380cd5d987
Model: fpadovani/swe-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed3407 Source: Original Platform
12057 lines
329 KiB
JSON
12057 lines
329 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.5040957781978576,
|
|
"eval_steps": 3000,
|
|
"global_step": 6000,
|
|
"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
|
|
}
|
|
],
|
|
"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": 1.6177520553984e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|