": 5.6362,
|
|
"mean_token_accuracy": 0.1572137139737606,
|
|
"num_tokens": 17448720.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.676210021972656,
|
|
"epoch": 0.7943709304767906,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004943267495546982,
|
|
"loss": 5.5135,
|
|
"mean_token_accuracy": 0.16351162791252136,
|
|
"num_tokens": 17457458.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.732522106170654,
|
|
"epoch": 0.7947910102919554,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004943200652273809,
|
|
"loss": 5.5481,
|
|
"mean_token_accuracy": 0.16332785785198212,
|
|
"num_tokens": 17467095.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.6177106380462645,
|
|
"epoch": 0.7952110901071203,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004943133770149216,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.15639227479696274,
|
|
"num_tokens": 17476247.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.722067785263062,
|
|
"epoch": 0.7956311699222852,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004943066849174386,
|
|
"loss": 5.5801,
|
|
"mean_token_accuracy": 0.16233462244272232,
|
|
"num_tokens": 17486352.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.737708044052124,
|
|
"epoch": 0.7960512497374501,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004942999889350508,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.15952325612306595,
|
|
"num_tokens": 17495633.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.705710554122925,
|
|
"epoch": 0.796471329552615,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004942932890678765,
|
|
"loss": 5.5931,
|
|
"mean_token_accuracy": 0.1573889285326004,
|
|
"num_tokens": 17504325.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.69957857131958,
|
|
"epoch": 0.7968914093677799,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004942865853160346,
|
|
"loss": 5.5992,
|
|
"mean_token_accuracy": 0.1549372524023056,
|
|
"num_tokens": 17513265.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.726451587677002,
|
|
"epoch": 0.7973114891829448,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004942798776796436,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.15643575862050058,
|
|
"num_tokens": 17522939.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.747159051895141,
|
|
"epoch": 0.7977315689981096,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004942731661588226,
|
|
"loss": 5.6201,
|
|
"mean_token_accuracy": 0.15074056014418602,
|
|
"num_tokens": 17532250.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.744595193862915,
|
|
"epoch": 0.7981516488132745,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004942664507536904,
|
|
"loss": 5.6216,
|
|
"mean_token_accuracy": 0.16153676807880402,
|
|
"num_tokens": 17541368.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.665510129928589,
|
|
"epoch": 0.7985717286284394,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004942597314643659,
|
|
"loss": 5.5775,
|
|
"mean_token_accuracy": 0.15800571888685228,
|
|
"num_tokens": 17550871.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.659941339492798,
|
|
"epoch": 0.7989918084436043,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942530082909681,
|
|
"loss": 5.4959,
|
|
"mean_token_accuracy": 0.1667015627026558,
|
|
"num_tokens": 17559683.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.669128704071045,
|
|
"epoch": 0.7994118882587692,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004942462812336163,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.16116804033517837,
|
|
"num_tokens": 17568877.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.7886709690094,
|
|
"epoch": 0.7998319680739341,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942395502924293,
|
|
"loss": 5.6565,
|
|
"mean_token_accuracy": 0.15164065062999726,
|
|
"num_tokens": 17578202.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.6807924747467045,
|
|
"epoch": 0.800252047889099,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004942328154675268,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.1627306804060936,
|
|
"num_tokens": 17587342.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.630272340774536,
|
|
"epoch": 0.8006721277042638,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004942260767590277,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.16487462520599366,
|
|
"num_tokens": 17595671.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.690436267852784,
|
|
"epoch": 0.8010922075194287,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004942193341670516,
|
|
"loss": 5.6735,
|
|
"mean_token_accuracy": 0.15220091938972474,
|
|
"num_tokens": 17605649.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.691447019577026,
|
|
"epoch": 0.8015122873345936,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004942125876917178,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.15388443917036057,
|
|
"num_tokens": 17615286.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.613958406448364,
|
|
"epoch": 0.8019323671497585,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000494205837333146,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.1583222895860672,
|
|
"num_tokens": 17624583.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.717194938659668,
|
|
"epoch": 0.8023524469649234,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004941990830914557,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16425732970237733,
|
|
"num_tokens": 17633894.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.757351922988891,
|
|
"epoch": 0.8027725267800883,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004941923249667663,
|
|
"loss": 5.6131,
|
|
"mean_token_accuracy": 0.15476072132587432,
|
|
"num_tokens": 17643172.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.701081371307373,
|
|
"epoch": 0.803192606595253,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004941855629591979,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.15671369135379792,
|
|
"num_tokens": 17651901.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.622681045532227,
|
|
"epoch": 0.8036126864104179,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004941787970688701,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.16184851676225662,
|
|
"num_tokens": 17660806.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.761856603622436,
|
|
"epoch": 0.8040327662255828,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941720272959027,
|
|
"loss": 5.5699,
|
|
"mean_token_accuracy": 0.16645232439041138,
|
|
"num_tokens": 17669157.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.619096279144287,
|
|
"epoch": 0.8044528460407477,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004941652536404157,
|
|
"loss": 5.4943,
|
|
"mean_token_accuracy": 0.15924308001995086,
|
|
"num_tokens": 17678664.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.673613357543945,
|
|
"epoch": 0.8048729258559126,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004941584761025291,
|
|
"loss": 5.5281,
|
|
"mean_token_accuracy": 0.1605657756328583,
|
|
"num_tokens": 17688252.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.641302871704101,
|
|
"epoch": 0.8052930056710775,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000494151694682363,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.16418962329626083,
|
|
"num_tokens": 17696473.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.629877805709839,
|
|
"epoch": 0.8057130854862424,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004941449093800374,
|
|
"loss": 5.5673,
|
|
"mean_token_accuracy": 0.15728162452578545,
|
|
"num_tokens": 17706177.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.620923471450806,
|
|
"epoch": 0.8061331653014072,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004941381201956726,
|
|
"loss": 5.4071,
|
|
"mean_token_accuracy": 0.1691529244184494,
|
|
"num_tokens": 17715355.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.623278331756592,
|
|
"epoch": 0.8065532451165721,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004941313271293889,
|
|
"loss": 5.5008,
|
|
"mean_token_accuracy": 0.16670178472995759,
|
|
"num_tokens": 17724345.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.654106616973877,
|
|
"epoch": 0.806973324931737,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941245301813065,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17143428921699524,
|
|
"num_tokens": 17732805.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.620670795440674,
|
|
"epoch": 0.8073934047469019,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004941177293515459,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.16311821192502976,
|
|
"num_tokens": 17741963.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.5626294136047365,
|
|
"epoch": 0.8078134845620668,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004941109246402275,
|
|
"loss": 5.5126,
|
|
"mean_token_accuracy": 0.15953077971935273,
|
|
"num_tokens": 17751858.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.737004566192627,
|
|
"epoch": 0.8082335643772317,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004941041160474721,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.15390506833791734,
|
|
"num_tokens": 17761152.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.729790878295899,
|
|
"epoch": 0.8086536441923966,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004940973035733999,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.16010648310184478,
|
|
"num_tokens": 17770493.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.743511009216308,
|
|
"epoch": 0.8090737240075614,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004940904872181318,
|
|
"loss": 5.5539,
|
|
"mean_token_accuracy": 0.15472937971353531,
|
|
"num_tokens": 17779871.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.71267032623291,
|
|
"epoch": 0.8094938038227263,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004940836669817887,
|
|
"loss": 5.5842,
|
|
"mean_token_accuracy": 0.15565359741449356,
|
|
"num_tokens": 17788606.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.613599967956543,
|
|
"epoch": 0.8099138836378912,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004940768428644911,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.16102469265460967,
|
|
"num_tokens": 17797458.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.596334409713745,
|
|
"epoch": 0.8103339634530561,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004940700148663601,
|
|
"loss": 5.4564,
|
|
"mean_token_accuracy": 0.1620950683951378,
|
|
"num_tokens": 17806902.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.73327784538269,
|
|
"epoch": 0.810754043268221,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004940631829875165,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.16165916323661805,
|
|
"num_tokens": 17816374.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.712001848220825,
|
|
"epoch": 0.8111741230833859,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004940563472280815,
|
|
"loss": 5.5728,
|
|
"mean_token_accuracy": 0.1657658874988556,
|
|
"num_tokens": 17825267.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.610749959945679,
|
|
"epoch": 0.8115942028985508,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004940495075881761,
|
|
"loss": 5.4791,
|
|
"mean_token_accuracy": 0.16635317206382752,
|
|
"num_tokens": 17834027.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.574903249740601,
|
|
"epoch": 0.8120142827137156,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940426640679214,
|
|
"loss": 5.4839,
|
|
"mean_token_accuracy": 0.1606460615992546,
|
|
"num_tokens": 17843587.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.689661979675293,
|
|
"epoch": 0.8124343625288805,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004940358166674388,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.16242198795080184,
|
|
"num_tokens": 17852284.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.723747253417969,
|
|
"epoch": 0.8128544423440454,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004940289653868494,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.16003253161907197,
|
|
"num_tokens": 17860896.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.5253918170928955,
|
|
"epoch": 0.8132745221592103,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004940221102262747,
|
|
"loss": 5.5117,
|
|
"mean_token_accuracy": 0.15657734125852585,
|
|
"num_tokens": 17870796.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.698360538482666,
|
|
"epoch": 0.8136946019743752,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004940152511858361,
|
|
"loss": 5.588,
|
|
"mean_token_accuracy": 0.15942368805408477,
|
|
"num_tokens": 17880016.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.813475561141968,
|
|
"epoch": 0.81411468178954,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004940083882656551,
|
|
"loss": 5.6518,
|
|
"mean_token_accuracy": 0.15555018186569214,
|
|
"num_tokens": 17889348.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.644897079467773,
|
|
"epoch": 0.814534761604705,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004940015214658532,
|
|
"loss": 5.5043,
|
|
"mean_token_accuracy": 0.1621764436364174,
|
|
"num_tokens": 17898392.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.6429681301116945,
|
|
"epoch": 0.8149548414198697,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004939946507865522,
|
|
"loss": 5.5817,
|
|
"mean_token_accuracy": 0.16317397505044937,
|
|
"num_tokens": 17907141.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.671615123748779,
|
|
"epoch": 0.8153749212350346,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004939877762278737,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.16062404215335846,
|
|
"num_tokens": 17915792.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.751763725280762,
|
|
"epoch": 0.8157950010501995,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004939808977899396,
|
|
"loss": 5.6207,
|
|
"mean_token_accuracy": 0.1522047832608223,
|
|
"num_tokens": 17925603.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.697290706634521,
|
|
"epoch": 0.8162150808653644,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004939740154728716,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.16246933341026307,
|
|
"num_tokens": 17934436.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.676386976242066,
|
|
"epoch": 0.8166351606805293,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004939671292767915,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.17046479880809784,
|
|
"num_tokens": 17942969.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.714960718154908,
|
|
"epoch": 0.8170552404956942,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004939602392018216,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.16091118156909942,
|
|
"num_tokens": 17952053.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.675097370147705,
|
|
"epoch": 0.817475320310859,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004939533452480839,
|
|
"loss": 5.5554,
|
|
"mean_token_accuracy": 0.1619985356926918,
|
|
"num_tokens": 17960707.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.7456968307495115,
|
|
"epoch": 0.8178954001260239,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004939464474157003,
|
|
"loss": 5.6414,
|
|
"mean_token_accuracy": 0.1500391572713852,
|
|
"num_tokens": 17971035.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.731802082061767,
|
|
"epoch": 0.8183154799411888,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004939395457047932,
|
|
"loss": 5.5165,
|
|
"mean_token_accuracy": 0.15629953145980835,
|
|
"num_tokens": 17980656.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.7165204048156735,
|
|
"epoch": 0.8187355597563537,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004939326401154847,
|
|
"loss": 5.5595,
|
|
"mean_token_accuracy": 0.15109186619520187,
|
|
"num_tokens": 17990977.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.62971863746643,
|
|
"epoch": 0.8191556395715186,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004939257306478973,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.16121531277894974,
|
|
"num_tokens": 18000186.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.70962438583374,
|
|
"epoch": 0.8195757193866835,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004939188173021532,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.1581372946500778,
|
|
"num_tokens": 18010269.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.664460325241089,
|
|
"epoch": 0.8199957992018484,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004939119000783751,
|
|
"loss": 5.472,
|
|
"mean_token_accuracy": 0.1687139466404915,
|
|
"num_tokens": 18018461.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.625735569000244,
|
|
"epoch": 0.8204158790170132,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004939049789766855,
|
|
"loss": 5.4871,
|
|
"mean_token_accuracy": 0.1622154951095581,
|
|
"num_tokens": 18027173.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.623517990112305,
|
|
"epoch": 0.8208359588321781,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004938980539972068,
|
|
"loss": 5.5813,
|
|
"mean_token_accuracy": 0.15948344767093658,
|
|
"num_tokens": 18036791.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.608444881439209,
|
|
"epoch": 0.821256038647343,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004938911251400617,
|
|
"loss": 5.5246,
|
|
"mean_token_accuracy": 0.16499666422605513,
|
|
"num_tokens": 18046908.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.666135549545288,
|
|
"epoch": 0.8216761184625079,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004938841924053731,
|
|
"loss": 5.4648,
|
|
"mean_token_accuracy": 0.16549027860164642,
|
|
"num_tokens": 18055825.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.765940713882446,
|
|
"epoch": 0.8220961982776728,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004938772557932637,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.1571800611913204,
|
|
"num_tokens": 18065334.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.630688571929932,
|
|
"epoch": 0.8225162780928377,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004938703153038565,
|
|
"loss": 5.4912,
|
|
"mean_token_accuracy": 0.16764561533927919,
|
|
"num_tokens": 18073999.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.563945531845093,
|
|
"epoch": 0.8229363579080026,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004938633709372744,
|
|
"loss": 5.5292,
|
|
"mean_token_accuracy": 0.15778465792536736,
|
|
"num_tokens": 18083665.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.66337776184082,
|
|
"epoch": 0.8233564377231674,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004938564226936403,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16438312083482742,
|
|
"num_tokens": 18092501.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.64669451713562,
|
|
"epoch": 0.8237765175383323,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004938494705730773,
|
|
"loss": 5.5221,
|
|
"mean_token_accuracy": 0.15949836522340774,
|
|
"num_tokens": 18101320.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.626850128173828,
|
|
"epoch": 0.8241965973534972,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004938425145757087,
|
|
"loss": 5.5371,
|
|
"mean_token_accuracy": 0.15716064274311065,
|
|
"num_tokens": 18110190.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.680644369125366,
|
|
"epoch": 0.824616677168662,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004938355547016577,
|
|
"loss": 5.5127,
|
|
"mean_token_accuracy": 0.16249138861894608,
|
|
"num_tokens": 18119301.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.7193972110748295,
|
|
"epoch": 0.825036756983827,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004938285909510474,
|
|
"loss": 5.5758,
|
|
"mean_token_accuracy": 0.1582377091050148,
|
|
"num_tokens": 18128959.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.6662201404571535,
|
|
"epoch": 0.8254568367989918,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004938216233240014,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.1582813560962677,
|
|
"num_tokens": 18138156.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.727919578552246,
|
|
"epoch": 0.8258769166141567,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.000493814651820643,
|
|
"loss": 5.585,
|
|
"mean_token_accuracy": 0.15460814982652665,
|
|
"num_tokens": 18147244.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.665496778488159,
|
|
"epoch": 0.8262969964293215,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004938076764410956,
|
|
"loss": 5.5885,
|
|
"mean_token_accuracy": 0.15983546376228333,
|
|
"num_tokens": 18156040.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.732932662963867,
|
|
"epoch": 0.8267170762444864,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000493800697185483,
|
|
"loss": 5.517,
|
|
"mean_token_accuracy": 0.1574488326907158,
|
|
"num_tokens": 18165210.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.734502363204956,
|
|
"epoch": 0.8271371560596513,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004937937140539288,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.15782398730516434,
|
|
"num_tokens": 18174841.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.62280797958374,
|
|
"epoch": 0.8275572358748162,
|
|
"grad_norm": 2.78125,
|
|
"learning_rate": 0.0004937867270465564,
|
|
"loss": 5.4522,
|
|
"mean_token_accuracy": 0.16294290423393248,
|
|
"num_tokens": 18184112.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.742010974884034,
|
|
"epoch": 0.8279773156899811,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004937797361634899,
|
|
"loss": 5.6596,
|
|
"mean_token_accuracy": 0.15312351733446122,
|
|
"num_tokens": 18193564.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.61360445022583,
|
|
"epoch": 0.828397395505146,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000493772741404853,
|
|
"loss": 5.3811,
|
|
"mean_token_accuracy": 0.1657651409506798,
|
|
"num_tokens": 18202836.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.662469673156738,
|
|
"epoch": 0.8288174753203108,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004937657427707698,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.17115799337625504,
|
|
"num_tokens": 18212098.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.703630208969116,
|
|
"epoch": 0.8292375551354757,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004937587402613639,
|
|
"loss": 5.5471,
|
|
"mean_token_accuracy": 0.16153400242328644,
|
|
"num_tokens": 18221541.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.612545967102051,
|
|
"epoch": 0.8296576349506406,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004937517338767597,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.15903571546077727,
|
|
"num_tokens": 18231015.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.756252431869507,
|
|
"epoch": 0.8300777147658055,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004937447236170811,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.15943876206874846,
|
|
"num_tokens": 18239729.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.7537188053131105,
|
|
"epoch": 0.8304977945809704,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004937377094824523,
|
|
"loss": 5.6072,
|
|
"mean_token_accuracy": 0.15652247965335847,
|
|
"num_tokens": 18249773.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.684403038024902,
|
|
"epoch": 0.8309178743961353,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004937306914729977,
|
|
"loss": 5.5693,
|
|
"mean_token_accuracy": 0.158055904507637,
|
|
"num_tokens": 18259179.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.591420412063599,
|
|
"epoch": 0.8313379542113002,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004937236695888416,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.17210163027048112,
|
|
"num_tokens": 18268164.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.726157283782959,
|
|
"epoch": 0.831758034026465,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004937166438301082,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.16078757047653197,
|
|
"num_tokens": 18276259.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.666176176071167,
|
|
"epoch": 0.8321781138416299,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004937096141969221,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1596865251660347,
|
|
"num_tokens": 18285729.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.763876485824585,
|
|
"epoch": 0.8325981936567948,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004937025806894077,
|
|
"loss": 5.7629,
|
|
"mean_token_accuracy": 0.1466881103813648,
|
|
"num_tokens": 18295873.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.774165105819702,
|
|
"epoch": 0.8330182734719597,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004936955433076899,
|
|
"loss": 5.572,
|
|
"mean_token_accuracy": 0.16771850138902664,
|
|
"num_tokens": 18305135.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.704055881500244,
|
|
"epoch": 0.8334383532871246,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000493688502051893,
|
|
"loss": 5.6165,
|
|
"mean_token_accuracy": 0.15885019153356553,
|
|
"num_tokens": 18314251.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.626564168930054,
|
|
"epoch": 0.8338584331022895,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004936814569221421,
|
|
"loss": 5.4544,
|
|
"mean_token_accuracy": 0.17203571647405624,
|
|
"num_tokens": 18322863.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.6520676612854,
|
|
"epoch": 0.8342785129174544,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004936744079185616,
|
|
"loss": 5.4672,
|
|
"mean_token_accuracy": 0.16363800168037415,
|
|
"num_tokens": 18332129.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.751771402359009,
|
|
"epoch": 0.8346985927326191,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004936673550412767,
|
|
"loss": 5.5544,
|
|
"mean_token_accuracy": 0.1615679681301117,
|
|
"num_tokens": 18341457.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.67233624458313,
|
|
"epoch": 0.835118672547784,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000493660298290412,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.15321808978915213,
|
|
"num_tokens": 18351397.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.660567092895508,
|
|
"epoch": 0.8355387523629489,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004936532376660929,
|
|
"loss": 5.4801,
|
|
"mean_token_accuracy": 0.16411369144916535,
|
|
"num_tokens": 18360005.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.729122304916382,
|
|
"epoch": 0.8359588321781138,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004936461731684442,
|
|
"loss": 5.5685,
|
|
"mean_token_accuracy": 0.1632169410586357,
|
|
"num_tokens": 18369707.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.814248561859131,
|
|
"epoch": 0.8363789119932787,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004936391047975912,
|
|
"loss": 5.6991,
|
|
"mean_token_accuracy": 0.15527767241001128,
|
|
"num_tokens": 18379514.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.689925670623779,
|
|
"epoch": 0.8367989918084436,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004936320325536589,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.16286465376615525,
|
|
"num_tokens": 18388854.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.72346682548523,
|
|
"epoch": 0.8372190716236085,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004936249564367729,
|
|
"loss": 5.5954,
|
|
"mean_token_accuracy": 0.15776865184307098,
|
|
"num_tokens": 18397806.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.619910860061646,
|
|
"epoch": 0.8376391514387733,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004936178764470583,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.16496019810438156,
|
|
"num_tokens": 18406645.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.587065267562866,
|
|
"epoch": 0.8380592312539382,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004936107925846405,
|
|
"loss": 5.4584,
|
|
"mean_token_accuracy": 0.16309986114501954,
|
|
"num_tokens": 18415730.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.6642388820648195,
|
|
"epoch": 0.8384793110691031,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004936037048496452,
|
|
"loss": 5.5638,
|
|
"mean_token_accuracy": 0.16353996396064757,
|
|
"num_tokens": 18424638.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.693403434753418,
|
|
"epoch": 0.838899390884268,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004935966132421977,
|
|
"loss": 5.6035,
|
|
"mean_token_accuracy": 0.15765634179115295,
|
|
"num_tokens": 18434090.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.589950704574585,
|
|
"epoch": 0.8393194706994329,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004935895177624239,
|
|
"loss": 5.4491,
|
|
"mean_token_accuracy": 0.16379072219133378,
|
|
"num_tokens": 18442965.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.756886720657349,
|
|
"epoch": 0.8397395505145978,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004935824184104493,
|
|
"loss": 5.4814,
|
|
"mean_token_accuracy": 0.1661657601594925,
|
|
"num_tokens": 18451553.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.6218055248260494,
|
|
"epoch": 0.8401596303297627,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004935753151863997,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.15614725649356842,
|
|
"num_tokens": 18461325.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.705133724212646,
|
|
"epoch": 0.8405797101449275,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004935682080904009,
|
|
"loss": 5.5278,
|
|
"mean_token_accuracy": 0.16865952163934708,
|
|
"num_tokens": 18469977.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.704347705841064,
|
|
"epoch": 0.8409997899600924,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004935610971225789,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16329597383737565,
|
|
"num_tokens": 18479534.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.642335319519043,
|
|
"epoch": 0.8414198697752573,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004935539822830597,
|
|
"loss": 5.6098,
|
|
"mean_token_accuracy": 0.15342649221420288,
|
|
"num_tokens": 18488800.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.700902891159058,
|
|
"epoch": 0.8418399495904222,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000493546863571969,
|
|
"loss": 5.5783,
|
|
"mean_token_accuracy": 0.16182019114494323,
|
|
"num_tokens": 18498083.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.679955768585205,
|
|
"epoch": 0.8422600294055871,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004935397409894333,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.15353272706270218,
|
|
"num_tokens": 18508265.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.6730622291564945,
|
|
"epoch": 0.842680109220752,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004935326145355787,
|
|
"loss": 5.5537,
|
|
"mean_token_accuracy": 0.1579386070370674,
|
|
"num_tokens": 18517283.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.7045755863189695,
|
|
"epoch": 0.8431001890359168,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004935254842105311,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.16146936714649202,
|
|
"num_tokens": 18526482.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.603598499298096,
|
|
"epoch": 0.8435202688510817,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004935183500144173,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.1751741036772728,
|
|
"num_tokens": 18536150.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.746985244750976,
|
|
"epoch": 0.8439403486662466,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004935112119473634,
|
|
"loss": 5.6208,
|
|
"mean_token_accuracy": 0.15574218332767487,
|
|
"num_tokens": 18545168.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.681631946563721,
|
|
"epoch": 0.8443604284814115,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004935040700094959,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.16096032857894899,
|
|
"num_tokens": 18553363.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.609125709533691,
|
|
"epoch": 0.8447805082965764,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004934969242009412,
|
|
"loss": 5.4781,
|
|
"mean_token_accuracy": 0.16653624624013902,
|
|
"num_tokens": 18562546.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.635621118545532,
|
|
"epoch": 0.8452005881117413,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004934897745218262,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.1550781711935997,
|
|
"num_tokens": 18572149.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.681614828109741,
|
|
"epoch": 0.8456206679269062,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004934826209722772,
|
|
"loss": 5.42,
|
|
"mean_token_accuracy": 0.16919473558664322,
|
|
"num_tokens": 18580842.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.661826229095459,
|
|
"epoch": 0.8460407477420709,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004934754635524211,
|
|
"loss": 5.5272,
|
|
"mean_token_accuracy": 0.15960330069065093,
|
|
"num_tokens": 18589765.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.664134693145752,
|
|
"epoch": 0.8464608275572358,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004934683022623847,
|
|
"loss": 5.5449,
|
|
"mean_token_accuracy": 0.15602806955575943,
|
|
"num_tokens": 18599532.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.598707628250122,
|
|
"epoch": 0.8468809073724007,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004934611371022947,
|
|
"loss": 5.4394,
|
|
"mean_token_accuracy": 0.16422633677721024,
|
|
"num_tokens": 18608438.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.69066367149353,
|
|
"epoch": 0.8473009871875656,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004934539680722783,
|
|
"loss": 5.596,
|
|
"mean_token_accuracy": 0.15671277940273284,
|
|
"num_tokens": 18617313.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.6565409183502195,
|
|
"epoch": 0.8477210670027305,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004934467951724622,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.1600039303302765,
|
|
"num_tokens": 18625880.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.683764934539795,
|
|
"epoch": 0.8481411468178954,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004934396184029737,
|
|
"loss": 5.5012,
|
|
"mean_token_accuracy": 0.1638655111193657,
|
|
"num_tokens": 18635727.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.644234943389892,
|
|
"epoch": 0.8485612266330603,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004934324377639398,
|
|
"loss": 5.5692,
|
|
"mean_token_accuracy": 0.15685787945985794,
|
|
"num_tokens": 18645619.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.63275990486145,
|
|
"epoch": 0.8489813064482251,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004934252532554878,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.1624760612845421,
|
|
"num_tokens": 18654901.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.754931497573852,
|
|
"epoch": 0.84940138626339,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004934180648777449,
|
|
"loss": 5.7184,
|
|
"mean_token_accuracy": 0.15616895407438278,
|
|
"num_tokens": 18664523.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.690887594223023,
|
|
"epoch": 0.8498214660785549,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004934108726308384,
|
|
"loss": 5.5559,
|
|
"mean_token_accuracy": 0.154204061627388,
|
|
"num_tokens": 18673685.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.676758527755737,
|
|
"epoch": 0.8502415458937198,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004934036765148958,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.15912752598524094,
|
|
"num_tokens": 18682889.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.700036525726318,
|
|
"epoch": 0.8506616257088847,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004933964765300446,
|
|
"loss": 5.5619,
|
|
"mean_token_accuracy": 0.15744878649711608,
|
|
"num_tokens": 18692978.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.651540040969849,
|
|
"epoch": 0.8510817055240496,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000493389272676412,
|
|
"loss": 5.485,
|
|
"mean_token_accuracy": 0.16274063736200334,
|
|
"num_tokens": 18701846.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.673055028915405,
|
|
"epoch": 0.8515017853392145,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004933820649541262,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.1706227630376816,
|
|
"num_tokens": 18711492.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.60514988899231,
|
|
"epoch": 0.8519218651543793,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004933748533633145,
|
|
"loss": 5.4485,
|
|
"mean_token_accuracy": 0.16744111329317093,
|
|
"num_tokens": 18720407.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.625371885299683,
|
|
"epoch": 0.8523419449695442,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004933676379041045,
|
|
"loss": 5.5183,
|
|
"mean_token_accuracy": 0.16600939780473709,
|
|
"num_tokens": 18729968.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.72891936302185,
|
|
"epoch": 0.8527620247847091,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004933604185766245,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.151386359333992,
|
|
"num_tokens": 18739525.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.730268430709839,
|
|
"epoch": 0.853182104599874,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004933531953810019,
|
|
"loss": 5.5,
|
|
"mean_token_accuracy": 0.16777922809123993,
|
|
"num_tokens": 18749087.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.7163464546203615,
|
|
"epoch": 0.8536021844150389,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004933459683173652,
|
|
"loss": 5.5329,
|
|
"mean_token_accuracy": 0.16302687674760818,
|
|
"num_tokens": 18758174.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.709117221832275,
|
|
"epoch": 0.8540222642302038,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004933387373858418,
|
|
"loss": 5.5632,
|
|
"mean_token_accuracy": 0.16024067923426627,
|
|
"num_tokens": 18767679.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.670746326446533,
|
|
"epoch": 0.8544423440453687,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004933315025865602,
|
|
"loss": 5.4889,
|
|
"mean_token_accuracy": 0.1621965780854225,
|
|
"num_tokens": 18776749.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.770751142501831,
|
|
"epoch": 0.8548624238605335,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004933242639196485,
|
|
"loss": 5.6762,
|
|
"mean_token_accuracy": 0.1487576313316822,
|
|
"num_tokens": 18786313.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.775333738327026,
|
|
"epoch": 0.8552825036756984,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004933170213852348,
|
|
"loss": 5.55,
|
|
"mean_token_accuracy": 0.15689792037010192,
|
|
"num_tokens": 18795340.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.641742849349976,
|
|
"epoch": 0.8557025834908633,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004933097749834476,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.1572565406560898,
|
|
"num_tokens": 18804114.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.663312005996704,
|
|
"epoch": 0.8561226633060282,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493302524714415,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.15901609212160112,
|
|
"num_tokens": 18813797.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.7054831981658936,
|
|
"epoch": 0.856542743121193,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004932952705782657,
|
|
"loss": 5.5388,
|
|
"mean_token_accuracy": 0.15331775918602944,
|
|
"num_tokens": 18822410.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.615892791748047,
|
|
"epoch": 0.856962822936358,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000493288012575128,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.16814546436071395,
|
|
"num_tokens": 18832091.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.661955499649048,
|
|
"epoch": 0.8573829027515227,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004932807507051307,
|
|
"loss": 5.5082,
|
|
"mean_token_accuracy": 0.1563362330198288,
|
|
"num_tokens": 18841298.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.606261587142944,
|
|
"epoch": 0.8578029825666876,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004932734849684022,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.1604735642671585,
|
|
"num_tokens": 18849683.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.6841357231140135,
|
|
"epoch": 0.8582230623818525,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004932662153650712,
|
|
"loss": 5.4177,
|
|
"mean_token_accuracy": 0.16244781017303467,
|
|
"num_tokens": 18858832.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.587029647827149,
|
|
"epoch": 0.8586431421970174,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004932589418952668,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.1638034462928772,
|
|
"num_tokens": 18867652.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.739847660064697,
|
|
"epoch": 0.8590632220121823,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004932516645591175,
|
|
"loss": 5.556,
|
|
"mean_token_accuracy": 0.16377656310796737,
|
|
"num_tokens": 18877282.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.71386079788208,
|
|
"epoch": 0.8594833018273472,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004932443833567524,
|
|
"loss": 5.6454,
|
|
"mean_token_accuracy": 0.15882862806320192,
|
|
"num_tokens": 18886565.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.699979639053344,
|
|
"epoch": 0.8599033816425121,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004932370982883003,
|
|
"loss": 5.592,
|
|
"mean_token_accuracy": 0.15794370770454408,
|
|
"num_tokens": 18896440.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.741853284835815,
|
|
"epoch": 0.8603234614576769,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004932298093538905,
|
|
"loss": 5.6174,
|
|
"mean_token_accuracy": 0.15673970580101013,
|
|
"num_tokens": 18906246.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.644249439239502,
|
|
"epoch": 0.8607435412728418,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000493222516553652,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.15427245274186135,
|
|
"num_tokens": 18915108.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.70051212310791,
|
|
"epoch": 0.8611636210880067,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004932152198877139,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.16063451319932937,
|
|
"num_tokens": 18923664.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.675086784362793,
|
|
"epoch": 0.8615837009031716,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004932079193562057,
|
|
"loss": 5.6133,
|
|
"mean_token_accuracy": 0.15742011070251466,
|
|
"num_tokens": 18933496.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.652376413345337,
|
|
"epoch": 0.8620037807183365,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004932006149592564,
|
|
"loss": 5.4804,
|
|
"mean_token_accuracy": 0.16196195781230927,
|
|
"num_tokens": 18942222.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.731272411346436,
|
|
"epoch": 0.8624238605335014,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004931933066969957,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.1656545579433441,
|
|
"num_tokens": 18952057.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.618059682846069,
|
|
"epoch": 0.8628439403486663,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004931859945695528,
|
|
"loss": 5.5597,
|
|
"mean_token_accuracy": 0.15741539001464844,
|
|
"num_tokens": 18961664.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.5474916934967045,
|
|
"epoch": 0.8632640201638311,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004931786785770575,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.17619887590408326,
|
|
"num_tokens": 18969900.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.721754789352417,
|
|
"epoch": 0.863684099978996,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004931713587196392,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.15274747163057328,
|
|
"num_tokens": 18979286.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.7611936092376705,
|
|
"epoch": 0.8641041797941609,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004931640349974275,
|
|
"loss": 5.5237,
|
|
"mean_token_accuracy": 0.15643700286746026,
|
|
"num_tokens": 18987553.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.683358573913575,
|
|
"epoch": 0.8645242596093258,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004931567074105524,
|
|
"loss": 5.6063,
|
|
"mean_token_accuracy": 0.16055196523666382,
|
|
"num_tokens": 18996354.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.577027750015259,
|
|
"epoch": 0.8649443394244907,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004931493759591435,
|
|
"loss": 5.482,
|
|
"mean_token_accuracy": 0.1618887558579445,
|
|
"num_tokens": 19005150.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.68660159111023,
|
|
"epoch": 0.8653644192396556,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004931420406433308,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.1582360938191414,
|
|
"num_tokens": 19014572.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.647102022171021,
|
|
"epoch": 0.8657844990548205,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000493134701463244,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.16853554248809816,
|
|
"num_tokens": 19023462.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.543448066711425,
|
|
"epoch": 0.8662045788699853,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004931273584190135,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.16720159947872162,
|
|
"num_tokens": 19032460.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.588135385513306,
|
|
"epoch": 0.8666246586851502,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004931200115107691,
|
|
"loss": 5.4846,
|
|
"mean_token_accuracy": 0.16485581398010254,
|
|
"num_tokens": 19041734.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.6352677822113035,
|
|
"epoch": 0.867044738500315,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000493112660738641,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.1592483252286911,
|
|
"num_tokens": 19050867.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.646694040298462,
|
|
"epoch": 0.86746481831548,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004931053061027594,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.16102246344089508,
|
|
"num_tokens": 19060518.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.634038686752319,
|
|
"epoch": 0.8678848981306448,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004930979476032546,
|
|
"loss": 5.4614,
|
|
"mean_token_accuracy": 0.164410237967968,
|
|
"num_tokens": 19069588.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.701401090621948,
|
|
"epoch": 0.8683049779458097,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000493090585240257,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.1488155022263527,
|
|
"num_tokens": 19079060.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.603839588165283,
|
|
"epoch": 0.8687250577609746,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004930832190138969,
|
|
"loss": 5.4475,
|
|
"mean_token_accuracy": 0.15975930094718932,
|
|
"num_tokens": 19087721.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.676361989974976,
|
|
"epoch": 0.8691451375761394,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000493075848924305,
|
|
"loss": 5.5022,
|
|
"mean_token_accuracy": 0.15760902911424637,
|
|
"num_tokens": 19096800.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.675476932525635,
|
|
"epoch": 0.8695652173913043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004930684749716117,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.1568011909723282,
|
|
"num_tokens": 19106774.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.688272190093994,
|
|
"epoch": 0.8699852972064692,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004930610971559476,
|
|
"loss": 5.4826,
|
|
"mean_token_accuracy": 0.16367388367652894,
|
|
"num_tokens": 19116413.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.701381874084473,
|
|
"epoch": 0.8704053770216341,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004930537154774436,
|
|
"loss": 5.5157,
|
|
"mean_token_accuracy": 0.159402497112751,
|
|
"num_tokens": 19125363.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.671617269515991,
|
|
"epoch": 0.870825456836799,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004930463299362302,
|
|
"loss": 5.5974,
|
|
"mean_token_accuracy": 0.15096435695886612,
|
|
"num_tokens": 19135461.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.698200702667236,
|
|
"epoch": 0.8712455366519639,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004930389405324383,
|
|
"loss": 5.4737,
|
|
"mean_token_accuracy": 0.16709906607866287,
|
|
"num_tokens": 19144085.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.6751556396484375,
|
|
"epoch": 0.8716656164671287,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004930315472661987,
|
|
"loss": 5.4761,
|
|
"mean_token_accuracy": 0.16794967502355576,
|
|
"num_tokens": 19153291.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.637331962585449,
|
|
"epoch": 0.8720856962822936,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004930241501376428,
|
|
"loss": 5.4874,
|
|
"mean_token_accuracy": 0.16048841327428817,
|
|
"num_tokens": 19163514.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.541778802871704,
|
|
"epoch": 0.8725057760974585,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004930167491469013,
|
|
"loss": 5.3944,
|
|
"mean_token_accuracy": 0.16507934480905534,
|
|
"num_tokens": 19172103.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.616076421737671,
|
|
"epoch": 0.8729258559126234,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004930093442941053,
|
|
"loss": 5.4627,
|
|
"mean_token_accuracy": 0.16135224401950837,
|
|
"num_tokens": 19180893.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.616441106796264,
|
|
"epoch": 0.8733459357277883,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004930019355793858,
|
|
"loss": 5.3856,
|
|
"mean_token_accuracy": 0.16465070396661757,
|
|
"num_tokens": 19190495.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.613911056518555,
|
|
"epoch": 0.8737660155429532,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004929945230028746,
|
|
"loss": 5.4796,
|
|
"mean_token_accuracy": 0.16515476107597352,
|
|
"num_tokens": 19198988.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.563373661041259,
|
|
"epoch": 0.8741860953581181,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004929871065647024,
|
|
"loss": 5.3916,
|
|
"mean_token_accuracy": 0.1638674646615982,
|
|
"num_tokens": 19208014.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.694887781143189,
|
|
"epoch": 0.8746061751732829,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004929796862650011,
|
|
"loss": 5.5893,
|
|
"mean_token_accuracy": 0.1591682493686676,
|
|
"num_tokens": 19218220.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.64337854385376,
|
|
"epoch": 0.8750262549884478,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004929722621039018,
|
|
"loss": 5.4937,
|
|
"mean_token_accuracy": 0.16073654294013978,
|
|
"num_tokens": 19227176.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.585389709472656,
|
|
"epoch": 0.8754463348036127,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004929648340815362,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.15821082442998885,
|
|
"num_tokens": 19236085.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.637318229675293,
|
|
"epoch": 0.8758664146187776,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004929574021980355,
|
|
"loss": 5.5567,
|
|
"mean_token_accuracy": 0.1564241960644722,
|
|
"num_tokens": 19246671.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.614260578155518,
|
|
"epoch": 0.8762864944339425,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004929499664535319,
|
|
"loss": 5.4661,
|
|
"mean_token_accuracy": 0.15873886793851852,
|
|
"num_tokens": 19256321.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.670866823196411,
|
|
"epoch": 0.8767065742491074,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004929425268481569,
|
|
"loss": 5.4349,
|
|
"mean_token_accuracy": 0.16390531361103058,
|
|
"num_tokens": 19265518.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.6090500831604,
|
|
"epoch": 0.8771266540642723,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004929350833820422,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1625059276819229,
|
|
"num_tokens": 19274120.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.675984525680542,
|
|
"epoch": 0.877546733879437,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004929276360553197,
|
|
"loss": 5.5116,
|
|
"mean_token_accuracy": 0.16215913146734237,
|
|
"num_tokens": 19284377.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.569582605361939,
|
|
"epoch": 0.8779668136946019,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004929201848681213,
|
|
"loss": 5.3817,
|
|
"mean_token_accuracy": 0.1601586326956749,
|
|
"num_tokens": 19293326.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.556849384307862,
|
|
"epoch": 0.8783868935097668,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004929127298205792,
|
|
"loss": 5.4279,
|
|
"mean_token_accuracy": 0.17152911871671678,
|
|
"num_tokens": 19302086.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.7007475852966305,
|
|
"epoch": 0.8788069733249317,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004929052709128251,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.1675509050488472,
|
|
"num_tokens": 19310124.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.588010692596436,
|
|
"epoch": 0.8792270531400966,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004928978081449914,
|
|
"loss": 5.4754,
|
|
"mean_token_accuracy": 0.16137903779745102,
|
|
"num_tokens": 19321269.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.652129220962524,
|
|
"epoch": 0.8796471329552615,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004928903415172103,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.163689923286438,
|
|
"num_tokens": 19330390.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.647299528121948,
|
|
"epoch": 0.8800672127704264,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000492882871029614,
|
|
"loss": 5.4939,
|
|
"mean_token_accuracy": 0.1618855006992817,
|
|
"num_tokens": 19339457.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.659735584259034,
|
|
"epoch": 0.8804872925855912,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004928753966823348,
|
|
"loss": 5.5482,
|
|
"mean_token_accuracy": 0.15688573122024535,
|
|
"num_tokens": 19348710.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.697210121154785,
|
|
"epoch": 0.8809073724007561,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004928679184755051,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.16629291623830794,
|
|
"num_tokens": 19357215.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.661016321182251,
|
|
"epoch": 0.881327452215921,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004928604364092574,
|
|
"loss": 5.5224,
|
|
"mean_token_accuracy": 0.16313585191965102,
|
|
"num_tokens": 19366043.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.675441455841065,
|
|
"epoch": 0.8817475320310859,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004928529504837243,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.15857910960912705,
|
|
"num_tokens": 19375468.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.799028491973877,
|
|
"epoch": 0.8821676118462508,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004928454606990383,
|
|
"loss": 5.4609,
|
|
"mean_token_accuracy": 0.1582179293036461,
|
|
"num_tokens": 19384467.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.642581987380981,
|
|
"epoch": 0.8825876916614157,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004928379670553322,
|
|
"loss": 5.5019,
|
|
"mean_token_accuracy": 0.1664658784866333,
|
|
"num_tokens": 19393618.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.677177000045776,
|
|
"epoch": 0.8830077714765806,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004928304695527387,
|
|
"loss": 5.565,
|
|
"mean_token_accuracy": 0.160389643907547,
|
|
"num_tokens": 19402921.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.731782722473144,
|
|
"epoch": 0.8834278512917454,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004928229681913905,
|
|
"loss": 5.5457,
|
|
"mean_token_accuracy": 0.16324697136878968,
|
|
"num_tokens": 19412048.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.733268880844117,
|
|
"epoch": 0.8838479311069103,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004928154629714207,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.16145433783531188,
|
|
"num_tokens": 19420993.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.6000950813293455,
|
|
"epoch": 0.8842680109220752,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000492807953892962,
|
|
"loss": 5.5009,
|
|
"mean_token_accuracy": 0.15950000733137132,
|
|
"num_tokens": 19430145.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.610482597351075,
|
|
"epoch": 0.8846880907372401,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004928004409561476,
|
|
"loss": 5.4,
|
|
"mean_token_accuracy": 0.16498225480318068,
|
|
"num_tokens": 19438918.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.56955246925354,
|
|
"epoch": 0.885108170552405,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004927929241611106,
|
|
"loss": 5.4581,
|
|
"mean_token_accuracy": 0.16881955415010452,
|
|
"num_tokens": 19448490.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.623895931243896,
|
|
"epoch": 0.8855282503675699,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000492785403507984,
|
|
"loss": 5.5227,
|
|
"mean_token_accuracy": 0.1571098670363426,
|
|
"num_tokens": 19457098.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.634610605239868,
|
|
"epoch": 0.8859483301827347,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004927778789969012,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.1569845736026764,
|
|
"num_tokens": 19466419.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.628296756744385,
|
|
"epoch": 0.8863684099978996,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004927703506279955,
|
|
"loss": 5.5628,
|
|
"mean_token_accuracy": 0.15323089063167572,
|
|
"num_tokens": 19475882.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.80163049697876,
|
|
"epoch": 0.8867884898130645,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004927628184014,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.159140382707119,
|
|
"num_tokens": 19485917.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.71609354019165,
|
|
"epoch": 0.8872085696282294,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004927552823172483,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.15823422372341156,
|
|
"num_tokens": 19494984.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.688808917999268,
|
|
"epoch": 0.8876286494433943,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000492747742375674,
|
|
"loss": 5.4744,
|
|
"mean_token_accuracy": 0.16675125807523727,
|
|
"num_tokens": 19504087.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.661811017990113,
|
|
"epoch": 0.8880487292585592,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004927401985768106,
|
|
"loss": 5.4992,
|
|
"mean_token_accuracy": 0.1689751848578453,
|
|
"num_tokens": 19512880.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.592242431640625,
|
|
"epoch": 0.888468809073724,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004927326509207915,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.16463636606931686,
|
|
"num_tokens": 19521723.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.759501934051514,
|
|
"epoch": 0.8888888888888888,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004927250994077508,
|
|
"loss": 5.5706,
|
|
"mean_token_accuracy": 0.16017245650291442,
|
|
"num_tokens": 19531352.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.75401029586792,
|
|
"epoch": 0.8893089687040537,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000492717544037822,
|
|
"loss": 5.6714,
|
|
"mean_token_accuracy": 0.16674605160951614,
|
|
"num_tokens": 19540943.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.614908599853516,
|
|
"epoch": 0.8897290485192186,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000492709984811139,
|
|
"loss": 5.4374,
|
|
"mean_token_accuracy": 0.16738452166318893,
|
|
"num_tokens": 19550527.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.6367579936981205,
|
|
"epoch": 0.8901491283343835,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004927024217278358,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.17424334436655045,
|
|
"num_tokens": 19559746.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.73973593711853,
|
|
"epoch": 0.8905692081495484,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004926948547880462,
|
|
"loss": 5.6008,
|
|
"mean_token_accuracy": 0.15189019665122033,
|
|
"num_tokens": 19569286.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.646059894561768,
|
|
"epoch": 0.8909892879647133,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004926872839919044,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.1616295322775841,
|
|
"num_tokens": 19578245.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.602351570129395,
|
|
"epoch": 0.8914093677798782,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004926797093395446,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.16678168177604674,
|
|
"num_tokens": 19587244.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.681618118286133,
|
|
"epoch": 0.891829447595043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004926721308311006,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.16693350076675414,
|
|
"num_tokens": 19596932.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.768650531768799,
|
|
"epoch": 0.8922495274102079,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004926645484667069,
|
|
"loss": 5.6125,
|
|
"mean_token_accuracy": 0.15693477988243104,
|
|
"num_tokens": 19606256.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.757310009002685,
|
|
"epoch": 0.8926696072253728,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004926569622464979,
|
|
"loss": 5.6243,
|
|
"mean_token_accuracy": 0.16205553114414215,
|
|
"num_tokens": 19615726.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.676463174819946,
|
|
"epoch": 0.8930896870405377,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004926493721706079,
|
|
"loss": 5.4859,
|
|
"mean_token_accuracy": 0.16073908805847167,
|
|
"num_tokens": 19624037.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.684830141067505,
|
|
"epoch": 0.8935097668557026,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004926417782391713,
|
|
"loss": 5.4641,
|
|
"mean_token_accuracy": 0.16800618469715117,
|
|
"num_tokens": 19632882.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.714396047592163,
|
|
"epoch": 0.8939298466708675,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004926341804523227,
|
|
"loss": 5.5903,
|
|
"mean_token_accuracy": 0.1597953498363495,
|
|
"num_tokens": 19642686.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.656919050216675,
|
|
"epoch": 0.8943499264860324,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004926265788101966,
|
|
"loss": 5.5042,
|
|
"mean_token_accuracy": 0.16232740730047227,
|
|
"num_tokens": 19651380.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.629188060760498,
|
|
"epoch": 0.8947700063011972,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004926189733129278,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.16030899584293365,
|
|
"num_tokens": 19660136.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.602889823913574,
|
|
"epoch": 0.8951900861163621,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004926113639606509,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.17339837849140166,
|
|
"num_tokens": 19669146.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.749970960617065,
|
|
"epoch": 0.895610165931527,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004926037507535008,
|
|
"loss": 5.5953,
|
|
"mean_token_accuracy": 0.1565776377916336,
|
|
"num_tokens": 19678627.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.68851056098938,
|
|
"epoch": 0.8960302457466919,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004925961336916122,
|
|
"loss": 5.5335,
|
|
"mean_token_accuracy": 0.16348532289266587,
|
|
"num_tokens": 19688033.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.685422372817993,
|
|
"epoch": 0.8964503255618568,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004925885127751202,
|
|
"loss": 5.5441,
|
|
"mean_token_accuracy": 0.1624837875366211,
|
|
"num_tokens": 19696523.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.724574613571167,
|
|
"epoch": 0.8968704053770217,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004925808880041596,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.1627603441476822,
|
|
"num_tokens": 19706339.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.6943115234375,
|
|
"epoch": 0.8972904851921865,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004925732593788658,
|
|
"loss": 5.4997,
|
|
"mean_token_accuracy": 0.15886156111955643,
|
|
"num_tokens": 19714779.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.638199138641357,
|
|
"epoch": 0.8977105650073514,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004925656268993737,
|
|
"loss": 5.5523,
|
|
"mean_token_accuracy": 0.16095577031373978,
|
|
"num_tokens": 19723727.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.653303480148315,
|
|
"epoch": 0.8981306448225163,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004925579905658185,
|
|
"loss": 5.5389,
|
|
"mean_token_accuracy": 0.16392706334590912,
|
|
"num_tokens": 19732783.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.677282476425171,
|
|
"epoch": 0.8985507246376812,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004925503503783355,
|
|
"loss": 5.4975,
|
|
"mean_token_accuracy": 0.15634912848472596,
|
|
"num_tokens": 19741268.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.6636802673339846,
|
|
"epoch": 0.898970804452846,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004925427063370601,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.16585467010736465,
|
|
"num_tokens": 19751490.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.662887954711914,
|
|
"epoch": 0.899390884268011,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004925350584421278,
|
|
"loss": 5.4835,
|
|
"mean_token_accuracy": 0.16281237900257112,
|
|
"num_tokens": 19760487.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.680135250091553,
|
|
"epoch": 0.8998109640831758,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004925274066936738,
|
|
"loss": 5.4377,
|
|
"mean_token_accuracy": 0.16982365995645524,
|
|
"num_tokens": 19768984.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.600447034835815,
|
|
"epoch": 0.9002310438983406,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004925197510918339,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.1686476871371269,
|
|
"num_tokens": 19778335.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.654651784896851,
|
|
"epoch": 0.9006511237135055,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004925120916367435,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.1537408173084259,
|
|
"num_tokens": 19789082.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.627911615371704,
|
|
"epoch": 0.9010712035286704,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004925044283285384,
|
|
"loss": 5.3205,
|
|
"mean_token_accuracy": 0.17863296270370482,
|
|
"num_tokens": 19797902.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.527833461761475,
|
|
"epoch": 0.9014912833438353,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004924967611673544,
|
|
"loss": 5.4749,
|
|
"mean_token_accuracy": 0.16872860938310624,
|
|
"num_tokens": 19806481.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.541446256637573,
|
|
"epoch": 0.9019113631590002,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004924890901533273,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.17880219370126724,
|
|
"num_tokens": 19815226.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.774983835220337,
|
|
"epoch": 0.9023314429741651,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004924814152865929,
|
|
"loss": 5.5806,
|
|
"mean_token_accuracy": 0.15592661499977112,
|
|
"num_tokens": 19824577.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.661573457717895,
|
|
"epoch": 0.90275152278933,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004924737365672873,
|
|
"loss": 5.5073,
|
|
"mean_token_accuracy": 0.16041582226753234,
|
|
"num_tokens": 19832936.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.730201482772827,
|
|
"epoch": 0.9031716026044948,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004924660539955463,
|
|
"loss": 5.6387,
|
|
"mean_token_accuracy": 0.1655229866504669,
|
|
"num_tokens": 19841946.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.709415626525879,
|
|
"epoch": 0.9035916824196597,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004924583675715063,
|
|
"loss": 5.5192,
|
|
"mean_token_accuracy": 0.16042786836624146,
|
|
"num_tokens": 19851469.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.729109477996826,
|
|
"epoch": 0.9040117622348246,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004924506772953031,
|
|
"loss": 5.5905,
|
|
"mean_token_accuracy": 0.15771916061639785,
|
|
"num_tokens": 19860731.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.630281686782837,
|
|
"epoch": 0.9044318420499895,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004924429831670733,
|
|
"loss": 5.5977,
|
|
"mean_token_accuracy": 0.15505731701850892,
|
|
"num_tokens": 19869717.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.670056867599487,
|
|
"epoch": 0.9048519218651544,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000492435285186953,
|
|
"loss": 5.5315,
|
|
"mean_token_accuracy": 0.16062338650226593,
|
|
"num_tokens": 19879229.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.7497491359710695,
|
|
"epoch": 0.9052720016803193,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004924275833550785,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.1601421967148781,
|
|
"num_tokens": 19888260.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.748339319229126,
|
|
"epoch": 0.9056920814954842,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004924198776715865,
|
|
"loss": 5.5553,
|
|
"mean_token_accuracy": 0.1663961872458458,
|
|
"num_tokens": 19897070.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.717373561859131,
|
|
"epoch": 0.906112161310649,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004924121681366132,
|
|
"loss": 5.516,
|
|
"mean_token_accuracy": 0.1547970689833164,
|
|
"num_tokens": 19907170.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.6512758255004885,
|
|
"epoch": 0.9065322411258139,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004924044547502951,
|
|
"loss": 5.477,
|
|
"mean_token_accuracy": 0.15937758833169938,
|
|
"num_tokens": 19917220.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.606697940826416,
|
|
"epoch": 0.9069523209409788,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004923967375127692,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.16532299369573594,
|
|
"num_tokens": 19926724.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.764872741699219,
|
|
"epoch": 0.9073724007561437,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000492389016424172,
|
|
"loss": 5.6433,
|
|
"mean_token_accuracy": 0.15729621946811675,
|
|
"num_tokens": 19936429.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.627816200256348,
|
|
"epoch": 0.9077924805713086,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004923812914846404,
|
|
"loss": 5.4148,
|
|
"mean_token_accuracy": 0.17244187742471695,
|
|
"num_tokens": 19945096.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.617258310317993,
|
|
"epoch": 0.9082125603864735,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004923735626943111,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.1648621678352356,
|
|
"num_tokens": 19953560.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.658634662628174,
|
|
"epoch": 0.9086326402016384,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004923658300533211,
|
|
"loss": 5.4752,
|
|
"mean_token_accuracy": 0.16002987921237946,
|
|
"num_tokens": 19962669.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.701725196838379,
|
|
"epoch": 0.9090527200168032,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004923580935618073,
|
|
"loss": 5.5337,
|
|
"mean_token_accuracy": 0.16278491616249086,
|
|
"num_tokens": 19971990.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.643719911575317,
|
|
"epoch": 0.909472799831968,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004923503532199069,
|
|
"loss": 5.5083,
|
|
"mean_token_accuracy": 0.16564737558364867,
|
|
"num_tokens": 19981850.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.67440276145935,
|
|
"epoch": 0.909892879647133,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004923426090277567,
|
|
"loss": 5.5631,
|
|
"mean_token_accuracy": 0.15856756269931793,
|
|
"num_tokens": 19991574.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.6700526714324955,
|
|
"epoch": 0.9103129594622978,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004923348609854943,
|
|
"loss": 5.5267,
|
|
"mean_token_accuracy": 0.16576842218637466,
|
|
"num_tokens": 20001392.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.65757007598877,
|
|
"epoch": 0.9107330392774627,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004923271090932566,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.15540991723537445,
|
|
"num_tokens": 20011277.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.6370244979858395,
|
|
"epoch": 0.9111531190926276,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004923193533511812,
|
|
"loss": 5.4852,
|
|
"mean_token_accuracy": 0.16075857132673263,
|
|
"num_tokens": 20021171.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.814991569519043,
|
|
"epoch": 0.9115731989077924,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004923115937594053,
|
|
"loss": 5.5416,
|
|
"mean_token_accuracy": 0.163661889731884,
|
|
"num_tokens": 20030189.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.692598056793213,
|
|
"epoch": 0.9119932787229573,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004923038303180664,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.16363249719142914,
|
|
"num_tokens": 20038287.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.63488359451294,
|
|
"epoch": 0.9124133585381222,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000492296063027302,
|
|
"loss": 5.5518,
|
|
"mean_token_accuracy": 0.15580225586891175,
|
|
"num_tokens": 20047653.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.688053321838379,
|
|
"epoch": 0.9128334383532871,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004922882918872498,
|
|
"loss": 5.5501,
|
|
"mean_token_accuracy": 0.15726881623268127,
|
|
"num_tokens": 20057415.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.78084363937378,
|
|
"epoch": 0.913253518168452,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004922805168980475,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.16048648655414582,
|
|
"num_tokens": 20065996.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.706553649902344,
|
|
"epoch": 0.9136735979836169,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004922727380598326,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.15912986695766448,
|
|
"num_tokens": 20075376.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.614659214019776,
|
|
"epoch": 0.9140936777987818,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.000492264955372743,
|
|
"loss": 5.5293,
|
|
"mean_token_accuracy": 0.15426042973995208,
|
|
"num_tokens": 20084950.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.729830312728882,
|
|
"epoch": 0.9145137576139466,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004922571688369165,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.16088814586400985,
|
|
"num_tokens": 20094011.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.693281841278076,
|
|
"epoch": 0.9149338374291115,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004922493784524914,
|
|
"loss": 5.489,
|
|
"mean_token_accuracy": 0.16421934738755226,
|
|
"num_tokens": 20103037.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.709012699127197,
|
|
"epoch": 0.9153539172442764,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004922415842196052,
|
|
"loss": 5.6312,
|
|
"mean_token_accuracy": 0.15036728978157043,
|
|
"num_tokens": 20112727.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.627096223831177,
|
|
"epoch": 0.9157739970594413,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004922337861383963,
|
|
"loss": 5.4382,
|
|
"mean_token_accuracy": 0.16880789548158645,
|
|
"num_tokens": 20122341.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.691968965530395,
|
|
"epoch": 0.9161940768746062,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004922259842090027,
|
|
"loss": 5.4329,
|
|
"mean_token_accuracy": 0.16247511506080628,
|
|
"num_tokens": 20131354.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.6311639785766605,
|
|
"epoch": 0.9166141566897711,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004922181784315627,
|
|
"loss": 5.4611,
|
|
"mean_token_accuracy": 0.16493925154209138,
|
|
"num_tokens": 20140440.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.651127910614013,
|
|
"epoch": 0.917034236504936,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004922103688062145,
|
|
"loss": 5.4833,
|
|
"mean_token_accuracy": 0.15852523893117904,
|
|
"num_tokens": 20149331.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.658089113235474,
|
|
"epoch": 0.9174543163201008,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004922025553330964,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.17089224606752396,
|
|
"num_tokens": 20158566.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.678445959091187,
|
|
"epoch": 0.9178743961352657,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000492194738012347,
|
|
"loss": 5.544,
|
|
"mean_token_accuracy": 0.16259633898735046,
|
|
"num_tokens": 20168339.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.716028356552124,
|
|
"epoch": 0.9182944759504306,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004921869168441045,
|
|
"loss": 5.5536,
|
|
"mean_token_accuracy": 0.15383095294237137,
|
|
"num_tokens": 20177967.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.637088251113892,
|
|
"epoch": 0.9187145557655955,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004921790918285077,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.16159048825502395,
|
|
"num_tokens": 20187279.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.707053279876709,
|
|
"epoch": 0.9191346355807604,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004921712629656951,
|
|
"loss": 5.6541,
|
|
"mean_token_accuracy": 0.17022398263216018,
|
|
"num_tokens": 20195324.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.740572452545166,
|
|
"epoch": 0.9195547153959253,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004921634302558054,
|
|
"loss": 5.5677,
|
|
"mean_token_accuracy": 0.16136983186006545,
|
|
"num_tokens": 20204985.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.679078197479248,
|
|
"epoch": 0.9199747952110902,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004921555936989773,
|
|
"loss": 5.5835,
|
|
"mean_token_accuracy": 0.15574949830770493,
|
|
"num_tokens": 20214553.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.698373556137085,
|
|
"epoch": 0.9203948750262549,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004921477532953497,
|
|
"loss": 5.4858,
|
|
"mean_token_accuracy": 0.16730043292045593,
|
|
"num_tokens": 20224118.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.6933988571167,
|
|
"epoch": 0.9208149548414198,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004921399090450616,
|
|
"loss": 5.4604,
|
|
"mean_token_accuracy": 0.15393470227718353,
|
|
"num_tokens": 20233719.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.638811302185059,
|
|
"epoch": 0.9212350346565847,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004921320609482517,
|
|
"loss": 5.5464,
|
|
"mean_token_accuracy": 0.1613891303539276,
|
|
"num_tokens": 20242311.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.718568897247314,
|
|
"epoch": 0.9216551144717496,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004921242090050591,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.15839444398880004,
|
|
"num_tokens": 20252998.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.725355386734009,
|
|
"epoch": 0.9220751942869145,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000492116353215623,
|
|
"loss": 5.63,
|
|
"mean_token_accuracy": 0.16329726874828338,
|
|
"num_tokens": 20262456.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.627430534362793,
|
|
"epoch": 0.9224952741020794,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004921084935800825,
|
|
"loss": 5.3904,
|
|
"mean_token_accuracy": 0.17261915653944016,
|
|
"num_tokens": 20271516.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.653037452697754,
|
|
"epoch": 0.9229153539172443,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004921006300985768,
|
|
"loss": 5.4391,
|
|
"mean_token_accuracy": 0.16310697942972183,
|
|
"num_tokens": 20280373.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.643791198730469,
|
|
"epoch": 0.9233354337324091,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004920927627712453,
|
|
"loss": 5.4371,
|
|
"mean_token_accuracy": 0.1669539228081703,
|
|
"num_tokens": 20289426.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.682681846618652,
|
|
"epoch": 0.923755513547574,
|
|
"grad_norm": 1.9296875,
|
|
"learning_rate": 0.0004920848915982273,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.1578148901462555,
|
|
"num_tokens": 20298045.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.6499217510223385,
|
|
"epoch": 0.9241755933627389,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004920770165796622,
|
|
"loss": 5.4716,
|
|
"mean_token_accuracy": 0.1633152633905411,
|
|
"num_tokens": 20307352.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.664845609664917,
|
|
"epoch": 0.9245956731779038,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004920691377156895,
|
|
"loss": 5.4945,
|
|
"mean_token_accuracy": 0.1626512423157692,
|
|
"num_tokens": 20316448.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.777086496353149,
|
|
"epoch": 0.9250157529930687,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004920612550064488,
|
|
"loss": 5.641,
|
|
"mean_token_accuracy": 0.1607293888926506,
|
|
"num_tokens": 20326440.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.655669260025024,
|
|
"epoch": 0.9254358328082336,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004920533684520797,
|
|
"loss": 5.431,
|
|
"mean_token_accuracy": 0.16383090168237685,
|
|
"num_tokens": 20335447.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.635196256637573,
|
|
"epoch": 0.9258559126233984,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000492045478052722,
|
|
"loss": 5.5698,
|
|
"mean_token_accuracy": 0.1583259880542755,
|
|
"num_tokens": 20344523.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.65436954498291,
|
|
"epoch": 0.9262759924385633,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004920375838085154,
|
|
"loss": 5.5243,
|
|
"mean_token_accuracy": 0.16398487687110902,
|
|
"num_tokens": 20354267.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.7046201705932615,
|
|
"epoch": 0.9266960722537282,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004920296857195998,
|
|
"loss": 5.6023,
|
|
"mean_token_accuracy": 0.15840856581926346,
|
|
"num_tokens": 20364137.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.6905293464660645,
|
|
"epoch": 0.9271161520688931,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.000492021783786115,
|
|
"loss": 5.4931,
|
|
"mean_token_accuracy": 0.16749118119478226,
|
|
"num_tokens": 20372583.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.655548763275147,
|
|
"epoch": 0.927536231884058,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004920138780082011,
|
|
"loss": 5.4444,
|
|
"mean_token_accuracy": 0.1603078469634056,
|
|
"num_tokens": 20382050.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.616688871383667,
|
|
"epoch": 0.9279563116992229,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004920059683859981,
|
|
"loss": 5.4141,
|
|
"mean_token_accuracy": 0.16826660186052322,
|
|
"num_tokens": 20391425.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.713768148422242,
|
|
"epoch": 0.9283763915143878,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004919980549196461,
|
|
"loss": 5.568,
|
|
"mean_token_accuracy": 0.159714911878109,
|
|
"num_tokens": 20400559.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.690584897994995,
|
|
"epoch": 0.9287964713295526,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004919901376092853,
|
|
"loss": 5.5072,
|
|
"mean_token_accuracy": 0.16440173387527465,
|
|
"num_tokens": 20408985.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.639202308654785,
|
|
"epoch": 0.9292165511447175,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004919822164550559,
|
|
"loss": 5.5997,
|
|
"mean_token_accuracy": 0.14894191175699234,
|
|
"num_tokens": 20417855.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.681364822387695,
|
|
"epoch": 0.9296366309598824,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004919742914570983,
|
|
"loss": 5.5513,
|
|
"mean_token_accuracy": 0.1600523427128792,
|
|
"num_tokens": 20426191.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.688843154907227,
|
|
"epoch": 0.9300567107750473,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000491966362615553,
|
|
"loss": 5.5361,
|
|
"mean_token_accuracy": 0.15442707315087317,
|
|
"num_tokens": 20435592.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.733451700210571,
|
|
"epoch": 0.9304767905902122,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00049195842993056,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.16001696437597274,
|
|
"num_tokens": 20445504.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.7029729843139645,
|
|
"epoch": 0.930896870405377,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004919504934022604,
|
|
"loss": 5.499,
|
|
"mean_token_accuracy": 0.15569454431533813,
|
|
"num_tokens": 20455153.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.661473369598388,
|
|
"epoch": 0.931316950220542,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004919425530307943,
|
|
"loss": 5.4993,
|
|
"mean_token_accuracy": 0.15951350182294846,
|
|
"num_tokens": 20465101.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.632450342178345,
|
|
"epoch": 0.9317370300357067,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004919346088163028,
|
|
"loss": 5.5358,
|
|
"mean_token_accuracy": 0.1622280955314636,
|
|
"num_tokens": 20474700.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.722516965866089,
|
|
"epoch": 0.9321571098508716,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004919266607589263,
|
|
"loss": 5.5613,
|
|
"mean_token_accuracy": 0.15339310318231583,
|
|
"num_tokens": 20483945.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.700594758987426,
|
|
"epoch": 0.9325771896660365,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004919187088588057,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.1624033495783806,
|
|
"num_tokens": 20493307.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.659552097320557,
|
|
"epoch": 0.9329972694812014,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004919107531160819,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.16901983320713043,
|
|
"num_tokens": 20501889.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.644443607330322,
|
|
"epoch": 0.9334173492963663,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004919027935308957,
|
|
"loss": 5.5147,
|
|
"mean_token_accuracy": 0.1635582149028778,
|
|
"num_tokens": 20510577.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.582364463806153,
|
|
"epoch": 0.9338374291115312,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004918948301033884,
|
|
"loss": 5.4685,
|
|
"mean_token_accuracy": 0.16453532576560975,
|
|
"num_tokens": 20520025.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.729832363128662,
|
|
"epoch": 0.9342575089266961,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.0004918868628337007,
|
|
"loss": 5.5364,
|
|
"mean_token_accuracy": 0.16004782021045685,
|
|
"num_tokens": 20528989.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.722401762008667,
|
|
"epoch": 0.9346775887418609,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004918788917219739,
|
|
"loss": 5.4639,
|
|
"mean_token_accuracy": 0.16330705732107162,
|
|
"num_tokens": 20538328.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.684643316268921,
|
|
"epoch": 0.9350976685570258,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004918709167683493,
|
|
"loss": 5.618,
|
|
"mean_token_accuracy": 0.15527107566595078,
|
|
"num_tokens": 20548069.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.62087116241455,
|
|
"epoch": 0.9355177483721907,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004918629379729681,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.1718309447169304,
|
|
"num_tokens": 20557128.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.642658615112305,
|
|
"epoch": 0.9359378281873556,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004918549553359715,
|
|
"loss": 5.4888,
|
|
"mean_token_accuracy": 0.1616463139653206,
|
|
"num_tokens": 20566352.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.673039436340332,
|
|
"epoch": 0.9363579080025205,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004918469688575012,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.1632925733923912,
|
|
"num_tokens": 20575814.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.649928092956543,
|
|
"epoch": 0.9367779878176854,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004918389785376983,
|
|
"loss": 5.399,
|
|
"mean_token_accuracy": 0.16439888179302214,
|
|
"num_tokens": 20584715.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.607899522781372,
|
|
"epoch": 0.9371980676328503,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004918309843767047,
|
|
"loss": 5.4657,
|
|
"mean_token_accuracy": 0.1584487035870552,
|
|
"num_tokens": 20594630.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.618726491928101,
|
|
"epoch": 0.9376181474480151,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004918229863746618,
|
|
"loss": 5.4674,
|
|
"mean_token_accuracy": 0.1587045595049858,
|
|
"num_tokens": 20603653.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.6923305034637455,
|
|
"epoch": 0.93803822726318,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004918149845317114,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16108497381210327,
|
|
"num_tokens": 20612188.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.654456329345703,
|
|
"epoch": 0.9384583070783449,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004918069788479952,
|
|
"loss": 5.4462,
|
|
"mean_token_accuracy": 0.1687158852815628,
|
|
"num_tokens": 20620933.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.652120113372803,
|
|
"epoch": 0.9388783868935098,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004917989693236549,
|
|
"loss": 5.4875,
|
|
"mean_token_accuracy": 0.1668206810951233,
|
|
"num_tokens": 20629919.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.682731342315674,
|
|
"epoch": 0.9392984667086747,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004917909559588326,
|
|
"loss": 5.465,
|
|
"mean_token_accuracy": 0.1615450456738472,
|
|
"num_tokens": 20638475.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.754220056533813,
|
|
"epoch": 0.9397185465238396,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00049178293875367,
|
|
"loss": 5.5823,
|
|
"mean_token_accuracy": 0.1557904876768589,
|
|
"num_tokens": 20648105.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.608329772949219,
|
|
"epoch": 0.9401386263390044,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004917749177083094,
|
|
"loss": 5.4916,
|
|
"mean_token_accuracy": 0.15995590686798095,
|
|
"num_tokens": 20657527.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.659386062622071,
|
|
"epoch": 0.9405587061541693,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004917668928228927,
|
|
"loss": 5.4957,
|
|
"mean_token_accuracy": 0.16557826548814775,
|
|
"num_tokens": 20666375.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.658402729034424,
|
|
"epoch": 0.9409787859693342,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004917588640975622,
|
|
"loss": 5.4458,
|
|
"mean_token_accuracy": 0.16658560037612916,
|
|
"num_tokens": 20675350.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.563868188858033,
|
|
"epoch": 0.941398865784499,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00049175083153246,
|
|
"loss": 5.3752,
|
|
"mean_token_accuracy": 0.16457706093788146,
|
|
"num_tokens": 20684072.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.598710680007935,
|
|
"epoch": 0.941818945599664,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004917427951277284,
|
|
"loss": 5.4561,
|
|
"mean_token_accuracy": 0.16836450397968292,
|
|
"num_tokens": 20692989.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.691392278671264,
|
|
"epoch": 0.9422390254148288,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004917347548835097,
|
|
"loss": 5.4403,
|
|
"mean_token_accuracy": 0.15893812775611876,
|
|
"num_tokens": 20701269.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.68915286064148,
|
|
"epoch": 0.9426591052299937,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004917267107999466,
|
|
"loss": 5.5515,
|
|
"mean_token_accuracy": 0.16261414885520936,
|
|
"num_tokens": 20709739.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.657668352127075,
|
|
"epoch": 0.9430791850451585,
|
|
"grad_norm": 2.296875,
|
|
"learning_rate": 0.0004917186628771812,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.1634127229452133,
|
|
"num_tokens": 20718950.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.669168424606323,
|
|
"epoch": 0.9434992648603234,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004917106111153565,
|
|
"loss": 5.4763,
|
|
"mean_token_accuracy": 0.16090827137231828,
|
|
"num_tokens": 20729469.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.717650508880615,
|
|
"epoch": 0.9439193446754883,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004917025555146148,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.17064472585916518,
|
|
"num_tokens": 20738231.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.70476598739624,
|
|
"epoch": 0.9443394244906532,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000491694496075099,
|
|
"loss": 5.6789,
|
|
"mean_token_accuracy": 0.14857278168201446,
|
|
"num_tokens": 20748578.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.7716655254364015,
|
|
"epoch": 0.9447595043058181,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004916864327969517,
|
|
"loss": 5.6139,
|
|
"mean_token_accuracy": 0.1479826033115387,
|
|
"num_tokens": 20759284.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.737630414962768,
|
|
"epoch": 0.945179584120983,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916783656803158,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.16123252511024475,
|
|
"num_tokens": 20768186.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.648173189163208,
|
|
"epoch": 0.9455996639361479,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004916702947253342,
|
|
"loss": 5.4262,
|
|
"mean_token_accuracy": 0.16916553676128387,
|
|
"num_tokens": 20776711.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.6307295799255375,
|
|
"epoch": 0.9460197437513127,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004916622199321501,
|
|
"loss": 5.5014,
|
|
"mean_token_accuracy": 0.15936348885297774,
|
|
"num_tokens": 20785154.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.677838134765625,
|
|
"epoch": 0.9464398235664776,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004916541413009062,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.1709165707230568,
|
|
"num_tokens": 20794114.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.734316635131836,
|
|
"epoch": 0.9468599033816425,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.0004916460588317458,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16012431532144547,
|
|
"num_tokens": 20803892.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.586827802658081,
|
|
"epoch": 0.9472799831968074,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004916379725248118,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1667679503560066,
|
|
"num_tokens": 20812892.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.660504627227783,
|
|
"epoch": 0.9477000630119723,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004916298823802479,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.15982511639595032,
|
|
"num_tokens": 20821934.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.59260663986206,
|
|
"epoch": 0.9481201428271372,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004916217883981971,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.16577256172895433,
|
|
"num_tokens": 20830100.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.655998659133911,
|
|
"epoch": 0.9485402226423021,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004916136905788029,
|
|
"loss": 5.486,
|
|
"mean_token_accuracy": 0.16212498694658278,
|
|
"num_tokens": 20839890.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.721244287490845,
|
|
"epoch": 0.9489603024574669,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004916055889222087,
|
|
"loss": 5.5913,
|
|
"mean_token_accuracy": 0.1496299162507057,
|
|
"num_tokens": 20848670.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.6661537170410154,
|
|
"epoch": 0.9493803822726318,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000491597483428558,
|
|
"loss": 5.4543,
|
|
"mean_token_accuracy": 0.16638226807117462,
|
|
"num_tokens": 20857291.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.579902648925781,
|
|
"epoch": 0.9498004620877967,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004915893740979944,
|
|
"loss": 5.4302,
|
|
"mean_token_accuracy": 0.16439789533615112,
|
|
"num_tokens": 20865341.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.676503372192383,
|
|
"epoch": 0.9502205419029616,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004915812609306617,
|
|
"loss": 5.5474,
|
|
"mean_token_accuracy": 0.16357194930315017,
|
|
"num_tokens": 20875194.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.66827392578125,
|
|
"epoch": 0.9506406217181265,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004915731439267034,
|
|
"loss": 5.4553,
|
|
"mean_token_accuracy": 0.16290259212255478,
|
|
"num_tokens": 20884831.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.562486600875855,
|
|
"epoch": 0.9510607015332914,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004915650230862634,
|
|
"loss": 5.3338,
|
|
"mean_token_accuracy": 0.1782681941986084,
|
|
"num_tokens": 20893790.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.596565675735474,
|
|
"epoch": 0.9514807813484563,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004915568984094854,
|
|
"loss": 5.4803,
|
|
"mean_token_accuracy": 0.16112319082021714,
|
|
"num_tokens": 20902175.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.726467943191528,
|
|
"epoch": 0.951900861163621,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004915487698965136,
|
|
"loss": 5.6184,
|
|
"mean_token_accuracy": 0.15359724164009095,
|
|
"num_tokens": 20911484.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.781221151351929,
|
|
"epoch": 0.952320940978786,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004915406375474917,
|
|
"loss": 5.5453,
|
|
"mean_token_accuracy": 0.15792252421379088,
|
|
"num_tokens": 20920916.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.741652107238769,
|
|
"epoch": 0.9527410207939508,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000491532501362564,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.16220796555280687,
|
|
"num_tokens": 20930219.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.57544355392456,
|
|
"epoch": 0.9531611006091157,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004915243613418745,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.17249523252248763,
|
|
"num_tokens": 20939591.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.6936798095703125,
|
|
"epoch": 0.9535811804242806,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004915162174855675,
|
|
"loss": 5.5717,
|
|
"mean_token_accuracy": 0.15805065482854844,
|
|
"num_tokens": 20950035.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.6745775699615475,
|
|
"epoch": 0.9540012602394455,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004915080697937872,
|
|
"loss": 5.4665,
|
|
"mean_token_accuracy": 0.16316088140010834,
|
|
"num_tokens": 20959168.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.566767168045044,
|
|
"epoch": 0.9544213400546103,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004914999182666779,
|
|
"loss": 5.415,
|
|
"mean_token_accuracy": 0.16996480226516725,
|
|
"num_tokens": 20967887.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.693580484390258,
|
|
"epoch": 0.9548414198697752,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004914917629043839,
|
|
"loss": 5.5077,
|
|
"mean_token_accuracy": 0.15940580666065216,
|
|
"num_tokens": 20977558.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.588667678833008,
|
|
"epoch": 0.9552614996849401,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00049148360370705,
|
|
"loss": 5.4812,
|
|
"mean_token_accuracy": 0.16379174292087556,
|
|
"num_tokens": 20986118.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.614265727996826,
|
|
"epoch": 0.955681579500105,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004914754406748204,
|
|
"loss": 5.3913,
|
|
"mean_token_accuracy": 0.1682723805308342,
|
|
"num_tokens": 20994623.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.693148231506347,
|
|
"epoch": 0.9561016593152699,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00049146727380784,
|
|
"loss": 5.5802,
|
|
"mean_token_accuracy": 0.16016335636377335,
|
|
"num_tokens": 21004193.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.597726583480835,
|
|
"epoch": 0.9565217391304348,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004914591031062531,
|
|
"loss": 5.4044,
|
|
"mean_token_accuracy": 0.17047665268182755,
|
|
"num_tokens": 21013125.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.515113019943238,
|
|
"epoch": 0.9569418189455997,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004914509285702048,
|
|
"loss": 5.3387,
|
|
"mean_token_accuracy": 0.1710033819079399,
|
|
"num_tokens": 21021402.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.614928150177002,
|
|
"epoch": 0.9573618987607645,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004914427501998397,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.16588329821825026,
|
|
"num_tokens": 21029639.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.619404268264771,
|
|
"epoch": 0.9577819785759294,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004914345679953027,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.16462402492761613,
|
|
"num_tokens": 21037525.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.662878179550171,
|
|
"epoch": 0.9582020583910943,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004914263819567388,
|
|
"loss": 5.5605,
|
|
"mean_token_accuracy": 0.15533360093832016,
|
|
"num_tokens": 21047702.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.694554328918457,
|
|
"epoch": 0.9586221382062592,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000491418192084293,
|
|
"loss": 5.4548,
|
|
"mean_token_accuracy": 0.16688745468854904,
|
|
"num_tokens": 21056379.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.633595609664917,
|
|
"epoch": 0.9590422180214241,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004914099983781104,
|
|
"loss": 5.4566,
|
|
"mean_token_accuracy": 0.16330905705690385,
|
|
"num_tokens": 21065283.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.640380907058716,
|
|
"epoch": 0.959462297836589,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.000491401800838336,
|
|
"loss": 5.5745,
|
|
"mean_token_accuracy": 0.15918146967887878,
|
|
"num_tokens": 21074938.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.626530456542969,
|
|
"epoch": 0.9598823776517539,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004913935994651153,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.17172765135765075,
|
|
"num_tokens": 21084729.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.564239358901977,
|
|
"epoch": 0.9603024574669187,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004913853942585932,
|
|
"loss": 5.3283,
|
|
"mean_token_accuracy": 0.17437093555927277,
|
|
"num_tokens": 21093456.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.600566244125366,
|
|
"epoch": 0.9607225372820836,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004913771852189155,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.15994736552238464,
|
|
"num_tokens": 21102980.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.754529666900635,
|
|
"epoch": 0.9611426170972485,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004913689723462271,
|
|
"loss": 5.6763,
|
|
"mean_token_accuracy": 0.17234763503074646,
|
|
"num_tokens": 21112777.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.676597976684571,
|
|
"epoch": 0.9615626969124134,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.000491360755640674,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.15645822137594223,
|
|
"num_tokens": 21122139.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.639119720458984,
|
|
"epoch": 0.9619827767275783,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004913525351024014,
|
|
"loss": 5.453,
|
|
"mean_token_accuracy": 0.1607119247317314,
|
|
"num_tokens": 21131425.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.6201681137084964,
|
|
"epoch": 0.9624028565427432,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004913443107315552,
|
|
"loss": 5.4341,
|
|
"mean_token_accuracy": 0.15983420610427856,
|
|
"num_tokens": 21140784.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.6580445766448975,
|
|
"epoch": 0.962822936357908,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004913360825282807,
|
|
"loss": 5.4335,
|
|
"mean_token_accuracy": 0.1675620973110199,
|
|
"num_tokens": 21150408.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.589797449111939,
|
|
"epoch": 0.9632430161730728,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000491327850492724,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.16759325116872786,
|
|
"num_tokens": 21158915.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.505474710464478,
|
|
"epoch": 0.9636630959882377,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004913196146250309,
|
|
"loss": 5.3419,
|
|
"mean_token_accuracy": 0.1716780662536621,
|
|
"num_tokens": 21167336.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.689284896850586,
|
|
"epoch": 0.9640831758034026,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004913113749253472,
|
|
"loss": 5.6449,
|
|
"mean_token_accuracy": 0.16215803027153014,
|
|
"num_tokens": 21177499.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.74305419921875,
|
|
"epoch": 0.9645032556185675,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004913031313938188,
|
|
"loss": 5.5509,
|
|
"mean_token_accuracy": 0.1595839351415634,
|
|
"num_tokens": 21186961.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.683131408691406,
|
|
"epoch": 0.9649233354337324,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004912948840305919,
|
|
"loss": 5.4379,
|
|
"mean_token_accuracy": 0.17446769773960114,
|
|
"num_tokens": 21196364.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.647530221939087,
|
|
"epoch": 0.9653434152488973,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004912866328358125,
|
|
"loss": 5.5191,
|
|
"mean_token_accuracy": 0.15950247049331664,
|
|
"num_tokens": 21206376.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.638066530227661,
|
|
"epoch": 0.9657634950640621,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004912783778096266,
|
|
"loss": 5.4934,
|
|
"mean_token_accuracy": 0.1693543791770935,
|
|
"num_tokens": 21215889.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.700996589660645,
|
|
"epoch": 0.966183574879227,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004912701189521808,
|
|
"loss": 5.5062,
|
|
"mean_token_accuracy": 0.16749416589736937,
|
|
"num_tokens": 21224959.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.757201671600342,
|
|
"epoch": 0.9666036546943919,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004912618562636211,
|
|
"loss": 5.6296,
|
|
"mean_token_accuracy": 0.15160779058933258,
|
|
"num_tokens": 21234495.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.642830944061279,
|
|
"epoch": 0.9670237345095568,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000491253589744094,
|
|
"loss": 5.47,
|
|
"mean_token_accuracy": 0.16335225403308867,
|
|
"num_tokens": 21244555.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.703874015808106,
|
|
"epoch": 0.9674438143247217,
|
|
"grad_norm": 1.8671875,
|
|
"learning_rate": 0.0004912453193937459,
|
|
"loss": 5.6037,
|
|
"mean_token_accuracy": 0.1612747997045517,
|
|
"num_tokens": 21254199.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.69853458404541,
|
|
"epoch": 0.9678638941398866,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004912370452127234,
|
|
"loss": 5.5001,
|
|
"mean_token_accuracy": 0.15972875952720642,
|
|
"num_tokens": 21262723.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.683942985534668,
|
|
"epoch": 0.9682839739550515,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004912287672011728,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.1622313767671585,
|
|
"num_tokens": 21271283.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.589861679077148,
|
|
"epoch": 0.9687040537702163,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004912204853592411,
|
|
"loss": 5.4774,
|
|
"mean_token_accuracy": 0.17342782616615296,
|
|
"num_tokens": 21279542.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.613545656204224,
|
|
"epoch": 0.9691241335853812,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004912121996870748,
|
|
"loss": 5.4448,
|
|
"mean_token_accuracy": 0.16918166279792785,
|
|
"num_tokens": 21288678.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.773236703872681,
|
|
"epoch": 0.9695442134005461,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004912039101848207,
|
|
"loss": 5.5955,
|
|
"mean_token_accuracy": 0.16231737807393073,
|
|
"num_tokens": 21298982.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.701774406433105,
|
|
"epoch": 0.969964293215711,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004911956168526257,
|
|
"loss": 5.5289,
|
|
"mean_token_accuracy": 0.16124602109193803,
|
|
"num_tokens": 21307663.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.712226152420044,
|
|
"epoch": 0.9703843730308759,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911873196906366,
|
|
"loss": 5.5326,
|
|
"mean_token_accuracy": 0.15940239503979683,
|
|
"num_tokens": 21318004.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.570864295959472,
|
|
"epoch": 0.9708044528460408,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004911790186990005,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.1776915341615677,
|
|
"num_tokens": 21327373.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.576349306106567,
|
|
"epoch": 0.9712245326612057,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004911707138778643,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.1666841670870781,
|
|
"num_tokens": 21335654.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.672850465774536,
|
|
"epoch": 0.9716446124763705,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911624052273754,
|
|
"loss": 5.5129,
|
|
"mean_token_accuracy": 0.1632431373000145,
|
|
"num_tokens": 21344464.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.76579852104187,
|
|
"epoch": 0.9720646922915354,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004911540927476807,
|
|
"loss": 5.6111,
|
|
"mean_token_accuracy": 0.15846215337514877,
|
|
"num_tokens": 21354121.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.708047771453858,
|
|
"epoch": 0.9724847721067003,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004911457764389275,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.1658056989312172,
|
|
"num_tokens": 21363395.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.672170209884643,
|
|
"epoch": 0.9729048519218652,
|
|
"grad_norm": 2.203125,
|
|
"learning_rate": 0.0004911374563012633,
|
|
"loss": 5.4944,
|
|
"mean_token_accuracy": 0.16023199558258056,
|
|
"num_tokens": 21372126.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.726519393920898,
|
|
"epoch": 0.97332493173703,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004911291323348352,
|
|
"loss": 5.5963,
|
|
"mean_token_accuracy": 0.1553143873810768,
|
|
"num_tokens": 21380554.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.6460357189178465,
|
|
"epoch": 0.973745011552195,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004911208045397909,
|
|
"loss": 5.4832,
|
|
"mean_token_accuracy": 0.16235848218202592,
|
|
"num_tokens": 21389317.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.753270435333252,
|
|
"epoch": 0.9741650913673598,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004911124729162778,
|
|
"loss": 5.593,
|
|
"mean_token_accuracy": 0.15693895667791366,
|
|
"num_tokens": 21398926.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.707015132904052,
|
|
"epoch": 0.9745851711825246,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004911041374644435,
|
|
"loss": 5.3961,
|
|
"mean_token_accuracy": 0.1671022891998291,
|
|
"num_tokens": 21406962.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.666591787338257,
|
|
"epoch": 0.9750052509976895,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004910957981844357,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.164098384976387,
|
|
"num_tokens": 21415868.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.754735374450684,
|
|
"epoch": 0.9754253308128544,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004910874550764022,
|
|
"loss": 5.6053,
|
|
"mean_token_accuracy": 0.1618281587958336,
|
|
"num_tokens": 21424544.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.600016689300537,
|
|
"epoch": 0.9758454106280193,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004910791081404907,
|
|
"loss": 5.4663,
|
|
"mean_token_accuracy": 0.17111330032348632,
|
|
"num_tokens": 21433589.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.637977123260498,
|
|
"epoch": 0.9762654904431842,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004910707573768489,
|
|
"loss": 5.5349,
|
|
"mean_token_accuracy": 0.1595746397972107,
|
|
"num_tokens": 21442084.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.64194393157959,
|
|
"epoch": 0.9766855702583491,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004910624027856251,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.16450028717517853,
|
|
"num_tokens": 21450962.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.686526966094971,
|
|
"epoch": 0.977105650073514,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004910540443669669,
|
|
"loss": 5.5391,
|
|
"mean_token_accuracy": 0.15900047048926352,
|
|
"num_tokens": 21461322.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.672098588943482,
|
|
"epoch": 0.9775257298886788,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004910456821210227,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.16485550701618196,
|
|
"num_tokens": 21470800.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.630803632736206,
|
|
"epoch": 0.9779458097038437,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004910373160479404,
|
|
"loss": 5.3681,
|
|
"mean_token_accuracy": 0.171659155189991,
|
|
"num_tokens": 21479707.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.655557298660279,
|
|
"epoch": 0.9783658895190086,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004910289461478683,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.15193586573004722,
|
|
"num_tokens": 21489469.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.692305946350098,
|
|
"epoch": 0.9787859693341735,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004910205724209547,
|
|
"loss": 5.5266,
|
|
"mean_token_accuracy": 0.15883257240056992,
|
|
"num_tokens": 21499226.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.579811143875122,
|
|
"epoch": 0.9792060491493384,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004910121948673478,
|
|
"loss": 5.391,
|
|
"mean_token_accuracy": 0.16931790709495545,
|
|
"num_tokens": 21508129.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.625033140182495,
|
|
"epoch": 0.9796261289645033,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004910038134871962,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.16273742616176606,
|
|
"num_tokens": 21516293.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.692939329147339,
|
|
"epoch": 0.9800462087796681,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004909954282806482,
|
|
"loss": 5.5821,
|
|
"mean_token_accuracy": 0.1591893032193184,
|
|
"num_tokens": 21525393.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.590066194534302,
|
|
"epoch": 0.980466288594833,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004909870392478524,
|
|
"loss": 5.4386,
|
|
"mean_token_accuracy": 0.1672815203666687,
|
|
"num_tokens": 21534585.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.601227903366089,
|
|
"epoch": 0.9808863684099979,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004909786463889575,
|
|
"loss": 5.3922,
|
|
"mean_token_accuracy": 0.16998750865459442,
|
|
"num_tokens": 21542947.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.647561883926391,
|
|
"epoch": 0.9813064482251628,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004909702497041121,
|
|
"loss": 5.4924,
|
|
"mean_token_accuracy": 0.16468349248170852,
|
|
"num_tokens": 21552168.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.675682210922242,
|
|
"epoch": 0.9817265280403277,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004909618491934648,
|
|
"loss": 5.5096,
|
|
"mean_token_accuracy": 0.1663383349776268,
|
|
"num_tokens": 21562131.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.604850959777832,
|
|
"epoch": 0.9821466078554926,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004909534448571647,
|
|
"loss": 5.4505,
|
|
"mean_token_accuracy": 0.17098020613193513,
|
|
"num_tokens": 21571363.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.635071516036987,
|
|
"epoch": 0.9825666876706575,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004909450366953604,
|
|
"loss": 5.4146,
|
|
"mean_token_accuracy": 0.16778166890144347,
|
|
"num_tokens": 21580754.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.620409727096558,
|
|
"epoch": 0.9829867674858223,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000490936624708201,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.16398802250623704,
|
|
"num_tokens": 21590053.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.581881427764893,
|
|
"epoch": 0.9834068473009872,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004909282088958356,
|
|
"loss": 5.4897,
|
|
"mean_token_accuracy": 0.16222208589315415,
|
|
"num_tokens": 21598681.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.7037766456604,
|
|
"epoch": 0.983826927116152,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000490919789258413,
|
|
"loss": 5.5024,
|
|
"mean_token_accuracy": 0.16776590049266815,
|
|
"num_tokens": 21607465.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.673490762710571,
|
|
"epoch": 0.984247006931317,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004909113657960826,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.15339512825012208,
|
|
"num_tokens": 21617480.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.655919981002808,
|
|
"epoch": 0.9846670867464818,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004909029385089935,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.16508855521678925,
|
|
"num_tokens": 21626434.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.6823704719543455,
|
|
"epoch": 0.9850871665616467,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000490894507397295,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.166464164853096,
|
|
"num_tokens": 21635627.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.6854860305786135,
|
|
"epoch": 0.9855072463768116,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004908860724611365,
|
|
"loss": 5.4769,
|
|
"mean_token_accuracy": 0.1653437554836273,
|
|
"num_tokens": 21644789.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.610777854919434,
|
|
"epoch": 0.9859273261919764,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004908776337006675,
|
|
"loss": 5.4821,
|
|
"mean_token_accuracy": 0.16152163594961166,
|
|
"num_tokens": 21653696.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.6638861179351805,
|
|
"epoch": 0.9863474060071413,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004908691911160373,
|
|
"loss": 5.4699,
|
|
"mean_token_accuracy": 0.15693951398134232,
|
|
"num_tokens": 21664420.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.65993366241455,
|
|
"epoch": 0.9867674858223062,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004908607447073954,
|
|
"loss": 5.4718,
|
|
"mean_token_accuracy": 0.16778032034635543,
|
|
"num_tokens": 21673716.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.634006547927856,
|
|
"epoch": 0.9871875656374711,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004908522944748917,
|
|
"loss": 5.4514,
|
|
"mean_token_accuracy": 0.17267897576093674,
|
|
"num_tokens": 21682860.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.509404897689819,
|
|
"epoch": 0.987607645452636,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004908438404186758,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.16950045078992843,
|
|
"num_tokens": 21691915.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.672783470153808,
|
|
"epoch": 0.9880277252678009,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004908353825388973,
|
|
"loss": 5.5825,
|
|
"mean_token_accuracy": 0.15650345236063004,
|
|
"num_tokens": 21701666.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.7960083961486815,
|
|
"epoch": 0.9884478050829658,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004908269208357062,
|
|
"loss": 5.5217,
|
|
"mean_token_accuracy": 0.16534726023674012,
|
|
"num_tokens": 21709267.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.622351837158203,
|
|
"epoch": 0.9888678848981306,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004908184553092523,
|
|
"loss": 5.3953,
|
|
"mean_token_accuracy": 0.16779804825782776,
|
|
"num_tokens": 21718117.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.647730779647827,
|
|
"epoch": 0.9892879647132955,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004908099859596856,
|
|
"loss": 5.543,
|
|
"mean_token_accuracy": 0.16623370349407196,
|
|
"num_tokens": 21727952.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.66669807434082,
|
|
"epoch": 0.9897080445284604,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004908015127871561,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.16361401975154877,
|
|
"num_tokens": 21737878.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.567669343948364,
|
|
"epoch": 0.9901281243436253,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000490793035791814,
|
|
"loss": 5.3689,
|
|
"mean_token_accuracy": 0.169732029736042,
|
|
"num_tokens": 21747391.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.570152378082275,
|
|
"epoch": 0.9905482041587902,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004907845549738093,
|
|
"loss": 5.3976,
|
|
"mean_token_accuracy": 0.16566923558712005,
|
|
"num_tokens": 21756791.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.51328330039978,
|
|
"epoch": 0.9909682839739551,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004907760703332923,
|
|
"loss": 5.4445,
|
|
"mean_token_accuracy": 0.16655617505311965,
|
|
"num_tokens": 21766020.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.70251579284668,
|
|
"epoch": 0.99138836378912,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004907675818704134,
|
|
"loss": 5.5443,
|
|
"mean_token_accuracy": 0.16133727729320527,
|
|
"num_tokens": 21775895.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.703081703186035,
|
|
"epoch": 0.9918084436042848,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004907590895853228,
|
|
"loss": 5.4606,
|
|
"mean_token_accuracy": 0.16604946404695511,
|
|
"num_tokens": 21784543.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.630713033676147,
|
|
"epoch": 0.9922285234194497,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004907505934781712,
|
|
"loss": 5.5144,
|
|
"mean_token_accuracy": 0.16048821806907654,
|
|
"num_tokens": 21793938.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.621685886383057,
|
|
"epoch": 0.9926486032346146,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004907420935491087,
|
|
"loss": 5.487,
|
|
"mean_token_accuracy": 0.16330500245094298,
|
|
"num_tokens": 21803641.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.652135419845581,
|
|
"epoch": 0.9930686830497795,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004907335897982862,
|
|
"loss": 5.4115,
|
|
"mean_token_accuracy": 0.17158966660499572,
|
|
"num_tokens": 21812542.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.599951648712159,
|
|
"epoch": 0.9934887628649444,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004907250822258543,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.16001633405685425,
|
|
"num_tokens": 21821847.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.774102830886841,
|
|
"epoch": 0.9939088426801093,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004907165708319637,
|
|
"loss": 5.5476,
|
|
"mean_token_accuracy": 0.16471952199935913,
|
|
"num_tokens": 21830799.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.616507863998413,
|
|
"epoch": 0.994328922495274,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004907080556167651,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.16898656040430068,
|
|
"num_tokens": 21840202.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.66267147064209,
|
|
"epoch": 0.994749002310439,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004906995365804093,
|
|
"loss": 5.5721,
|
|
"mean_token_accuracy": 0.15978300273418428,
|
|
"num_tokens": 21849701.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.700849723815918,
|
|
"epoch": 0.9951690821256038,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004906910137230472,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.1672790139913559,
|
|
"num_tokens": 21859191.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.632527494430542,
|
|
"epoch": 0.9955891619407687,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.00049068248704483,
|
|
"loss": 5.4493,
|
|
"mean_token_accuracy": 0.16411733329296113,
|
|
"num_tokens": 21867944.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.5771478652954105,
|
|
"epoch": 0.9960092417559336,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004906739565459085,
|
|
"loss": 5.4698,
|
|
"mean_token_accuracy": 0.16230135709047316,
|
|
"num_tokens": 21876368.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.753003358840942,
|
|
"epoch": 0.9964293215710985,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.000490665422226434,
|
|
"loss": 5.5633,
|
|
"mean_token_accuracy": 0.15508055686950684,
|
|
"num_tokens": 21885634.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.568900871276855,
|
|
"epoch": 0.9968494013862634,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004906568840865576,
|
|
"loss": 5.3646,
|
|
"mean_token_accuracy": 0.17266131490468978,
|
|
"num_tokens": 21894315.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.576476907730102,
|
|
"epoch": 0.9972694812014282,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004906483421264305,
|
|
"loss": 5.4972,
|
|
"mean_token_accuracy": 0.16627979129552842,
|
|
"num_tokens": 21903342.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.677194356918335,
|
|
"epoch": 0.9976895610165931,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000490639796346204,
|
|
"loss": 5.5986,
|
|
"mean_token_accuracy": 0.15755953639745712,
|
|
"num_tokens": 21914158.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.770134115219117,
|
|
"epoch": 0.998109640831758,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004906312467460297,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.1663819894194603,
|
|
"num_tokens": 21922639.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.622851228713989,
|
|
"epoch": 0.9985297206469229,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004906226933260588,
|
|
"loss": 5.4633,
|
|
"mean_token_accuracy": 0.16364375054836272,
|
|
"num_tokens": 21931385.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.684553384780884,
|
|
"epoch": 0.9989498004620878,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004906141360864429,
|
|
"loss": 5.4898,
|
|
"mean_token_accuracy": 0.16104650050401687,
|
|
"num_tokens": 21940788.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.725577688217163,
|
|
"epoch": 0.9993698802772527,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004906055750273336,
|
|
"loss": 5.4977,
|
|
"mean_token_accuracy": 0.16556380838155746,
|
|
"num_tokens": 21950309.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.6455409049987795,
|
|
"epoch": 0.9997899600924176,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004905970101488826,
|
|
"loss": 5.5074,
|
|
"mean_token_accuracy": 0.16334970146417618,
|
|
"num_tokens": 21959141.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.710307068294949,
|
|
"epoch": 1.000168031926066,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004905884414512416,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1661406440867318,
|
|
"num_tokens": 21966665.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.709056758880616,
|
|
"epoch": 1.0005881117412307,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004905798689345623,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.16853023320436478,
|
|
"num_tokens": 21976728.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.63147554397583,
|
|
"epoch": 1.0010081915563958,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004905712925989968,
|
|
"loss": 5.3332,
|
|
"mean_token_accuracy": 0.1637764275074005,
|
|
"num_tokens": 21985915.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.627887344360351,
|
|
"epoch": 1.0014282713715605,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004905627124446967,
|
|
"loss": 5.3974,
|
|
"mean_token_accuracy": 0.16635343581438064,
|
|
"num_tokens": 21995826.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.627153444290161,
|
|
"epoch": 1.0018483511867255,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004905541284718142,
|
|
"loss": 5.3478,
|
|
"mean_token_accuracy": 0.170246821641922,
|
|
"num_tokens": 22005299.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.641215467453003,
|
|
"epoch": 1.0022684310018903,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004905455406805011,
|
|
"loss": 5.3837,
|
|
"mean_token_accuracy": 0.16680040806531907,
|
|
"num_tokens": 22014499.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.672396039962768,
|
|
"epoch": 1.0026885108170553,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00049053694907091,
|
|
"loss": 5.5323,
|
|
"mean_token_accuracy": 0.15733788013458253,
|
|
"num_tokens": 22024531.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.646308374404907,
|
|
"epoch": 1.0031085906322201,
|
|
"grad_norm": 2.21875,
|
|
"learning_rate": 0.0004905283536431928,
|
|
"loss": 5.426,
|
|
"mean_token_accuracy": 0.16464308202266692,
|
|
"num_tokens": 22034036.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.607198762893677,
|
|
"epoch": 1.003528670447385,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004905197543975017,
|
|
"loss": 5.3512,
|
|
"mean_token_accuracy": 0.1657976523041725,
|
|
"num_tokens": 22042910.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.660063123703003,
|
|
"epoch": 1.00394875026255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004905111513339892,
|
|
"loss": 5.461,
|
|
"mean_token_accuracy": 0.16730546355247497,
|
|
"num_tokens": 22052242.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.648103475570679,
|
|
"epoch": 1.0043688300777147,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004905025444528076,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.16425618678331375,
|
|
"num_tokens": 22061467.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.526777505874634,
|
|
"epoch": 1.0047889098928797,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004904939337541093,
|
|
"loss": 5.2711,
|
|
"mean_token_accuracy": 0.17251382023096085,
|
|
"num_tokens": 22070300.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.673946237564087,
|
|
"epoch": 1.0052089897080445,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004904853192380472,
|
|
"loss": 5.4353,
|
|
"mean_token_accuracy": 0.1664825990796089,
|
|
"num_tokens": 22078960.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.659275007247925,
|
|
"epoch": 1.0056290695232095,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004904767009047733,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.16314680129289627,
|
|
"num_tokens": 22088135.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.664426994323731,
|
|
"epoch": 1.0060491493383743,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004904680787544408,
|
|
"loss": 5.4914,
|
|
"mean_token_accuracy": 0.16022274345159532,
|
|
"num_tokens": 22098004.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.702074432373047,
|
|
"epoch": 1.006469229153539,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004904594527872022,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.15825158208608628,
|
|
"num_tokens": 22107680.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.68216609954834,
|
|
"epoch": 1.006889308968704,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004904508230032103,
|
|
"loss": 5.4545,
|
|
"mean_token_accuracy": 0.1670009523630142,
|
|
"num_tokens": 22118004.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.61159930229187,
|
|
"epoch": 1.0073093887838689,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.000490442189402618,
|
|
"loss": 5.406,
|
|
"mean_token_accuracy": 0.1737432822585106,
|
|
"num_tokens": 22127825.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.6002617359161375,
|
|
"epoch": 1.007729468599034,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004904335519855783,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.1677705705165863,
|
|
"num_tokens": 22136448.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.57069959640503,
|
|
"epoch": 1.0081495484141987,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004904249107522442,
|
|
"loss": 5.4416,
|
|
"mean_token_accuracy": 0.16570404022932053,
|
|
"num_tokens": 22146415.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 1.0081495484141987,
|
|
"eval_entropy": 5.448210272077472,
|
|
"eval_loss": 5.511696815490723,
|
|
"eval_mean_token_accuracy": 0.17007384661069086,
|
|
"eval_num_tokens": 22146415.0,
|
|
"eval_runtime": 27.4734,
|
|
"eval_samples_per_second": 1360.078,
|
|
"eval_steps_per_second": 170.019,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"entropy": 5.7423820972442625,
|
|
"epoch": 1.0085696282293637,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004904162657027685,
|
|
"loss": 5.5822,
|
|
"mean_token_accuracy": 0.16078717708587648,
|
|
"num_tokens": 22156327.0,
|
|
"step": 12005
|
|
},
|
|
{
|
|
"entropy": 5.66963791847229,
|
|
"epoch": 1.0089897080445285,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004904076168373049,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.17133131325244905,
|
|
"num_tokens": 22165677.0,
|
|
"step": 12010
|
|
},
|
|
{
|
|
"entropy": 5.660669994354248,
|
|
"epoch": 1.0094097878596933,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004903989641560061,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.1685717523097992,
|
|
"num_tokens": 22175232.0,
|
|
"step": 12015
|
|
},
|
|
{
|
|
"entropy": 5.688869380950928,
|
|
"epoch": 1.0098298676748583,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004903903076590256,
|
|
"loss": 5.3645,
|
|
"mean_token_accuracy": 0.16198563128709792,
|
|
"num_tokens": 22184026.0,
|
|
"step": 12020
|
|
},
|
|
{
|
|
"entropy": 5.54636435508728,
|
|
"epoch": 1.010249947490023,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004903816473465167,
|
|
"loss": 5.2858,
|
|
"mean_token_accuracy": 0.18181220293045045,
|
|
"num_tokens": 22192020.0,
|
|
"step": 12025
|
|
},
|
|
{
|
|
"entropy": 5.477762174606323,
|
|
"epoch": 1.010670027305188,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004903729832186328,
|
|
"loss": 5.2837,
|
|
"mean_token_accuracy": 0.17269555926322938,
|
|
"num_tokens": 22200060.0,
|
|
"step": 12030
|
|
},
|
|
{
|
|
"entropy": 5.626640844345093,
|
|
"epoch": 1.0110901071203529,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004903643152755274,
|
|
"loss": 5.3175,
|
|
"mean_token_accuracy": 0.1659637376666069,
|
|
"num_tokens": 22208625.0,
|
|
"step": 12035
|
|
},
|
|
{
|
|
"entropy": 5.63057050704956,
|
|
"epoch": 1.0115101869355176,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004903556435173541,
|
|
"loss": 5.3185,
|
|
"mean_token_accuracy": 0.16828427612781524,
|
|
"num_tokens": 22217781.0,
|
|
"step": 12040
|
|
},
|
|
{
|
|
"entropy": 5.634527635574341,
|
|
"epoch": 1.0119302667506826,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004903469679442665,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.16385108083486558,
|
|
"num_tokens": 22226432.0,
|
|
"step": 12045
|
|
},
|
|
{
|
|
"entropy": 5.567414665222168,
|
|
"epoch": 1.0123503465658474,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004903382885564181,
|
|
"loss": 5.4451,
|
|
"mean_token_accuracy": 0.16746296286582946,
|
|
"num_tokens": 22234811.0,
|
|
"step": 12050
|
|
},
|
|
{
|
|
"entropy": 5.530305528640747,
|
|
"epoch": 1.0127704263810124,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.000490329605353963,
|
|
"loss": 5.3303,
|
|
"mean_token_accuracy": 0.1724723160266876,
|
|
"num_tokens": 22242808.0,
|
|
"step": 12055
|
|
},
|
|
{
|
|
"entropy": 5.664348220825195,
|
|
"epoch": 1.0131905061961772,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004903209183370547,
|
|
"loss": 5.383,
|
|
"mean_token_accuracy": 0.16988759338855744,
|
|
"num_tokens": 22251371.0,
|
|
"step": 12060
|
|
},
|
|
{
|
|
"entropy": 5.7766921043396,
|
|
"epoch": 1.0136105860113422,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004903122275058472,
|
|
"loss": 5.4667,
|
|
"mean_token_accuracy": 0.16579170525074005,
|
|
"num_tokens": 22260868.0,
|
|
"step": 12065
|
|
},
|
|
{
|
|
"entropy": 5.582829332351684,
|
|
"epoch": 1.014030665826507,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004903035328604944,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.16627193689346315,
|
|
"num_tokens": 22270554.0,
|
|
"step": 12070
|
|
},
|
|
{
|
|
"entropy": 5.596042013168335,
|
|
"epoch": 1.0144507456416718,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004902948344011506,
|
|
"loss": 5.3626,
|
|
"mean_token_accuracy": 0.16696448624134064,
|
|
"num_tokens": 22279170.0,
|
|
"step": 12075
|
|
},
|
|
{
|
|
"entropy": 5.681842565536499,
|
|
"epoch": 1.0148708254568368,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004902861321279694,
|
|
"loss": 5.4919,
|
|
"mean_token_accuracy": 0.16172150075435637,
|
|
"num_tokens": 22288788.0,
|
|
"step": 12080
|
|
},
|
|
{
|
|
"entropy": 5.57488694190979,
|
|
"epoch": 1.0152909052720016,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004902774260411055,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17076831310987473,
|
|
"num_tokens": 22297501.0,
|
|
"step": 12085
|
|
},
|
|
{
|
|
"entropy": 5.55194787979126,
|
|
"epoch": 1.0157109850871666,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004902687161407126,
|
|
"loss": 5.2508,
|
|
"mean_token_accuracy": 0.17739553600549698,
|
|
"num_tokens": 22306181.0,
|
|
"step": 12090
|
|
},
|
|
{
|
|
"entropy": 5.574270343780517,
|
|
"epoch": 1.0161310649023314,
|
|
"grad_norm": 2.03125,
|
|
"learning_rate": 0.0004902600024269454,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.17074478268623353,
|
|
"num_tokens": 22315762.0,
|
|
"step": 12095
|
|
},
|
|
{
|
|
"entropy": 5.56434326171875,
|
|
"epoch": 1.0165511447174964,
|
|
"grad_norm": 1.9140625,
|
|
"learning_rate": 0.000490251284899958,
|
|
"loss": 5.3602,
|
|
"mean_token_accuracy": 0.166584350168705,
|
|
"num_tokens": 22325127.0,
|
|
"step": 12100
|
|
},
|
|
{
|
|
"entropy": 5.566229295730591,
|
|
"epoch": 1.0169712245326612,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.000490242563559905,
|
|
"loss": 5.4461,
|
|
"mean_token_accuracy": 0.1646648034453392,
|
|
"num_tokens": 22334038.0,
|
|
"step": 12105
|
|
},
|
|
{
|
|
"entropy": 5.610032463073731,
|
|
"epoch": 1.017391304347826,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004902338384069408,
|
|
"loss": 5.2956,
|
|
"mean_token_accuracy": 0.17210006713867188,
|
|
"num_tokens": 22342658.0,
|
|
"step": 12110
|
|
},
|
|
{
|
|
"entropy": 5.700829744338989,
|
|
"epoch": 1.017811384162991,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00049022510944122,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.1618720069527626,
|
|
"num_tokens": 22352559.0,
|
|
"step": 12115
|
|
},
|
|
{
|
|
"entropy": 5.652797079086303,
|
|
"epoch": 1.0182314639781558,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004902163766628972,
|
|
"loss": 5.3819,
|
|
"mean_token_accuracy": 0.16738210171461104,
|
|
"num_tokens": 22361455.0,
|
|
"step": 12120
|
|
},
|
|
{
|
|
"entropy": 5.668959331512451,
|
|
"epoch": 1.0186515437933208,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004902076400721271,
|
|
"loss": 5.4144,
|
|
"mean_token_accuracy": 0.1660313591361046,
|
|
"num_tokens": 22371163.0,
|
|
"step": 12125
|
|
},
|
|
{
|
|
"entropy": 5.692332792282104,
|
|
"epoch": 1.0190716236084856,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004901988996690645,
|
|
"loss": 5.4026,
|
|
"mean_token_accuracy": 0.17311506420373918,
|
|
"num_tokens": 22379975.0,
|
|
"step": 12130
|
|
},
|
|
{
|
|
"entropy": 5.713879871368408,
|
|
"epoch": 1.0194917034236506,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004901901554538641,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.16618536561727523,
|
|
"num_tokens": 22389657.0,
|
|
"step": 12135
|
|
},
|
|
{
|
|
"entropy": 5.539191389083863,
|
|
"epoch": 1.0199117832388154,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000490181407426681,
|
|
"loss": 5.289,
|
|
"mean_token_accuracy": 0.17534529268741608,
|
|
"num_tokens": 22398320.0,
|
|
"step": 12140
|
|
},
|
|
{
|
|
"entropy": 5.5694207668304445,
|
|
"epoch": 1.0203318630539802,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004901726555876701,
|
|
"loss": 5.4911,
|
|
"mean_token_accuracy": 0.16052723973989486,
|
|
"num_tokens": 22406634.0,
|
|
"step": 12145
|
|
},
|
|
{
|
|
"entropy": 5.658481025695801,
|
|
"epoch": 1.0207519428691452,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004901638999369862,
|
|
"loss": 5.5276,
|
|
"mean_token_accuracy": 0.1623757913708687,
|
|
"num_tokens": 22415939.0,
|
|
"step": 12150
|
|
},
|
|
{
|
|
"entropy": 5.691515064239502,
|
|
"epoch": 1.02117202268431,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004901551404747847,
|
|
"loss": 5.4431,
|
|
"mean_token_accuracy": 0.16109129637479783,
|
|
"num_tokens": 22425256.0,
|
|
"step": 12155
|
|
},
|
|
{
|
|
"entropy": 5.649143648147583,
|
|
"epoch": 1.021592102499475,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004901463772012209,
|
|
"loss": 5.5128,
|
|
"mean_token_accuracy": 0.16139682829380037,
|
|
"num_tokens": 22434750.0,
|
|
"step": 12160
|
|
},
|
|
{
|
|
"entropy": 5.584879207611084,
|
|
"epoch": 1.0220121823146397,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004901376101164495,
|
|
"loss": 5.3978,
|
|
"mean_token_accuracy": 0.16362105011940004,
|
|
"num_tokens": 22443426.0,
|
|
"step": 12165
|
|
},
|
|
{
|
|
"entropy": 5.607901620864868,
|
|
"epoch": 1.0224322621298048,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.0004901288392206263,
|
|
"loss": 5.4015,
|
|
"mean_token_accuracy": 0.16088145673274995,
|
|
"num_tokens": 22452778.0,
|
|
"step": 12170
|
|
},
|
|
{
|
|
"entropy": 5.598963737487793,
|
|
"epoch": 1.0228523419449695,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004901200645139064,
|
|
"loss": 5.3614,
|
|
"mean_token_accuracy": 0.1733039990067482,
|
|
"num_tokens": 22462864.0,
|
|
"step": 12175
|
|
},
|
|
{
|
|
"entropy": 5.589771032333374,
|
|
"epoch": 1.0232724217601343,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004901112859964454,
|
|
"loss": 5.4078,
|
|
"mean_token_accuracy": 0.1707241028547287,
|
|
"num_tokens": 22472849.0,
|
|
"step": 12180
|
|
},
|
|
{
|
|
"entropy": 5.596211242675781,
|
|
"epoch": 1.0236925015752993,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004901025036683987,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.16777551621198655,
|
|
"num_tokens": 22481693.0,
|
|
"step": 12185
|
|
},
|
|
{
|
|
"entropy": 5.585362195968628,
|
|
"epoch": 1.0241125813904641,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004900937175299219,
|
|
"loss": 5.3664,
|
|
"mean_token_accuracy": 0.17000767588615417,
|
|
"num_tokens": 22490934.0,
|
|
"step": 12190
|
|
},
|
|
{
|
|
"entropy": 5.606501674652099,
|
|
"epoch": 1.0245326612056291,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004900849275811707,
|
|
"loss": 5.4103,
|
|
"mean_token_accuracy": 0.1638326808810234,
|
|
"num_tokens": 22500457.0,
|
|
"step": 12195
|
|
},
|
|
{
|
|
"entropy": 5.653303146362305,
|
|
"epoch": 1.024952741020794,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004900761338223007,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.16317504793405532,
|
|
"num_tokens": 22509641.0,
|
|
"step": 12200
|
|
},
|
|
{
|
|
"entropy": 5.549904870986938,
|
|
"epoch": 1.025372820835959,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004900673362534677,
|
|
"loss": 5.2831,
|
|
"mean_token_accuracy": 0.17752161622047424,
|
|
"num_tokens": 22518616.0,
|
|
"step": 12205
|
|
},
|
|
{
|
|
"entropy": 5.593005084991455,
|
|
"epoch": 1.0257929006511237,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004900585348748277,
|
|
"loss": 5.4345,
|
|
"mean_token_accuracy": 0.1716150164604187,
|
|
"num_tokens": 22527599.0,
|
|
"step": 12210
|
|
},
|
|
{
|
|
"entropy": 5.5883626461029055,
|
|
"epoch": 1.0262129804662885,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004900497296865365,
|
|
"loss": 5.4513,
|
|
"mean_token_accuracy": 0.15790560841560364,
|
|
"num_tokens": 22537399.0,
|
|
"step": 12215
|
|
},
|
|
{
|
|
"entropy": 5.835514545440674,
|
|
"epoch": 1.0266330602814535,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004900409206887499,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.15950456708669664,
|
|
"num_tokens": 22546746.0,
|
|
"step": 12220
|
|
},
|
|
{
|
|
"entropy": 5.738766622543335,
|
|
"epoch": 1.0270531400966183,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004900321078816243,
|
|
"loss": 5.4261,
|
|
"mean_token_accuracy": 0.1695483461022377,
|
|
"num_tokens": 22555735.0,
|
|
"step": 12225
|
|
},
|
|
{
|
|
"entropy": 5.64575343132019,
|
|
"epoch": 1.0274732199117833,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004900232912653156,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.16903394013643264,
|
|
"num_tokens": 22565010.0,
|
|
"step": 12230
|
|
},
|
|
{
|
|
"entropy": 5.622378730773926,
|
|
"epoch": 1.027893299726948,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00049001447083998,
|
|
"loss": 5.4049,
|
|
"mean_token_accuracy": 0.16650903224945068,
|
|
"num_tokens": 22573565.0,
|
|
"step": 12235
|
|
},
|
|
{
|
|
"entropy": 5.621281671524048,
|
|
"epoch": 1.028313379542113,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004900056466057737,
|
|
"loss": 5.3948,
|
|
"mean_token_accuracy": 0.1670803725719452,
|
|
"num_tokens": 22582549.0,
|
|
"step": 12240
|
|
},
|
|
{
|
|
"entropy": 5.609878969192505,
|
|
"epoch": 1.028733459357278,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004899968185628531,
|
|
"loss": 5.4517,
|
|
"mean_token_accuracy": 0.16443442553281784,
|
|
"num_tokens": 22592112.0,
|
|
"step": 12245
|
|
},
|
|
{
|
|
"entropy": 5.614514493942261,
|
|
"epoch": 1.0291535391724427,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004899879867113746,
|
|
"loss": 5.2862,
|
|
"mean_token_accuracy": 0.17238962799310684,
|
|
"num_tokens": 22600581.0,
|
|
"step": 12250
|
|
},
|
|
{
|
|
"entropy": 5.687255477905273,
|
|
"epoch": 1.0295736189876077,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004899791510514945,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.16246309280395507,
|
|
"num_tokens": 22610822.0,
|
|
"step": 12255
|
|
},
|
|
{
|
|
"entropy": 5.670682430267334,
|
|
"epoch": 1.0299936988027725,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004899703115833696,
|
|
"loss": 5.5025,
|
|
"mean_token_accuracy": 0.16369097977876662,
|
|
"num_tokens": 22619484.0,
|
|
"step": 12260
|
|
},
|
|
{
|
|
"entropy": 5.6433234214782715,
|
|
"epoch": 1.0304137786179375,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004899614683071563,
|
|
"loss": 5.3418,
|
|
"mean_token_accuracy": 0.16978320479393005,
|
|
"num_tokens": 22629038.0,
|
|
"step": 12265
|
|
},
|
|
{
|
|
"entropy": 5.630164051055909,
|
|
"epoch": 1.0308338584331023,
|
|
"grad_norm": 1.953125,
|
|
"learning_rate": 0.0004899526212230112,
|
|
"loss": 5.4258,
|
|
"mean_token_accuracy": 0.15771337747573852,
|
|
"num_tokens": 22638619.0,
|
|
"step": 12270
|
|
},
|
|
{
|
|
"entropy": 5.556281185150146,
|
|
"epoch": 1.0312539382482673,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004899437703310912,
|
|
"loss": 5.4118,
|
|
"mean_token_accuracy": 0.16302530169487,
|
|
"num_tokens": 22648065.0,
|
|
"step": 12275
|
|
},
|
|
{
|
|
"entropy": 5.7112713813781735,
|
|
"epoch": 1.031674018063432,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004899349156315529,
|
|
"loss": 5.4726,
|
|
"mean_token_accuracy": 0.16393186151981354,
|
|
"num_tokens": 22658107.0,
|
|
"step": 12280
|
|
},
|
|
{
|
|
"entropy": 5.662258052825928,
|
|
"epoch": 1.0320940978785969,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004899260571245533,
|
|
"loss": 5.3623,
|
|
"mean_token_accuracy": 0.17062537670135497,
|
|
"num_tokens": 22667103.0,
|
|
"step": 12285
|
|
},
|
|
{
|
|
"entropy": 5.555991840362549,
|
|
"epoch": 1.0325141776937619,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004899171948102492,
|
|
"loss": 5.3425,
|
|
"mean_token_accuracy": 0.16608135551214218,
|
|
"num_tokens": 22676792.0,
|
|
"step": 12290
|
|
},
|
|
{
|
|
"entropy": 5.612425088882446,
|
|
"epoch": 1.0329342575089266,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004899083286887977,
|
|
"loss": 5.3765,
|
|
"mean_token_accuracy": 0.16904007345438005,
|
|
"num_tokens": 22685344.0,
|
|
"step": 12295
|
|
},
|
|
{
|
|
"entropy": 5.665998268127441,
|
|
"epoch": 1.0333543373240917,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004898994587603559,
|
|
"loss": 5.4213,
|
|
"mean_token_accuracy": 0.1652013510465622,
|
|
"num_tokens": 22694387.0,
|
|
"step": 12300
|
|
},
|
|
{
|
|
"entropy": 5.581104946136475,
|
|
"epoch": 1.0337744171392564,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004898905850250807,
|
|
"loss": 5.4686,
|
|
"mean_token_accuracy": 0.16657924205064772,
|
|
"num_tokens": 22704203.0,
|
|
"step": 12305
|
|
},
|
|
{
|
|
"entropy": 5.690647602081299,
|
|
"epoch": 1.0341944969544214,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004898817074831295,
|
|
"loss": 5.5006,
|
|
"mean_token_accuracy": 0.16644016206264495,
|
|
"num_tokens": 22713518.0,
|
|
"step": 12310
|
|
},
|
|
{
|
|
"entropy": 5.730755805969238,
|
|
"epoch": 1.0346145767695862,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004898728261346595,
|
|
"loss": 5.5162,
|
|
"mean_token_accuracy": 0.15961872935295104,
|
|
"num_tokens": 22722997.0,
|
|
"step": 12315
|
|
},
|
|
{
|
|
"entropy": 5.690422677993775,
|
|
"epoch": 1.035034656584751,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000489863940979828,
|
|
"loss": 5.448,
|
|
"mean_token_accuracy": 0.1639517143368721,
|
|
"num_tokens": 22732385.0,
|
|
"step": 12320
|
|
},
|
|
{
|
|
"entropy": 5.5706113338470455,
|
|
"epoch": 1.035454736399916,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004898550520187925,
|
|
"loss": 5.3195,
|
|
"mean_token_accuracy": 0.17500197887420654,
|
|
"num_tokens": 22741148.0,
|
|
"step": 12325
|
|
},
|
|
{
|
|
"entropy": 5.583190250396728,
|
|
"epoch": 1.0358748162150808,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004898461592517103,
|
|
"loss": 5.3239,
|
|
"mean_token_accuracy": 0.17272863388061524,
|
|
"num_tokens": 22750239.0,
|
|
"step": 12330
|
|
},
|
|
{
|
|
"entropy": 5.684148597717285,
|
|
"epoch": 1.0362948960302458,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004898372626787391,
|
|
"loss": 5.4773,
|
|
"mean_token_accuracy": 0.16207296401262283,
|
|
"num_tokens": 22759290.0,
|
|
"step": 12335
|
|
},
|
|
{
|
|
"entropy": 5.689363956451416,
|
|
"epoch": 1.0367149758454106,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004898283623000364,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.15504724234342576,
|
|
"num_tokens": 22768450.0,
|
|
"step": 12340
|
|
},
|
|
{
|
|
"entropy": 5.665671014785767,
|
|
"epoch": 1.0371350556605754,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004898194581157598,
|
|
"loss": 5.3457,
|
|
"mean_token_accuracy": 0.16443716287612914,
|
|
"num_tokens": 22777711.0,
|
|
"step": 12345
|
|
},
|
|
{
|
|
"entropy": 5.654232358932495,
|
|
"epoch": 1.0375551354757404,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004898105501260671,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.16645502150058747,
|
|
"num_tokens": 22787153.0,
|
|
"step": 12350
|
|
},
|
|
{
|
|
"entropy": 5.686613702774048,
|
|
"epoch": 1.0379752152909052,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004898016383311163,
|
|
"loss": 5.4173,
|
|
"mean_token_accuracy": 0.1745339259505272,
|
|
"num_tokens": 22797125.0,
|
|
"step": 12355
|
|
},
|
|
{
|
|
"entropy": 5.6651740074157715,
|
|
"epoch": 1.0383952951060702,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000489792722731065,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.16517363041639327,
|
|
"num_tokens": 22806478.0,
|
|
"step": 12360
|
|
},
|
|
{
|
|
"entropy": 5.676910877227783,
|
|
"epoch": 1.038815374921235,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004897838033260712,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.15935799479484558,
|
|
"num_tokens": 22815375.0,
|
|
"step": 12365
|
|
},
|
|
{
|
|
"entropy": 5.680210399627685,
|
|
"epoch": 1.0392354547364,
|
|
"grad_norm": 2.359375,
|
|
"learning_rate": 0.0004897748801162929,
|
|
"loss": 5.4069,
|
|
"mean_token_accuracy": 0.16446397304534913,
|
|
"num_tokens": 22824401.0,
|
|
"step": 12370
|
|
},
|
|
{
|
|
"entropy": 5.650290250778198,
|
|
"epoch": 1.0396555345515648,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004897659531018882,
|
|
"loss": 5.5155,
|
|
"mean_token_accuracy": 0.1638687551021576,
|
|
"num_tokens": 22833933.0,
|
|
"step": 12375
|
|
},
|
|
{
|
|
"entropy": 5.5616044998168945,
|
|
"epoch": 1.0400756143667296,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004897570222830152,
|
|
"loss": 5.3881,
|
|
"mean_token_accuracy": 0.16457553654909135,
|
|
"num_tokens": 22843779.0,
|
|
"step": 12380
|
|
},
|
|
{
|
|
"entropy": 5.750216913223267,
|
|
"epoch": 1.0404956941818946,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004897480876598322,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.16095164567232131,
|
|
"num_tokens": 22852951.0,
|
|
"step": 12385
|
|
},
|
|
{
|
|
"entropy": 5.728332042694092,
|
|
"epoch": 1.0409157739970594,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004897391492324974,
|
|
"loss": 5.4784,
|
|
"mean_token_accuracy": 0.16274571269750596,
|
|
"num_tokens": 22861398.0,
|
|
"step": 12390
|
|
},
|
|
{
|
|
"entropy": 5.6263368129730225,
|
|
"epoch": 1.0413358538122244,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004897302070011691,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.17079239189624787,
|
|
"num_tokens": 22870518.0,
|
|
"step": 12395
|
|
},
|
|
{
|
|
"entropy": 5.606213474273682,
|
|
"epoch": 1.0417559336273892,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004897212609660058,
|
|
"loss": 5.4476,
|
|
"mean_token_accuracy": 0.1651351511478424,
|
|
"num_tokens": 22879389.0,
|
|
"step": 12400
|
|
},
|
|
{
|
|
"entropy": 5.606588840484619,
|
|
"epoch": 1.0421760134425542,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004897123111271659,
|
|
"loss": 5.4434,
|
|
"mean_token_accuracy": 0.17210057824850084,
|
|
"num_tokens": 22888977.0,
|
|
"step": 12405
|
|
},
|
|
{
|
|
"entropy": 5.714909410476684,
|
|
"epoch": 1.042596093257719,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004897033574848079,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.16815780401229857,
|
|
"num_tokens": 22898446.0,
|
|
"step": 12410
|
|
},
|
|
{
|
|
"entropy": 5.635931825637817,
|
|
"epoch": 1.0430161730728837,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004896944000390907,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.16541572213172911,
|
|
"num_tokens": 22908044.0,
|
|
"step": 12415
|
|
},
|
|
{
|
|
"entropy": 5.68047137260437,
|
|
"epoch": 1.0434362528880488,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004896854387901725,
|
|
"loss": 5.5176,
|
|
"mean_token_accuracy": 0.15805390030145644,
|
|
"num_tokens": 22917330.0,
|
|
"step": 12420
|
|
},
|
|
{
|
|
"entropy": 5.704816675186157,
|
|
"epoch": 1.0438563327032135,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004896764737382124,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.17054068595170974,
|
|
"num_tokens": 22927160.0,
|
|
"step": 12425
|
|
},
|
|
{
|
|
"entropy": 5.693249273300171,
|
|
"epoch": 1.0442764125183785,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004896675048833691,
|
|
"loss": 5.4172,
|
|
"mean_token_accuracy": 0.16629046201705933,
|
|
"num_tokens": 22936755.0,
|
|
"step": 12430
|
|
},
|
|
{
|
|
"entropy": 5.65311713218689,
|
|
"epoch": 1.0446964923335433,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004896585322258014,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.16618072092533112,
|
|
"num_tokens": 22945699.0,
|
|
"step": 12435
|
|
},
|
|
{
|
|
"entropy": 5.583677911758423,
|
|
"epoch": 1.0451165721487083,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896495557656685,
|
|
"loss": 5.3931,
|
|
"mean_token_accuracy": 0.17709663063287734,
|
|
"num_tokens": 22954001.0,
|
|
"step": 12440
|
|
},
|
|
{
|
|
"entropy": 5.696814155578613,
|
|
"epoch": 1.0455366519638731,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004896405755031293,
|
|
"loss": 5.4766,
|
|
"mean_token_accuracy": 0.16204729974269866,
|
|
"num_tokens": 22963805.0,
|
|
"step": 12445
|
|
},
|
|
{
|
|
"entropy": 5.61180157661438,
|
|
"epoch": 1.045956731779038,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004896315914383427,
|
|
"loss": 5.4318,
|
|
"mean_token_accuracy": 0.15509928911924362,
|
|
"num_tokens": 22973542.0,
|
|
"step": 12450
|
|
},
|
|
{
|
|
"entropy": 5.540133476257324,
|
|
"epoch": 1.046376811594203,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004896226035714679,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.17043613642454147,
|
|
"num_tokens": 22982417.0,
|
|
"step": 12455
|
|
},
|
|
{
|
|
"entropy": 5.597504425048828,
|
|
"epoch": 1.0467968914093677,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.0004896136119026642,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.16592884063720703,
|
|
"num_tokens": 22992879.0,
|
|
"step": 12460
|
|
},
|
|
{
|
|
"entropy": 5.59436526298523,
|
|
"epoch": 1.0472169712245327,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004896046164320911,
|
|
"loss": 5.3045,
|
|
"mean_token_accuracy": 0.17583135962486268,
|
|
"num_tokens": 23001344.0,
|
|
"step": 12465
|
|
},
|
|
{
|
|
"entropy": 5.55146484375,
|
|
"epoch": 1.0476370510396975,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004895956171599075,
|
|
"loss": 5.3568,
|
|
"mean_token_accuracy": 0.1739198938012123,
|
|
"num_tokens": 23010007.0,
|
|
"step": 12470
|
|
},
|
|
{
|
|
"entropy": 5.65653715133667,
|
|
"epoch": 1.0480571308548625,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004895866140862731,
|
|
"loss": 5.4797,
|
|
"mean_token_accuracy": 0.16263213604688645,
|
|
"num_tokens": 23019120.0,
|
|
"step": 12475
|
|
},
|
|
{
|
|
"entropy": 5.662118196487427,
|
|
"epoch": 1.0484772106700273,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004895776072113473,
|
|
"loss": 5.4555,
|
|
"mean_token_accuracy": 0.1633812740445137,
|
|
"num_tokens": 23028562.0,
|
|
"step": 12480
|
|
},
|
|
{
|
|
"entropy": 5.583648824691773,
|
|
"epoch": 1.048897290485192,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004895685965352898,
|
|
"loss": 5.4124,
|
|
"mean_token_accuracy": 0.1627751737833023,
|
|
"num_tokens": 23037687.0,
|
|
"step": 12485
|
|
},
|
|
{
|
|
"entropy": 5.637997770309449,
|
|
"epoch": 1.049317370300357,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004895595820582601,
|
|
"loss": 5.3911,
|
|
"mean_token_accuracy": 0.16933690309524535,
|
|
"num_tokens": 23047475.0,
|
|
"step": 12490
|
|
},
|
|
{
|
|
"entropy": 5.622006130218506,
|
|
"epoch": 1.0497374501155219,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004895505637804177,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.164679816365242,
|
|
"num_tokens": 23057475.0,
|
|
"step": 12495
|
|
},
|
|
{
|
|
"entropy": 5.546265506744385,
|
|
"epoch": 1.050157529930687,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004895415417019227,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.16429776102304458,
|
|
"num_tokens": 23066419.0,
|
|
"step": 12500
|
|
},
|
|
{
|
|
"entropy": 5.677910614013672,
|
|
"epoch": 1.0505776097458517,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004895325158229346,
|
|
"loss": 5.456,
|
|
"mean_token_accuracy": 0.16541764587163926,
|
|
"num_tokens": 23075516.0,
|
|
"step": 12505
|
|
},
|
|
{
|
|
"entropy": 5.615484428405762,
|
|
"epoch": 1.0509976895610167,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004895234861436136,
|
|
"loss": 5.345,
|
|
"mean_token_accuracy": 0.1746780276298523,
|
|
"num_tokens": 23084132.0,
|
|
"step": 12510
|
|
},
|
|
{
|
|
"entropy": 5.671827888488769,
|
|
"epoch": 1.0514177693761815,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004895144526641194,
|
|
"loss": 5.4084,
|
|
"mean_token_accuracy": 0.16155407577753067,
|
|
"num_tokens": 23093958.0,
|
|
"step": 12515
|
|
},
|
|
{
|
|
"entropy": 5.699568223953247,
|
|
"epoch": 1.0518378491913463,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004895054153846123,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.15948740541934966,
|
|
"num_tokens": 23103524.0,
|
|
"step": 12520
|
|
},
|
|
{
|
|
"entropy": 5.5832483768463135,
|
|
"epoch": 1.0522579290065113,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004894963743052521,
|
|
"loss": 5.366,
|
|
"mean_token_accuracy": 0.1638748675584793,
|
|
"num_tokens": 23112445.0,
|
|
"step": 12525
|
|
},
|
|
{
|
|
"entropy": 5.661851692199707,
|
|
"epoch": 1.052678008821676,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004894873294261991,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.16422830671072006,
|
|
"num_tokens": 23121299.0,
|
|
"step": 12530
|
|
},
|
|
{
|
|
"entropy": 5.722447490692138,
|
|
"epoch": 1.053098088636841,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.0004894782807476134,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16310823261737822,
|
|
"num_tokens": 23130260.0,
|
|
"step": 12535
|
|
},
|
|
{
|
|
"entropy": 5.64654655456543,
|
|
"epoch": 1.0535181684520059,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004894692282696555,
|
|
"loss": 5.3685,
|
|
"mean_token_accuracy": 0.16636543869972228,
|
|
"num_tokens": 23139335.0,
|
|
"step": 12540
|
|
},
|
|
{
|
|
"entropy": 5.5218949794769285,
|
|
"epoch": 1.0539382482671709,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004894601719924857,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.17038656622171403,
|
|
"num_tokens": 23149299.0,
|
|
"step": 12545
|
|
},
|
|
{
|
|
"entropy": 5.543263053894043,
|
|
"epoch": 1.0543583280823356,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004894511119162644,
|
|
"loss": 5.3341,
|
|
"mean_token_accuracy": 0.17221007347106934,
|
|
"num_tokens": 23158651.0,
|
|
"step": 12550
|
|
},
|
|
{
|
|
"entropy": 5.678027200698852,
|
|
"epoch": 1.0547784078975004,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000489442048041152,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.15821332037448882,
|
|
"num_tokens": 23167629.0,
|
|
"step": 12555
|
|
},
|
|
{
|
|
"entropy": 5.635254526138306,
|
|
"epoch": 1.0551984877126654,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004894329803673092,
|
|
"loss": 5.416,
|
|
"mean_token_accuracy": 0.16229169964790344,
|
|
"num_tokens": 23177026.0,
|
|
"step": 12560
|
|
},
|
|
{
|
|
"entropy": 5.622007846832275,
|
|
"epoch": 1.0556185675278302,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004894239088948964,
|
|
"loss": 5.3761,
|
|
"mean_token_accuracy": 0.16643615067005157,
|
|
"num_tokens": 23185297.0,
|
|
"step": 12565
|
|
},
|
|
{
|
|
"entropy": 5.585867691040039,
|
|
"epoch": 1.0560386473429952,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004894148336240747,
|
|
"loss": 5.3981,
|
|
"mean_token_accuracy": 0.16961814016103743,
|
|
"num_tokens": 23194804.0,
|
|
"step": 12570
|
|
},
|
|
{
|
|
"entropy": 5.6445718765258786,
|
|
"epoch": 1.05645872715816,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004894057545550045,
|
|
"loss": 5.4304,
|
|
"mean_token_accuracy": 0.1647735506296158,
|
|
"num_tokens": 23205063.0,
|
|
"step": 12575
|
|
},
|
|
{
|
|
"entropy": 5.633014106750489,
|
|
"epoch": 1.056878806973325,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.0004893966716878467,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.16172896772623063,
|
|
"num_tokens": 23215038.0,
|
|
"step": 12580
|
|
},
|
|
{
|
|
"entropy": 5.695857429504395,
|
|
"epoch": 1.0572988867884898,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004893875850227624,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.16041227877140046,
|
|
"num_tokens": 23223530.0,
|
|
"step": 12585
|
|
},
|
|
{
|
|
"entropy": 5.65571699142456,
|
|
"epoch": 1.0577189666036546,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004893784945599124,
|
|
"loss": 5.4589,
|
|
"mean_token_accuracy": 0.16575109511613845,
|
|
"num_tokens": 23232547.0,
|
|
"step": 12590
|
|
},
|
|
{
|
|
"entropy": 5.610851764678955,
|
|
"epoch": 1.0581390464188196,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004893694002994577,
|
|
"loss": 5.4865,
|
|
"mean_token_accuracy": 0.16560802906751632,
|
|
"num_tokens": 23241305.0,
|
|
"step": 12595
|
|
},
|
|
{
|
|
"entropy": 5.7720519542694095,
|
|
"epoch": 1.0585591262339844,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004893603022415595,
|
|
"loss": 5.5079,
|
|
"mean_token_accuracy": 0.16662406772375107,
|
|
"num_tokens": 23250708.0,
|
|
"step": 12600
|
|
},
|
|
{
|
|
"entropy": 5.691384363174438,
|
|
"epoch": 1.0589792060491494,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004893512003863788,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.15989451110363007,
|
|
"num_tokens": 23260161.0,
|
|
"step": 12605
|
|
},
|
|
{
|
|
"entropy": 5.570341491699219,
|
|
"epoch": 1.0593992858643142,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004893420947340771,
|
|
"loss": 5.3169,
|
|
"mean_token_accuracy": 0.16430822163820266,
|
|
"num_tokens": 23268932.0,
|
|
"step": 12610
|
|
},
|
|
{
|
|
"entropy": 5.551045656204224,
|
|
"epoch": 1.0598193656794792,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004893329852848155,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.1701897993683815,
|
|
"num_tokens": 23277741.0,
|
|
"step": 12615
|
|
},
|
|
{
|
|
"entropy": 5.573561477661133,
|
|
"epoch": 1.060239445494644,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004893238720387555,
|
|
"loss": 5.4199,
|
|
"mean_token_accuracy": 0.16308623701334,
|
|
"num_tokens": 23286982.0,
|
|
"step": 12620
|
|
},
|
|
{
|
|
"entropy": 5.668636322021484,
|
|
"epoch": 1.0606595253098088,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004893147549960584,
|
|
"loss": 5.3587,
|
|
"mean_token_accuracy": 0.16592552214860917,
|
|
"num_tokens": 23296902.0,
|
|
"step": 12625
|
|
},
|
|
{
|
|
"entropy": 5.609336996078492,
|
|
"epoch": 1.0610796051249738,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004893056341568857,
|
|
"loss": 5.3749,
|
|
"mean_token_accuracy": 0.174351204931736,
|
|
"num_tokens": 23305443.0,
|
|
"step": 12630
|
|
},
|
|
{
|
|
"entropy": 5.561859083175659,
|
|
"epoch": 1.0614996849401386,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004892965095213992,
|
|
"loss": 5.3316,
|
|
"mean_token_accuracy": 0.1718878448009491,
|
|
"num_tokens": 23315420.0,
|
|
"step": 12635
|
|
},
|
|
{
|
|
"entropy": 5.622679424285889,
|
|
"epoch": 1.0619197647553036,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.0004892873810897604,
|
|
"loss": 5.4359,
|
|
"mean_token_accuracy": 0.16049171537160872,
|
|
"num_tokens": 23324540.0,
|
|
"step": 12640
|
|
},
|
|
{
|
|
"entropy": 5.616107416152954,
|
|
"epoch": 1.0623398445704684,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.0004892782488621308,
|
|
"loss": 5.3718,
|
|
"mean_token_accuracy": 0.1706625148653984,
|
|
"num_tokens": 23334282.0,
|
|
"step": 12645
|
|
},
|
|
{
|
|
"entropy": 5.657419586181641,
|
|
"epoch": 1.0627599243856332,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004892691128386725,
|
|
"loss": 5.3693,
|
|
"mean_token_accuracy": 0.16586438268423082,
|
|
"num_tokens": 23342836.0,
|
|
"step": 12650
|
|
},
|
|
{
|
|
"entropy": 5.64911413192749,
|
|
"epoch": 1.0631800042007982,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004892599730195471,
|
|
"loss": 5.3567,
|
|
"mean_token_accuracy": 0.1705513373017311,
|
|
"num_tokens": 23351863.0,
|
|
"step": 12655
|
|
},
|
|
{
|
|
"entropy": 5.720103025436401,
|
|
"epoch": 1.063600084015963,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004892508294049167,
|
|
"loss": 5.4967,
|
|
"mean_token_accuracy": 0.1687561333179474,
|
|
"num_tokens": 23361788.0,
|
|
"step": 12660
|
|
},
|
|
{
|
|
"entropy": 5.59014482498169,
|
|
"epoch": 1.064020163831128,
|
|
"grad_norm": 2.046875,
|
|
"learning_rate": 0.0004892416819949431,
|
|
"loss": 5.3525,
|
|
"mean_token_accuracy": 0.16308819353580475,
|
|
"num_tokens": 23370175.0,
|
|
"step": 12665
|
|
},
|
|
{
|
|
"entropy": 5.52400312423706,
|
|
"epoch": 1.0644402436462927,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004892325307897886,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.16833132803440093,
|
|
"num_tokens": 23378835.0,
|
|
"step": 12670
|
|
},
|
|
{
|
|
"entropy": 5.621381092071533,
|
|
"epoch": 1.0648603234614578,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004892233757896149,
|
|
"loss": 5.4064,
|
|
"mean_token_accuracy": 0.16472738981246948,
|
|
"num_tokens": 23389390.0,
|
|
"step": 12675
|
|
},
|
|
{
|
|
"entropy": 5.648614740371704,
|
|
"epoch": 1.0652804032766225,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.0004892142169945845,
|
|
"loss": 5.4098,
|
|
"mean_token_accuracy": 0.1647957906126976,
|
|
"num_tokens": 23398802.0,
|
|
"step": 12680
|
|
},
|
|
{
|
|
"entropy": 5.630923318862915,
|
|
"epoch": 1.0657004830917876,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004892050544048596,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.16518343836069108,
|
|
"num_tokens": 23407731.0,
|
|
"step": 12685
|
|
},
|
|
{
|
|
"entropy": 5.618378114700318,
|
|
"epoch": 1.0661205629069523,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004891958880206024,
|
|
"loss": 5.4326,
|
|
"mean_token_accuracy": 0.16275406628847122,
|
|
"num_tokens": 23417046.0,
|
|
"step": 12690
|
|
},
|
|
{
|
|
"entropy": 5.613988065719605,
|
|
"epoch": 1.0665406427221171,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004891867178419753,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.1696673572063446,
|
|
"num_tokens": 23426107.0,
|
|
"step": 12695
|
|
},
|
|
{
|
|
"entropy": 5.662841749191284,
|
|
"epoch": 1.0669607225372821,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004891775438691408,
|
|
"loss": 5.4467,
|
|
"mean_token_accuracy": 0.1709218829870224,
|
|
"num_tokens": 23435523.0,
|
|
"step": 12700
|
|
},
|
|
{
|
|
"entropy": 5.624844980239868,
|
|
"epoch": 1.067380802352447,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004891683661022615,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.17338791787624358,
|
|
"num_tokens": 23444185.0,
|
|
"step": 12705
|
|
},
|
|
{
|
|
"entropy": 5.768259763717651,
|
|
"epoch": 1.067800882167612,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004891591845414997,
|
|
"loss": 5.6144,
|
|
"mean_token_accuracy": 0.14980095773935317,
|
|
"num_tokens": 23454100.0,
|
|
"step": 12710
|
|
},
|
|
{
|
|
"entropy": 5.727353096008301,
|
|
"epoch": 1.0682209619827767,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004891499991870184,
|
|
"loss": 5.4873,
|
|
"mean_token_accuracy": 0.16231284141540528,
|
|
"num_tokens": 23463415.0,
|
|
"step": 12715
|
|
},
|
|
{
|
|
"entropy": 5.651056814193725,
|
|
"epoch": 1.0686410417979415,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048914081003898,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.16605685353279115,
|
|
"num_tokens": 23471515.0,
|
|
"step": 12720
|
|
},
|
|
{
|
|
"entropy": 5.669055986404419,
|
|
"epoch": 1.0690611216131065,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004891316170975475,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.16459901630878448,
|
|
"num_tokens": 23481696.0,
|
|
"step": 12725
|
|
},
|
|
{
|
|
"entropy": 5.720963811874389,
|
|
"epoch": 1.0694812014282713,
|
|
"grad_norm": 1.7890625,
|
|
"learning_rate": 0.0004891224203628836,
|
|
"loss": 5.4151,
|
|
"mean_token_accuracy": 0.17059700489044188,
|
|
"num_tokens": 23490714.0,
|
|
"step": 12730
|
|
},
|
|
{
|
|
"entropy": 5.59767165184021,
|
|
"epoch": 1.0699012812434363,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004891132198351514,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.17071119844913482,
|
|
"num_tokens": 23500368.0,
|
|
"step": 12735
|
|
},
|
|
{
|
|
"entropy": 5.492298889160156,
|
|
"epoch": 1.070321361058601,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.0004891040155145137,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.17299245446920394,
|
|
"num_tokens": 23508857.0,
|
|
"step": 12740
|
|
},
|
|
{
|
|
"entropy": 5.555435657501221,
|
|
"epoch": 1.070741440873766,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004890948074011335,
|
|
"loss": 5.3092,
|
|
"mean_token_accuracy": 0.17295463085174562,
|
|
"num_tokens": 23518128.0,
|
|
"step": 12745
|
|
},
|
|
{
|
|
"entropy": 5.670081424713135,
|
|
"epoch": 1.071161520688931,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004890855954951741,
|
|
"loss": 5.4175,
|
|
"mean_token_accuracy": 0.17026563137769699,
|
|
"num_tokens": 23527292.0,
|
|
"step": 12750
|
|
},
|
|
{
|
|
"entropy": 5.697415733337403,
|
|
"epoch": 1.0715816005040957,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004890763797967987,
|
|
"loss": 5.4211,
|
|
"mean_token_accuracy": 0.16530265808105468,
|
|
"num_tokens": 23535694.0,
|
|
"step": 12755
|
|
},
|
|
{
|
|
"entropy": 5.633253765106201,
|
|
"epoch": 1.0720016803192607,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004890671603061704,
|
|
"loss": 5.41,
|
|
"mean_token_accuracy": 0.16988277137279512,
|
|
"num_tokens": 23544766.0,
|
|
"step": 12760
|
|
},
|
|
{
|
|
"entropy": 5.59822449684143,
|
|
"epoch": 1.0724217601344255,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004890579370234526,
|
|
"loss": 5.3867,
|
|
"mean_token_accuracy": 0.17475670129060744,
|
|
"num_tokens": 23554037.0,
|
|
"step": 12765
|
|
},
|
|
{
|
|
"entropy": 5.654851055145263,
|
|
"epoch": 1.0728418399495905,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004890487099488086,
|
|
"loss": 5.4579,
|
|
"mean_token_accuracy": 0.16293169558048248,
|
|
"num_tokens": 23562282.0,
|
|
"step": 12770
|
|
},
|
|
{
|
|
"entropy": 5.716164493560791,
|
|
"epoch": 1.0732619197647553,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.000489039479082402,
|
|
"loss": 5.496,
|
|
"mean_token_accuracy": 0.15957446098327638,
|
|
"num_tokens": 23571955.0,
|
|
"step": 12775
|
|
},
|
|
{
|
|
"entropy": 5.642240190505982,
|
|
"epoch": 1.0736819995799203,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004890302444243962,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.16422138661146163,
|
|
"num_tokens": 23580996.0,
|
|
"step": 12780
|
|
},
|
|
{
|
|
"entropy": 5.6740892887115475,
|
|
"epoch": 1.074102079395085,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004890210059749549,
|
|
"loss": 5.5027,
|
|
"mean_token_accuracy": 0.15336771160364152,
|
|
"num_tokens": 23589618.0,
|
|
"step": 12785
|
|
},
|
|
{
|
|
"entropy": 5.63664698600769,
|
|
"epoch": 1.0745221592102498,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004890117637342416,
|
|
"loss": 5.34,
|
|
"mean_token_accuracy": 0.16738679707050325,
|
|
"num_tokens": 23599574.0,
|
|
"step": 12790
|
|
},
|
|
{
|
|
"entropy": 5.629761743545532,
|
|
"epoch": 1.0749422390254149,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004890025177024202,
|
|
"loss": 5.4003,
|
|
"mean_token_accuracy": 0.16000826209783553,
|
|
"num_tokens": 23609205.0,
|
|
"step": 12795
|
|
},
|
|
{
|
|
"entropy": 5.607318305969239,
|
|
"epoch": 1.0753623188405796,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004889932678796543,
|
|
"loss": 5.4182,
|
|
"mean_token_accuracy": 0.15812145173549652,
|
|
"num_tokens": 23617554.0,
|
|
"step": 12800
|
|
},
|
|
{
|
|
"entropy": 5.6223344802856445,
|
|
"epoch": 1.0757823986557447,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004889840142661078,
|
|
"loss": 5.4894,
|
|
"mean_token_accuracy": 0.16154404506087303,
|
|
"num_tokens": 23626757.0,
|
|
"step": 12805
|
|
},
|
|
{
|
|
"entropy": 5.682391214370727,
|
|
"epoch": 1.0762024784709094,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004889747568619447,
|
|
"loss": 5.422,
|
|
"mean_token_accuracy": 0.16666488647460936,
|
|
"num_tokens": 23636111.0,
|
|
"step": 12810
|
|
},
|
|
{
|
|
"entropy": 5.675402879714966,
|
|
"epoch": 1.0766225582860744,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004889654956673291,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.16374361217021943,
|
|
"num_tokens": 23644579.0,
|
|
"step": 12815
|
|
},
|
|
{
|
|
"entropy": 5.6301075458526615,
|
|
"epoch": 1.0770426381012392,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004889562306824248,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.16753521859645842,
|
|
"num_tokens": 23653263.0,
|
|
"step": 12820
|
|
},
|
|
{
|
|
"entropy": 5.493171119689942,
|
|
"epoch": 1.077462717916404,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.000488946961907396,
|
|
"loss": 5.2889,
|
|
"mean_token_accuracy": 0.17843078672885895,
|
|
"num_tokens": 23662529.0,
|
|
"step": 12825
|
|
},
|
|
{
|
|
"entropy": 5.500955486297608,
|
|
"epoch": 1.077882797731569,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004889376893424071,
|
|
"loss": 5.3314,
|
|
"mean_token_accuracy": 0.17671893090009688,
|
|
"num_tokens": 23671491.0,
|
|
"step": 12830
|
|
},
|
|
{
|
|
"entropy": 5.594093990325928,
|
|
"epoch": 1.0783028775467338,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004889284129876221,
|
|
"loss": 5.3215,
|
|
"mean_token_accuracy": 0.17135681062936783,
|
|
"num_tokens": 23680121.0,
|
|
"step": 12835
|
|
},
|
|
{
|
|
"entropy": 5.652432584762574,
|
|
"epoch": 1.0787229573618988,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004889191328432054,
|
|
"loss": 5.3861,
|
|
"mean_token_accuracy": 0.16644245833158494,
|
|
"num_tokens": 23689008.0,
|
|
"step": 12840
|
|
},
|
|
{
|
|
"entropy": 5.633866977691651,
|
|
"epoch": 1.0791430371770636,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0004889098489093215,
|
|
"loss": 5.4145,
|
|
"mean_token_accuracy": 0.1661999359726906,
|
|
"num_tokens": 23698551.0,
|
|
"step": 12845
|
|
},
|
|
{
|
|
"entropy": 5.737457704544068,
|
|
"epoch": 1.0795631169922286,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004889005611861347,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.16424480825662613,
|
|
"num_tokens": 23707438.0,
|
|
"step": 12850
|
|
},
|
|
{
|
|
"entropy": 5.6380579471588135,
|
|
"epoch": 1.0799831968073934,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.0004888912696738096,
|
|
"loss": 5.4216,
|
|
"mean_token_accuracy": 0.16508191749453544,
|
|
"num_tokens": 23715822.0,
|
|
"step": 12855
|
|
},
|
|
{
|
|
"entropy": 5.665700483322143,
|
|
"epoch": 1.0804032766225582,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004888819743725108,
|
|
"loss": 5.4439,
|
|
"mean_token_accuracy": 0.1673838436603546,
|
|
"num_tokens": 23725426.0,
|
|
"step": 12860
|
|
},
|
|
{
|
|
"entropy": 5.660395002365112,
|
|
"epoch": 1.0808233564377232,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000488872675282403,
|
|
"loss": 5.4191,
|
|
"mean_token_accuracy": 0.16672058403491974,
|
|
"num_tokens": 23735092.0,
|
|
"step": 12865
|
|
},
|
|
{
|
|
"entropy": 5.6598817825317385,
|
|
"epoch": 1.081243436252888,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004888633724036509,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.16880684196949006,
|
|
"num_tokens": 23744255.0,
|
|
"step": 12870
|
|
},
|
|
{
|
|
"entropy": 5.572845077514648,
|
|
"epoch": 1.081663516068053,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0004888540657364192,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.17684861570596694,
|
|
"num_tokens": 23752978.0,
|
|
"step": 12875
|
|
},
|
|
{
|
|
"entropy": 5.612951946258545,
|
|
"epoch": 1.0820835958832178,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004888447552808729,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.16552072912454605,
|
|
"num_tokens": 23761051.0,
|
|
"step": 12880
|
|
},
|
|
{
|
|
"entropy": 5.67154974937439,
|
|
"epoch": 1.0825036756983828,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004888354410371768,
|
|
"loss": 5.4789,
|
|
"mean_token_accuracy": 0.15792061686515807,
|
|
"num_tokens": 23770818.0,
|
|
"step": 12885
|
|
},
|
|
{
|
|
"entropy": 5.746588897705078,
|
|
"epoch": 1.0829237555135476,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000488826123005496,
|
|
"loss": 5.4892,
|
|
"mean_token_accuracy": 0.16944090873003007,
|
|
"num_tokens": 23780597.0,
|
|
"step": 12890
|
|
},
|
|
{
|
|
"entropy": 5.60015287399292,
|
|
"epoch": 1.0833438353287124,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004888168011859957,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.16784373819828033,
|
|
"num_tokens": 23790119.0,
|
|
"step": 12895
|
|
},
|
|
{
|
|
"entropy": 5.59284782409668,
|
|
"epoch": 1.0837639151438774,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004888074755788407,
|
|
"loss": 5.4074,
|
|
"mean_token_accuracy": 0.1683492362499237,
|
|
"num_tokens": 23798972.0,
|
|
"step": 12900
|
|
},
|
|
{
|
|
"entropy": 5.622417688369751,
|
|
"epoch": 1.0841839949590422,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004887981461841963,
|
|
"loss": 5.3743,
|
|
"mean_token_accuracy": 0.17346876859664917,
|
|
"num_tokens": 23808685.0,
|
|
"step": 12905
|
|
},
|
|
{
|
|
"entropy": 5.64064130783081,
|
|
"epoch": 1.0846040747742072,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004887888130022279,
|
|
"loss": 5.3748,
|
|
"mean_token_accuracy": 0.16767643988132477,
|
|
"num_tokens": 23817721.0,
|
|
"step": 12910
|
|
},
|
|
{
|
|
"entropy": 5.5321691036224365,
|
|
"epoch": 1.085024154589372,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004887794760331008,
|
|
"loss": 5.3404,
|
|
"mean_token_accuracy": 0.16723188161849975,
|
|
"num_tokens": 23826892.0,
|
|
"step": 12915
|
|
},
|
|
{
|
|
"entropy": 5.568603563308716,
|
|
"epoch": 1.085444234404537,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004887701352769804,
|
|
"loss": 5.2879,
|
|
"mean_token_accuracy": 0.1780572459101677,
|
|
"num_tokens": 23835717.0,
|
|
"step": 12920
|
|
},
|
|
{
|
|
"entropy": 5.583135890960693,
|
|
"epoch": 1.0858643142197018,
|
|
"grad_norm": 1.7578125,
|
|
"learning_rate": 0.000488760790734032,
|
|
"loss": 5.4029,
|
|
"mean_token_accuracy": 0.1701557457447052,
|
|
"num_tokens": 23845814.0,
|
|
"step": 12925
|
|
},
|
|
{
|
|
"entropy": 5.669702625274658,
|
|
"epoch": 1.0862843940348665,
|
|
"grad_norm": 1.8046875,
|
|
"learning_rate": 0.0004887514424044214,
|
|
"loss": 5.3864,
|
|
"mean_token_accuracy": 0.16005658805370332,
|
|
"num_tokens": 23854779.0,
|
|
"step": 12930
|
|
},
|
|
{
|
|
"entropy": 5.590376663208008,
|
|
"epoch": 1.0867044738500315,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000488742090288314,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.16315811723470688,
|
|
"num_tokens": 23863533.0,
|
|
"step": 12935
|
|
},
|
|
{
|
|
"entropy": 5.5997072696685795,
|
|
"epoch": 1.0871245536651963,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004887327343858755,
|
|
"loss": 5.4511,
|
|
"mean_token_accuracy": 0.16439618468284606,
|
|
"num_tokens": 23872725.0,
|
|
"step": 12940
|
|
},
|
|
{
|
|
"entropy": 5.6145484924316404,
|
|
"epoch": 1.0875446334803613,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004887233746972717,
|
|
"loss": 5.4415,
|
|
"mean_token_accuracy": 0.16163852512836457,
|
|
"num_tokens": 23881799.0,
|
|
"step": 12945
|
|
},
|
|
{
|
|
"entropy": 5.652968406677246,
|
|
"epoch": 1.0879647132955261,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004887140112226684,
|
|
"loss": 5.4582,
|
|
"mean_token_accuracy": 0.16318671107292176,
|
|
"num_tokens": 23890628.0,
|
|
"step": 12950
|
|
},
|
|
{
|
|
"entropy": 5.651101064682007,
|
|
"epoch": 1.088384793110691,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004887046439622314,
|
|
"loss": 5.4392,
|
|
"mean_token_accuracy": 0.17248670607805253,
|
|
"num_tokens": 23899968.0,
|
|
"step": 12955
|
|
},
|
|
{
|
|
"entropy": 5.665786266326904,
|
|
"epoch": 1.088804872925856,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004886952729161267,
|
|
"loss": 5.3178,
|
|
"mean_token_accuracy": 0.16974089592695235,
|
|
"num_tokens": 23908634.0,
|
|
"step": 12960
|
|
},
|
|
{
|
|
"entropy": 5.6458399295806885,
|
|
"epoch": 1.0892249527410207,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886858980845202,
|
|
"loss": 5.4628,
|
|
"mean_token_accuracy": 0.16651467829942704,
|
|
"num_tokens": 23917925.0,
|
|
"step": 12965
|
|
},
|
|
{
|
|
"entropy": 5.533213710784912,
|
|
"epoch": 1.0896450325561857,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004886765194675782,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17183977067470552,
|
|
"num_tokens": 23927173.0,
|
|
"step": 12970
|
|
},
|
|
{
|
|
"entropy": 5.6211940288543705,
|
|
"epoch": 1.0900651123713505,
|
|
"grad_norm": 1.8125,
|
|
"learning_rate": 0.0004886671370654665,
|
|
"loss": 5.3276,
|
|
"mean_token_accuracy": 0.17467257082462312,
|
|
"num_tokens": 23936258.0,
|
|
"step": 12975
|
|
},
|
|
{
|
|
"entropy": 5.6253503322601315,
|
|
"epoch": 1.0904851921865155,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.0004886577508783516,
|
|
"loss": 5.3035,
|
|
"mean_token_accuracy": 0.17414060682058335,
|
|
"num_tokens": 23944215.0,
|
|
"step": 12980
|
|
},
|
|
{
|
|
"entropy": 5.640400552749634,
|
|
"epoch": 1.0909052720016803,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004886483609063997,
|
|
"loss": 5.3807,
|
|
"mean_token_accuracy": 0.16728059202432632,
|
|
"num_tokens": 23953151.0,
|
|
"step": 12985
|
|
},
|
|
{
|
|
"entropy": 5.515423250198364,
|
|
"epoch": 1.0913253518168453,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004886389671497769,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.17380398660898208,
|
|
"num_tokens": 23962919.0,
|
|
"step": 12990
|
|
},
|
|
{
|
|
"entropy": 5.668184280395508,
|
|
"epoch": 1.09174543163201,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048862956960865,
|
|
"loss": 5.3966,
|
|
"mean_token_accuracy": 0.16712536364793779,
|
|
"num_tokens": 23971900.0,
|
|
"step": 12995
|
|
},
|
|
{
|
|
"entropy": 5.6605853080749515,
|
|
"epoch": 1.0921655114471749,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004886201682831852,
|
|
"loss": 5.3723,
|
|
"mean_token_accuracy": 0.17093730568885804,
|
|
"num_tokens": 23980945.0,
|
|
"step": 13000
|
|
},
|
|
{
|
|
"entropy": 5.574681234359741,
|
|
"epoch": 1.09258559126234,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004886107631735491,
|
|
"loss": 5.3296,
|
|
"mean_token_accuracy": 0.16935485750436782,
|
|
"num_tokens": 23990460.0,
|
|
"step": 13005
|
|
},
|
|
{
|
|
"entropy": 5.643135356903076,
|
|
"epoch": 1.0930056710775047,
|
|
"grad_norm": 2.28125,
|
|
"learning_rate": 0.0004886013542799083,
|
|
"loss": 5.5015,
|
|
"mean_token_accuracy": 0.15477217584848404,
|
|
"num_tokens": 23999925.0,
|
|
"step": 13010
|
|
},
|
|
{
|
|
"entropy": 5.581091022491455,
|
|
"epoch": 1.0934257508926697,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004885919416024296,
|
|
"loss": 5.3405,
|
|
"mean_token_accuracy": 0.16890386044979094,
|
|
"num_tokens": 24009039.0,
|
|
"step": 13015
|
|
},
|
|
{
|
|
"entropy": 5.655356359481812,
|
|
"epoch": 1.0938458307078345,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004885825251412796,
|
|
"loss": 5.3971,
|
|
"mean_token_accuracy": 0.17056007087230682,
|
|
"num_tokens": 24017725.0,
|
|
"step": 13020
|
|
},
|
|
{
|
|
"entropy": 5.652591800689697,
|
|
"epoch": 1.0942659105229993,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004885731048966252,
|
|
"loss": 5.4265,
|
|
"mean_token_accuracy": 0.1609223946928978,
|
|
"num_tokens": 24027158.0,
|
|
"step": 13025
|
|
},
|
|
{
|
|
"entropy": 5.652519559860229,
|
|
"epoch": 1.0946859903381643,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.0004885636808686331,
|
|
"loss": 5.4738,
|
|
"mean_token_accuracy": 0.1661706432700157,
|
|
"num_tokens": 24037224.0,
|
|
"step": 13030
|
|
},
|
|
{
|
|
"entropy": 5.654554319381714,
|
|
"epoch": 1.095106070153329,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004885542530574705,
|
|
"loss": 5.4282,
|
|
"mean_token_accuracy": 0.1631125405430794,
|
|
"num_tokens": 24046097.0,
|
|
"step": 13035
|
|
},
|
|
{
|
|
"entropy": 5.627096652984619,
|
|
"epoch": 1.095526149968494,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004885448214633042,
|
|
"loss": 5.3062,
|
|
"mean_token_accuracy": 0.1716091126203537,
|
|
"num_tokens": 24055270.0,
|
|
"step": 13040
|
|
},
|
|
{
|
|
"entropy": 5.673101949691772,
|
|
"epoch": 1.0959462297836589,
|
|
"grad_norm": 1.859375,
|
|
"learning_rate": 0.0004885353860863013,
|
|
"loss": 5.4825,
|
|
"mean_token_accuracy": 0.15423855185508728,
|
|
"num_tokens": 24064995.0,
|
|
"step": 13045
|
|
},
|
|
{
|
|
"entropy": 5.692544794082641,
|
|
"epoch": 1.0963663095988239,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 0.000488525946926629,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.15968327820301056,
|
|
"num_tokens": 24075523.0,
|
|
"step": 13050
|
|
},
|
|
{
|
|
"entropy": 5.633663845062256,
|
|
"epoch": 1.0967863894139886,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004885165039844545,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.17032116651535034,
|
|
"num_tokens": 24084933.0,
|
|
"step": 13055
|
|
},
|
|
{
|
|
"entropy": 5.626227521896363,
|
|
"epoch": 1.0972064692291534,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004885070572599452,
|
|
"loss": 5.436,
|
|
"mean_token_accuracy": 0.15822404623031616,
|
|
"num_tokens": 24093964.0,
|
|
"step": 13060
|
|
},
|
|
{
|
|
"entropy": 5.616829252243042,
|
|
"epoch": 1.0976265490443184,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004884976067532681,
|
|
"loss": 5.3764,
|
|
"mean_token_accuracy": 0.15617975145578383,
|
|
"num_tokens": 24103951.0,
|
|
"step": 13065
|
|
},
|
|
{
|
|
"entropy": 5.588425588607788,
|
|
"epoch": 1.0980466288594832,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000488488152464591,
|
|
"loss": 5.4879,
|
|
"mean_token_accuracy": 0.15913376361131668,
|
|
"num_tokens": 24113392.0,
|
|
"step": 13070
|
|
},
|
|
{
|
|
"entropy": 5.615650415420532,
|
|
"epoch": 1.0984667086746482,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004884786943940812,
|
|
"loss": 5.3558,
|
|
"mean_token_accuracy": 0.16624071300029755,
|
|
"num_tokens": 24123165.0,
|
|
"step": 13075
|
|
},
|
|
{
|
|
"entropy": 5.608291578292847,
|
|
"epoch": 1.098886788489813,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004884692325419063,
|
|
"loss": 5.3988,
|
|
"mean_token_accuracy": 0.16643917858600615,
|
|
"num_tokens": 24132176.0,
|
|
"step": 13080
|
|
},
|
|
{
|
|
"entropy": 5.581974601745605,
|
|
"epoch": 1.099306868304978,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004884597669082336,
|
|
"loss": 5.458,
|
|
"mean_token_accuracy": 0.1615513488650322,
|
|
"num_tokens": 24141737.0,
|
|
"step": 13085
|
|
},
|
|
{
|
|
"entropy": 5.628212356567383,
|
|
"epoch": 1.0997269481201428,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004884502974932313,
|
|
"loss": 5.3815,
|
|
"mean_token_accuracy": 0.16735443249344825,
|
|
"num_tokens": 24150477.0,
|
|
"step": 13090
|
|
},
|
|
{
|
|
"entropy": 5.739729356765747,
|
|
"epoch": 1.1001470279353076,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004884408242970668,
|
|
"loss": 5.4863,
|
|
"mean_token_accuracy": 0.1622896149754524,
|
|
"num_tokens": 24158739.0,
|
|
"step": 13095
|
|
},
|
|
{
|
|
"entropy": 5.5542552947998045,
|
|
"epoch": 1.1005671077504726,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004884313473199081,
|
|
"loss": 5.3319,
|
|
"mean_token_accuracy": 0.17589967846870422,
|
|
"num_tokens": 24167511.0,
|
|
"step": 13100
|
|
},
|
|
{
|
|
"entropy": 5.561865520477295,
|
|
"epoch": 1.1009871875656374,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004884218665619229,
|
|
"loss": 5.3163,
|
|
"mean_token_accuracy": 0.16600671410560608,
|
|
"num_tokens": 24176413.0,
|
|
"step": 13105
|
|
},
|
|
{
|
|
"entropy": 5.584618663787841,
|
|
"epoch": 1.1014072673808024,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004884123820232792,
|
|
"loss": 5.2803,
|
|
"mean_token_accuracy": 0.17590437978506088,
|
|
"num_tokens": 24185135.0,
|
|
"step": 13110
|
|
},
|
|
{
|
|
"entropy": 5.556184577941894,
|
|
"epoch": 1.1018273471959672,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004884028937041451,
|
|
"loss": 5.3612,
|
|
"mean_token_accuracy": 0.17218423038721084,
|
|
"num_tokens": 24193273.0,
|
|
"step": 13115
|
|
},
|
|
{
|
|
"entropy": 5.674712181091309,
|
|
"epoch": 1.1022474270111322,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004883934016046886,
|
|
"loss": 5.4296,
|
|
"mean_token_accuracy": 0.16387299448251724,
|
|
"num_tokens": 24202509.0,
|
|
"step": 13120
|
|
},
|
|
{
|
|
"entropy": 5.638438415527344,
|
|
"epoch": 1.102667506826297,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.000488383905725078,
|
|
"loss": 5.4361,
|
|
"mean_token_accuracy": 0.15972956120967866,
|
|
"num_tokens": 24212644.0,
|
|
"step": 13125
|
|
},
|
|
{
|
|
"entropy": 5.581481313705444,
|
|
"epoch": 1.1030875866414618,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004883744060654811,
|
|
"loss": 5.3231,
|
|
"mean_token_accuracy": 0.166090789437294,
|
|
"num_tokens": 24221838.0,
|
|
"step": 13130
|
|
},
|
|
{
|
|
"entropy": 5.599612712860107,
|
|
"epoch": 1.1035076664566268,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004883649026260667,
|
|
"loss": 5.4107,
|
|
"mean_token_accuracy": 0.1680230289697647,
|
|
"num_tokens": 24230987.0,
|
|
"step": 13135
|
|
},
|
|
{
|
|
"entropy": 5.583003854751587,
|
|
"epoch": 1.1039277462717916,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004883553954070028,
|
|
"loss": 5.3501,
|
|
"mean_token_accuracy": 0.16952130943536758,
|
|
"num_tokens": 24240523.0,
|
|
"step": 13140
|
|
},
|
|
{
|
|
"entropy": 5.640346050262451,
|
|
"epoch": 1.1043478260869566,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.000488345884408458,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.17038542330265044,
|
|
"num_tokens": 24249799.0,
|
|
"step": 13145
|
|
},
|
|
{
|
|
"entropy": 5.63459324836731,
|
|
"epoch": 1.1047679059021214,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004883363696306007,
|
|
"loss": 5.3915,
|
|
"mean_token_accuracy": 0.17235672175884248,
|
|
"num_tokens": 24259361.0,
|
|
"step": 13150
|
|
},
|
|
{
|
|
"entropy": 5.598242950439453,
|
|
"epoch": 1.1051879857172864,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004883268510735995,
|
|
"loss": 5.3733,
|
|
"mean_token_accuracy": 0.16741275489330293,
|
|
"num_tokens": 24268010.0,
|
|
"step": 13155
|
|
},
|
|
{
|
|
"entropy": 5.520478200912476,
|
|
"epoch": 1.1056080655324512,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.0004883173287376229,
|
|
"loss": 5.4047,
|
|
"mean_token_accuracy": 0.1646900400519371,
|
|
"num_tokens": 24277416.0,
|
|
"step": 13160
|
|
},
|
|
{
|
|
"entropy": 5.688388013839722,
|
|
"epoch": 1.106028145347616,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004883078026228397,
|
|
"loss": 5.4788,
|
|
"mean_token_accuracy": 0.16411201059818267,
|
|
"num_tokens": 24286185.0,
|
|
"step": 13165
|
|
},
|
|
{
|
|
"entropy": 5.653516483306885,
|
|
"epoch": 1.106448225162781,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004882982727294187,
|
|
"loss": 5.3392,
|
|
"mean_token_accuracy": 0.16574593335390092,
|
|
"num_tokens": 24295382.0,
|
|
"step": 13170
|
|
},
|
|
{
|
|
"entropy": 5.580877017974854,
|
|
"epoch": 1.1068683049779457,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.0004882887390575284,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.16956889778375625,
|
|
"num_tokens": 24305197.0,
|
|
"step": 13175
|
|
},
|
|
{
|
|
"entropy": 5.642392110824585,
|
|
"epoch": 1.1072883847931108,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004882792016073381,
|
|
"loss": 5.4575,
|
|
"mean_token_accuracy": 0.1588519960641861,
|
|
"num_tokens": 24314149.0,
|
|
"step": 13180
|
|
},
|
|
{
|
|
"entropy": 5.680260229110718,
|
|
"epoch": 1.1077084646082755,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048826966037901655,
|
|
"loss": 5.3905,
|
|
"mean_token_accuracy": 0.16521805226802827,
|
|
"num_tokens": 24323737.0,
|
|
"step": 13185
|
|
},
|
|
{
|
|
"entropy": 5.5753613948822025,
|
|
"epoch": 1.1081285444234406,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048826011537273276,
|
|
"loss": 5.3475,
|
|
"mean_token_accuracy": 0.17049191743135453,
|
|
"num_tokens": 24332853.0,
|
|
"step": 13190
|
|
},
|
|
{
|
|
"entropy": 5.601475477218628,
|
|
"epoch": 1.1085486242386053,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004882505665886558,
|
|
"loss": 5.4938,
|
|
"mean_token_accuracy": 0.16070522665977477,
|
|
"num_tokens": 24342632.0,
|
|
"step": 13195
|
|
},
|
|
{
|
|
"entropy": 5.597259950637818,
|
|
"epoch": 1.1089687040537701,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048824101402695493,
|
|
"loss": 5.3294,
|
|
"mean_token_accuracy": 0.16487249583005906,
|
|
"num_tokens": 24351659.0,
|
|
"step": 13200
|
|
},
|
|
{
|
|
"entropy": 5.573502779006958,
|
|
"epoch": 1.1093887838689351,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004882314576877993,
|
|
"loss": 5.3573,
|
|
"mean_token_accuracy": 0.16396226584911347,
|
|
"num_tokens": 24360938.0,
|
|
"step": 13205
|
|
},
|
|
{
|
|
"entropy": 5.590566873550415,
|
|
"epoch": 1.1098088636841,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004882218975713581,
|
|
"loss": 5.4325,
|
|
"mean_token_accuracy": 0.1662053346633911,
|
|
"num_tokens": 24369603.0,
|
|
"step": 13210
|
|
},
|
|
{
|
|
"entropy": 5.55758228302002,
|
|
"epoch": 1.110228943499265,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004882123336778009,
|
|
"loss": 5.3622,
|
|
"mean_token_accuracy": 0.16560360342264174,
|
|
"num_tokens": 24377605.0,
|
|
"step": 13215
|
|
},
|
|
{
|
|
"entropy": 5.629861640930176,
|
|
"epoch": 1.1106490233144297,
|
|
"grad_norm": 2.109375,
|
|
"learning_rate": 0.0004882027660072969,
|
|
"loss": 5.411,
|
|
"mean_token_accuracy": 0.16419745087623597,
|
|
"num_tokens": 24386930.0,
|
|
"step": 13220
|
|
},
|
|
{
|
|
"entropy": 5.585262393951416,
|
|
"epoch": 1.1110691031295947,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004881931945600157,
|
|
"loss": 5.3849,
|
|
"mean_token_accuracy": 0.17502808570861816,
|
|
"num_tokens": 24396473.0,
|
|
"step": 13225
|
|
},
|
|
{
|
|
"entropy": 5.652954816818237,
|
|
"epoch": 1.1114891829447595,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004881836193361269,
|
|
"loss": 5.4586,
|
|
"mean_token_accuracy": 0.1681210294365883,
|
|
"num_tokens": 24405461.0,
|
|
"step": 13230
|
|
},
|
|
{
|
|
"entropy": 5.652054214477539,
|
|
"epoch": 1.1119092627599243,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004881740403358,
|
|
"loss": 5.4116,
|
|
"mean_token_accuracy": 0.1679125174880028,
|
|
"num_tokens": 24414138.0,
|
|
"step": 13235
|
|
},
|
|
{
|
|
"entropy": 5.619665193557739,
|
|
"epoch": 1.1123293425750893,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048816445755920474,
|
|
"loss": 5.4036,
|
|
"mean_token_accuracy": 0.17271453738212586,
|
|
"num_tokens": 24423386.0,
|
|
"step": 13240
|
|
},
|
|
{
|
|
"entropy": 5.601930093765259,
|
|
"epoch": 1.112749422390254,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004881548710065109,
|
|
"loss": 5.3854,
|
|
"mean_token_accuracy": 0.16733854860067368,
|
|
"num_tokens": 24433637.0,
|
|
"step": 13245
|
|
},
|
|
{
|
|
"entropy": 5.606436014175415,
|
|
"epoch": 1.113169502205419,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004881452806778883,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.1666820153594017,
|
|
"num_tokens": 24443677.0,
|
|
"step": 13250
|
|
},
|
|
{
|
|
"entropy": 5.591290473937988,
|
|
"epoch": 1.113589582020584,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048813568657350676,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.17067422717809677,
|
|
"num_tokens": 24452317.0,
|
|
"step": 13255
|
|
},
|
|
{
|
|
"entropy": 5.629110860824585,
|
|
"epoch": 1.1140096618357487,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004881260886935363,
|
|
"loss": 5.3715,
|
|
"mean_token_accuracy": 0.16931205689907075,
|
|
"num_tokens": 24460626.0,
|
|
"step": 13260
|
|
},
|
|
{
|
|
"entropy": 5.678458547592163,
|
|
"epoch": 1.1144297416509137,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00048811648703814693,
|
|
"loss": 5.4479,
|
|
"mean_token_accuracy": 0.15688713639974594,
|
|
"num_tokens": 24469583.0,
|
|
"step": 13265
|
|
},
|
|
{
|
|
"entropy": 5.631380414962768,
|
|
"epoch": 1.1148498214660785,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004881068816075087,
|
|
"loss": 5.401,
|
|
"mean_token_accuracy": 0.16380657255649567,
|
|
"num_tokens": 24478811.0,
|
|
"step": 13270
|
|
},
|
|
{
|
|
"entropy": 5.622896528244018,
|
|
"epoch": 1.1152699012812435,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00048809727240179193,
|
|
"loss": 5.4255,
|
|
"mean_token_accuracy": 0.1649166464805603,
|
|
"num_tokens": 24487818.0,
|
|
"step": 13275
|
|
},
|
|
{
|
|
"entropy": 5.600995302200317,
|
|
"epoch": 1.1156899810964083,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004880876594211665,
|
|
"loss": 5.4096,
|
|
"mean_token_accuracy": 0.16489541977643968,
|
|
"num_tokens": 24497087.0,
|
|
"step": 13280
|
|
},
|
|
{
|
|
"entropy": 5.6360047340393065,
|
|
"epoch": 1.1161100609115733,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048807804266580304,
|
|
"loss": 5.3632,
|
|
"mean_token_accuracy": 0.16394616216421126,
|
|
"num_tokens": 24505347.0,
|
|
"step": 13285
|
|
},
|
|
{
|
|
"entropy": 5.695936107635498,
|
|
"epoch": 1.116530140726738,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004880684221358717,
|
|
"loss": 5.3831,
|
|
"mean_token_accuracy": 0.1704442098736763,
|
|
"num_tokens": 24514732.0,
|
|
"step": 13290
|
|
},
|
|
{
|
|
"entropy": 5.634682989120483,
|
|
"epoch": 1.116950220541903,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048805879783154305,
|
|
"loss": 5.4159,
|
|
"mean_token_accuracy": 0.1660299375653267,
|
|
"num_tokens": 24523295.0,
|
|
"step": 13295
|
|
},
|
|
{
|
|
"entropy": 5.53900842666626,
|
|
"epoch": 1.1173703003570679,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048804916975298744,
|
|
"loss": 5.3212,
|
|
"mean_token_accuracy": 0.1719472512602806,
|
|
"num_tokens": 24532415.0,
|
|
"step": 13300
|
|
},
|
|
{
|
|
"entropy": 5.6734466552734375,
|
|
"epoch": 1.1177903801722326,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004880395379003755,
|
|
"loss": 5.4459,
|
|
"mean_token_accuracy": 0.16593600958585739,
|
|
"num_tokens": 24541856.0,
|
|
"step": 13305
|
|
},
|
|
{
|
|
"entropy": 5.593643999099731,
|
|
"epoch": 1.1182104599873977,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048802990227387797,
|
|
"loss": 5.4327,
|
|
"mean_token_accuracy": 0.16149331778287887,
|
|
"num_tokens": 24550982.0,
|
|
"step": 13310
|
|
},
|
|
{
|
|
"entropy": 5.648898267745972,
|
|
"epoch": 1.1186305398025624,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048802026287366525,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.15624148845672609,
|
|
"num_tokens": 24561176.0,
|
|
"step": 13315
|
|
},
|
|
{
|
|
"entropy": 5.700360822677612,
|
|
"epoch": 1.1190506196177274,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048801061969990834,
|
|
"loss": 5.3903,
|
|
"mean_token_accuracy": 0.16208946257829665,
|
|
"num_tokens": 24570741.0,
|
|
"step": 13320
|
|
},
|
|
{
|
|
"entropy": 5.6200910091400145,
|
|
"epoch": 1.1194706994328922,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00048800097275277795,
|
|
"loss": 5.3888,
|
|
"mean_token_accuracy": 0.16930052489042283,
|
|
"num_tokens": 24580175.0,
|
|
"step": 13325
|
|
},
|
|
{
|
|
"entropy": 5.646196603775024,
|
|
"epoch": 1.119890779248057,
|
|
"grad_norm": 2.140625,
|
|
"learning_rate": 0.000487991322032445,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.17066533267498016,
|
|
"num_tokens": 24588754.0,
|
|
"step": 13330
|
|
},
|
|
{
|
|
"entropy": 5.754522705078125,
|
|
"epoch": 1.120310859063222,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004879816675390805,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.1605545163154602,
|
|
"num_tokens": 24599429.0,
|
|
"step": 13335
|
|
},
|
|
{
|
|
"entropy": 5.567851495742798,
|
|
"epoch": 1.1207309388783868,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048797200927285547,
|
|
"loss": 5.3155,
|
|
"mean_token_accuracy": 0.16831441819667817,
|
|
"num_tokens": 24608767.0,
|
|
"step": 13340
|
|
},
|
|
{
|
|
"entropy": 5.608456087112427,
|
|
"epoch": 1.1211510186935518,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004879623472339409,
|
|
"loss": 5.4713,
|
|
"mean_token_accuracy": 0.16665953397750854,
|
|
"num_tokens": 24618232.0,
|
|
"step": 13345
|
|
},
|
|
{
|
|
"entropy": 5.660943508148193,
|
|
"epoch": 1.1215710985087166,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000487952681422508,
|
|
"loss": 5.3619,
|
|
"mean_token_accuracy": 0.16547955572605133,
|
|
"num_tokens": 24626986.0,
|
|
"step": 13350
|
|
},
|
|
{
|
|
"entropy": 5.511749696731568,
|
|
"epoch": 1.1219911783238816,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000487943011838728,
|
|
"loss": 5.2437,
|
|
"mean_token_accuracy": 0.17598886042833328,
|
|
"num_tokens": 24635283.0,
|
|
"step": 13355
|
|
},
|
|
{
|
|
"entropy": 5.4977783203125,
|
|
"epoch": 1.1224112581390464,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004879333384827722,
|
|
"loss": 5.3552,
|
|
"mean_token_accuracy": 0.16658277064561844,
|
|
"num_tokens": 24644451.0,
|
|
"step": 13360
|
|
},
|
|
{
|
|
"entropy": 5.711081838607788,
|
|
"epoch": 1.1228313379542114,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004879236613548119,
|
|
"loss": 5.4771,
|
|
"mean_token_accuracy": 0.16327747851610183,
|
|
"num_tokens": 24654811.0,
|
|
"step": 13365
|
|
},
|
|
{
|
|
"entropy": 5.649907445907592,
|
|
"epoch": 1.1232514177693762,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004879139804550187,
|
|
"loss": 5.4013,
|
|
"mean_token_accuracy": 0.16892933398485183,
|
|
"num_tokens": 24663712.0,
|
|
"step": 13370
|
|
},
|
|
{
|
|
"entropy": 5.661358642578125,
|
|
"epoch": 1.123671497584541,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048790429578356387,
|
|
"loss": 5.5134,
|
|
"mean_token_accuracy": 0.16258434057235718,
|
|
"num_tokens": 24672518.0,
|
|
"step": 13375
|
|
},
|
|
{
|
|
"entropy": 5.632959175109863,
|
|
"epoch": 1.124091577399706,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048789460734061915,
|
|
"loss": 5.3936,
|
|
"mean_token_accuracy": 0.16919077038764954,
|
|
"num_tokens": 24681900.0,
|
|
"step": 13380
|
|
},
|
|
{
|
|
"entropy": 5.604445552825927,
|
|
"epoch": 1.1245116572148708,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004878849151263561,
|
|
"loss": 5.379,
|
|
"mean_token_accuracy": 0.17044458240270616,
|
|
"num_tokens": 24691760.0,
|
|
"step": 13385
|
|
},
|
|
{
|
|
"entropy": 5.671233224868774,
|
|
"epoch": 1.1249317370300358,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004878752191409463,
|
|
"loss": 5.3569,
|
|
"mean_token_accuracy": 0.17419452518224715,
|
|
"num_tokens": 24700742.0,
|
|
"step": 13390
|
|
},
|
|
{
|
|
"entropy": 5.60303225517273,
|
|
"epoch": 1.1253518168452006,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004878655193845616,
|
|
"loss": 5.4102,
|
|
"mean_token_accuracy": 0.16591497808694838,
|
|
"num_tokens": 24709329.0,
|
|
"step": 13395
|
|
},
|
|
{
|
|
"entropy": 5.610186529159546,
|
|
"epoch": 1.1257718966603654,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048785581585737394,
|
|
"loss": 5.5499,
|
|
"mean_token_accuracy": 0.160182985663414,
|
|
"num_tokens": 24718475.0,
|
|
"step": 13400
|
|
},
|
|
{
|
|
"entropy": 5.656254863739013,
|
|
"epoch": 1.1261919764755304,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000487846108559555,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.17357761263847352,
|
|
"num_tokens": 24727817.0,
|
|
"step": 13405
|
|
},
|
|
{
|
|
"entropy": 5.617264366149902,
|
|
"epoch": 1.1266120562906952,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048783639749127694,
|
|
"loss": 5.4067,
|
|
"mean_token_accuracy": 0.164626245200634,
|
|
"num_tokens": 24737057.0,
|
|
"step": 13410
|
|
},
|
|
{
|
|
"entropy": 5.627209663391113,
|
|
"epoch": 1.1270321361058602,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004878266826527116,
|
|
"loss": 5.446,
|
|
"mean_token_accuracy": 0.15796937346458434,
|
|
"num_tokens": 24746016.0,
|
|
"step": 13415
|
|
},
|
|
{
|
|
"entropy": 5.673505258560181,
|
|
"epoch": 1.127452215921025,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048781696404403126,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.16286305636167525,
|
|
"num_tokens": 24755978.0,
|
|
"step": 13420
|
|
},
|
|
{
|
|
"entropy": 5.607972860336304,
|
|
"epoch": 1.12787229573619,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048780724166540794,
|
|
"loss": 5.3502,
|
|
"mean_token_accuracy": 0.17005843669176102,
|
|
"num_tokens": 24765255.0,
|
|
"step": 13425
|
|
},
|
|
{
|
|
"entropy": 5.568961668014526,
|
|
"epoch": 1.1282923755513548,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004877975155170139,
|
|
"loss": 5.4052,
|
|
"mean_token_accuracy": 0.16267422288656236,
|
|
"num_tokens": 24774339.0,
|
|
"step": 13430
|
|
},
|
|
{
|
|
"entropy": 5.621396780014038,
|
|
"epoch": 1.1287124553665198,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004877877855990215,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.16280805170536042,
|
|
"num_tokens": 24783236.0,
|
|
"step": 13435
|
|
},
|
|
{
|
|
"entropy": 5.57719235420227,
|
|
"epoch": 1.1291325351816845,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.000487778051911603,
|
|
"loss": 5.3125,
|
|
"mean_token_accuracy": 0.17248792499303817,
|
|
"num_tokens": 24792168.0,
|
|
"step": 13440
|
|
},
|
|
{
|
|
"entropy": 5.6991523742675785,
|
|
"epoch": 1.1295526149968493,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004877683144549308,
|
|
"loss": 5.4719,
|
|
"mean_token_accuracy": 0.1690712794661522,
|
|
"num_tokens": 24800843.0,
|
|
"step": 13445
|
|
},
|
|
{
|
|
"entropy": 5.594174861907959,
|
|
"epoch": 1.1299726948120143,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00048775857322917753,
|
|
"loss": 5.357,
|
|
"mean_token_accuracy": 0.1660827800631523,
|
|
"num_tokens": 24810475.0,
|
|
"step": 13450
|
|
},
|
|
{
|
|
"entropy": 5.524617290496826,
|
|
"epoch": 1.1303927746271791,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004877488282345158,
|
|
"loss": 5.4315,
|
|
"mean_token_accuracy": 0.16663852632045745,
|
|
"num_tokens": 24820486.0,
|
|
"step": 13455
|
|
},
|
|
{
|
|
"entropy": 5.7005352020263675,
|
|
"epoch": 1.1308128544423441,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.000487739079471118,
|
|
"loss": 5.4918,
|
|
"mean_token_accuracy": 0.16643402948975564,
|
|
"num_tokens": 24830243.0,
|
|
"step": 13460
|
|
},
|
|
{
|
|
"entropy": 5.7090178489685055,
|
|
"epoch": 1.131232934257509,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000487729326939157,
|
|
"loss": 5.4034,
|
|
"mean_token_accuracy": 0.1664557173848152,
|
|
"num_tokens": 24839090.0,
|
|
"step": 13465
|
|
},
|
|
{
|
|
"entropy": 5.620492267608642,
|
|
"epoch": 1.1316530140726737,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048771957063880553,
|
|
"loss": 5.3924,
|
|
"mean_token_accuracy": 0.163766011595726,
|
|
"num_tokens": 24847933.0,
|
|
"step": 13470
|
|
},
|
|
{
|
|
"entropy": 5.647629690170288,
|
|
"epoch": 1.1320730938878387,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004877098105702363,
|
|
"loss": 5.3983,
|
|
"mean_token_accuracy": 0.16802556663751603,
|
|
"num_tokens": 24857037.0,
|
|
"step": 13475
|
|
},
|
|
{
|
|
"entropy": 5.5166588306427,
|
|
"epoch": 1.1324931737030035,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048770004673362243,
|
|
"loss": 5.2202,
|
|
"mean_token_accuracy": 0.17570091038942337,
|
|
"num_tokens": 24866042.0,
|
|
"step": 13480
|
|
},
|
|
{
|
|
"entropy": 5.475602483749389,
|
|
"epoch": 1.1329132535181685,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048769027912913673,
|
|
"loss": 5.1931,
|
|
"mean_token_accuracy": 0.17908476293087006,
|
|
"num_tokens": 24873735.0,
|
|
"step": 13485
|
|
},
|
|
{
|
|
"entropy": 5.45988130569458,
|
|
"epoch": 1.1333333333333333,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.0004876805077569522,
|
|
"loss": 5.28,
|
|
"mean_token_accuracy": 0.17178382575511933,
|
|
"num_tokens": 24882277.0,
|
|
"step": 13490
|
|
},
|
|
{
|
|
"entropy": 5.546327066421509,
|
|
"epoch": 1.133753413148498,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048767073261724204,
|
|
"loss": 5.3993,
|
|
"mean_token_accuracy": 0.16492031663656234,
|
|
"num_tokens": 24891354.0,
|
|
"step": 13495
|
|
},
|
|
{
|
|
"entropy": 5.649689531326294,
|
|
"epoch": 1.134173492963663,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0004876609537101793,
|
|
"loss": 5.387,
|
|
"mean_token_accuracy": 0.16514926701784133,
|
|
"num_tokens": 24899887.0,
|
|
"step": 13500
|
|
},
|
|
{
|
|
"entropy": 5.702745819091797,
|
|
"epoch": 1.1345935727788279,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004876511710359374,
|
|
"loss": 5.4035,
|
|
"mean_token_accuracy": 0.16728077232837676,
|
|
"num_tokens": 24908616.0,
|
|
"step": 13505
|
|
},
|
|
{
|
|
"entropy": 5.617979431152344,
|
|
"epoch": 1.135013652593993,
|
|
"grad_norm": 2.53125,
|
|
"learning_rate": 0.00048764138459468935,
|
|
"loss": 5.4362,
|
|
"mean_token_accuracy": 0.16735305339097978,
|
|
"num_tokens": 24917864.0,
|
|
"step": 13510
|
|
},
|
|
{
|
|
"entropy": 5.677032327651977,
|
|
"epoch": 1.1354337324091577,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048763159438660876,
|
|
"loss": 5.4697,
|
|
"mean_token_accuracy": 0.16366630792617798,
|
|
"num_tokens": 24927864.0,
|
|
"step": 13515
|
|
},
|
|
{
|
|
"entropy": 5.5547889232635494,
|
|
"epoch": 1.1358538122243227,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048762180041186893,
|
|
"loss": 5.3571,
|
|
"mean_token_accuracy": 0.17089581340551377,
|
|
"num_tokens": 24937146.0,
|
|
"step": 13520
|
|
},
|
|
{
|
|
"entropy": 5.657744407653809,
|
|
"epoch": 1.1362738920394875,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004876120026706434,
|
|
"loss": 5.4354,
|
|
"mean_token_accuracy": 0.1635855630040169,
|
|
"num_tokens": 24945694.0,
|
|
"step": 13525
|
|
},
|
|
{
|
|
"entropy": 5.61405930519104,
|
|
"epoch": 1.1366939718546525,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004876022011631057,
|
|
"loss": 5.3377,
|
|
"mean_token_accuracy": 0.17318065762519835,
|
|
"num_tokens": 24955325.0,
|
|
"step": 13530
|
|
},
|
|
{
|
|
"entropy": 5.529127979278565,
|
|
"epoch": 1.1371140516698173,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004875923958894295,
|
|
"loss": 5.228,
|
|
"mean_token_accuracy": 0.17365142405033113,
|
|
"num_tokens": 24964028.0,
|
|
"step": 13535
|
|
},
|
|
{
|
|
"entropy": 5.591036605834961,
|
|
"epoch": 1.137534131484982,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048758258684978846,
|
|
"loss": 5.413,
|
|
"mean_token_accuracy": 0.1684279128909111,
|
|
"num_tokens": 24972923.0,
|
|
"step": 13540
|
|
},
|
|
{
|
|
"entropy": 5.604875659942627,
|
|
"epoch": 1.137954211300147,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048757277404435636,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.16950101405382156,
|
|
"num_tokens": 24982156.0,
|
|
"step": 13545
|
|
},
|
|
{
|
|
"entropy": 5.595570707321167,
|
|
"epoch": 1.1383742911153119,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.000487562957473307,
|
|
"loss": 5.3656,
|
|
"mean_token_accuracy": 0.16865910440683365,
|
|
"num_tokens": 24991616.0,
|
|
"step": 13550
|
|
},
|
|
{
|
|
"entropy": 5.593280410766601,
|
|
"epoch": 1.1387943709304769,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004875531371368144,
|
|
"loss": 5.4201,
|
|
"mean_token_accuracy": 0.16665563136339187,
|
|
"num_tokens": 25001140.0,
|
|
"step": 13555
|
|
},
|
|
{
|
|
"entropy": 5.606621646881104,
|
|
"epoch": 1.1392144507456416,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048754331303505236,
|
|
"loss": 5.3333,
|
|
"mean_token_accuracy": 0.17235686779022216,
|
|
"num_tokens": 25010863.0,
|
|
"step": 13560
|
|
},
|
|
{
|
|
"entropy": 5.632106494903565,
|
|
"epoch": 1.1396345305608064,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048753348516819496,
|
|
"loss": 5.4277,
|
|
"mean_token_accuracy": 0.1671194389462471,
|
|
"num_tokens": 25019770.0,
|
|
"step": 13565
|
|
},
|
|
{
|
|
"entropy": 5.715825510025025,
|
|
"epoch": 1.1400546103759714,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004875236535364163,
|
|
"loss": 5.4702,
|
|
"mean_token_accuracy": 0.16148280426859857,
|
|
"num_tokens": 25029900.0,
|
|
"step": 13570
|
|
},
|
|
{
|
|
"entropy": 5.705228042602539,
|
|
"epoch": 1.1404746901911362,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004875138181398906,
|
|
"loss": 5.4363,
|
|
"mean_token_accuracy": 0.165011228621006,
|
|
"num_tokens": 25039428.0,
|
|
"step": 13575
|
|
},
|
|
{
|
|
"entropy": 5.6060789108276365,
|
|
"epoch": 1.1408947700063012,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.000487503978978792,
|
|
"loss": 5.3975,
|
|
"mean_token_accuracy": 0.16259874999523163,
|
|
"num_tokens": 25049145.0,
|
|
"step": 13580
|
|
},
|
|
{
|
|
"entropy": 5.631357717514038,
|
|
"epoch": 1.141314849821466,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048749413605329487,
|
|
"loss": 5.4398,
|
|
"mean_token_accuracy": 0.1695747569203377,
|
|
"num_tokens": 25058772.0,
|
|
"step": 13585
|
|
},
|
|
{
|
|
"entropy": 5.635422277450561,
|
|
"epoch": 1.141734929636631,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048748428936357346,
|
|
"loss": 5.3524,
|
|
"mean_token_accuracy": 0.1705583453178406,
|
|
"num_tokens": 25067249.0,
|
|
"step": 13590
|
|
},
|
|
{
|
|
"entropy": 5.56702938079834,
|
|
"epoch": 1.1421550094517958,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004874744389098024,
|
|
"loss": 5.3114,
|
|
"mean_token_accuracy": 0.16375732421875,
|
|
"num_tokens": 25076893.0,
|
|
"step": 13595
|
|
},
|
|
{
|
|
"entropy": 5.507349300384521,
|
|
"epoch": 1.1425750892669608,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004874645846921559,
|
|
"loss": 5.3208,
|
|
"mean_token_accuracy": 0.1698176808655262,
|
|
"num_tokens": 25086238.0,
|
|
"step": 13600
|
|
},
|
|
{
|
|
"entropy": 5.549192476272583,
|
|
"epoch": 1.1429951690821256,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048745472671080884,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.16234881430864334,
|
|
"num_tokens": 25095334.0,
|
|
"step": 13605
|
|
},
|
|
{
|
|
"entropy": 5.610916471481323,
|
|
"epoch": 1.1434152488972904,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048744486496593565,
|
|
"loss": 5.3356,
|
|
"mean_token_accuracy": 0.16913952976465224,
|
|
"num_tokens": 25104136.0,
|
|
"step": 13610
|
|
},
|
|
{
|
|
"entropy": 5.624828624725342,
|
|
"epoch": 1.1438353287124554,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.000487434999457711,
|
|
"loss": 5.3358,
|
|
"mean_token_accuracy": 0.17875144481658936,
|
|
"num_tokens": 25112629.0,
|
|
"step": 13615
|
|
},
|
|
{
|
|
"entropy": 5.611724948883056,
|
|
"epoch": 1.1442554085276202,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004874251301863098,
|
|
"loss": 5.3789,
|
|
"mean_token_accuracy": 0.1664452612400055,
|
|
"num_tokens": 25121014.0,
|
|
"step": 13620
|
|
},
|
|
{
|
|
"entropy": 5.567342233657837,
|
|
"epoch": 1.1446754883427852,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048741525715190675,
|
|
"loss": 5.4235,
|
|
"mean_token_accuracy": 0.16376064270734786,
|
|
"num_tokens": 25130097.0,
|
|
"step": 13625
|
|
},
|
|
{
|
|
"entropy": 5.6526110649108885,
|
|
"epoch": 1.14509556815795,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004874053803546769,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.17253290265798568,
|
|
"num_tokens": 25139065.0,
|
|
"step": 13630
|
|
},
|
|
{
|
|
"entropy": 5.585218048095703,
|
|
"epoch": 1.1455156479731148,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 0.000487395499794795,
|
|
"loss": 5.3932,
|
|
"mean_token_accuracy": 0.16701920330524445,
|
|
"num_tokens": 25148852.0,
|
|
"step": 13635
|
|
},
|
|
{
|
|
"entropy": 5.5763102054595945,
|
|
"epoch": 1.1459357277882798,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004873856154724362,
|
|
"loss": 5.2999,
|
|
"mean_token_accuracy": 0.17658825665712358,
|
|
"num_tokens": 25157580.0,
|
|
"step": 13640
|
|
},
|
|
{
|
|
"entropy": 5.624576044082642,
|
|
"epoch": 1.1463558076034446,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.0004873757273877756,
|
|
"loss": 5.3987,
|
|
"mean_token_accuracy": 0.16335485577583314,
|
|
"num_tokens": 25166243.0,
|
|
"step": 13645
|
|
},
|
|
{
|
|
"entropy": 5.665804243087768,
|
|
"epoch": 1.1467758874186096,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00048736583554098836,
|
|
"loss": 5.4097,
|
|
"mean_token_accuracy": 0.16634505987167358,
|
|
"num_tokens": 25174674.0,
|
|
"step": 13650
|
|
},
|
|
{
|
|
"entropy": 5.593222188949585,
|
|
"epoch": 1.1471959672337744,
|
|
"grad_norm": 1.734375,
|
|
"learning_rate": 0.00048735593993224973,
|
|
"loss": 5.3078,
|
|
"mean_token_accuracy": 0.17730923742055893,
|
|
"num_tokens": 25183892.0,
|
|
"step": 13655
|
|
},
|
|
{
|
|
"entropy": 5.549776411056518,
|
|
"epoch": 1.1476160470489394,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 0.00048734604056173495,
|
|
"loss": 5.3598,
|
|
"mean_token_accuracy": 0.16848810911178588,
|
|
"num_tokens": 25192731.0,
|
|
"step": 13660
|
|
},
|
|
{
|
|
"entropy": 5.613305473327637,
|
|
"epoch": 1.1480361268641042,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048733613742961933,
|
|
"loss": 5.4558,
|
|
"mean_token_accuracy": 0.16849016547203063,
|
|
"num_tokens": 25201280.0,
|
|
"step": 13665
|
|
},
|
|
{
|
|
"entropy": 5.5975159168243405,
|
|
"epoch": 1.1484562066792692,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048732623053607846,
|
|
"loss": 5.3408,
|
|
"mean_token_accuracy": 0.1680586501955986,
|
|
"num_tokens": 25209929.0,
|
|
"step": 13670
|
|
},
|
|
{
|
|
"entropy": 5.595581865310669,
|
|
"epoch": 1.148876286494434,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004873163198812877,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.17326510548591614,
|
|
"num_tokens": 25218583.0,
|
|
"step": 13675
|
|
},
|
|
{
|
|
"entropy": 5.670962858200073,
|
|
"epoch": 1.1492963663095987,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004873064054654227,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.16238503828644751,
|
|
"num_tokens": 25228949.0,
|
|
"step": 13680
|
|
},
|
|
{
|
|
"entropy": 5.6353504180908205,
|
|
"epoch": 1.1497164461247638,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048729648728865904,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.1810284286737442,
|
|
"num_tokens": 25238603.0,
|
|
"step": 13685
|
|
},
|
|
{
|
|
"entropy": 5.592605924606323,
|
|
"epoch": 1.1501365259399285,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048728656535117237,
|
|
"loss": 5.4358,
|
|
"mean_token_accuracy": 0.15900354832410812,
|
|
"num_tokens": 25248265.0,
|
|
"step": 13690
|
|
},
|
|
{
|
|
"entropy": 5.600039768218994,
|
|
"epoch": 1.1505566057550936,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004872766396531386,
|
|
"loss": 5.4156,
|
|
"mean_token_accuracy": 0.17142994403839112,
|
|
"num_tokens": 25258195.0,
|
|
"step": 13695
|
|
},
|
|
{
|
|
"entropy": 5.654155158996582,
|
|
"epoch": 1.1509766855702583,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048726671019473335,
|
|
"loss": 5.3735,
|
|
"mean_token_accuracy": 0.17005601674318313,
|
|
"num_tokens": 25267886.0,
|
|
"step": 13700
|
|
},
|
|
{
|
|
"entropy": 5.640446376800537,
|
|
"epoch": 1.1513967653854231,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048725677697613267,
|
|
"loss": 5.4046,
|
|
"mean_token_accuracy": 0.16572085916996002,
|
|
"num_tokens": 25277304.0,
|
|
"step": 13705
|
|
},
|
|
{
|
|
"entropy": 5.649771642684937,
|
|
"epoch": 1.1518168452005881,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004872468399975125,
|
|
"loss": 5.421,
|
|
"mean_token_accuracy": 0.15717388838529586,
|
|
"num_tokens": 25286771.0,
|
|
"step": 13710
|
|
},
|
|
{
|
|
"entropy": 5.703133583068848,
|
|
"epoch": 1.152236925015753,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048723689925904884,
|
|
"loss": 5.4695,
|
|
"mean_token_accuracy": 0.16371950656175613,
|
|
"num_tokens": 25296018.0,
|
|
"step": 13715
|
|
},
|
|
{
|
|
"entropy": 5.61578860282898,
|
|
"epoch": 1.152657004830918,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004872269547609179,
|
|
"loss": 5.4264,
|
|
"mean_token_accuracy": 0.1729790225625038,
|
|
"num_tokens": 25305737.0,
|
|
"step": 13720
|
|
},
|
|
{
|
|
"entropy": 5.544830274581909,
|
|
"epoch": 1.1530770846460827,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004872170065032956,
|
|
"loss": 5.2474,
|
|
"mean_token_accuracy": 0.17219720929861068,
|
|
"num_tokens": 25314625.0,
|
|
"step": 13725
|
|
},
|
|
{
|
|
"entropy": 5.61985330581665,
|
|
"epoch": 1.1534971644612477,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004872070544863584,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.1666283816099167,
|
|
"num_tokens": 25323453.0,
|
|
"step": 13730
|
|
},
|
|
{
|
|
"entropy": 5.626963329315186,
|
|
"epoch": 1.1539172442764125,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004871970987102824,
|
|
"loss": 5.4085,
|
|
"mean_token_accuracy": 0.16893158257007598,
|
|
"num_tokens": 25333236.0,
|
|
"step": 13735
|
|
},
|
|
{
|
|
"entropy": 5.609739208221436,
|
|
"epoch": 1.1543373240915775,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004871871391752442,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.16515172719955445,
|
|
"num_tokens": 25341993.0,
|
|
"step": 13740
|
|
},
|
|
{
|
|
"entropy": 5.62867693901062,
|
|
"epoch": 1.1547574039067423,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048717717588141993,
|
|
"loss": 5.3267,
|
|
"mean_token_accuracy": 0.1705668330192566,
|
|
"num_tokens": 25350695.0,
|
|
"step": 13745
|
|
},
|
|
{
|
|
"entropy": 5.608707094192505,
|
|
"epoch": 1.155177483721907,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004871672088289863,
|
|
"loss": 5.39,
|
|
"mean_token_accuracy": 0.17076995223760605,
|
|
"num_tokens": 25359044.0,
|
|
"step": 13750
|
|
},
|
|
{
|
|
"entropy": 5.566635465621948,
|
|
"epoch": 1.155597563537072,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048715723801811986,
|
|
"loss": 5.3938,
|
|
"mean_token_accuracy": 0.1646006867289543,
|
|
"num_tokens": 25367959.0,
|
|
"step": 13755
|
|
},
|
|
{
|
|
"entropy": 5.59621958732605,
|
|
"epoch": 1.156017643352237,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048714726344899716,
|
|
"loss": 5.4061,
|
|
"mean_token_accuracy": 0.16776042878627778,
|
|
"num_tokens": 25376968.0,
|
|
"step": 13760
|
|
},
|
|
{
|
|
"entropy": 5.534719324111938,
|
|
"epoch": 1.156437723167402,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004871372851217949,
|
|
"loss": 5.303,
|
|
"mean_token_accuracy": 0.17216388881206512,
|
|
"num_tokens": 25385381.0,
|
|
"step": 13765
|
|
},
|
|
{
|
|
"entropy": 5.618631601333618,
|
|
"epoch": 1.1568578029825667,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004871273030366899,
|
|
"loss": 5.4117,
|
|
"mean_token_accuracy": 0.1639874517917633,
|
|
"num_tokens": 25394647.0,
|
|
"step": 13770
|
|
},
|
|
{
|
|
"entropy": 5.5666650295257565,
|
|
"epoch": 1.1572778827977315,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004871173171938589,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.17487365901470184,
|
|
"num_tokens": 25403973.0,
|
|
"step": 13775
|
|
},
|
|
{
|
|
"entropy": 5.593236780166626,
|
|
"epoch": 1.1576979626128965,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.0004871073275934789,
|
|
"loss": 5.3521,
|
|
"mean_token_accuracy": 0.16769609302282334,
|
|
"num_tokens": 25412319.0,
|
|
"step": 13780
|
|
},
|
|
{
|
|
"entropy": 5.55703592300415,
|
|
"epoch": 1.1581180424280613,
|
|
"grad_norm": 2.0,
|
|
"learning_rate": 0.00048709733423572685,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.16842261999845504,
|
|
"num_tokens": 25420558.0,
|
|
"step": 13785
|
|
},
|
|
{
|
|
"entropy": 5.518136262893677,
|
|
"epoch": 1.1585381222432263,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048708733712077973,
|
|
"loss": 5.3248,
|
|
"mean_token_accuracy": 0.16903136074543,
|
|
"num_tokens": 25429258.0,
|
|
"step": 13790
|
|
},
|
|
{
|
|
"entropy": 5.607215785980225,
|
|
"epoch": 1.158958202058391,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004870773362488146,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.1754231795668602,
|
|
"num_tokens": 25438005.0,
|
|
"step": 13795
|
|
},
|
|
{
|
|
"entropy": 5.542892122268677,
|
|
"epoch": 1.159378281873556,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004870673316200087,
|
|
"loss": 5.3058,
|
|
"mean_token_accuracy": 0.17361946552991867,
|
|
"num_tokens": 25447120.0,
|
|
"step": 13800
|
|
},
|
|
{
|
|
"entropy": 5.529282331466675,
|
|
"epoch": 1.1597983616887209,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004870573232345392,
|
|
"loss": 5.295,
|
|
"mean_token_accuracy": 0.17088494449853897,
|
|
"num_tokens": 25456216.0,
|
|
"step": 13805
|
|
},
|
|
{
|
|
"entropy": 5.784336519241333,
|
|
"epoch": 1.1602184415038856,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004870473110925834,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.16316404044628144,
|
|
"num_tokens": 25466456.0,
|
|
"step": 13810
|
|
},
|
|
{
|
|
"entropy": 5.544894504547119,
|
|
"epoch": 1.1606385213190507,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004870372951943187,
|
|
"loss": 5.2263,
|
|
"mean_token_accuracy": 0.17741502523422242,
|
|
"num_tokens": 25475217.0,
|
|
"step": 13815
|
|
},
|
|
{
|
|
"entropy": 5.584645557403564,
|
|
"epoch": 1.1610586011342154,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048702727553992243,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.15981806218624114,
|
|
"num_tokens": 25484617.0,
|
|
"step": 13820
|
|
},
|
|
{
|
|
"entropy": 5.6074260711669925,
|
|
"epoch": 1.1614786809493804,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00048701725212957223,
|
|
"loss": 5.3281,
|
|
"mean_token_accuracy": 0.17539868801832198,
|
|
"num_tokens": 25493936.0,
|
|
"step": 13825
|
|
},
|
|
{
|
|
"entropy": 5.609130477905273,
|
|
"epoch": 1.1618987607645452,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004870072249634455,
|
|
"loss": 5.2952,
|
|
"mean_token_accuracy": 0.17726642042398452,
|
|
"num_tokens": 25502306.0,
|
|
"step": 13830
|
|
},
|
|
{
|
|
"entropy": 5.567359161376953,
|
|
"epoch": 1.1623188405797102,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00048699719404172006,
|
|
"loss": 5.3697,
|
|
"mean_token_accuracy": 0.166751691699028,
|
|
"num_tokens": 25511247.0,
|
|
"step": 13835
|
|
},
|
|
{
|
|
"entropy": 5.600587511062622,
|
|
"epoch": 1.162738920394875,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048698715936457344,
|
|
"loss": 5.4214,
|
|
"mean_token_accuracy": 0.164691025018692,
|
|
"num_tokens": 25520482.0,
|
|
"step": 13840
|
|
},
|
|
{
|
|
"entropy": 5.6135289669036865,
|
|
"epoch": 1.1631590002100398,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048697712093218336,
|
|
"loss": 5.3012,
|
|
"mean_token_accuracy": 0.17024406641721726,
|
|
"num_tokens": 25529854.0,
|
|
"step": 13845
|
|
},
|
|
{
|
|
"entropy": 5.528973960876465,
|
|
"epoch": 1.1635790800252048,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004869670787447279,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.1754808947443962,
|
|
"num_tokens": 25538251.0,
|
|
"step": 13850
|
|
},
|
|
{
|
|
"entropy": 5.520005512237549,
|
|
"epoch": 1.1639991598403696,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004869570328023846,
|
|
"loss": 5.3322,
|
|
"mean_token_accuracy": 0.17265767753124237,
|
|
"num_tokens": 25546889.0,
|
|
"step": 13855
|
|
},
|
|
{
|
|
"entropy": 5.559149742126465,
|
|
"epoch": 1.1644192396555346,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048694698310533177,
|
|
"loss": 5.3699,
|
|
"mean_token_accuracy": 0.167795892059803,
|
|
"num_tokens": 25557040.0,
|
|
"step": 13860
|
|
},
|
|
{
|
|
"entropy": 5.695978212356567,
|
|
"epoch": 1.1648393194706994,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004869369296537472,
|
|
"loss": 5.5365,
|
|
"mean_token_accuracy": 0.15896812081336975,
|
|
"num_tokens": 25565798.0,
|
|
"step": 13865
|
|
},
|
|
{
|
|
"entropy": 5.715288591384888,
|
|
"epoch": 1.1652593992858642,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004869268724478091,
|
|
"loss": 5.386,
|
|
"mean_token_accuracy": 0.1702848941087723,
|
|
"num_tokens": 25575039.0,
|
|
"step": 13870
|
|
},
|
|
{
|
|
"entropy": 5.666198587417602,
|
|
"epoch": 1.1656794791010292,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048691681148769545,
|
|
"loss": 5.382,
|
|
"mean_token_accuracy": 0.16508956253528595,
|
|
"num_tokens": 25584635.0,
|
|
"step": 13875
|
|
},
|
|
{
|
|
"entropy": 5.506886911392212,
|
|
"epoch": 1.166099558916194,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004869067467735847,
|
|
"loss": 5.2984,
|
|
"mean_token_accuracy": 0.17627811133861543,
|
|
"num_tokens": 25593736.0,
|
|
"step": 13880
|
|
},
|
|
{
|
|
"entropy": 5.5315882682800295,
|
|
"epoch": 1.166519638731359,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.0004868966783056551,
|
|
"loss": 5.2671,
|
|
"mean_token_accuracy": 0.18442590683698654,
|
|
"num_tokens": 25602685.0,
|
|
"step": 13885
|
|
},
|
|
{
|
|
"entropy": 5.558185482025147,
|
|
"epoch": 1.1669397185465238,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048688660608408484,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1673026517033577,
|
|
"num_tokens": 25610690.0,
|
|
"step": 13890
|
|
},
|
|
{
|
|
"entropy": 5.519009828567505,
|
|
"epoch": 1.1673597983616888,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048687653010905254,
|
|
"loss": 5.2548,
|
|
"mean_token_accuracy": 0.1778439462184906,
|
|
"num_tokens": 25619805.0,
|
|
"step": 13895
|
|
},
|
|
{
|
|
"entropy": 5.68157844543457,
|
|
"epoch": 1.1677798781768536,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048686645038073664,
|
|
"loss": 5.457,
|
|
"mean_token_accuracy": 0.16299156993627548,
|
|
"num_tokens": 25629447.0,
|
|
"step": 13900
|
|
},
|
|
{
|
|
"entropy": 5.638311815261841,
|
|
"epoch": 1.1681999579920186,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048685636689931554,
|
|
"loss": 5.3085,
|
|
"mean_token_accuracy": 0.1740482419729233,
|
|
"num_tokens": 25638619.0,
|
|
"step": 13905
|
|
},
|
|
{
|
|
"entropy": 5.6293586730957035,
|
|
"epoch": 1.1686200378071834,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048684627966496803,
|
|
"loss": 5.3962,
|
|
"mean_token_accuracy": 0.17413543313741683,
|
|
"num_tokens": 25648255.0,
|
|
"step": 13910
|
|
},
|
|
{
|
|
"entropy": 5.560601282119751,
|
|
"epoch": 1.1690401176223482,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048683618867787284,
|
|
"loss": 5.4378,
|
|
"mean_token_accuracy": 0.1661060631275177,
|
|
"num_tokens": 25657881.0,
|
|
"step": 13915
|
|
},
|
|
{
|
|
"entropy": 5.648235702514649,
|
|
"epoch": 1.1694601974375132,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004868260939382086,
|
|
"loss": 5.452,
|
|
"mean_token_accuracy": 0.1665305510163307,
|
|
"num_tokens": 25666773.0,
|
|
"step": 13920
|
|
},
|
|
{
|
|
"entropy": 5.632356214523315,
|
|
"epoch": 1.169880277252678,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004868159954461542,
|
|
"loss": 5.3471,
|
|
"mean_token_accuracy": 0.1685002401471138,
|
|
"num_tokens": 25675152.0,
|
|
"step": 13925
|
|
},
|
|
{
|
|
"entropy": 5.725224542617798,
|
|
"epoch": 1.170300357067843,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048680589320188847,
|
|
"loss": 5.4441,
|
|
"mean_token_accuracy": 0.16157277077436447,
|
|
"num_tokens": 25684962.0,
|
|
"step": 13930
|
|
},
|
|
{
|
|
"entropy": 5.576214838027954,
|
|
"epoch": 1.1707204368830078,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.0004867957872055904,
|
|
"loss": 5.3605,
|
|
"mean_token_accuracy": 0.16613447070121765,
|
|
"num_tokens": 25693782.0,
|
|
"step": 13935
|
|
},
|
|
{
|
|
"entropy": 5.543605089187622,
|
|
"epoch": 1.1711405166981725,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048678567745743905,
|
|
"loss": 5.325,
|
|
"mean_token_accuracy": 0.1713411509990692,
|
|
"num_tokens": 25703081.0,
|
|
"step": 13940
|
|
},
|
|
{
|
|
"entropy": 5.59487566947937,
|
|
"epoch": 1.1715605965133375,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004867755639576135,
|
|
"loss": 5.3436,
|
|
"mean_token_accuracy": 0.1717812567949295,
|
|
"num_tokens": 25711628.0,
|
|
"step": 13945
|
|
},
|
|
{
|
|
"entropy": 5.524281072616577,
|
|
"epoch": 1.1719806763285023,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004867654467062928,
|
|
"loss": 5.3767,
|
|
"mean_token_accuracy": 0.17248852252960206,
|
|
"num_tokens": 25720676.0,
|
|
"step": 13950
|
|
},
|
|
{
|
|
"entropy": 5.5976708889007565,
|
|
"epoch": 1.1724007561436673,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00048675532570365633,
|
|
"loss": 5.3365,
|
|
"mean_token_accuracy": 0.17378393113613128,
|
|
"num_tokens": 25729920.0,
|
|
"step": 13955
|
|
},
|
|
{
|
|
"entropy": 5.5958537578582765,
|
|
"epoch": 1.1728208359588321,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048674520094988327,
|
|
"loss": 5.3109,
|
|
"mean_token_accuracy": 0.17501317262649535,
|
|
"num_tokens": 25739745.0,
|
|
"step": 13960
|
|
},
|
|
{
|
|
"entropy": 5.550080633163452,
|
|
"epoch": 1.1732409157739971,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048673507244515303,
|
|
"loss": 5.3275,
|
|
"mean_token_accuracy": 0.17092910557985305,
|
|
"num_tokens": 25748636.0,
|
|
"step": 13965
|
|
},
|
|
{
|
|
"entropy": 5.649429512023926,
|
|
"epoch": 1.173660995589162,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.000486724940189645,
|
|
"loss": 5.4664,
|
|
"mean_token_accuracy": 0.16761331260204315,
|
|
"num_tokens": 25758393.0,
|
|
"step": 13970
|
|
},
|
|
{
|
|
"entropy": 5.626720714569092,
|
|
"epoch": 1.174081075404327,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004867148041835386,
|
|
"loss": 5.439,
|
|
"mean_token_accuracy": 0.1595470979809761,
|
|
"num_tokens": 25768520.0,
|
|
"step": 13975
|
|
},
|
|
{
|
|
"entropy": 5.5244852066040036,
|
|
"epoch": 1.1745011552194917,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004867046644270136,
|
|
"loss": 5.2576,
|
|
"mean_token_accuracy": 0.1772868111729622,
|
|
"num_tokens": 25777168.0,
|
|
"step": 13980
|
|
},
|
|
{
|
|
"entropy": 5.71324348449707,
|
|
"epoch": 1.1749212350346565,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004866945209202494,
|
|
"loss": 5.5505,
|
|
"mean_token_accuracy": 0.15432295054197312,
|
|
"num_tokens": 25787042.0,
|
|
"step": 13985
|
|
},
|
|
{
|
|
"entropy": 5.648117446899414,
|
|
"epoch": 1.1753413148498215,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004866843736634258,
|
|
"loss": 5.4295,
|
|
"mean_token_accuracy": 0.1675956055521965,
|
|
"num_tokens": 25796784.0,
|
|
"step": 13990
|
|
},
|
|
{
|
|
"entropy": 5.692070960998535,
|
|
"epoch": 1.1757613946649863,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004866742226567225,
|
|
"loss": 5.4677,
|
|
"mean_token_accuracy": 0.15732361227273942,
|
|
"num_tokens": 25806285.0,
|
|
"step": 13995
|
|
},
|
|
{
|
|
"entropy": 5.618652057647705,
|
|
"epoch": 1.1761814744801513,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048666406790031936,
|
|
"loss": 5.3144,
|
|
"mean_token_accuracy": 0.1640985354781151,
|
|
"num_tokens": 25814889.0,
|
|
"step": 14000
|
|
},
|
|
{
|
|
"entropy": 5.572588062286377,
|
|
"epoch": 1.176601554295316,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004866539093943962,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.1675340011715889,
|
|
"num_tokens": 25824551.0,
|
|
"step": 14005
|
|
},
|
|
{
|
|
"entropy": 5.628482294082642,
|
|
"epoch": 1.1770216341104809,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048664374713913304,
|
|
"loss": 5.4206,
|
|
"mean_token_accuracy": 0.16298734694719313,
|
|
"num_tokens": 25834482.0,
|
|
"step": 14010
|
|
},
|
|
{
|
|
"entropy": 5.671939754486084,
|
|
"epoch": 1.177441713925646,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004866335811347099,
|
|
"loss": 5.4331,
|
|
"mean_token_accuracy": 0.16675578504800798,
|
|
"num_tokens": 25843274.0,
|
|
"step": 14015
|
|
},
|
|
{
|
|
"entropy": 5.684998893737793,
|
|
"epoch": 1.1778617937408107,
|
|
"grad_norm": 1.8828125,
|
|
"learning_rate": 0.00048662341138130683,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.1594082310795784,
|
|
"num_tokens": 25852482.0,
|
|
"step": 14020
|
|
},
|
|
{
|
|
"entropy": 5.665592050552368,
|
|
"epoch": 1.1782818735559757,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048661323787910405,
|
|
"loss": 5.4246,
|
|
"mean_token_accuracy": 0.16257014721632004,
|
|
"num_tokens": 25862657.0,
|
|
"step": 14025
|
|
},
|
|
{
|
|
"entropy": 5.586136817932129,
|
|
"epoch": 1.1787019533711405,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004866030606282817,
|
|
"loss": 5.3726,
|
|
"mean_token_accuracy": 0.16970161497592925,
|
|
"num_tokens": 25871492.0,
|
|
"step": 14030
|
|
},
|
|
{
|
|
"entropy": 5.62667407989502,
|
|
"epoch": 1.1791220331863055,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048659287962902006,
|
|
"loss": 5.3666,
|
|
"mean_token_accuracy": 0.17091266363859176,
|
|
"num_tokens": 25880979.0,
|
|
"step": 14035
|
|
},
|
|
{
|
|
"entropy": 5.580191278457642,
|
|
"epoch": 1.1795421130014703,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048658269488149945,
|
|
"loss": 5.3535,
|
|
"mean_token_accuracy": 0.16362757086753846,
|
|
"num_tokens": 25891060.0,
|
|
"step": 14040
|
|
},
|
|
{
|
|
"entropy": 5.705811500549316,
|
|
"epoch": 1.1799621928166353,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0004865725063859005,
|
|
"loss": 5.488,
|
|
"mean_token_accuracy": 0.1669595867395401,
|
|
"num_tokens": 25900421.0,
|
|
"step": 14045
|
|
},
|
|
{
|
|
"entropy": 5.618188953399658,
|
|
"epoch": 1.1803822726318,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048656231414240345,
|
|
"loss": 5.3797,
|
|
"mean_token_accuracy": 0.16654564589262008,
|
|
"num_tokens": 25909614.0,
|
|
"step": 14050
|
|
},
|
|
{
|
|
"entropy": 5.541171455383301,
|
|
"epoch": 1.1808023524469649,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000486552118151189,
|
|
"loss": 5.4244,
|
|
"mean_token_accuracy": 0.16173808872699738,
|
|
"num_tokens": 25919324.0,
|
|
"step": 14055
|
|
},
|
|
{
|
|
"entropy": 5.612274122238159,
|
|
"epoch": 1.1812224322621299,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00048654191841243763,
|
|
"loss": 5.4059,
|
|
"mean_token_accuracy": 0.1739427775144577,
|
|
"num_tokens": 25928818.0,
|
|
"step": 14060
|
|
},
|
|
{
|
|
"entropy": 5.616962432861328,
|
|
"epoch": 1.1816425120772946,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004865317149263301,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.16519006937742234,
|
|
"num_tokens": 25938148.0,
|
|
"step": 14065
|
|
},
|
|
{
|
|
"entropy": 5.56295223236084,
|
|
"epoch": 1.1820625918924597,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004865215076930473,
|
|
"loss": 5.3754,
|
|
"mean_token_accuracy": 0.16697040051221848,
|
|
"num_tokens": 25947210.0,
|
|
"step": 14070
|
|
},
|
|
{
|
|
"entropy": 5.593865633010864,
|
|
"epoch": 1.1824826717076244,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004865112967127697,
|
|
"loss": 5.3583,
|
|
"mean_token_accuracy": 0.170071779191494,
|
|
"num_tokens": 25955949.0,
|
|
"step": 14075
|
|
},
|
|
{
|
|
"entropy": 5.5404736518859865,
|
|
"epoch": 1.1829027515227892,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004865010819856786,
|
|
"loss": 5.2969,
|
|
"mean_token_accuracy": 0.16847216039896012,
|
|
"num_tokens": 25964193.0,
|
|
"step": 14080
|
|
},
|
|
{
|
|
"entropy": 5.551244688034058,
|
|
"epoch": 1.1833228313379542,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0004864908635119546,
|
|
"loss": 5.3896,
|
|
"mean_token_accuracy": 0.16945898830890654,
|
|
"num_tokens": 25973141.0,
|
|
"step": 14085
|
|
},
|
|
{
|
|
"entropy": 5.681430816650391,
|
|
"epoch": 1.183742911153119,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004864806412917788,
|
|
"loss": 5.4456,
|
|
"mean_token_accuracy": 0.17200513929128647,
|
|
"num_tokens": 25982650.0,
|
|
"step": 14090
|
|
},
|
|
{
|
|
"entropy": 5.736534643173218,
|
|
"epoch": 1.184162990968284,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004864704153253325,
|
|
"loss": 5.4406,
|
|
"mean_token_accuracy": 0.1592070296406746,
|
|
"num_tokens": 25992096.0,
|
|
"step": 14095
|
|
},
|
|
{
|
|
"entropy": 5.6888525009155275,
|
|
"epoch": 1.1845830707834488,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 0.00048646018561279665,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.16635299921035768,
|
|
"num_tokens": 26002063.0,
|
|
"step": 14100
|
|
},
|
|
{
|
|
"entropy": 5.502923154830933,
|
|
"epoch": 1.1850031505986138,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048644995215435245,
|
|
"loss": 5.2612,
|
|
"mean_token_accuracy": 0.1743235930800438,
|
|
"num_tokens": 26010716.0,
|
|
"step": 14105
|
|
},
|
|
{
|
|
"entropy": 5.574075698852539,
|
|
"epoch": 1.1854232304137786,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004864397149501812,
|
|
"loss": 5.3586,
|
|
"mean_token_accuracy": 0.167898553609848,
|
|
"num_tokens": 26019136.0,
|
|
"step": 14110
|
|
},
|
|
{
|
|
"entropy": 5.629922819137573,
|
|
"epoch": 1.1858433102289434,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 0.00048642947400046434,
|
|
"loss": 5.3827,
|
|
"mean_token_accuracy": 0.17956559509038925,
|
|
"num_tokens": 26028029.0,
|
|
"step": 14115
|
|
},
|
|
{
|
|
"entropy": 5.686328029632568,
|
|
"epoch": 1.1862633900441084,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048641922930538325,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.16046979129314423,
|
|
"num_tokens": 26038025.0,
|
|
"step": 14120
|
|
},
|
|
{
|
|
"entropy": 5.6663109302520756,
|
|
"epoch": 1.1866834698592732,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004864089808651193,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.1532455489039421,
|
|
"num_tokens": 26048427.0,
|
|
"step": 14125
|
|
},
|
|
{
|
|
"entropy": 5.605689144134521,
|
|
"epoch": 1.1871035496744382,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 0.0004863987286798541,
|
|
"loss": 5.3066,
|
|
"mean_token_accuracy": 0.16599408239126207,
|
|
"num_tokens": 26057682.0,
|
|
"step": 14130
|
|
},
|
|
{
|
|
"entropy": 5.567851543426514,
|
|
"epoch": 1.187523629489603,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004863884727497693,
|
|
"loss": 5.3759,
|
|
"mean_token_accuracy": 0.1674002528190613,
|
|
"num_tokens": 26066562.0,
|
|
"step": 14135
|
|
},
|
|
{
|
|
"entropy": 5.563521385192871,
|
|
"epoch": 1.187943709304768,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004863782130750466,
|
|
"loss": 5.2897,
|
|
"mean_token_accuracy": 0.17027911990880967,
|
|
"num_tokens": 26075633.0,
|
|
"step": 14140
|
|
},
|
|
{
|
|
"entropy": 5.6153826236724855,
|
|
"epoch": 1.1883637891199328,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048636794965586764,
|
|
"loss": 5.4471,
|
|
"mean_token_accuracy": 0.16176531463861465,
|
|
"num_tokens": 26085160.0,
|
|
"step": 14145
|
|
},
|
|
{
|
|
"entropy": 5.546812963485718,
|
|
"epoch": 1.1887838689350976,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048635768249241434,
|
|
"loss": 5.3516,
|
|
"mean_token_accuracy": 0.17043941468000412,
|
|
"num_tokens": 26094157.0,
|
|
"step": 14150
|
|
},
|
|
{
|
|
"entropy": 5.674842119216919,
|
|
"epoch": 1.1892039487502626,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004863474115848685,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.16983729153871535,
|
|
"num_tokens": 26104459.0,
|
|
"step": 14155
|
|
},
|
|
{
|
|
"entropy": 5.590853452682495,
|
|
"epoch": 1.1896240285654274,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048633713693341214,
|
|
"loss": 5.3959,
|
|
"mean_token_accuracy": 0.1641297832131386,
|
|
"num_tokens": 26114468.0,
|
|
"step": 14160
|
|
},
|
|
{
|
|
"entropy": 5.568353366851807,
|
|
"epoch": 1.1900441083805924,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048632685853822714,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.16373370140790938,
|
|
"num_tokens": 26123408.0,
|
|
"step": 14165
|
|
},
|
|
{
|
|
"entropy": 5.572306394577026,
|
|
"epoch": 1.1904641881957572,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004863165763994957,
|
|
"loss": 5.3678,
|
|
"mean_token_accuracy": 0.1610241025686264,
|
|
"num_tokens": 26132692.0,
|
|
"step": 14170
|
|
},
|
|
{
|
|
"entropy": 5.696545028686524,
|
|
"epoch": 1.190884268010922,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004863062905173999,
|
|
"loss": 5.5264,
|
|
"mean_token_accuracy": 0.16376537829637527,
|
|
"num_tokens": 26142259.0,
|
|
"step": 14175
|
|
},
|
|
{
|
|
"entropy": 5.65267333984375,
|
|
"epoch": 1.191304347826087,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.000486296000892122,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.16619327515363694,
|
|
"num_tokens": 26151782.0,
|
|
"step": 14180
|
|
},
|
|
{
|
|
"entropy": 5.531172466278076,
|
|
"epoch": 1.1917244276412517,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00048628570752384424,
|
|
"loss": 5.2208,
|
|
"mean_token_accuracy": 0.17376811504364015,
|
|
"num_tokens": 26160449.0,
|
|
"step": 14185
|
|
},
|
|
{
|
|
"entropy": 5.609526109695435,
|
|
"epoch": 1.1921445074564168,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048627541041274897,
|
|
"loss": 5.4643,
|
|
"mean_token_accuracy": 0.16051455587148666,
|
|
"num_tokens": 26169764.0,
|
|
"step": 14190
|
|
},
|
|
{
|
|
"entropy": 5.644153261184693,
|
|
"epoch": 1.1925645872715815,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048626510955901854,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.16696933507919312,
|
|
"num_tokens": 26178759.0,
|
|
"step": 14195
|
|
},
|
|
{
|
|
"entropy": 5.687915563583374,
|
|
"epoch": 1.1929846670867466,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004862548049628356,
|
|
"loss": 5.4591,
|
|
"mean_token_accuracy": 0.16625112295150757,
|
|
"num_tokens": 26187904.0,
|
|
"step": 14200
|
|
},
|
|
{
|
|
"entropy": 5.636867952346802,
|
|
"epoch": 1.1934047469019113,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0004862444966243824,
|
|
"loss": 5.3852,
|
|
"mean_token_accuracy": 0.17131132632493973,
|
|
"num_tokens": 26196563.0,
|
|
"step": 14205
|
|
},
|
|
{
|
|
"entropy": 5.701703214645386,
|
|
"epoch": 1.1938248267170763,
|
|
"grad_norm": 2.328125,
|
|
"learning_rate": 0.0004862341845438419,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.1661001428961754,
|
|
"num_tokens": 26206573.0,
|
|
"step": 14210
|
|
},
|
|
{
|
|
"entropy": 5.6225780010223385,
|
|
"epoch": 1.1942449065322411,
|
|
"grad_norm": 1.90625,
|
|
"learning_rate": 0.00048622386872139645,
|
|
"loss": 5.3207,
|
|
"mean_token_accuracy": 0.16739476919174195,
|
|
"num_tokens": 26215308.0,
|
|
"step": 14215
|
|
},
|
|
{
|
|
"entropy": 5.550726795196534,
|
|
"epoch": 1.194664986347406,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000486213549157229,
|
|
"loss": 5.3796,
|
|
"mean_token_accuracy": 0.16657185107469558,
|
|
"num_tokens": 26224379.0,
|
|
"step": 14220
|
|
},
|
|
{
|
|
"entropy": 5.580405950546265,
|
|
"epoch": 1.195085066162571,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004862032258515222,
|
|
"loss": 5.3572,
|
|
"mean_token_accuracy": 0.17274150252342224,
|
|
"num_tokens": 26233620.0,
|
|
"step": 14225
|
|
},
|
|
{
|
|
"entropy": 5.579659271240234,
|
|
"epoch": 1.1955051459777357,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004861928988044592,
|
|
"loss": 5.4351,
|
|
"mean_token_accuracy": 0.16125431805849075,
|
|
"num_tokens": 26242556.0,
|
|
"step": 14230
|
|
},
|
|
{
|
|
"entropy": 5.631987619400024,
|
|
"epoch": 1.1959252257929007,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004861825680162226,
|
|
"loss": 5.4119,
|
|
"mean_token_accuracy": 0.16598995327949523,
|
|
"num_tokens": 26251561.0,
|
|
"step": 14235
|
|
},
|
|
{
|
|
"entropy": 5.5751265525817875,
|
|
"epoch": 1.1963453056080655,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048617223348699546,
|
|
"loss": 5.3389,
|
|
"mean_token_accuracy": 0.17048846334218978,
|
|
"num_tokens": 26261115.0,
|
|
"step": 14240
|
|
},
|
|
{
|
|
"entropy": 5.708127737045288,
|
|
"epoch": 1.1967653854232303,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.0004861618952169611,
|
|
"loss": 5.4989,
|
|
"mean_token_accuracy": 0.17341294065117835,
|
|
"num_tokens": 26271165.0,
|
|
"step": 14245
|
|
},
|
|
{
|
|
"entropy": 5.619239473342896,
|
|
"epoch": 1.1971854652383953,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004861515532063025,
|
|
"loss": 5.4541,
|
|
"mean_token_accuracy": 0.1659351631999016,
|
|
"num_tokens": 26280822.0,
|
|
"step": 14250
|
|
},
|
|
{
|
|
"entropy": 5.605314683914185,
|
|
"epoch": 1.19760554505356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048614120745520275,
|
|
"loss": 5.3373,
|
|
"mean_token_accuracy": 0.17087636142969131,
|
|
"num_tokens": 26288747.0,
|
|
"step": 14255
|
|
},
|
|
{
|
|
"entropy": 5.633758163452148,
|
|
"epoch": 1.198025624868725,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048613085796384524,
|
|
"loss": 5.4121,
|
|
"mean_token_accuracy": 0.16057505309581757,
|
|
"num_tokens": 26298387.0,
|
|
"step": 14260
|
|
},
|
|
{
|
|
"entropy": 5.604875898361206,
|
|
"epoch": 1.19844570468389,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00048612050473241335,
|
|
"loss": 5.3026,
|
|
"mean_token_accuracy": 0.17800578474998474,
|
|
"num_tokens": 26307016.0,
|
|
"step": 14265
|
|
},
|
|
{
|
|
"entropy": 5.608559846878052,
|
|
"epoch": 1.198865784499055,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004861101477610905,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.16609525978565215,
|
|
"num_tokens": 26316296.0,
|
|
"step": 14270
|
|
},
|
|
{
|
|
"entropy": 5.620381259918213,
|
|
"epoch": 1.1992858643142197,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048609978705006,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.16030900180339813,
|
|
"num_tokens": 26325525.0,
|
|
"step": 14275
|
|
},
|
|
{
|
|
"entropy": 5.588323783874512,
|
|
"epoch": 1.1997059441293847,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004860894225995055,
|
|
"loss": 5.2936,
|
|
"mean_token_accuracy": 0.17848464250564575,
|
|
"num_tokens": 26334195.0,
|
|
"step": 14280
|
|
},
|
|
{
|
|
"entropy": 5.591770601272583,
|
|
"epoch": 1.2001260239445495,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00048607905440961054,
|
|
"loss": 5.4193,
|
|
"mean_token_accuracy": 0.16965034008026122,
|
|
"num_tokens": 26343933.0,
|
|
"step": 14285
|
|
},
|
|
{
|
|
"entropy": 5.585553359985352,
|
|
"epoch": 1.2005461037597143,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00048606868248055887,
|
|
"loss": 5.3655,
|
|
"mean_token_accuracy": 0.17240449637174607,
|
|
"num_tokens": 26353455.0,
|
|
"step": 14290
|
|
},
|
|
{
|
|
"entropy": 5.625445175170898,
|
|
"epoch": 1.2009661835748793,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.0004860583068125341,
|
|
"loss": 5.3595,
|
|
"mean_token_accuracy": 0.1763713002204895,
|
|
"num_tokens": 26362662.0,
|
|
"step": 14295
|
|
},
|
|
{
|
|
"entropy": 5.617782211303711,
|
|
"epoch": 1.201386263390044,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 0.0004860479274057202,
|
|
"loss": 5.3823,
|
|
"mean_token_accuracy": 0.16244335919618608,
|
|
"num_tokens": 26371536.0,
|
|
"step": 14300
|
|
},
|
|
{
|
|
"entropy": 5.688301944732666,
|
|
"epoch": 1.201806343205209,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 0.00048603754426030087,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.16066131889820098,
|
|
"num_tokens": 26381925.0,
|
|
"step": 14305
|
|
},
|
|
{
|
|
"entropy": 5.561420583724976,
|
|
"epoch": 1.2022264230203739,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00048602715737646016,
|
|
"loss": 5.3225,
|
|
"mean_token_accuracy": 0.1739985778927803,
|
|
"num_tokens": 26391111.0,
|
|
"step": 14310
|
|
},
|
|
{
|
|
"entropy": 5.65993103981018,
|
|
"epoch": 1.2026465028355386,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048601676675438197,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.15840389132499694,
|
|
"num_tokens": 26401667.0,
|
|
"step": 14315
|
|
},
|
|
{
|
|
"entropy": 5.5718177318572994,
|
|
"epoch": 1.2030665826507037,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00048600637239425045,
|
|
"loss": 5.2976,
|
|
"mean_token_accuracy": 0.1749270662665367,
|
|
"num_tokens": 26411261.0,
|
|
"step": 14320
|
|
},
|
|
{
|
|
"entropy": 5.594204330444336,
|
|
"epoch": 1.2034866624658684,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00048599597429624966,
|
|
"loss": 5.4523,
|
|
"mean_token_accuracy": 0.1678444340825081,
|
|
"num_tokens": 26419808.0,
|
|
"step": 14325
|
|
},
|
|
{
|
|
"entropy": 5.619553756713867,
|
|
"epoch": 1.2039067422810334,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00048598557246056385,
|
|
"loss": 5.3716,
|
|
"mean_token_accuracy": 0.17062055170536042,
|
|
"num_tokens": 26429160.0,
|
|
"step": 14330
|
|
},
|
|
{
|
|
"entropy": 5.646615076065063,
|
|
"epoch": 1.2043268220961982,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00048597516688737727,
|
|
"loss": 5.323,
|
|
"mean_token_accuracy": 0.16848173439502717,
|
|
"num_tokens": 26437675.0,
|
|
"step": 14335
|
|
},
|
|
{
|
|
"entropy": 5.617009687423706,
|
|
"epoch": 1.2047469019113632,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048596475757687425,
|
|
"loss": 5.3784,
|
|
"mean_token_accuracy": 0.16564128547906876,
|
|
"num_tokens": 26446317.0,
|
|
"step": 14340
|
|
},
|
|
{
|
|
"entropy": 5.646167993545532,
|
|
"epoch": 1.205166981726528,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048595434452923915,
|
|
"loss": 5.4281,
|
|
"mean_token_accuracy": 0.1695418119430542,
|
|
"num_tokens": 26456183.0,
|
|
"step": 14345
|
|
},
|
|
{
|
|
"entropy": 5.607500267028809,
|
|
"epoch": 1.205587061541693,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048594392774465656,
|
|
"loss": 5.3788,
|
|
"mean_token_accuracy": 0.16330490559339522,
|
|
"num_tokens": 26466324.0,
|
|
"step": 14350
|
|
},
|
|
{
|
|
"entropy": 5.617480373382568,
|
|
"epoch": 1.2060071413568578,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 0.00048593350722331074,
|
|
"loss": 5.3833,
|
|
"mean_token_accuracy": 0.1691987097263336,
|
|
"num_tokens": 26475560.0,
|
|
"step": 14355
|
|
},
|
|
{
|
|
"entropy": 5.594552421569825,
|
|
"epoch": 1.2064272211720226,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00048592308296538654,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.1720819890499115,
|
|
"num_tokens": 26484955.0,
|
|
"step": 14360
|
|
},
|
|
{
|
|
"entropy": 5.626417207717895,
|
|
"epoch": 1.2068473009871876,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004859126549710686,
|
|
"loss": 5.3285,
|
|
"mean_token_accuracy": 0.1755720019340515,
|
|
"num_tokens": 26494306.0,
|
|
"step": 14365
|
|
},
|
|
{
|
|
"entropy": 5.5393060684204105,
|
|
"epoch": 1.2072673808023524,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048590222324054153,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.1715349316596985,
|
|
"num_tokens": 26503871.0,
|
|
"step": 14370
|
|
},
|
|
{
|
|
"entropy": 5.69525637626648,
|
|
"epoch": 1.2076874606175174,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004858917877739901,
|
|
"loss": 5.4348,
|
|
"mean_token_accuracy": 0.16756290048360825,
|
|
"num_tokens": 26511929.0,
|
|
"step": 14375
|
|
},
|
|
{
|
|
"entropy": 5.635641384124756,
|
|
"epoch": 1.2081075404326822,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.0004858813485715994,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.1570291668176651,
|
|
"num_tokens": 26520469.0,
|
|
"step": 14380
|
|
},
|
|
{
|
|
"entropy": 5.578332471847534,
|
|
"epoch": 1.208527620247847,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004858709056335541,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.17001325488090516,
|
|
"num_tokens": 26530102.0,
|
|
"step": 14385
|
|
},
|
|
{
|
|
"entropy": 5.59905424118042,
|
|
"epoch": 1.208947700063012,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048586045896003926,
|
|
"loss": 5.4087,
|
|
"mean_token_accuracy": 0.16630999445915223,
|
|
"num_tokens": 26538705.0,
|
|
"step": 14390
|
|
},
|
|
{
|
|
"entropy": 5.69228982925415,
|
|
"epoch": 1.2093677798781768,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004858500085512401,
|
|
"loss": 5.4881,
|
|
"mean_token_accuracy": 0.1661173954606056,
|
|
"num_tokens": 26548315.0,
|
|
"step": 14395
|
|
},
|
|
{
|
|
"entropy": 5.649106121063232,
|
|
"epoch": 1.2097878596933418,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048583955440734144,
|
|
"loss": 5.3282,
|
|
"mean_token_accuracy": 0.17240462452173233,
|
|
"num_tokens": 26556412.0,
|
|
"step": 14400
|
|
},
|
|
{
|
|
"entropy": 5.625435066223145,
|
|
"epoch": 1.2102079395085066,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048582909652852873,
|
|
"loss": 5.4968,
|
|
"mean_token_accuracy": 0.16067309379577638,
|
|
"num_tokens": 26566146.0,
|
|
"step": 14405
|
|
},
|
|
{
|
|
"entropy": 5.625951051712036,
|
|
"epoch": 1.2106280193236716,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004858186349149871,
|
|
"loss": 5.3675,
|
|
"mean_token_accuracy": 0.17302857339382172,
|
|
"num_tokens": 26576019.0,
|
|
"step": 14410
|
|
},
|
|
{
|
|
"entropy": 5.502639245986939,
|
|
"epoch": 1.2110480991388364,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.000485808169566902,
|
|
"loss": 5.2506,
|
|
"mean_token_accuracy": 0.1733314648270607,
|
|
"num_tokens": 26585461.0,
|
|
"step": 14415
|
|
},
|
|
{
|
|
"entropy": 5.525038766860962,
|
|
"epoch": 1.2114681789540014,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048579770048445863,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.18916076570749282,
|
|
"num_tokens": 26594021.0,
|
|
"step": 14420
|
|
},
|
|
{
|
|
"entropy": 5.684835815429688,
|
|
"epoch": 1.2118882587691662,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00048578722766784253,
|
|
"loss": 5.4226,
|
|
"mean_token_accuracy": 0.17051784992218016,
|
|
"num_tokens": 26602712.0,
|
|
"step": 14425
|
|
},
|
|
{
|
|
"entropy": 5.488742208480835,
|
|
"epoch": 1.212308338584331,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00048577675111723925,
|
|
"loss": 5.126,
|
|
"mean_token_accuracy": 0.18584653735160828,
|
|
"num_tokens": 26610970.0,
|
|
"step": 14430
|
|
},
|
|
{
|
|
"entropy": 5.540399980545044,
|
|
"epoch": 1.212728418399496,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048576627083283435,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.1722578689455986,
|
|
"num_tokens": 26619840.0,
|
|
"step": 14435
|
|
},
|
|
{
|
|
"entropy": 5.57360143661499,
|
|
"epoch": 1.2131484982146608,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004857557868148136,
|
|
"loss": 5.2954,
|
|
"mean_token_accuracy": 0.1812925085425377,
|
|
"num_tokens": 26629271.0,
|
|
"step": 14440
|
|
},
|
|
{
|
|
"entropy": 5.578191137313842,
|
|
"epoch": 1.2135685780298258,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0004857452990633625,
|
|
"loss": 5.3284,
|
|
"mean_token_accuracy": 0.16607633531093596,
|
|
"num_tokens": 26638610.0,
|
|
"step": 14445
|
|
},
|
|
{
|
|
"entropy": 5.695629978179932,
|
|
"epoch": 1.2139886578449905,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00048573480757866695,
|
|
"loss": 5.4857,
|
|
"mean_token_accuracy": 0.1657136708498001,
|
|
"num_tokens": 26648504.0,
|
|
"step": 14450
|
|
},
|
|
{
|
|
"entropy": 5.607351779937744,
|
|
"epoch": 1.2144087376601553,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048572431236091284,
|
|
"loss": 5.3873,
|
|
"mean_token_accuracy": 0.16882047355175017,
|
|
"num_tokens": 26658084.0,
|
|
"step": 14455
|
|
},
|
|
{
|
|
"entropy": 5.644829940795899,
|
|
"epoch": 1.2148288174753203,
|
|
"grad_norm": 1.7265625,
|
|
"learning_rate": 0.00048571381341028604,
|
|
"loss": 5.4706,
|
|
"mean_token_accuracy": 0.1678345263004303,
|
|
"num_tokens": 26666933.0,
|
|
"step": 14460
|
|
},
|
|
{
|
|
"entropy": 5.644724893569946,
|
|
"epoch": 1.2152488972904851,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004857033107269725,
|
|
"loss": 5.3232,
|
|
"mean_token_accuracy": 0.1732431948184967,
|
|
"num_tokens": 26675049.0,
|
|
"step": 14465
|
|
},
|
|
{
|
|
"entropy": 5.52176342010498,
|
|
"epoch": 1.2156689771056501,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00048569280431115823,
|
|
"loss": 5.4043,
|
|
"mean_token_accuracy": 0.16803978532552719,
|
|
"num_tokens": 26684223.0,
|
|
"step": 14470
|
|
},
|
|
{
|
|
"entropy": 5.621050262451172,
|
|
"epoch": 1.216089056920815,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004856822941630296,
|
|
"loss": 5.3435,
|
|
"mean_token_accuracy": 0.16737112104892732,
|
|
"num_tokens": 26693605.0,
|
|
"step": 14475
|
|
},
|
|
{
|
|
"entropy": 5.710792303085327,
|
|
"epoch": 1.2165091367359797,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048567178028277255,
|
|
"loss": 5.4134,
|
|
"mean_token_accuracy": 0.1695218563079834,
|
|
"num_tokens": 26702829.0,
|
|
"step": 14480
|
|
},
|
|
{
|
|
"entropy": 5.642229652404785,
|
|
"epoch": 1.2169292165511447,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004856612626705733,
|
|
"loss": 5.4595,
|
|
"mean_token_accuracy": 0.16188946068286897,
|
|
"num_tokens": 26712466.0,
|
|
"step": 14485
|
|
},
|
|
{
|
|
"entropy": 5.596743965148926,
|
|
"epoch": 1.2173492963663095,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0004856507413266183,
|
|
"loss": 5.3383,
|
|
"mean_token_accuracy": 0.1772727981209755,
|
|
"num_tokens": 26721730.0,
|
|
"step": 14490
|
|
},
|
|
{
|
|
"entropy": 5.599400043487549,
|
|
"epoch": 1.2177693761814745,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.000485640216251094,
|
|
"loss": 5.4108,
|
|
"mean_token_accuracy": 0.16504266113042831,
|
|
"num_tokens": 26731017.0,
|
|
"step": 14495
|
|
},
|
|
{
|
|
"entropy": 5.61780891418457,
|
|
"epoch": 1.2181894559966393,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00048562968744418665,
|
|
"loss": 5.3921,
|
|
"mean_token_accuracy": 0.16558818370103837,
|
|
"num_tokens": 26739588.0,
|
|
"step": 14500
|
|
},
|
|
{
|
|
"entropy": 5.671893072128296,
|
|
"epoch": 1.2186095358118043,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004856191549060828,
|
|
"loss": 5.4964,
|
|
"mean_token_accuracy": 0.1626824587583542,
|
|
"num_tokens": 26748889.0,
|
|
"step": 14505
|
|
},
|
|
{
|
|
"entropy": 5.732660531997681,
|
|
"epoch": 1.219029615626969,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048560861863696913,
|
|
"loss": 5.4597,
|
|
"mean_token_accuracy": 0.16027596443891526,
|
|
"num_tokens": 26757979.0,
|
|
"step": 14510
|
|
},
|
|
{
|
|
"entropy": 5.643172311782837,
|
|
"epoch": 1.219449695442134,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004855980786370322,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.17041491568088532,
|
|
"num_tokens": 26767225.0,
|
|
"step": 14515
|
|
},
|
|
{
|
|
"entropy": 5.515580940246582,
|
|
"epoch": 1.219869775257299,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004855875349064588,
|
|
"loss": 5.3028,
|
|
"mean_token_accuracy": 0.17166967391967775,
|
|
"num_tokens": 26776289.0,
|
|
"step": 14520
|
|
},
|
|
{
|
|
"entropy": 5.628920555114746,
|
|
"epoch": 1.2202898550724637,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004855769874454356,
|
|
"loss": 5.4263,
|
|
"mean_token_accuracy": 0.16554307341575622,
|
|
"num_tokens": 26785631.0,
|
|
"step": 14525
|
|
},
|
|
{
|
|
"entropy": 5.6312535285949705,
|
|
"epoch": 1.2207099348876287,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004855664362541495,
|
|
"loss": 5.4299,
|
|
"mean_token_accuracy": 0.1641710191965103,
|
|
"num_tokens": 26795285.0,
|
|
"step": 14530
|
|
},
|
|
{
|
|
"entropy": 5.590521383285522,
|
|
"epoch": 1.2211300147027935,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00048555588133278744,
|
|
"loss": 5.3621,
|
|
"mean_token_accuracy": 0.16726839244365693,
|
|
"num_tokens": 26804584.0,
|
|
"step": 14535
|
|
},
|
|
{
|
|
"entropy": 5.49451699256897,
|
|
"epoch": 1.2215500945179585,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004855453226815363,
|
|
"loss": 5.246,
|
|
"mean_token_accuracy": 0.17162280678749084,
|
|
"num_tokens": 26814354.0,
|
|
"step": 14540
|
|
},
|
|
{
|
|
"entropy": 5.510982656478882,
|
|
"epoch": 1.2219701743331233,
|
|
"grad_norm": 1.84375,
|
|
"learning_rate": 0.00048553476030058326,
|
|
"loss": 5.253,
|
|
"mean_token_accuracy": 0.17902337461709977,
|
|
"num_tokens": 26824274.0,
|
|
"step": 14545
|
|
},
|
|
{
|
|
"entropy": 5.539727735519409,
|
|
"epoch": 1.222390254148288,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048552419419011536,
|
|
"loss": 5.3939,
|
|
"mean_token_accuracy": 0.16667712926864625,
|
|
"num_tokens": 26833155.0,
|
|
"step": 14550
|
|
},
|
|
{
|
|
"entropy": 5.56984052658081,
|
|
"epoch": 1.222810333963453,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004855136243503196,
|
|
"loss": 5.3381,
|
|
"mean_token_accuracy": 0.1722673550248146,
|
|
"num_tokens": 26842545.0,
|
|
"step": 14555
|
|
},
|
|
{
|
|
"entropy": 5.685318660736084,
|
|
"epoch": 1.2232304137786179,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048550305078138363,
|
|
"loss": 5.3956,
|
|
"mean_token_accuracy": 0.17062428295612336,
|
|
"num_tokens": 26851772.0,
|
|
"step": 14560
|
|
},
|
|
{
|
|
"entropy": 5.568029260635376,
|
|
"epoch": 1.2236504935937829,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00048549247348349435,
|
|
"loss": 5.2793,
|
|
"mean_token_accuracy": 0.174759641289711,
|
|
"num_tokens": 26860884.0,
|
|
"step": 14565
|
|
},
|
|
{
|
|
"entropy": 5.564513111114502,
|
|
"epoch": 1.2240705734089476,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00048548189245683934,
|
|
"loss": 5.4267,
|
|
"mean_token_accuracy": 0.16911133825778962,
|
|
"num_tokens": 26869435.0,
|
|
"step": 14570
|
|
},
|
|
{
|
|
"entropy": 5.592051601409912,
|
|
"epoch": 1.2244906532241127,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00048547130770160596,
|
|
"loss": 5.3124,
|
|
"mean_token_accuracy": 0.16932346522808076,
|
|
"num_tokens": 26878852.0,
|
|
"step": 14575
|
|
},
|
|
{
|
|
"entropy": 5.577689075469971,
|
|
"epoch": 1.2249107330392774,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004854607192179817,
|
|
"loss": 5.2905,
|
|
"mean_token_accuracy": 0.17675579339265823,
|
|
"num_tokens": 26887532.0,
|
|
"step": 14580
|
|
},
|
|
{
|
|
"entropy": 5.715707492828369,
|
|
"epoch": 1.2253308128544425,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004854501270061543,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16146958619356155,
|
|
"num_tokens": 26897459.0,
|
|
"step": 14585
|
|
},
|
|
{
|
|
"entropy": 5.579214477539063,
|
|
"epoch": 1.2257508926696072,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048543953106631115,
|
|
"loss": 5.2892,
|
|
"mean_token_accuracy": 0.17801006734371186,
|
|
"num_tokens": 26907156.0,
|
|
"step": 14590
|
|
},
|
|
{
|
|
"entropy": 5.656476449966431,
|
|
"epoch": 1.226170972484772,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004854289313986401,
|
|
"loss": 5.3707,
|
|
"mean_token_accuracy": 0.17163809537887573,
|
|
"num_tokens": 26915764.0,
|
|
"step": 14595
|
|
},
|
|
{
|
|
"entropy": 5.503813743591309,
|
|
"epoch": 1.226591052299937,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004854183280033289,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.17583397030830383,
|
|
"num_tokens": 26924166.0,
|
|
"step": 14600
|
|
},
|
|
{
|
|
"entropy": 5.597974634170532,
|
|
"epoch": 1.2270111321151018,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004854077208805654,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.16351360082626343,
|
|
"num_tokens": 26933546.0,
|
|
"step": 14605
|
|
},
|
|
{
|
|
"entropy": 5.665269470214843,
|
|
"epoch": 1.2274312119302668,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004853971100305374,
|
|
"loss": 5.4106,
|
|
"mean_token_accuracy": 0.17088524252176285,
|
|
"num_tokens": 26943213.0,
|
|
"step": 14610
|
|
},
|
|
{
|
|
"entropy": 5.642615509033203,
|
|
"epoch": 1.2278512917454316,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000485386495453433,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.17016868144273758,
|
|
"num_tokens": 26952968.0,
|
|
"step": 14615
|
|
},
|
|
{
|
|
"entropy": 5.602711772918701,
|
|
"epoch": 1.2282713715605964,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00048537587714944007,
|
|
"loss": 5.3617,
|
|
"mean_token_accuracy": 0.17121365219354628,
|
|
"num_tokens": 26962230.0,
|
|
"step": 14620
|
|
},
|
|
{
|
|
"entropy": 5.569738960266113,
|
|
"epoch": 1.2286914513757614,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 0.0004853652551187469,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.1704752415418625,
|
|
"num_tokens": 26970985.0,
|
|
"step": 14625
|
|
},
|
|
{
|
|
"entropy": 5.595652675628662,
|
|
"epoch": 1.2291115311909262,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048535462936154147,
|
|
"loss": 5.4432,
|
|
"mean_token_accuracy": 0.16540713161230086,
|
|
"num_tokens": 26981138.0,
|
|
"step": 14630
|
|
},
|
|
{
|
|
"entropy": 5.571217012405396,
|
|
"epoch": 1.2295316110060912,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004853439998780122,
|
|
"loss": 5.2923,
|
|
"mean_token_accuracy": 0.17418538480997087,
|
|
"num_tokens": 26990158.0,
|
|
"step": 14635
|
|
},
|
|
{
|
|
"entropy": 5.555435848236084,
|
|
"epoch": 1.229951690821256,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004853333666683472,
|
|
"loss": 5.4524,
|
|
"mean_token_accuracy": 0.15979965180158615,
|
|
"num_tokens": 26998889.0,
|
|
"step": 14640
|
|
},
|
|
{
|
|
"entropy": 5.5809015274047855,
|
|
"epoch": 1.230371770636421,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048532272973273496,
|
|
"loss": 5.3746,
|
|
"mean_token_accuracy": 0.1682994320988655,
|
|
"num_tokens": 27008912.0,
|
|
"step": 14645
|
|
},
|
|
{
|
|
"entropy": 5.584909915924072,
|
|
"epoch": 1.2307918504515858,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00048531208907136384,
|
|
"loss": 5.2717,
|
|
"mean_token_accuracy": 0.1803266391158104,
|
|
"num_tokens": 27017573.0,
|
|
"step": 14650
|
|
},
|
|
{
|
|
"entropy": 5.545006895065308,
|
|
"epoch": 1.2312119302667508,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048530144468442236,
|
|
"loss": 5.3466,
|
|
"mean_token_accuracy": 0.16579411923885345,
|
|
"num_tokens": 27027205.0,
|
|
"step": 14655
|
|
},
|
|
{
|
|
"entropy": 5.5912316799163815,
|
|
"epoch": 1.2316320100819156,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048529079657209906,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.17231107950210572,
|
|
"num_tokens": 27035882.0,
|
|
"step": 14660
|
|
},
|
|
{
|
|
"entropy": 5.567312002182007,
|
|
"epoch": 1.2320520898970804,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0004852801447345826,
|
|
"loss": 5.3731,
|
|
"mean_token_accuracy": 0.17508108913898468,
|
|
"num_tokens": 27044761.0,
|
|
"step": 14665
|
|
},
|
|
{
|
|
"entropy": 5.584702253341675,
|
|
"epoch": 1.2324721697122454,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004852694891720617,
|
|
"loss": 5.4038,
|
|
"mean_token_accuracy": 0.16734053641557695,
|
|
"num_tokens": 27054149.0,
|
|
"step": 14670
|
|
},
|
|
{
|
|
"entropy": 5.618700885772705,
|
|
"epoch": 1.2328922495274102,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.000485258829884725,
|
|
"loss": 5.4268,
|
|
"mean_token_accuracy": 0.16779596209526063,
|
|
"num_tokens": 27063145.0,
|
|
"step": 14675
|
|
},
|
|
{
|
|
"entropy": 5.663679790496826,
|
|
"epoch": 1.2333123293425752,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004852481668727614,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.16674899011850358,
|
|
"num_tokens": 27072378.0,
|
|
"step": 14680
|
|
},
|
|
{
|
|
"entropy": 5.482738351821899,
|
|
"epoch": 1.23373240915774,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00048523750013635986,
|
|
"loss": 5.2766,
|
|
"mean_token_accuracy": 0.16852893084287643,
|
|
"num_tokens": 27082241.0,
|
|
"step": 14685
|
|
},
|
|
{
|
|
"entropy": 5.538816165924072,
|
|
"epoch": 1.2341524889729047,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0004852268296757092,
|
|
"loss": 5.2809,
|
|
"mean_token_accuracy": 0.1719914510846138,
|
|
"num_tokens": 27091488.0,
|
|
"step": 14690
|
|
},
|
|
{
|
|
"entropy": 5.646978235244751,
|
|
"epoch": 1.2345725687880698,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004852161554909985,
|
|
"loss": 5.3468,
|
|
"mean_token_accuracy": 0.17167492508888244,
|
|
"num_tokens": 27100378.0,
|
|
"step": 14695
|
|
},
|
|
{
|
|
"entropy": 5.596823120117188,
|
|
"epoch": 1.2349926486032345,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048520547758241686,
|
|
"loss": 5.3657,
|
|
"mean_token_accuracy": 0.1682916134595871,
|
|
"num_tokens": 27110341.0,
|
|
"step": 14700
|
|
},
|
|
{
|
|
"entropy": 5.5891765594482425,
|
|
"epoch": 1.2354127284183996,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00048519479595015343,
|
|
"loss": 5.301,
|
|
"mean_token_accuracy": 0.16862540543079377,
|
|
"num_tokens": 27119381.0,
|
|
"step": 14705
|
|
},
|
|
{
|
|
"entropy": 5.552208662033081,
|
|
"epoch": 1.2358328082335643,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048518411059439746,
|
|
"loss": 5.4066,
|
|
"mean_token_accuracy": 0.16474692076444625,
|
|
"num_tokens": 27129167.0,
|
|
"step": 14710
|
|
},
|
|
{
|
|
"entropy": 5.632622337341308,
|
|
"epoch": 1.2362528880487293,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00048517342151533813,
|
|
"loss": 5.4217,
|
|
"mean_token_accuracy": 0.16225503087043763,
|
|
"num_tokens": 27138479.0,
|
|
"step": 14715
|
|
},
|
|
{
|
|
"entropy": 5.650741481781006,
|
|
"epoch": 1.2366729678638941,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004851627287131649,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.17363323420286178,
|
|
"num_tokens": 27147197.0,
|
|
"step": 14720
|
|
},
|
|
{
|
|
"entropy": 5.559444570541382,
|
|
"epoch": 1.2370930476790591,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004851520321880672,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.17298350632190704,
|
|
"num_tokens": 27155854.0,
|
|
"step": 14725
|
|
},
|
|
{
|
|
"entropy": 5.521408653259277,
|
|
"epoch": 1.237513127494224,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 0.0004851413319402344,
|
|
"loss": 5.2974,
|
|
"mean_token_accuracy": 0.17052881568670272,
|
|
"num_tokens": 27165069.0,
|
|
"step": 14730
|
|
},
|
|
{
|
|
"entropy": 5.574164962768554,
|
|
"epoch": 1.2379332073093887,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0004851306279698561,
|
|
"loss": 5.3423,
|
|
"mean_token_accuracy": 0.16862837523221968,
|
|
"num_tokens": 27174070.0,
|
|
"step": 14735
|
|
},
|
|
{
|
|
"entropy": 5.6579419612884525,
|
|
"epoch": 1.2383532871245537,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004851199202771219,
|
|
"loss": 5.4081,
|
|
"mean_token_accuracy": 0.17232888638973237,
|
|
"num_tokens": 27182903.0,
|
|
"step": 14740
|
|
},
|
|
{
|
|
"entropy": 5.600107097625733,
|
|
"epoch": 1.2387733669397185,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.0004851092088622216,
|
|
"loss": 5.3261,
|
|
"mean_token_accuracy": 0.17474351972341537,
|
|
"num_tokens": 27192747.0,
|
|
"step": 14745
|
|
},
|
|
{
|
|
"entropy": 5.612848854064941,
|
|
"epoch": 1.2391934467548835,
|
|
"grad_norm": 2.484375,
|
|
"learning_rate": 0.0004850984937253448,
|
|
"loss": 5.3556,
|
|
"mean_token_accuracy": 0.17478209882974624,
|
|
"num_tokens": 27201657.0,
|
|
"step": 14750
|
|
},
|
|
{
|
|
"entropy": 5.615834140777588,
|
|
"epoch": 1.2396135265700483,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0004850877748666814,
|
|
"loss": 5.3847,
|
|
"mean_token_accuracy": 0.16818059235811234,
|
|
"num_tokens": 27211794.0,
|
|
"step": 14755
|
|
},
|
|
{
|
|
"entropy": 5.55868353843689,
|
|
"epoch": 1.240033606385213,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00048507705228642117,
|
|
"loss": 5.3335,
|
|
"mean_token_accuracy": 0.1659922033548355,
|
|
"num_tokens": 27221852.0,
|
|
"step": 14760
|
|
},
|
|
{
|
|
"entropy": 5.535787153244018,
|
|
"epoch": 1.240453686200378,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004850663259847542,
|
|
"loss": 5.3732,
|
|
"mean_token_accuracy": 0.16893673092126846,
|
|
"num_tokens": 27231558.0,
|
|
"step": 14765
|
|
},
|
|
{
|
|
"entropy": 5.583010578155518,
|
|
"epoch": 1.240873766015543,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00048505559596187037,
|
|
"loss": 5.367,
|
|
"mean_token_accuracy": 0.1675555646419525,
|
|
"num_tokens": 27241053.0,
|
|
"step": 14770
|
|
},
|
|
{
|
|
"entropy": 5.5506453037261965,
|
|
"epoch": 1.241293845830708,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004850448622179599,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.1718742474913597,
|
|
"num_tokens": 27249770.0,
|
|
"step": 14775
|
|
},
|
|
{
|
|
"entropy": 5.689253664016723,
|
|
"epoch": 1.2417139256458727,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004850341247532128,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.16661347299814225,
|
|
"num_tokens": 27258883.0,
|
|
"step": 14780
|
|
},
|
|
{
|
|
"entropy": 5.706023788452148,
|
|
"epoch": 1.2421340054610377,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004850233835678194,
|
|
"loss": 5.4073,
|
|
"mean_token_accuracy": 0.16898039877414703,
|
|
"num_tokens": 27268056.0,
|
|
"step": 14785
|
|
},
|
|
{
|
|
"entropy": 5.5874651908874515,
|
|
"epoch": 1.2425540852762025,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004850126386619699,
|
|
"loss": 5.2741,
|
|
"mean_token_accuracy": 0.17798781841993333,
|
|
"num_tokens": 27276965.0,
|
|
"step": 14790
|
|
},
|
|
{
|
|
"entropy": 5.542857933044433,
|
|
"epoch": 1.2429741650913673,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004850018900358545,
|
|
"loss": 5.3366,
|
|
"mean_token_accuracy": 0.172660693526268,
|
|
"num_tokens": 27286173.0,
|
|
"step": 14795
|
|
},
|
|
{
|
|
"entropy": 5.521266126632691,
|
|
"epoch": 1.2433942449065323,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00048499113768966386,
|
|
"loss": 5.3327,
|
|
"mean_token_accuracy": 0.17302975356578826,
|
|
"num_tokens": 27294863.0,
|
|
"step": 14800
|
|
},
|
|
{
|
|
"entropy": 5.655036687850952,
|
|
"epoch": 1.243814324721697,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004849803816235884,
|
|
"loss": 5.3766,
|
|
"mean_token_accuracy": 0.16847763061523438,
|
|
"num_tokens": 27304427.0,
|
|
"step": 14805
|
|
},
|
|
{
|
|
"entropy": 5.688740253448486,
|
|
"epoch": 1.244234404536862,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004849696218378185,
|
|
"loss": 5.4333,
|
|
"mean_token_accuracy": 0.17155794352293013,
|
|
"num_tokens": 27313716.0,
|
|
"step": 14810
|
|
},
|
|
{
|
|
"entropy": 5.617390871047974,
|
|
"epoch": 1.2446544843520269,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0004849588583325449,
|
|
"loss": 5.3292,
|
|
"mean_token_accuracy": 0.18261649310588837,
|
|
"num_tokens": 27322342.0,
|
|
"step": 14815
|
|
},
|
|
{
|
|
"entropy": 5.616417503356933,
|
|
"epoch": 1.2450745641671919,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004849480911079583,
|
|
"loss": 5.4174,
|
|
"mean_token_accuracy": 0.15718486905097961,
|
|
"num_tokens": 27331892.0,
|
|
"step": 14820
|
|
},
|
|
{
|
|
"entropy": 5.610023641586304,
|
|
"epoch": 1.2454946439823567,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004849373201642493,
|
|
"loss": 5.3836,
|
|
"mean_token_accuracy": 0.1622963383793831,
|
|
"num_tokens": 27340428.0,
|
|
"step": 14825
|
|
},
|
|
{
|
|
"entropy": 5.621714544296265,
|
|
"epoch": 1.2459147237975214,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004849265455016088,
|
|
"loss": 5.3862,
|
|
"mean_token_accuracy": 0.1723904699087143,
|
|
"num_tokens": 27349224.0,
|
|
"step": 14830
|
|
},
|
|
{
|
|
"entropy": 5.606583881378174,
|
|
"epoch": 1.2463348036126864,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0004849157671202277,
|
|
"loss": 5.3828,
|
|
"mean_token_accuracy": 0.1659926727414131,
|
|
"num_tokens": 27357480.0,
|
|
"step": 14835
|
|
},
|
|
{
|
|
"entropy": 5.552874517440796,
|
|
"epoch": 1.2467548834278512,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004849049850202968,
|
|
"loss": 5.2868,
|
|
"mean_token_accuracy": 0.17431298196315764,
|
|
"num_tokens": 27366732.0,
|
|
"step": 14840
|
|
},
|
|
{
|
|
"entropy": 5.611221361160278,
|
|
"epoch": 1.2471749632430162,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0004848941992020072,
|
|
"loss": 5.3869,
|
|
"mean_token_accuracy": 0.16717041432857513,
|
|
"num_tokens": 27375834.0,
|
|
"step": 14845
|
|
},
|
|
{
|
|
"entropy": 5.643020820617676,
|
|
"epoch": 1.247595043058181,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0004848834096655499,
|
|
"loss": 5.3826,
|
|
"mean_token_accuracy": 0.17003615349531173,
|
|
"num_tokens": 27385311.0,
|
|
"step": 14850
|
|
},
|
|
{
|
|
"entropy": 5.604761075973511,
|
|
"epoch": 1.2480151228733458,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00048487261641111607,
|
|
"loss": 5.4224,
|
|
"mean_token_accuracy": 0.168009015917778,
|
|
"num_tokens": 27394587.0,
|
|
"step": 14855
|
|
},
|
|
{
|
|
"entropy": 5.527986001968384,
|
|
"epoch": 1.2484352026885108,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000484861819438897,
|
|
"loss": 5.2958,
|
|
"mean_token_accuracy": 0.16891696453094482,
|
|
"num_tokens": 27403316.0,
|
|
"step": 14860
|
|
},
|
|
{
|
|
"entropy": 5.620045137405396,
|
|
"epoch": 1.2488552825036756,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004848510187490838,
|
|
"loss": 5.3531,
|
|
"mean_token_accuracy": 0.1735784664750099,
|
|
"num_tokens": 27412709.0,
|
|
"step": 14865
|
|
},
|
|
{
|
|
"entropy": 5.631797504425049,
|
|
"epoch": 1.2492753623188406,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0004848402143418679,
|
|
"loss": 5.3955,
|
|
"mean_token_accuracy": 0.16247193217277528,
|
|
"num_tokens": 27422004.0,
|
|
"step": 14870
|
|
},
|
|
{
|
|
"entropy": 5.619765853881836,
|
|
"epoch": 1.2496954421340054,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00048482940621744053,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.1660287693142891,
|
|
"num_tokens": 27431931.0,
|
|
"step": 14875
|
|
},
|
|
{
|
|
"entropy": 5.5691510200500485,
|
|
"epoch": 1.2501155219491704,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004848185943759934,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.17852565497159958,
|
|
"num_tokens": 27441527.0,
|
|
"step": 14880
|
|
},
|
|
{
|
|
"entropy": 5.679601383209229,
|
|
"epoch": 1.2505356017643352,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00048480777881771786,
|
|
"loss": 5.4032,
|
|
"mean_token_accuracy": 0.17205158323049546,
|
|
"num_tokens": 27449964.0,
|
|
"step": 14885
|
|
},
|
|
{
|
|
"entropy": 5.577618885040283,
|
|
"epoch": 1.2509556815795002,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004847969595428056,
|
|
"loss": 5.4068,
|
|
"mean_token_accuracy": 0.16642248779535293,
|
|
"num_tokens": 27459044.0,
|
|
"step": 14890
|
|
},
|
|
{
|
|
"entropy": 5.516439294815063,
|
|
"epoch": 1.251375761394665,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00048478613655144817,
|
|
"loss": 5.3848,
|
|
"mean_token_accuracy": 0.17271924316883086,
|
|
"num_tokens": 27467644.0,
|
|
"step": 14895
|
|
},
|
|
{
|
|
"entropy": 5.647580671310425,
|
|
"epoch": 1.2517958412098298,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0004847753098438374,
|
|
"loss": 5.4163,
|
|
"mean_token_accuracy": 0.1645412638783455,
|
|
"num_tokens": 27476899.0,
|
|
"step": 14900
|
|
},
|
|
{
|
|
"entropy": 5.652610969543457,
|
|
"epoch": 1.2522159210249948,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000484764479420165,
|
|
"loss": 5.3022,
|
|
"mean_token_accuracy": 0.17347924262285233,
|
|
"num_tokens": 27485167.0,
|
|
"step": 14905
|
|
},
|
|
{
|
|
"entropy": 5.605359888076782,
|
|
"epoch": 1.2526360008401596,
|
|
"grad_norm": 2.125,
|
|
"learning_rate": 0.00048475364528062287,
|
|
"loss": 5.3489,
|
|
"mean_token_accuracy": 0.16680347472429274,
|
|
"num_tokens": 27493986.0,
|
|
"step": 14910
|
|
},
|
|
{
|
|
"entropy": 5.598525142669677,
|
|
"epoch": 1.2530560806553246,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0004847428074254029,
|
|
"loss": 5.3958,
|
|
"mean_token_accuracy": 0.17133786529302597,
|
|
"num_tokens": 27503896.0,
|
|
"step": 14915
|
|
},
|
|
{
|
|
"entropy": 5.594638013839722,
|
|
"epoch": 1.2534761604704894,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00048473196585469713,
|
|
"loss": 5.3445,
|
|
"mean_token_accuracy": 0.17187246382236482,
|
|
"num_tokens": 27513485.0,
|
|
"step": 14920
|
|
},
|
|
{
|
|
"entropy": 5.675473594665528,
|
|
"epoch": 1.2538962402856542,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00048472112056869763,
|
|
"loss": 5.4025,
|
|
"mean_token_accuracy": 0.16582921296358108,
|
|
"num_tokens": 27523164.0,
|
|
"step": 14925
|
|
},
|
|
{
|
|
"entropy": 5.656335401535034,
|
|
"epoch": 1.2543163201008192,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004847102715675964,
|
|
"loss": 5.3543,
|
|
"mean_token_accuracy": 0.1656375214457512,
|
|
"num_tokens": 27531387.0,
|
|
"step": 14930
|
|
},
|
|
{
|
|
"entropy": 5.529454326629638,
|
|
"epoch": 1.254736399915984,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0004846994188515857,
|
|
"loss": 5.3584,
|
|
"mean_token_accuracy": 0.1758265182375908,
|
|
"num_tokens": 27541754.0,
|
|
"step": 14935
|
|
},
|
|
{
|
|
"entropy": 5.71507420539856,
|
|
"epoch": 1.255156479731149,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004846885624208578,
|
|
"loss": 5.4257,
|
|
"mean_token_accuracy": 0.1660853862762451,
|
|
"num_tokens": 27551458.0,
|
|
"step": 14940
|
|
},
|
|
{
|
|
"entropy": 5.602577018737793,
|
|
"epoch": 1.2555765595463138,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000484677702275605,
|
|
"loss": 5.3479,
|
|
"mean_token_accuracy": 0.17095886170864105,
|
|
"num_tokens": 27560797.0,
|
|
"step": 14945
|
|
},
|
|
{
|
|
"entropy": 5.6042085647583,
|
|
"epoch": 1.2559966393614788,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00048466683841601963,
|
|
"loss": 5.3411,
|
|
"mean_token_accuracy": 0.17054116278886794,
|
|
"num_tokens": 27570166.0,
|
|
"step": 14950
|
|
},
|
|
{
|
|
"entropy": 5.517857694625855,
|
|
"epoch": 1.2564167191766435,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048465597084229416,
|
|
"loss": 5.2558,
|
|
"mean_token_accuracy": 0.17219745814800264,
|
|
"num_tokens": 27579411.0,
|
|
"step": 14955
|
|
},
|
|
{
|
|
"entropy": 5.601072359085083,
|
|
"epoch": 1.2568367989918086,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0004846450995546212,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.16506696194410325,
|
|
"num_tokens": 27589124.0,
|
|
"step": 14960
|
|
},
|
|
{
|
|
"entropy": 5.6472714900970455,
|
|
"epoch": 1.2572568788069733,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0004846342245531932,
|
|
"loss": 5.464,
|
|
"mean_token_accuracy": 0.16000686436891556,
|
|
"num_tokens": 27598664.0,
|
|
"step": 14965
|
|
},
|
|
{
|
|
"entropy": 5.678275871276855,
|
|
"epoch": 1.2576769586221381,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0004846233458382029,
|
|
"loss": 5.3874,
|
|
"mean_token_accuracy": 0.1715864896774292,
|
|
"num_tokens": 27607189.0,
|
|
"step": 14970
|
|
},
|
|
{
|
|
"entropy": 5.669829320907593,
|
|
"epoch": 1.2580970384373031,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00048461246340984293,
|
|
"loss": 5.4133,
|
|
"mean_token_accuracy": 0.16904016584157944,
|
|
"num_tokens": 27616415.0,
|
|
"step": 14975
|
|
},
|
|
{
|
|
"entropy": 5.568628215789795,
|
|
"epoch": 1.258517118252468,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0004846015772683061,
|
|
"loss": 5.3917,
|
|
"mean_token_accuracy": 0.17225440591573715,
|
|
"num_tokens": 27624492.0,
|
|
"step": 14980
|
|
},
|
|
{
|
|
"entropy": 5.503430938720703,
|
|
"epoch": 1.258937198067633,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00048459068741378526,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.17117979377508163,
|
|
"num_tokens": 27634243.0,
|
|
"step": 14985
|
|
},
|
|
{
|
|
"entropy": 5.620176553726196,
|
|
"epoch": 1.2593572778827977,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004845797938464734,
|
|
"loss": 5.3965,
|
|
"mean_token_accuracy": 0.17155803442001344,
|
|
"num_tokens": 27642887.0,
|
|
"step": 14990
|
|
},
|
|
{
|
|
"entropy": 5.611432361602783,
|
|
"epoch": 1.2597773576979625,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0004845688965665633,
|
|
"loss": 5.4007,
|
|
"mean_token_accuracy": 0.16408128738403321,
|
|
"num_tokens": 27652524.0,
|
|
"step": 14995
|
|
},
|
|
{
|
|
"entropy": 5.605330944061279,
|
|
"epoch": 1.2601974375131275,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00048455799557424814,
|
|
"loss": 5.2526,
|
|
"mean_token_accuracy": 0.18249338418245314,
|
|
"num_tokens": 27661306.0,
|
|
"step": 15000
|
|
},
|
|
{
|
|
"epoch": 1.2601974375131275,
|
|
"eval_entropy": 5.487832695583898,
|
|
"eval_loss": 5.448311805725098,
|
|
"eval_mean_token_accuracy": 0.17504042461099753,
|
|
"eval_num_tokens": 27661306.0,
|
|
"eval_runtime": 27.5042,
|
|
"eval_samples_per_second": 1358.558,
|
|
"eval_steps_per_second": 169.829,
|
|
"step": 15000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 119020,
|
|
"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": 4.0484285319168e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|