0b04222315
Model: fpadovani/swe-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed3407 Source: Original Platform
24299 lines
665 KiB
JSON
24299 lines
665 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 9.942004971002486,
|
|
"eval_steps": 500,
|
|
"global_step": 12000,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.316415309906006,
|
|
"epoch": 0.004142502071251036,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.9577,
|
|
"mean_token_accuracy": 0.09107546955347061,
|
|
"num_tokens": 9149.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.29176926612854,
|
|
"epoch": 0.008285004142502071,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 6.815,
|
|
"mean_token_accuracy": 0.09366189837455749,
|
|
"num_tokens": 16800.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.258940315246582,
|
|
"epoch": 0.012427506213753107,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.949,
|
|
"mean_token_accuracy": 0.09261607527732849,
|
|
"num_tokens": 26617.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.274951076507568,
|
|
"epoch": 0.016570008285004142,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 6.8768,
|
|
"mean_token_accuracy": 0.09439559504389763,
|
|
"num_tokens": 35855.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.333089065551758,
|
|
"epoch": 0.020712510356255178,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.0807,
|
|
"mean_token_accuracy": 0.08799155950546264,
|
|
"num_tokens": 45644.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.298266220092773,
|
|
"epoch": 0.024855012427506214,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9578,
|
|
"mean_token_accuracy": 0.09257320761680603,
|
|
"num_tokens": 54641.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.2906664371490475,
|
|
"epoch": 0.02899751449875725,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.8371,
|
|
"mean_token_accuracy": 0.08952230289578438,
|
|
"num_tokens": 63924.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.365257406234742,
|
|
"epoch": 0.033140016570008285,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.9731,
|
|
"mean_token_accuracy": 0.09005696997046471,
|
|
"num_tokens": 73452.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.326370525360107,
|
|
"epoch": 0.037282518641259324,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.0211,
|
|
"mean_token_accuracy": 0.0873270682990551,
|
|
"num_tokens": 82731.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.339514112472534,
|
|
"epoch": 0.041425020712510356,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.8651,
|
|
"mean_token_accuracy": 0.08901808261871338,
|
|
"num_tokens": 92626.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.389622354507447,
|
|
"epoch": 0.045567522783761395,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.0312,
|
|
"mean_token_accuracy": 0.08305057361721993,
|
|
"num_tokens": 101380.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.367127227783203,
|
|
"epoch": 0.04971002485501243,
|
|
"grad_norm": 0.9140625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 6.9496,
|
|
"mean_token_accuracy": 0.09191007390618325,
|
|
"num_tokens": 109895.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.404217004776001,
|
|
"epoch": 0.053852526926263466,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 6.9489,
|
|
"mean_token_accuracy": 0.08632109612226486,
|
|
"num_tokens": 119203.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.383033037185669,
|
|
"epoch": 0.0579950289975145,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.8909,
|
|
"mean_token_accuracy": 0.0960758812725544,
|
|
"num_tokens": 127572.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.323318862915039,
|
|
"epoch": 0.06213753106876554,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.924,
|
|
"mean_token_accuracy": 0.08685562647879123,
|
|
"num_tokens": 137161.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.288953590393066,
|
|
"epoch": 0.06628003314001657,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 7.0298,
|
|
"mean_token_accuracy": 0.08434623554348945,
|
|
"num_tokens": 145991.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.325984477996826,
|
|
"epoch": 0.07042253521126761,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.937,
|
|
"mean_token_accuracy": 0.0885515496134758,
|
|
"num_tokens": 154927.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.31841459274292,
|
|
"epoch": 0.07456503728251865,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.8509,
|
|
"mean_token_accuracy": 0.09631360918283463,
|
|
"num_tokens": 163234.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.365633821487426,
|
|
"epoch": 0.07870753935376967,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.8134,
|
|
"mean_token_accuracy": 0.09503689482808113,
|
|
"num_tokens": 171554.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.308236169815063,
|
|
"epoch": 0.08285004142502071,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.9083,
|
|
"mean_token_accuracy": 0.09420166239142418,
|
|
"num_tokens": 180171.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.272618198394776,
|
|
"epoch": 0.08699254349627175,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 6.8556,
|
|
"mean_token_accuracy": 0.09322545379400253,
|
|
"num_tokens": 189216.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.345879077911377,
|
|
"epoch": 0.09113504556752279,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.0522,
|
|
"mean_token_accuracy": 0.08772843405604362,
|
|
"num_tokens": 200022.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.375020217895508,
|
|
"epoch": 0.09527754763877382,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.9495,
|
|
"mean_token_accuracy": 0.0907869316637516,
|
|
"num_tokens": 208686.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.387457752227784,
|
|
"epoch": 0.09942004971002485,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.9723,
|
|
"mean_token_accuracy": 0.09134301021695138,
|
|
"num_tokens": 218266.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.271829748153687,
|
|
"epoch": 0.1035625517812759,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.8557,
|
|
"mean_token_accuracy": 0.08564562872052192,
|
|
"num_tokens": 227658.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.235640192031861,
|
|
"epoch": 0.10770505385252693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 6.8059,
|
|
"mean_token_accuracy": 0.0986194871366024,
|
|
"num_tokens": 236301.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.342151260375976,
|
|
"epoch": 0.11184755592377796,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.9379,
|
|
"mean_token_accuracy": 0.08733796998858452,
|
|
"num_tokens": 246355.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.415835380554199,
|
|
"epoch": 0.115990057995029,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9199,
|
|
"mean_token_accuracy": 0.08878825083374978,
|
|
"num_tokens": 256023.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.297379016876221,
|
|
"epoch": 0.12013256006628004,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 7.0053,
|
|
"mean_token_accuracy": 0.08748594373464584,
|
|
"num_tokens": 266893.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.238939237594605,
|
|
"epoch": 0.12427506213753108,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.7696,
|
|
"mean_token_accuracy": 0.09012725874781609,
|
|
"num_tokens": 276075.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.302191066741943,
|
|
"epoch": 0.12841756420878211,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.8603,
|
|
"mean_token_accuracy": 0.08920295760035515,
|
|
"num_tokens": 285529.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.233504438400269,
|
|
"epoch": 0.13256006628003314,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.866,
|
|
"mean_token_accuracy": 0.09255343899130822,
|
|
"num_tokens": 294403.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.361068534851074,
|
|
"epoch": 0.13670256835128416,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.9542,
|
|
"mean_token_accuracy": 0.0920793354511261,
|
|
"num_tokens": 303507.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.357890844345093,
|
|
"epoch": 0.14084507042253522,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.864,
|
|
"mean_token_accuracy": 0.09164286777377129,
|
|
"num_tokens": 312393.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.18741021156311,
|
|
"epoch": 0.14498757249378624,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.8295,
|
|
"mean_token_accuracy": 0.09937396124005318,
|
|
"num_tokens": 321309.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.408359384536743,
|
|
"epoch": 0.1491300745650373,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.885,
|
|
"mean_token_accuracy": 0.09395725503563881,
|
|
"num_tokens": 330217.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.256880092620849,
|
|
"epoch": 0.15327257663628832,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.9273,
|
|
"mean_token_accuracy": 0.09338772147893906,
|
|
"num_tokens": 339587.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.283669328689575,
|
|
"epoch": 0.15741507870753935,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.8494,
|
|
"mean_token_accuracy": 0.09577088207006454,
|
|
"num_tokens": 349367.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.2921398162841795,
|
|
"epoch": 0.1615575807787904,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.7565,
|
|
"mean_token_accuracy": 0.09605895429849624,
|
|
"num_tokens": 358272.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.314898586273193,
|
|
"epoch": 0.16570008285004142,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.9815,
|
|
"mean_token_accuracy": 0.09187402427196503,
|
|
"num_tokens": 367709.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.341378116607666,
|
|
"epoch": 0.16984258492129245,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.8415,
|
|
"mean_token_accuracy": 0.09144494608044625,
|
|
"num_tokens": 376180.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.2672590732574465,
|
|
"epoch": 0.1739850869925435,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 6.9873,
|
|
"mean_token_accuracy": 0.08560611009597778,
|
|
"num_tokens": 385636.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.31936240196228,
|
|
"epoch": 0.17812758906379453,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.8665,
|
|
"mean_token_accuracy": 0.10073013603687286,
|
|
"num_tokens": 394486.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.240320158004761,
|
|
"epoch": 0.18227009113504558,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 6.8339,
|
|
"mean_token_accuracy": 0.09145828187465668,
|
|
"num_tokens": 403765.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.176674270629883,
|
|
"epoch": 0.1864125932062966,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.8192,
|
|
"mean_token_accuracy": 0.09741753935813904,
|
|
"num_tokens": 412988.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.243546390533448,
|
|
"epoch": 0.19055509527754763,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.7247,
|
|
"mean_token_accuracy": 0.09494704753160477,
|
|
"num_tokens": 422096.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.259120273590088,
|
|
"epoch": 0.19469759734879868,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.8913,
|
|
"mean_token_accuracy": 0.0842115230858326,
|
|
"num_tokens": 431333.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.322444343566895,
|
|
"epoch": 0.1988400994200497,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.9209,
|
|
"mean_token_accuracy": 0.09764085784554481,
|
|
"num_tokens": 440382.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.303359937667847,
|
|
"epoch": 0.20298260149130073,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.8237,
|
|
"mean_token_accuracy": 0.09803626388311386,
|
|
"num_tokens": 448469.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.2807892799377445,
|
|
"epoch": 0.2071251035625518,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.8631,
|
|
"mean_token_accuracy": 0.09314201548695564,
|
|
"num_tokens": 457356.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.395456218719483,
|
|
"epoch": 0.2112676056338028,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8936,
|
|
"mean_token_accuracy": 0.09395477920770645,
|
|
"num_tokens": 465928.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.177229928970337,
|
|
"epoch": 0.21541010770505387,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.7914,
|
|
"mean_token_accuracy": 0.09916061088442803,
|
|
"num_tokens": 475269.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.238220596313477,
|
|
"epoch": 0.2195526097763049,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.7807,
|
|
"mean_token_accuracy": 0.09297533929347992,
|
|
"num_tokens": 485450.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.214696550369263,
|
|
"epoch": 0.22369511184755592,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.8391,
|
|
"mean_token_accuracy": 0.10058524161577224,
|
|
"num_tokens": 494029.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.255264091491699,
|
|
"epoch": 0.22783761391880697,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.7793,
|
|
"mean_token_accuracy": 0.10096407309174538,
|
|
"num_tokens": 503253.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.156082010269165,
|
|
"epoch": 0.231980115990058,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.7768,
|
|
"mean_token_accuracy": 0.09033024087548255,
|
|
"num_tokens": 512857.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.303338527679443,
|
|
"epoch": 0.23612261806130902,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8719,
|
|
"mean_token_accuracy": 0.09036988765001297,
|
|
"num_tokens": 522319.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.218528747558594,
|
|
"epoch": 0.24026512013256007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8263,
|
|
"mean_token_accuracy": 0.09190768375992775,
|
|
"num_tokens": 531469.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.2514721870422365,
|
|
"epoch": 0.2444076222038111,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8537,
|
|
"mean_token_accuracy": 0.09450737237930298,
|
|
"num_tokens": 540470.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.243441724777222,
|
|
"epoch": 0.24855012427506215,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.8472,
|
|
"mean_token_accuracy": 0.0973442628979683,
|
|
"num_tokens": 550317.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.2743926525115965,
|
|
"epoch": 0.2526926263463132,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.8027,
|
|
"mean_token_accuracy": 0.09109159633517265,
|
|
"num_tokens": 559409.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.125630617141724,
|
|
"epoch": 0.25683512841756423,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.8497,
|
|
"mean_token_accuracy": 0.10476837977766991,
|
|
"num_tokens": 568726.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.3812638282775875,
|
|
"epoch": 0.2609776304888152,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8242,
|
|
"mean_token_accuracy": 0.0930200308561325,
|
|
"num_tokens": 577926.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.191781997680664,
|
|
"epoch": 0.2651201325600663,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8386,
|
|
"mean_token_accuracy": 0.09706645980477333,
|
|
"num_tokens": 586695.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.304094886779785,
|
|
"epoch": 0.26926263463131733,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8637,
|
|
"mean_token_accuracy": 0.09343150332570076,
|
|
"num_tokens": 596250.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.277995014190674,
|
|
"epoch": 0.27340513670256833,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.9091,
|
|
"mean_token_accuracy": 0.09041907489299775,
|
|
"num_tokens": 605761.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.221877241134644,
|
|
"epoch": 0.2775476387738194,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.8331,
|
|
"mean_token_accuracy": 0.09750878065824509,
|
|
"num_tokens": 614313.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.308935832977295,
|
|
"epoch": 0.28169014084507044,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.86,
|
|
"mean_token_accuracy": 0.09677010327577591,
|
|
"num_tokens": 624470.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.216413593292236,
|
|
"epoch": 0.28583264291632143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.7866,
|
|
"mean_token_accuracy": 0.09221929684281349,
|
|
"num_tokens": 633458.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.228837203979492,
|
|
"epoch": 0.2899751449875725,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.7796,
|
|
"mean_token_accuracy": 0.095080154389143,
|
|
"num_tokens": 643251.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.234794759750367,
|
|
"epoch": 0.29411764705882354,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.8515,
|
|
"mean_token_accuracy": 0.09346813485026359,
|
|
"num_tokens": 652005.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.190905666351318,
|
|
"epoch": 0.2982601491300746,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.7442,
|
|
"mean_token_accuracy": 0.0977424830198288,
|
|
"num_tokens": 661003.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.124666595458985,
|
|
"epoch": 0.3024026512013256,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.7269,
|
|
"mean_token_accuracy": 0.09757486581802369,
|
|
"num_tokens": 670221.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.42992148399353,
|
|
"epoch": 0.30654515327257664,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 7.0088,
|
|
"mean_token_accuracy": 0.08780332058668136,
|
|
"num_tokens": 680756.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.103591108322144,
|
|
"epoch": 0.3106876553438277,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.7083,
|
|
"mean_token_accuracy": 0.09910113140940666,
|
|
"num_tokens": 689641.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.170710134506225,
|
|
"epoch": 0.3148301574150787,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.6639,
|
|
"mean_token_accuracy": 0.09918258264660836,
|
|
"num_tokens": 698209.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.087573099136352,
|
|
"epoch": 0.31897265948632975,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.6625,
|
|
"mean_token_accuracy": 0.10349222794175147,
|
|
"num_tokens": 706712.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.24962100982666,
|
|
"epoch": 0.3231151615575808,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8702,
|
|
"mean_token_accuracy": 0.09640411287546158,
|
|
"num_tokens": 716087.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.140476322174072,
|
|
"epoch": 0.3272576636288318,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.7452,
|
|
"mean_token_accuracy": 0.09067876264452934,
|
|
"num_tokens": 725913.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 7.217365264892578,
|
|
"epoch": 0.33140016570008285,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.8095,
|
|
"mean_token_accuracy": 0.10141430869698524,
|
|
"num_tokens": 735020.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.1846894264221195,
|
|
"epoch": 0.3355426677713339,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7136,
|
|
"mean_token_accuracy": 0.09213051795959473,
|
|
"num_tokens": 744299.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.125712251663208,
|
|
"epoch": 0.3396851698425849,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.6868,
|
|
"mean_token_accuracy": 0.09798395857214928,
|
|
"num_tokens": 753231.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.11104679107666,
|
|
"epoch": 0.34382767191383595,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.7589,
|
|
"mean_token_accuracy": 0.09906982332468033,
|
|
"num_tokens": 763043.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.237280750274659,
|
|
"epoch": 0.347970173985087,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7865,
|
|
"mean_token_accuracy": 0.1009935662150383,
|
|
"num_tokens": 771977.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.055163717269897,
|
|
"epoch": 0.352112676056338,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7041,
|
|
"mean_token_accuracy": 0.10424543470144272,
|
|
"num_tokens": 780285.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.228680515289307,
|
|
"epoch": 0.35625517812758906,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.7506,
|
|
"mean_token_accuracy": 0.09805167838931084,
|
|
"num_tokens": 789980.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.116986274719238,
|
|
"epoch": 0.3603976801988401,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7287,
|
|
"mean_token_accuracy": 0.10292106568813324,
|
|
"num_tokens": 798700.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 7.054797267913818,
|
|
"epoch": 0.36454018227009116,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.7877,
|
|
"mean_token_accuracy": 0.09516645893454552,
|
|
"num_tokens": 808758.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.259660816192627,
|
|
"epoch": 0.36868268434134216,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7511,
|
|
"mean_token_accuracy": 0.10131709128618241,
|
|
"num_tokens": 817692.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 7.174760341644287,
|
|
"epoch": 0.3728251864125932,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.8063,
|
|
"mean_token_accuracy": 0.10130528211593628,
|
|
"num_tokens": 827052.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.13604998588562,
|
|
"epoch": 0.37696768848384427,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.7821,
|
|
"mean_token_accuracy": 0.10629323869943619,
|
|
"num_tokens": 836442.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 7.191133499145508,
|
|
"epoch": 0.38111019055509526,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6717,
|
|
"mean_token_accuracy": 0.10159996896982193,
|
|
"num_tokens": 846441.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 7.073972415924072,
|
|
"epoch": 0.3852526926263463,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7128,
|
|
"mean_token_accuracy": 0.10559298172593116,
|
|
"num_tokens": 856108.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.137764835357666,
|
|
"epoch": 0.38939519469759737,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.665,
|
|
"mean_token_accuracy": 0.09864805340766906,
|
|
"num_tokens": 865788.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 7.0983226776123045,
|
|
"epoch": 0.39353769676884837,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.7292,
|
|
"mean_token_accuracy": 0.09705496057868004,
|
|
"num_tokens": 874833.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 7.023185586929321,
|
|
"epoch": 0.3976801988400994,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6816,
|
|
"mean_token_accuracy": 0.10277220755815505,
|
|
"num_tokens": 883685.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 7.133955621719361,
|
|
"epoch": 0.40182270091135047,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.67,
|
|
"mean_token_accuracy": 0.09730359986424446,
|
|
"num_tokens": 893908.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 7.086344528198242,
|
|
"epoch": 0.40596520298260147,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.7808,
|
|
"mean_token_accuracy": 0.09705358296632767,
|
|
"num_tokens": 903081.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 7.025259399414063,
|
|
"epoch": 0.4101077050538525,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.10383275151252747,
|
|
"num_tokens": 912515.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 7.203283357620239,
|
|
"epoch": 0.4142502071251036,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.6473,
|
|
"mean_token_accuracy": 0.10783689767122269,
|
|
"num_tokens": 921056.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.4142502071251036,
|
|
"eval_entropy": 6.835995750386577,
|
|
"eval_loss": 6.763827800750732,
|
|
"eval_mean_token_accuracy": 0.10202416494838211,
|
|
"eval_num_tokens": 921056.0,
|
|
"eval_runtime": 2.1276,
|
|
"eval_samples_per_second": 1761.098,
|
|
"eval_steps_per_second": 220.431,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.907085657119751,
|
|
"epoch": 0.4183927091963546,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.611,
|
|
"mean_token_accuracy": 0.10536315441131591,
|
|
"num_tokens": 931112.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 7.0663305759429935,
|
|
"epoch": 0.4225352112676056,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.7483,
|
|
"mean_token_accuracy": 0.10146113634109497,
|
|
"num_tokens": 941120.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 7.127016544342041,
|
|
"epoch": 0.4266777133388567,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6883,
|
|
"mean_token_accuracy": 0.09923007488250732,
|
|
"num_tokens": 950041.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 7.057574129104614,
|
|
"epoch": 0.43082021541010773,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6703,
|
|
"mean_token_accuracy": 0.10598697513341904,
|
|
"num_tokens": 958608.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 7.187314367294311,
|
|
"epoch": 0.43496271748135873,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.7852,
|
|
"mean_token_accuracy": 0.09927874878048897,
|
|
"num_tokens": 966901.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.984877586364746,
|
|
"epoch": 0.4391052195526098,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.623,
|
|
"mean_token_accuracy": 0.10634999126195907,
|
|
"num_tokens": 976198.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 7.135362672805786,
|
|
"epoch": 0.44324772162386084,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.6937,
|
|
"mean_token_accuracy": 0.09986837655305862,
|
|
"num_tokens": 985248.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.943363761901855,
|
|
"epoch": 0.44739022369511183,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.6052,
|
|
"mean_token_accuracy": 0.1056825801730156,
|
|
"num_tokens": 993289.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 7.099994421005249,
|
|
"epoch": 0.4515327257663629,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.6611,
|
|
"mean_token_accuracy": 0.10454976856708527,
|
|
"num_tokens": 1001784.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 7.149687051773071,
|
|
"epoch": 0.45567522783761394,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6452,
|
|
"mean_token_accuracy": 0.11003177165985108,
|
|
"num_tokens": 1010445.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.970145893096924,
|
|
"epoch": 0.45981772990886494,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6866,
|
|
"mean_token_accuracy": 0.10296825990080834,
|
|
"num_tokens": 1019084.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 7.00351128578186,
|
|
"epoch": 0.463960231980116,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.6045,
|
|
"mean_token_accuracy": 0.10343219712376595,
|
|
"num_tokens": 1027263.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 7.118851375579834,
|
|
"epoch": 0.46810273405136704,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7038,
|
|
"mean_token_accuracy": 0.10047925561666489,
|
|
"num_tokens": 1036275.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 7.024382400512695,
|
|
"epoch": 0.47224523612261804,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7695,
|
|
"mean_token_accuracy": 0.09930935353040696,
|
|
"num_tokens": 1045208.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 7.1062685489654545,
|
|
"epoch": 0.4763877381938691,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.692,
|
|
"mean_token_accuracy": 0.10427912548184395,
|
|
"num_tokens": 1054703.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.880273103713989,
|
|
"epoch": 0.48053024026512015,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.5487,
|
|
"mean_token_accuracy": 0.1035312443971634,
|
|
"num_tokens": 1063652.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.948973989486694,
|
|
"epoch": 0.48467274233637114,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.6483,
|
|
"mean_token_accuracy": 0.10299907624721527,
|
|
"num_tokens": 1072070.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 7.205907678604126,
|
|
"epoch": 0.4888152444076222,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6786,
|
|
"mean_token_accuracy": 0.10379905477166176,
|
|
"num_tokens": 1079992.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.94438328742981,
|
|
"epoch": 0.49295774647887325,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6762,
|
|
"mean_token_accuracy": 0.10331593230366706,
|
|
"num_tokens": 1088862.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.976015233993531,
|
|
"epoch": 0.4971002485501243,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.4811,
|
|
"mean_token_accuracy": 0.11253077536821365,
|
|
"num_tokens": 1097614.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.891912937164307,
|
|
"epoch": 0.5012427506213754,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6811,
|
|
"mean_token_accuracy": 0.1095806010067463,
|
|
"num_tokens": 1107347.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 7.113644981384278,
|
|
"epoch": 0.5053852526926264,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.7093,
|
|
"mean_token_accuracy": 0.10049239173531532,
|
|
"num_tokens": 1116707.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 7.003044986724854,
|
|
"epoch": 0.5095277547638773,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7031,
|
|
"mean_token_accuracy": 0.1056403562426567,
|
|
"num_tokens": 1126356.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.974148845672607,
|
|
"epoch": 0.5136702568351285,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6467,
|
|
"mean_token_accuracy": 0.10070049464702606,
|
|
"num_tokens": 1136281.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.98663740158081,
|
|
"epoch": 0.5178127589063795,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.6011,
|
|
"mean_token_accuracy": 0.10273146480321885,
|
|
"num_tokens": 1145466.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.933039379119873,
|
|
"epoch": 0.5219552609776305,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.6061,
|
|
"mean_token_accuracy": 0.10639488324522972,
|
|
"num_tokens": 1154225.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 7.023647594451904,
|
|
"epoch": 0.5260977630488816,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.6404,
|
|
"mean_token_accuracy": 0.10065171793103218,
|
|
"num_tokens": 1163872.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.9506641864776615,
|
|
"epoch": 0.5302402651201326,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5717,
|
|
"mean_token_accuracy": 0.11115986928343773,
|
|
"num_tokens": 1172695.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.853932952880859,
|
|
"epoch": 0.5343827671913836,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.4515,
|
|
"mean_token_accuracy": 0.1125042974948883,
|
|
"num_tokens": 1181291.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 7.001178407669068,
|
|
"epoch": 0.5385252692626347,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.10361743718385696,
|
|
"num_tokens": 1189927.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.9009294509887695,
|
|
"epoch": 0.5426677713338857,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.5567,
|
|
"mean_token_accuracy": 0.11111297979950904,
|
|
"num_tokens": 1197913.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.887521409988404,
|
|
"epoch": 0.5468102734051367,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.4824,
|
|
"mean_token_accuracy": 0.11478215083479881,
|
|
"num_tokens": 1207032.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.917655086517334,
|
|
"epoch": 0.5509527754763878,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5899,
|
|
"mean_token_accuracy": 0.10642103552818298,
|
|
"num_tokens": 1215710.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.945044994354248,
|
|
"epoch": 0.5550952775476388,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.5707,
|
|
"mean_token_accuracy": 0.10297949239611626,
|
|
"num_tokens": 1225619.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.85495548248291,
|
|
"epoch": 0.5592377796188898,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5078,
|
|
"mean_token_accuracy": 0.10624194070696831,
|
|
"num_tokens": 1235000.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.8498025894165036,
|
|
"epoch": 0.5633802816901409,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.5083,
|
|
"mean_token_accuracy": 0.10908133909106255,
|
|
"num_tokens": 1243594.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.964477157592773,
|
|
"epoch": 0.5675227837613919,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.7039,
|
|
"mean_token_accuracy": 0.10716133862733841,
|
|
"num_tokens": 1252279.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 7.074165916442871,
|
|
"epoch": 0.5716652858326429,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6102,
|
|
"mean_token_accuracy": 0.10797887593507767,
|
|
"num_tokens": 1261314.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.786513042449951,
|
|
"epoch": 0.575807787903894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.489,
|
|
"mean_token_accuracy": 0.11091019809246064,
|
|
"num_tokens": 1270854.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.820779418945312,
|
|
"epoch": 0.579950289975145,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.459,
|
|
"mean_token_accuracy": 0.11137820258736611,
|
|
"num_tokens": 1279183.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.864804220199585,
|
|
"epoch": 0.584092792046396,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.5622,
|
|
"mean_token_accuracy": 0.10689144134521485,
|
|
"num_tokens": 1288347.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.890985202789307,
|
|
"epoch": 0.5882352941176471,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5705,
|
|
"mean_token_accuracy": 0.10670721456408501,
|
|
"num_tokens": 1297449.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.991053485870362,
|
|
"epoch": 0.5923777961888981,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5221,
|
|
"mean_token_accuracy": 0.10960500165820122,
|
|
"num_tokens": 1306232.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.839966917037964,
|
|
"epoch": 0.5965202982601492,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.5397,
|
|
"mean_token_accuracy": 0.11476544663310051,
|
|
"num_tokens": 1315073.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.873430061340332,
|
|
"epoch": 0.6006628003314002,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.5763,
|
|
"mean_token_accuracy": 0.10628646165132523,
|
|
"num_tokens": 1324629.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.988832902908325,
|
|
"epoch": 0.6048053024026512,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.6889,
|
|
"mean_token_accuracy": 0.10445819571614265,
|
|
"num_tokens": 1334152.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 7.004844760894775,
|
|
"epoch": 0.6089478044739023,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.649,
|
|
"mean_token_accuracy": 0.10557386428117752,
|
|
"num_tokens": 1343063.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.872599458694458,
|
|
"epoch": 0.6130903065451533,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5733,
|
|
"mean_token_accuracy": 0.10616720467805862,
|
|
"num_tokens": 1352632.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.796925640106201,
|
|
"epoch": 0.6172328086164043,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5249,
|
|
"mean_token_accuracy": 0.10955940410494805,
|
|
"num_tokens": 1361103.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.843691015243531,
|
|
"epoch": 0.6213753106876554,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5141,
|
|
"mean_token_accuracy": 0.11272492855787278,
|
|
"num_tokens": 1370658.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.910959482192993,
|
|
"epoch": 0.6255178127589064,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5224,
|
|
"mean_token_accuracy": 0.1089279018342495,
|
|
"num_tokens": 1379817.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.854007911682129,
|
|
"epoch": 0.6296603148301574,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4741,
|
|
"mean_token_accuracy": 0.11225551590323449,
|
|
"num_tokens": 1389329.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.684650230407715,
|
|
"epoch": 0.6338028169014085,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.5244,
|
|
"mean_token_accuracy": 0.1060152791440487,
|
|
"num_tokens": 1399279.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.8729455947875975,
|
|
"epoch": 0.6379453189726595,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.4704,
|
|
"mean_token_accuracy": 0.11294344514608383,
|
|
"num_tokens": 1408765.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.890125322341919,
|
|
"epoch": 0.6420878210439105,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.6028,
|
|
"mean_token_accuracy": 0.1117846891283989,
|
|
"num_tokens": 1418615.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.825809049606323,
|
|
"epoch": 0.6462303231151616,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.5069,
|
|
"mean_token_accuracy": 0.10702720955014229,
|
|
"num_tokens": 1427359.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.951959133148193,
|
|
"epoch": 0.6503728251864126,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.6603,
|
|
"mean_token_accuracy": 0.10913564860820771,
|
|
"num_tokens": 1435516.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.917226839065552,
|
|
"epoch": 0.6545153272576636,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.6098,
|
|
"mean_token_accuracy": 0.10673258900642395,
|
|
"num_tokens": 1444438.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.90554518699646,
|
|
"epoch": 0.6586578293289147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.5247,
|
|
"mean_token_accuracy": 0.10866252556443215,
|
|
"num_tokens": 1453740.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.866510057449341,
|
|
"epoch": 0.6628003314001657,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5261,
|
|
"mean_token_accuracy": 0.11231514811515808,
|
|
"num_tokens": 1462083.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.730630588531494,
|
|
"epoch": 0.6669428334714167,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.4459,
|
|
"mean_token_accuracy": 0.11757130473852158,
|
|
"num_tokens": 1471459.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.8137424945831295,
|
|
"epoch": 0.6710853355426678,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4358,
|
|
"mean_token_accuracy": 0.11511573269963264,
|
|
"num_tokens": 1480516.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.697441339492798,
|
|
"epoch": 0.6752278376139188,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.3422,
|
|
"mean_token_accuracy": 0.1162965439260006,
|
|
"num_tokens": 1489268.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.893553256988525,
|
|
"epoch": 0.6793703396851698,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.5562,
|
|
"mean_token_accuracy": 0.10877497121691704,
|
|
"num_tokens": 1498819.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.8146172046661375,
|
|
"epoch": 0.6835128417564209,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5384,
|
|
"mean_token_accuracy": 0.1133031778037548,
|
|
"num_tokens": 1507852.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.823567295074463,
|
|
"epoch": 0.6876553438276719,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.5635,
|
|
"mean_token_accuracy": 0.1100037857890129,
|
|
"num_tokens": 1517538.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.773430204391479,
|
|
"epoch": 0.6917978458989229,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4425,
|
|
"mean_token_accuracy": 0.11734201833605766,
|
|
"num_tokens": 1525389.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.780531215667724,
|
|
"epoch": 0.695940347970174,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.4279,
|
|
"mean_token_accuracy": 0.1151418298482895,
|
|
"num_tokens": 1534117.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.773794269561767,
|
|
"epoch": 0.700082850041425,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.4497,
|
|
"mean_token_accuracy": 0.11154624596238136,
|
|
"num_tokens": 1542610.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.658645105361939,
|
|
"epoch": 0.704225352112676,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.433,
|
|
"mean_token_accuracy": 0.1151619479060173,
|
|
"num_tokens": 1551771.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.913496255874634,
|
|
"epoch": 0.7083678541839271,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.6156,
|
|
"mean_token_accuracy": 0.10468344464898109,
|
|
"num_tokens": 1560231.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.773072385787964,
|
|
"epoch": 0.7125103562551781,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.5598,
|
|
"mean_token_accuracy": 0.10812477022409439,
|
|
"num_tokens": 1569578.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.792055749893189,
|
|
"epoch": 0.7166528583264291,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4507,
|
|
"mean_token_accuracy": 0.11864269822835923,
|
|
"num_tokens": 1579308.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.788659477233887,
|
|
"epoch": 0.7207953603976802,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.6271,
|
|
"mean_token_accuracy": 0.10858385637402534,
|
|
"num_tokens": 1589506.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.7048583984375,
|
|
"epoch": 0.7249378624689312,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.4141,
|
|
"mean_token_accuracy": 0.11191320866346359,
|
|
"num_tokens": 1598127.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.74589695930481,
|
|
"epoch": 0.7290803645401823,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.4341,
|
|
"mean_token_accuracy": 0.1158210128545761,
|
|
"num_tokens": 1608073.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.75485463142395,
|
|
"epoch": 0.7332228666114333,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4678,
|
|
"mean_token_accuracy": 0.11686542183160782,
|
|
"num_tokens": 1616272.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.78275499343872,
|
|
"epoch": 0.7373653686826843,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.4752,
|
|
"mean_token_accuracy": 0.11307700201869011,
|
|
"num_tokens": 1625577.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.852141284942627,
|
|
"epoch": 0.7415078707539354,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.5666,
|
|
"mean_token_accuracy": 0.10551101639866829,
|
|
"num_tokens": 1634902.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.698729467391968,
|
|
"epoch": 0.7456503728251864,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.4872,
|
|
"mean_token_accuracy": 0.11352990567684174,
|
|
"num_tokens": 1644131.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.733800840377808,
|
|
"epoch": 0.7497928748964374,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.3909,
|
|
"mean_token_accuracy": 0.12015661895275116,
|
|
"num_tokens": 1652272.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.715107011795044,
|
|
"epoch": 0.7539353769676885,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4837,
|
|
"mean_token_accuracy": 0.11517259702086449,
|
|
"num_tokens": 1660962.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.6873085498809814,
|
|
"epoch": 0.7580778790389395,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.419,
|
|
"mean_token_accuracy": 0.11443299949169158,
|
|
"num_tokens": 1670570.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.761066484451294,
|
|
"epoch": 0.7622203811101905,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4911,
|
|
"mean_token_accuracy": 0.11005624011158943,
|
|
"num_tokens": 1679674.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.826864004135132,
|
|
"epoch": 0.7663628831814416,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.4624,
|
|
"mean_token_accuracy": 0.11269745901226998,
|
|
"num_tokens": 1688849.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.581996488571167,
|
|
"epoch": 0.7705053852526926,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.3407,
|
|
"mean_token_accuracy": 0.11457516700029373,
|
|
"num_tokens": 1698565.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.744958591461182,
|
|
"epoch": 0.7746478873239436,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4315,
|
|
"mean_token_accuracy": 0.12229297310113907,
|
|
"num_tokens": 1708009.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.778655099868774,
|
|
"epoch": 0.7787903893951947,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4339,
|
|
"mean_token_accuracy": 0.1131053164601326,
|
|
"num_tokens": 1716497.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.6028002262115475,
|
|
"epoch": 0.7829328914664457,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4305,
|
|
"mean_token_accuracy": 0.11531242653727532,
|
|
"num_tokens": 1725609.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.682197093963623,
|
|
"epoch": 0.7870753935376967,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.353,
|
|
"mean_token_accuracy": 0.12001026049256325,
|
|
"num_tokens": 1734165.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.697330379486084,
|
|
"epoch": 0.7912178956089478,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4756,
|
|
"mean_token_accuracy": 0.10846871361136437,
|
|
"num_tokens": 1744856.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.672932958602905,
|
|
"epoch": 0.7953603976801988,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.4727,
|
|
"mean_token_accuracy": 0.10662268623709678,
|
|
"num_tokens": 1753386.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.7072113990783695,
|
|
"epoch": 0.7995028997514498,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.3358,
|
|
"mean_token_accuracy": 0.11681910082697869,
|
|
"num_tokens": 1762521.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.579640007019043,
|
|
"epoch": 0.8036454018227009,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3898,
|
|
"mean_token_accuracy": 0.11789416447281838,
|
|
"num_tokens": 1772403.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.674222660064697,
|
|
"epoch": 0.8077879038939519,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3007,
|
|
"mean_token_accuracy": 0.11631953716278076,
|
|
"num_tokens": 1780924.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.698087358474732,
|
|
"epoch": 0.8119304059652029,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.4432,
|
|
"mean_token_accuracy": 0.11354917660355568,
|
|
"num_tokens": 1789992.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.653201007843018,
|
|
"epoch": 0.816072908036454,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.11834764555096626,
|
|
"num_tokens": 1799513.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.569394779205322,
|
|
"epoch": 0.820215410107705,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.261,
|
|
"mean_token_accuracy": 0.11697232872247695,
|
|
"num_tokens": 1807393.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.676162242889404,
|
|
"epoch": 0.824357912178956,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.5097,
|
|
"mean_token_accuracy": 0.10958585515618324,
|
|
"num_tokens": 1817284.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.682469367980957,
|
|
"epoch": 0.8285004142502072,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2843,
|
|
"mean_token_accuracy": 0.11956144273281097,
|
|
"num_tokens": 1825591.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.8285004142502072,
|
|
"eval_entropy": 6.44553795653874,
|
|
"eval_loss": 6.471545696258545,
|
|
"eval_mean_token_accuracy": 0.11671354705845115,
|
|
"eval_num_tokens": 1825591.0,
|
|
"eval_runtime": 2.123,
|
|
"eval_samples_per_second": 1764.978,
|
|
"eval_steps_per_second": 220.917,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.6662139892578125,
|
|
"epoch": 0.8326429163214581,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0004999998547681232,
|
|
"loss": 6.4046,
|
|
"mean_token_accuracy": 0.12007165029644966,
|
|
"num_tokens": 1834655.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.467186403274536,
|
|
"epoch": 0.8367854183927091,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999992647639447,
|
|
"loss": 6.2657,
|
|
"mean_token_accuracy": 0.12069680243730545,
|
|
"num_tokens": 1844187.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.612904119491577,
|
|
"epoch": 0.8409279204639603,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999982209116618,
|
|
"loss": 6.3449,
|
|
"mean_token_accuracy": 0.11403246521949768,
|
|
"num_tokens": 1852768.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.624643278121948,
|
|
"epoch": 0.8450704225352113,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004999967232133796,
|
|
"loss": 6.393,
|
|
"mean_token_accuracy": 0.12195011600852013,
|
|
"num_tokens": 1862095.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.616990756988526,
|
|
"epoch": 0.8492129246064622,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004999947716721196,
|
|
"loss": 6.422,
|
|
"mean_token_accuracy": 0.11276146695017815,
|
|
"num_tokens": 1871239.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.637329816818237,
|
|
"epoch": 0.8533554266777134,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999923662918179,
|
|
"loss": 6.4264,
|
|
"mean_token_accuracy": 0.11726627275347709,
|
|
"num_tokens": 1880065.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.669142055511474,
|
|
"epoch": 0.8574979287489644,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999895070773266,
|
|
"loss": 6.4692,
|
|
"mean_token_accuracy": 0.11147499307990075,
|
|
"num_tokens": 1889065.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.697521781921386,
|
|
"epoch": 0.8616404308202155,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999861940344129,
|
|
"loss": 6.4571,
|
|
"mean_token_accuracy": 0.11582566872239113,
|
|
"num_tokens": 1898238.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.651687860488892,
|
|
"epoch": 0.8657829328914665,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004999824271697597,
|
|
"loss": 6.3975,
|
|
"mean_token_accuracy": 0.1222484327852726,
|
|
"num_tokens": 1906780.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.710152673721313,
|
|
"epoch": 0.8699254349627175,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499978206490965,
|
|
"loss": 6.4905,
|
|
"mean_token_accuracy": 0.11242052838206291,
|
|
"num_tokens": 1916183.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.546902227401733,
|
|
"epoch": 0.8740679370339686,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999735320065427,
|
|
"loss": 6.3458,
|
|
"mean_token_accuracy": 0.1232548326253891,
|
|
"num_tokens": 1925382.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.567516803741455,
|
|
"epoch": 0.8782104391052196,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999684037259216,
|
|
"loss": 6.2036,
|
|
"mean_token_accuracy": 0.12797800078988075,
|
|
"num_tokens": 1933639.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.524128103256226,
|
|
"epoch": 0.8823529411764706,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0004999628216594456,
|
|
"loss": 6.4724,
|
|
"mean_token_accuracy": 0.11707659810781479,
|
|
"num_tokens": 1943044.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.655896615982056,
|
|
"epoch": 0.8864954432477217,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000499956785818375,
|
|
"loss": 6.3217,
|
|
"mean_token_accuracy": 0.11736537888646126,
|
|
"num_tokens": 1951777.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.527218246459961,
|
|
"epoch": 0.8906379453189727,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004999502962148843,
|
|
"loss": 6.3884,
|
|
"mean_token_accuracy": 0.11941609233617782,
|
|
"num_tokens": 1961356.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.738359689712524,
|
|
"epoch": 0.8947804473902237,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000499943352862064,
|
|
"loss": 6.4322,
|
|
"mean_token_accuracy": 0.11732709258794785,
|
|
"num_tokens": 1970341.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.593241596221924,
|
|
"epoch": 0.8989229494614748,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004999359557739194,
|
|
"loss": 6.2907,
|
|
"mean_token_accuracy": 0.11967678442597389,
|
|
"num_tokens": 1978576.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.591588544845581,
|
|
"epoch": 0.9030654515327258,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004999281049653713,
|
|
"loss": 6.3461,
|
|
"mean_token_accuracy": 0.11938407868146897,
|
|
"num_tokens": 1987229.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.569654750823974,
|
|
"epoch": 0.9072079536039768,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999198004522557,
|
|
"loss": 6.26,
|
|
"mean_token_accuracy": 0.12861526757478714,
|
|
"num_tokens": 1996473.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.511166715621949,
|
|
"epoch": 0.9113504556752279,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004999110422513237,
|
|
"loss": 6.2915,
|
|
"mean_token_accuracy": 0.12253913059830665,
|
|
"num_tokens": 2005551.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.5116040229797365,
|
|
"epoch": 0.9154929577464789,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004999018303802414,
|
|
"loss": 6.3972,
|
|
"mean_token_accuracy": 0.12215510085225105,
|
|
"num_tokens": 2015012.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.654548215866089,
|
|
"epoch": 0.9196354598177299,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004998921648575904,
|
|
"loss": 6.3983,
|
|
"mean_token_accuracy": 0.11905976086854934,
|
|
"num_tokens": 2024435.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.544571256637573,
|
|
"epoch": 0.923777961888981,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004998820457028669,
|
|
"loss": 6.3065,
|
|
"mean_token_accuracy": 0.12046469524502754,
|
|
"num_tokens": 2033991.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.558928680419922,
|
|
"epoch": 0.927920463960232,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998714729364824,
|
|
"loss": 6.3193,
|
|
"mean_token_accuracy": 0.1266247771680355,
|
|
"num_tokens": 2043117.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.59407753944397,
|
|
"epoch": 0.932062966031483,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004998604465797634,
|
|
"loss": 6.3396,
|
|
"mean_token_accuracy": 0.12249568551778793,
|
|
"num_tokens": 2052304.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.464563369750977,
|
|
"epoch": 0.9362054681027341,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004998489666549512,
|
|
"loss": 6.2867,
|
|
"mean_token_accuracy": 0.12436222359538078,
|
|
"num_tokens": 2061217.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.460366916656494,
|
|
"epoch": 0.9403479701739851,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998370331852021,
|
|
"loss": 6.2685,
|
|
"mean_token_accuracy": 0.1200811967253685,
|
|
"num_tokens": 2070796.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.664331769943237,
|
|
"epoch": 0.9444904722452361,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004998246461945872,
|
|
"loss": 6.3871,
|
|
"mean_token_accuracy": 0.12616615518927574,
|
|
"num_tokens": 2080202.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.546797418594361,
|
|
"epoch": 0.9486329743164872,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004998118057080923,
|
|
"loss": 6.3135,
|
|
"mean_token_accuracy": 0.121537134796381,
|
|
"num_tokens": 2089788.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.597958517074585,
|
|
"epoch": 0.9527754763877382,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997985117516183,
|
|
"loss": 6.3355,
|
|
"mean_token_accuracy": 0.11748650595545769,
|
|
"num_tokens": 2098727.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.42893352508545,
|
|
"epoch": 0.9569179784589892,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004997847643519803,
|
|
"loss": 6.2309,
|
|
"mean_token_accuracy": 0.11966113150119781,
|
|
"num_tokens": 2107645.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.408219528198242,
|
|
"epoch": 0.9610604805302403,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004997705635369085,
|
|
"loss": 6.2108,
|
|
"mean_token_accuracy": 0.12341454103589058,
|
|
"num_tokens": 2116613.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.519371175765992,
|
|
"epoch": 0.9652029826014913,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004997559093350474,
|
|
"loss": 6.2133,
|
|
"mean_token_accuracy": 0.12186720743775367,
|
|
"num_tokens": 2125585.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.568776416778564,
|
|
"epoch": 0.9693454846727423,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004997408017759562,
|
|
"loss": 6.3294,
|
|
"mean_token_accuracy": 0.12122908607125282,
|
|
"num_tokens": 2134795.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.521303701400757,
|
|
"epoch": 0.9734879867439934,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004997252408901084,
|
|
"loss": 6.3297,
|
|
"mean_token_accuracy": 0.11886916756629944,
|
|
"num_tokens": 2143699.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.602518701553345,
|
|
"epoch": 0.9776304888152444,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004997092267088922,
|
|
"loss": 6.2718,
|
|
"mean_token_accuracy": 0.12022883147001266,
|
|
"num_tokens": 2152187.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.49890923500061,
|
|
"epoch": 0.9817729908864954,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004996927592646097,
|
|
"loss": 6.3403,
|
|
"mean_token_accuracy": 0.12049522399902343,
|
|
"num_tokens": 2160941.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.568722772598266,
|
|
"epoch": 0.9859154929577465,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004996758385904776,
|
|
"loss": 6.3268,
|
|
"mean_token_accuracy": 0.12370333299040795,
|
|
"num_tokens": 2168946.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.424992275238037,
|
|
"epoch": 0.9900579950289975,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004996584647206269,
|
|
"loss": 6.234,
|
|
"mean_token_accuracy": 0.12237700819969177,
|
|
"num_tokens": 2177662.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.488782596588135,
|
|
"epoch": 0.9942004971002486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004996406376901026,
|
|
"loss": 6.3339,
|
|
"mean_token_accuracy": 0.1301935538649559,
|
|
"num_tokens": 2187461.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.459936046600342,
|
|
"epoch": 0.9983429991714996,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004996223575348635,
|
|
"loss": 6.2143,
|
|
"mean_token_accuracy": 0.1307205244898796,
|
|
"num_tokens": 2196878.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.549283266067505,
|
|
"epoch": 1.0024855012427507,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004996036242917828,
|
|
"loss": 6.2226,
|
|
"mean_token_accuracy": 0.11891174912452698,
|
|
"num_tokens": 2206178.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.446871328353882,
|
|
"epoch": 1.0066280033140016,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004995844379986476,
|
|
"loss": 6.0874,
|
|
"mean_token_accuracy": 0.12653569504618645,
|
|
"num_tokens": 2215330.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.492379474639892,
|
|
"epoch": 1.0107705053852527,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004995647986941587,
|
|
"loss": 6.0875,
|
|
"mean_token_accuracy": 0.12935211285948753,
|
|
"num_tokens": 2224146.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.480843734741211,
|
|
"epoch": 1.0149130074565038,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004995447064179308,
|
|
"loss": 6.0677,
|
|
"mean_token_accuracy": 0.13676073402166367,
|
|
"num_tokens": 2233646.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.290753316879273,
|
|
"epoch": 1.0190555095277547,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000499524161210492,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.13070207014679908,
|
|
"num_tokens": 2243663.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.452328014373779,
|
|
"epoch": 1.0231980115990058,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004995031631132844,
|
|
"loss": 6.1289,
|
|
"mean_token_accuracy": 0.13538116291165353,
|
|
"num_tokens": 2252564.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.454355192184448,
|
|
"epoch": 1.027340513670257,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004994817121686633,
|
|
"loss": 6.1202,
|
|
"mean_token_accuracy": 0.12975577935576438,
|
|
"num_tokens": 2262504.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.441025686264038,
|
|
"epoch": 1.0314830157415078,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004994598084198979,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.1423887699842453,
|
|
"num_tokens": 2270553.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.357677888870239,
|
|
"epoch": 1.035625517812759,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0004994374519111701,
|
|
"loss": 6.0331,
|
|
"mean_token_accuracy": 0.13042610734701157,
|
|
"num_tokens": 2279319.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.440127897262573,
|
|
"epoch": 1.03976801988401,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004994146426875757,
|
|
"loss": 6.1553,
|
|
"mean_token_accuracy": 0.1311718061566353,
|
|
"num_tokens": 2288749.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.413478183746338,
|
|
"epoch": 1.043910521955261,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004993913807951232,
|
|
"loss": 6.0368,
|
|
"mean_token_accuracy": 0.13126998767256737,
|
|
"num_tokens": 2298272.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.417128038406372,
|
|
"epoch": 1.048053024026512,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004993676662807345,
|
|
"loss": 6.0957,
|
|
"mean_token_accuracy": 0.1319083034992218,
|
|
"num_tokens": 2307230.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.449226379394531,
|
|
"epoch": 1.0521955260977631,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004993434991922443,
|
|
"loss": 6.1669,
|
|
"mean_token_accuracy": 0.12653778642416,
|
|
"num_tokens": 2316306.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.432471418380738,
|
|
"epoch": 1.056338028169014,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004993188795784002,
|
|
"loss": 6.0938,
|
|
"mean_token_accuracy": 0.12626147791743278,
|
|
"num_tokens": 2325672.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.298291969299316,
|
|
"epoch": 1.0604805302402651,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004992938074888628,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.13139547854661943,
|
|
"num_tokens": 2335251.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.4482035636901855,
|
|
"epoch": 1.0646230323115162,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004992682829742052,
|
|
"loss": 6.0507,
|
|
"mean_token_accuracy": 0.1331412188708782,
|
|
"num_tokens": 2344054.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.267281532287598,
|
|
"epoch": 1.0687655343827671,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004992423060859132,
|
|
"loss": 6.0521,
|
|
"mean_token_accuracy": 0.1336584560573101,
|
|
"num_tokens": 2353493.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.503845310211181,
|
|
"epoch": 1.0729080364540182,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004992158768763849,
|
|
"loss": 6.158,
|
|
"mean_token_accuracy": 0.1326499328017235,
|
|
"num_tokens": 2362687.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.422919511795044,
|
|
"epoch": 1.0770505385252693,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004991889953989308,
|
|
"loss": 6.1223,
|
|
"mean_token_accuracy": 0.12865589410066605,
|
|
"num_tokens": 2372325.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.428432607650757,
|
|
"epoch": 1.0811930405965202,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004991616617077741,
|
|
"loss": 6.1441,
|
|
"mean_token_accuracy": 0.13311094492673875,
|
|
"num_tokens": 2381987.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.520003366470337,
|
|
"epoch": 1.0853355426677713,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004991338758580496,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.13536124899983407,
|
|
"num_tokens": 2390901.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.266488838195801,
|
|
"epoch": 1.0894780447390224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004991056379058045,
|
|
"loss": 6.1041,
|
|
"mean_token_accuracy": 0.12899856343865396,
|
|
"num_tokens": 2400756.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.308699131011963,
|
|
"epoch": 1.0936205468102733,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004990769479079976,
|
|
"loss": 5.9385,
|
|
"mean_token_accuracy": 0.13213619813323021,
|
|
"num_tokens": 2409526.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.35676589012146,
|
|
"epoch": 1.0977630488815244,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004990478059225003,
|
|
"loss": 6.1008,
|
|
"mean_token_accuracy": 0.1294182427227497,
|
|
"num_tokens": 2419583.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.438393783569336,
|
|
"epoch": 1.1019055509527755,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004990182120080945,
|
|
"loss": 6.0619,
|
|
"mean_token_accuracy": 0.13824906051158906,
|
|
"num_tokens": 2429439.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.262748527526855,
|
|
"epoch": 1.1060480530240264,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004989881662244748,
|
|
"loss": 6.0582,
|
|
"mean_token_accuracy": 0.1282345525920391,
|
|
"num_tokens": 2438467.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.38105845451355,
|
|
"epoch": 1.1101905550952775,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004989576686322468,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1415070377290249,
|
|
"num_tokens": 2446619.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.294713640213013,
|
|
"epoch": 1.1143330571665286,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004989267192929272,
|
|
"loss": 6.0653,
|
|
"mean_token_accuracy": 0.13668779358267785,
|
|
"num_tokens": 2454998.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.358230304718018,
|
|
"epoch": 1.1184755592377795,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004988953182689445,
|
|
"loss": 6.0325,
|
|
"mean_token_accuracy": 0.13635167926549913,
|
|
"num_tokens": 2463497.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.3403887271881105,
|
|
"epoch": 1.1226180613090306,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004988634656236378,
|
|
"loss": 5.9655,
|
|
"mean_token_accuracy": 0.13428828567266465,
|
|
"num_tokens": 2471763.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.300700998306274,
|
|
"epoch": 1.1267605633802817,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004988311614212576,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.13982509970664977,
|
|
"num_tokens": 2479949.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.378063678741455,
|
|
"epoch": 1.1309030654515326,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004987984057269648,
|
|
"loss": 6.0715,
|
|
"mean_token_accuracy": 0.13535686433315278,
|
|
"num_tokens": 2489097.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.149481630325317,
|
|
"epoch": 1.1350455675227837,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004987651986068311,
|
|
"loss": 5.9023,
|
|
"mean_token_accuracy": 0.13939108699560165,
|
|
"num_tokens": 2497625.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.340058994293213,
|
|
"epoch": 1.1391880695940348,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004987315401278394,
|
|
"loss": 6.1463,
|
|
"mean_token_accuracy": 0.12731209993362427,
|
|
"num_tokens": 2507107.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.482500743865967,
|
|
"epoch": 1.143330571665286,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004986974303578819,
|
|
"loss": 6.1447,
|
|
"mean_token_accuracy": 0.12803158536553383,
|
|
"num_tokens": 2516629.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.342242622375489,
|
|
"epoch": 1.1474730737365368,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004986628693657621,
|
|
"loss": 6.0298,
|
|
"mean_token_accuracy": 0.1318236358463764,
|
|
"num_tokens": 2525924.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.442188549041748,
|
|
"epoch": 1.151615575807788,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0004986278572211933,
|
|
"loss": 6.1865,
|
|
"mean_token_accuracy": 0.1275293305516243,
|
|
"num_tokens": 2535586.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.4357420921325685,
|
|
"epoch": 1.1557580778790388,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985923939947987,
|
|
"loss": 6.2509,
|
|
"mean_token_accuracy": 0.12767949104309081,
|
|
"num_tokens": 2546685.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.281386995315552,
|
|
"epoch": 1.15990057995029,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004985564797581115,
|
|
"loss": 5.9787,
|
|
"mean_token_accuracy": 0.1356250524520874,
|
|
"num_tokens": 2556873.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.330170154571533,
|
|
"epoch": 1.164043082021541,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004985201145835747,
|
|
"loss": 6.0158,
|
|
"mean_token_accuracy": 0.13851649388670922,
|
|
"num_tokens": 2565222.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.281029844284058,
|
|
"epoch": 1.1681855840927922,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000498483298544541,
|
|
"loss": 6.0105,
|
|
"mean_token_accuracy": 0.1319947473704815,
|
|
"num_tokens": 2575467.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.319263124465943,
|
|
"epoch": 1.172328086164043,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000498446031715272,
|
|
"loss": 6.0273,
|
|
"mean_token_accuracy": 0.13361441418528558,
|
|
"num_tokens": 2583963.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.354074096679687,
|
|
"epoch": 1.1764705882352942,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004984083141709391,
|
|
"loss": 6.0681,
|
|
"mean_token_accuracy": 0.1338679425418377,
|
|
"num_tokens": 2593350.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.172420501708984,
|
|
"epoch": 1.180613090306545,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000498370145987623,
|
|
"loss": 5.9719,
|
|
"mean_token_accuracy": 0.1350063219666481,
|
|
"num_tokens": 2602191.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.360668754577636,
|
|
"epoch": 1.1847555923777962,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004983315272423127,
|
|
"loss": 6.1037,
|
|
"mean_token_accuracy": 0.1312294103205204,
|
|
"num_tokens": 2613590.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.241883325576782,
|
|
"epoch": 1.1888980944490473,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004982924580129066,
|
|
"loss": 5.9199,
|
|
"mean_token_accuracy": 0.13844091519713403,
|
|
"num_tokens": 2622072.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.380551862716675,
|
|
"epoch": 1.1930405965202984,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004982529383782116,
|
|
"loss": 6.1199,
|
|
"mean_token_accuracy": 0.1306464396417141,
|
|
"num_tokens": 2630904.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.325322961807251,
|
|
"epoch": 1.1971830985915493,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004982129684179432,
|
|
"loss": 6.0949,
|
|
"mean_token_accuracy": 0.13483623936772346,
|
|
"num_tokens": 2639925.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.305817794799805,
|
|
"epoch": 1.2013256006628004,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004981725482127251,
|
|
"loss": 5.9931,
|
|
"mean_token_accuracy": 0.13657744973897934,
|
|
"num_tokens": 2649397.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.366173505783081,
|
|
"epoch": 1.2054681027340513,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981316778440892,
|
|
"loss": 6.1291,
|
|
"mean_token_accuracy": 0.1340840056538582,
|
|
"num_tokens": 2658877.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.301034593582154,
|
|
"epoch": 1.2096106048053024,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004980903573944756,
|
|
"loss": 6.0426,
|
|
"mean_token_accuracy": 0.13118910491466523,
|
|
"num_tokens": 2668518.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.283834028244018,
|
|
"epoch": 1.2137531068765535,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004980485869472322,
|
|
"loss": 6.1132,
|
|
"mean_token_accuracy": 0.13253218531608582,
|
|
"num_tokens": 2677459.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.37120361328125,
|
|
"epoch": 1.2178956089478046,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004980063665866143,
|
|
"loss": 6.097,
|
|
"mean_token_accuracy": 0.1286916382610798,
|
|
"num_tokens": 2686668.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.197322845458984,
|
|
"epoch": 1.2220381110190555,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004979636963977853,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.13604906648397447,
|
|
"num_tokens": 2695545.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.325300121307373,
|
|
"epoch": 1.2261806130903066,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004979205764668156,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.13842247277498246,
|
|
"num_tokens": 2705514.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.290655946731567,
|
|
"epoch": 1.2303231151615575,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004978770068806825,
|
|
"loss": 5.9642,
|
|
"mean_token_accuracy": 0.13589237332344056,
|
|
"num_tokens": 2714373.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.317065334320068,
|
|
"epoch": 1.2344656172328086,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000497832987727271,
|
|
"loss": 6.0969,
|
|
"mean_token_accuracy": 0.1277540720999241,
|
|
"num_tokens": 2723887.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.267973613739014,
|
|
"epoch": 1.2386081193040597,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004977885190953724,
|
|
"loss": 5.9704,
|
|
"mean_token_accuracy": 0.1360554203391075,
|
|
"num_tokens": 2733591.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.34386134147644,
|
|
"epoch": 1.2427506213753108,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004977436010746846,
|
|
"loss": 6.0837,
|
|
"mean_token_accuracy": 0.137542824447155,
|
|
"num_tokens": 2741638.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 1.2427506213753108,
|
|
"eval_entropy": 6.1450459260676205,
|
|
"eval_loss": 6.2417120933532715,
|
|
"eval_mean_token_accuracy": 0.13248178126143495,
|
|
"eval_num_tokens": 2741638.0,
|
|
"eval_runtime": 2.108,
|
|
"eval_samples_per_second": 1777.534,
|
|
"eval_steps_per_second": 222.488,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.328186321258545,
|
|
"epoch": 1.2468931234465617,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0004976982337558124,
|
|
"loss": 5.9465,
|
|
"mean_token_accuracy": 0.1384536549448967,
|
|
"num_tokens": 2749711.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.20745882987976,
|
|
"epoch": 1.2510356255178128,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004976524172302665,
|
|
"loss": 6.133,
|
|
"mean_token_accuracy": 0.13232308104634286,
|
|
"num_tokens": 2758121.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.424034690856933,
|
|
"epoch": 1.2551781275890637,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004976061515904641,
|
|
"loss": 6.1357,
|
|
"mean_token_accuracy": 0.12840573713183404,
|
|
"num_tokens": 2766764.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.323179292678833,
|
|
"epoch": 1.2593206296603148,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004975594369297277,
|
|
"loss": 6.0763,
|
|
"mean_token_accuracy": 0.1378533735871315,
|
|
"num_tokens": 2775561.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 6.318216180801391,
|
|
"epoch": 1.2634631317315659,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004975122733422861,
|
|
"loss": 6.0375,
|
|
"mean_token_accuracy": 0.13417807072401047,
|
|
"num_tokens": 2784691.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.251212882995605,
|
|
"epoch": 1.267605633802817,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004974646609232732,
|
|
"loss": 6.0122,
|
|
"mean_token_accuracy": 0.13721995949745178,
|
|
"num_tokens": 2793893.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.333720350265503,
|
|
"epoch": 1.2717481358740679,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004974165997687288,
|
|
"loss": 6.0845,
|
|
"mean_token_accuracy": 0.13510174974799155,
|
|
"num_tokens": 2804479.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.308886861801147,
|
|
"epoch": 1.275890637945319,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004973680899755972,
|
|
"loss": 6.1243,
|
|
"mean_token_accuracy": 0.13202088996767997,
|
|
"num_tokens": 2813966.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.304367351531982,
|
|
"epoch": 1.2800331400165699,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000497319131641728,
|
|
"loss": 5.9402,
|
|
"mean_token_accuracy": 0.14228401854634284,
|
|
"num_tokens": 2822328.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.229106187820435,
|
|
"epoch": 1.284175642087821,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004972697248658755,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.14200907796621323,
|
|
"num_tokens": 2829845.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.192464447021484,
|
|
"epoch": 1.288318144159072,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0004972198697476987,
|
|
"loss": 5.892,
|
|
"mean_token_accuracy": 0.14023082777857782,
|
|
"num_tokens": 2839040.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 6.137626218795776,
|
|
"epoch": 1.2924606462303232,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004971695663877607,
|
|
"loss": 5.9873,
|
|
"mean_token_accuracy": 0.14122241362929344,
|
|
"num_tokens": 2848574.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.311916446685791,
|
|
"epoch": 1.296603148301574,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004971188148875289,
|
|
"loss": 5.9471,
|
|
"mean_token_accuracy": 0.14324187487363815,
|
|
"num_tokens": 2856812.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.200193786621094,
|
|
"epoch": 1.3007456503728252,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004970676153493748,
|
|
"loss": 6.0356,
|
|
"mean_token_accuracy": 0.13674534633755683,
|
|
"num_tokens": 2866001.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.309698963165284,
|
|
"epoch": 1.3048881524440763,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004970159678765731,
|
|
"loss": 6.0376,
|
|
"mean_token_accuracy": 0.1356910966336727,
|
|
"num_tokens": 2875181.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.287196111679077,
|
|
"epoch": 1.3090306545153272,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004969638725733028,
|
|
"loss": 5.9585,
|
|
"mean_token_accuracy": 0.14128673523664476,
|
|
"num_tokens": 2885103.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.100416755676269,
|
|
"epoch": 1.3131731565865783,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969113295446455,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.1386077396571636,
|
|
"num_tokens": 2894055.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.278606128692627,
|
|
"epoch": 1.3173156586578294,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004968583388965863,
|
|
"loss": 5.9981,
|
|
"mean_token_accuracy": 0.13714988753199578,
|
|
"num_tokens": 2903391.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.237105989456177,
|
|
"epoch": 1.3214581607290803,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004968049007360132,
|
|
"loss": 5.994,
|
|
"mean_token_accuracy": 0.1386870786547661,
|
|
"num_tokens": 2911760.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.175147151947021,
|
|
"epoch": 1.3256006628003314,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004967510151707169,
|
|
"loss": 5.9475,
|
|
"mean_token_accuracy": 0.13915018290281295,
|
|
"num_tokens": 2920589.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.369753313064575,
|
|
"epoch": 1.3297431648715825,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004966966823093903,
|
|
"loss": 6.0644,
|
|
"mean_token_accuracy": 0.13484889045357704,
|
|
"num_tokens": 2929635.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.208001518249512,
|
|
"epoch": 1.3338856669428334,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004966419022616287,
|
|
"loss": 5.9566,
|
|
"mean_token_accuracy": 0.13991843163967133,
|
|
"num_tokens": 2938778.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.194763469696045,
|
|
"epoch": 1.3380281690140845,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0004965866751379296,
|
|
"loss": 6.0578,
|
|
"mean_token_accuracy": 0.13248574435710908,
|
|
"num_tokens": 2947836.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.303940629959106,
|
|
"epoch": 1.3421706710853356,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004965310010496922,
|
|
"loss": 6.0104,
|
|
"mean_token_accuracy": 0.13229761198163031,
|
|
"num_tokens": 2957028.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.224971008300781,
|
|
"epoch": 1.3463131731565865,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004964748801092168,
|
|
"loss": 5.9812,
|
|
"mean_token_accuracy": 0.1363674595952034,
|
|
"num_tokens": 2966088.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.262715864181518,
|
|
"epoch": 1.3504556752278376,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004964183124297059,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.13448460698127745,
|
|
"num_tokens": 2975271.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.237486219406128,
|
|
"epoch": 1.3545981772990887,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004963612981252625,
|
|
"loss": 6.0718,
|
|
"mean_token_accuracy": 0.13386934548616408,
|
|
"num_tokens": 2983799.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.270224094390869,
|
|
"epoch": 1.3587406793703396,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004963038373108908,
|
|
"loss": 6.0232,
|
|
"mean_token_accuracy": 0.13873186558485032,
|
|
"num_tokens": 2992675.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.297949504852295,
|
|
"epoch": 1.3628831814415907,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004962459301024954,
|
|
"loss": 6.0931,
|
|
"mean_token_accuracy": 0.13615495786070825,
|
|
"num_tokens": 3002483.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.247576522827148,
|
|
"epoch": 1.3670256835128418,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004961875766168816,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.14012517556548118,
|
|
"num_tokens": 3010611.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.24715633392334,
|
|
"epoch": 1.371168185584093,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004961287769717547,
|
|
"loss": 5.952,
|
|
"mean_token_accuracy": 0.13905780464410783,
|
|
"num_tokens": 3019928.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.097472667694092,
|
|
"epoch": 1.3753106876553438,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004960695312857199,
|
|
"loss": 5.954,
|
|
"mean_token_accuracy": 0.1395553819835186,
|
|
"num_tokens": 3029003.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.237765502929688,
|
|
"epoch": 1.379453189726595,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004960098396782824,
|
|
"loss": 5.9547,
|
|
"mean_token_accuracy": 0.14094383865594864,
|
|
"num_tokens": 3038049.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.171917200088501,
|
|
"epoch": 1.3835956917978458,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004959497022698466,
|
|
"loss": 5.9515,
|
|
"mean_token_accuracy": 0.14299275428056718,
|
|
"num_tokens": 3046674.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.184727478027344,
|
|
"epoch": 1.387738193869097,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004958891191817163,
|
|
"loss": 5.9909,
|
|
"mean_token_accuracy": 0.13421738520264626,
|
|
"num_tokens": 3056459.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 6.252535200119018,
|
|
"epoch": 1.391880695940348,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000495828090536094,
|
|
"loss": 5.9889,
|
|
"mean_token_accuracy": 0.13265592753887176,
|
|
"num_tokens": 3066294.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.246398258209228,
|
|
"epoch": 1.3960231980115991,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004957666164560815,
|
|
"loss": 5.9621,
|
|
"mean_token_accuracy": 0.13426307439804078,
|
|
"num_tokens": 3075420.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.238082504272461,
|
|
"epoch": 1.40016570008285,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004957046970656784,
|
|
"loss": 6.0458,
|
|
"mean_token_accuracy": 0.13898480013012887,
|
|
"num_tokens": 3084373.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 6.207704544067383,
|
|
"epoch": 1.4043082021541011,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004956423324897831,
|
|
"loss": 6.028,
|
|
"mean_token_accuracy": 0.1410148784518242,
|
|
"num_tokens": 3094212.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.219083452224732,
|
|
"epoch": 1.408450704225352,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004955795228541917,
|
|
"loss": 5.9578,
|
|
"mean_token_accuracy": 0.14651229679584504,
|
|
"num_tokens": 3102769.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.253363990783692,
|
|
"epoch": 1.4125932062966031,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000495516268285598,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.14103352129459382,
|
|
"num_tokens": 3111465.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.130880308151245,
|
|
"epoch": 1.4167357083678542,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004954525689115935,
|
|
"loss": 5.9386,
|
|
"mean_token_accuracy": 0.14037666097283363,
|
|
"num_tokens": 3121106.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 6.199966049194336,
|
|
"epoch": 1.4208782104391053,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004953884248606669,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.14885828047990798,
|
|
"num_tokens": 3130662.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 6.178520822525025,
|
|
"epoch": 1.4250207125103562,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004953238362622034,
|
|
"loss": 5.9958,
|
|
"mean_token_accuracy": 0.13654247894883156,
|
|
"num_tokens": 3139538.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 6.213479042053223,
|
|
"epoch": 1.4291632145816073,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004952588032464855,
|
|
"loss": 6.0324,
|
|
"mean_token_accuracy": 0.1318473756313324,
|
|
"num_tokens": 3148552.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.1035576343536375,
|
|
"epoch": 1.4333057166528582,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004951933259446919,
|
|
"loss": 5.9302,
|
|
"mean_token_accuracy": 0.14550063461065293,
|
|
"num_tokens": 3156549.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 6.3432533740997314,
|
|
"epoch": 1.4374482187241093,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004951274044888975,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.12662078365683554,
|
|
"num_tokens": 3166821.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.133205366134644,
|
|
"epoch": 1.4415907207953604,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004950610390120731,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.1397806391119957,
|
|
"num_tokens": 3174962.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.2480703830719,
|
|
"epoch": 1.4457332228666115,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000494994229648085,
|
|
"loss": 5.9114,
|
|
"mean_token_accuracy": 0.1379687950015068,
|
|
"num_tokens": 3184027.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.124183797836304,
|
|
"epoch": 1.4498757249378624,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004949269765316948,
|
|
"loss": 6.0494,
|
|
"mean_token_accuracy": 0.13002555593848228,
|
|
"num_tokens": 3193186.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 6.289375114440918,
|
|
"epoch": 1.4540182270091135,
|
|
"grad_norm": 2.171875,
|
|
"learning_rate": 0.0004948592797985599,
|
|
"loss": 6.0505,
|
|
"mean_token_accuracy": 0.13690062686800958,
|
|
"num_tokens": 3202676.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.324394416809082,
|
|
"epoch": 1.4581607290803644,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004947911395852317,
|
|
"loss": 6.1426,
|
|
"mean_token_accuracy": 0.13963466808199881,
|
|
"num_tokens": 3211950.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.339489889144898,
|
|
"epoch": 1.4623032311516155,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004947225560291565,
|
|
"loss": 6.0873,
|
|
"mean_token_accuracy": 0.13304879441857337,
|
|
"num_tokens": 3221135.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.130894613265991,
|
|
"epoch": 1.4664457332228666,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004946535292686746,
|
|
"loss": 5.8989,
|
|
"mean_token_accuracy": 0.14152208119630813,
|
|
"num_tokens": 3230174.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.11918535232544,
|
|
"epoch": 1.4705882352941178,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004945840594430209,
|
|
"loss": 5.9032,
|
|
"mean_token_accuracy": 0.14170208424329758,
|
|
"num_tokens": 3238898.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.205544185638428,
|
|
"epoch": 1.4747307373653686,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004945141466923235,
|
|
"loss": 5.9335,
|
|
"mean_token_accuracy": 0.14418990314006805,
|
|
"num_tokens": 3247550.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 6.305442523956299,
|
|
"epoch": 1.4788732394366197,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004944437911576041,
|
|
"loss": 6.0756,
|
|
"mean_token_accuracy": 0.13215108439326287,
|
|
"num_tokens": 3256810.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 6.062059831619263,
|
|
"epoch": 1.4830157415078706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004943729929807772,
|
|
"loss": 5.8655,
|
|
"mean_token_accuracy": 0.14079953730106354,
|
|
"num_tokens": 3265886.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.228650426864624,
|
|
"epoch": 1.4871582435791217,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004943017523046507,
|
|
"loss": 5.9409,
|
|
"mean_token_accuracy": 0.14057195484638213,
|
|
"num_tokens": 3274522.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 6.238694429397583,
|
|
"epoch": 1.4913007456503728,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000494230069272925,
|
|
"loss": 6.0456,
|
|
"mean_token_accuracy": 0.14020049646496774,
|
|
"num_tokens": 3283388.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.1787903785705565,
|
|
"epoch": 1.495443247721624,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004941579440301923,
|
|
"loss": 5.9095,
|
|
"mean_token_accuracy": 0.13298032581806182,
|
|
"num_tokens": 3291887.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.147898387908936,
|
|
"epoch": 1.4995857497928748,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004940853767219372,
|
|
"loss": 5.9886,
|
|
"mean_token_accuracy": 0.13950188905000688,
|
|
"num_tokens": 3300674.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.09293565750122,
|
|
"epoch": 1.503728251864126,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004940123674945359,
|
|
"loss": 5.8255,
|
|
"mean_token_accuracy": 0.14723611921072005,
|
|
"num_tokens": 3309745.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.203557109832763,
|
|
"epoch": 1.5078707539353768,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004939389164952561,
|
|
"loss": 5.979,
|
|
"mean_token_accuracy": 0.14057357907295226,
|
|
"num_tokens": 3318888.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 6.158121776580811,
|
|
"epoch": 1.512013256006628,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004938650238722564,
|
|
"loss": 5.9485,
|
|
"mean_token_accuracy": 0.14149481058120728,
|
|
"num_tokens": 3328274.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 6.215224170684815,
|
|
"epoch": 1.516155758077879,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004937906897745861,
|
|
"loss": 5.9563,
|
|
"mean_token_accuracy": 0.14156463742256165,
|
|
"num_tokens": 3337579.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 6.200045490264893,
|
|
"epoch": 1.5202982601491302,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004937159143521856,
|
|
"loss": 5.937,
|
|
"mean_token_accuracy": 0.14527209475636482,
|
|
"num_tokens": 3346262.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.115064001083374,
|
|
"epoch": 1.5244407622203813,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004936406977558847,
|
|
"loss": 5.9957,
|
|
"mean_token_accuracy": 0.1344020515680313,
|
|
"num_tokens": 3354833.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 6.233158111572266,
|
|
"epoch": 1.5285832642916322,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004935650401374039,
|
|
"loss": 6.0827,
|
|
"mean_token_accuracy": 0.14519838392734527,
|
|
"num_tokens": 3364314.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.171499109268188,
|
|
"epoch": 1.532725766362883,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004934889416493524,
|
|
"loss": 5.908,
|
|
"mean_token_accuracy": 0.1396942026913166,
|
|
"num_tokens": 3373648.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 6.06867733001709,
|
|
"epoch": 1.5368682684341342,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004934124024452295,
|
|
"loss": 5.7969,
|
|
"mean_token_accuracy": 0.14711106717586517,
|
|
"num_tokens": 3382919.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.084351205825806,
|
|
"epoch": 1.5410107705053853,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004933354226794232,
|
|
"loss": 5.9393,
|
|
"mean_token_accuracy": 0.13947515338659286,
|
|
"num_tokens": 3391814.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 6.199561548233032,
|
|
"epoch": 1.5451532725766364,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004932580025072098,
|
|
"loss": 5.9788,
|
|
"mean_token_accuracy": 0.1385117821395397,
|
|
"num_tokens": 3400392.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.148109245300293,
|
|
"epoch": 1.5492957746478875,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004931801420847545,
|
|
"loss": 6.0351,
|
|
"mean_token_accuracy": 0.13209574967622756,
|
|
"num_tokens": 3410430.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 6.122993516921997,
|
|
"epoch": 1.5534382767191384,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004931018415691102,
|
|
"loss": 5.8696,
|
|
"mean_token_accuracy": 0.13951531648635865,
|
|
"num_tokens": 3420654.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 6.151796579360962,
|
|
"epoch": 1.5575807787903893,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004930231011182176,
|
|
"loss": 6.0094,
|
|
"mean_token_accuracy": 0.13828911855816842,
|
|
"num_tokens": 3430514.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.229997634887695,
|
|
"epoch": 1.5617232808616404,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004929439208909048,
|
|
"loss": 5.9334,
|
|
"mean_token_accuracy": 0.14276001006364822,
|
|
"num_tokens": 3439551.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 6.119334411621094,
|
|
"epoch": 1.5658657829328915,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004928643010468869,
|
|
"loss": 5.907,
|
|
"mean_token_accuracy": 0.1400480180978775,
|
|
"num_tokens": 3448160.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.153133869171143,
|
|
"epoch": 1.5700082850041426,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004927842417467659,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.14561555981636048,
|
|
"num_tokens": 3457296.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 6.184989786148071,
|
|
"epoch": 1.5741507870753937,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004927037431520302,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.14709929376840591,
|
|
"num_tokens": 3466108.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 6.082920551300049,
|
|
"epoch": 1.5782932891466446,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004926228054250541,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.13886846452951432,
|
|
"num_tokens": 3475336.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.2809975147247314,
|
|
"epoch": 1.5824357912178955,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004925414287290979,
|
|
"loss": 5.9805,
|
|
"mean_token_accuracy": 0.13600327223539352,
|
|
"num_tokens": 3483963.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 6.0389931201934814,
|
|
"epoch": 1.5865782932891466,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004924596132283075,
|
|
"loss": 5.8814,
|
|
"mean_token_accuracy": 0.14751892685890197,
|
|
"num_tokens": 3492947.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.1129943370819095,
|
|
"epoch": 1.5907207953603977,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004923773590877135,
|
|
"loss": 5.9607,
|
|
"mean_token_accuracy": 0.13690620362758638,
|
|
"num_tokens": 3501877.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 6.226007652282715,
|
|
"epoch": 1.5948632974316488,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004922946664732314,
|
|
"loss": 6.0179,
|
|
"mean_token_accuracy": 0.13733150959014892,
|
|
"num_tokens": 3510610.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 6.226138401031494,
|
|
"epoch": 1.5990057995029,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004922115355516615,
|
|
"loss": 5.987,
|
|
"mean_token_accuracy": 0.1421550303697586,
|
|
"num_tokens": 3519829.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 6.18082628250122,
|
|
"epoch": 1.6031483015741508,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004921279664906877,
|
|
"loss": 5.9649,
|
|
"mean_token_accuracy": 0.13739833384752273,
|
|
"num_tokens": 3529408.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.077984142303467,
|
|
"epoch": 1.6072908036454017,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004920439594588781,
|
|
"loss": 5.9104,
|
|
"mean_token_accuracy": 0.14634366631507872,
|
|
"num_tokens": 3538068.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 6.192194318771362,
|
|
"epoch": 1.6114333057166528,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000491959514625684,
|
|
"loss": 6.019,
|
|
"mean_token_accuracy": 0.14332248717546464,
|
|
"num_tokens": 3547302.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.125579690933227,
|
|
"epoch": 1.6155758077879039,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00049187463216144,
|
|
"loss": 5.9024,
|
|
"mean_token_accuracy": 0.14861151427030564,
|
|
"num_tokens": 3556087.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.207472896575927,
|
|
"epoch": 1.619718309859155,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.000491789312237363,
|
|
"loss": 5.9691,
|
|
"mean_token_accuracy": 0.14141590148210526,
|
|
"num_tokens": 3566235.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 6.1809961795806885,
|
|
"epoch": 1.623860811930406,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004917035550255528,
|
|
"loss": 5.9154,
|
|
"mean_token_accuracy": 0.14227381274104117,
|
|
"num_tokens": 3574762.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 6.051875114440918,
|
|
"epoch": 1.628003314001657,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000491617360698991,
|
|
"loss": 5.8849,
|
|
"mean_token_accuracy": 0.14124636650085448,
|
|
"num_tokens": 3583359.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 6.050506448745727,
|
|
"epoch": 1.6321458160729079,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004915307294315412,
|
|
"loss": 5.8328,
|
|
"mean_token_accuracy": 0.146518924087286,
|
|
"num_tokens": 3591436.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 6.101462888717651,
|
|
"epoch": 1.636288318144159,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000491443661397948,
|
|
"loss": 5.9486,
|
|
"mean_token_accuracy": 0.13945667892694474,
|
|
"num_tokens": 3601054.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 6.16776819229126,
|
|
"epoch": 1.64043082021541,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004913561567738368,
|
|
"loss": 5.9127,
|
|
"mean_token_accuracy": 0.1449202612042427,
|
|
"num_tokens": 3610641.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 6.071323442459106,
|
|
"epoch": 1.6445733222866612,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004912682157357146,
|
|
"loss": 5.8402,
|
|
"mean_token_accuracy": 0.14677978903055192,
|
|
"num_tokens": 3619351.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.988628768920899,
|
|
"epoch": 1.6487158243579123,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004911798384609675,
|
|
"loss": 5.8414,
|
|
"mean_token_accuracy": 0.14875895008444787,
|
|
"num_tokens": 3627341.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 6.1566671371459964,
|
|
"epoch": 1.6528583264291632,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004910910251278626,
|
|
"loss": 5.8825,
|
|
"mean_token_accuracy": 0.1572631388902664,
|
|
"num_tokens": 3637132.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 6.139908933639527,
|
|
"epoch": 1.6570008285004143,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004910017759155458,
|
|
"loss": 5.9317,
|
|
"mean_token_accuracy": 0.14228944033384322,
|
|
"num_tokens": 3646196.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.6570008285004143,
|
|
"eval_entropy": 5.874023848250985,
|
|
"eval_loss": 6.080362319946289,
|
|
"eval_mean_token_accuracy": 0.14062138028871785,
|
|
"eval_num_tokens": 3646196.0,
|
|
"eval_runtime": 2.1129,
|
|
"eval_samples_per_second": 1773.361,
|
|
"eval_steps_per_second": 221.966,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 6.043913221359253,
|
|
"epoch": 1.6611433305716652,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004909120910040427,
|
|
"loss": 5.8727,
|
|
"mean_token_accuracy": 0.1496455654501915,
|
|
"num_tokens": 3654658.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 6.245485258102417,
|
|
"epoch": 1.6652858326429163,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004908219705742574,
|
|
"loss": 6.1474,
|
|
"mean_token_accuracy": 0.13809763565659522,
|
|
"num_tokens": 3664509.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 6.0975141525268555,
|
|
"epoch": 1.6694283347141674,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004907314148079727,
|
|
"loss": 5.8596,
|
|
"mean_token_accuracy": 0.143882005661726,
|
|
"num_tokens": 3672983.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.997087240219116,
|
|
"epoch": 1.6735708367854185,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004906404238878496,
|
|
"loss": 5.717,
|
|
"mean_token_accuracy": 0.15030423998832704,
|
|
"num_tokens": 3681196.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 6.160958909988404,
|
|
"epoch": 1.6777133388566694,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004905489979974265,
|
|
"loss": 5.9034,
|
|
"mean_token_accuracy": 0.14250049591064454,
|
|
"num_tokens": 3690077.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 6.110355710983276,
|
|
"epoch": 1.6818558409279205,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004904571373211197,
|
|
"loss": 5.9626,
|
|
"mean_token_accuracy": 0.13948154225945472,
|
|
"num_tokens": 3700121.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 6.085564708709716,
|
|
"epoch": 1.6859983429991714,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000490364842044222,
|
|
"loss": 5.8071,
|
|
"mean_token_accuracy": 0.15038276463747025,
|
|
"num_tokens": 3709618.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 6.05253415107727,
|
|
"epoch": 1.6901408450704225,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004902721123529031,
|
|
"loss": 6.0018,
|
|
"mean_token_accuracy": 0.13299599811434745,
|
|
"num_tokens": 3719570.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 6.275170803070068,
|
|
"epoch": 1.6942833471416736,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000490178948434209,
|
|
"loss": 5.9256,
|
|
"mean_token_accuracy": 0.14927142709493638,
|
|
"num_tokens": 3729354.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 6.055284786224365,
|
|
"epoch": 1.6984258492129247,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004900853504760614,
|
|
"loss": 5.8397,
|
|
"mean_token_accuracy": 0.14695540443062782,
|
|
"num_tokens": 3738453.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.981637811660766,
|
|
"epoch": 1.7025683512841756,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004899913186672577,
|
|
"loss": 5.8159,
|
|
"mean_token_accuracy": 0.14908216297626495,
|
|
"num_tokens": 3747815.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 6.06216344833374,
|
|
"epoch": 1.7067108533554267,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004898968531974702,
|
|
"loss": 5.8997,
|
|
"mean_token_accuracy": 0.15259757190942763,
|
|
"num_tokens": 3757298.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 6.112562417984009,
|
|
"epoch": 1.7108533554266776,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004898019542572462,
|
|
"loss": 5.9202,
|
|
"mean_token_accuracy": 0.14373964965343475,
|
|
"num_tokens": 3765939.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 6.191072845458985,
|
|
"epoch": 1.7149958574979287,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004897066220380073,
|
|
"loss": 5.9279,
|
|
"mean_token_accuracy": 0.1386391043663025,
|
|
"num_tokens": 3775160.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 6.114138412475586,
|
|
"epoch": 1.7191383595691798,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004896108567320489,
|
|
"loss": 5.8384,
|
|
"mean_token_accuracy": 0.14560278803110122,
|
|
"num_tokens": 3785181.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 6.127746057510376,
|
|
"epoch": 1.723280861640431,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048951465853254,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.14337964877486228,
|
|
"num_tokens": 3794531.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 6.036863708496094,
|
|
"epoch": 1.7274233637116818,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004894180276335231,
|
|
"loss": 5.9311,
|
|
"mean_token_accuracy": 0.14032400846481324,
|
|
"num_tokens": 3804602.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 6.191616439819336,
|
|
"epoch": 1.731565865782933,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004893209642299132,
|
|
"loss": 5.9663,
|
|
"mean_token_accuracy": 0.14373981803655625,
|
|
"num_tokens": 3813394.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 6.114638471603394,
|
|
"epoch": 1.7357083678541838,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004892234685174976,
|
|
"loss": 5.967,
|
|
"mean_token_accuracy": 0.1415805034339428,
|
|
"num_tokens": 3821604.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 6.157201480865479,
|
|
"epoch": 1.739850869925435,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004891255406929359,
|
|
"loss": 5.9503,
|
|
"mean_token_accuracy": 0.1427985519170761,
|
|
"num_tokens": 3831977.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 6.134490919113159,
|
|
"epoch": 1.743993371996686,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004890271809537595,
|
|
"loss": 5.8902,
|
|
"mean_token_accuracy": 0.14459130316972732,
|
|
"num_tokens": 3840684.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.99285569190979,
|
|
"epoch": 1.7481358740679371,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004889283894983704,
|
|
"loss": 5.822,
|
|
"mean_token_accuracy": 0.14208590537309645,
|
|
"num_tokens": 3851147.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 6.158426713943482,
|
|
"epoch": 1.752278376139188,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000488829166526042,
|
|
"loss": 5.9451,
|
|
"mean_token_accuracy": 0.14956211298704147,
|
|
"num_tokens": 3859881.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 6.1649645328521725,
|
|
"epoch": 1.7564208782104391,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004887295122369176,
|
|
"loss": 6.0039,
|
|
"mean_token_accuracy": 0.14027811884880065,
|
|
"num_tokens": 3870151.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 6.098885107040405,
|
|
"epoch": 1.76056338028169,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000488629426832011,
|
|
"loss": 5.9401,
|
|
"mean_token_accuracy": 0.14093397855758666,
|
|
"num_tokens": 3878398.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 6.1110546588897705,
|
|
"epoch": 1.7647058823529411,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004885289105132054,
|
|
"loss": 5.88,
|
|
"mean_token_accuracy": 0.13898311480879783,
|
|
"num_tokens": 3888007.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 6.088969039916992,
|
|
"epoch": 1.7688483844241922,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004884279634832532,
|
|
"loss": 5.8674,
|
|
"mean_token_accuracy": 0.14867447167634965,
|
|
"num_tokens": 3896945.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 6.1467766761779785,
|
|
"epoch": 1.7729908864954433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004883265859457754,
|
|
"loss": 5.8735,
|
|
"mean_token_accuracy": 0.15197214633226394,
|
|
"num_tokens": 3906049.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 6.028802394866943,
|
|
"epoch": 1.7771333885666944,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048822477810526186,
|
|
"loss": 5.8429,
|
|
"mean_token_accuracy": 0.1435732439160347,
|
|
"num_tokens": 3915050.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 6.134473705291748,
|
|
"epoch": 1.7812758906379453,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048812254016706994,
|
|
"loss": 5.9224,
|
|
"mean_token_accuracy": 0.1448567934334278,
|
|
"num_tokens": 3924031.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 6.084311532974243,
|
|
"epoch": 1.7854183927091962,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004880198723374247,
|
|
"loss": 5.9685,
|
|
"mean_token_accuracy": 0.14345090091228485,
|
|
"num_tokens": 3933756.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 6.121155500411987,
|
|
"epoch": 1.7895608947804473,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00048791677482341845,
|
|
"loss": 5.9416,
|
|
"mean_token_accuracy": 0.13881594836711883,
|
|
"num_tokens": 3943129.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 6.021676874160766,
|
|
"epoch": 1.7937033968516984,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048781324783301016,
|
|
"loss": 5.782,
|
|
"mean_token_accuracy": 0.1462274558842182,
|
|
"num_tokens": 3951494.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 6.067917156219482,
|
|
"epoch": 1.7978458989229495,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048770929157502505,
|
|
"loss": 5.9381,
|
|
"mean_token_accuracy": 0.14510203301906585,
|
|
"num_tokens": 3960588.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 6.183278799057007,
|
|
"epoch": 1.8019884009942007,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004876049062591543,
|
|
"loss": 5.927,
|
|
"mean_token_accuracy": 0.13713768348097802,
|
|
"num_tokens": 3970135.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 6.1064512729644775,
|
|
"epoch": 1.8061309030654515,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048750009209595443,
|
|
"loss": 5.9004,
|
|
"mean_token_accuracy": 0.1408342719078064,
|
|
"num_tokens": 3979569.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 6.010239458084106,
|
|
"epoch": 1.8102734051367024,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048739484929684714,
|
|
"loss": 5.8322,
|
|
"mean_token_accuracy": 0.14995085150003434,
|
|
"num_tokens": 3987885.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 6.10627007484436,
|
|
"epoch": 1.8144159072079535,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00048728917807411856,
|
|
"loss": 6.0092,
|
|
"mean_token_accuracy": 0.1335530586540699,
|
|
"num_tokens": 3997726.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 6.109944820404053,
|
|
"epoch": 1.8185584092792046,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004871830786409191,
|
|
"loss": 5.8324,
|
|
"mean_token_accuracy": 0.1525810420513153,
|
|
"num_tokens": 4006437.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 6.003955411911011,
|
|
"epoch": 1.8227009113504558,
|
|
"grad_norm": 1.703125,
|
|
"learning_rate": 0.00048707655121126296,
|
|
"loss": 5.8011,
|
|
"mean_token_accuracy": 0.15133841037750245,
|
|
"num_tokens": 4015326.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 6.083161973953247,
|
|
"epoch": 1.8268434134217069,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048696959600002767,
|
|
"loss": 5.8624,
|
|
"mean_token_accuracy": 0.140908819437027,
|
|
"num_tokens": 4024294.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 6.029014587402344,
|
|
"epoch": 1.8309859154929577,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048686221322295347,
|
|
"loss": 5.8801,
|
|
"mean_token_accuracy": 0.15111605525016786,
|
|
"num_tokens": 4033341.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 6.027010774612426,
|
|
"epoch": 1.8351284175642086,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048675440309664314,
|
|
"loss": 5.832,
|
|
"mean_token_accuracy": 0.15358244329690934,
|
|
"num_tokens": 4042446.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.998649644851684,
|
|
"epoch": 1.8392709196354597,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048664616583856166,
|
|
"loss": 5.8709,
|
|
"mean_token_accuracy": 0.13802095353603364,
|
|
"num_tokens": 4051849.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 6.173512172698975,
|
|
"epoch": 1.8434134217067109,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048653750166703516,
|
|
"loss": 5.9489,
|
|
"mean_token_accuracy": 0.1443096585571766,
|
|
"num_tokens": 4061075.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 6.132181167602539,
|
|
"epoch": 1.847555923777962,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004864284108012513,
|
|
"loss": 5.9492,
|
|
"mean_token_accuracy": 0.1360410049557686,
|
|
"num_tokens": 4071022.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 6.038720178604126,
|
|
"epoch": 1.851698425849213,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004863188934612583,
|
|
"loss": 5.8462,
|
|
"mean_token_accuracy": 0.14651346057653428,
|
|
"num_tokens": 4080728.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 6.01682415008545,
|
|
"epoch": 1.855840927920464,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004862089498679645,
|
|
"loss": 5.8092,
|
|
"mean_token_accuracy": 0.15180521160364152,
|
|
"num_tokens": 4088712.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 6.045846223831177,
|
|
"epoch": 1.8599834299917148,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004860985802431383,
|
|
"loss": 5.8297,
|
|
"mean_token_accuracy": 0.15167509615421296,
|
|
"num_tokens": 4097488.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.994900369644165,
|
|
"epoch": 1.864125932062966,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004859877848094071,
|
|
"loss": 5.8087,
|
|
"mean_token_accuracy": 0.1456088751554489,
|
|
"num_tokens": 4106485.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 6.084024572372437,
|
|
"epoch": 1.868268434134217,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004858765637902575,
|
|
"loss": 5.7849,
|
|
"mean_token_accuracy": 0.1513776436448097,
|
|
"num_tokens": 4115806.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 6.1543549537658695,
|
|
"epoch": 1.8724109362054682,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004857649174100344,
|
|
"loss": 5.9323,
|
|
"mean_token_accuracy": 0.1476415552198887,
|
|
"num_tokens": 4124636.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 6.017945241928101,
|
|
"epoch": 1.8765534382767193,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0004856528458939409,
|
|
"loss": 5.8882,
|
|
"mean_token_accuracy": 0.13946284651756286,
|
|
"num_tokens": 4133876.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 6.021767807006836,
|
|
"epoch": 1.8806959403479702,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004855403494680373,
|
|
"loss": 5.8053,
|
|
"mean_token_accuracy": 0.1419292762875557,
|
|
"num_tokens": 4143555.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 6.008573961257935,
|
|
"epoch": 1.884838442419221,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00048542742835924133,
|
|
"loss": 5.7626,
|
|
"mean_token_accuracy": 0.14792594760656358,
|
|
"num_tokens": 4153007.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.91074275970459,
|
|
"epoch": 1.8889809444904722,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048531408279532705,
|
|
"loss": 5.8032,
|
|
"mean_token_accuracy": 0.142525102943182,
|
|
"num_tokens": 4162107.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 6.0140910148620605,
|
|
"epoch": 1.8931234465617233,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048520031300492507,
|
|
"loss": 5.8061,
|
|
"mean_token_accuracy": 0.1468598410487175,
|
|
"num_tokens": 4170920.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 6.079481410980224,
|
|
"epoch": 1.8972659486329744,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048508611921752124,
|
|
"loss": 5.8315,
|
|
"mean_token_accuracy": 0.14988012462854386,
|
|
"num_tokens": 4180226.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.958925056457519,
|
|
"epoch": 1.9014084507042255,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048497150166345703,
|
|
"loss": 5.7554,
|
|
"mean_token_accuracy": 0.14854799956083298,
|
|
"num_tokens": 4189283.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.96260290145874,
|
|
"epoch": 1.9055509527754764,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004848564605739287,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.14435628652572632,
|
|
"num_tokens": 4199017.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 6.1000776290893555,
|
|
"epoch": 1.9096934548467275,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00048474099618098644,
|
|
"loss": 5.9415,
|
|
"mean_token_accuracy": 0.14426328167319297,
|
|
"num_tokens": 4207756.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 6.022288465499878,
|
|
"epoch": 1.9138359569179784,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004846251087175348,
|
|
"loss": 5.8266,
|
|
"mean_token_accuracy": 0.1475055083632469,
|
|
"num_tokens": 4216721.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 6.032358646392822,
|
|
"epoch": 1.9179784589892295,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004845087984173312,
|
|
"loss": 5.8168,
|
|
"mean_token_accuracy": 0.15082903131842612,
|
|
"num_tokens": 4225596.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 6.084334421157837,
|
|
"epoch": 1.9221209610604806,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048439206551498644,
|
|
"loss": 5.849,
|
|
"mean_token_accuracy": 0.1496099904179573,
|
|
"num_tokens": 4234500.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.992849826812744,
|
|
"epoch": 1.9262634631317317,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004842749102459635,
|
|
"loss": 5.8144,
|
|
"mean_token_accuracy": 0.14916087314486504,
|
|
"num_tokens": 4243240.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.945455312728882,
|
|
"epoch": 1.9304059652029826,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048415733284657727,
|
|
"loss": 5.8038,
|
|
"mean_token_accuracy": 0.15595563054084777,
|
|
"num_tokens": 4251892.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 6.017211198806763,
|
|
"epoch": 1.9345484672742337,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004840393335539943,
|
|
"loss": 5.7671,
|
|
"mean_token_accuracy": 0.15037013292312623,
|
|
"num_tokens": 4261447.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 6.039053583145142,
|
|
"epoch": 1.9386909693454846,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00048392091260623195,
|
|
"loss": 5.9215,
|
|
"mean_token_accuracy": 0.14951857775449753,
|
|
"num_tokens": 4270120.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 6.031311130523681,
|
|
"epoch": 1.9428334714167357,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048380207024215836,
|
|
"loss": 5.7906,
|
|
"mean_token_accuracy": 0.14514822512865067,
|
|
"num_tokens": 4278300.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 6.057702875137329,
|
|
"epoch": 1.9469759734879868,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00048368280670149145,
|
|
"loss": 5.8306,
|
|
"mean_token_accuracy": 0.14935216754674913,
|
|
"num_tokens": 4286454.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.917616987228394,
|
|
"epoch": 1.951118475559238,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004835631222247989,
|
|
"loss": 5.71,
|
|
"mean_token_accuracy": 0.1527955412864685,
|
|
"num_tokens": 4294752.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.98473014831543,
|
|
"epoch": 1.9552609776304888,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00048344301705349735,
|
|
"loss": 5.7704,
|
|
"mean_token_accuracy": 0.15101421475410462,
|
|
"num_tokens": 4303195.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 6.040767526626587,
|
|
"epoch": 1.95940347970174,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00048332249142985195,
|
|
"loss": 5.9161,
|
|
"mean_token_accuracy": 0.1434949241578579,
|
|
"num_tokens": 4311961.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 6.024049615859985,
|
|
"epoch": 1.9635459817729908,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004832015455969763,
|
|
"loss": 5.7595,
|
|
"mean_token_accuracy": 0.14508079290390014,
|
|
"num_tokens": 4322267.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.939272403717041,
|
|
"epoch": 1.9676884838442419,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048308017979883114,
|
|
"loss": 5.8657,
|
|
"mean_token_accuracy": 0.1457856371998787,
|
|
"num_tokens": 4330584.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.925167560577393,
|
|
"epoch": 1.971830985915493,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048295839428022454,
|
|
"loss": 5.7161,
|
|
"mean_token_accuracy": 0.14976125806570054,
|
|
"num_tokens": 4339215.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 6.032935953140258,
|
|
"epoch": 1.975973487986744,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00048283618928681127,
|
|
"loss": 5.7382,
|
|
"mean_token_accuracy": 0.15662530511617662,
|
|
"num_tokens": 4347711.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.927608680725098,
|
|
"epoch": 1.980115990057995,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004827135650650923,
|
|
"loss": 5.732,
|
|
"mean_token_accuracy": 0.15485673546791076,
|
|
"num_tokens": 4356982.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.8668547630310055,
|
|
"epoch": 1.984258492129246,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004825905218624139,
|
|
"loss": 5.7539,
|
|
"mean_token_accuracy": 0.1500335916876793,
|
|
"num_tokens": 4365378.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 6.162260103225708,
|
|
"epoch": 1.988400994200497,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048246705992696756,
|
|
"loss": 5.8111,
|
|
"mean_token_accuracy": 0.140972301363945,
|
|
"num_tokens": 4374007.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 6.086604118347168,
|
|
"epoch": 1.992543496271748,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048234317950778975,
|
|
"loss": 5.906,
|
|
"mean_token_accuracy": 0.1491197317838669,
|
|
"num_tokens": 4383909.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 6.080717754364014,
|
|
"epoch": 1.9966859983429992,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004822188808547607,
|
|
"loss": 5.9774,
|
|
"mean_token_accuracy": 0.1428071916103363,
|
|
"num_tokens": 4393145.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.962521982192993,
|
|
"epoch": 2.0008285004142503,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004820941642186043,
|
|
"loss": 5.692,
|
|
"mean_token_accuracy": 0.14557612016797067,
|
|
"num_tokens": 4402024.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 6.005666828155517,
|
|
"epoch": 2.0049710024855014,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004819690298508879,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.1672823339700699,
|
|
"num_tokens": 4411377.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.966760778427124,
|
|
"epoch": 2.009113504556752,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048184347800402083,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.17516808956861496,
|
|
"num_tokens": 4419781.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.804680967330933,
|
|
"epoch": 2.013256006628003,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004817175089312551,
|
|
"loss": 5.4488,
|
|
"mean_token_accuracy": 0.17022604495286942,
|
|
"num_tokens": 4428427.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.961127233505249,
|
|
"epoch": 2.0173985086992543,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048159112288668403,
|
|
"loss": 5.4711,
|
|
"mean_token_accuracy": 0.1661138951778412,
|
|
"num_tokens": 4438156.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 6.000173330307007,
|
|
"epoch": 2.0215410107705054,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048146432012524215,
|
|
"loss": 5.4878,
|
|
"mean_token_accuracy": 0.17110148221254348,
|
|
"num_tokens": 4446342.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.898652982711792,
|
|
"epoch": 2.0256835128417565,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048133710090270446,
|
|
"loss": 5.5409,
|
|
"mean_token_accuracy": 0.16039638221263885,
|
|
"num_tokens": 4455582.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 6.023085260391236,
|
|
"epoch": 2.0298260149130076,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048120946547568596,
|
|
"loss": 5.5748,
|
|
"mean_token_accuracy": 0.1651100292801857,
|
|
"num_tokens": 4464518.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 6.046728134155273,
|
|
"epoch": 2.0339685169842583,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00048108141410164133,
|
|
"loss": 5.6752,
|
|
"mean_token_accuracy": 0.1500121273100376,
|
|
"num_tokens": 4475031.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 6.013257789611816,
|
|
"epoch": 2.0381110190555094,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004809529470388642,
|
|
"loss": 5.5562,
|
|
"mean_token_accuracy": 0.16635677367448806,
|
|
"num_tokens": 4484609.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.94019513130188,
|
|
"epoch": 2.0422535211267605,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004808240645464866,
|
|
"loss": 5.573,
|
|
"mean_token_accuracy": 0.1624813809990883,
|
|
"num_tokens": 4494238.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.855140542984008,
|
|
"epoch": 2.0463960231980116,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004806947668844787,
|
|
"loss": 5.4625,
|
|
"mean_token_accuracy": 0.17260214388370515,
|
|
"num_tokens": 4503258.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.941313695907593,
|
|
"epoch": 2.0505385252692627,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048056505431364794,
|
|
"loss": 5.5238,
|
|
"mean_token_accuracy": 0.16605687141418457,
|
|
"num_tokens": 4512071.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.907178926467895,
|
|
"epoch": 2.054681027340514,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048043492709563877,
|
|
"loss": 5.3627,
|
|
"mean_token_accuracy": 0.17821477800607682,
|
|
"num_tokens": 4520219.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.868778133392334,
|
|
"epoch": 2.0588235294117645,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048030438549293193,
|
|
"loss": 5.5781,
|
|
"mean_token_accuracy": 0.16587240397930145,
|
|
"num_tokens": 4529386.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.954671621322632,
|
|
"epoch": 2.0629660314830156,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00048017342976884424,
|
|
"loss": 5.5779,
|
|
"mean_token_accuracy": 0.1579540751874447,
|
|
"num_tokens": 4538860.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.901145601272583,
|
|
"epoch": 2.0671085335542667,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048004206018752773,
|
|
"loss": 5.5405,
|
|
"mean_token_accuracy": 0.1605120435357094,
|
|
"num_tokens": 4547842.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.86530909538269,
|
|
"epoch": 2.071251035625518,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047991027701396895,
|
|
"loss": 5.532,
|
|
"mean_token_accuracy": 0.16047001928091048,
|
|
"num_tokens": 4556238.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 2.071251035625518,
|
|
"eval_entropy": 5.700431426196719,
|
|
"eval_loss": 5.979622840881348,
|
|
"eval_mean_token_accuracy": 0.14706116486618767,
|
|
"eval_num_tokens": 4556238.0,
|
|
"eval_runtime": 2.0999,
|
|
"eval_samples_per_second": 1784.392,
|
|
"eval_steps_per_second": 223.347,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.91064567565918,
|
|
"epoch": 2.075393537696769,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004797780805139892,
|
|
"loss": 5.5194,
|
|
"mean_token_accuracy": 0.16701295971870422,
|
|
"num_tokens": 4565684.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.8715479373931885,
|
|
"epoch": 2.07953603976802,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004796454709542432,
|
|
"loss": 5.4743,
|
|
"mean_token_accuracy": 0.1701912671327591,
|
|
"num_tokens": 4575001.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.894387054443359,
|
|
"epoch": 2.083678541839271,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004795124486022189,
|
|
"loss": 5.5998,
|
|
"mean_token_accuracy": 0.1611030802130699,
|
|
"num_tokens": 4584128.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.919654273986817,
|
|
"epoch": 2.087821043910522,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047937901372623694,
|
|
"loss": 5.4421,
|
|
"mean_token_accuracy": 0.16908973455429077,
|
|
"num_tokens": 4593011.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.818285036087036,
|
|
"epoch": 2.091963545981773,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047924516659545005,
|
|
"loss": 5.498,
|
|
"mean_token_accuracy": 0.16083064973354338,
|
|
"num_tokens": 4602676.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.995373773574829,
|
|
"epoch": 2.096106048053024,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004791109074798425,
|
|
"loss": 5.5647,
|
|
"mean_token_accuracy": 0.16249934434890748,
|
|
"num_tokens": 4611915.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.904282283782959,
|
|
"epoch": 2.100248550124275,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004789762366502296,
|
|
"loss": 5.5341,
|
|
"mean_token_accuracy": 0.165102981030941,
|
|
"num_tokens": 4621396.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.916229724884033,
|
|
"epoch": 2.1043910521955262,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004788411543782571,
|
|
"loss": 5.5333,
|
|
"mean_token_accuracy": 0.1635112926363945,
|
|
"num_tokens": 4630533.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.833063125610352,
|
|
"epoch": 2.108533554266777,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004787056609364008,
|
|
"loss": 5.4904,
|
|
"mean_token_accuracy": 0.16558443307876586,
|
|
"num_tokens": 4639023.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.932992315292358,
|
|
"epoch": 2.112676056338028,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004785697565979657,
|
|
"loss": 5.4844,
|
|
"mean_token_accuracy": 0.16980037093162537,
|
|
"num_tokens": 4647975.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.849015378952027,
|
|
"epoch": 2.116818558409279,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004784334416370857,
|
|
"loss": 5.5125,
|
|
"mean_token_accuracy": 0.15812072902917862,
|
|
"num_tokens": 4657555.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.860912609100342,
|
|
"epoch": 2.1209610604805302,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004782967163287231,
|
|
"loss": 5.4232,
|
|
"mean_token_accuracy": 0.1693859726190567,
|
|
"num_tokens": 4667228.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.854128408432007,
|
|
"epoch": 2.1251035625517813,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047815958094866756,
|
|
"loss": 5.5068,
|
|
"mean_token_accuracy": 0.16066872626543044,
|
|
"num_tokens": 4676723.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.834451913833618,
|
|
"epoch": 2.1292460646230325,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004780220357735363,
|
|
"loss": 5.4848,
|
|
"mean_token_accuracy": 0.16301569640636443,
|
|
"num_tokens": 4686241.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.884823274612427,
|
|
"epoch": 2.1333885666942836,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047788408108077294,
|
|
"loss": 5.5521,
|
|
"mean_token_accuracy": 0.1669829785823822,
|
|
"num_tokens": 4695195.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.897109127044677,
|
|
"epoch": 2.1375310687655342,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004777457171486471,
|
|
"loss": 5.5862,
|
|
"mean_token_accuracy": 0.1627011328935623,
|
|
"num_tokens": 4704716.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.881407833099365,
|
|
"epoch": 2.1416735708367853,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004776069442562541,
|
|
"loss": 5.5701,
|
|
"mean_token_accuracy": 0.15754837542772293,
|
|
"num_tokens": 4713720.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.888014125823974,
|
|
"epoch": 2.1458160729080364,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004774677626835138,
|
|
"loss": 5.5318,
|
|
"mean_token_accuracy": 0.1549442321062088,
|
|
"num_tokens": 4722428.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.978774785995483,
|
|
"epoch": 2.1499585749792876,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047732817271117084,
|
|
"loss": 5.536,
|
|
"mean_token_accuracy": 0.15985957831144332,
|
|
"num_tokens": 4732395.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.876013517379761,
|
|
"epoch": 2.1541010770505387,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004771881746207934,
|
|
"loss": 5.529,
|
|
"mean_token_accuracy": 0.16375088393688203,
|
|
"num_tokens": 4741071.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.871488332748413,
|
|
"epoch": 2.1582435791217898,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00047704776869477285,
|
|
"loss": 5.5259,
|
|
"mean_token_accuracy": 0.15932013094425201,
|
|
"num_tokens": 4749876.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.908699417114258,
|
|
"epoch": 2.1623860811930404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00047690695521632344,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.16755755990743637,
|
|
"num_tokens": 4758721.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.8012388229370115,
|
|
"epoch": 2.1665285832642915,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047676573446948114,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.16403038650751114,
|
|
"num_tokens": 4767162.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.957990026473999,
|
|
"epoch": 2.1706710853355426,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047662410673910376,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.17056044489145278,
|
|
"num_tokens": 4776397.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.808328533172608,
|
|
"epoch": 2.1748135874067938,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00047648207231087,
|
|
"loss": 5.4696,
|
|
"mean_token_accuracy": 0.16226063668727875,
|
|
"num_tokens": 4784822.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.8803400039672855,
|
|
"epoch": 2.178956089478045,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004763396314712786,
|
|
"loss": 5.5386,
|
|
"mean_token_accuracy": 0.164871746301651,
|
|
"num_tokens": 4794272.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.7970967292785645,
|
|
"epoch": 2.183098591549296,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004761967845076484,
|
|
"loss": 5.4707,
|
|
"mean_token_accuracy": 0.1630651980638504,
|
|
"num_tokens": 4804314.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.8478696823120115,
|
|
"epoch": 2.1872410936205466,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004760535317081174,
|
|
"loss": 5.4786,
|
|
"mean_token_accuracy": 0.163403283059597,
|
|
"num_tokens": 4812685.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.864224481582641,
|
|
"epoch": 2.1913835956917977,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047590987336164207,
|
|
"loss": 5.552,
|
|
"mean_token_accuracy": 0.16005686074495315,
|
|
"num_tokens": 4821761.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.890404462814331,
|
|
"epoch": 2.195526097763049,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00047576580975799705,
|
|
"loss": 5.5598,
|
|
"mean_token_accuracy": 0.1633346602320671,
|
|
"num_tokens": 4830515.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.911027812957764,
|
|
"epoch": 2.1996685998343,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004756213411877743,
|
|
"loss": 5.5057,
|
|
"mean_token_accuracy": 0.16152726709842682,
|
|
"num_tokens": 4840741.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.786312103271484,
|
|
"epoch": 2.203811101905551,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047547646794238277,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.17090066373348237,
|
|
"num_tokens": 4849571.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.782705068588257,
|
|
"epoch": 2.207953603976802,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00047533119031404757,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.1744443506002426,
|
|
"num_tokens": 4857194.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.780950593948364,
|
|
"epoch": 2.212096106048053,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00047518550859580966,
|
|
"loss": 5.5164,
|
|
"mean_token_accuracy": 0.16455501317977905,
|
|
"num_tokens": 4865894.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.885499715805054,
|
|
"epoch": 2.216238608119304,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004750394230815249,
|
|
"loss": 5.5244,
|
|
"mean_token_accuracy": 0.16542572677135467,
|
|
"num_tokens": 4875131.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.795029067993164,
|
|
"epoch": 2.220381110190555,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00047489293406586375,
|
|
"loss": 5.3891,
|
|
"mean_token_accuracy": 0.17154104858636857,
|
|
"num_tokens": 4884098.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.7773130416870115,
|
|
"epoch": 2.224523612261806,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004747460418443106,
|
|
"loss": 5.4498,
|
|
"mean_token_accuracy": 0.16123902201652526,
|
|
"num_tokens": 4892963.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.887063694000244,
|
|
"epoch": 2.2286661143330573,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00047459874671316305,
|
|
"loss": 5.5169,
|
|
"mean_token_accuracy": 0.16128448247909546,
|
|
"num_tokens": 4902097.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.751895809173584,
|
|
"epoch": 2.2328086164043084,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047445104896953153,
|
|
"loss": 5.4179,
|
|
"mean_token_accuracy": 0.17486145794391633,
|
|
"num_tokens": 4910469.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 6.011729669570923,
|
|
"epoch": 2.236951118475559,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047430294891133846,
|
|
"loss": 5.693,
|
|
"mean_token_accuracy": 0.1579521968960762,
|
|
"num_tokens": 4921024.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.897257661819458,
|
|
"epoch": 2.24109362054681,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004741544468373179,
|
|
"loss": 5.5352,
|
|
"mean_token_accuracy": 0.1622954562306404,
|
|
"num_tokens": 4930297.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.858204364776611,
|
|
"epoch": 2.2452361226180613,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047400554304701474,
|
|
"loss": 5.4703,
|
|
"mean_token_accuracy": 0.16952212154865265,
|
|
"num_tokens": 4938971.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.736092233657837,
|
|
"epoch": 2.2493786246893124,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047385623784078427,
|
|
"loss": 5.4983,
|
|
"mean_token_accuracy": 0.1607481509447098,
|
|
"num_tokens": 4948531.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.897338581085205,
|
|
"epoch": 2.2535211267605635,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004737065315197913,
|
|
"loss": 5.5588,
|
|
"mean_token_accuracy": 0.1676310196518898,
|
|
"num_tokens": 4957430.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.8622315406799315,
|
|
"epoch": 2.2576636288318146,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047355642438600987,
|
|
"loss": 5.5583,
|
|
"mean_token_accuracy": 0.1619584560394287,
|
|
"num_tokens": 4966681.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.813560342788696,
|
|
"epoch": 2.2618061309030653,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004734059167422225,
|
|
"loss": 5.4184,
|
|
"mean_token_accuracy": 0.17226676046848297,
|
|
"num_tokens": 4975327.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.728217124938965,
|
|
"epoch": 2.2659486329743164,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00047325500889201956,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.16976486146450043,
|
|
"num_tokens": 4983741.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.841625738143921,
|
|
"epoch": 2.2700911350455675,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004731037011397986,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.16324040293693542,
|
|
"num_tokens": 4993171.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.934147357940674,
|
|
"epoch": 2.2742336371168186,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047295199379076403,
|
|
"loss": 5.61,
|
|
"mean_token_accuracy": 0.1584983289241791,
|
|
"num_tokens": 5002810.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.811686086654663,
|
|
"epoch": 2.2783761391880697,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000472799887150926,
|
|
"loss": 5.4942,
|
|
"mean_token_accuracy": 0.16332145929336547,
|
|
"num_tokens": 5011875.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.856362628936767,
|
|
"epoch": 2.282518641259321,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004726473815271003,
|
|
"loss": 5.5263,
|
|
"mean_token_accuracy": 0.16980284899473191,
|
|
"num_tokens": 5020780.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.806266975402832,
|
|
"epoch": 2.286661143330572,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047249447722690747,
|
|
"loss": 5.4321,
|
|
"mean_token_accuracy": 0.1647959068417549,
|
|
"num_tokens": 5029896.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.861921787261963,
|
|
"epoch": 2.2908036454018226,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047234117455877215,
|
|
"loss": 5.5179,
|
|
"mean_token_accuracy": 0.16179582476615906,
|
|
"num_tokens": 5038956.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.813634967803955,
|
|
"epoch": 2.2949461474730737,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004721874738319225,
|
|
"loss": 5.4632,
|
|
"mean_token_accuracy": 0.17373612970113755,
|
|
"num_tokens": 5047005.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.804528903961182,
|
|
"epoch": 2.299088649544325,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004720333753563898,
|
|
"loss": 5.526,
|
|
"mean_token_accuracy": 0.15704508125782013,
|
|
"num_tokens": 5056475.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.815530300140381,
|
|
"epoch": 2.303231151615576,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00047187887944300747,
|
|
"loss": 5.5013,
|
|
"mean_token_accuracy": 0.1687375158071518,
|
|
"num_tokens": 5064978.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.865201950073242,
|
|
"epoch": 2.307373653686827,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004717239864034107,
|
|
"loss": 5.5812,
|
|
"mean_token_accuracy": 0.16235170215368272,
|
|
"num_tokens": 5074235.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.82843165397644,
|
|
"epoch": 2.3115161557580777,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047156869655003554,
|
|
"loss": 5.4408,
|
|
"mean_token_accuracy": 0.16791896969079972,
|
|
"num_tokens": 5082386.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.766846418380737,
|
|
"epoch": 2.315658657829329,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00047141301019611875,
|
|
"loss": 5.4334,
|
|
"mean_token_accuracy": 0.1712301880121231,
|
|
"num_tokens": 5090634.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.967849349975586,
|
|
"epoch": 2.31980115990058,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004712569276556967,
|
|
"loss": 5.5878,
|
|
"mean_token_accuracy": 0.16059968620538712,
|
|
"num_tokens": 5099003.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.787600946426392,
|
|
"epoch": 2.323943661971831,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047110044924360484,
|
|
"loss": 5.6732,
|
|
"mean_token_accuracy": 0.15896357521414756,
|
|
"num_tokens": 5108631.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.796855211257935,
|
|
"epoch": 2.328086164043082,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047094357527547725,
|
|
"loss": 5.4452,
|
|
"mean_token_accuracy": 0.166446553170681,
|
|
"num_tokens": 5117309.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.886296510696411,
|
|
"epoch": 2.332228666114333,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004707863060677459,
|
|
"loss": 5.5608,
|
|
"mean_token_accuracy": 0.1704049676656723,
|
|
"num_tokens": 5126305.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.948070526123047,
|
|
"epoch": 2.3363711681855843,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047062864193764,
|
|
"loss": 5.626,
|
|
"mean_token_accuracy": 0.1627499058842659,
|
|
"num_tokens": 5135338.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.821083450317383,
|
|
"epoch": 2.340513670256835,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047047058320318525,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1675426945090294,
|
|
"num_tokens": 5144518.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.848140001296997,
|
|
"epoch": 2.344656172328086,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004703121301832034,
|
|
"loss": 5.6316,
|
|
"mean_token_accuracy": 0.15992611795663833,
|
|
"num_tokens": 5154102.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.895147371292114,
|
|
"epoch": 2.348798674399337,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00047015328319731153,
|
|
"loss": 5.577,
|
|
"mean_token_accuracy": 0.15829345881938933,
|
|
"num_tokens": 5163719.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.83940577507019,
|
|
"epoch": 2.3529411764705883,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004699940425659215,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.1642977774143219,
|
|
"num_tokens": 5173192.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.75920729637146,
|
|
"epoch": 2.3570836785418394,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046983440861023877,
|
|
"loss": 5.478,
|
|
"mean_token_accuracy": 0.17017790228128432,
|
|
"num_tokens": 5182438.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.852911281585693,
|
|
"epoch": 2.36122618061309,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046967438165226275,
|
|
"loss": 5.58,
|
|
"mean_token_accuracy": 0.15865150541067125,
|
|
"num_tokens": 5191595.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.7768883228302,
|
|
"epoch": 2.365368682684341,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004695139620147851,
|
|
"loss": 5.4778,
|
|
"mean_token_accuracy": 0.17112626433372496,
|
|
"num_tokens": 5200174.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.891972255706787,
|
|
"epoch": 2.3695111847555923,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046935315002138994,
|
|
"loss": 5.5743,
|
|
"mean_token_accuracy": 0.16057804375886917,
|
|
"num_tokens": 5210454.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.828851795196533,
|
|
"epoch": 2.3736536868268434,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004691919459964525,
|
|
"loss": 5.5133,
|
|
"mean_token_accuracy": 0.16855535954236983,
|
|
"num_tokens": 5219243.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.6906946182250975,
|
|
"epoch": 2.3777961888980945,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046903035026513894,
|
|
"loss": 5.4128,
|
|
"mean_token_accuracy": 0.1679743379354477,
|
|
"num_tokens": 5228656.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.81590838432312,
|
|
"epoch": 2.3819386909693456,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004688683631534056,
|
|
"loss": 5.493,
|
|
"mean_token_accuracy": 0.1606264054775238,
|
|
"num_tokens": 5237807.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.93833179473877,
|
|
"epoch": 2.3860811930405967,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004687059849879981,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.16789772659540175,
|
|
"num_tokens": 5247432.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.769515132904052,
|
|
"epoch": 2.3902236951118474,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046854321609645093,
|
|
"loss": 5.4293,
|
|
"mean_token_accuracy": 0.1679755300283432,
|
|
"num_tokens": 5256680.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.781009340286255,
|
|
"epoch": 2.3943661971830985,
|
|
"grad_norm": 2.1875,
|
|
"learning_rate": 0.00046838005680708677,
|
|
"loss": 5.5561,
|
|
"mean_token_accuracy": 0.15484578013420106,
|
|
"num_tokens": 5266793.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.785918760299682,
|
|
"epoch": 2.3985086992543496,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046821650744901573,
|
|
"loss": 5.4506,
|
|
"mean_token_accuracy": 0.16751299500465394,
|
|
"num_tokens": 5275028.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.724029159545898,
|
|
"epoch": 2.4026512013256007,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004680525683521347,
|
|
"loss": 5.511,
|
|
"mean_token_accuracy": 0.16009988784790039,
|
|
"num_tokens": 5284162.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.938899421691895,
|
|
"epoch": 2.406793703396852,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004678882398471269,
|
|
"loss": 5.5904,
|
|
"mean_token_accuracy": 0.15319840013980865,
|
|
"num_tokens": 5293263.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.795382261276245,
|
|
"epoch": 2.4109362054681025,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046772352226546066,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.17464249432086945,
|
|
"num_tokens": 5301373.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.81425256729126,
|
|
"epoch": 2.4150787075393536,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004675584159393895,
|
|
"loss": 5.5178,
|
|
"mean_token_accuracy": 0.16518327295780183,
|
|
"num_tokens": 5311009.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.85831036567688,
|
|
"epoch": 2.4192212096106047,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00046739292120195083,
|
|
"loss": 5.5199,
|
|
"mean_token_accuracy": 0.16533831655979156,
|
|
"num_tokens": 5320341.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.816470098495484,
|
|
"epoch": 2.423363711681856,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004672270383869657,
|
|
"loss": 5.4838,
|
|
"mean_token_accuracy": 0.16495863646268843,
|
|
"num_tokens": 5329250.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.707045841217041,
|
|
"epoch": 2.427506213753107,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004670607678290379,
|
|
"loss": 5.4653,
|
|
"mean_token_accuracy": 0.1688676357269287,
|
|
"num_tokens": 5336515.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.742906761169434,
|
|
"epoch": 2.431648715824358,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004668941098635532,
|
|
"loss": 5.5376,
|
|
"mean_token_accuracy": 0.16896287947893143,
|
|
"num_tokens": 5346043.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.862775087356567,
|
|
"epoch": 2.435791217895609,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046672706482667897,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.16607862263917922,
|
|
"num_tokens": 5355124.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.763607597351074,
|
|
"epoch": 2.43993371996686,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004665596330553633,
|
|
"loss": 5.5103,
|
|
"mean_token_accuracy": 0.16795327365398408,
|
|
"num_tokens": 5364556.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.820324087142945,
|
|
"epoch": 2.444076222038111,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046639181488733445,
|
|
"loss": 5.5533,
|
|
"mean_token_accuracy": 0.1670700043439865,
|
|
"num_tokens": 5373778.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.827516508102417,
|
|
"epoch": 2.448218724109362,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004662236106610999,
|
|
"loss": 5.5201,
|
|
"mean_token_accuracy": 0.16433579325675965,
|
|
"num_tokens": 5382633.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.73263373374939,
|
|
"epoch": 2.452361226180613,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00046605502071594604,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16572020649909974,
|
|
"num_tokens": 5391442.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.729014730453491,
|
|
"epoch": 2.4565037282518642,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004658860453919371,
|
|
"loss": 5.4245,
|
|
"mean_token_accuracy": 0.1716168373823166,
|
|
"num_tokens": 5400504.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.748004531860351,
|
|
"epoch": 2.460646230323115,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004657166850299149,
|
|
"loss": 5.4487,
|
|
"mean_token_accuracy": 0.17349344938993455,
|
|
"num_tokens": 5408939.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.76081337928772,
|
|
"epoch": 2.464788732394366,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004655469399714978,
|
|
"loss": 5.4732,
|
|
"mean_token_accuracy": 0.1633571669459343,
|
|
"num_tokens": 5418934.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.719039440155029,
|
|
"epoch": 2.468931234465617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004653768105590799,
|
|
"loss": 5.4851,
|
|
"mean_token_accuracy": 0.16778907030820847,
|
|
"num_tokens": 5427894.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.808207082748413,
|
|
"epoch": 2.4730737365368682,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00046520629713583115,
|
|
"loss": 5.4731,
|
|
"mean_token_accuracy": 0.1672350972890854,
|
|
"num_tokens": 5436830.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.713041210174561,
|
|
"epoch": 2.4772162386081193,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00046503540004569555,
|
|
"loss": 5.4592,
|
|
"mean_token_accuracy": 0.1743247002363205,
|
|
"num_tokens": 5445504.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.789522886276245,
|
|
"epoch": 2.4813587406793705,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046486411963339125,
|
|
"loss": 5.5394,
|
|
"mean_token_accuracy": 0.15771088749170303,
|
|
"num_tokens": 5455378.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.846792459487915,
|
|
"epoch": 2.4855012427506216,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046469245624440955,
|
|
"loss": 5.5936,
|
|
"mean_token_accuracy": 0.16458921432495116,
|
|
"num_tokens": 5465334.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 2.4855012427506216,
|
|
"eval_entropy": 5.656050709519051,
|
|
"eval_loss": 5.90228796005249,
|
|
"eval_mean_token_accuracy": 0.15245503703477795,
|
|
"eval_num_tokens": 5465334.0,
|
|
"eval_runtime": 2.1213,
|
|
"eval_samples_per_second": 1766.397,
|
|
"eval_steps_per_second": 221.094,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.914564323425293,
|
|
"epoch": 2.4896437448218722,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046452041022501423,
|
|
"loss": 5.5795,
|
|
"mean_token_accuracy": 0.15947357565164566,
|
|
"num_tokens": 5475701.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.8098790645599365,
|
|
"epoch": 2.4937862468931233,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004643479819222411,
|
|
"loss": 5.4724,
|
|
"mean_token_accuracy": 0.1679657831788063,
|
|
"num_tokens": 5485244.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.75299220085144,
|
|
"epoch": 2.4979287489643744,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046417517168389664,
|
|
"loss": 5.4446,
|
|
"mean_token_accuracy": 0.1756052017211914,
|
|
"num_tokens": 5493587.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.75340085029602,
|
|
"epoch": 2.5020712510356256,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004640019798585581,
|
|
"loss": 5.5658,
|
|
"mean_token_accuracy": 0.15904781520366668,
|
|
"num_tokens": 5503117.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.897297000885009,
|
|
"epoch": 2.5062137531068767,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00046382840679557233,
|
|
"loss": 5.5242,
|
|
"mean_token_accuracy": 0.16687027961015702,
|
|
"num_tokens": 5512742.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.802408981323242,
|
|
"epoch": 2.5103562551781273,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046365445284505516,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16409519016742707,
|
|
"num_tokens": 5521862.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.728432035446167,
|
|
"epoch": 2.5144987572493784,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004634801183578907,
|
|
"loss": 5.4693,
|
|
"mean_token_accuracy": 0.16907058358192445,
|
|
"num_tokens": 5531244.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.818651151657105,
|
|
"epoch": 2.5186412593206295,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046330540368573063,
|
|
"loss": 5.533,
|
|
"mean_token_accuracy": 0.16057599037885667,
|
|
"num_tokens": 5540786.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.834894847869873,
|
|
"epoch": 2.5227837613918807,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046313030918099365,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.16715315133333206,
|
|
"num_tokens": 5549961.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.8362329483032225,
|
|
"epoch": 2.5269262634631318,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00046295483519686437,
|
|
"loss": 5.4637,
|
|
"mean_token_accuracy": 0.1704350382089615,
|
|
"num_tokens": 5558941.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.780770015716553,
|
|
"epoch": 2.531068765534383,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00046277898208729306,
|
|
"loss": 5.4687,
|
|
"mean_token_accuracy": 0.17228198945522308,
|
|
"num_tokens": 5567630.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.76056432723999,
|
|
"epoch": 2.535211267605634,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004626027502069947,
|
|
"loss": 5.4291,
|
|
"mean_token_accuracy": 0.17223766446113586,
|
|
"num_tokens": 5576430.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.762398624420166,
|
|
"epoch": 2.539353769676885,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046242613991144814,
|
|
"loss": 5.5425,
|
|
"mean_token_accuracy": 0.16799665689468385,
|
|
"num_tokens": 5584785.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.681229543685913,
|
|
"epoch": 2.5434962717481358,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00046224915155689586,
|
|
"loss": 5.463,
|
|
"mean_token_accuracy": 0.16333075165748595,
|
|
"num_tokens": 5594583.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.840403652191162,
|
|
"epoch": 2.547638773819387,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046207178550034244,
|
|
"loss": 5.4168,
|
|
"mean_token_accuracy": 0.17153728008270264,
|
|
"num_tokens": 5603498.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.838770627975464,
|
|
"epoch": 2.551781275890638,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004618940420995547,
|
|
"loss": 5.5674,
|
|
"mean_token_accuracy": 0.16025356948375702,
|
|
"num_tokens": 5613101.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.832324838638305,
|
|
"epoch": 2.555923777961889,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004617159217130606,
|
|
"loss": 5.5458,
|
|
"mean_token_accuracy": 0.15903787612915038,
|
|
"num_tokens": 5621821.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.803797245025635,
|
|
"epoch": 2.5600662800331397,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004615374247001483,
|
|
"loss": 5.5568,
|
|
"mean_token_accuracy": 0.16145259216427804,
|
|
"num_tokens": 5631006.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.798919773101806,
|
|
"epoch": 2.564208782104391,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004613585514208659,
|
|
"loss": 5.5478,
|
|
"mean_token_accuracy": 0.15834410786628722,
|
|
"num_tokens": 5640159.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.758146095275879,
|
|
"epoch": 2.568351284175642,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00046117930223602016,
|
|
"loss": 5.374,
|
|
"mean_token_accuracy": 0.17416420131921767,
|
|
"num_tokens": 5648369.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.771967172622681,
|
|
"epoch": 2.572493786246893,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004609996775071765,
|
|
"loss": 5.4613,
|
|
"mean_token_accuracy": 0.16731293201446534,
|
|
"num_tokens": 5657669.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.789367580413819,
|
|
"epoch": 2.576636288318144,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004608196775966575,
|
|
"loss": 5.5049,
|
|
"mean_token_accuracy": 0.16762578785419463,
|
|
"num_tokens": 5666601.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.728751134872437,
|
|
"epoch": 2.5807787903893953,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046063930286754267,
|
|
"loss": 5.4399,
|
|
"mean_token_accuracy": 0.16545719504356385,
|
|
"num_tokens": 5675243.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.699541187286377,
|
|
"epoch": 2.5849212924606464,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00046045855368366756,
|
|
"loss": 5.4616,
|
|
"mean_token_accuracy": 0.1634269416332245,
|
|
"num_tokens": 5683646.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.824839019775391,
|
|
"epoch": 2.5890637945318975,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000460277430409623,
|
|
"loss": 5.5011,
|
|
"mean_token_accuracy": 0.17967819571495056,
|
|
"num_tokens": 5693069.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.706517457962036,
|
|
"epoch": 2.593206296603148,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046009593341075444,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.17086281776428222,
|
|
"num_tokens": 5701527.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.702413845062256,
|
|
"epoch": 2.5973487986743993,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004599140630531612,
|
|
"loss": 5.5286,
|
|
"mean_token_accuracy": 0.16691497564315796,
|
|
"num_tokens": 5710379.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.869003677368164,
|
|
"epoch": 2.6014913007456504,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004597318197036956,
|
|
"loss": 5.449,
|
|
"mean_token_accuracy": 0.16944495141506194,
|
|
"num_tokens": 5719217.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.763718891143799,
|
|
"epoch": 2.6056338028169015,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004595492037299624,
|
|
"loss": 5.5381,
|
|
"mean_token_accuracy": 0.16387716680765152,
|
|
"num_tokens": 5728331.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.773723316192627,
|
|
"epoch": 2.6097763048881526,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00045936621550031806,
|
|
"loss": 5.4953,
|
|
"mean_token_accuracy": 0.16249915808439255,
|
|
"num_tokens": 5737696.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.85468635559082,
|
|
"epoch": 2.6139188069594033,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045918285538386973,
|
|
"loss": 5.5652,
|
|
"mean_token_accuracy": 0.17016023844480516,
|
|
"num_tokens": 5746191.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.8019898414611815,
|
|
"epoch": 2.6180613090306544,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00045899912375047485,
|
|
"loss": 5.5593,
|
|
"mean_token_accuracy": 0.16703492477536203,
|
|
"num_tokens": 5754824.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.787224292755127,
|
|
"epoch": 2.6222038111019055,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045881502097074023,
|
|
"loss": 5.523,
|
|
"mean_token_accuracy": 0.16068582385778427,
|
|
"num_tokens": 5764863.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.750904369354248,
|
|
"epoch": 2.6263463131731566,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004586305474160212,
|
|
"loss": 5.5372,
|
|
"mean_token_accuracy": 0.15608163475990294,
|
|
"num_tokens": 5774273.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.754891872406006,
|
|
"epoch": 2.6304888152444077,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045844570345842116,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.1675620496273041,
|
|
"num_tokens": 5784085.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.759196949005127,
|
|
"epoch": 2.634631317315659,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004582604894707906,
|
|
"loss": 5.5189,
|
|
"mean_token_accuracy": 0.1714040830731392,
|
|
"num_tokens": 5793921.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.770182132720947,
|
|
"epoch": 2.63877381938691,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045807490582672634,
|
|
"loss": 5.4755,
|
|
"mean_token_accuracy": 0.15773507803678513,
|
|
"num_tokens": 5803902.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.754958963394165,
|
|
"epoch": 2.6429163214581606,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045788895290057083,
|
|
"loss": 5.4088,
|
|
"mean_token_accuracy": 0.17135379761457442,
|
|
"num_tokens": 5812089.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.83141303062439,
|
|
"epoch": 2.6470588235294117,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045770263106741137,
|
|
"loss": 5.5798,
|
|
"mean_token_accuracy": 0.1662437751889229,
|
|
"num_tokens": 5821072.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.762010908126831,
|
|
"epoch": 2.651201325600663,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004575159407030797,
|
|
"loss": 5.4075,
|
|
"mean_token_accuracy": 0.16858580559492112,
|
|
"num_tokens": 5829725.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.651156377792359,
|
|
"epoch": 2.655343827671914,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004573288821841505,
|
|
"loss": 5.4684,
|
|
"mean_token_accuracy": 0.170504392683506,
|
|
"num_tokens": 5838153.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.721271610260009,
|
|
"epoch": 2.659486329743165,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004571414558879413,
|
|
"loss": 5.4157,
|
|
"mean_token_accuracy": 0.16800788789987564,
|
|
"num_tokens": 5847270.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.768667364120484,
|
|
"epoch": 2.6636288318144157,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004569536621925114,
|
|
"loss": 5.5346,
|
|
"mean_token_accuracy": 0.15528512746095657,
|
|
"num_tokens": 5855954.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.752230453491211,
|
|
"epoch": 2.667771333885667,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004567655014766612,
|
|
"loss": 5.4526,
|
|
"mean_token_accuracy": 0.16863793283700942,
|
|
"num_tokens": 5864435.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.756985664367676,
|
|
"epoch": 2.671913835956918,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004565769741199314,
|
|
"loss": 5.5205,
|
|
"mean_token_accuracy": 0.16575470119714736,
|
|
"num_tokens": 5873964.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.856758451461792,
|
|
"epoch": 2.676056338028169,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045638808050260237,
|
|
"loss": 5.4701,
|
|
"mean_token_accuracy": 0.16698733419179917,
|
|
"num_tokens": 5882738.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.710201787948608,
|
|
"epoch": 2.68019884009942,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045619882100569317,
|
|
"loss": 5.5967,
|
|
"mean_token_accuracy": 0.16321074962615967,
|
|
"num_tokens": 5891749.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.801533222198486,
|
|
"epoch": 2.684341342170671,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004560091960109608,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.15850342363119124,
|
|
"num_tokens": 5900551.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.81293306350708,
|
|
"epoch": 2.6884838442419223,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004558192059008996,
|
|
"loss": 5.5384,
|
|
"mean_token_accuracy": 0.1598558768630028,
|
|
"num_tokens": 5909254.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.738259124755859,
|
|
"epoch": 2.692626346313173,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004556288510587406,
|
|
"loss": 5.4907,
|
|
"mean_token_accuracy": 0.16425517126917838,
|
|
"num_tokens": 5918357.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.800414085388184,
|
|
"epoch": 2.696768848384424,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00045543813186845004,
|
|
"loss": 5.4905,
|
|
"mean_token_accuracy": 0.1593318447470665,
|
|
"num_tokens": 5927742.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.779916143417358,
|
|
"epoch": 2.700911350455675,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004552470487147294,
|
|
"loss": 5.5725,
|
|
"mean_token_accuracy": 0.16214122474193574,
|
|
"num_tokens": 5937025.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.8742701530456545,
|
|
"epoch": 2.7050538525269263,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045505560198301443,
|
|
"loss": 5.5591,
|
|
"mean_token_accuracy": 0.16014052033424378,
|
|
"num_tokens": 5946176.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.811063575744629,
|
|
"epoch": 2.7091963545981774,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00045486379205947396,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.1603608623147011,
|
|
"num_tokens": 5955550.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.741652774810791,
|
|
"epoch": 2.713338856669428,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004546716193310098,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.17048551887273788,
|
|
"num_tokens": 5964467.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.708764839172363,
|
|
"epoch": 2.717481358740679,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000454479084185255,
|
|
"loss": 5.4733,
|
|
"mean_token_accuracy": 0.16376140117645263,
|
|
"num_tokens": 5973906.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.813305187225342,
|
|
"epoch": 2.7216238608119303,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004542861870105743,
|
|
"loss": 5.5296,
|
|
"mean_token_accuracy": 0.16012001484632493,
|
|
"num_tokens": 5983701.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.748534345626831,
|
|
"epoch": 2.7257663628831814,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045409292819606224,
|
|
"loss": 5.4868,
|
|
"mean_token_accuracy": 0.1683947667479515,
|
|
"num_tokens": 5993367.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.761485385894775,
|
|
"epoch": 2.7299088649544325,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045389930813154297,
|
|
"loss": 5.4473,
|
|
"mean_token_accuracy": 0.164425852894783,
|
|
"num_tokens": 6003752.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.813571357727051,
|
|
"epoch": 2.7340513670256836,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004537053272075693,
|
|
"loss": 5.5171,
|
|
"mean_token_accuracy": 0.16819205284118652,
|
|
"num_tokens": 6012486.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.705581426620483,
|
|
"epoch": 2.7381938690969347,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045351098581542204,
|
|
"loss": 5.45,
|
|
"mean_token_accuracy": 0.1731782466173172,
|
|
"num_tokens": 6020742.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.764031171798706,
|
|
"epoch": 2.742336371168186,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004533162843471089,
|
|
"loss": 5.4962,
|
|
"mean_token_accuracy": 0.16076465398073198,
|
|
"num_tokens": 6030248.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.752740144729614,
|
|
"epoch": 2.7464788732394365,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004531212231953641,
|
|
"loss": 5.5274,
|
|
"mean_token_accuracy": 0.1619992196559906,
|
|
"num_tokens": 6039293.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.764484214782715,
|
|
"epoch": 2.7506213753106876,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004529258027536473,
|
|
"loss": 5.3994,
|
|
"mean_token_accuracy": 0.1740379586815834,
|
|
"num_tokens": 6048081.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.773984909057617,
|
|
"epoch": 2.7547638773819387,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004527300234161428,
|
|
"loss": 5.5525,
|
|
"mean_token_accuracy": 0.16989483833312988,
|
|
"num_tokens": 6057549.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.801596546173096,
|
|
"epoch": 2.75890637945319,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004525338855777591,
|
|
"loss": 5.5442,
|
|
"mean_token_accuracy": 0.15882744565606116,
|
|
"num_tokens": 6067372.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.7431878566741945,
|
|
"epoch": 2.7630488815244405,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00045233738963412746,
|
|
"loss": 5.4319,
|
|
"mean_token_accuracy": 0.172615684568882,
|
|
"num_tokens": 6075532.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.658958435058594,
|
|
"epoch": 2.7671913835956916,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045214053598160173,
|
|
"loss": 5.428,
|
|
"mean_token_accuracy": 0.16530137956142427,
|
|
"num_tokens": 6084389.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.706263065338135,
|
|
"epoch": 2.7713338856669427,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045194332501725725,
|
|
"loss": 5.4516,
|
|
"mean_token_accuracy": 0.17387880086898805,
|
|
"num_tokens": 6093536.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.805906820297241,
|
|
"epoch": 2.775476387738194,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045174575713889014,
|
|
"loss": 5.5156,
|
|
"mean_token_accuracy": 0.16971641331911086,
|
|
"num_tokens": 6102677.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.7577433586120605,
|
|
"epoch": 2.779618889809445,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004515478327450164,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.15872112661600113,
|
|
"num_tokens": 6112430.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.798976182937622,
|
|
"epoch": 2.783761391880696,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00045134955223487093,
|
|
"loss": 5.4679,
|
|
"mean_token_accuracy": 0.16966949105262757,
|
|
"num_tokens": 6121408.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.688184547424316,
|
|
"epoch": 2.787903893951947,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045115091600840757,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.16572752445936204,
|
|
"num_tokens": 6131339.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.788509750366211,
|
|
"epoch": 2.7920463960231983,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00045095192446629697,
|
|
"loss": 5.4849,
|
|
"mean_token_accuracy": 0.17105671763420105,
|
|
"num_tokens": 6140590.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.873730754852295,
|
|
"epoch": 2.796188898094449,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000450752578009927,
|
|
"loss": 5.5617,
|
|
"mean_token_accuracy": 0.16861443668603898,
|
|
"num_tokens": 6149958.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.706935691833496,
|
|
"epoch": 2.8003314001657,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045055287704140115,
|
|
"loss": 5.4164,
|
|
"mean_token_accuracy": 0.16622787863016128,
|
|
"num_tokens": 6159411.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.739952230453492,
|
|
"epoch": 2.804473902236951,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004503528219635381,
|
|
"loss": 5.4969,
|
|
"mean_token_accuracy": 0.16039616614580154,
|
|
"num_tokens": 6169264.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.7836833000183105,
|
|
"epoch": 2.8086164043082023,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004501524131798709,
|
|
"loss": 5.479,
|
|
"mean_token_accuracy": 0.1654949814081192,
|
|
"num_tokens": 6178374.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.787517404556274,
|
|
"epoch": 2.812758906379453,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000449951651094646,
|
|
"loss": 5.4675,
|
|
"mean_token_accuracy": 0.16262983530759811,
|
|
"num_tokens": 6186918.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.6543309688568115,
|
|
"epoch": 2.816901408450704,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044975053611282217,
|
|
"loss": 5.5311,
|
|
"mean_token_accuracy": 0.1693658247590065,
|
|
"num_tokens": 6196400.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.6317651748657225,
|
|
"epoch": 2.821043910521955,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004495490686400706,
|
|
"loss": 5.3787,
|
|
"mean_token_accuracy": 0.16933436095714569,
|
|
"num_tokens": 6204849.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.752957725524903,
|
|
"epoch": 2.8251864125932062,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044934724908277313,
|
|
"loss": 5.4714,
|
|
"mean_token_accuracy": 0.16995579451322557,
|
|
"num_tokens": 6214121.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.699260520935058,
|
|
"epoch": 2.8293289146644574,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044914507784802184,
|
|
"loss": 5.4658,
|
|
"mean_token_accuracy": 0.16969568133354188,
|
|
"num_tokens": 6223163.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.726906681060791,
|
|
"epoch": 2.8334714167357085,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004489425553436182,
|
|
"loss": 5.5226,
|
|
"mean_token_accuracy": 0.16584552228450775,
|
|
"num_tokens": 6231581.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.822454357147217,
|
|
"epoch": 2.8376139188069596,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00044873968197807213,
|
|
"loss": 5.5723,
|
|
"mean_token_accuracy": 0.16670656055212021,
|
|
"num_tokens": 6240015.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.813776588439941,
|
|
"epoch": 2.8417564208782107,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044853645816060156,
|
|
"loss": 5.5837,
|
|
"mean_token_accuracy": 0.16062843948602676,
|
|
"num_tokens": 6249083.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.8432635307312015,
|
|
"epoch": 2.8458989229494613,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044833288430113104,
|
|
"loss": 5.5411,
|
|
"mean_token_accuracy": 0.17005591839551926,
|
|
"num_tokens": 6258798.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.751342487335205,
|
|
"epoch": 2.8500414250207124,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044812896081029136,
|
|
"loss": 5.3838,
|
|
"mean_token_accuracy": 0.17221174538135528,
|
|
"num_tokens": 6267819.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.757843351364135,
|
|
"epoch": 2.8541839270919636,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004479246880994183,
|
|
"loss": 5.5119,
|
|
"mean_token_accuracy": 0.16272529363632202,
|
|
"num_tokens": 6276915.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.77875394821167,
|
|
"epoch": 2.8583264291632147,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004477200665805525,
|
|
"loss": 5.5101,
|
|
"mean_token_accuracy": 0.16577985435724257,
|
|
"num_tokens": 6285880.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.783086729049683,
|
|
"epoch": 2.8624689312344658,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00044751509666643777,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.1583674356341362,
|
|
"num_tokens": 6295408.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.759187269210815,
|
|
"epoch": 2.8666114333057164,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00044730977877052084,
|
|
"loss": 5.3824,
|
|
"mean_token_accuracy": 0.1693664237856865,
|
|
"num_tokens": 6304110.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.783472061157227,
|
|
"epoch": 2.8707539353769675,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00044710411330695045,
|
|
"loss": 5.5399,
|
|
"mean_token_accuracy": 0.16439478397369384,
|
|
"num_tokens": 6312577.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.891426753997803,
|
|
"epoch": 2.8748964374482187,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00044689810069057615,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.1536042645573616,
|
|
"num_tokens": 6321766.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.811576461791992,
|
|
"epoch": 2.8790389395194698,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004466917413369479,
|
|
"loss": 5.5639,
|
|
"mean_token_accuracy": 0.16207059174776078,
|
|
"num_tokens": 6330327.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.759015989303589,
|
|
"epoch": 2.883181441590721,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004464850356623152,
|
|
"loss": 5.4855,
|
|
"mean_token_accuracy": 0.16795404702425004,
|
|
"num_tokens": 6339596.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.718622493743896,
|
|
"epoch": 2.887323943661972,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00044627798408362597,
|
|
"loss": 5.404,
|
|
"mean_token_accuracy": 0.17235597223043442,
|
|
"num_tokens": 6348080.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.782154560089111,
|
|
"epoch": 2.891466445733223,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004460705870185258,
|
|
"loss": 5.5167,
|
|
"mean_token_accuracy": 0.16079007238149642,
|
|
"num_tokens": 6357725.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.697278308868408,
|
|
"epoch": 2.8956089478044738,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004458628448853572,
|
|
"loss": 5.4599,
|
|
"mean_token_accuracy": 0.17365020364522935,
|
|
"num_tokens": 6366821.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.884949445724487,
|
|
"epoch": 2.899751449875725,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004456547581031589,
|
|
"loss": 5.5218,
|
|
"mean_token_accuracy": 0.16513780802488326,
|
|
"num_tokens": 6375641.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 2.899751449875725,
|
|
"eval_entropy": 5.4757287995393344,
|
|
"eval_loss": 5.827961444854736,
|
|
"eval_mean_token_accuracy": 0.1573650076477004,
|
|
"eval_num_tokens": 6375641.0,
|
|
"eval_runtime": 2.123,
|
|
"eval_samples_per_second": 1764.936,
|
|
"eval_steps_per_second": 220.911,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.659141874313354,
|
|
"epoch": 2.903893951946976,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004454463270916646,
|
|
"loss": 5.3878,
|
|
"mean_token_accuracy": 0.17062876969575883,
|
|
"num_tokens": 6384596.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.883829498291016,
|
|
"epoch": 2.908036454018227,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004452375522713023,
|
|
"loss": 5.7511,
|
|
"mean_token_accuracy": 0.15101574063301088,
|
|
"num_tokens": 6395048.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.7422182083129885,
|
|
"epoch": 2.912178956089478,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004450284340631938,
|
|
"loss": 5.554,
|
|
"mean_token_accuracy": 0.16014589816331865,
|
|
"num_tokens": 6404828.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.788592100143433,
|
|
"epoch": 2.916321458160729,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044481897288915334,
|
|
"loss": 5.4429,
|
|
"mean_token_accuracy": 0.16897255778312684,
|
|
"num_tokens": 6414670.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.568955516815185,
|
|
"epoch": 2.92046396023198,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044460916917168697,
|
|
"loss": 5.3698,
|
|
"mean_token_accuracy": 0.17270153462886811,
|
|
"num_tokens": 6423446.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.623572492599488,
|
|
"epoch": 2.924606462303231,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004443990233339918,
|
|
"loss": 5.4617,
|
|
"mean_token_accuracy": 0.16115631014108658,
|
|
"num_tokens": 6433412.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.774356079101563,
|
|
"epoch": 2.928748964374482,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004441885357999548,
|
|
"loss": 5.4311,
|
|
"mean_token_accuracy": 0.17228814363479614,
|
|
"num_tokens": 6443520.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.800971984863281,
|
|
"epoch": 2.9328914664457333,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004439777069941524,
|
|
"loss": 5.5403,
|
|
"mean_token_accuracy": 0.1595218874514103,
|
|
"num_tokens": 6452933.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.662924432754517,
|
|
"epoch": 2.9370339685169844,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044376653734184935,
|
|
"loss": 5.3565,
|
|
"mean_token_accuracy": 0.17528989911079407,
|
|
"num_tokens": 6462113.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.623508501052856,
|
|
"epoch": 2.9411764705882355,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004435550272689979,
|
|
"loss": 5.4209,
|
|
"mean_token_accuracy": 0.17549460828304292,
|
|
"num_tokens": 6471411.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.786066102981567,
|
|
"epoch": 2.945318972659486,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044334317720223706,
|
|
"loss": 5.5235,
|
|
"mean_token_accuracy": 0.16949946731328963,
|
|
"num_tokens": 6480682.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.811757326126099,
|
|
"epoch": 2.9494614747307373,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00044313098756889154,
|
|
"loss": 5.562,
|
|
"mean_token_accuracy": 0.16019560992717743,
|
|
"num_tokens": 6490614.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.7563964366912845,
|
|
"epoch": 2.9536039768019884,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004429184587969708,
|
|
"loss": 5.4238,
|
|
"mean_token_accuracy": 0.16828618198633194,
|
|
"num_tokens": 6499079.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.766819000244141,
|
|
"epoch": 2.9577464788732395,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004427055913151689,
|
|
"loss": 5.5258,
|
|
"mean_token_accuracy": 0.16020953357219697,
|
|
"num_tokens": 6508556.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.842855978012085,
|
|
"epoch": 2.9618889809444906,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004424923855528626,
|
|
"loss": 5.537,
|
|
"mean_token_accuracy": 0.16368937641382217,
|
|
"num_tokens": 6517934.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.72537055015564,
|
|
"epoch": 2.9660314830157413,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004422788419401114,
|
|
"loss": 5.4285,
|
|
"mean_token_accuracy": 0.1749083310365677,
|
|
"num_tokens": 6526995.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.732391834259033,
|
|
"epoch": 2.9701739850869924,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00044206496090765595,
|
|
"loss": 5.4847,
|
|
"mean_token_accuracy": 0.1568613499403,
|
|
"num_tokens": 6535264.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.786244201660156,
|
|
"epoch": 2.9743164871582435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044185074288691776,
|
|
"loss": 5.3818,
|
|
"mean_token_accuracy": 0.17809101194143295,
|
|
"num_tokens": 6544498.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.660001802444458,
|
|
"epoch": 2.9784589892294946,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00044163618830999794,
|
|
"loss": 5.4901,
|
|
"mean_token_accuracy": 0.1674646705389023,
|
|
"num_tokens": 6554761.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.766847324371338,
|
|
"epoch": 2.9826014913007457,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00044142129760967643,
|
|
"loss": 5.5421,
|
|
"mean_token_accuracy": 0.15879848450422288,
|
|
"num_tokens": 6564039.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.785932493209839,
|
|
"epoch": 2.986743993371997,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004412060712194115,
|
|
"loss": 5.504,
|
|
"mean_token_accuracy": 0.1650686576962471,
|
|
"num_tokens": 6572559.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.748941087722779,
|
|
"epoch": 2.990886495443248,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004409905095733381,
|
|
"loss": 5.4982,
|
|
"mean_token_accuracy": 0.16846567690372466,
|
|
"num_tokens": 6581621.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.6914866924285885,
|
|
"epoch": 2.995028997514499,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044077461310626764,
|
|
"loss": 5.4583,
|
|
"mean_token_accuracy": 0.16134192273020745,
|
|
"num_tokens": 6590353.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.687563180923462,
|
|
"epoch": 2.9991714995857497,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000440558382253687,
|
|
"loss": 5.4645,
|
|
"mean_token_accuracy": 0.16758733093738556,
|
|
"num_tokens": 6598822.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.7134661197662355,
|
|
"epoch": 3.003314001657001,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004403418174517573,
|
|
"loss": 5.2483,
|
|
"mean_token_accuracy": 0.17731166034936904,
|
|
"num_tokens": 6606728.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.763548755645752,
|
|
"epoch": 3.007456503728252,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044012491913731353,
|
|
"loss": 5.1834,
|
|
"mean_token_accuracy": 0.1845538094639778,
|
|
"num_tokens": 6616226.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.647686576843261,
|
|
"epoch": 3.011599005799503,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004399076877478632,
|
|
"loss": 5.0478,
|
|
"mean_token_accuracy": 0.19241824746131897,
|
|
"num_tokens": 6624801.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.759692573547364,
|
|
"epoch": 3.015741507870754,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004396901237215858,
|
|
"loss": 5.2235,
|
|
"mean_token_accuracy": 0.17856706976890563,
|
|
"num_tokens": 6633043.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.704078674316406,
|
|
"epoch": 3.019884009942005,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00043947222749733173,
|
|
"loss": 5.1763,
|
|
"mean_token_accuracy": 0.18094127923250197,
|
|
"num_tokens": 6641197.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.772066402435303,
|
|
"epoch": 3.024026512013256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00043925399951462153,
|
|
"loss": 5.1956,
|
|
"mean_token_accuracy": 0.1870351865887642,
|
|
"num_tokens": 6650411.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5801839351654055,
|
|
"epoch": 3.028169014084507,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004390354402136449,
|
|
"loss": 5.0965,
|
|
"mean_token_accuracy": 0.19041540175676347,
|
|
"num_tokens": 6659405.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.688499450683594,
|
|
"epoch": 3.032311516155758,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004388165500352597,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.18378936201334,
|
|
"num_tokens": 6667701.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.690164089202881,
|
|
"epoch": 3.036454018227009,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004385973294209915,
|
|
"loss": 5.1994,
|
|
"mean_token_accuracy": 0.1872095689177513,
|
|
"num_tokens": 6676801.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.610604619979858,
|
|
"epoch": 3.0405965202982603,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004383777788130321,
|
|
"loss": 5.0724,
|
|
"mean_token_accuracy": 0.19022455364465712,
|
|
"num_tokens": 6686005.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.614531183242798,
|
|
"epoch": 3.044739022369511,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004381578986542393,
|
|
"loss": 5.1014,
|
|
"mean_token_accuracy": 0.1851173833012581,
|
|
"num_tokens": 6694884.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.6209056854248045,
|
|
"epoch": 3.048881524440762,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004379376893881352,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.18749409765005112,
|
|
"num_tokens": 6703476.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.7340391159057615,
|
|
"epoch": 3.053024026512013,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004377171514589059,
|
|
"loss": 5.2395,
|
|
"mean_token_accuracy": 0.18214525580406188,
|
|
"num_tokens": 6712576.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.548529958724975,
|
|
"epoch": 3.0571665285832643,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004374962853114007,
|
|
"loss": 5.0604,
|
|
"mean_token_accuracy": 0.19115135669708253,
|
|
"num_tokens": 6721532.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.665778398513794,
|
|
"epoch": 3.0613090306545154,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004372750913911306,
|
|
"loss": 5.1572,
|
|
"mean_token_accuracy": 0.18904639780521393,
|
|
"num_tokens": 6730055.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.575237274169922,
|
|
"epoch": 3.0654515327257665,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004370535701442679,
|
|
"loss": 5.1624,
|
|
"mean_token_accuracy": 0.1865699902176857,
|
|
"num_tokens": 6739310.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.719792079925537,
|
|
"epoch": 3.069594034797017,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043683172201764537,
|
|
"loss": 5.2491,
|
|
"mean_token_accuracy": 0.17855707108974456,
|
|
"num_tokens": 6748976.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.6290325164794925,
|
|
"epoch": 3.0737365368682683,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004366095474587547,
|
|
"loss": 5.0998,
|
|
"mean_token_accuracy": 0.18970801681280136,
|
|
"num_tokens": 6758043.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.626490688323974,
|
|
"epoch": 3.0778790389395194,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043638704691574646,
|
|
"loss": 5.1721,
|
|
"mean_token_accuracy": 0.18541784286499025,
|
|
"num_tokens": 6767554.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.719451856613159,
|
|
"epoch": 3.0820215410107705,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004361642208374283,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.1812313124537468,
|
|
"num_tokens": 6776161.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.646106100082397,
|
|
"epoch": 3.0861640430820216,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043594106967326495,
|
|
"loss": 5.1188,
|
|
"mean_token_accuracy": 0.19058042019605637,
|
|
"num_tokens": 6785371.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.6641051292419435,
|
|
"epoch": 3.0903065451532727,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043571759387337665,
|
|
"loss": 5.1419,
|
|
"mean_token_accuracy": 0.18899417370557786,
|
|
"num_tokens": 6795242.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.659932279586792,
|
|
"epoch": 3.0944490472245234,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004354937938885385,
|
|
"loss": 5.2136,
|
|
"mean_token_accuracy": 0.18589263409376144,
|
|
"num_tokens": 6805423.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.683835744857788,
|
|
"epoch": 3.0985915492957745,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004352696701701796,
|
|
"loss": 5.1512,
|
|
"mean_token_accuracy": 0.19135665148496628,
|
|
"num_tokens": 6814377.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.621399831771851,
|
|
"epoch": 3.1027340513670256,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004350452231703819,
|
|
"loss": 5.2155,
|
|
"mean_token_accuracy": 0.18173784464597703,
|
|
"num_tokens": 6824025.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.61470217704773,
|
|
"epoch": 3.1068765534382767,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00043482045334187954,
|
|
"loss": 5.1384,
|
|
"mean_token_accuracy": 0.19231966584920884,
|
|
"num_tokens": 6833071.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.5463276386260985,
|
|
"epoch": 3.111019055509528,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00043459536113805785,
|
|
"loss": 5.108,
|
|
"mean_token_accuracy": 0.18516573756933213,
|
|
"num_tokens": 6841983.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.5930225372314455,
|
|
"epoch": 3.115161557580779,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00043436994701295237,
|
|
"loss": 5.1077,
|
|
"mean_token_accuracy": 0.1899734452366829,
|
|
"num_tokens": 6851436.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.604737186431885,
|
|
"epoch": 3.1193040596520296,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00043414421142124804,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.18167357444763182,
|
|
"num_tokens": 6861810.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.647305679321289,
|
|
"epoch": 3.1234465617232807,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00043391815481827814,
|
|
"loss": 5.0811,
|
|
"mean_token_accuracy": 0.19235028475522994,
|
|
"num_tokens": 6870418.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.53998556137085,
|
|
"epoch": 3.127589063794532,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004336917776600237,
|
|
"loss": 5.0649,
|
|
"mean_token_accuracy": 0.19226059168577195,
|
|
"num_tokens": 6879419.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.574113082885742,
|
|
"epoch": 3.131731565865783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004334650804031122,
|
|
"loss": 5.2109,
|
|
"mean_token_accuracy": 0.18221246004104613,
|
|
"num_tokens": 6888768.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.668018865585327,
|
|
"epoch": 3.135874067937034,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004332380635048165,
|
|
"loss": 5.1483,
|
|
"mean_token_accuracy": 0.1864844635128975,
|
|
"num_tokens": 6897133.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.688458251953125,
|
|
"epoch": 3.140016570008285,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043301072742305474,
|
|
"loss": 5.1605,
|
|
"mean_token_accuracy": 0.1893605798482895,
|
|
"num_tokens": 6904976.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.643799734115601,
|
|
"epoch": 3.1441590720795363,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004327830726163886,
|
|
"loss": 5.178,
|
|
"mean_token_accuracy": 0.1901219218969345,
|
|
"num_tokens": 6915138.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.668399381637573,
|
|
"epoch": 3.148301574150787,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0004325550995440226,
|
|
"loss": 5.1442,
|
|
"mean_token_accuracy": 0.1849392205476761,
|
|
"num_tokens": 6923962.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.5434407711029055,
|
|
"epoch": 3.152444076222038,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043232680866580356,
|
|
"loss": 5.1306,
|
|
"mean_token_accuracy": 0.1914771690964699,
|
|
"num_tokens": 6932102.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.613216924667358,
|
|
"epoch": 3.156586578293289,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00043209820044221893,
|
|
"loss": 5.1616,
|
|
"mean_token_accuracy": 0.18996156007051468,
|
|
"num_tokens": 6940354.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.594096565246582,
|
|
"epoch": 3.1607290803645403,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00043186927533439654,
|
|
"loss": 5.1852,
|
|
"mean_token_accuracy": 0.1773633748292923,
|
|
"num_tokens": 6949779.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.742680025100708,
|
|
"epoch": 3.1648715824357914,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00043164003380410335,
|
|
"loss": 5.2265,
|
|
"mean_token_accuracy": 0.18539713323116302,
|
|
"num_tokens": 6958760.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.646546173095703,
|
|
"epoch": 3.169014084507042,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004314104763137445,
|
|
"loss": 5.0841,
|
|
"mean_token_accuracy": 0.1947013482451439,
|
|
"num_tokens": 6967535.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.594086408615112,
|
|
"epoch": 3.173156586578293,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043118060332636264,
|
|
"loss": 5.2197,
|
|
"mean_token_accuracy": 0.18882258534431456,
|
|
"num_tokens": 6976211.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.726991415023804,
|
|
"epoch": 3.1772990886495442,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043095041530563665,
|
|
"loss": 5.2182,
|
|
"mean_token_accuracy": 0.18605553954839707,
|
|
"num_tokens": 6986001.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.585007810592652,
|
|
"epoch": 3.1814415907207954,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043071991271588104,
|
|
"loss": 5.2026,
|
|
"mean_token_accuracy": 0.1912832126021385,
|
|
"num_tokens": 6994568.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.701341390609741,
|
|
"epoch": 3.1855840927920465,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004304890960220446,
|
|
"loss": 5.3141,
|
|
"mean_token_accuracy": 0.17634288668632508,
|
|
"num_tokens": 7004744.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.651245403289795,
|
|
"epoch": 3.1897265948632976,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043025796568970975,
|
|
"loss": 5.2762,
|
|
"mean_token_accuracy": 0.18054914921522142,
|
|
"num_tokens": 7014315.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.64104700088501,
|
|
"epoch": 3.1938690969345487,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00043002652218509184,
|
|
"loss": 5.1365,
|
|
"mean_token_accuracy": 0.1899659290909767,
|
|
"num_tokens": 7022258.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.6505451679229735,
|
|
"epoch": 3.1980115990057993,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004297947659750376,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.1783803090453148,
|
|
"num_tokens": 7031732.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.631345415115357,
|
|
"epoch": 3.2021541010770505,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004295626975270246,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.1890062063932419,
|
|
"num_tokens": 7040478.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.670590496063232,
|
|
"epoch": 3.2062966031483016,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042933031730916024,
|
|
"loss": 5.1374,
|
|
"mean_token_accuracy": 0.18894131630659103,
|
|
"num_tokens": 7049360.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.666132545471191,
|
|
"epoch": 3.2104391052195527,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000429097625790181,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18217806816101073,
|
|
"num_tokens": 7059271.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.5448277473449705,
|
|
"epoch": 3.2145816072908038,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004288646234394508,
|
|
"loss": 5.1898,
|
|
"mean_token_accuracy": 0.18378292620182038,
|
|
"num_tokens": 7069038.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.691568040847779,
|
|
"epoch": 3.218724109362055,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042863131072696115,
|
|
"loss": 5.1467,
|
|
"mean_token_accuracy": 0.19004709422588348,
|
|
"num_tokens": 7077971.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.625791883468628,
|
|
"epoch": 3.2228666114333056,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042839768812332905,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18205430954694748,
|
|
"num_tokens": 7086821.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.561760568618775,
|
|
"epoch": 3.2270091135045567,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000428163756099797,
|
|
"loss": 5.1873,
|
|
"mean_token_accuracy": 0.1800561308860779,
|
|
"num_tokens": 7095407.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.5761185646057125,
|
|
"epoch": 3.2311516155758078,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004279295151282314,
|
|
"loss": 5.1217,
|
|
"mean_token_accuracy": 0.19417204409837724,
|
|
"num_tokens": 7103964.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.678389930725098,
|
|
"epoch": 3.235294117647059,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004276949656811217,
|
|
"loss": 5.2382,
|
|
"mean_token_accuracy": 0.18186860978603364,
|
|
"num_tokens": 7113571.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.684243965148926,
|
|
"epoch": 3.23943661971831,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00042746010823158006,
|
|
"loss": 5.256,
|
|
"mean_token_accuracy": 0.1811550036072731,
|
|
"num_tokens": 7122844.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.593107748031616,
|
|
"epoch": 3.243579121789561,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00042722494325333945,
|
|
"loss": 5.1498,
|
|
"mean_token_accuracy": 0.18408443182706832,
|
|
"num_tokens": 7132123.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.603302955627441,
|
|
"epoch": 3.2477216238608118,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004269894712207533,
|
|
"loss": 5.175,
|
|
"mean_token_accuracy": 0.18924234211444854,
|
|
"num_tokens": 7141068.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.597929763793945,
|
|
"epoch": 3.251864125932063,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004267536926087947,
|
|
"loss": 5.1917,
|
|
"mean_token_accuracy": 0.1828271746635437,
|
|
"num_tokens": 7150829.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.604876327514648,
|
|
"epoch": 3.256006628003314,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004265176078930545,
|
|
"loss": 5.189,
|
|
"mean_token_accuracy": 0.18515739291906358,
|
|
"num_tokens": 7160814.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.678644418716431,
|
|
"epoch": 3.260149130074565,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00042628121754974166,
|
|
"loss": 5.2543,
|
|
"mean_token_accuracy": 0.18169930279254914,
|
|
"num_tokens": 7170085.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.732874631881714,
|
|
"epoch": 3.264291632145816,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004260445220556811,
|
|
"loss": 5.2171,
|
|
"mean_token_accuracy": 0.18695585429668427,
|
|
"num_tokens": 7179366.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.657085037231445,
|
|
"epoch": 3.2684341342170673,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00042580752188831376,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.17909180372953415,
|
|
"num_tokens": 7188342.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.7282510757446286,
|
|
"epoch": 3.272576636288318,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004255702175256946,
|
|
"loss": 5.3069,
|
|
"mean_token_accuracy": 0.1846114918589592,
|
|
"num_tokens": 7197466.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.622539758682251,
|
|
"epoch": 3.276719138359569,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00042533260944649273,
|
|
"loss": 5.1659,
|
|
"mean_token_accuracy": 0.18751862049102783,
|
|
"num_tokens": 7205462.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.614587879180908,
|
|
"epoch": 3.28086164043082,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004250946981299893,
|
|
"loss": 5.1868,
|
|
"mean_token_accuracy": 0.1857294872403145,
|
|
"num_tokens": 7215115.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.63320951461792,
|
|
"epoch": 3.2850041425020713,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042485648405607776,
|
|
"loss": 5.139,
|
|
"mean_token_accuracy": 0.182099050283432,
|
|
"num_tokens": 7224909.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.516879463195801,
|
|
"epoch": 3.2891466445733224,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004246179677052617,
|
|
"loss": 5.0658,
|
|
"mean_token_accuracy": 0.19667475372552873,
|
|
"num_tokens": 7232946.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.556838798522949,
|
|
"epoch": 3.2932891466445735,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0004243791495586547,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.1923754870891571,
|
|
"num_tokens": 7241104.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.708092784881591,
|
|
"epoch": 3.297431648715824,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004241400300979791,
|
|
"loss": 5.2207,
|
|
"mean_token_accuracy": 0.18612581193447114,
|
|
"num_tokens": 7250749.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.611432361602783,
|
|
"epoch": 3.3015741507870753,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004239006098055651,
|
|
"loss": 5.1103,
|
|
"mean_token_accuracy": 0.19173226207494737,
|
|
"num_tokens": 7258687.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.5728600978851315,
|
|
"epoch": 3.3057166528583264,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004236608891643494,
|
|
"loss": 5.1604,
|
|
"mean_token_accuracy": 0.1844268724322319,
|
|
"num_tokens": 7267316.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.579600477218628,
|
|
"epoch": 3.3098591549295775,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004234208686578748,
|
|
"loss": 5.1773,
|
|
"mean_token_accuracy": 0.1862543687224388,
|
|
"num_tokens": 7276734.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.580500507354737,
|
|
"epoch": 3.3140016570008286,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00042318054877028876,
|
|
"loss": 5.1719,
|
|
"mean_token_accuracy": 0.1836218684911728,
|
|
"num_tokens": 7285916.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 3.3140016570008286,
|
|
"eval_entropy": 5.4536612770959,
|
|
"eval_loss": 5.814967632293701,
|
|
"eval_mean_token_accuracy": 0.1589502211509229,
|
|
"eval_num_tokens": 7285916.0,
|
|
"eval_runtime": 2.1074,
|
|
"eval_samples_per_second": 1778.003,
|
|
"eval_steps_per_second": 222.547,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.668316316604614,
|
|
"epoch": 3.3181441590720797,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00042293992998634314,
|
|
"loss": 5.1522,
|
|
"mean_token_accuracy": 0.19257433116436004,
|
|
"num_tokens": 7294184.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.557364845275879,
|
|
"epoch": 3.3222866611433304,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0004226990127913918,
|
|
"loss": 5.171,
|
|
"mean_token_accuracy": 0.18853513896465302,
|
|
"num_tokens": 7302647.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.598273038864136,
|
|
"epoch": 3.3264291632145815,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004224577976713915,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.17716234177350998,
|
|
"num_tokens": 7311455.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.723063898086548,
|
|
"epoch": 3.3305716652858326,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00042221628511289927,
|
|
"loss": 5.3166,
|
|
"mean_token_accuracy": 0.1700568437576294,
|
|
"num_tokens": 7320978.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.784033870697021,
|
|
"epoch": 3.3347141673570837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004219744756030723,
|
|
"loss": 5.3354,
|
|
"mean_token_accuracy": 0.1783115193247795,
|
|
"num_tokens": 7330202.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.5498302459716795,
|
|
"epoch": 3.338856669428335,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042173236962966706,
|
|
"loss": 5.1534,
|
|
"mean_token_accuracy": 0.19193593114614488,
|
|
"num_tokens": 7339121.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.60600790977478,
|
|
"epoch": 3.342999171499586,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004214899676810375,
|
|
"loss": 5.2248,
|
|
"mean_token_accuracy": 0.17973909825086593,
|
|
"num_tokens": 7348631.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.644072484970093,
|
|
"epoch": 3.347141673570837,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004212472702461348,
|
|
"loss": 5.1932,
|
|
"mean_token_accuracy": 0.18887644112110138,
|
|
"num_tokens": 7358354.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.588744735717773,
|
|
"epoch": 3.3512841756420877,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004210042778145064,
|
|
"loss": 5.2152,
|
|
"mean_token_accuracy": 0.18782011419534683,
|
|
"num_tokens": 7367031.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.562919569015503,
|
|
"epoch": 3.355426677713339,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00042076099087629443,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.18633589297533035,
|
|
"num_tokens": 7375996.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.736072206497193,
|
|
"epoch": 3.35956917978459,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00042051740992223534,
|
|
"loss": 5.2649,
|
|
"mean_token_accuracy": 0.17588813751935958,
|
|
"num_tokens": 7385355.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.551749849319458,
|
|
"epoch": 3.363711681855841,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004202735354436586,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.19093554317951203,
|
|
"num_tokens": 7394384.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.644789218902588,
|
|
"epoch": 3.367854183927092,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00042002936793248546,
|
|
"loss": 5.2327,
|
|
"mean_token_accuracy": 0.18787333220243455,
|
|
"num_tokens": 7403141.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.630174732208252,
|
|
"epoch": 3.371996685998343,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004197849078812286,
|
|
"loss": 5.2002,
|
|
"mean_token_accuracy": 0.18249061405658723,
|
|
"num_tokens": 7413331.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.6429643630981445,
|
|
"epoch": 3.376139188069594,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004195401557829907,
|
|
"loss": 5.2294,
|
|
"mean_token_accuracy": 0.18183289915323259,
|
|
"num_tokens": 7422362.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.565690612792968,
|
|
"epoch": 3.380281690140845,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041929511213146343,
|
|
"loss": 5.1539,
|
|
"mean_token_accuracy": 0.18606581240892411,
|
|
"num_tokens": 7431350.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.634101533889771,
|
|
"epoch": 3.384424192212096,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004190497774209266,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.18882956951856614,
|
|
"num_tokens": 7440382.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.638964033126831,
|
|
"epoch": 3.3885666942833472,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041880415214624715,
|
|
"loss": 5.2519,
|
|
"mean_token_accuracy": 0.1846897065639496,
|
|
"num_tokens": 7449357.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.66209397315979,
|
|
"epoch": 3.3927091963545983,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004185582368028781,
|
|
"loss": 5.1541,
|
|
"mean_token_accuracy": 0.19304556846618653,
|
|
"num_tokens": 7457544.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.566800212860107,
|
|
"epoch": 3.3968516984258494,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004183120318868577,
|
|
"loss": 5.1562,
|
|
"mean_token_accuracy": 0.19666593223810197,
|
|
"num_tokens": 7465915.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.5809026718139645,
|
|
"epoch": 3.4009942004971,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00041806553789480787,
|
|
"loss": 5.1231,
|
|
"mean_token_accuracy": 0.18676048517227173,
|
|
"num_tokens": 7474551.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.610612249374389,
|
|
"epoch": 3.405136702568351,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00041781875532393423,
|
|
"loss": 5.2252,
|
|
"mean_token_accuracy": 0.18217408955097197,
|
|
"num_tokens": 7483271.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.658124017715454,
|
|
"epoch": 3.4092792046396023,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00041757168467202404,
|
|
"loss": 5.2416,
|
|
"mean_token_accuracy": 0.1792655035853386,
|
|
"num_tokens": 7493179.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.61301555633545,
|
|
"epoch": 3.4134217067108534,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00041732432643744576,
|
|
"loss": 5.2075,
|
|
"mean_token_accuracy": 0.1837758481502533,
|
|
"num_tokens": 7501858.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.658749961853028,
|
|
"epoch": 3.4175642087821045,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004170766811191481,
|
|
"loss": 5.2824,
|
|
"mean_token_accuracy": 0.17987780272960663,
|
|
"num_tokens": 7511817.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.61474986076355,
|
|
"epoch": 3.421706710853355,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004168287492166587,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.1849779263138771,
|
|
"num_tokens": 7521655.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.684850072860717,
|
|
"epoch": 3.4258492129246063,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00041658053123008325,
|
|
"loss": 5.2108,
|
|
"mean_token_accuracy": 0.18221887797117234,
|
|
"num_tokens": 7531321.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.632678079605102,
|
|
"epoch": 3.4299917149958574,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004163320276601046,
|
|
"loss": 5.2204,
|
|
"mean_token_accuracy": 0.1837646558880806,
|
|
"num_tokens": 7540613.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.579312753677368,
|
|
"epoch": 3.4341342170671085,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004160832390079816,
|
|
"loss": 5.2785,
|
|
"mean_token_accuracy": 0.18566041588783264,
|
|
"num_tokens": 7549598.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.608151054382324,
|
|
"epoch": 3.4382767191383596,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00041583416577554815,
|
|
"loss": 5.1601,
|
|
"mean_token_accuracy": 0.18614359349012374,
|
|
"num_tokens": 7558738.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.608538866043091,
|
|
"epoch": 3.4424192212096107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00041558480846521213,
|
|
"loss": 5.1952,
|
|
"mean_token_accuracy": 0.18425507992506027,
|
|
"num_tokens": 7566873.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.563886451721191,
|
|
"epoch": 3.446561723280862,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00041533516757995455,
|
|
"loss": 5.1641,
|
|
"mean_token_accuracy": 0.18772312700748445,
|
|
"num_tokens": 7576645.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.638494300842285,
|
|
"epoch": 3.4507042253521125,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004150852436233283,
|
|
"loss": 5.1674,
|
|
"mean_token_accuracy": 0.18532244116067886,
|
|
"num_tokens": 7584854.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.624472665786743,
|
|
"epoch": 3.4548467274233636,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004148350370994574,
|
|
"loss": 5.3113,
|
|
"mean_token_accuracy": 0.17539304196834565,
|
|
"num_tokens": 7594022.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.613860654830932,
|
|
"epoch": 3.4589892294946147,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004145845485130357,
|
|
"loss": 5.1762,
|
|
"mean_token_accuracy": 0.1872359946370125,
|
|
"num_tokens": 7603259.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.598962068557739,
|
|
"epoch": 3.463131731565866,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00041433377836932594,
|
|
"loss": 5.2801,
|
|
"mean_token_accuracy": 0.17806156873703002,
|
|
"num_tokens": 7613451.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.727210760116577,
|
|
"epoch": 3.467274233637117,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00041408272717415913,
|
|
"loss": 5.2379,
|
|
"mean_token_accuracy": 0.1807100236415863,
|
|
"num_tokens": 7622218.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.5481668472290036,
|
|
"epoch": 3.4714167357083676,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004138313954339327,
|
|
"loss": 5.0931,
|
|
"mean_token_accuracy": 0.1846869558095932,
|
|
"num_tokens": 7630508.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.59676775932312,
|
|
"epoch": 3.4755592377796187,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004135797836556106,
|
|
"loss": 5.1823,
|
|
"mean_token_accuracy": 0.18439439088106155,
|
|
"num_tokens": 7640141.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.5729227542877195,
|
|
"epoch": 3.47970173985087,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041332789234672094,
|
|
"loss": 5.19,
|
|
"mean_token_accuracy": 0.1772349953651428,
|
|
"num_tokens": 7648764.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.580587005615234,
|
|
"epoch": 3.483844241922121,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004130757220153561,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.19089400619268418,
|
|
"num_tokens": 7658642.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.655549192428589,
|
|
"epoch": 3.487986743993372,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004128232731701712,
|
|
"loss": 5.3533,
|
|
"mean_token_accuracy": 0.17611879408359526,
|
|
"num_tokens": 7667524.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.626485157012939,
|
|
"epoch": 3.492129246064623,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004125705463203833,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19230241626501082,
|
|
"num_tokens": 7675800.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.618916749954224,
|
|
"epoch": 3.4962717481358743,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00041231754197576986,
|
|
"loss": 5.2309,
|
|
"mean_token_accuracy": 0.18466396033763885,
|
|
"num_tokens": 7683742.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.548590278625488,
|
|
"epoch": 3.5004142502071254,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004120642606466685,
|
|
"loss": 5.2304,
|
|
"mean_token_accuracy": 0.1903707817196846,
|
|
"num_tokens": 7692379.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.671255397796631,
|
|
"epoch": 3.504556752278376,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004118107028439751,
|
|
"loss": 5.2092,
|
|
"mean_token_accuracy": 0.1839378446340561,
|
|
"num_tokens": 7702156.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.640768909454346,
|
|
"epoch": 3.508699254349627,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00041155686907914365,
|
|
"loss": 5.209,
|
|
"mean_token_accuracy": 0.18331051766872405,
|
|
"num_tokens": 7712135.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.531083965301514,
|
|
"epoch": 3.5128417564208783,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004113027598641845,
|
|
"loss": 5.1706,
|
|
"mean_token_accuracy": 0.18631251901388168,
|
|
"num_tokens": 7721347.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.610216331481934,
|
|
"epoch": 3.5169842584921294,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004110483757116637,
|
|
"loss": 5.2034,
|
|
"mean_token_accuracy": 0.1870657205581665,
|
|
"num_tokens": 7731351.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.5788719177246096,
|
|
"epoch": 3.52112676056338,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041079371713470195,
|
|
"loss": 5.1042,
|
|
"mean_token_accuracy": 0.19566077888011932,
|
|
"num_tokens": 7740413.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.577755928039551,
|
|
"epoch": 3.525269262634631,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00041053878464697343,
|
|
"loss": 5.1945,
|
|
"mean_token_accuracy": 0.1878727927803993,
|
|
"num_tokens": 7749319.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.639510536193848,
|
|
"epoch": 3.5294117647058822,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004102835787627047,
|
|
"loss": 5.2512,
|
|
"mean_token_accuracy": 0.18048267662525178,
|
|
"num_tokens": 7757936.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.723114919662476,
|
|
"epoch": 3.5335542667771334,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0004100280999966741,
|
|
"loss": 5.3021,
|
|
"mean_token_accuracy": 0.18259284645318985,
|
|
"num_tokens": 7767349.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.527202224731445,
|
|
"epoch": 3.5376967688483845,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040977234886421007,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.18135430961847304,
|
|
"num_tokens": 7776448.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.51872615814209,
|
|
"epoch": 3.5418392709196356,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040951632588119064,
|
|
"loss": 5.1863,
|
|
"mean_token_accuracy": 0.18220845311880113,
|
|
"num_tokens": 7785768.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.728793382644653,
|
|
"epoch": 3.5459817729908867,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004092600315640422,
|
|
"loss": 5.2996,
|
|
"mean_token_accuracy": 0.18172710090875627,
|
|
"num_tokens": 7794803.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.588451719284057,
|
|
"epoch": 3.550124275062138,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004090034664297382,
|
|
"loss": 5.1388,
|
|
"mean_token_accuracy": 0.18972845524549484,
|
|
"num_tokens": 7803533.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.582978010177612,
|
|
"epoch": 3.5542667771333885,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040874663099579883,
|
|
"loss": 5.2257,
|
|
"mean_token_accuracy": 0.18069180101156235,
|
|
"num_tokens": 7812854.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.586122512817383,
|
|
"epoch": 3.5584092792046396,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040848952578028915,
|
|
"loss": 5.1866,
|
|
"mean_token_accuracy": 0.18150721192359925,
|
|
"num_tokens": 7821683.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.569479608535767,
|
|
"epoch": 3.5625517812758907,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004082321513018183,
|
|
"loss": 5.1687,
|
|
"mean_token_accuracy": 0.19054441452026366,
|
|
"num_tokens": 7830967.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.644843196868896,
|
|
"epoch": 3.566694283347142,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00040797450807953897,
|
|
"loss": 5.2282,
|
|
"mean_token_accuracy": 0.17865598499774932,
|
|
"num_tokens": 7841179.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.607931804656983,
|
|
"epoch": 3.5708367854183924,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004077165966331454,
|
|
"loss": 5.1655,
|
|
"mean_token_accuracy": 0.1889963284134865,
|
|
"num_tokens": 7849841.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.48652195930481,
|
|
"epoch": 3.5749792874896436,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004074584174828735,
|
|
"loss": 5.1965,
|
|
"mean_token_accuracy": 0.18973682224750518,
|
|
"num_tokens": 7859390.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.60177059173584,
|
|
"epoch": 3.5791217895608947,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00040719997114949856,
|
|
"loss": 5.1824,
|
|
"mean_token_accuracy": 0.18775663077831267,
|
|
"num_tokens": 7868848.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.59824504852295,
|
|
"epoch": 3.5832642916321458,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040694125815433533,
|
|
"loss": 5.2275,
|
|
"mean_token_accuracy": 0.18797820210456848,
|
|
"num_tokens": 7877521.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.644321632385254,
|
|
"epoch": 3.587406793703397,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004066822790192359,
|
|
"loss": 5.1928,
|
|
"mean_token_accuracy": 0.1843762755393982,
|
|
"num_tokens": 7886355.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.595470666885376,
|
|
"epoch": 3.591549295774648,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00040642303426658967,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.17985173612833022,
|
|
"num_tokens": 7895028.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.499622058868408,
|
|
"epoch": 3.595691797845899,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040616352441932163,
|
|
"loss": 5.1285,
|
|
"mean_token_accuracy": 0.18672627210617065,
|
|
"num_tokens": 7904192.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.568276596069336,
|
|
"epoch": 3.59983429991715,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040590375000089146,
|
|
"loss": 5.2119,
|
|
"mean_token_accuracy": 0.17803653776645662,
|
|
"num_tokens": 7912328.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.6243757724761965,
|
|
"epoch": 3.603976801988401,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00040564371153529256,
|
|
"loss": 5.2355,
|
|
"mean_token_accuracy": 0.17802826017141343,
|
|
"num_tokens": 7922594.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.585995769500732,
|
|
"epoch": 3.608119304059652,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004053834095470509,
|
|
"loss": 5.2037,
|
|
"mean_token_accuracy": 0.16916441321372985,
|
|
"num_tokens": 7932345.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.627918481826782,
|
|
"epoch": 3.612261806130903,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040512284456122407,
|
|
"loss": 5.1982,
|
|
"mean_token_accuracy": 0.1880348280072212,
|
|
"num_tokens": 7942800.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.546682548522949,
|
|
"epoch": 3.616404308202154,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00040486201710340016,
|
|
"loss": 5.1144,
|
|
"mean_token_accuracy": 0.18868523389101027,
|
|
"num_tokens": 7951094.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.5294066905975345,
|
|
"epoch": 3.6205468102734053,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00040460092769969654,
|
|
"loss": 5.1862,
|
|
"mean_token_accuracy": 0.18286736756563188,
|
|
"num_tokens": 7960652.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.6999537467956545,
|
|
"epoch": 3.624689312344656,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004043395768767592,
|
|
"loss": 5.2873,
|
|
"mean_token_accuracy": 0.17761841416358948,
|
|
"num_tokens": 7969350.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.6177233219146725,
|
|
"epoch": 3.628831814415907,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004040779651617612,
|
|
"loss": 5.1839,
|
|
"mean_token_accuracy": 0.18447677046060562,
|
|
"num_tokens": 7978969.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.508784055709839,
|
|
"epoch": 3.632974316487158,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00040381609308240207,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.18703774511814117,
|
|
"num_tokens": 7988531.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.6016326427459715,
|
|
"epoch": 3.6371168185584093,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00040355396116690634,
|
|
"loss": 5.173,
|
|
"mean_token_accuracy": 0.18201700001955032,
|
|
"num_tokens": 7996576.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.574258947372437,
|
|
"epoch": 3.6412593206296604,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004032915699440227,
|
|
"loss": 5.2452,
|
|
"mean_token_accuracy": 0.18273275047540666,
|
|
"num_tokens": 8006279.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.627894544601441,
|
|
"epoch": 3.6454018227009115,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000403028919943023,
|
|
"loss": 5.1879,
|
|
"mean_token_accuracy": 0.1842435047030449,
|
|
"num_tokens": 8015476.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.6452454090118405,
|
|
"epoch": 3.6495443247721626,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004027660116937009,
|
|
"loss": 5.223,
|
|
"mean_token_accuracy": 0.18443273454904557,
|
|
"num_tokens": 8025450.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.602872133255005,
|
|
"epoch": 3.6536868268434133,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004025028457263712,
|
|
"loss": 5.2179,
|
|
"mean_token_accuracy": 0.18903184980154036,
|
|
"num_tokens": 8034850.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.527483081817627,
|
|
"epoch": 3.6578293289146644,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004022394225718684,
|
|
"loss": 5.1661,
|
|
"mean_token_accuracy": 0.1812977150082588,
|
|
"num_tokens": 8044526.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.544975137710571,
|
|
"epoch": 3.6619718309859155,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004019757427615456,
|
|
"loss": 5.1119,
|
|
"mean_token_accuracy": 0.18823791146278382,
|
|
"num_tokens": 8054033.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.608935356140137,
|
|
"epoch": 3.6661143330571666,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0004017118068272739,
|
|
"loss": 5.2245,
|
|
"mean_token_accuracy": 0.18635667413473128,
|
|
"num_tokens": 8063535.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.621490430831909,
|
|
"epoch": 3.6702568351284177,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00040144761530144096,
|
|
"loss": 5.2269,
|
|
"mean_token_accuracy": 0.19260986149311066,
|
|
"num_tokens": 8073079.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.531931972503662,
|
|
"epoch": 3.6743993371996684,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040118316871695,
|
|
"loss": 5.135,
|
|
"mean_token_accuracy": 0.1935441389679909,
|
|
"num_tokens": 8082925.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.571213626861573,
|
|
"epoch": 3.6785418392709195,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00040091846760721857,
|
|
"loss": 5.2464,
|
|
"mean_token_accuracy": 0.1839121863245964,
|
|
"num_tokens": 8092038.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.580021095275879,
|
|
"epoch": 3.6826843413421706,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00040065351250617774,
|
|
"loss": 5.2107,
|
|
"mean_token_accuracy": 0.17862264513969422,
|
|
"num_tokens": 8101581.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.578744173049927,
|
|
"epoch": 3.6868268434134217,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00040038830394827107,
|
|
"loss": 5.2814,
|
|
"mean_token_accuracy": 0.17334320843219758,
|
|
"num_tokens": 8111392.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.660773277282715,
|
|
"epoch": 3.690969345484673,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000400122842468453,
|
|
"loss": 5.2851,
|
|
"mean_token_accuracy": 0.17835751920938492,
|
|
"num_tokens": 8120941.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.576557159423828,
|
|
"epoch": 3.695111847555924,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003998571286021884,
|
|
"loss": 5.1791,
|
|
"mean_token_accuracy": 0.17894805371761321,
|
|
"num_tokens": 8129983.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.634583044052124,
|
|
"epoch": 3.699254349627175,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003995911628854512,
|
|
"loss": 5.2882,
|
|
"mean_token_accuracy": 0.18596843630075455,
|
|
"num_tokens": 8139428.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.592116212844848,
|
|
"epoch": 3.7033968516984257,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003993249458547234,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.18245391994714738,
|
|
"num_tokens": 8148520.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.5100151062011715,
|
|
"epoch": 3.707539353769677,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039905847804699363,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.19856512546539307,
|
|
"num_tokens": 8156908.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.577142810821533,
|
|
"epoch": 3.711681855840928,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039879175999975677,
|
|
"loss": 5.1998,
|
|
"mean_token_accuracy": 0.18479604423046112,
|
|
"num_tokens": 8165677.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.5765032291412355,
|
|
"epoch": 3.715824357912179,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039852479225101217,
|
|
"loss": 5.1663,
|
|
"mean_token_accuracy": 0.18231395184993743,
|
|
"num_tokens": 8174786.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.653572463989258,
|
|
"epoch": 3.71996685998343,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039825757533926305,
|
|
"loss": 5.2423,
|
|
"mean_token_accuracy": 0.17364872694015504,
|
|
"num_tokens": 8184150.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.569239139556885,
|
|
"epoch": 3.724109362054681,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039799010980351494,
|
|
"loss": 5.1473,
|
|
"mean_token_accuracy": 0.1986028343439102,
|
|
"num_tokens": 8192257.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.597325086593628,
|
|
"epoch": 3.728251864125932,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039772239618327535,
|
|
"loss": 5.2247,
|
|
"mean_token_accuracy": 0.18215775787830352,
|
|
"num_tokens": 8201041.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"epoch": 3.728251864125932,
|
|
"eval_entropy": 5.311673710341139,
|
|
"eval_loss": 5.772946834564209,
|
|
"eval_mean_token_accuracy": 0.16216642469930242,
|
|
"eval_num_tokens": 8201041.0,
|
|
"eval_runtime": 2.118,
|
|
"eval_samples_per_second": 1769.109,
|
|
"eval_steps_per_second": 221.434,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.531625461578369,
|
|
"epoch": 3.732394366197183,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00039745443501855156,
|
|
"loss": 5.1864,
|
|
"mean_token_accuracy": 0.1922898769378662,
|
|
"num_tokens": 8209881.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.6132255554199215,
|
|
"epoch": 3.736536868268434,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039718622684985075,
|
|
"loss": 5.2149,
|
|
"mean_token_accuracy": 0.19007077515125276,
|
|
"num_tokens": 8218504.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.5605991840362545,
|
|
"epoch": 3.7406793703396852,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000396917772218178,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.19522940814495088,
|
|
"num_tokens": 8226785.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.615779685974121,
|
|
"epoch": 3.7448218724109363,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003966490716650357,
|
|
"loss": 5.1929,
|
|
"mean_token_accuracy": 0.18394671827554704,
|
|
"num_tokens": 8236092.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.536267232894898,
|
|
"epoch": 3.7489643744821874,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039638012573242225,
|
|
"loss": 5.1909,
|
|
"mean_token_accuracy": 0.18858025968074799,
|
|
"num_tokens": 8245297.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.625736951828003,
|
|
"epoch": 3.7531068765534386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003961109349628309,
|
|
"loss": 5.2648,
|
|
"mean_token_accuracy": 0.17192120254039764,
|
|
"num_tokens": 8254772.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.642834186553955,
|
|
"epoch": 3.757249378624689,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000395841499899249,
|
|
"loss": 5.2965,
|
|
"mean_token_accuracy": 0.17538157254457473,
|
|
"num_tokens": 8264310.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.65706696510315,
|
|
"epoch": 3.7613918806959403,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039557182108515624,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.18849442154169083,
|
|
"num_tokens": 8274184.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.576530599594117,
|
|
"epoch": 3.7655343827671914,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00039530189906452457,
|
|
"loss": 5.1527,
|
|
"mean_token_accuracy": 0.1931835487484932,
|
|
"num_tokens": 8283151.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.62188949584961,
|
|
"epoch": 3.7696768848384425,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039503173438181605,
|
|
"loss": 5.2447,
|
|
"mean_token_accuracy": 0.18366555720567704,
|
|
"num_tokens": 8292574.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.5170197010040285,
|
|
"epoch": 3.773819386909693,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00039476132758198236,
|
|
"loss": 5.1577,
|
|
"mean_token_accuracy": 0.18609999269247054,
|
|
"num_tokens": 8301281.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.550332164764404,
|
|
"epoch": 3.7779618889809443,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039449067921046353,
|
|
"loss": 5.2086,
|
|
"mean_token_accuracy": 0.1915401801466942,
|
|
"num_tokens": 8310201.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.642763566970825,
|
|
"epoch": 3.7821043910521954,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00039421978981318703,
|
|
"loss": 5.2338,
|
|
"mean_token_accuracy": 0.18259721845388413,
|
|
"num_tokens": 8320369.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.62627911567688,
|
|
"epoch": 3.7862468931234465,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00039394865993656625,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.18421761840581893,
|
|
"num_tokens": 8329519.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.565040731430054,
|
|
"epoch": 3.7903893951946976,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003936772901274999,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.17980142682790756,
|
|
"num_tokens": 8338282.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.57489652633667,
|
|
"epoch": 3.7945318972659487,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003934056809333705,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18412036895751954,
|
|
"num_tokens": 8346861.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.603010416030884,
|
|
"epoch": 3.7986743993372,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00039313383290204333,
|
|
"loss": 5.2718,
|
|
"mean_token_accuracy": 0.18404911160469056,
|
|
"num_tokens": 8356078.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.606864595413208,
|
|
"epoch": 3.802816901408451,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003928617465818658,
|
|
"loss": 5.2317,
|
|
"mean_token_accuracy": 0.17510210275650023,
|
|
"num_tokens": 8365487.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.628439426422119,
|
|
"epoch": 3.8069594034797016,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039258942252166554,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.18452014327049254,
|
|
"num_tokens": 8374622.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.595311021804809,
|
|
"epoch": 3.8111019055509527,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003923168612707502,
|
|
"loss": 5.1357,
|
|
"mean_token_accuracy": 0.1948317214846611,
|
|
"num_tokens": 8383312.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.5251976490020756,
|
|
"epoch": 3.815244407622204,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003920440633789053,
|
|
"loss": 5.1664,
|
|
"mean_token_accuracy": 0.1859973818063736,
|
|
"num_tokens": 8391987.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.549222660064697,
|
|
"epoch": 3.819386909693455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00039177102939639424,
|
|
"loss": 5.1652,
|
|
"mean_token_accuracy": 0.18119524717330932,
|
|
"num_tokens": 8401263.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.664898872375488,
|
|
"epoch": 3.8235294117647056,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003914977598739563,
|
|
"loss": 5.2015,
|
|
"mean_token_accuracy": 0.19347340911626815,
|
|
"num_tokens": 8410110.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.639330434799194,
|
|
"epoch": 3.8276719138359567,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003912242553628059,
|
|
"loss": 5.2853,
|
|
"mean_token_accuracy": 0.17986278384923934,
|
|
"num_tokens": 8419321.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.650160598754883,
|
|
"epoch": 3.831814415907208,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003909505164146318,
|
|
"loss": 5.2584,
|
|
"mean_token_accuracy": 0.18256509602069854,
|
|
"num_tokens": 8428376.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.583395195007324,
|
|
"epoch": 3.835956917978459,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000390676543581595,
|
|
"loss": 5.1813,
|
|
"mean_token_accuracy": 0.18814439773559571,
|
|
"num_tokens": 8437263.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.5551060199737545,
|
|
"epoch": 3.84009942004971,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003904023374163289,
|
|
"loss": 5.1822,
|
|
"mean_token_accuracy": 0.1936976671218872,
|
|
"num_tokens": 8445889.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.647480106353759,
|
|
"epoch": 3.844241922120961,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003901278984719372,
|
|
"loss": 5.3633,
|
|
"mean_token_accuracy": 0.1729968771338463,
|
|
"num_tokens": 8456086.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.649803352355957,
|
|
"epoch": 3.8483844241922123,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00038985322730199326,
|
|
"loss": 5.1933,
|
|
"mean_token_accuracy": 0.190676811337471,
|
|
"num_tokens": 8465150.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.580242347717285,
|
|
"epoch": 3.8525269262634634,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003895783244605389,
|
|
"loss": 5.2611,
|
|
"mean_token_accuracy": 0.18282774090766907,
|
|
"num_tokens": 8474172.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.529580974578858,
|
|
"epoch": 3.856669428334714,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00038930319050208315,
|
|
"loss": 5.1587,
|
|
"mean_token_accuracy": 0.19163762480020524,
|
|
"num_tokens": 8483636.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.559849548339844,
|
|
"epoch": 3.860811930405965,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00038902782598160127,
|
|
"loss": 5.1124,
|
|
"mean_token_accuracy": 0.1960015267133713,
|
|
"num_tokens": 8491560.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.644432830810547,
|
|
"epoch": 3.8649544324772163,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038875223145453346,
|
|
"loss": 5.3892,
|
|
"mean_token_accuracy": 0.18815068155527115,
|
|
"num_tokens": 8501685.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.67485408782959,
|
|
"epoch": 3.8690969345484674,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003884764074767842,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.17898965924978255,
|
|
"num_tokens": 8510580.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.605153179168701,
|
|
"epoch": 3.873239436619718,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003882003546047205,
|
|
"loss": 5.2006,
|
|
"mean_token_accuracy": 0.17807233035564424,
|
|
"num_tokens": 8519595.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.674193572998047,
|
|
"epoch": 3.877381938690969,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038792407339517123,
|
|
"loss": 5.2983,
|
|
"mean_token_accuracy": 0.17992409467697143,
|
|
"num_tokens": 8529118.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.606718397140503,
|
|
"epoch": 3.8815244407622203,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038764756440542574,
|
|
"loss": 5.2368,
|
|
"mean_token_accuracy": 0.18252530992031096,
|
|
"num_tokens": 8539322.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.513642168045044,
|
|
"epoch": 3.8856669428334714,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038737082819323285,
|
|
"loss": 5.1653,
|
|
"mean_token_accuracy": 0.18386729061603546,
|
|
"num_tokens": 8548707.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.596105718612671,
|
|
"epoch": 3.8898094449047225,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00038709386531679974,
|
|
"loss": 5.2598,
|
|
"mean_token_accuracy": 0.1857382208108902,
|
|
"num_tokens": 8557500.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.6174877166748045,
|
|
"epoch": 3.8939519469759736,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00038681667633479086,
|
|
"loss": 5.2688,
|
|
"mean_token_accuracy": 0.17494362443685532,
|
|
"num_tokens": 8567465.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.530113601684571,
|
|
"epoch": 3.8980944490472247,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00038653926180632665,
|
|
"loss": 5.1003,
|
|
"mean_token_accuracy": 0.19298917502164842,
|
|
"num_tokens": 8576680.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.595879030227661,
|
|
"epoch": 3.902236951118476,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038626162229098257,
|
|
"loss": 5.258,
|
|
"mean_token_accuracy": 0.174155992269516,
|
|
"num_tokens": 8585539.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.583592748641967,
|
|
"epoch": 3.9063794531897265,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003859837583487877,
|
|
"loss": 5.1154,
|
|
"mean_token_accuracy": 0.1933972254395485,
|
|
"num_tokens": 8593598.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.580497789382934,
|
|
"epoch": 3.9105219552609776,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003857056705402241,
|
|
"loss": 5.2353,
|
|
"mean_token_accuracy": 0.18164603263139725,
|
|
"num_tokens": 8603440.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.4803260326385494,
|
|
"epoch": 3.9146644573322287,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003854273594262253,
|
|
"loss": 5.0608,
|
|
"mean_token_accuracy": 0.1953197881579399,
|
|
"num_tokens": 8612490.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.539776611328125,
|
|
"epoch": 3.91880695940348,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003851488255681752,
|
|
"loss": 5.1314,
|
|
"mean_token_accuracy": 0.1871775284409523,
|
|
"num_tokens": 8621994.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.566745805740356,
|
|
"epoch": 3.922949461474731,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000384870069527907,
|
|
"loss": 5.2273,
|
|
"mean_token_accuracy": 0.18442534804344177,
|
|
"num_tokens": 8631185.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.559898710250854,
|
|
"epoch": 3.9270919635459816,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00038459109186770213,
|
|
"loss": 5.1147,
|
|
"mean_token_accuracy": 0.1990325629711151,
|
|
"num_tokens": 8639018.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.527312421798706,
|
|
"epoch": 3.9312344656172327,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00038431189315028905,
|
|
"loss": 5.1219,
|
|
"mean_token_accuracy": 0.19203291088342667,
|
|
"num_tokens": 8647672.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.578536605834961,
|
|
"epoch": 3.9353769676884838,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003840324739388419,
|
|
"loss": 5.2402,
|
|
"mean_token_accuracy": 0.1752921849489212,
|
|
"num_tokens": 8656638.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.57722578048706,
|
|
"epoch": 3.939519469759735,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038375283479698,
|
|
"loss": 5.2097,
|
|
"mean_token_accuracy": 0.19240249693393707,
|
|
"num_tokens": 8666167.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.673281288146972,
|
|
"epoch": 3.943661971830986,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003834729762887659,
|
|
"loss": 5.2987,
|
|
"mean_token_accuracy": 0.17263731807470323,
|
|
"num_tokens": 8676435.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.547123861312866,
|
|
"epoch": 3.947804473902237,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003831928989787049,
|
|
"loss": 5.1812,
|
|
"mean_token_accuracy": 0.19059114307165145,
|
|
"num_tokens": 8686011.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.59344630241394,
|
|
"epoch": 3.951946975973488,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003829126034317435,
|
|
"loss": 5.2063,
|
|
"mean_token_accuracy": 0.17830358892679216,
|
|
"num_tokens": 8695063.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.670311832427979,
|
|
"epoch": 3.956089478044739,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003826320902132684,
|
|
"loss": 5.2953,
|
|
"mean_token_accuracy": 0.17167302668094636,
|
|
"num_tokens": 8704585.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.6066474437713625,
|
|
"epoch": 3.96023198011599,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038235135988910545,
|
|
"loss": 5.2048,
|
|
"mean_token_accuracy": 0.17712028324604034,
|
|
"num_tokens": 8714097.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.561362075805664,
|
|
"epoch": 3.964374482187241,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00038207041302551844,
|
|
"loss": 5.1322,
|
|
"mean_token_accuracy": 0.18891288191080094,
|
|
"num_tokens": 8722890.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.502840232849121,
|
|
"epoch": 3.968516984258492,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003817892501892078,
|
|
"loss": 5.1448,
|
|
"mean_token_accuracy": 0.1889907270669937,
|
|
"num_tokens": 8732046.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.530641841888428,
|
|
"epoch": 3.9726594863297433,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038150787194730977,
|
|
"loss": 5.1794,
|
|
"mean_token_accuracy": 0.19253561794757842,
|
|
"num_tokens": 8741750.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.602096176147461,
|
|
"epoch": 3.976801988400994,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000381226278867395,
|
|
"loss": 5.1665,
|
|
"mean_token_accuracy": 0.181898732483387,
|
|
"num_tokens": 8750141.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.556561803817749,
|
|
"epoch": 3.980944490472245,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00038094447151746746,
|
|
"loss": 5.0873,
|
|
"mean_token_accuracy": 0.1942881762981415,
|
|
"num_tokens": 8758567.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.564284420013427,
|
|
"epoch": 3.985086992543496,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003806624504659635,
|
|
"loss": 5.1897,
|
|
"mean_token_accuracy": 0.18416618257761003,
|
|
"num_tokens": 8767829.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.495919513702392,
|
|
"epoch": 3.9892294946147473,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003803802162817503,
|
|
"loss": 5.0791,
|
|
"mean_token_accuracy": 0.19538603723049164,
|
|
"num_tokens": 8776911.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.538990926742554,
|
|
"epoch": 3.9933719966859984,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000380097769534125,
|
|
"loss": 5.191,
|
|
"mean_token_accuracy": 0.18687430322170256,
|
|
"num_tokens": 8786117.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.544359540939331,
|
|
"epoch": 3.9975144987572495,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003798151107928136,
|
|
"loss": 5.1309,
|
|
"mean_token_accuracy": 0.19450936168432237,
|
|
"num_tokens": 8795647.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.509383916854858,
|
|
"epoch": 4.001657000828501,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00037953224062796967,
|
|
"loss": 5.1101,
|
|
"mean_token_accuracy": 0.1884679153561592,
|
|
"num_tokens": 8803480.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.653050899505615,
|
|
"epoch": 4.005799502899752,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003792491596101733,
|
|
"loss": 4.9646,
|
|
"mean_token_accuracy": 0.20317898094654083,
|
|
"num_tokens": 8812825.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.638010120391845,
|
|
"epoch": 4.009942004971003,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003789658683104298,
|
|
"loss": 5.0175,
|
|
"mean_token_accuracy": 0.2056334912776947,
|
|
"num_tokens": 8821911.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.589036130905152,
|
|
"epoch": 4.014084507042254,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00037868236730016866,
|
|
"loss": 4.9586,
|
|
"mean_token_accuracy": 0.19691554456949234,
|
|
"num_tokens": 8830691.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.535768604278564,
|
|
"epoch": 4.018227009113504,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037839865715124234,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.19637838900089263,
|
|
"num_tokens": 8840410.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.528214168548584,
|
|
"epoch": 4.022369511184755,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00037811473843592534,
|
|
"loss": 4.9174,
|
|
"mean_token_accuracy": 0.20173235535621642,
|
|
"num_tokens": 8849662.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.549580049514771,
|
|
"epoch": 4.026512013256006,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037783061172691273,
|
|
"loss": 4.9242,
|
|
"mean_token_accuracy": 0.20168643593788146,
|
|
"num_tokens": 8858666.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.588992547988892,
|
|
"epoch": 4.0306545153272575,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003775462775973191,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20111242234706878,
|
|
"num_tokens": 8867885.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.53621621131897,
|
|
"epoch": 4.034797017398509,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003772617366206773,
|
|
"loss": 4.9254,
|
|
"mean_token_accuracy": 0.2095017820596695,
|
|
"num_tokens": 8877458.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.456454515457153,
|
|
"epoch": 4.03893951946976,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037697698937093783,
|
|
"loss": 4.9387,
|
|
"mean_token_accuracy": 0.1983737602829933,
|
|
"num_tokens": 8886995.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.597288656234741,
|
|
"epoch": 4.043082021541011,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00037669203642246685,
|
|
"loss": 5.0264,
|
|
"mean_token_accuracy": 0.19989616870880128,
|
|
"num_tokens": 8895224.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.617550611495972,
|
|
"epoch": 4.047224523612262,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037640687835004567,
|
|
"loss": 4.9697,
|
|
"mean_token_accuracy": 0.1948849081993103,
|
|
"num_tokens": 8905216.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.547549247741699,
|
|
"epoch": 4.051367025683513,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003761215157288692,
|
|
"loss": 4.9721,
|
|
"mean_token_accuracy": 0.2027720496058464,
|
|
"num_tokens": 8915493.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.46840991973877,
|
|
"epoch": 4.055509527754764,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037583594913454514,
|
|
"loss": 4.9211,
|
|
"mean_token_accuracy": 0.2074059635400772,
|
|
"num_tokens": 8924740.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.536762237548828,
|
|
"epoch": 4.059652029826015,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003755501791430925,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.19338685423135757,
|
|
"num_tokens": 8934726.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.563719463348389,
|
|
"epoch": 4.063794531897266,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00037526420633094044,
|
|
"loss": 4.9707,
|
|
"mean_token_accuracy": 0.20555391907691956,
|
|
"num_tokens": 8944301.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.600133609771729,
|
|
"epoch": 4.067937033968517,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00037497803127492757,
|
|
"loss": 4.9945,
|
|
"mean_token_accuracy": 0.20445024967193604,
|
|
"num_tokens": 8953967.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.488191938400268,
|
|
"epoch": 4.072079536039768,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003746916545523001,
|
|
"loss": 4.9012,
|
|
"mean_token_accuracy": 0.20824553668498993,
|
|
"num_tokens": 8962983.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.583401250839233,
|
|
"epoch": 4.076222038111019,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003744050767407113,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.1962846115231514,
|
|
"num_tokens": 8972019.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.527191925048828,
|
|
"epoch": 4.08036454018227,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003741182984182198,
|
|
"loss": 4.9095,
|
|
"mean_token_accuracy": 0.21398218274116515,
|
|
"num_tokens": 8981751.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.5010823726654055,
|
|
"epoch": 4.084507042253521,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003738313201632889,
|
|
"loss": 4.9019,
|
|
"mean_token_accuracy": 0.20898395776748657,
|
|
"num_tokens": 8990330.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.426370096206665,
|
|
"epoch": 4.088649544324772,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003735441425547851,
|
|
"loss": 4.9189,
|
|
"mean_token_accuracy": 0.20117240250110627,
|
|
"num_tokens": 8998366.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.4455788135528564,
|
|
"epoch": 4.092792046396023,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037325676617197697,
|
|
"loss": 4.8516,
|
|
"mean_token_accuracy": 0.20921480059623718,
|
|
"num_tokens": 9006881.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.451267385482788,
|
|
"epoch": 4.096934548467274,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003729691915945342,
|
|
"loss": 4.8883,
|
|
"mean_token_accuracy": 0.21209601759910585,
|
|
"num_tokens": 9015415.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.56810154914856,
|
|
"epoch": 4.1010770505385254,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000372681419402526,
|
|
"loss": 4.9574,
|
|
"mean_token_accuracy": 0.19999348521232604,
|
|
"num_tokens": 9024578.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.513975524902344,
|
|
"epoch": 4.105219552609777,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003723934501764203,
|
|
"loss": 4.9628,
|
|
"mean_token_accuracy": 0.19574711620807647,
|
|
"num_tokens": 9032637.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.530683422088623,
|
|
"epoch": 4.109362054681028,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003721052844970826,
|
|
"loss": 4.9087,
|
|
"mean_token_accuracy": 0.20097477436065675,
|
|
"num_tokens": 9041513.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.583151006698609,
|
|
"epoch": 4.113504556752279,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00037181692294577457,
|
|
"loss": 4.9355,
|
|
"mean_token_accuracy": 0.20051016360521318,
|
|
"num_tokens": 9051024.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.433324861526489,
|
|
"epoch": 4.117647058823529,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00037152836610415284,
|
|
"loss": 4.8949,
|
|
"mean_token_accuracy": 0.2090902104973793,
|
|
"num_tokens": 9059494.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.439336490631104,
|
|
"epoch": 4.12178956089478,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00037123961455426836,
|
|
"loss": 4.8217,
|
|
"mean_token_accuracy": 0.2072136253118515,
|
|
"num_tokens": 9068166.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.493520832061767,
|
|
"epoch": 4.125932062966031,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037095066887856434,
|
|
"loss": 4.9234,
|
|
"mean_token_accuracy": 0.2002037927508354,
|
|
"num_tokens": 9077283.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.5299314022064205,
|
|
"epoch": 4.130074565037282,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003706615296598758,
|
|
"loss": 4.9208,
|
|
"mean_token_accuracy": 0.20447264164686202,
|
|
"num_tokens": 9086605.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.446752071380615,
|
|
"epoch": 4.134217067108533,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003703721974814282,
|
|
"loss": 4.921,
|
|
"mean_token_accuracy": 0.20757367759943007,
|
|
"num_tokens": 9095567.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.482961511611938,
|
|
"epoch": 4.1383595691797845,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00037008267292683615,
|
|
"loss": 4.903,
|
|
"mean_token_accuracy": 0.2004641354084015,
|
|
"num_tokens": 9104457.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.497553014755249,
|
|
"epoch": 4.142502071251036,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00036979295658010227,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.21054159104824066,
|
|
"num_tokens": 9113945.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 4.142502071251036,
|
|
"eval_entropy": 5.277666482335723,
|
|
"eval_loss": 5.767280101776123,
|
|
"eval_mean_token_accuracy": 0.1633036951266372,
|
|
"eval_num_tokens": 9113945.0,
|
|
"eval_runtime": 2.1177,
|
|
"eval_samples_per_second": 1769.414,
|
|
"eval_steps_per_second": 221.472,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.556628656387329,
|
|
"epoch": 4.146644573322287,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003695030490256161,
|
|
"loss": 5.04,
|
|
"mean_token_accuracy": 0.19981113970279693,
|
|
"num_tokens": 9122996.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.540997457504273,
|
|
"epoch": 4.150787075393538,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000369212950848153,
|
|
"loss": 4.8825,
|
|
"mean_token_accuracy": 0.20235711187124253,
|
|
"num_tokens": 9132079.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.498419380187988,
|
|
"epoch": 4.154929577464789,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003689226626328725,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.19626692533493043,
|
|
"num_tokens": 9141335.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.5333349227905275,
|
|
"epoch": 4.15907207953604,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036863218496531767,
|
|
"loss": 5.0284,
|
|
"mean_token_accuracy": 0.2034590870141983,
|
|
"num_tokens": 9150049.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.585499620437622,
|
|
"epoch": 4.163214581607291,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003683415184314139,
|
|
"loss": 4.9166,
|
|
"mean_token_accuracy": 0.20537189096212388,
|
|
"num_tokens": 9159245.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.4638427734375,
|
|
"epoch": 4.167357083678542,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00036805066361746716,
|
|
"loss": 4.9275,
|
|
"mean_token_accuracy": 0.20150275379419327,
|
|
"num_tokens": 9167892.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.429712629318237,
|
|
"epoch": 4.1714995857497925,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00036775962111016346,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.2092901051044464,
|
|
"num_tokens": 9176067.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.506008863449097,
|
|
"epoch": 4.175642087821044,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00036746839149656734,
|
|
"loss": 4.9197,
|
|
"mean_token_accuracy": 0.20309799760580063,
|
|
"num_tokens": 9185318.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.471706199645996,
|
|
"epoch": 4.179784589892295,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003671769753641207,
|
|
"loss": 4.9522,
|
|
"mean_token_accuracy": 0.20279468595981598,
|
|
"num_tokens": 9194885.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.504672813415527,
|
|
"epoch": 4.183927091963546,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036688537330064187,
|
|
"loss": 4.9975,
|
|
"mean_token_accuracy": 0.19840419590473174,
|
|
"num_tokens": 9203906.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.457697582244873,
|
|
"epoch": 4.188069594034797,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000366593585894324,
|
|
"loss": 4.8582,
|
|
"mean_token_accuracy": 0.2118522748351097,
|
|
"num_tokens": 9213351.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.507823276519775,
|
|
"epoch": 4.192212096106048,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003663016137337341,
|
|
"loss": 4.9527,
|
|
"mean_token_accuracy": 0.20061722695827483,
|
|
"num_tokens": 9222191.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.517373180389404,
|
|
"epoch": 4.196354598177299,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00036600945740781197,
|
|
"loss": 4.9737,
|
|
"mean_token_accuracy": 0.20068385154008866,
|
|
"num_tokens": 9231517.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.568848276138306,
|
|
"epoch": 4.20049710024855,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00036571711750586896,
|
|
"loss": 4.994,
|
|
"mean_token_accuracy": 0.20795601159334182,
|
|
"num_tokens": 9241208.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.530167198181152,
|
|
"epoch": 4.204639602319801,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003654245946175864,
|
|
"loss": 4.9033,
|
|
"mean_token_accuracy": 0.21201791614294052,
|
|
"num_tokens": 9250237.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.540363550186157,
|
|
"epoch": 4.2087821043910525,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036513188933301504,
|
|
"loss": 5.055,
|
|
"mean_token_accuracy": 0.1944010466337204,
|
|
"num_tokens": 9260273.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.509495735168457,
|
|
"epoch": 4.212924606462304,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003648390022425734,
|
|
"loss": 4.9154,
|
|
"mean_token_accuracy": 0.20339929014444352,
|
|
"num_tokens": 9268878.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.490254640579224,
|
|
"epoch": 4.217067108533554,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003645459339370468,
|
|
"loss": 4.9121,
|
|
"mean_token_accuracy": 0.21325588524341582,
|
|
"num_tokens": 9276324.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.463070869445801,
|
|
"epoch": 4.221209610604805,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036425268500758594,
|
|
"loss": 4.9838,
|
|
"mean_token_accuracy": 0.2090938776731491,
|
|
"num_tokens": 9285052.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.480539131164551,
|
|
"epoch": 4.225352112676056,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036395925604570614,
|
|
"loss": 4.8884,
|
|
"mean_token_accuracy": 0.20643478333950044,
|
|
"num_tokens": 9293324.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.534584808349609,
|
|
"epoch": 4.229494614747307,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003636656476432854,
|
|
"loss": 4.9546,
|
|
"mean_token_accuracy": 0.1993372842669487,
|
|
"num_tokens": 9302131.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.4102489948272705,
|
|
"epoch": 4.233637116818558,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003633718603925642,
|
|
"loss": 4.852,
|
|
"mean_token_accuracy": 0.20362935960292816,
|
|
"num_tokens": 9311128.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.55282073020935,
|
|
"epoch": 4.237779618889809,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003630778948861434,
|
|
"loss": 4.9428,
|
|
"mean_token_accuracy": 0.19605285227298735,
|
|
"num_tokens": 9319849.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.464523983001709,
|
|
"epoch": 4.2419221209610605,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003627837517169836,
|
|
"loss": 4.9604,
|
|
"mean_token_accuracy": 0.20025073736906052,
|
|
"num_tokens": 9328355.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.460433101654052,
|
|
"epoch": 4.246064623032312,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003624894314784037,
|
|
"loss": 4.9229,
|
|
"mean_token_accuracy": 0.2031237840652466,
|
|
"num_tokens": 9337562.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.486879444122314,
|
|
"epoch": 4.250207125103563,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003621949347640797,
|
|
"loss": 4.9589,
|
|
"mean_token_accuracy": 0.20713071674108505,
|
|
"num_tokens": 9347851.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.540704870223999,
|
|
"epoch": 4.254349627174814,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003619002621680439,
|
|
"loss": 4.9372,
|
|
"mean_token_accuracy": 0.20312865674495698,
|
|
"num_tokens": 9356524.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.573979473114013,
|
|
"epoch": 4.258492129246065,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003616054142846829,
|
|
"loss": 5.0366,
|
|
"mean_token_accuracy": 0.19623506516218187,
|
|
"num_tokens": 9365521.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.4263763427734375,
|
|
"epoch": 4.262634631317316,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003613103917087371,
|
|
"loss": 4.9304,
|
|
"mean_token_accuracy": 0.19938443154096602,
|
|
"num_tokens": 9374088.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.4591536045074465,
|
|
"epoch": 4.266777133388567,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003610151950352994,
|
|
"loss": 4.9913,
|
|
"mean_token_accuracy": 0.20375241041183473,
|
|
"num_tokens": 9382683.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.459029483795166,
|
|
"epoch": 4.270919635459817,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003607198248598137,
|
|
"loss": 4.9056,
|
|
"mean_token_accuracy": 0.21091930270195008,
|
|
"num_tokens": 9391790.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.568620395660401,
|
|
"epoch": 4.2750621375310685,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003604242817780739,
|
|
"loss": 4.9938,
|
|
"mean_token_accuracy": 0.20009204745292664,
|
|
"num_tokens": 9400234.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.545598554611206,
|
|
"epoch": 4.27920463960232,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00036012856638622273,
|
|
"loss": 4.89,
|
|
"mean_token_accuracy": 0.20271323025226592,
|
|
"num_tokens": 9409513.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.459887552261352,
|
|
"epoch": 4.283347141673571,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003598326792807504,
|
|
"loss": 4.9902,
|
|
"mean_token_accuracy": 0.1967105597257614,
|
|
"num_tokens": 9418608.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.5267308235168455,
|
|
"epoch": 4.287489643744822,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035953662105849357,
|
|
"loss": 5.0142,
|
|
"mean_token_accuracy": 0.19972590804100038,
|
|
"num_tokens": 9428705.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.510860824584961,
|
|
"epoch": 4.291632145816073,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.000359240392316634,
|
|
"loss": 4.9215,
|
|
"mean_token_accuracy": 0.20435694009065627,
|
|
"num_tokens": 9438149.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.510298156738282,
|
|
"epoch": 4.295774647887324,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003589439936526974,
|
|
"loss": 4.8957,
|
|
"mean_token_accuracy": 0.20918154418468476,
|
|
"num_tokens": 9447566.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.450149965286255,
|
|
"epoch": 4.299917149958575,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003586474256645525,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.19984477758407593,
|
|
"num_tokens": 9458156.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.565996885299683,
|
|
"epoch": 4.304059652029826,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00035835068895040905,
|
|
"loss": 5.0223,
|
|
"mean_token_accuracy": 0.20106985718011855,
|
|
"num_tokens": 9467388.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.527838087081909,
|
|
"epoch": 4.308202154101077,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00035805378410881753,
|
|
"loss": 4.9746,
|
|
"mean_token_accuracy": 0.20401760339736938,
|
|
"num_tokens": 9477515.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.484229516983032,
|
|
"epoch": 4.312344656172328,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003577567117386675,
|
|
"loss": 4.9807,
|
|
"mean_token_accuracy": 0.20119694024324417,
|
|
"num_tokens": 9485851.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.54345850944519,
|
|
"epoch": 4.3164871582435795,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003574594724391863,
|
|
"loss": 4.9922,
|
|
"mean_token_accuracy": 0.20046252459287645,
|
|
"num_tokens": 9495523.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.514360237121582,
|
|
"epoch": 4.32062966031483,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003571620668099382,
|
|
"loss": 4.9341,
|
|
"mean_token_accuracy": 0.2039078429341316,
|
|
"num_tokens": 9504195.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.518636560440063,
|
|
"epoch": 4.324772162386081,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003568644954508227,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.2081555351614952,
|
|
"num_tokens": 9513313.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.524921798706055,
|
|
"epoch": 4.328914664457332,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003565667589620739,
|
|
"loss": 5.0305,
|
|
"mean_token_accuracy": 0.19236165881156922,
|
|
"num_tokens": 9522387.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.525107955932617,
|
|
"epoch": 4.333057166528583,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003562688579442588,
|
|
"loss": 4.9761,
|
|
"mean_token_accuracy": 0.20175130069255828,
|
|
"num_tokens": 9531522.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.505756998062134,
|
|
"epoch": 4.337199668599834,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035597079299827625,
|
|
"loss": 4.992,
|
|
"mean_token_accuracy": 0.1966295510530472,
|
|
"num_tokens": 9540248.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.45184736251831,
|
|
"epoch": 4.341342170671085,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00035567256472535585,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.20498101115226747,
|
|
"num_tokens": 9549850.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.506281423568725,
|
|
"epoch": 4.345484672742336,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003553741737270566,
|
|
"loss": 4.9289,
|
|
"mean_token_accuracy": 0.20623278021812438,
|
|
"num_tokens": 9558929.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.478454542160034,
|
|
"epoch": 4.3496271748135875,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00035507562060526574,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.20452658236026763,
|
|
"num_tokens": 9567627.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.509828996658325,
|
|
"epoch": 4.353769676884839,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00035477690596219763,
|
|
"loss": 5.0716,
|
|
"mean_token_accuracy": 0.19206265062093736,
|
|
"num_tokens": 9576223.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.543297624588012,
|
|
"epoch": 4.35791217895609,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00035447803040039225,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.20088694840669633,
|
|
"num_tokens": 9585510.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.510033750534058,
|
|
"epoch": 4.362054681027341,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0003541789945227143,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.20869722962379456,
|
|
"num_tokens": 9594843.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.559547042846679,
|
|
"epoch": 4.366197183098592,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00035387979893235184,
|
|
"loss": 4.9723,
|
|
"mean_token_accuracy": 0.20713944286108016,
|
|
"num_tokens": 9604142.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.460270261764526,
|
|
"epoch": 4.370339685169842,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003535804442328151,
|
|
"loss": 5.0071,
|
|
"mean_token_accuracy": 0.20352598428726196,
|
|
"num_tokens": 9613669.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.5713756561279295,
|
|
"epoch": 4.374482187241093,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035328093102793506,
|
|
"loss": 4.9783,
|
|
"mean_token_accuracy": 0.20624274909496307,
|
|
"num_tokens": 9623502.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.570702600479126,
|
|
"epoch": 4.378624689312344,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00035298125992186283,
|
|
"loss": 4.9957,
|
|
"mean_token_accuracy": 0.19906429350376129,
|
|
"num_tokens": 9632041.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.512222719192505,
|
|
"epoch": 4.3827671913835955,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00035268143151906764,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.19845877289772035,
|
|
"num_tokens": 9641442.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.47532901763916,
|
|
"epoch": 4.386909693454847,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035238144642433616,
|
|
"loss": 4.9576,
|
|
"mean_token_accuracy": 0.19792149513959884,
|
|
"num_tokens": 9650857.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.542174482345581,
|
|
"epoch": 4.391052195526098,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000352081305242771,
|
|
"loss": 4.9944,
|
|
"mean_token_accuracy": 0.20782216042280197,
|
|
"num_tokens": 9659173.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.504279136657715,
|
|
"epoch": 4.395194697597349,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00035178100857978994,
|
|
"loss": 4.9245,
|
|
"mean_token_accuracy": 0.20672913044691085,
|
|
"num_tokens": 9668114.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.451822519302368,
|
|
"epoch": 4.3993371996686,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035148055704112405,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.20474138408899306,
|
|
"num_tokens": 9676628.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.405401515960693,
|
|
"epoch": 4.403479701739851,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003511799512328168,
|
|
"loss": 4.8921,
|
|
"mean_token_accuracy": 0.2065173029899597,
|
|
"num_tokens": 9685801.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.476840209960938,
|
|
"epoch": 4.407622203811102,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003508791917612232,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.20102325528860093,
|
|
"num_tokens": 9694237.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.557550716400146,
|
|
"epoch": 4.411764705882353,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035057827923300785,
|
|
"loss": 4.9081,
|
|
"mean_token_accuracy": 0.20714397430419923,
|
|
"num_tokens": 9701904.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.451809597015381,
|
|
"epoch": 4.415907207953604,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00035027721425514414,
|
|
"loss": 4.8765,
|
|
"mean_token_accuracy": 0.20882560908794404,
|
|
"num_tokens": 9710784.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.484688997268677,
|
|
"epoch": 4.4200497100248555,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003499759974349131,
|
|
"loss": 4.9943,
|
|
"mean_token_accuracy": 0.20253860354423522,
|
|
"num_tokens": 9720452.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.474400377273559,
|
|
"epoch": 4.424192212096106,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034967462937990194,
|
|
"loss": 4.9776,
|
|
"mean_token_accuracy": 0.19362543374300004,
|
|
"num_tokens": 9729122.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.5871623992919925,
|
|
"epoch": 4.428334714167357,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000349373110698003,
|
|
"loss": 5.0423,
|
|
"mean_token_accuracy": 0.1959236592054367,
|
|
"num_tokens": 9738756.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.562018918991089,
|
|
"epoch": 4.432477216238608,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003490714419974124,
|
|
"loss": 4.9919,
|
|
"mean_token_accuracy": 0.20110233277082443,
|
|
"num_tokens": 9748547.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.54822473526001,
|
|
"epoch": 4.436619718309859,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00034876962388662885,
|
|
"loss": 5.0578,
|
|
"mean_token_accuracy": 0.19230944365262986,
|
|
"num_tokens": 9758421.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.423689937591552,
|
|
"epoch": 4.44076222038111,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003484676569744525,
|
|
"loss": 4.8724,
|
|
"mean_token_accuracy": 0.19919645190238952,
|
|
"num_tokens": 9766855.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.482143115997315,
|
|
"epoch": 4.444904722452361,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003481655418699836,
|
|
"loss": 4.9541,
|
|
"mean_token_accuracy": 0.20723489671945572,
|
|
"num_tokens": 9776157.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.515763902664185,
|
|
"epoch": 4.449047224523612,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00034786327918262126,
|
|
"loss": 4.8648,
|
|
"mean_token_accuracy": 0.21377205699682236,
|
|
"num_tokens": 9784386.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.502019166946411,
|
|
"epoch": 4.4531897265948635,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00034756086952206255,
|
|
"loss": 4.9204,
|
|
"mean_token_accuracy": 0.20676726549863816,
|
|
"num_tokens": 9793838.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.5229016780853275,
|
|
"epoch": 4.457332228666115,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003472583134983005,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.19750352799892426,
|
|
"num_tokens": 9802595.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.544244432449341,
|
|
"epoch": 4.461474730737366,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00034695561172162396,
|
|
"loss": 4.9899,
|
|
"mean_token_accuracy": 0.2024237260222435,
|
|
"num_tokens": 9811309.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.412449789047241,
|
|
"epoch": 4.465617232808617,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00034665276480261526,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.20176597982645034,
|
|
"num_tokens": 9820327.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.487935781478882,
|
|
"epoch": 4.469759734879867,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003463497733521499,
|
|
"loss": 5.0217,
|
|
"mean_token_accuracy": 0.1915983021259308,
|
|
"num_tokens": 9829588.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.612684202194214,
|
|
"epoch": 4.473902236951118,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003460466379813947,
|
|
"loss": 4.9886,
|
|
"mean_token_accuracy": 0.2009852796792984,
|
|
"num_tokens": 9838548.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.447125577926636,
|
|
"epoch": 4.478044739022369,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003457433593018068,
|
|
"loss": 5.0068,
|
|
"mean_token_accuracy": 0.19739576578140258,
|
|
"num_tokens": 9847925.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.530708074569702,
|
|
"epoch": 4.48218724109362,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034543993792513243,
|
|
"loss": 5.0301,
|
|
"mean_token_accuracy": 0.1953074812889099,
|
|
"num_tokens": 9856839.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.603340721130371,
|
|
"epoch": 4.486329743164871,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003451363744634057,
|
|
"loss": 4.9973,
|
|
"mean_token_accuracy": 0.19945238679647445,
|
|
"num_tokens": 9866519.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.5518810749053955,
|
|
"epoch": 4.4904722452361225,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00034483266952894725,
|
|
"loss": 5.0633,
|
|
"mean_token_accuracy": 0.20334184616804124,
|
|
"num_tokens": 9876866.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.524944543838501,
|
|
"epoch": 4.494614747307374,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003445288237343632,
|
|
"loss": 5.0069,
|
|
"mean_token_accuracy": 0.20186655074357987,
|
|
"num_tokens": 9884639.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.465000247955322,
|
|
"epoch": 4.498757249378625,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003442248376925436,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.19831803292036057,
|
|
"num_tokens": 9893819.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.415613031387329,
|
|
"epoch": 4.502899751449876,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00034392071201666167,
|
|
"loss": 4.9262,
|
|
"mean_token_accuracy": 0.20202706158161163,
|
|
"num_tokens": 9902419.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.541242074966431,
|
|
"epoch": 4.507042253521127,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000343616447320172,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.20519603043794632,
|
|
"num_tokens": 9912434.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.54941349029541,
|
|
"epoch": 4.511184755592378,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003433120442168097,
|
|
"loss": 4.9236,
|
|
"mean_token_accuracy": 0.2109712079167366,
|
|
"num_tokens": 9921800.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.466617155075073,
|
|
"epoch": 4.515327257663629,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00034300750332058924,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.20112911015748977,
|
|
"num_tokens": 9930863.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.47055983543396,
|
|
"epoch": 4.51946975973488,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003427028252458028,
|
|
"loss": 5.0011,
|
|
"mean_token_accuracy": 0.19888981133699418,
|
|
"num_tokens": 9940524.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.539919757843018,
|
|
"epoch": 4.5236122618061305,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003423980106070194,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.19968555718660355,
|
|
"num_tokens": 9948949.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.534714603424073,
|
|
"epoch": 4.527754763877382,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003420930600190834,
|
|
"loss": 5.0136,
|
|
"mean_token_accuracy": 0.1967662662267685,
|
|
"num_tokens": 9958154.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.482914590835572,
|
|
"epoch": 4.531897265948633,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003417879740971135,
|
|
"loss": 4.9135,
|
|
"mean_token_accuracy": 0.20155586749315263,
|
|
"num_tokens": 9967023.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.543978691101074,
|
|
"epoch": 4.536039768019884,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003414827534565014,
|
|
"loss": 4.9927,
|
|
"mean_token_accuracy": 0.19888052940368653,
|
|
"num_tokens": 9976596.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.492054748535156,
|
|
"epoch": 4.540182270091135,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00034117739871291036,
|
|
"loss": 4.9164,
|
|
"mean_token_accuracy": 0.20937184542417525,
|
|
"num_tokens": 9985330.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.49746470451355,
|
|
"epoch": 4.544324772162386,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00034087191048227445,
|
|
"loss": 5.0273,
|
|
"mean_token_accuracy": 0.19777625501155854,
|
|
"num_tokens": 9996053.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.467337131500244,
|
|
"epoch": 4.548467274233637,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003405662893807967,
|
|
"loss": 4.9416,
|
|
"mean_token_accuracy": 0.1999909520149231,
|
|
"num_tokens": 10005517.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.543141460418701,
|
|
"epoch": 4.552609776304888,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003402605360249482,
|
|
"loss": 5.0434,
|
|
"mean_token_accuracy": 0.20232620537281037,
|
|
"num_tokens": 10014354.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.480380821228027,
|
|
"epoch": 4.556752278376139,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000339954651031467,
|
|
"loss": 4.9311,
|
|
"mean_token_accuracy": 0.20428754091262818,
|
|
"num_tokens": 10023194.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"epoch": 4.556752278376139,
|
|
"eval_entropy": 5.280215176946319,
|
|
"eval_loss": 5.734766960144043,
|
|
"eval_mean_token_accuracy": 0.1652140333168288,
|
|
"eval_num_tokens": 10023194.0,
|
|
"eval_runtime": 2.1075,
|
|
"eval_samples_per_second": 1777.922,
|
|
"eval_steps_per_second": 222.537,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.428198575973511,
|
|
"epoch": 4.5608947804473905,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033964863501735647,
|
|
"loss": 4.947,
|
|
"mean_token_accuracy": 0.20238611102104187,
|
|
"num_tokens": 10032490.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.475922393798828,
|
|
"epoch": 4.565037282518642,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00033934248859988453,
|
|
"loss": 4.9571,
|
|
"mean_token_accuracy": 0.20601299852132798,
|
|
"num_tokens": 10041613.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.428575801849365,
|
|
"epoch": 4.569179784589892,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003390362123965817,
|
|
"loss": 4.8758,
|
|
"mean_token_accuracy": 0.2019354745745659,
|
|
"num_tokens": 10050500.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.5513709545135494,
|
|
"epoch": 4.573322286661144,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003387298070252407,
|
|
"loss": 4.9607,
|
|
"mean_token_accuracy": 0.1994292125105858,
|
|
"num_tokens": 10059650.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.498982954025268,
|
|
"epoch": 4.577464788732394,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003384232731039146,
|
|
"loss": 5.0086,
|
|
"mean_token_accuracy": 0.20603219270706177,
|
|
"num_tokens": 10067882.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.421421194076538,
|
|
"epoch": 4.581607290803645,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033811661125091584,
|
|
"loss": 4.9296,
|
|
"mean_token_accuracy": 0.20492664873600006,
|
|
"num_tokens": 10077147.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.46508822441101,
|
|
"epoch": 4.585749792874896,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00033780982208481494,
|
|
"loss": 4.987,
|
|
"mean_token_accuracy": 0.19994274228811265,
|
|
"num_tokens": 10086149.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.460728597640991,
|
|
"epoch": 4.589892294946147,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003375029062244392,
|
|
"loss": 4.9078,
|
|
"mean_token_accuracy": 0.21085822880268096,
|
|
"num_tokens": 10094997.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.590810918807984,
|
|
"epoch": 4.5940347970173985,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00033719586428887125,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.20356753915548326,
|
|
"num_tokens": 10103585.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.482003307342529,
|
|
"epoch": 4.59817729908865,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00033688869689744836,
|
|
"loss": 4.8853,
|
|
"mean_token_accuracy": 0.20405055284500123,
|
|
"num_tokens": 10113877.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.450593709945679,
|
|
"epoch": 4.602319801159901,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003365814046697608,
|
|
"loss": 4.9759,
|
|
"mean_token_accuracy": 0.19292860180139543,
|
|
"num_tokens": 10123127.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.553015518188476,
|
|
"epoch": 4.606462303231152,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003362739882256504,
|
|
"loss": 5.0502,
|
|
"mean_token_accuracy": 0.19311599135398866,
|
|
"num_tokens": 10132301.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.544152164459229,
|
|
"epoch": 4.610604805302403,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0003359664481852099,
|
|
"loss": 5.0387,
|
|
"mean_token_accuracy": 0.1911822885274887,
|
|
"num_tokens": 10140985.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.435737657546997,
|
|
"epoch": 4.614747307373654,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033565878516878103,
|
|
"loss": 4.9426,
|
|
"mean_token_accuracy": 0.1987643301486969,
|
|
"num_tokens": 10149668.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.454352331161499,
|
|
"epoch": 4.618889809444905,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003353509997969537,
|
|
"loss": 5.0178,
|
|
"mean_token_accuracy": 0.1965770572423935,
|
|
"num_tokens": 10158584.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.505445575714111,
|
|
"epoch": 4.623032311516155,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00033504309269056484,
|
|
"loss": 4.9553,
|
|
"mean_token_accuracy": 0.20094942897558213,
|
|
"num_tokens": 10167657.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.405519104003906,
|
|
"epoch": 4.6271748135874065,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003347350644706965,
|
|
"loss": 4.8563,
|
|
"mean_token_accuracy": 0.20983149111270905,
|
|
"num_tokens": 10176657.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.500864696502686,
|
|
"epoch": 4.631317315658658,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003344269157586754,
|
|
"loss": 4.9801,
|
|
"mean_token_accuracy": 0.2089939907193184,
|
|
"num_tokens": 10185132.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.435798168182373,
|
|
"epoch": 4.635459817729909,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00033411864717607114,
|
|
"loss": 4.8662,
|
|
"mean_token_accuracy": 0.20337844043970107,
|
|
"num_tokens": 10193428.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.535364580154419,
|
|
"epoch": 4.63960231980116,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003338102593446951,
|
|
"loss": 5.0405,
|
|
"mean_token_accuracy": 0.19729718416929246,
|
|
"num_tokens": 10202549.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.528780794143676,
|
|
"epoch": 4.643744821872411,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00033350175288659925,
|
|
"loss": 4.9101,
|
|
"mean_token_accuracy": 0.20742549747228622,
|
|
"num_tokens": 10211161.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.466907691955567,
|
|
"epoch": 4.647887323943662,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00033319312842407483,
|
|
"loss": 4.9883,
|
|
"mean_token_accuracy": 0.19961451292037963,
|
|
"num_tokens": 10220988.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.45111083984375,
|
|
"epoch": 4.652029826014913,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003328843865796511,
|
|
"loss": 4.9111,
|
|
"mean_token_accuracy": 0.20649857819080353,
|
|
"num_tokens": 10229383.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.523708343505859,
|
|
"epoch": 4.656172328086164,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033257552797609426,
|
|
"loss": 4.9806,
|
|
"mean_token_accuracy": 0.19797324985265732,
|
|
"num_tokens": 10238622.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.669767761230469,
|
|
"epoch": 4.660314830157415,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00033226655323640553,
|
|
"loss": 5.088,
|
|
"mean_token_accuracy": 0.19369446337223054,
|
|
"num_tokens": 10248201.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.596281051635742,
|
|
"epoch": 4.664457332228666,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000331957462983821,
|
|
"loss": 5.1081,
|
|
"mean_token_accuracy": 0.18510288447141648,
|
|
"num_tokens": 10258239.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.488994455337524,
|
|
"epoch": 4.668599834299917,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003316482578418094,
|
|
"loss": 4.983,
|
|
"mean_token_accuracy": 0.20095534920692443,
|
|
"num_tokens": 10266915.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.504779911041259,
|
|
"epoch": 4.672742336371169,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033133893843407126,
|
|
"loss": 5.091,
|
|
"mean_token_accuracy": 0.1991728812456131,
|
|
"num_tokens": 10276826.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.4984949111938475,
|
|
"epoch": 4.676884838442419,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00033102950538453776,
|
|
"loss": 5.0177,
|
|
"mean_token_accuracy": 0.20115947723388672,
|
|
"num_tokens": 10286041.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.539341259002685,
|
|
"epoch": 4.68102734051367,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00033071995931736897,
|
|
"loss": 5.0148,
|
|
"mean_token_accuracy": 0.20080637633800508,
|
|
"num_tokens": 10295258.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.530173635482788,
|
|
"epoch": 4.685169842584921,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00033041030085695323,
|
|
"loss": 4.9359,
|
|
"mean_token_accuracy": 0.20575648844242095,
|
|
"num_tokens": 10304726.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.457293319702148,
|
|
"epoch": 4.689312344656172,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003301005306279055,
|
|
"loss": 4.9106,
|
|
"mean_token_accuracy": 0.20743891298770906,
|
|
"num_tokens": 10312912.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.501268672943115,
|
|
"epoch": 4.693454846727423,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00032979064925506627,
|
|
"loss": 4.9878,
|
|
"mean_token_accuracy": 0.20031296759843825,
|
|
"num_tokens": 10322046.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.431628084182739,
|
|
"epoch": 4.697597348798674,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003294806573634999,
|
|
"loss": 4.9468,
|
|
"mean_token_accuracy": 0.2115650773048401,
|
|
"num_tokens": 10331375.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.511561727523803,
|
|
"epoch": 4.7017398508699255,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003291705555784942,
|
|
"loss": 5.0401,
|
|
"mean_token_accuracy": 0.20154966562986373,
|
|
"num_tokens": 10341465.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.607239532470703,
|
|
"epoch": 4.705882352941177,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00032886034452555814,
|
|
"loss": 5.064,
|
|
"mean_token_accuracy": 0.19994643181562424,
|
|
"num_tokens": 10350137.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.446545600891113,
|
|
"epoch": 4.710024855012428,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003285500248304214,
|
|
"loss": 4.9693,
|
|
"mean_token_accuracy": 0.20075221061706544,
|
|
"num_tokens": 10358666.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.45259575843811,
|
|
"epoch": 4.714167357083679,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003282395971190328,
|
|
"loss": 4.8641,
|
|
"mean_token_accuracy": 0.21069184988737105,
|
|
"num_tokens": 10366910.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.524970149993896,
|
|
"epoch": 4.71830985915493,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00032792906201755876,
|
|
"loss": 5.0189,
|
|
"mean_token_accuracy": 0.19810162484645844,
|
|
"num_tokens": 10376435.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.445844411849976,
|
|
"epoch": 4.72245236122618,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00032761842015238256,
|
|
"loss": 4.9249,
|
|
"mean_token_accuracy": 0.21194297075271606,
|
|
"num_tokens": 10384670.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.42976393699646,
|
|
"epoch": 4.726594863297431,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003273076721501029,
|
|
"loss": 4.9145,
|
|
"mean_token_accuracy": 0.2067621499300003,
|
|
"num_tokens": 10393731.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.499672889709473,
|
|
"epoch": 4.730737365368682,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003269968186375325,
|
|
"loss": 5.0196,
|
|
"mean_token_accuracy": 0.20302713066339492,
|
|
"num_tokens": 10402369.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.548381567001343,
|
|
"epoch": 4.7348798674399335,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003266858602416967,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.20000933706760407,
|
|
"num_tokens": 10411566.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.544900846481323,
|
|
"epoch": 4.739022369511185,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032637479758983255,
|
|
"loss": 5.0288,
|
|
"mean_token_accuracy": 0.19865677058696746,
|
|
"num_tokens": 10420086.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.516452169418335,
|
|
"epoch": 4.743164871582436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00032606363130938766,
|
|
"loss": 5.0717,
|
|
"mean_token_accuracy": 0.19777458906173706,
|
|
"num_tokens": 10429746.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.5131408214569095,
|
|
"epoch": 4.747307373653687,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003257523620280181,
|
|
"loss": 4.9417,
|
|
"mean_token_accuracy": 0.20001468062400818,
|
|
"num_tokens": 10438536.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.5026021003723145,
|
|
"epoch": 4.751449875724938,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00032544099037358834,
|
|
"loss": 4.9617,
|
|
"mean_token_accuracy": 0.20604867935180665,
|
|
"num_tokens": 10447471.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.463160037994385,
|
|
"epoch": 4.755592377796189,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003251295169741688,
|
|
"loss": 4.9779,
|
|
"mean_token_accuracy": 0.20730176866054534,
|
|
"num_tokens": 10457179.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.473241806030273,
|
|
"epoch": 4.75973487986744,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032481794245803536,
|
|
"loss": 5.0389,
|
|
"mean_token_accuracy": 0.19745467901229857,
|
|
"num_tokens": 10466291.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.457436275482178,
|
|
"epoch": 4.763877381938691,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032450626745366806,
|
|
"loss": 4.9042,
|
|
"mean_token_accuracy": 0.20180842280387878,
|
|
"num_tokens": 10475452.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.519482803344727,
|
|
"epoch": 4.768019884009942,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00032419449258974924,
|
|
"loss": 4.9108,
|
|
"mean_token_accuracy": 0.20732126533985137,
|
|
"num_tokens": 10484381.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.503123044967651,
|
|
"epoch": 4.7721623860811935,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000323882618495163,
|
|
"loss": 5.0769,
|
|
"mean_token_accuracy": 0.1928909167647362,
|
|
"num_tokens": 10495132.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.510592412948609,
|
|
"epoch": 4.776304888152444,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003235706457989934,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.1930343598127365,
|
|
"num_tokens": 10504519.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.554948806762695,
|
|
"epoch": 4.780447390223695,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00032325857513052354,
|
|
"loss": 4.9846,
|
|
"mean_token_accuracy": 0.20321227610111237,
|
|
"num_tokens": 10513575.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.510985469818115,
|
|
"epoch": 4.784589892294946,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.000322946407119234,
|
|
"loss": 5.0659,
|
|
"mean_token_accuracy": 0.19863056391477585,
|
|
"num_tokens": 10522148.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.489944505691528,
|
|
"epoch": 4.788732394366197,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00032263414239480187,
|
|
"loss": 4.9898,
|
|
"mean_token_accuracy": 0.19475526958703995,
|
|
"num_tokens": 10531183.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.495128631591797,
|
|
"epoch": 4.792874896437448,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000322321781587099,
|
|
"loss": 4.9314,
|
|
"mean_token_accuracy": 0.20469003766775132,
|
|
"num_tokens": 10540677.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.4877594947814945,
|
|
"epoch": 4.797017398508699,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003220093253261915,
|
|
"loss": 4.9516,
|
|
"mean_token_accuracy": 0.19251628816127778,
|
|
"num_tokens": 10550009.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.516810512542724,
|
|
"epoch": 4.80115990057995,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003216967742423377,
|
|
"loss": 4.9829,
|
|
"mean_token_accuracy": 0.20415710061788558,
|
|
"num_tokens": 10559694.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.493601083755493,
|
|
"epoch": 4.8053024026512015,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003213841289659872,
|
|
"loss": 4.9769,
|
|
"mean_token_accuracy": 0.21076644361019134,
|
|
"num_tokens": 10567965.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.4885248184204105,
|
|
"epoch": 4.809444904722453,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003210713901277799,
|
|
"loss": 4.9824,
|
|
"mean_token_accuracy": 0.20494343638420104,
|
|
"num_tokens": 10577653.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.53714656829834,
|
|
"epoch": 4.813587406793704,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000320758558358544,
|
|
"loss": 4.9814,
|
|
"mean_token_accuracy": 0.19627270847558975,
|
|
"num_tokens": 10586903.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.47290072441101,
|
|
"epoch": 4.817729908864955,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0003204456342892955,
|
|
"loss": 4.8933,
|
|
"mean_token_accuracy": 0.20565903186798096,
|
|
"num_tokens": 10595411.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.429231119155884,
|
|
"epoch": 4.821872410936205,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00032013261855123637,
|
|
"loss": 4.9752,
|
|
"mean_token_accuracy": 0.19773368239402772,
|
|
"num_tokens": 10604147.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.510287570953369,
|
|
"epoch": 4.826014913007457,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00031981951177575366,
|
|
"loss": 5.068,
|
|
"mean_token_accuracy": 0.1976555421948433,
|
|
"num_tokens": 10614048.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.545227527618408,
|
|
"epoch": 4.830157415078707,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0003195063145944178,
|
|
"loss": 5.0899,
|
|
"mean_token_accuracy": 0.1938260391354561,
|
|
"num_tokens": 10623399.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.540503263473511,
|
|
"epoch": 4.834299917149958,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003191930276389819,
|
|
"loss": 4.9187,
|
|
"mean_token_accuracy": 0.20434982031583787,
|
|
"num_tokens": 10632627.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.516217041015625,
|
|
"epoch": 4.838442419221209,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00031887965154137987,
|
|
"loss": 4.9832,
|
|
"mean_token_accuracy": 0.19208359122276306,
|
|
"num_tokens": 10641155.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.532131767272949,
|
|
"epoch": 4.8425849212924605,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003185661869337255,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.20005885809659957,
|
|
"num_tokens": 10649661.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.4014593124389645,
|
|
"epoch": 4.846727423363712,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00031825263444831137,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.20210169553756713,
|
|
"num_tokens": 10658652.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.528108787536621,
|
|
"epoch": 4.850869925434963,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003179389947176069,
|
|
"loss": 5.0451,
|
|
"mean_token_accuracy": 0.19872143715620041,
|
|
"num_tokens": 10668703.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.496721982955933,
|
|
"epoch": 4.855012427506214,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003176252683742578,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.2013947531580925,
|
|
"num_tokens": 10677740.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.475582122802734,
|
|
"epoch": 4.859154929577465,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003173114560510843,
|
|
"loss": 4.9593,
|
|
"mean_token_accuracy": 0.20154381543397903,
|
|
"num_tokens": 10686429.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.552850770950317,
|
|
"epoch": 4.863297431648716,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00031699755838108027,
|
|
"loss": 5.0464,
|
|
"mean_token_accuracy": 0.2031494066119194,
|
|
"num_tokens": 10696367.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.53972806930542,
|
|
"epoch": 4.867439933719967,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0003166835759974115,
|
|
"loss": 5.0146,
|
|
"mean_token_accuracy": 0.19527551978826524,
|
|
"num_tokens": 10705712.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.523019742965698,
|
|
"epoch": 4.871582435791218,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00031636950953341486,
|
|
"loss": 5.0188,
|
|
"mean_token_accuracy": 0.1950419321656227,
|
|
"num_tokens": 10715897.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.475591135025025,
|
|
"epoch": 4.8757249378624685,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00031605535962259666,
|
|
"loss": 4.9467,
|
|
"mean_token_accuracy": 0.19443950355052947,
|
|
"num_tokens": 10724810.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.509956026077271,
|
|
"epoch": 4.87986743993372,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003157411268986316,
|
|
"loss": 4.9884,
|
|
"mean_token_accuracy": 0.20243558138608933,
|
|
"num_tokens": 10734661.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.452711153030395,
|
|
"epoch": 4.884009942004971,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003154268119953615,
|
|
"loss": 4.9481,
|
|
"mean_token_accuracy": 0.20909017622470855,
|
|
"num_tokens": 10743642.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.4960111618042,
|
|
"epoch": 4.888152444076222,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003151124155467938,
|
|
"loss": 4.9911,
|
|
"mean_token_accuracy": 0.20212035179138182,
|
|
"num_tokens": 10752812.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.501538515090942,
|
|
"epoch": 4.892294946147473,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00031479793818710056,
|
|
"loss": 4.9891,
|
|
"mean_token_accuracy": 0.19804088175296783,
|
|
"num_tokens": 10762117.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.456381225585938,
|
|
"epoch": 4.896437448218724,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00031448338055061685,
|
|
"loss": 4.9179,
|
|
"mean_token_accuracy": 0.21142183244228363,
|
|
"num_tokens": 10771515.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.487845802307129,
|
|
"epoch": 4.900579950289975,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00031416874327183994,
|
|
"loss": 4.948,
|
|
"mean_token_accuracy": 0.202542807161808,
|
|
"num_tokens": 10780610.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.408059406280517,
|
|
"epoch": 4.904722452361226,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00031385402698542753,
|
|
"loss": 4.9339,
|
|
"mean_token_accuracy": 0.2014468267560005,
|
|
"num_tokens": 10789169.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.474399852752685,
|
|
"epoch": 4.908864954432477,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00031353923232619674,
|
|
"loss": 4.9212,
|
|
"mean_token_accuracy": 0.20666908025741576,
|
|
"num_tokens": 10798636.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.487254333496094,
|
|
"epoch": 4.9130074565037285,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003132243599291229,
|
|
"loss": 4.9882,
|
|
"mean_token_accuracy": 0.20385005176067353,
|
|
"num_tokens": 10808245.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.4965846061706545,
|
|
"epoch": 4.91714995857498,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00031290941042933797,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.1993364319205284,
|
|
"num_tokens": 10817164.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.463863706588745,
|
|
"epoch": 4.92129246064623,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00031259438446212953,
|
|
"loss": 5.0032,
|
|
"mean_token_accuracy": 0.19624511897563934,
|
|
"num_tokens": 10826098.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.493185043334961,
|
|
"epoch": 4.925434962717482,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00031227928266293933,
|
|
"loss": 5.0304,
|
|
"mean_token_accuracy": 0.19388315826654434,
|
|
"num_tokens": 10836427.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.467928791046143,
|
|
"epoch": 4.929577464788732,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00031196410566736215,
|
|
"loss": 4.9917,
|
|
"mean_token_accuracy": 0.19984488636255265,
|
|
"num_tokens": 10845804.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.507134199142456,
|
|
"epoch": 4.933719966859983,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00031164885411114453,
|
|
"loss": 4.9703,
|
|
"mean_token_accuracy": 0.1995445653796196,
|
|
"num_tokens": 10855951.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.502026081085205,
|
|
"epoch": 4.937862468931234,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00031133352863018315,
|
|
"loss": 5.073,
|
|
"mean_token_accuracy": 0.19959353655576706,
|
|
"num_tokens": 10865528.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.514502048492432,
|
|
"epoch": 4.942004971002485,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00031101812986052406,
|
|
"loss": 5.0204,
|
|
"mean_token_accuracy": 0.20280986726284028,
|
|
"num_tokens": 10874365.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.478115510940552,
|
|
"epoch": 4.9461474730737365,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00031070265843836107,
|
|
"loss": 4.9232,
|
|
"mean_token_accuracy": 0.2066433385014534,
|
|
"num_tokens": 10883034.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.509155035018921,
|
|
"epoch": 4.950289975144988,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003103871150000345,
|
|
"loss": 5.0127,
|
|
"mean_token_accuracy": 0.2026904210448265,
|
|
"num_tokens": 10892307.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.539677619934082,
|
|
"epoch": 4.954432477216239,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00031007150018202983,
|
|
"loss": 5.0489,
|
|
"mean_token_accuracy": 0.20027800500392914,
|
|
"num_tokens": 10902074.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.492472696304321,
|
|
"epoch": 4.95857497928749,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00030975581462097673,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.206236432492733,
|
|
"num_tokens": 10911205.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.436374568939209,
|
|
"epoch": 4.962717481358741,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00030944005895364754,
|
|
"loss": 4.9415,
|
|
"mean_token_accuracy": 0.19798921197652816,
|
|
"num_tokens": 10920371.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.449835872650146,
|
|
"epoch": 4.966859983429992,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00030912423381695584,
|
|
"loss": 4.9171,
|
|
"mean_token_accuracy": 0.21043355166912078,
|
|
"num_tokens": 10928741.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.456011819839477,
|
|
"epoch": 4.971002485501243,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00030880833984795554,
|
|
"loss": 4.9404,
|
|
"mean_token_accuracy": 0.2026234284043312,
|
|
"num_tokens": 10938074.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 4.971002485501243,
|
|
"eval_entropy": 5.296275578073855,
|
|
"eval_loss": 5.708754062652588,
|
|
"eval_mean_token_accuracy": 0.16855560824560967,
|
|
"eval_num_tokens": 10938074.0,
|
|
"eval_runtime": 2.1133,
|
|
"eval_samples_per_second": 1773.059,
|
|
"eval_steps_per_second": 221.928,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.434592914581299,
|
|
"epoch": 4.975144987572493,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0003084923776838392,
|
|
"loss": 4.9591,
|
|
"mean_token_accuracy": 0.20336992144584656,
|
|
"num_tokens": 10946756.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.4559859275817875,
|
|
"epoch": 4.9792874896437445,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00030817634796193705,
|
|
"loss": 4.9256,
|
|
"mean_token_accuracy": 0.20407280027866365,
|
|
"num_tokens": 10956313.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.56329870223999,
|
|
"epoch": 4.983429991714996,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00030786025131971555,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.19975896179676056,
|
|
"num_tokens": 10964333.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.464806461334229,
|
|
"epoch": 4.987572493786247,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003075440883947764,
|
|
"loss": 4.9217,
|
|
"mean_token_accuracy": 0.2059024453163147,
|
|
"num_tokens": 10974110.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.407712411880493,
|
|
"epoch": 4.991714995857498,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003072278598248544,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.20504568368196488,
|
|
"num_tokens": 10983186.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.433735132217407,
|
|
"epoch": 4.995857497928749,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00030691156624781734,
|
|
"loss": 4.9618,
|
|
"mean_token_accuracy": 0.2060353085398674,
|
|
"num_tokens": 10992244.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.477440452575683,
|
|
"epoch": 5.0,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 0.000306595208301664,
|
|
"loss": 4.9419,
|
|
"mean_token_accuracy": 0.20980150401592254,
|
|
"num_tokens": 11000005.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.54671049118042,
|
|
"epoch": 5.004142502071251,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00030627878662452273,
|
|
"loss": 4.7865,
|
|
"mean_token_accuracy": 0.2183009222149849,
|
|
"num_tokens": 11009346.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.53459358215332,
|
|
"epoch": 5.008285004142502,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003059623018546508,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.2178610861301422,
|
|
"num_tokens": 11017844.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.543945407867431,
|
|
"epoch": 5.012427506213753,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003056457546304326,
|
|
"loss": 4.8027,
|
|
"mean_token_accuracy": 0.2212585374712944,
|
|
"num_tokens": 11026840.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.424530076980591,
|
|
"epoch": 5.016570008285004,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0003053291455903782,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.2201804429292679,
|
|
"num_tokens": 11034906.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.443517446517944,
|
|
"epoch": 5.0207125103562555,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00030501247537312293,
|
|
"loss": 4.7972,
|
|
"mean_token_accuracy": 0.22060494720935822,
|
|
"num_tokens": 11044403.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.495531892776489,
|
|
"epoch": 5.024855012427507,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003046957446174251,
|
|
"loss": 4.7615,
|
|
"mean_token_accuracy": 0.22449178695678712,
|
|
"num_tokens": 11052685.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.437995862960816,
|
|
"epoch": 5.028997514498757,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00030437895396216524,
|
|
"loss": 4.6301,
|
|
"mean_token_accuracy": 0.23209116011857986,
|
|
"num_tokens": 11060830.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.50439305305481,
|
|
"epoch": 5.033140016570008,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00030406210404634475,
|
|
"loss": 4.8071,
|
|
"mean_token_accuracy": 0.21365117728710176,
|
|
"num_tokens": 11070220.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.475464868545532,
|
|
"epoch": 5.037282518641259,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003037451955090846,
|
|
"loss": 4.7205,
|
|
"mean_token_accuracy": 0.21721062958240508,
|
|
"num_tokens": 11079171.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.461078071594239,
|
|
"epoch": 5.04142502071251,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00030342822898962377,
|
|
"loss": 4.8007,
|
|
"mean_token_accuracy": 0.21912437826395034,
|
|
"num_tokens": 11089205.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.485667514801025,
|
|
"epoch": 5.045567522783761,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003031112051273185,
|
|
"loss": 4.7943,
|
|
"mean_token_accuracy": 0.22152974754571914,
|
|
"num_tokens": 11098339.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.48903751373291,
|
|
"epoch": 5.049710024855012,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0003027941245616405,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.23162438124418258,
|
|
"num_tokens": 11107218.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.45196270942688,
|
|
"epoch": 5.0538525269262635,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003024769879321761,
|
|
"loss": 4.8055,
|
|
"mean_token_accuracy": 0.2136471837759018,
|
|
"num_tokens": 11116457.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.423411893844604,
|
|
"epoch": 5.057995028997515,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0003021597958786243,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.217820605635643,
|
|
"num_tokens": 11124834.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.435670328140259,
|
|
"epoch": 5.062137531068766,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003018425490407962,
|
|
"loss": 4.8014,
|
|
"mean_token_accuracy": 0.2182242438197136,
|
|
"num_tokens": 11133920.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.562355184555054,
|
|
"epoch": 5.066280033140017,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00030152524805861344,
|
|
"loss": 4.8058,
|
|
"mean_token_accuracy": 0.21577051281929016,
|
|
"num_tokens": 11143573.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.482943058013916,
|
|
"epoch": 5.070422535211268,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00030120789357210667,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.2163441449403763,
|
|
"num_tokens": 11154255.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.500601816177368,
|
|
"epoch": 5.074565037282519,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00030089048622141453,
|
|
"loss": 4.7747,
|
|
"mean_token_accuracy": 0.21439629495143891,
|
|
"num_tokens": 11163306.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.5382904529571535,
|
|
"epoch": 5.078707539353769,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00030057302664678243,
|
|
"loss": 4.7991,
|
|
"mean_token_accuracy": 0.21621798127889633,
|
|
"num_tokens": 11172763.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.466233539581299,
|
|
"epoch": 5.08285004142502,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00030025551548856105,
|
|
"loss": 4.77,
|
|
"mean_token_accuracy": 0.21921129375696183,
|
|
"num_tokens": 11182196.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.468366909027099,
|
|
"epoch": 5.0869925434962715,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002999379533872051,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.21205754429101945,
|
|
"num_tokens": 11192462.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.425205373764038,
|
|
"epoch": 5.091135045567523,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002996203409832719,
|
|
"loss": 4.7792,
|
|
"mean_token_accuracy": 0.21951339691877364,
|
|
"num_tokens": 11201805.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.437849760055542,
|
|
"epoch": 5.095277547638774,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002993026789174205,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.22762458622455597,
|
|
"num_tokens": 11210114.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.512630844116211,
|
|
"epoch": 5.099420049710025,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002989849678304099,
|
|
"loss": 4.8429,
|
|
"mean_token_accuracy": 0.21700824201107025,
|
|
"num_tokens": 11219725.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.48822021484375,
|
|
"epoch": 5.103562551781276,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00029866720836309817,
|
|
"loss": 4.7736,
|
|
"mean_token_accuracy": 0.2168612539768219,
|
|
"num_tokens": 11228583.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.473045015335083,
|
|
"epoch": 5.107705053852527,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00029834940115644086,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.21598098427057266,
|
|
"num_tokens": 11237787.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.420677042007446,
|
|
"epoch": 5.111847555923778,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002980315468514898,
|
|
"loss": 4.8204,
|
|
"mean_token_accuracy": 0.21146066039800643,
|
|
"num_tokens": 11247136.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.385526943206787,
|
|
"epoch": 5.115990057995029,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00029771364608939196,
|
|
"loss": 4.7385,
|
|
"mean_token_accuracy": 0.21921426802873611,
|
|
"num_tokens": 11256931.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.469808959960938,
|
|
"epoch": 5.12013256006628,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002973956995113878,
|
|
"loss": 4.734,
|
|
"mean_token_accuracy": 0.21496936976909636,
|
|
"num_tokens": 11266457.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.394120216369629,
|
|
"epoch": 5.1242750621375315,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0002970777077588103,
|
|
"loss": 4.6961,
|
|
"mean_token_accuracy": 0.22433629184961318,
|
|
"num_tokens": 11274239.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.451945686340332,
|
|
"epoch": 5.128417564208782,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002967596714730837,
|
|
"loss": 4.8111,
|
|
"mean_token_accuracy": 0.21598152667284012,
|
|
"num_tokens": 11283239.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.458475017547608,
|
|
"epoch": 5.132560066280033,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00029644159129572185,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.21690089702606202,
|
|
"num_tokens": 11291662.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.433885192871093,
|
|
"epoch": 5.136702568351284,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002961234678683272,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.22493115663528443,
|
|
"num_tokens": 11300165.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.498241662979126,
|
|
"epoch": 5.140845070422535,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002958053018325896,
|
|
"loss": 4.7612,
|
|
"mean_token_accuracy": 0.22691311985254287,
|
|
"num_tokens": 11309729.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.523032808303833,
|
|
"epoch": 5.144987572493786,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002954870938302846,
|
|
"loss": 4.8042,
|
|
"mean_token_accuracy": 0.21613097339868545,
|
|
"num_tokens": 11318674.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.493018388748169,
|
|
"epoch": 5.149130074565037,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002951688445032726,
|
|
"loss": 4.7708,
|
|
"mean_token_accuracy": 0.2174537107348442,
|
|
"num_tokens": 11327583.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.4980837345123295,
|
|
"epoch": 5.153272576636288,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002948505544934971,
|
|
"loss": 4.804,
|
|
"mean_token_accuracy": 0.2136198654770851,
|
|
"num_tokens": 11338132.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.481460809707642,
|
|
"epoch": 5.1574150787075395,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000294532224442984,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.21525772362947465,
|
|
"num_tokens": 11347210.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.444097328186035,
|
|
"epoch": 5.161557580778791,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00029421385499383976,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.22854493111371993,
|
|
"num_tokens": 11355479.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.490810203552246,
|
|
"epoch": 5.165700082850042,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00029389544678825035,
|
|
"loss": 4.8484,
|
|
"mean_token_accuracy": 0.21038521826267242,
|
|
"num_tokens": 11364518.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.389109516143799,
|
|
"epoch": 5.169842584921293,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00029357700046847985,
|
|
"loss": 4.7861,
|
|
"mean_token_accuracy": 0.21885032802820206,
|
|
"num_tokens": 11373589.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.553474092483521,
|
|
"epoch": 5.173985086992544,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002932585166768694,
|
|
"loss": 4.8408,
|
|
"mean_token_accuracy": 0.21405028253793718,
|
|
"num_tokens": 11383209.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.477250289916992,
|
|
"epoch": 5.178127589063794,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00029293999605583545,
|
|
"loss": 4.7577,
|
|
"mean_token_accuracy": 0.21740917563438417,
|
|
"num_tokens": 11392012.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.450908756256103,
|
|
"epoch": 5.182270091135045,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00029262143924786905,
|
|
"loss": 4.8238,
|
|
"mean_token_accuracy": 0.22159677743911743,
|
|
"num_tokens": 11400489.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.43045744895935,
|
|
"epoch": 5.186412593206296,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00029230284689553404,
|
|
"loss": 4.7171,
|
|
"mean_token_accuracy": 0.21798312813043594,
|
|
"num_tokens": 11409337.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.5001136302948,
|
|
"epoch": 5.190555095277547,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00029198421964146605,
|
|
"loss": 4.7935,
|
|
"mean_token_accuracy": 0.2265946686267853,
|
|
"num_tokens": 11418650.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.411663293838501,
|
|
"epoch": 5.1946975973487985,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002916655581283709,
|
|
"loss": 4.7852,
|
|
"mean_token_accuracy": 0.2133668601512909,
|
|
"num_tokens": 11427516.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.376194429397583,
|
|
"epoch": 5.19884009942005,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00029134686299902397,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.2218948170542717,
|
|
"num_tokens": 11435676.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.467239189147949,
|
|
"epoch": 5.202982601491301,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002910281348962679,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.20708006471395493,
|
|
"num_tokens": 11444520.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.488400840759278,
|
|
"epoch": 5.207125103562552,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00029070937446301225,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.21598300486803054,
|
|
"num_tokens": 11453759.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.6054548740386965,
|
|
"epoch": 5.211267605633803,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002903905823422317,
|
|
"loss": 4.9528,
|
|
"mean_token_accuracy": 0.20207468271255494,
|
|
"num_tokens": 11463409.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.474619579315186,
|
|
"epoch": 5.215410107705054,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002900717591769646,
|
|
"loss": 4.8425,
|
|
"mean_token_accuracy": 0.2173923060297966,
|
|
"num_tokens": 11473440.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.42722373008728,
|
|
"epoch": 5.219552609776305,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002897529056103122,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.2310476452112198,
|
|
"num_tokens": 11482353.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.4291102409362795,
|
|
"epoch": 5.223695111847556,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002894340222854371,
|
|
"loss": 4.8123,
|
|
"mean_token_accuracy": 0.2134431555867195,
|
|
"num_tokens": 11491331.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.382833099365234,
|
|
"epoch": 5.2278376139188065,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002891151098455617,
|
|
"loss": 4.7439,
|
|
"mean_token_accuracy": 0.21155617535114288,
|
|
"num_tokens": 11500553.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.336650228500366,
|
|
"epoch": 5.231980115990058,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002887961689339672,
|
|
"loss": 4.6728,
|
|
"mean_token_accuracy": 0.22340597510337828,
|
|
"num_tokens": 11509146.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.4905458927154545,
|
|
"epoch": 5.236122618061309,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002884772001939924,
|
|
"loss": 4.7963,
|
|
"mean_token_accuracy": 0.21873704791069032,
|
|
"num_tokens": 11518172.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.432288312911988,
|
|
"epoch": 5.24026512013256,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.000288158204269032,
|
|
"loss": 4.7826,
|
|
"mean_token_accuracy": 0.21512478739023208,
|
|
"num_tokens": 11527291.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.442513132095337,
|
|
"epoch": 5.244407622203811,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00028783918180253567,
|
|
"loss": 4.8212,
|
|
"mean_token_accuracy": 0.22035094797611238,
|
|
"num_tokens": 11536306.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.449393844604492,
|
|
"epoch": 5.248550124275062,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002875201334380066,
|
|
"loss": 4.8354,
|
|
"mean_token_accuracy": 0.21605363339185715,
|
|
"num_tokens": 11545879.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.367585945129394,
|
|
"epoch": 5.252692626346313,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002872010598190002,
|
|
"loss": 4.754,
|
|
"mean_token_accuracy": 0.22542914003133774,
|
|
"num_tokens": 11555067.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.455197715759278,
|
|
"epoch": 5.256835128417564,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002868819615891229,
|
|
"loss": 4.7377,
|
|
"mean_token_accuracy": 0.21600868701934814,
|
|
"num_tokens": 11563419.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.369559574127197,
|
|
"epoch": 5.260977630488815,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002865628393920305,
|
|
"loss": 4.7944,
|
|
"mean_token_accuracy": 0.21465019583702089,
|
|
"num_tokens": 11573018.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.372798061370849,
|
|
"epoch": 5.2651201325600665,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002862436938714276,
|
|
"loss": 4.7337,
|
|
"mean_token_accuracy": 0.22554460614919664,
|
|
"num_tokens": 11581996.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.540317010879517,
|
|
"epoch": 5.269262634631318,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002859245256710654,
|
|
"loss": 4.7967,
|
|
"mean_token_accuracy": 0.21396736204624175,
|
|
"num_tokens": 11591706.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.450193929672241,
|
|
"epoch": 5.273405136702569,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002856053354347411,
|
|
"loss": 4.8125,
|
|
"mean_token_accuracy": 0.21414102911949157,
|
|
"num_tokens": 11600616.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.360368824005127,
|
|
"epoch": 5.27754763877382,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002852861238062963,
|
|
"loss": 4.7212,
|
|
"mean_token_accuracy": 0.21919759958982468,
|
|
"num_tokens": 11609650.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.4136251449584964,
|
|
"epoch": 5.28169014084507,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002849668914296157,
|
|
"loss": 4.7251,
|
|
"mean_token_accuracy": 0.22138044685125352,
|
|
"num_tokens": 11618785.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.446357870101929,
|
|
"epoch": 5.285832642916321,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000284647638948626,
|
|
"loss": 4.8075,
|
|
"mean_token_accuracy": 0.2109614446759224,
|
|
"num_tokens": 11628089.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.438767051696777,
|
|
"epoch": 5.289975144987572,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0002843283670072942,
|
|
"loss": 4.8932,
|
|
"mean_token_accuracy": 0.21152670830488204,
|
|
"num_tokens": 11636954.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.443055963516235,
|
|
"epoch": 5.294117647058823,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002840090762496268,
|
|
"loss": 4.8193,
|
|
"mean_token_accuracy": 0.21605568379163742,
|
|
"num_tokens": 11646719.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.426901769638062,
|
|
"epoch": 5.2982601491300745,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002836897673196681,
|
|
"loss": 4.7349,
|
|
"mean_token_accuracy": 0.2195914387702942,
|
|
"num_tokens": 11655589.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.418212175369263,
|
|
"epoch": 5.302402651201326,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00028337044086149913,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.21529311388731004,
|
|
"num_tokens": 11663703.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.462692499160767,
|
|
"epoch": 5.306545153272577,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00028305109751923616,
|
|
"loss": 4.8566,
|
|
"mean_token_accuracy": 0.21293438971042633,
|
|
"num_tokens": 11672643.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.377314710617066,
|
|
"epoch": 5.310687655343828,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00028273173793702967,
|
|
"loss": 4.7273,
|
|
"mean_token_accuracy": 0.21619559526443483,
|
|
"num_tokens": 11681449.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.451302099227905,
|
|
"epoch": 5.314830157415079,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002824123627590629,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.20987386107444764,
|
|
"num_tokens": 11690820.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.436727476119995,
|
|
"epoch": 5.31897265948633,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002820929726295504,
|
|
"loss": 4.8237,
|
|
"mean_token_accuracy": 0.21839972883462905,
|
|
"num_tokens": 11699705.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.41420693397522,
|
|
"epoch": 5.323115161557581,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002817735681927371,
|
|
"loss": 4.7723,
|
|
"mean_token_accuracy": 0.2233524888753891,
|
|
"num_tokens": 11709417.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.483141183853149,
|
|
"epoch": 5.327257663628831,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00028145415009289644,
|
|
"loss": 4.7978,
|
|
"mean_token_accuracy": 0.21502114534378053,
|
|
"num_tokens": 11718661.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.430308866500854,
|
|
"epoch": 5.3314001657000825,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002811347189743297,
|
|
"loss": 4.7851,
|
|
"mean_token_accuracy": 0.21711207926273346,
|
|
"num_tokens": 11727568.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.433426713943481,
|
|
"epoch": 5.335542667771334,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00028081527548136446,
|
|
"loss": 4.7362,
|
|
"mean_token_accuracy": 0.22984818816185,
|
|
"num_tokens": 11736615.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.50225191116333,
|
|
"epoch": 5.339685169842585,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002804958202583531,
|
|
"loss": 4.8527,
|
|
"mean_token_accuracy": 0.20280222445726395,
|
|
"num_tokens": 11747458.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.457773733139038,
|
|
"epoch": 5.343827671913836,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002801763539496718,
|
|
"loss": 4.8257,
|
|
"mean_token_accuracy": 0.21286758184432983,
|
|
"num_tokens": 11756279.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.447610473632812,
|
|
"epoch": 5.347970173985087,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002798568771997188,
|
|
"loss": 4.8226,
|
|
"mean_token_accuracy": 0.21676857620477677,
|
|
"num_tokens": 11765022.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.345885276794434,
|
|
"epoch": 5.352112676056338,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002795373906529137,
|
|
"loss": 4.756,
|
|
"mean_token_accuracy": 0.22197990268468856,
|
|
"num_tokens": 11774704.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.4084617614746096,
|
|
"epoch": 5.356255178127589,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002792178949536959,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.22327479869127273,
|
|
"num_tokens": 11782309.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.437936162948608,
|
|
"epoch": 5.36039768019884,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.000278898390746523,
|
|
"loss": 4.7709,
|
|
"mean_token_accuracy": 0.2152014806866646,
|
|
"num_tokens": 11792595.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.371346807479858,
|
|
"epoch": 5.364540182270091,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00027857887867587005,
|
|
"loss": 4.768,
|
|
"mean_token_accuracy": 0.221083202958107,
|
|
"num_tokens": 11801536.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.431948041915893,
|
|
"epoch": 5.368682684341342,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002782593593862276,
|
|
"loss": 4.836,
|
|
"mean_token_accuracy": 0.21182270348072052,
|
|
"num_tokens": 11810222.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.453006219863892,
|
|
"epoch": 5.3728251864125935,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002779398335221011,
|
|
"loss": 4.8469,
|
|
"mean_token_accuracy": 0.21338119059801103,
|
|
"num_tokens": 11819310.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.431055021286011,
|
|
"epoch": 5.376967688483845,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002776203017280092,
|
|
"loss": 4.8079,
|
|
"mean_token_accuracy": 0.20887526869773865,
|
|
"num_tokens": 11827916.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.381584882736206,
|
|
"epoch": 5.381110190555095,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00027730076464848225,
|
|
"loss": 4.8033,
|
|
"mean_token_accuracy": 0.21812884509563446,
|
|
"num_tokens": 11836770.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.4272040843963625,
|
|
"epoch": 5.385252692626346,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00027698122292806174,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.2201109305024147,
|
|
"num_tokens": 11845917.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"epoch": 5.385252692626346,
|
|
"eval_entropy": 5.295482677183172,
|
|
"eval_loss": 5.71823263168335,
|
|
"eval_mean_token_accuracy": 0.16696258799544275,
|
|
"eval_num_tokens": 11845917.0,
|
|
"eval_runtime": 2.1056,
|
|
"eval_samples_per_second": 1779.554,
|
|
"eval_steps_per_second": 222.741,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.433831596374512,
|
|
"epoch": 5.389395194697597,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000276661677211298,
|
|
"loss": 4.7718,
|
|
"mean_token_accuracy": 0.2149569123983383,
|
|
"num_tokens": 11855118.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.451683187484742,
|
|
"epoch": 5.393537696768848,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0002763421281427497,
|
|
"loss": 4.7155,
|
|
"mean_token_accuracy": 0.21902398765087128,
|
|
"num_tokens": 11863793.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.520257616043091,
|
|
"epoch": 5.397680198840099,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002760225763669823,
|
|
"loss": 4.8627,
|
|
"mean_token_accuracy": 0.2073139250278473,
|
|
"num_tokens": 11873194.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.496034860610962,
|
|
"epoch": 5.40182270091135,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00027570302252856666,
|
|
"loss": 4.8173,
|
|
"mean_token_accuracy": 0.2138901025056839,
|
|
"num_tokens": 11882566.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.403211545944214,
|
|
"epoch": 5.4059652029826015,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00027538346727207767,
|
|
"loss": 4.7676,
|
|
"mean_token_accuracy": 0.22867733985185623,
|
|
"num_tokens": 11892267.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.447514152526855,
|
|
"epoch": 5.410107705053853,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002750639112420934,
|
|
"loss": 4.7926,
|
|
"mean_token_accuracy": 0.2151178926229477,
|
|
"num_tokens": 11901440.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.436370372772217,
|
|
"epoch": 5.414250207125104,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00027474435508319304,
|
|
"loss": 4.877,
|
|
"mean_token_accuracy": 0.21419017314910888,
|
|
"num_tokens": 11911259.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.425209617614746,
|
|
"epoch": 5.418392709196355,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00027442479943995645,
|
|
"loss": 4.8228,
|
|
"mean_token_accuracy": 0.20975672602653503,
|
|
"num_tokens": 11920467.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.47640438079834,
|
|
"epoch": 5.422535211267606,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002741052449569624,
|
|
"loss": 4.848,
|
|
"mean_token_accuracy": 0.21582854837179183,
|
|
"num_tokens": 11929971.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.475642824172974,
|
|
"epoch": 5.426677713338857,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002737856922787869,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.20614602863788606,
|
|
"num_tokens": 11938585.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.443374443054199,
|
|
"epoch": 5.430820215410108,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00027346614205000277,
|
|
"loss": 4.8231,
|
|
"mean_token_accuracy": 0.21363846063613892,
|
|
"num_tokens": 11948264.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.452631330490112,
|
|
"epoch": 5.434962717481358,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00027314659491517777,
|
|
"loss": 4.8363,
|
|
"mean_token_accuracy": 0.21714870631694794,
|
|
"num_tokens": 11958459.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.427863264083863,
|
|
"epoch": 5.4391052195526095,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002728270515188733,
|
|
"loss": 4.8065,
|
|
"mean_token_accuracy": 0.21028958410024642,
|
|
"num_tokens": 11967994.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.495046663284302,
|
|
"epoch": 5.443247721623861,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002725075125056435,
|
|
"loss": 4.8295,
|
|
"mean_token_accuracy": 0.21979930847883225,
|
|
"num_tokens": 11976564.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.468563222885132,
|
|
"epoch": 5.447390223695112,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002721879785200333,
|
|
"loss": 4.7863,
|
|
"mean_token_accuracy": 0.22143933027982712,
|
|
"num_tokens": 11985682.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.485648536682129,
|
|
"epoch": 5.451532725766363,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002718684502065777,
|
|
"loss": 4.8473,
|
|
"mean_token_accuracy": 0.21255629360675812,
|
|
"num_tokens": 11995098.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.496157789230347,
|
|
"epoch": 5.455675227837614,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00027154892820980024,
|
|
"loss": 4.8404,
|
|
"mean_token_accuracy": 0.21534334123134613,
|
|
"num_tokens": 12004538.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.409381484985351,
|
|
"epoch": 5.459817729908865,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00027122941317421175,
|
|
"loss": 4.7927,
|
|
"mean_token_accuracy": 0.21715094596147538,
|
|
"num_tokens": 12012568.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.436244249343872,
|
|
"epoch": 5.463960231980116,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000270909905744309,
|
|
"loss": 4.7992,
|
|
"mean_token_accuracy": 0.2163640022277832,
|
|
"num_tokens": 12021934.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.455532073974609,
|
|
"epoch": 5.468102734051367,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00027059040656457316,
|
|
"loss": 4.8236,
|
|
"mean_token_accuracy": 0.21352484077215195,
|
|
"num_tokens": 12031158.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.530529737472534,
|
|
"epoch": 5.472245236122618,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002702709162794692,
|
|
"loss": 4.8338,
|
|
"mean_token_accuracy": 0.21034690141677856,
|
|
"num_tokens": 12040392.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.426986646652222,
|
|
"epoch": 5.4763877381938695,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00026995143553344394,
|
|
"loss": 4.6976,
|
|
"mean_token_accuracy": 0.2305135667324066,
|
|
"num_tokens": 12048412.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.4003509998321535,
|
|
"epoch": 5.48053024026512,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00026963196497092483,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.21875041872262954,
|
|
"num_tokens": 12057681.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.450639915466309,
|
|
"epoch": 5.484672742336371,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00026931250523631905,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21470981538295747,
|
|
"num_tokens": 12066243.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.37305006980896,
|
|
"epoch": 5.488815244407622,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00026899305697401175,
|
|
"loss": 4.7931,
|
|
"mean_token_accuracy": 0.21998220831155776,
|
|
"num_tokens": 12075312.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.370273876190185,
|
|
"epoch": 5.492957746478873,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002686736208283649,
|
|
"loss": 4.7946,
|
|
"mean_token_accuracy": 0.21559907197952272,
|
|
"num_tokens": 12083990.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.547422075271607,
|
|
"epoch": 5.497100248550124,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00026835419744371627,
|
|
"loss": 4.9039,
|
|
"mean_token_accuracy": 0.20916301608085633,
|
|
"num_tokens": 12093301.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.461936330795288,
|
|
"epoch": 5.501242750621375,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002680347874643775,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.22069742977619172,
|
|
"num_tokens": 12102054.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.403611421585083,
|
|
"epoch": 5.505385252692626,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002677153915346336,
|
|
"loss": 4.8019,
|
|
"mean_token_accuracy": 0.21449972987174987,
|
|
"num_tokens": 12111432.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.361560726165772,
|
|
"epoch": 5.5095277547638775,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002673960102987412,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.22286477982997893,
|
|
"num_tokens": 12120424.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.414562654495239,
|
|
"epoch": 5.513670256835129,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00026707664440092676,
|
|
"loss": 4.8759,
|
|
"mean_token_accuracy": 0.21343374997377396,
|
|
"num_tokens": 12130210.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.580032777786255,
|
|
"epoch": 5.51781275890638,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00026675729448538655,
|
|
"loss": 4.8791,
|
|
"mean_token_accuracy": 0.2155965894460678,
|
|
"num_tokens": 12139366.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.4376091957092285,
|
|
"epoch": 5.521955260977631,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00026643796119628404,
|
|
"loss": 4.6933,
|
|
"mean_token_accuracy": 0.22246579974889755,
|
|
"num_tokens": 12148385.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.469590425491333,
|
|
"epoch": 5.526097763048882,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002661186451777495,
|
|
"loss": 4.8196,
|
|
"mean_token_accuracy": 0.2189146474003792,
|
|
"num_tokens": 12156640.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.467385959625244,
|
|
"epoch": 5.530240265120133,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002657993470738781,
|
|
"loss": 4.9072,
|
|
"mean_token_accuracy": 0.21009976863861085,
|
|
"num_tokens": 12166532.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.378302764892578,
|
|
"epoch": 5.534382767191383,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00026548006752872915,
|
|
"loss": 4.7177,
|
|
"mean_token_accuracy": 0.22540457248687745,
|
|
"num_tokens": 12175239.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.366231632232666,
|
|
"epoch": 5.538525269262634,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002651608071863244,
|
|
"loss": 4.7903,
|
|
"mean_token_accuracy": 0.21326003819704056,
|
|
"num_tokens": 12184588.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.5102955341339115,
|
|
"epoch": 5.542667771333885,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00026484156669064665,
|
|
"loss": 4.8608,
|
|
"mean_token_accuracy": 0.21068965494632722,
|
|
"num_tokens": 12194140.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.471796941757202,
|
|
"epoch": 5.5468102734051365,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.000264522346685639,
|
|
"loss": 4.844,
|
|
"mean_token_accuracy": 0.21482213735580444,
|
|
"num_tokens": 12203504.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.4267150402069095,
|
|
"epoch": 5.550952775476388,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002642031478152031,
|
|
"loss": 4.8191,
|
|
"mean_token_accuracy": 0.2151138424873352,
|
|
"num_tokens": 12212594.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.5075420379638675,
|
|
"epoch": 5.555095277547639,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00026388397072319786,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.21435722410678865,
|
|
"num_tokens": 12222101.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.506843423843383,
|
|
"epoch": 5.55923777961889,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002635648160534385,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.20830531865358354,
|
|
"num_tokens": 12232118.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.511098623275757,
|
|
"epoch": 5.563380281690141,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00026324568444969473,
|
|
"loss": 4.7825,
|
|
"mean_token_accuracy": 0.21439243704080582,
|
|
"num_tokens": 12241275.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.406356430053711,
|
|
"epoch": 5.567522783761392,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026292657655569,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.21956529468297958,
|
|
"num_tokens": 12251125.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.385691452026367,
|
|
"epoch": 5.571665285832643,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00026260749301509954,
|
|
"loss": 4.775,
|
|
"mean_token_accuracy": 0.21846856772899628,
|
|
"num_tokens": 12260613.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.490492105484009,
|
|
"epoch": 5.575807787903894,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00026228843447155005,
|
|
"loss": 4.7807,
|
|
"mean_token_accuracy": 0.2206036329269409,
|
|
"num_tokens": 12269878.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.413063955307007,
|
|
"epoch": 5.5799502899751445,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00026196940156861736,
|
|
"loss": 4.8207,
|
|
"mean_token_accuracy": 0.2111745446920395,
|
|
"num_tokens": 12278616.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.3655540466308596,
|
|
"epoch": 5.584092792046396,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00026165039494982555,
|
|
"loss": 4.7677,
|
|
"mean_token_accuracy": 0.21751515418291092,
|
|
"num_tokens": 12287104.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.3296552181243895,
|
|
"epoch": 5.588235294117647,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00026133141525864605,
|
|
"loss": 4.7678,
|
|
"mean_token_accuracy": 0.21843255311250687,
|
|
"num_tokens": 12296503.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.396792936325073,
|
|
"epoch": 5.592377796188898,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00026101246313849557,
|
|
"loss": 4.7401,
|
|
"mean_token_accuracy": 0.2221747577190399,
|
|
"num_tokens": 12306298.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.437176847457886,
|
|
"epoch": 5.596520298260149,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002606935392327356,
|
|
"loss": 4.7996,
|
|
"mean_token_accuracy": 0.2148914933204651,
|
|
"num_tokens": 12314826.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.427867364883423,
|
|
"epoch": 5.6006628003314,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00026037464418467035,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.22763794362545015,
|
|
"num_tokens": 12323776.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.4940508842468265,
|
|
"epoch": 5.604805302402651,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002600557786375459,
|
|
"loss": 4.8424,
|
|
"mean_token_accuracy": 0.21349895745515823,
|
|
"num_tokens": 12332374.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.391257381439209,
|
|
"epoch": 5.608947804473902,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00025973694323454916,
|
|
"loss": 4.7115,
|
|
"mean_token_accuracy": 0.2260136589407921,
|
|
"num_tokens": 12341007.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.366173505783081,
|
|
"epoch": 5.613090306545153,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00025941813861880575,
|
|
"loss": 4.729,
|
|
"mean_token_accuracy": 0.2264116406440735,
|
|
"num_tokens": 12350330.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.420543146133423,
|
|
"epoch": 5.6172328086164045,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00025909936543337957,
|
|
"loss": 4.7884,
|
|
"mean_token_accuracy": 0.21202905625104904,
|
|
"num_tokens": 12358592.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.458145046234131,
|
|
"epoch": 5.621375310687656,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002587806243212709,
|
|
"loss": 4.814,
|
|
"mean_token_accuracy": 0.21548593640327454,
|
|
"num_tokens": 12368195.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.428471422195434,
|
|
"epoch": 5.625517812758907,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0002584619159254154,
|
|
"loss": 4.7533,
|
|
"mean_token_accuracy": 0.21757490783929825,
|
|
"num_tokens": 12377206.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.385932731628418,
|
|
"epoch": 5.629660314830158,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00025814324088868276,
|
|
"loss": 4.8218,
|
|
"mean_token_accuracy": 0.21550559252500534,
|
|
"num_tokens": 12386595.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.362193059921265,
|
|
"epoch": 5.633802816901408,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00025782459985387526,
|
|
"loss": 4.6784,
|
|
"mean_token_accuracy": 0.2239501655101776,
|
|
"num_tokens": 12395923.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.45798978805542,
|
|
"epoch": 5.637945318972659,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002575059934637268,
|
|
"loss": 4.8486,
|
|
"mean_token_accuracy": 0.21079568564891815,
|
|
"num_tokens": 12405094.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.456348562240601,
|
|
"epoch": 5.64208782104391,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002571874223609012,
|
|
"loss": 4.8478,
|
|
"mean_token_accuracy": 0.2149242639541626,
|
|
"num_tokens": 12414834.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.458777570724488,
|
|
"epoch": 5.646230323115161,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00025686888718799136,
|
|
"loss": 4.7811,
|
|
"mean_token_accuracy": 0.2163038283586502,
|
|
"num_tokens": 12423485.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.491563034057617,
|
|
"epoch": 5.6503728251864125,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002565503885875173,
|
|
"loss": 4.8269,
|
|
"mean_token_accuracy": 0.2157120317220688,
|
|
"num_tokens": 12432149.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.451877498626709,
|
|
"epoch": 5.654515327257664,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00025623192720192564,
|
|
"loss": 4.7999,
|
|
"mean_token_accuracy": 0.2211366355419159,
|
|
"num_tokens": 12441272.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.38624849319458,
|
|
"epoch": 5.658657829328915,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002559135036735877,
|
|
"loss": 4.7687,
|
|
"mean_token_accuracy": 0.21585090160369874,
|
|
"num_tokens": 12449318.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.344919109344483,
|
|
"epoch": 5.662800331400166,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00025559511864479864,
|
|
"loss": 4.7152,
|
|
"mean_token_accuracy": 0.2242381677031517,
|
|
"num_tokens": 12458473.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.452657794952392,
|
|
"epoch": 5.666942833471417,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002552767727577758,
|
|
"loss": 4.8539,
|
|
"mean_token_accuracy": 0.21101416945457457,
|
|
"num_tokens": 12467703.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.462840604782104,
|
|
"epoch": 5.671085335542668,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00025495846665465774,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.22720852345228196,
|
|
"num_tokens": 12476166.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.39289665222168,
|
|
"epoch": 5.675227837613919,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002546402009775024,
|
|
"loss": 4.7635,
|
|
"mean_token_accuracy": 0.22041042149066925,
|
|
"num_tokens": 12484880.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.449253273010254,
|
|
"epoch": 5.679370339685169,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00025432197636828663,
|
|
"loss": 4.855,
|
|
"mean_token_accuracy": 0.21183215379714965,
|
|
"num_tokens": 12494208.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.459166622161865,
|
|
"epoch": 5.683512841756421,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002540037934689042,
|
|
"loss": 4.8403,
|
|
"mean_token_accuracy": 0.21034154295921326,
|
|
"num_tokens": 12503647.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.426748514175415,
|
|
"epoch": 5.687655343827672,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00025368565292116475,
|
|
"loss": 4.86,
|
|
"mean_token_accuracy": 0.21162693351507186,
|
|
"num_tokens": 12512869.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.432263469696045,
|
|
"epoch": 5.691797845898923,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002533675553667927,
|
|
"loss": 4.8972,
|
|
"mean_token_accuracy": 0.20358630418777465,
|
|
"num_tokens": 12523222.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.394979238510132,
|
|
"epoch": 5.695940347970174,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00025304950144742523,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.21640509963035584,
|
|
"num_tokens": 12532343.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.446890449523925,
|
|
"epoch": 5.700082850041425,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002527314918046122,
|
|
"loss": 4.7788,
|
|
"mean_token_accuracy": 0.22089651525020598,
|
|
"num_tokens": 12541508.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.4063488960266115,
|
|
"epoch": 5.704225352112676,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002524135270798136,
|
|
"loss": 4.8384,
|
|
"mean_token_accuracy": 0.2116884022951126,
|
|
"num_tokens": 12550837.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.441629123687744,
|
|
"epoch": 5.708367854183927,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00025209560791439914,
|
|
"loss": 4.7483,
|
|
"mean_token_accuracy": 0.22623147517442704,
|
|
"num_tokens": 12559859.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.42566876411438,
|
|
"epoch": 5.712510356255178,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002517777349496465,
|
|
"loss": 4.8475,
|
|
"mean_token_accuracy": 0.2152115598320961,
|
|
"num_tokens": 12569137.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.489132213592529,
|
|
"epoch": 5.716652858326429,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002514599088267401,
|
|
"loss": 4.8636,
|
|
"mean_token_accuracy": 0.2143091231584549,
|
|
"num_tokens": 12578111.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.453101730346679,
|
|
"epoch": 5.72079536039768,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00025114213018677004,
|
|
"loss": 4.8121,
|
|
"mean_token_accuracy": 0.2178980067372322,
|
|
"num_tokens": 12587604.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.470661211013794,
|
|
"epoch": 5.7249378624689315,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002508243996707305,
|
|
"loss": 4.8448,
|
|
"mean_token_accuracy": 0.20644305199384688,
|
|
"num_tokens": 12596620.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.378992223739624,
|
|
"epoch": 5.729080364540183,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00025050671791951887,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.2147867947816849,
|
|
"num_tokens": 12605452.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.332366514205932,
|
|
"epoch": 5.733222866611433,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002501890855739337,
|
|
"loss": 4.699,
|
|
"mean_token_accuracy": 0.22592171728610994,
|
|
"num_tokens": 12614009.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.467163944244385,
|
|
"epoch": 5.737365368682684,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00024987150327467414,
|
|
"loss": 4.8418,
|
|
"mean_token_accuracy": 0.21397867798805237,
|
|
"num_tokens": 12624135.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.386633348464966,
|
|
"epoch": 5.741507870753935,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00024955397166233855,
|
|
"loss": 4.6884,
|
|
"mean_token_accuracy": 0.2314105212688446,
|
|
"num_tokens": 12632870.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.465042543411255,
|
|
"epoch": 5.745650372825186,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00024923649137742276,
|
|
"loss": 4.8813,
|
|
"mean_token_accuracy": 0.20644859820604325,
|
|
"num_tokens": 12643606.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.532325887680054,
|
|
"epoch": 5.749792874896437,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002489190630603194,
|
|
"loss": 4.9305,
|
|
"mean_token_accuracy": 0.20975972414016725,
|
|
"num_tokens": 12652926.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.484173440933228,
|
|
"epoch": 5.753935376967688,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002486016873513159,
|
|
"loss": 4.8619,
|
|
"mean_token_accuracy": 0.2134840279817581,
|
|
"num_tokens": 12661841.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.383624649047851,
|
|
"epoch": 5.7580778790389395,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0002482843648905937,
|
|
"loss": 4.7864,
|
|
"mean_token_accuracy": 0.21137550771236419,
|
|
"num_tokens": 12670527.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.381709146499634,
|
|
"epoch": 5.762220381110191,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002479670963182271,
|
|
"loss": 4.7845,
|
|
"mean_token_accuracy": 0.20977838933467866,
|
|
"num_tokens": 12680346.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.505164670944214,
|
|
"epoch": 5.766362883181442,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00024764988227418114,
|
|
"loss": 4.8937,
|
|
"mean_token_accuracy": 0.2154889702796936,
|
|
"num_tokens": 12691088.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.499098539352417,
|
|
"epoch": 5.770505385252693,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002473327233983116,
|
|
"loss": 4.8247,
|
|
"mean_token_accuracy": 0.22050438523292543,
|
|
"num_tokens": 12700296.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.395793437957764,
|
|
"epoch": 5.774647887323944,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002470156203303622,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.2142333909869194,
|
|
"num_tokens": 12709595.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.435588741302491,
|
|
"epoch": 5.778790389395195,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002466985737099649,
|
|
"loss": 4.8652,
|
|
"mean_token_accuracy": 0.21067107766866683,
|
|
"num_tokens": 12719052.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.382388067245484,
|
|
"epoch": 5.782932891466446,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002463815841766371,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.22334711998701096,
|
|
"num_tokens": 12727287.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.425153970718384,
|
|
"epoch": 5.787075393537696,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002460646523697813,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.21460428535938264,
|
|
"num_tokens": 12736511.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.513502597808838,
|
|
"epoch": 5.7912178956089475,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00024574777892868386,
|
|
"loss": 4.8182,
|
|
"mean_token_accuracy": 0.21320644915103912,
|
|
"num_tokens": 12745597.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.428305006027221,
|
|
"epoch": 5.795360397680199,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00024543096449251286,
|
|
"loss": 4.7194,
|
|
"mean_token_accuracy": 0.22388887852430345,
|
|
"num_tokens": 12753492.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.446717643737793,
|
|
"epoch": 5.79950289975145,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002451142097003177,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.21813539117574693,
|
|
"num_tokens": 12761999.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 5.79950289975145,
|
|
"eval_entropy": 5.235626658905289,
|
|
"eval_loss": 5.702425003051758,
|
|
"eval_mean_token_accuracy": 0.16891642941086532,
|
|
"eval_num_tokens": 12761999.0,
|
|
"eval_runtime": 2.1043,
|
|
"eval_samples_per_second": 1780.681,
|
|
"eval_steps_per_second": 222.882,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.418811655044555,
|
|
"epoch": 5.803645401822701,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002447975151910276,
|
|
"loss": 4.7522,
|
|
"mean_token_accuracy": 0.2154719799757004,
|
|
"num_tokens": 12770922.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.357079744338989,
|
|
"epoch": 5.807787903893952,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00024448088160344974,
|
|
"loss": 4.7685,
|
|
"mean_token_accuracy": 0.21935390383005143,
|
|
"num_tokens": 12779539.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.4172591209411625,
|
|
"epoch": 5.811930405965203,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002441643095762688,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.22305272817611693,
|
|
"num_tokens": 12788121.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.330478572845459,
|
|
"epoch": 5.816072908036454,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000243847799748045,
|
|
"loss": 4.6684,
|
|
"mean_token_accuracy": 0.22373983412981033,
|
|
"num_tokens": 12797390.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.407525873184204,
|
|
"epoch": 5.820215410107705,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00024353135275721356,
|
|
"loss": 4.8941,
|
|
"mean_token_accuracy": 0.2051371768116951,
|
|
"num_tokens": 12807876.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.3585597515106205,
|
|
"epoch": 5.824357912178956,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00024321496924208235,
|
|
"loss": 4.7197,
|
|
"mean_token_accuracy": 0.21914468556642533,
|
|
"num_tokens": 12816496.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.448475694656372,
|
|
"epoch": 5.8285004142502075,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00024289864984083166,
|
|
"loss": 4.8093,
|
|
"mean_token_accuracy": 0.22273148447275162,
|
|
"num_tokens": 12825925.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.4641180515289305,
|
|
"epoch": 5.832642916321458,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002425823951915122,
|
|
"loss": 4.8153,
|
|
"mean_token_accuracy": 0.21765077263116836,
|
|
"num_tokens": 12835479.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.389421844482422,
|
|
"epoch": 5.836785418392709,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002422662059320442,
|
|
"loss": 4.7148,
|
|
"mean_token_accuracy": 0.22057704776525497,
|
|
"num_tokens": 12844024.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.387544202804565,
|
|
"epoch": 5.84092792046396,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00024195008270021595,
|
|
"loss": 4.7252,
|
|
"mean_token_accuracy": 0.22140638828277587,
|
|
"num_tokens": 12852673.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.356906509399414,
|
|
"epoch": 5.845070422535211,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00024163402613368252,
|
|
"loss": 4.7316,
|
|
"mean_token_accuracy": 0.22485412955284118,
|
|
"num_tokens": 12861191.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.45589017868042,
|
|
"epoch": 5.849212924606462,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00024131803686996457,
|
|
"loss": 4.8975,
|
|
"mean_token_accuracy": 0.21427571773529053,
|
|
"num_tokens": 12870874.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.448425054550171,
|
|
"epoch": 5.853355426677713,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00024100211554644696,
|
|
"loss": 4.801,
|
|
"mean_token_accuracy": 0.21553736925125122,
|
|
"num_tokens": 12879896.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.429235935211182,
|
|
"epoch": 5.857497928748964,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00024068626280037753,
|
|
"loss": 4.8229,
|
|
"mean_token_accuracy": 0.21774092465639114,
|
|
"num_tokens": 12888665.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.418640899658203,
|
|
"epoch": 5.8616404308202155,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00024037047926886578,
|
|
"loss": 4.7761,
|
|
"mean_token_accuracy": 0.2152970626950264,
|
|
"num_tokens": 12897477.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.416188097000122,
|
|
"epoch": 5.865782932891467,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00024005476558888172,
|
|
"loss": 4.8292,
|
|
"mean_token_accuracy": 0.20965196341276168,
|
|
"num_tokens": 12905934.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.429769134521484,
|
|
"epoch": 5.869925434962718,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002397391223972541,
|
|
"loss": 4.8169,
|
|
"mean_token_accuracy": 0.21462374925613403,
|
|
"num_tokens": 12915092.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.457979917526245,
|
|
"epoch": 5.874067937033969,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00023942355033066993,
|
|
"loss": 4.8998,
|
|
"mean_token_accuracy": 0.21498225033283233,
|
|
"num_tokens": 12924775.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.409198045730591,
|
|
"epoch": 5.87821043910522,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00023910805002567244,
|
|
"loss": 4.8118,
|
|
"mean_token_accuracy": 0.21778009384870528,
|
|
"num_tokens": 12933677.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.424250841140747,
|
|
"epoch": 5.882352941176471,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002387926221186603,
|
|
"loss": 4.8387,
|
|
"mean_token_accuracy": 0.2145596042275429,
|
|
"num_tokens": 12942416.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.43080096244812,
|
|
"epoch": 5.886495443247721,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00023847726724588608,
|
|
"loss": 4.8221,
|
|
"mean_token_accuracy": 0.21646394580602646,
|
|
"num_tokens": 12952284.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.471028137207031,
|
|
"epoch": 5.890637945318972,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0002381619860434549,
|
|
"loss": 4.8522,
|
|
"mean_token_accuracy": 0.209468112885952,
|
|
"num_tokens": 12960694.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.333981895446778,
|
|
"epoch": 5.894780447390223,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023784677914732356,
|
|
"loss": 4.7653,
|
|
"mean_token_accuracy": 0.21474358737468718,
|
|
"num_tokens": 12969138.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.3828911781311035,
|
|
"epoch": 5.8989229494614746,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023753164719329868,
|
|
"loss": 4.794,
|
|
"mean_token_accuracy": 0.21704438030719758,
|
|
"num_tokens": 12978518.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.441351222991943,
|
|
"epoch": 5.903065451532726,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00023721659081703595,
|
|
"loss": 4.8347,
|
|
"mean_token_accuracy": 0.21918709576129913,
|
|
"num_tokens": 12987506.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.459297752380371,
|
|
"epoch": 5.907207953603977,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00023690161065403838,
|
|
"loss": 4.8064,
|
|
"mean_token_accuracy": 0.20995470583438874,
|
|
"num_tokens": 12996259.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.475612354278565,
|
|
"epoch": 5.911350455675228,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002365867073396555,
|
|
"loss": 4.8259,
|
|
"mean_token_accuracy": 0.21085815876722336,
|
|
"num_tokens": 13005430.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.4514258861541744,
|
|
"epoch": 5.915492957746479,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00023627188150908174,
|
|
"loss": 4.791,
|
|
"mean_token_accuracy": 0.21973721981048583,
|
|
"num_tokens": 13014915.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.387937116622925,
|
|
"epoch": 5.91963545981773,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023595713379735494,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.21673050671815872,
|
|
"num_tokens": 13023471.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.43996114730835,
|
|
"epoch": 5.923777961888981,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00023564246483935602,
|
|
"loss": 4.7821,
|
|
"mean_token_accuracy": 0.21156890243291854,
|
|
"num_tokens": 13033270.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.435056924819946,
|
|
"epoch": 5.927920463960232,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002353278752698063,
|
|
"loss": 4.7449,
|
|
"mean_token_accuracy": 0.22070836573839187,
|
|
"num_tokens": 13043300.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.415340614318848,
|
|
"epoch": 5.9320629660314825,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002350133657232676,
|
|
"loss": 4.8112,
|
|
"mean_token_accuracy": 0.21366030871868133,
|
|
"num_tokens": 13052152.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.457115364074707,
|
|
"epoch": 5.9362054681027345,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0002346989368341399,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.21786862909793853,
|
|
"num_tokens": 13061704.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.454596471786499,
|
|
"epoch": 5.940347970173985,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00023438458923666057,
|
|
"loss": 4.7859,
|
|
"mean_token_accuracy": 0.22503578960895537,
|
|
"num_tokens": 13071055.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.405187892913818,
|
|
"epoch": 5.944490472245236,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0002340703235649032,
|
|
"loss": 4.8502,
|
|
"mean_token_accuracy": 0.2069684997200966,
|
|
"num_tokens": 13080023.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.46453890800476,
|
|
"epoch": 5.948632974316487,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00023375614045277593,
|
|
"loss": 4.7902,
|
|
"mean_token_accuracy": 0.21278283149003982,
|
|
"num_tokens": 13088690.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.389859294891357,
|
|
"epoch": 5.952775476387738,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00023344204053402047,
|
|
"loss": 4.7786,
|
|
"mean_token_accuracy": 0.2167215809226036,
|
|
"num_tokens": 13097116.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.4843591213226315,
|
|
"epoch": 5.956917978458989,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00023312802444221066,
|
|
"loss": 4.8453,
|
|
"mean_token_accuracy": 0.21450560092926024,
|
|
"num_tokens": 13106463.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.420597934722901,
|
|
"epoch": 5.96106048053024,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002328140928107511,
|
|
"loss": 4.7629,
|
|
"mean_token_accuracy": 0.2191462829709053,
|
|
"num_tokens": 13115769.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.496691179275513,
|
|
"epoch": 5.965202982601491,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.0002325002462728766,
|
|
"loss": 4.864,
|
|
"mean_token_accuracy": 0.2178991138935089,
|
|
"num_tokens": 13124928.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.440690040588379,
|
|
"epoch": 5.9693454846727425,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00023218648546164945,
|
|
"loss": 4.779,
|
|
"mean_token_accuracy": 0.21622900068759918,
|
|
"num_tokens": 13134106.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.553424501419068,
|
|
"epoch": 5.973487986743994,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0002318728110099599,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.20522000938653945,
|
|
"num_tokens": 13143019.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.465690851211548,
|
|
"epoch": 5.977630488815245,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 0.00023155922355052339,
|
|
"loss": 4.7324,
|
|
"mean_token_accuracy": 0.23542484045028686,
|
|
"num_tokens": 13152675.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.413678789138794,
|
|
"epoch": 5.981772990886496,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00023124572371588,
|
|
"loss": 4.7548,
|
|
"mean_token_accuracy": 0.22440996915102004,
|
|
"num_tokens": 13161094.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.377568340301513,
|
|
"epoch": 5.985915492957746,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023093231213839344,
|
|
"loss": 4.8311,
|
|
"mean_token_accuracy": 0.21527986079454423,
|
|
"num_tokens": 13170858.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.439410066604614,
|
|
"epoch": 5.990057995028997,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002306189894502488,
|
|
"loss": 4.8954,
|
|
"mean_token_accuracy": 0.20768713355064392,
|
|
"num_tokens": 13179668.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.453110408782959,
|
|
"epoch": 5.994200497100248,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023030575628345246,
|
|
"loss": 4.7523,
|
|
"mean_token_accuracy": 0.22022200077772142,
|
|
"num_tokens": 13188312.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.3985027313232425,
|
|
"epoch": 5.998342999171499,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00022999261326982985,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.21452391147613525,
|
|
"num_tokens": 13196989.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.407035970687867,
|
|
"epoch": 6.0024855012427505,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00022967956104102445,
|
|
"loss": 4.6917,
|
|
"mean_token_accuracy": 0.22965297251939773,
|
|
"num_tokens": 13205830.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.517871284484864,
|
|
"epoch": 6.006628003314002,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00022936660022849714,
|
|
"loss": 4.663,
|
|
"mean_token_accuracy": 0.24019485265016555,
|
|
"num_tokens": 13214711.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.417104768753052,
|
|
"epoch": 6.010770505385253,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022905373146352382,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.22497337758541108,
|
|
"num_tokens": 13223736.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.427345323562622,
|
|
"epoch": 6.014913007456504,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002287409553771952,
|
|
"loss": 4.6264,
|
|
"mean_token_accuracy": 0.2284184142947197,
|
|
"num_tokens": 13232666.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.43447585105896,
|
|
"epoch": 6.019055509527755,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00022842827260041455,
|
|
"loss": 4.6657,
|
|
"mean_token_accuracy": 0.22457592636346818,
|
|
"num_tokens": 13241770.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.40849871635437,
|
|
"epoch": 6.023198011599006,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022811568376389745,
|
|
"loss": 4.611,
|
|
"mean_token_accuracy": 0.23637997806072236,
|
|
"num_tokens": 13250475.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.386483097076416,
|
|
"epoch": 6.027340513670257,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00022780318949816963,
|
|
"loss": 4.5883,
|
|
"mean_token_accuracy": 0.23193755596876145,
|
|
"num_tokens": 13259587.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.365642404556274,
|
|
"epoch": 6.031483015741508,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00022749079043356623,
|
|
"loss": 4.6041,
|
|
"mean_token_accuracy": 0.23995189517736434,
|
|
"num_tokens": 13269681.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.384715127944946,
|
|
"epoch": 6.0356255178127585,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00022717848720023022,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.23736099302768707,
|
|
"num_tokens": 13278186.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.4106611728668215,
|
|
"epoch": 6.03976801988401,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00022686628042811142,
|
|
"loss": 4.6958,
|
|
"mean_token_accuracy": 0.22742535471916198,
|
|
"num_tokens": 13287194.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.4748200416564945,
|
|
"epoch": 6.043910521955261,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.000226554170746965,
|
|
"loss": 4.7461,
|
|
"mean_token_accuracy": 0.2214070588350296,
|
|
"num_tokens": 13296774.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.5224097728729244,
|
|
"epoch": 6.048053024026512,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00022624215878635023,
|
|
"loss": 4.6573,
|
|
"mean_token_accuracy": 0.22894876599311828,
|
|
"num_tokens": 13306368.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.495062398910522,
|
|
"epoch": 6.052195526097763,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00022593024517562945,
|
|
"loss": 4.6456,
|
|
"mean_token_accuracy": 0.23093235194683076,
|
|
"num_tokens": 13315393.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.3749932765960695,
|
|
"epoch": 6.056338028169014,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022561843054396636,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.24058791846036912,
|
|
"num_tokens": 13324384.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.418632364273071,
|
|
"epoch": 6.060480530240265,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00022530671552032521,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.22645162642002106,
|
|
"num_tokens": 13333191.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.384301567077637,
|
|
"epoch": 6.064623032311516,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002249951007334693,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.2274565726518631,
|
|
"num_tokens": 13342911.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.493674087524414,
|
|
"epoch": 6.068765534382767,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00022468358681195966,
|
|
"loss": 4.6457,
|
|
"mean_token_accuracy": 0.23302445709705352,
|
|
"num_tokens": 13352464.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.437693977355957,
|
|
"epoch": 6.072908036454018,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00022437217438415393,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.23085545003414154,
|
|
"num_tokens": 13361812.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.444894409179687,
|
|
"epoch": 6.0770505385252696,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00022406086407820503,
|
|
"loss": 4.7199,
|
|
"mean_token_accuracy": 0.2264823228120804,
|
|
"num_tokens": 13372080.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.471525001525879,
|
|
"epoch": 6.081193040596521,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00022374965652205975,
|
|
"loss": 4.7722,
|
|
"mean_token_accuracy": 0.2198364943265915,
|
|
"num_tokens": 13380897.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.542355155944824,
|
|
"epoch": 6.085335542667772,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00022343855234345796,
|
|
"loss": 4.7816,
|
|
"mean_token_accuracy": 0.21735544204711915,
|
|
"num_tokens": 13389885.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.422695779800415,
|
|
"epoch": 6.089478044739022,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022312755216993065,
|
|
"loss": 4.691,
|
|
"mean_token_accuracy": 0.2277865320444107,
|
|
"num_tokens": 13399734.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.341671085357666,
|
|
"epoch": 6.093620546810273,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022281665662879903,
|
|
"loss": 4.6126,
|
|
"mean_token_accuracy": 0.2335656002163887,
|
|
"num_tokens": 13408641.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.403586101531983,
|
|
"epoch": 6.097763048881524,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022250586634717362,
|
|
"loss": 4.6798,
|
|
"mean_token_accuracy": 0.2260579138994217,
|
|
"num_tokens": 13418585.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.401862049102784,
|
|
"epoch": 6.101905550952775,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00022219518195195216,
|
|
"loss": 4.5915,
|
|
"mean_token_accuracy": 0.23450362533330918,
|
|
"num_tokens": 13427897.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.309825325012207,
|
|
"epoch": 6.106048053024026,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00022188460406981925,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.23063685446977616,
|
|
"num_tokens": 13437311.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.4363795757293705,
|
|
"epoch": 6.1101905550952775,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00022157413332724436,
|
|
"loss": 4.6386,
|
|
"mean_token_accuracy": 0.2336140379309654,
|
|
"num_tokens": 13446359.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.4612593173980715,
|
|
"epoch": 6.114333057166529,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022126377035048072,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.22881311178207397,
|
|
"num_tokens": 13455302.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.5382421016693115,
|
|
"epoch": 6.11847555923778,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002209535157655646,
|
|
"loss": 4.7901,
|
|
"mean_token_accuracy": 0.22807631641626358,
|
|
"num_tokens": 13466391.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.410840320587158,
|
|
"epoch": 6.122618061309031,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00022064337019831322,
|
|
"loss": 4.6077,
|
|
"mean_token_accuracy": 0.23774069547653198,
|
|
"num_tokens": 13476130.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.377289199829102,
|
|
"epoch": 6.126760563380282,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 0.00022033333427432422,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.23769891262054443,
|
|
"num_tokens": 13485105.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.411421012878418,
|
|
"epoch": 6.130903065451533,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0002200234086189738,
|
|
"loss": 4.6604,
|
|
"mean_token_accuracy": 0.22594629228115082,
|
|
"num_tokens": 13494914.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.386888837814331,
|
|
"epoch": 6.135045567522784,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00021971359385741608,
|
|
"loss": 4.6906,
|
|
"mean_token_accuracy": 0.23008441030979157,
|
|
"num_tokens": 13504293.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.506200551986694,
|
|
"epoch": 6.139188069594034,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00021940389061458115,
|
|
"loss": 4.7719,
|
|
"mean_token_accuracy": 0.22557346373796464,
|
|
"num_tokens": 13513972.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.441185045242309,
|
|
"epoch": 6.1433305716652855,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0002190942995151743,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.22787799835205078,
|
|
"num_tokens": 13522508.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.476191234588623,
|
|
"epoch": 6.147473073736537,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002187848211836746,
|
|
"loss": 4.6114,
|
|
"mean_token_accuracy": 0.23429475128650665,
|
|
"num_tokens": 13531235.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.431963109970093,
|
|
"epoch": 6.151615575807788,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002184754562443337,
|
|
"loss": 4.6372,
|
|
"mean_token_accuracy": 0.23329923152923585,
|
|
"num_tokens": 13541023.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.387637186050415,
|
|
"epoch": 6.155758077879039,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00021816620532117448,
|
|
"loss": 4.6503,
|
|
"mean_token_accuracy": 0.2339947521686554,
|
|
"num_tokens": 13550622.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.380233955383301,
|
|
"epoch": 6.15990057995029,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002178570690379899,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22735521644353868,
|
|
"num_tokens": 13559423.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.401749134063721,
|
|
"epoch": 6.164043082021541,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00021754804801834144,
|
|
"loss": 4.6489,
|
|
"mean_token_accuracy": 0.23022455126047134,
|
|
"num_tokens": 13569306.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.41665678024292,
|
|
"epoch": 6.168185584092792,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002172391428855585,
|
|
"loss": 4.6048,
|
|
"mean_token_accuracy": 0.24071319103240968,
|
|
"num_tokens": 13578367.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.408527803421021,
|
|
"epoch": 6.172328086164043,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00021693035426273633,
|
|
"loss": 4.6713,
|
|
"mean_token_accuracy": 0.2261669874191284,
|
|
"num_tokens": 13586930.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.39840292930603,
|
|
"epoch": 6.176470588235294,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00021662168277273547,
|
|
"loss": 4.6486,
|
|
"mean_token_accuracy": 0.23442137390375137,
|
|
"num_tokens": 13595891.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.458778619766235,
|
|
"epoch": 6.1806130903065455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002163131290381799,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.22754103392362596,
|
|
"num_tokens": 13605786.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.3644359588623045,
|
|
"epoch": 6.184755592377797,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00021600469368145624,
|
|
"loss": 4.6143,
|
|
"mean_token_accuracy": 0.24066076725721358,
|
|
"num_tokens": 13614561.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.407718133926392,
|
|
"epoch": 6.188898094449047,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002156963773247124,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.23384837210178375,
|
|
"num_tokens": 13622853.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.398718929290771,
|
|
"epoch": 6.193040596520298,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002153881805898561,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.23089651316404342,
|
|
"num_tokens": 13631709.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.469316196441651,
|
|
"epoch": 6.197183098591549,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002150801040985539,
|
|
"loss": 4.679,
|
|
"mean_token_accuracy": 0.22968138456344606,
|
|
"num_tokens": 13640854.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.361333322525025,
|
|
"epoch": 6.2013256006628,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00021477214847222958,
|
|
"loss": 4.6128,
|
|
"mean_token_accuracy": 0.2349829852581024,
|
|
"num_tokens": 13649318.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.446784496307373,
|
|
"epoch": 6.205468102734051,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00021446431433206348,
|
|
"loss": 4.7157,
|
|
"mean_token_accuracy": 0.22905034869909285,
|
|
"num_tokens": 13658738.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.3289001941680905,
|
|
"epoch": 6.209610604805302,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0002141566022989907,
|
|
"loss": 4.6213,
|
|
"mean_token_accuracy": 0.236270672082901,
|
|
"num_tokens": 13667315.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.40364441871643,
|
|
"epoch": 6.2137531068765535,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0002138490129936998,
|
|
"loss": 4.7165,
|
|
"mean_token_accuracy": 0.22361717373132706,
|
|
"num_tokens": 13676665.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"epoch": 6.2137531068765535,
|
|
"eval_entropy": 5.220506001128825,
|
|
"eval_loss": 5.715770721435547,
|
|
"eval_mean_token_accuracy": 0.16852646487862316,
|
|
"eval_num_tokens": 13676665.0,
|
|
"eval_runtime": 2.0998,
|
|
"eval_samples_per_second": 1784.498,
|
|
"eval_steps_per_second": 223.36,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.377321052551269,
|
|
"epoch": 6.217895608947805,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002135415470366323,
|
|
"loss": 4.6707,
|
|
"mean_token_accuracy": 0.22697622776031495,
|
|
"num_tokens": 13685774.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.395576333999633,
|
|
"epoch": 6.222038111019056,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00021323420504798047,
|
|
"loss": 4.6983,
|
|
"mean_token_accuracy": 0.22571493238210677,
|
|
"num_tokens": 13695700.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.44204273223877,
|
|
"epoch": 6.226180613090307,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00021292698764768675,
|
|
"loss": 4.7053,
|
|
"mean_token_accuracy": 0.2294199526309967,
|
|
"num_tokens": 13704675.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.413439607620239,
|
|
"epoch": 6.230323115161558,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00021261989545544218,
|
|
"loss": 4.7466,
|
|
"mean_token_accuracy": 0.230139821767807,
|
|
"num_tokens": 13714562.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.504620313644409,
|
|
"epoch": 6.234465617232809,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00021231292909068534,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.23259584307670594,
|
|
"num_tokens": 13723917.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.461557865142822,
|
|
"epoch": 6.238608119304059,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00021200608917260082,
|
|
"loss": 4.6472,
|
|
"mean_token_accuracy": 0.234765163064003,
|
|
"num_tokens": 13732482.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.447933483123779,
|
|
"epoch": 6.24275062137531,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00021169937632011838,
|
|
"loss": 4.7117,
|
|
"mean_token_accuracy": 0.22556028217077256,
|
|
"num_tokens": 13742110.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.371204948425293,
|
|
"epoch": 6.2468931234465614,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00021139279115191123,
|
|
"loss": 4.6491,
|
|
"mean_token_accuracy": 0.22453851550817489,
|
|
"num_tokens": 13750501.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.400085353851319,
|
|
"epoch": 6.2510356255178126,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00021108633428639534,
|
|
"loss": 4.6253,
|
|
"mean_token_accuracy": 0.2346968710422516,
|
|
"num_tokens": 13759786.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.415467071533203,
|
|
"epoch": 6.255178127589064,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002107800063417275,
|
|
"loss": 4.6853,
|
|
"mean_token_accuracy": 0.2291399508714676,
|
|
"num_tokens": 13768476.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.436420249938965,
|
|
"epoch": 6.259320629660315,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002104738079358048,
|
|
"loss": 4.7153,
|
|
"mean_token_accuracy": 0.21263056099414826,
|
|
"num_tokens": 13778721.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.4649742603302,
|
|
"epoch": 6.263463131731566,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002101677396862628,
|
|
"loss": 4.6912,
|
|
"mean_token_accuracy": 0.22945401221513748,
|
|
"num_tokens": 13787108.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.375363063812256,
|
|
"epoch": 6.267605633802817,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00020986180221047463,
|
|
"loss": 4.6151,
|
|
"mean_token_accuracy": 0.23926387578248978,
|
|
"num_tokens": 13795021.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.339077949523926,
|
|
"epoch": 6.271748135874068,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00020955599612554966,
|
|
"loss": 4.6686,
|
|
"mean_token_accuracy": 0.2295590743422508,
|
|
"num_tokens": 13804750.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.360949230194092,
|
|
"epoch": 6.275890637945319,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00020925032204833206,
|
|
"loss": 4.6445,
|
|
"mean_token_accuracy": 0.23648180067539215,
|
|
"num_tokens": 13813910.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.492851400375367,
|
|
"epoch": 6.28003314001657,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00020894478059539995,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.2301545411348343,
|
|
"num_tokens": 13822832.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.355139064788818,
|
|
"epoch": 6.284175642087821,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00020863937238306375,
|
|
"loss": 4.6217,
|
|
"mean_token_accuracy": 0.23455758690834044,
|
|
"num_tokens": 13831951.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.320128583908081,
|
|
"epoch": 6.2883181441590725,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00020833409802736535,
|
|
"loss": 4.6016,
|
|
"mean_token_accuracy": 0.23716724365949632,
|
|
"num_tokens": 13840422.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.44162950515747,
|
|
"epoch": 6.292460646230323,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00020802895814407636,
|
|
"loss": 4.6967,
|
|
"mean_token_accuracy": 0.22992716133594512,
|
|
"num_tokens": 13850903.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.438109397888184,
|
|
"epoch": 6.296603148301574,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0002077239533486972,
|
|
"loss": 4.7542,
|
|
"mean_token_accuracy": 0.21345373690128328,
|
|
"num_tokens": 13859972.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.408207511901855,
|
|
"epoch": 6.300745650372825,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00020741908425645606,
|
|
"loss": 4.7168,
|
|
"mean_token_accuracy": 0.230913382768631,
|
|
"num_tokens": 13868980.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.404915857315063,
|
|
"epoch": 6.304888152444076,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00020711435148230707,
|
|
"loss": 4.6481,
|
|
"mean_token_accuracy": 0.23207687884569167,
|
|
"num_tokens": 13877901.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.359070444107056,
|
|
"epoch": 6.309030654515327,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00020680975564092968,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.23118752986192703,
|
|
"num_tokens": 13887081.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.442977809906006,
|
|
"epoch": 6.313173156586578,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020650529734672686,
|
|
"loss": 4.7498,
|
|
"mean_token_accuracy": 0.22648316919803618,
|
|
"num_tokens": 13896645.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.509846210479736,
|
|
"epoch": 6.317315658657829,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00020620097721382424,
|
|
"loss": 4.7144,
|
|
"mean_token_accuracy": 0.22262957841157913,
|
|
"num_tokens": 13905975.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.466513299942017,
|
|
"epoch": 6.3214581607290805,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.0002058967958560689,
|
|
"loss": 4.6649,
|
|
"mean_token_accuracy": 0.23391267359256745,
|
|
"num_tokens": 13914605.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.407799148559571,
|
|
"epoch": 6.325600662800332,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00020559275388702775,
|
|
"loss": 4.618,
|
|
"mean_token_accuracy": 0.23507697582244874,
|
|
"num_tokens": 13924592.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.336037254333496,
|
|
"epoch": 6.329743164871583,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.00020528885191998682,
|
|
"loss": 4.6526,
|
|
"mean_token_accuracy": 0.22918911427259445,
|
|
"num_tokens": 13933513.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.298666095733642,
|
|
"epoch": 6.333885666942834,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00020498509056794952,
|
|
"loss": 4.5275,
|
|
"mean_token_accuracy": 0.24376317113637924,
|
|
"num_tokens": 13942173.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.32671160697937,
|
|
"epoch": 6.338028169014084,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00020468147044363556,
|
|
"loss": 4.5434,
|
|
"mean_token_accuracy": 0.24203468710184098,
|
|
"num_tokens": 13950205.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.376557111740112,
|
|
"epoch": 6.342170671085335,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00020437799215948017,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.23451030105352402,
|
|
"num_tokens": 13958956.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.353063440322876,
|
|
"epoch": 6.346313173156586,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0002040746563276319,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.23232905119657515,
|
|
"num_tokens": 13967718.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.357116842269898,
|
|
"epoch": 6.350455675227837,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00020377146355995257,
|
|
"loss": 4.7321,
|
|
"mean_token_accuracy": 0.22148074060678483,
|
|
"num_tokens": 13976841.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.427138471603394,
|
|
"epoch": 6.3545981772990885,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00020346841446801495,
|
|
"loss": 4.6149,
|
|
"mean_token_accuracy": 0.23659945726394654,
|
|
"num_tokens": 13984946.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.390640163421631,
|
|
"epoch": 6.35874067937034,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00020316550966310222,
|
|
"loss": 4.6678,
|
|
"mean_token_accuracy": 0.2283580020070076,
|
|
"num_tokens": 13993521.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.364171171188355,
|
|
"epoch": 6.362883181441591,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0002028627497562065,
|
|
"loss": 4.6609,
|
|
"mean_token_accuracy": 0.2294827491044998,
|
|
"num_tokens": 14002777.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.373416805267334,
|
|
"epoch": 6.367025683512842,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00020256013535802748,
|
|
"loss": 4.6919,
|
|
"mean_token_accuracy": 0.2223594069480896,
|
|
"num_tokens": 14012708.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.424908447265625,
|
|
"epoch": 6.371168185584093,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0002022576670789717,
|
|
"loss": 4.7122,
|
|
"mean_token_accuracy": 0.2232012704014778,
|
|
"num_tokens": 14021088.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.429780721664429,
|
|
"epoch": 6.375310687655344,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0002019553455291505,
|
|
"loss": 4.7181,
|
|
"mean_token_accuracy": 0.22308735251426698,
|
|
"num_tokens": 14031650.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.416965579986572,
|
|
"epoch": 6.379453189726595,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0002016531713183797,
|
|
"loss": 4.7304,
|
|
"mean_token_accuracy": 0.22664651423692703,
|
|
"num_tokens": 14040741.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.413306999206543,
|
|
"epoch": 6.383595691797846,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00020135114505617752,
|
|
"loss": 4.6942,
|
|
"mean_token_accuracy": 0.22197419852018357,
|
|
"num_tokens": 14049913.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.413315343856811,
|
|
"epoch": 6.387738193869097,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00020104926735176393,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.23318218141794206,
|
|
"num_tokens": 14059583.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.454882049560547,
|
|
"epoch": 6.391880695940348,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00020074753881405949,
|
|
"loss": 4.6294,
|
|
"mean_token_accuracy": 0.23486190438270568,
|
|
"num_tokens": 14067376.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.39584755897522,
|
|
"epoch": 6.396023198011599,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002004459600516833,
|
|
"loss": 4.6936,
|
|
"mean_token_accuracy": 0.23382564932107924,
|
|
"num_tokens": 14076415.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.452566242218017,
|
|
"epoch": 6.40016570008285,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00020014453167295298,
|
|
"loss": 4.6863,
|
|
"mean_token_accuracy": 0.2241110160946846,
|
|
"num_tokens": 14085418.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.389129161834717,
|
|
"epoch": 6.404308202154101,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00019984325428588229,
|
|
"loss": 4.6766,
|
|
"mean_token_accuracy": 0.23349845111370088,
|
|
"num_tokens": 14094454.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.401219081878662,
|
|
"epoch": 6.408450704225352,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00019954212849818077,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.23996456414461137,
|
|
"num_tokens": 14103611.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.355923509597778,
|
|
"epoch": 6.412593206296603,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00019924115491725197,
|
|
"loss": 4.5352,
|
|
"mean_token_accuracy": 0.23699738830327988,
|
|
"num_tokens": 14112145.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.366793012619018,
|
|
"epoch": 6.416735708367854,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00019894033415019253,
|
|
"loss": 4.675,
|
|
"mean_token_accuracy": 0.2298393502831459,
|
|
"num_tokens": 14121215.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.314970970153809,
|
|
"epoch": 6.420878210439105,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00019863966680379086,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.23198034316301347,
|
|
"num_tokens": 14130106.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.329961919784546,
|
|
"epoch": 6.4250207125103564,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001983391534845258,
|
|
"loss": 4.6059,
|
|
"mean_token_accuracy": 0.2420319452881813,
|
|
"num_tokens": 14139071.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.381771469116211,
|
|
"epoch": 6.4291632145816076,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00019803879479856547,
|
|
"loss": 4.6541,
|
|
"mean_token_accuracy": 0.23084716349840165,
|
|
"num_tokens": 14148018.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.373312711715698,
|
|
"epoch": 6.433305716652859,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00019773859135176626,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.23925475180149078,
|
|
"num_tokens": 14156369.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.414871120452881,
|
|
"epoch": 6.43744821872411,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001974385437496713,
|
|
"loss": 4.7009,
|
|
"mean_token_accuracy": 0.22606036812067032,
|
|
"num_tokens": 14165930.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.353491735458374,
|
|
"epoch": 6.44159072079536,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019713865259750945,
|
|
"loss": 4.6531,
|
|
"mean_token_accuracy": 0.23343491405248643,
|
|
"num_tokens": 14175557.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.44106616973877,
|
|
"epoch": 6.445733222866611,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00019683891850019391,
|
|
"loss": 4.7258,
|
|
"mean_token_accuracy": 0.22561880946159363,
|
|
"num_tokens": 14185532.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.496881294250488,
|
|
"epoch": 6.449875724937862,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00019653934206232098,
|
|
"loss": 4.8074,
|
|
"mean_token_accuracy": 0.21910179406404495,
|
|
"num_tokens": 14194307.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.4424745559692385,
|
|
"epoch": 6.454018227009113,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019623992388816935,
|
|
"loss": 4.7585,
|
|
"mean_token_accuracy": 0.22818599939346312,
|
|
"num_tokens": 14203900.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.406968879699707,
|
|
"epoch": 6.458160729080364,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001959406645816979,
|
|
"loss": 4.6568,
|
|
"mean_token_accuracy": 0.23045513331890105,
|
|
"num_tokens": 14213232.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.375060319900513,
|
|
"epoch": 6.4623032311516155,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00019564156474654554,
|
|
"loss": 4.5948,
|
|
"mean_token_accuracy": 0.2270186647772789,
|
|
"num_tokens": 14221365.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.335002613067627,
|
|
"epoch": 6.466445733222867,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00019534262498602928,
|
|
"loss": 4.6377,
|
|
"mean_token_accuracy": 0.22887873351573945,
|
|
"num_tokens": 14229878.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.4351935386657715,
|
|
"epoch": 6.470588235294118,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00019504384590314318,
|
|
"loss": 4.6832,
|
|
"mean_token_accuracy": 0.2247671127319336,
|
|
"num_tokens": 14239132.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.423367023468018,
|
|
"epoch": 6.474730737365369,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00019474522810055745,
|
|
"loss": 4.6966,
|
|
"mean_token_accuracy": 0.23264526724815368,
|
|
"num_tokens": 14247116.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.350279140472412,
|
|
"epoch": 6.47887323943662,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00019444677218061673,
|
|
"loss": 4.66,
|
|
"mean_token_accuracy": 0.23234000951051711,
|
|
"num_tokens": 14255423.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.383958196640014,
|
|
"epoch": 6.483015741507871,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.0001941484787453393,
|
|
"loss": 4.6318,
|
|
"mean_token_accuracy": 0.23316776305437087,
|
|
"num_tokens": 14263836.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.3744409561157225,
|
|
"epoch": 6.487158243579122,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019385034839641558,
|
|
"loss": 4.7284,
|
|
"mean_token_accuracy": 0.22707869559526445,
|
|
"num_tokens": 14273460.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.405040121078491,
|
|
"epoch": 6.491300745650372,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001935523817352071,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.22828752249479295,
|
|
"num_tokens": 14282925.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.426750326156617,
|
|
"epoch": 6.4954432477216235,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00019325457936274516,
|
|
"loss": 4.6596,
|
|
"mean_token_accuracy": 0.2346562296152115,
|
|
"num_tokens": 14292059.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.436620473861694,
|
|
"epoch": 6.499585749792875,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00019295694187972955,
|
|
"loss": 4.6809,
|
|
"mean_token_accuracy": 0.22864598631858826,
|
|
"num_tokens": 14301276.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.434348821640015,
|
|
"epoch": 6.503728251864126,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00019265946988652783,
|
|
"loss": 4.6985,
|
|
"mean_token_accuracy": 0.2246260389685631,
|
|
"num_tokens": 14310259.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.370514154434204,
|
|
"epoch": 6.507870753935377,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001923621639831733,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.2369073823094368,
|
|
"num_tokens": 14318782.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.334285926818848,
|
|
"epoch": 6.512013256006628,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00019206502476936467,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.24181342869997025,
|
|
"num_tokens": 14327571.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.310634899139404,
|
|
"epoch": 6.516155758077879,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00019176805284446414,
|
|
"loss": 4.5963,
|
|
"mean_token_accuracy": 0.23608282804489136,
|
|
"num_tokens": 14336974.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.428483533859253,
|
|
"epoch": 6.52029826014913,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00019147124880749633,
|
|
"loss": 4.7499,
|
|
"mean_token_accuracy": 0.22559782415628432,
|
|
"num_tokens": 14346367.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.417099189758301,
|
|
"epoch": 6.524440762220381,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00019117461325714768,
|
|
"loss": 4.6905,
|
|
"mean_token_accuracy": 0.23086734861135483,
|
|
"num_tokens": 14355641.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.436104011535645,
|
|
"epoch": 6.528583264291632,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00019087814679176436,
|
|
"loss": 4.6334,
|
|
"mean_token_accuracy": 0.22980011850595475,
|
|
"num_tokens": 14364927.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.406087398529053,
|
|
"epoch": 6.5327257663628835,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00019058185000935175,
|
|
"loss": 4.6236,
|
|
"mean_token_accuracy": 0.23580149561166763,
|
|
"num_tokens": 14373370.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.441199588775635,
|
|
"epoch": 6.536868268434135,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00019028572350757278,
|
|
"loss": 4.6847,
|
|
"mean_token_accuracy": 0.2277800604701042,
|
|
"num_tokens": 14381820.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.413390636444092,
|
|
"epoch": 6.541010770505386,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018998976788374682,
|
|
"loss": 4.6665,
|
|
"mean_token_accuracy": 0.23163654506206513,
|
|
"num_tokens": 14391158.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.3650702953338625,
|
|
"epoch": 6.545153272576636,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00018969398373484898,
|
|
"loss": 4.6816,
|
|
"mean_token_accuracy": 0.22842385470867158,
|
|
"num_tokens": 14399945.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.389668655395508,
|
|
"epoch": 6.549295774647887,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00018939837165750796,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.23485509753227235,
|
|
"num_tokens": 14410275.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.454287767410278,
|
|
"epoch": 6.553438276719138,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00018910293224800584,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.23126854002475739,
|
|
"num_tokens": 14420369.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.457191038131714,
|
|
"epoch": 6.557580778790389,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00018880766610227608,
|
|
"loss": 4.6968,
|
|
"mean_token_accuracy": 0.23245848268270491,
|
|
"num_tokens": 14429078.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.380857133865357,
|
|
"epoch": 6.56172328086164,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00018851257381590264,
|
|
"loss": 4.6152,
|
|
"mean_token_accuracy": 0.23285982757806778,
|
|
"num_tokens": 14438920.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.46284852027893,
|
|
"epoch": 6.5658657829328915,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00018821765598411917,
|
|
"loss": 4.8346,
|
|
"mean_token_accuracy": 0.22055337429046631,
|
|
"num_tokens": 14449164.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.368284559249878,
|
|
"epoch": 6.570008285004143,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00018792291320180693,
|
|
"loss": 4.7315,
|
|
"mean_token_accuracy": 0.21904008835554123,
|
|
"num_tokens": 14459418.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.469215631484985,
|
|
"epoch": 6.574150787075394,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00018762834606349455,
|
|
"loss": 4.6787,
|
|
"mean_token_accuracy": 0.2300884559750557,
|
|
"num_tokens": 14468691.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.4986177444458,
|
|
"epoch": 6.578293289146645,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018733395516335588,
|
|
"loss": 4.7409,
|
|
"mean_token_accuracy": 0.2248911291360855,
|
|
"num_tokens": 14477936.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.456164216995239,
|
|
"epoch": 6.582435791217896,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00018703974109520976,
|
|
"loss": 4.73,
|
|
"mean_token_accuracy": 0.2340969204902649,
|
|
"num_tokens": 14487191.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.336252737045288,
|
|
"epoch": 6.586578293289147,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00018674570445251798,
|
|
"loss": 4.6401,
|
|
"mean_token_accuracy": 0.2337484613060951,
|
|
"num_tokens": 14495731.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.337139749526978,
|
|
"epoch": 6.590720795360397,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00018645184582838465,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.23295338302850724,
|
|
"num_tokens": 14505009.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.355250501632691,
|
|
"epoch": 6.594863297431648,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00018615816581555466,
|
|
"loss": 4.6891,
|
|
"mean_token_accuracy": 0.2260056585073471,
|
|
"num_tokens": 14513843.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.369057464599609,
|
|
"epoch": 6.5990057995028994,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001858646650064128,
|
|
"loss": 4.6925,
|
|
"mean_token_accuracy": 0.22871135026216508,
|
|
"num_tokens": 14523405.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.460236978530884,
|
|
"epoch": 6.603148301574151,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00018557134399298215,
|
|
"loss": 4.7566,
|
|
"mean_token_accuracy": 0.2261204555630684,
|
|
"num_tokens": 14532615.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.433869123458862,
|
|
"epoch": 6.607290803645402,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001852782033669233,
|
|
"loss": 4.6642,
|
|
"mean_token_accuracy": 0.24049948453903197,
|
|
"num_tokens": 14541297.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.388047695159912,
|
|
"epoch": 6.611433305716653,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00018498524371953295,
|
|
"loss": 4.6281,
|
|
"mean_token_accuracy": 0.23109858930110933,
|
|
"num_tokens": 14549867.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.376550340652466,
|
|
"epoch": 6.615575807787904,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00018469246564174275,
|
|
"loss": 4.7317,
|
|
"mean_token_accuracy": 0.21710989624261856,
|
|
"num_tokens": 14558708.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.392497825622558,
|
|
"epoch": 6.619718309859155,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000184399869724118,
|
|
"loss": 4.7094,
|
|
"mean_token_accuracy": 0.21922535300254822,
|
|
"num_tokens": 14567917.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.354313611984253,
|
|
"epoch": 6.623860811930406,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00018410745655685662,
|
|
"loss": 4.5729,
|
|
"mean_token_accuracy": 0.24423988163471222,
|
|
"num_tokens": 14576417.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.341135835647583,
|
|
"epoch": 6.628003314001657,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00018381522672978806,
|
|
"loss": 4.6807,
|
|
"mean_token_accuracy": 0.23046873658895492,
|
|
"num_tokens": 14585172.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 6.628003314001657,
|
|
"eval_entropy": 5.216681515992577,
|
|
"eval_loss": 5.7060418128967285,
|
|
"eval_mean_token_accuracy": 0.16986569171267024,
|
|
"eval_num_tokens": 14585172.0,
|
|
"eval_runtime": 2.1049,
|
|
"eval_samples_per_second": 1780.162,
|
|
"eval_steps_per_second": 222.817,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.437498283386231,
|
|
"epoch": 6.632145816072908,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00018352318083237167,
|
|
"loss": 4.7023,
|
|
"mean_token_accuracy": 0.22048562616109849,
|
|
"num_tokens": 14593758.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.400953006744385,
|
|
"epoch": 6.636288318144159,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00018323131945369603,
|
|
"loss": 4.6711,
|
|
"mean_token_accuracy": 0.2311324194073677,
|
|
"num_tokens": 14602558.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.461669635772705,
|
|
"epoch": 6.6404308202154105,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018293964318247735,
|
|
"loss": 4.6693,
|
|
"mean_token_accuracy": 0.2335198238492012,
|
|
"num_tokens": 14611463.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.406110763549805,
|
|
"epoch": 6.644573322286661,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00018264815260705863,
|
|
"loss": 4.7064,
|
|
"mean_token_accuracy": 0.22768237441778183,
|
|
"num_tokens": 14619951.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.435851335525513,
|
|
"epoch": 6.648715824357912,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00018235684831540826,
|
|
"loss": 4.7335,
|
|
"mean_token_accuracy": 0.22859640866518022,
|
|
"num_tokens": 14629332.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.3771130561828615,
|
|
"epoch": 6.652858326429163,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018206573089511862,
|
|
"loss": 4.6729,
|
|
"mean_token_accuracy": 0.23165991604328157,
|
|
"num_tokens": 14639010.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.392232990264892,
|
|
"epoch": 6.657000828500414,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00018177480093340564,
|
|
"loss": 4.7086,
|
|
"mean_token_accuracy": 0.22031079083681107,
|
|
"num_tokens": 14648507.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.384860992431641,
|
|
"epoch": 6.661143330571665,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001814840590171065,
|
|
"loss": 4.6939,
|
|
"mean_token_accuracy": 0.2266337141394615,
|
|
"num_tokens": 14657892.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.391514587402344,
|
|
"epoch": 6.665285832642916,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00018119350573267979,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.2297707051038742,
|
|
"num_tokens": 14666460.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.382449674606323,
|
|
"epoch": 6.669428334714167,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00018090314166620302,
|
|
"loss": 4.6589,
|
|
"mean_token_accuracy": 0.23258178681135178,
|
|
"num_tokens": 14675046.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.376294946670532,
|
|
"epoch": 6.6735708367854185,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00018061296740337225,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.2257002055644989,
|
|
"num_tokens": 14685055.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.4051848411560055,
|
|
"epoch": 6.67771333885667,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00018032298352950077,
|
|
"loss": 4.6724,
|
|
"mean_token_accuracy": 0.22643814533948897,
|
|
"num_tokens": 14695371.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.366548776626587,
|
|
"epoch": 6.681855840927921,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00018003319062951756,
|
|
"loss": 4.6347,
|
|
"mean_token_accuracy": 0.23298760503530502,
|
|
"num_tokens": 14703671.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.388493537902832,
|
|
"epoch": 6.685998342999172,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00017974358928796682,
|
|
"loss": 4.6703,
|
|
"mean_token_accuracy": 0.23872009962797164,
|
|
"num_tokens": 14712527.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.378263902664185,
|
|
"epoch": 6.690140845070422,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017945418008900594,
|
|
"loss": 4.707,
|
|
"mean_token_accuracy": 0.22742003351449966,
|
|
"num_tokens": 14720711.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.42297101020813,
|
|
"epoch": 6.694283347141674,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001791649636164049,
|
|
"loss": 4.732,
|
|
"mean_token_accuracy": 0.22016503810882568,
|
|
"num_tokens": 14729667.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.475334358215332,
|
|
"epoch": 6.698425849212924,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000178875940453545,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.2326573684811592,
|
|
"num_tokens": 14738614.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.454048204421997,
|
|
"epoch": 6.702568351284175,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00017858711118341742,
|
|
"loss": 4.6862,
|
|
"mean_token_accuracy": 0.22685618251562117,
|
|
"num_tokens": 14747724.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.380194759368896,
|
|
"epoch": 6.7067108533554265,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017829847638862255,
|
|
"loss": 4.6407,
|
|
"mean_token_accuracy": 0.23056415617465972,
|
|
"num_tokens": 14757436.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.332231569290161,
|
|
"epoch": 6.710853355426678,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00017801003665136823,
|
|
"loss": 4.6297,
|
|
"mean_token_accuracy": 0.23559218943119048,
|
|
"num_tokens": 14765948.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.379305171966553,
|
|
"epoch": 6.714995857497929,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017772179255346883,
|
|
"loss": 4.6578,
|
|
"mean_token_accuracy": 0.2284479707479477,
|
|
"num_tokens": 14775397.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.374171161651612,
|
|
"epoch": 6.71913835956918,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00017743374467634433,
|
|
"loss": 4.6283,
|
|
"mean_token_accuracy": 0.23269655406475068,
|
|
"num_tokens": 14783605.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.401924419403076,
|
|
"epoch": 6.723280861640431,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017714589360101862,
|
|
"loss": 4.7358,
|
|
"mean_token_accuracy": 0.2255132243037224,
|
|
"num_tokens": 14792210.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.388115930557251,
|
|
"epoch": 6.727423363711682,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000176858239908119,
|
|
"loss": 4.646,
|
|
"mean_token_accuracy": 0.22638098895549774,
|
|
"num_tokens": 14801186.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.319604873657227,
|
|
"epoch": 6.731565865782933,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00017657078417787414,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.23525837659835816,
|
|
"num_tokens": 14810100.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.305578327178955,
|
|
"epoch": 6.735708367854184,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00017628352699011396,
|
|
"loss": 4.5664,
|
|
"mean_token_accuracy": 0.23098524361848832,
|
|
"num_tokens": 14819335.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.35836238861084,
|
|
"epoch": 6.739850869925435,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001759964689242674,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.23369785398244858,
|
|
"num_tokens": 14828686.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.417706441879273,
|
|
"epoch": 6.743993371996686,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001757096105593619,
|
|
"loss": 4.6869,
|
|
"mean_token_accuracy": 0.22359532117843628,
|
|
"num_tokens": 14838312.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.303466367721557,
|
|
"epoch": 6.748135874067937,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017542295247402234,
|
|
"loss": 4.6156,
|
|
"mean_token_accuracy": 0.22814530730247498,
|
|
"num_tokens": 14846838.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.385804080963135,
|
|
"epoch": 6.752278376139188,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00017513649524646919,
|
|
"loss": 4.6829,
|
|
"mean_token_accuracy": 0.22239037305116655,
|
|
"num_tokens": 14857427.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.391503572463989,
|
|
"epoch": 6.756420878210439,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001748502394545181,
|
|
"loss": 4.6789,
|
|
"mean_token_accuracy": 0.2228201925754547,
|
|
"num_tokens": 14866244.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.384431266784668,
|
|
"epoch": 6.76056338028169,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001745641856755783,
|
|
"loss": 4.6956,
|
|
"mean_token_accuracy": 0.22541685104370118,
|
|
"num_tokens": 14875697.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.372077608108521,
|
|
"epoch": 6.764705882352941,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00017427833448665136,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.22829881310462952,
|
|
"num_tokens": 14884650.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.338526678085327,
|
|
"epoch": 6.768848384424192,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00017399268646433065,
|
|
"loss": 4.6512,
|
|
"mean_token_accuracy": 0.23240379244089127,
|
|
"num_tokens": 14894058.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.4246265411376955,
|
|
"epoch": 6.772990886495443,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00017370724218479912,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.22694970071315765,
|
|
"num_tokens": 14903219.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.440188932418823,
|
|
"epoch": 6.7771333885666944,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00017342200222382934,
|
|
"loss": 4.674,
|
|
"mean_token_accuracy": 0.23060814887285233,
|
|
"num_tokens": 14913051.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.445666313171387,
|
|
"epoch": 6.781275890637946,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00017313696715678134,
|
|
"loss": 4.7043,
|
|
"mean_token_accuracy": 0.2224097490310669,
|
|
"num_tokens": 14921777.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.467958736419678,
|
|
"epoch": 6.785418392709197,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.000172852137558602,
|
|
"loss": 4.8434,
|
|
"mean_token_accuracy": 0.21314134299755097,
|
|
"num_tokens": 14931558.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.425095748901367,
|
|
"epoch": 6.789560894780448,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017256751400382384,
|
|
"loss": 4.726,
|
|
"mean_token_accuracy": 0.23319334536790848,
|
|
"num_tokens": 14940584.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.429497814178466,
|
|
"epoch": 6.793703396851699,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00017228309706656354,
|
|
"loss": 4.6892,
|
|
"mean_token_accuracy": 0.23467843532562255,
|
|
"num_tokens": 14950830.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.440125513076782,
|
|
"epoch": 6.797845898922949,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001719988873205213,
|
|
"loss": 4.6779,
|
|
"mean_token_accuracy": 0.22622185796499253,
|
|
"num_tokens": 14958990.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.35979528427124,
|
|
"epoch": 6.8019884009942,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00017171488533897916,
|
|
"loss": 4.6957,
|
|
"mean_token_accuracy": 0.23544275015592575,
|
|
"num_tokens": 14967451.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.334678077697754,
|
|
"epoch": 6.806130903065451,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00017143109169480005,
|
|
"loss": 4.626,
|
|
"mean_token_accuracy": 0.22895882427692413,
|
|
"num_tokens": 14976157.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.416842317581176,
|
|
"epoch": 6.810273405136702,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00017114750696042695,
|
|
"loss": 4.7492,
|
|
"mean_token_accuracy": 0.2208598330616951,
|
|
"num_tokens": 14985591.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.406585073471069,
|
|
"epoch": 6.8144159072079535,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00017086413170788107,
|
|
"loss": 4.6403,
|
|
"mean_token_accuracy": 0.22974326461553574,
|
|
"num_tokens": 14994513.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.405246019363403,
|
|
"epoch": 6.818558409279205,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017058096650876143,
|
|
"loss": 4.7195,
|
|
"mean_token_accuracy": 0.2242250293493271,
|
|
"num_tokens": 15003252.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.425994777679444,
|
|
"epoch": 6.822700911350456,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00017029801193424313,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.23010726720094682,
|
|
"num_tokens": 15012342.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.313027095794678,
|
|
"epoch": 6.826843413421707,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00017001526855507632,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.22759608030319214,
|
|
"num_tokens": 15021336.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.373293828964234,
|
|
"epoch": 6.830985915492958,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00016973273694158555,
|
|
"loss": 4.6376,
|
|
"mean_token_accuracy": 0.22353117167949677,
|
|
"num_tokens": 15031016.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.453372430801392,
|
|
"epoch": 6.835128417564209,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00016945041766366773,
|
|
"loss": 4.6826,
|
|
"mean_token_accuracy": 0.22561344057321547,
|
|
"num_tokens": 15039181.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.422851514816284,
|
|
"epoch": 6.83927091963546,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016916831129079187,
|
|
"loss": 4.7136,
|
|
"mean_token_accuracy": 0.22176968008279802,
|
|
"num_tokens": 15048563.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.3804244041442875,
|
|
"epoch": 6.84341342170671,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001688864183919973,
|
|
"loss": 4.6647,
|
|
"mean_token_accuracy": 0.22724962681531907,
|
|
"num_tokens": 15056960.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.431652593612671,
|
|
"epoch": 6.8475559237779615,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016860473953589266,
|
|
"loss": 4.6948,
|
|
"mean_token_accuracy": 0.22999462932348252,
|
|
"num_tokens": 15065645.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.435272169113159,
|
|
"epoch": 6.851698425849213,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016832327529065522,
|
|
"loss": 4.6777,
|
|
"mean_token_accuracy": 0.22991640120744705,
|
|
"num_tokens": 15074544.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.439657926559448,
|
|
"epoch": 6.855840927920464,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001680420262240289,
|
|
"loss": 4.7059,
|
|
"mean_token_accuracy": 0.22804920226335526,
|
|
"num_tokens": 15083543.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.3538445949554445,
|
|
"epoch": 6.859983429991715,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00016776099290332397,
|
|
"loss": 4.6827,
|
|
"mean_token_accuracy": 0.23394815176725386,
|
|
"num_tokens": 15092291.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.448794794082642,
|
|
"epoch": 6.864125932062966,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00016748017589541525,
|
|
"loss": 4.7334,
|
|
"mean_token_accuracy": 0.22686232179403304,
|
|
"num_tokens": 15100875.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.396376132965088,
|
|
"epoch": 6.868268434134217,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001671995757667414,
|
|
"loss": 4.7089,
|
|
"mean_token_accuracy": 0.22739924639463424,
|
|
"num_tokens": 15111385.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.48860650062561,
|
|
"epoch": 6.872410936205468,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00016691919308330343,
|
|
"loss": 4.7489,
|
|
"mean_token_accuracy": 0.22990463376045228,
|
|
"num_tokens": 15121153.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.440316820144654,
|
|
"epoch": 6.876553438276719,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00016663902841066404,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.22355819195508958,
|
|
"num_tokens": 15130132.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.373796176910401,
|
|
"epoch": 6.88069594034797,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016635908231394587,
|
|
"loss": 4.6726,
|
|
"mean_token_accuracy": 0.22897688001394273,
|
|
"num_tokens": 15138878.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.385159969329834,
|
|
"epoch": 6.8848384424192215,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001660793553578307,
|
|
"loss": 4.7632,
|
|
"mean_token_accuracy": 0.21799678206443787,
|
|
"num_tokens": 15148727.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.408531665802002,
|
|
"epoch": 6.888980944490473,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00016579984810655856,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.23072180151939392,
|
|
"num_tokens": 15158107.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.418443489074707,
|
|
"epoch": 6.893123446561724,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00016552056112392594,
|
|
"loss": 4.6941,
|
|
"mean_token_accuracy": 0.22518327236175537,
|
|
"num_tokens": 15168101.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.378847646713257,
|
|
"epoch": 6.897265948632974,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001652414949732854,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.2315477818250656,
|
|
"num_tokens": 15176376.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.381583976745605,
|
|
"epoch": 6.901408450704225,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00016496265021754365,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.22750615775585176,
|
|
"num_tokens": 15184936.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.420657587051392,
|
|
"epoch": 6.905550952775476,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016468402741916124,
|
|
"loss": 4.7445,
|
|
"mean_token_accuracy": 0.2231239765882492,
|
|
"num_tokens": 15194846.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.394508647918701,
|
|
"epoch": 6.909693454846727,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001644056271401506,
|
|
"loss": 4.6913,
|
|
"mean_token_accuracy": 0.22933473587036132,
|
|
"num_tokens": 15204543.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.408537149429321,
|
|
"epoch": 6.913835956917978,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00016412744994207573,
|
|
"loss": 4.6603,
|
|
"mean_token_accuracy": 0.22653643190860748,
|
|
"num_tokens": 15213459.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.411208629608154,
|
|
"epoch": 6.9179784589892295,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00016384949638605025,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.21084464639425277,
|
|
"num_tokens": 15223841.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.357303333282471,
|
|
"epoch": 6.922120961060481,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016357176703273696,
|
|
"loss": 4.6845,
|
|
"mean_token_accuracy": 0.23062540888786315,
|
|
"num_tokens": 15233594.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.395097827911377,
|
|
"epoch": 6.926263463131732,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001632942624423463,
|
|
"loss": 4.6285,
|
|
"mean_token_accuracy": 0.23301408141851426,
|
|
"num_tokens": 15242876.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.469443511962891,
|
|
"epoch": 6.930405965202983,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00016301698317463525,
|
|
"loss": 4.7276,
|
|
"mean_token_accuracy": 0.23090613186359404,
|
|
"num_tokens": 15251581.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.409171152114868,
|
|
"epoch": 6.934548467274234,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00016273992978890658,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.23247742503881455,
|
|
"num_tokens": 15260601.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.383829164505005,
|
|
"epoch": 6.938690969345485,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001624631028440071,
|
|
"loss": 4.6191,
|
|
"mean_token_accuracy": 0.2301475450396538,
|
|
"num_tokens": 15270123.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.4292529106140135,
|
|
"epoch": 6.942833471416735,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001621865028983271,
|
|
"loss": 4.7253,
|
|
"mean_token_accuracy": 0.2276384115219116,
|
|
"num_tokens": 15278623.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.342248201370239,
|
|
"epoch": 6.946975973487987,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001619101305097988,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.23078329414129256,
|
|
"num_tokens": 15287789.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.272088241577149,
|
|
"epoch": 6.9511184755592375,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00016163398623589563,
|
|
"loss": 4.5929,
|
|
"mean_token_accuracy": 0.2331315666437149,
|
|
"num_tokens": 15296266.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.431140565872193,
|
|
"epoch": 6.955260977630489,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00016135807063363074,
|
|
"loss": 4.7041,
|
|
"mean_token_accuracy": 0.221357099711895,
|
|
"num_tokens": 15304785.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.314264488220215,
|
|
"epoch": 6.95940347970174,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00016108238425955584,
|
|
"loss": 4.591,
|
|
"mean_token_accuracy": 0.2362232819199562,
|
|
"num_tokens": 15313727.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.4426140785217285,
|
|
"epoch": 6.963545981772991,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001608069276697608,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.2226940080523491,
|
|
"num_tokens": 15322911.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.447377300262451,
|
|
"epoch": 6.967688483844242,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001605317014198714,
|
|
"loss": 4.692,
|
|
"mean_token_accuracy": 0.23092361092567443,
|
|
"num_tokens": 15330882.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.375608682632446,
|
|
"epoch": 6.971830985915493,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00016025670606504926,
|
|
"loss": 4.5811,
|
|
"mean_token_accuracy": 0.2336902916431427,
|
|
"num_tokens": 15339915.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.35202169418335,
|
|
"epoch": 6.975973487986744,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001599819421599899,
|
|
"loss": 4.6525,
|
|
"mean_token_accuracy": 0.23036704063415528,
|
|
"num_tokens": 15348181.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.323818254470825,
|
|
"epoch": 6.980115990057995,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015970741025892233,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.23783685863018036,
|
|
"num_tokens": 15357128.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.353246402740479,
|
|
"epoch": 6.984258492129246,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00015943311091560721,
|
|
"loss": 4.722,
|
|
"mean_token_accuracy": 0.2279161974787712,
|
|
"num_tokens": 15366878.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.470389747619629,
|
|
"epoch": 6.988400994200497,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00015915904468333635,
|
|
"loss": 4.6922,
|
|
"mean_token_accuracy": 0.2388680949807167,
|
|
"num_tokens": 15376101.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.355824756622314,
|
|
"epoch": 6.9925434962717485,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00015888521211493135,
|
|
"loss": 4.6119,
|
|
"mean_token_accuracy": 0.228062604367733,
|
|
"num_tokens": 15384942.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.362313461303711,
|
|
"epoch": 6.996685998342999,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001586116137627423,
|
|
"loss": 4.6411,
|
|
"mean_token_accuracy": 0.23070871233940124,
|
|
"num_tokens": 15394380.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.453443145751953,
|
|
"epoch": 7.00082850041425,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00015833825017864711,
|
|
"loss": 4.5862,
|
|
"mean_token_accuracy": 0.23864850550889968,
|
|
"num_tokens": 15402180.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.409005165100098,
|
|
"epoch": 7.004971002485501,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00015806512191405,
|
|
"loss": 4.6352,
|
|
"mean_token_accuracy": 0.23993055373430253,
|
|
"num_tokens": 15411434.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.4142608642578125,
|
|
"epoch": 7.009113504556752,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001577922295198803,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.24158467948436738,
|
|
"num_tokens": 15419905.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.364171934127808,
|
|
"epoch": 7.013256006628003,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00015751957354659206,
|
|
"loss": 4.6168,
|
|
"mean_token_accuracy": 0.23063095957040786,
|
|
"num_tokens": 15429200.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.375877857208252,
|
|
"epoch": 7.017398508699254,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00015724715454416206,
|
|
"loss": 4.588,
|
|
"mean_token_accuracy": 0.2476017117500305,
|
|
"num_tokens": 15439328.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.357981395721436,
|
|
"epoch": 7.021541010770505,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00015697497306208926,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.24448583126068116,
|
|
"num_tokens": 15447739.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.411028718948364,
|
|
"epoch": 7.0256835128417565,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001567030296493934,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.2458529531955719,
|
|
"num_tokens": 15456598.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.423058366775512,
|
|
"epoch": 7.029826014913008,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015643132485461395,
|
|
"loss": 4.6355,
|
|
"mean_token_accuracy": 0.2339696168899536,
|
|
"num_tokens": 15466633.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.443295812606811,
|
|
"epoch": 7.033968516984259,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0001561598592258094,
|
|
"loss": 4.5705,
|
|
"mean_token_accuracy": 0.25076698660850527,
|
|
"num_tokens": 15476809.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.326943206787109,
|
|
"epoch": 7.03811101905551,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00015588863331055541,
|
|
"loss": 4.5229,
|
|
"mean_token_accuracy": 0.2415056750178337,
|
|
"num_tokens": 15484964.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.3414990425109865,
|
|
"epoch": 7.042253521126761,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001556176476559444,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.24135807305574417,
|
|
"num_tokens": 15493600.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"epoch": 7.042253521126761,
|
|
"eval_entropy": 5.198448402795202,
|
|
"eval_loss": 5.707950592041016,
|
|
"eval_mean_token_accuracy": 0.17043713348379522,
|
|
"eval_num_tokens": 15493600.0,
|
|
"eval_runtime": 2.2994,
|
|
"eval_samples_per_second": 1629.583,
|
|
"eval_steps_per_second": 203.97,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.302147102355957,
|
|
"epoch": 7.046396023198011,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015534690280858405,
|
|
"loss": 4.5357,
|
|
"mean_token_accuracy": 0.24755738526582718,
|
|
"num_tokens": 15502614.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.465841245651245,
|
|
"epoch": 7.050538525269262,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00015507639931459615,
|
|
"loss": 4.6517,
|
|
"mean_token_accuracy": 0.23790536373853682,
|
|
"num_tokens": 15511521.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.358317518234253,
|
|
"epoch": 7.054681027340513,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000154806137719616,
|
|
"loss": 4.568,
|
|
"mean_token_accuracy": 0.24197252839803696,
|
|
"num_tokens": 15520220.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.326447248458862,
|
|
"epoch": 7.0588235294117645,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001545361185687906,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.2515454486012459,
|
|
"num_tokens": 15528924.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.308388328552246,
|
|
"epoch": 7.062966031483016,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00015426634240677824,
|
|
"loss": 4.509,
|
|
"mean_token_accuracy": 0.2400757610797882,
|
|
"num_tokens": 15539722.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.379448890686035,
|
|
"epoch": 7.067108533554267,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015399680977774689,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.24012591689825058,
|
|
"num_tokens": 15548682.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.427528524398804,
|
|
"epoch": 7.071251035625518,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015372752122537318,
|
|
"loss": 4.5884,
|
|
"mean_token_accuracy": 0.23884914070367813,
|
|
"num_tokens": 15557508.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.400093460083008,
|
|
"epoch": 7.075393537696769,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00015345847729284168,
|
|
"loss": 4.6147,
|
|
"mean_token_accuracy": 0.23873291313648223,
|
|
"num_tokens": 15566120.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.373989534378052,
|
|
"epoch": 7.07953603976802,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00015318967852284335,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.2465381219983101,
|
|
"num_tokens": 15575166.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.33354926109314,
|
|
"epoch": 7.083678541839271,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015292112545757476,
|
|
"loss": 4.5443,
|
|
"mean_token_accuracy": 0.23690295815467835,
|
|
"num_tokens": 15585063.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.361451530456543,
|
|
"epoch": 7.087821043910522,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.00015265281863873663,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.23441902697086334,
|
|
"num_tokens": 15594386.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.355977201461792,
|
|
"epoch": 7.091963545981773,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00015238475860753338,
|
|
"loss": 4.5875,
|
|
"mean_token_accuracy": 0.2397656634449959,
|
|
"num_tokens": 15603796.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.392573022842408,
|
|
"epoch": 7.096106048053024,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00015211694590467118,
|
|
"loss": 4.5361,
|
|
"mean_token_accuracy": 0.24704737216234207,
|
|
"num_tokens": 15612752.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.3774511337280275,
|
|
"epoch": 7.100248550124275,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001518493810703575,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.23409268260002136,
|
|
"num_tokens": 15621995.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.328475379943848,
|
|
"epoch": 7.104391052195526,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015158206464430002,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.24047859907150268,
|
|
"num_tokens": 15630390.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.253737497329712,
|
|
"epoch": 7.108533554266777,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.000151314997165705,
|
|
"loss": 4.4948,
|
|
"mean_token_accuracy": 0.2454523265361786,
|
|
"num_tokens": 15639723.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.289352321624756,
|
|
"epoch": 7.112676056338028,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00015104817917327694,
|
|
"loss": 4.4347,
|
|
"mean_token_accuracy": 0.25129385143518446,
|
|
"num_tokens": 15647755.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.370699691772461,
|
|
"epoch": 7.116818558409279,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00015078161120521676,
|
|
"loss": 4.5889,
|
|
"mean_token_accuracy": 0.24578483700752257,
|
|
"num_tokens": 15656949.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.334399843215943,
|
|
"epoch": 7.12096106048053,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001505152937992211,
|
|
"loss": 4.5256,
|
|
"mean_token_accuracy": 0.24481884837150575,
|
|
"num_tokens": 15666290.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.406169843673706,
|
|
"epoch": 7.125103562551781,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015024922749248143,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.23699966222047805,
|
|
"num_tokens": 15675728.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.36447925567627,
|
|
"epoch": 7.1292460646230325,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00014998341282168243,
|
|
"loss": 4.5084,
|
|
"mean_token_accuracy": 0.2515394002199173,
|
|
"num_tokens": 15684519.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.388670349121094,
|
|
"epoch": 7.133388566694284,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001497178503230015,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.23927262425422668,
|
|
"num_tokens": 15693813.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.393256902694702,
|
|
"epoch": 7.137531068765535,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00014945254053210712,
|
|
"loss": 4.5903,
|
|
"mean_token_accuracy": 0.23963564038276672,
|
|
"num_tokens": 15702245.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.416450071334839,
|
|
"epoch": 7.141673570836786,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014918748398415801,
|
|
"loss": 4.607,
|
|
"mean_token_accuracy": 0.23970014601945877,
|
|
"num_tokens": 15712246.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.352137517929077,
|
|
"epoch": 7.145816072908037,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00014892268121380244,
|
|
"loss": 4.536,
|
|
"mean_token_accuracy": 0.24030404388904572,
|
|
"num_tokens": 15720904.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.373089408874511,
|
|
"epoch": 7.149958574979287,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00014865813275517637,
|
|
"loss": 4.5316,
|
|
"mean_token_accuracy": 0.24839761555194856,
|
|
"num_tokens": 15730595.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.310306262969971,
|
|
"epoch": 7.154101077050538,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00014839383914190302,
|
|
"loss": 4.4959,
|
|
"mean_token_accuracy": 0.24333667755126953,
|
|
"num_tokens": 15739475.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.343496322631836,
|
|
"epoch": 7.158243579121789,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001481298009070915,
|
|
"loss": 4.5439,
|
|
"mean_token_accuracy": 0.2447204679250717,
|
|
"num_tokens": 15748672.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.403918838500976,
|
|
"epoch": 7.16238608119304,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00014786601858333566,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.2420036405324936,
|
|
"num_tokens": 15757540.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.315920782089234,
|
|
"epoch": 7.1665285832642915,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00014760249270271341,
|
|
"loss": 4.5814,
|
|
"mean_token_accuracy": 0.23670318722724915,
|
|
"num_tokens": 15767198.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.314662885665894,
|
|
"epoch": 7.170671085335543,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00014733922379678513,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.2367343783378601,
|
|
"num_tokens": 15776818.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.450958681106568,
|
|
"epoch": 7.174813587406794,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00014707621239659312,
|
|
"loss": 4.6688,
|
|
"mean_token_accuracy": 0.2335329160094261,
|
|
"num_tokens": 15786054.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.3997351169586185,
|
|
"epoch": 7.178956089478045,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001468134590326601,
|
|
"loss": 4.6337,
|
|
"mean_token_accuracy": 0.2310939222574234,
|
|
"num_tokens": 15795367.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.4148002624511715,
|
|
"epoch": 7.183098591549296,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001465509642349881,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.2371065765619278,
|
|
"num_tokens": 15805006.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.426094722747803,
|
|
"epoch": 7.187241093620547,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00014628872853305808,
|
|
"loss": 4.6499,
|
|
"mean_token_accuracy": 0.23190061748027802,
|
|
"num_tokens": 15813978.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.416024112701416,
|
|
"epoch": 7.191383595691798,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00014602675245582795,
|
|
"loss": 4.6099,
|
|
"mean_token_accuracy": 0.23663106560707092,
|
|
"num_tokens": 15824156.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.468415975570679,
|
|
"epoch": 7.195526097763049,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014576503653173219,
|
|
"loss": 4.6749,
|
|
"mean_token_accuracy": 0.23007816523313523,
|
|
"num_tokens": 15833514.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.3923811435699465,
|
|
"epoch": 7.1996685998342995,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00014550358128868036,
|
|
"loss": 4.6209,
|
|
"mean_token_accuracy": 0.2349981501698494,
|
|
"num_tokens": 15842047.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.424600410461426,
|
|
"epoch": 7.203811101905551,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00014524238725405615,
|
|
"loss": 4.6553,
|
|
"mean_token_accuracy": 0.23375312089920045,
|
|
"num_tokens": 15851916.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.377563905715943,
|
|
"epoch": 7.207953603976802,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00014498145495471664,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.23947150707244874,
|
|
"num_tokens": 15860776.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.363483142852783,
|
|
"epoch": 7.212096106048053,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00014472078491699076,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.23763834834098815,
|
|
"num_tokens": 15870272.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.397445821762085,
|
|
"epoch": 7.216238608119304,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001444603776666784,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.24451150894165039,
|
|
"num_tokens": 15879448.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.452851915359497,
|
|
"epoch": 7.220381110190555,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00014420023372904944,
|
|
"loss": 4.6494,
|
|
"mean_token_accuracy": 0.23384447991847992,
|
|
"num_tokens": 15888806.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.3707479476928714,
|
|
"epoch": 7.224523612261806,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00014394035362884274,
|
|
"loss": 4.6025,
|
|
"mean_token_accuracy": 0.24241653084754944,
|
|
"num_tokens": 15898443.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.3550385475158695,
|
|
"epoch": 7.228666114333057,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00014368073789026482,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.24393291175365447,
|
|
"num_tokens": 15907759.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.382049131393432,
|
|
"epoch": 7.232808616404308,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00014342138703698882,
|
|
"loss": 4.5286,
|
|
"mean_token_accuracy": 0.24000653773546218,
|
|
"num_tokens": 15916687.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.351828956604004,
|
|
"epoch": 7.2369511184755595,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.000143162301592154,
|
|
"loss": 4.5656,
|
|
"mean_token_accuracy": 0.24622284919023513,
|
|
"num_tokens": 15925422.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.3737608909606935,
|
|
"epoch": 7.241093620546811,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00014290348207836385,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.2353345811367035,
|
|
"num_tokens": 15934279.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.347350263595581,
|
|
"epoch": 7.245236122618062,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001426449290176857,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.245602086186409,
|
|
"num_tokens": 15943565.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.307773637771606,
|
|
"epoch": 7.249378624689312,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00014238664293164934,
|
|
"loss": 4.5426,
|
|
"mean_token_accuracy": 0.24556828588247298,
|
|
"num_tokens": 15952360.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.384998893737793,
|
|
"epoch": 7.253521126760563,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.0001421286243412459,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.23576582819223404,
|
|
"num_tokens": 15960715.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.449563789367676,
|
|
"epoch": 7.257663628831814,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00014187087376692724,
|
|
"loss": 4.5986,
|
|
"mean_token_accuracy": 0.23827928751707078,
|
|
"num_tokens": 15969543.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.293625545501709,
|
|
"epoch": 7.261806130903065,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001416133917286043,
|
|
"loss": 4.5259,
|
|
"mean_token_accuracy": 0.23794226199388505,
|
|
"num_tokens": 15978256.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.313066482543945,
|
|
"epoch": 7.265948632974316,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001413561787456466,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.24075379073619843,
|
|
"num_tokens": 15987646.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.356533479690552,
|
|
"epoch": 7.2700911350455675,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00014109923533688068,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.23621369600296022,
|
|
"num_tokens": 15996767.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.371524286270142,
|
|
"epoch": 7.274233637116819,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001408425620205897,
|
|
"loss": 4.5739,
|
|
"mean_token_accuracy": 0.24063031673431395,
|
|
"num_tokens": 16007170.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.428442525863647,
|
|
"epoch": 7.27837613918807,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001405861593145116,
|
|
"loss": 4.6089,
|
|
"mean_token_accuracy": 0.2327800139784813,
|
|
"num_tokens": 16015354.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.444035911560059,
|
|
"epoch": 7.282518641259321,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00014033002773583872,
|
|
"loss": 4.6002,
|
|
"mean_token_accuracy": 0.2320488542318344,
|
|
"num_tokens": 16024600.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.424409961700439,
|
|
"epoch": 7.286661143330572,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.0001400741678012164,
|
|
"loss": 4.5839,
|
|
"mean_token_accuracy": 0.24527119249105453,
|
|
"num_tokens": 16033301.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.3897385597229,
|
|
"epoch": 7.290803645401823,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00013981858002674223,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.23764747828245164,
|
|
"num_tokens": 16043539.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.454379892349243,
|
|
"epoch": 7.294946147473074,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001395632649279645,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.23376276046037675,
|
|
"num_tokens": 16052861.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.427953767776489,
|
|
"epoch": 7.299088649544325,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00013930822301988177,
|
|
"loss": 4.551,
|
|
"mean_token_accuracy": 0.24481629729270935,
|
|
"num_tokens": 16062454.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.352642488479614,
|
|
"epoch": 7.3032311516155755,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00013905345481694147,
|
|
"loss": 4.5591,
|
|
"mean_token_accuracy": 0.2431754484772682,
|
|
"num_tokens": 16071432.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.352116298675537,
|
|
"epoch": 7.307373653686827,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001387989608330388,
|
|
"loss": 4.5421,
|
|
"mean_token_accuracy": 0.24364028126001358,
|
|
"num_tokens": 16080411.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.367006921768189,
|
|
"epoch": 7.311516155758078,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00013854474158151602,
|
|
"loss": 4.5777,
|
|
"mean_token_accuracy": 0.23942873775959014,
|
|
"num_tokens": 16089396.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.410627126693726,
|
|
"epoch": 7.315658657829329,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00013829079757516106,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.23337575495243074,
|
|
"num_tokens": 16099308.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.371023797988892,
|
|
"epoch": 7.31980115990058,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00013803712932620681,
|
|
"loss": 4.6064,
|
|
"mean_token_accuracy": 0.23385393619537354,
|
|
"num_tokens": 16109336.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.401296710968017,
|
|
"epoch": 7.323943661971831,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001377837373463298,
|
|
"loss": 4.5746,
|
|
"mean_token_accuracy": 0.23738930225372315,
|
|
"num_tokens": 16118483.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.411250925064087,
|
|
"epoch": 7.328086164043082,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001375306221466494,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.23917246758937835,
|
|
"num_tokens": 16127302.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.350257730484008,
|
|
"epoch": 7.332228666114333,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00013727778423772654,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.2390030086040497,
|
|
"num_tokens": 16136361.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.4359992980957035,
|
|
"epoch": 7.336371168185584,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00013702522412956304,
|
|
"loss": 4.6831,
|
|
"mean_token_accuracy": 0.2355972021818161,
|
|
"num_tokens": 16146071.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.39995379447937,
|
|
"epoch": 7.340513670256835,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00013677294233160016,
|
|
"loss": 4.6177,
|
|
"mean_token_accuracy": 0.23512682914733887,
|
|
"num_tokens": 16154606.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.327909708023071,
|
|
"epoch": 7.3446561723280865,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013652093935271776,
|
|
"loss": 4.5803,
|
|
"mean_token_accuracy": 0.24811757504940032,
|
|
"num_tokens": 16163648.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.452345705032348,
|
|
"epoch": 7.348798674399337,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00013626921570123357,
|
|
"loss": 4.6199,
|
|
"mean_token_accuracy": 0.24011715054512023,
|
|
"num_tokens": 16172693.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.391722202301025,
|
|
"epoch": 7.352941176470588,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00013601777188490156,
|
|
"loss": 4.5482,
|
|
"mean_token_accuracy": 0.2449846625328064,
|
|
"num_tokens": 16181689.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.3501299858093265,
|
|
"epoch": 7.357083678541839,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001357666084109115,
|
|
"loss": 4.6532,
|
|
"mean_token_accuracy": 0.23543318957090378,
|
|
"num_tokens": 16191254.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.400330495834351,
|
|
"epoch": 7.36122618061309,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001355157257858875,
|
|
"loss": 4.562,
|
|
"mean_token_accuracy": 0.23455071151256562,
|
|
"num_tokens": 16199613.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.352452802658081,
|
|
"epoch": 7.365368682684341,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00013526512451588718,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.24179937839508056,
|
|
"num_tokens": 16208345.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.38597469329834,
|
|
"epoch": 7.369511184755592,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001350148051064008,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.23526992052793502,
|
|
"num_tokens": 16217964.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.439091730117798,
|
|
"epoch": 7.373653686826843,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013476476806234983,
|
|
"loss": 4.6802,
|
|
"mean_token_accuracy": 0.23555166870355607,
|
|
"num_tokens": 16227140.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.471381998062133,
|
|
"epoch": 7.3777961888980945,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0001345150138880865,
|
|
"loss": 4.6409,
|
|
"mean_token_accuracy": 0.23331766128540038,
|
|
"num_tokens": 16237416.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.477898788452149,
|
|
"epoch": 7.381938690969346,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00013426554308739214,
|
|
"loss": 4.6381,
|
|
"mean_token_accuracy": 0.2336421549320221,
|
|
"num_tokens": 16246682.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.378126096725464,
|
|
"epoch": 7.386081193040597,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00013401635616347655,
|
|
"loss": 4.6195,
|
|
"mean_token_accuracy": 0.23749187737703323,
|
|
"num_tokens": 16255450.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.280774879455566,
|
|
"epoch": 7.390223695111848,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00013376745361897712,
|
|
"loss": 4.531,
|
|
"mean_token_accuracy": 0.23915939629077912,
|
|
"num_tokens": 16265014.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.438695001602173,
|
|
"epoch": 7.394366197183099,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00013351883595595743,
|
|
"loss": 4.6084,
|
|
"mean_token_accuracy": 0.24529333412647247,
|
|
"num_tokens": 16273309.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.357016944885254,
|
|
"epoch": 7.39850869925435,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001332705036759065,
|
|
"loss": 4.5772,
|
|
"mean_token_accuracy": 0.23661576807498932,
|
|
"num_tokens": 16282129.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.2955512523651125,
|
|
"epoch": 7.4026512013256,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.0001330224572797377,
|
|
"loss": 4.5418,
|
|
"mean_token_accuracy": 0.24318578094244003,
|
|
"num_tokens": 16291208.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.394471216201782,
|
|
"epoch": 7.406793703396851,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00013277469726778756,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.2463047608733177,
|
|
"num_tokens": 16300111.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.3964122295379635,
|
|
"epoch": 7.4109362054681025,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.0001325272241398153,
|
|
"loss": 4.5125,
|
|
"mean_token_accuracy": 0.2442508190870285,
|
|
"num_tokens": 16308653.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.45100212097168,
|
|
"epoch": 7.415078707539354,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00013228003839500113,
|
|
"loss": 4.609,
|
|
"mean_token_accuracy": 0.23141717165708542,
|
|
"num_tokens": 16317986.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.3862952709198,
|
|
"epoch": 7.419221209610605,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.0001320331405319458,
|
|
"loss": 4.5933,
|
|
"mean_token_accuracy": 0.23522500991821288,
|
|
"num_tokens": 16326889.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.316311597824097,
|
|
"epoch": 7.423363711681856,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00013178653104866926,
|
|
"loss": 4.6141,
|
|
"mean_token_accuracy": 0.23636786490678788,
|
|
"num_tokens": 16336121.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.369629573822022,
|
|
"epoch": 7.427506213753107,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00013154021044260966,
|
|
"loss": 4.6674,
|
|
"mean_token_accuracy": 0.2315174162387848,
|
|
"num_tokens": 16345216.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.349261474609375,
|
|
"epoch": 7.431648715824358,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00013129417921062275,
|
|
"loss": 4.513,
|
|
"mean_token_accuracy": 0.24793354719877242,
|
|
"num_tokens": 16353735.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.368741464614868,
|
|
"epoch": 7.435791217895609,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001310484378489803,
|
|
"loss": 4.5403,
|
|
"mean_token_accuracy": 0.24288982301950454,
|
|
"num_tokens": 16362474.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.3739166259765625,
|
|
"epoch": 7.43993371996686,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013080298685336957,
|
|
"loss": 4.6615,
|
|
"mean_token_accuracy": 0.23430476635694503,
|
|
"num_tokens": 16371948.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.337637233734131,
|
|
"epoch": 7.444076222038111,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00013055782671889205,
|
|
"loss": 4.5476,
|
|
"mean_token_accuracy": 0.24226045310497285,
|
|
"num_tokens": 16380849.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.4270960807800295,
|
|
"epoch": 7.448218724109362,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.0001303129579400624,
|
|
"loss": 4.6431,
|
|
"mean_token_accuracy": 0.23084071576595305,
|
|
"num_tokens": 16389495.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.389580917358399,
|
|
"epoch": 7.452361226180613,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001300683810108078,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.2424330309033394,
|
|
"num_tokens": 16397744.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.338866806030273,
|
|
"epoch": 7.456503728251864,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001298240964244666,
|
|
"loss": 4.5783,
|
|
"mean_token_accuracy": 0.23190100044012069,
|
|
"num_tokens": 16406785.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 7.456503728251864,
|
|
"eval_entropy": 5.21050775991574,
|
|
"eval_loss": 5.709653377532959,
|
|
"eval_mean_token_accuracy": 0.17036682975762435,
|
|
"eval_num_tokens": 16406785.0,
|
|
"eval_runtime": 2.1133,
|
|
"eval_samples_per_second": 1773.015,
|
|
"eval_steps_per_second": 221.923,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.380531597137451,
|
|
"epoch": 7.460646230323115,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001295801046737876,
|
|
"loss": 4.5851,
|
|
"mean_token_accuracy": 0.24526306986808777,
|
|
"num_tokens": 16415768.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.3370277881622314,
|
|
"epoch": 7.464788732394366,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00012933640625092867,
|
|
"loss": 4.5775,
|
|
"mean_token_accuracy": 0.2405696138739586,
|
|
"num_tokens": 16424722.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.36087384223938,
|
|
"epoch": 7.468931234465617,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.00012909300164745636,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.2423337996006012,
|
|
"num_tokens": 16433797.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.337210083007813,
|
|
"epoch": 7.473073736536868,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00012884989135434423,
|
|
"loss": 4.4845,
|
|
"mean_token_accuracy": 0.24548748135566711,
|
|
"num_tokens": 16442537.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.411793375015259,
|
|
"epoch": 7.477216238608119,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00012860707586197218,
|
|
"loss": 4.6057,
|
|
"mean_token_accuracy": 0.23318703323602677,
|
|
"num_tokens": 16451440.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.382363748550415,
|
|
"epoch": 7.4813587406793705,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00012836455566012586,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.2367062970995903,
|
|
"num_tokens": 16459358.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.338227081298828,
|
|
"epoch": 7.485501242750622,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00012812233123799481,
|
|
"loss": 4.4929,
|
|
"mean_token_accuracy": 0.250929456949234,
|
|
"num_tokens": 16467584.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.37768521308899,
|
|
"epoch": 7.489643744821873,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00012788040308417232,
|
|
"loss": 4.6194,
|
|
"mean_token_accuracy": 0.23286612182855607,
|
|
"num_tokens": 16476674.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.339299583435059,
|
|
"epoch": 7.493786246893124,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012763877168665383,
|
|
"loss": 4.4997,
|
|
"mean_token_accuracy": 0.24312551468610763,
|
|
"num_tokens": 16485422.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.375254917144775,
|
|
"epoch": 7.497928748964375,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012739743753283617,
|
|
"loss": 4.6696,
|
|
"mean_token_accuracy": 0.2340833365917206,
|
|
"num_tokens": 16494024.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.3393960952758786,
|
|
"epoch": 7.502071251035625,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001271564011095169,
|
|
"loss": 4.6504,
|
|
"mean_token_accuracy": 0.23398083448410034,
|
|
"num_tokens": 16503805.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.3824413299560545,
|
|
"epoch": 7.506213753106876,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.0001269156629028927,
|
|
"loss": 4.5987,
|
|
"mean_token_accuracy": 0.2322842836380005,
|
|
"num_tokens": 16512559.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.4658221244812015,
|
|
"epoch": 7.510356255178127,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001266752233985589,
|
|
"loss": 4.6631,
|
|
"mean_token_accuracy": 0.2289978951215744,
|
|
"num_tokens": 16521910.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.378844833374023,
|
|
"epoch": 7.514498757249378,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00012643508308150822,
|
|
"loss": 4.5765,
|
|
"mean_token_accuracy": 0.2366702973842621,
|
|
"num_tokens": 16530802.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.341800165176392,
|
|
"epoch": 7.5186412593206295,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001261952424361299,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.23952031135559082,
|
|
"num_tokens": 16540519.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.356250286102295,
|
|
"epoch": 7.522783761391881,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.0001259557019462088,
|
|
"loss": 4.5415,
|
|
"mean_token_accuracy": 0.23725043386220931,
|
|
"num_tokens": 16549433.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.353562736511231,
|
|
"epoch": 7.526926263463132,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00012571646209492417,
|
|
"loss": 4.6026,
|
|
"mean_token_accuracy": 0.23459005504846572,
|
|
"num_tokens": 16558128.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.3514008045196535,
|
|
"epoch": 7.531068765534383,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00012547752336484908,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.24552911520004272,
|
|
"num_tokens": 16566636.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.4071478843688965,
|
|
"epoch": 7.535211267605634,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.00012523888623794892,
|
|
"loss": 4.556,
|
|
"mean_token_accuracy": 0.23766732215881348,
|
|
"num_tokens": 16575036.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.366435718536377,
|
|
"epoch": 7.539353769676885,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.0001250005511955809,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.24135154932737352,
|
|
"num_tokens": 16584146.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.465256595611573,
|
|
"epoch": 7.543496271748136,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001247625187184929,
|
|
"loss": 4.6574,
|
|
"mean_token_accuracy": 0.23949182480573655,
|
|
"num_tokens": 16593915.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.38883900642395,
|
|
"epoch": 7.547638773819386,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0001245247892868223,
|
|
"loss": 4.5081,
|
|
"mean_token_accuracy": 0.2506419360637665,
|
|
"num_tokens": 16601490.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.3614363193511965,
|
|
"epoch": 7.551781275890638,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001242873633800955,
|
|
"loss": 4.6075,
|
|
"mean_token_accuracy": 0.23226021230220795,
|
|
"num_tokens": 16610972.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.404771709442139,
|
|
"epoch": 7.555923777961889,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00012405024147722643,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.2363522991538048,
|
|
"num_tokens": 16619388.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.297590684890747,
|
|
"epoch": 7.56006628003314,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0001238134240565158,
|
|
"loss": 4.5184,
|
|
"mean_token_accuracy": 0.24358752518892288,
|
|
"num_tokens": 16628265.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.34783411026001,
|
|
"epoch": 7.564208782104391,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.0001235769115956504,
|
|
"loss": 4.5017,
|
|
"mean_token_accuracy": 0.25338298082351685,
|
|
"num_tokens": 16636809.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.445653629302979,
|
|
"epoch": 7.568351284175642,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00012334070457170151,
|
|
"loss": 4.6888,
|
|
"mean_token_accuracy": 0.2253960594534874,
|
|
"num_tokens": 16646084.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.426211357116699,
|
|
"epoch": 7.572493786246893,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00012310480346112472,
|
|
"loss": 4.6833,
|
|
"mean_token_accuracy": 0.22619519829750062,
|
|
"num_tokens": 16656196.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.329517412185669,
|
|
"epoch": 7.576636288318144,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00012286920873975815,
|
|
"loss": 4.6148,
|
|
"mean_token_accuracy": 0.23367678374052048,
|
|
"num_tokens": 16665770.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.348250102996826,
|
|
"epoch": 7.580778790389395,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00012263392088282226,
|
|
"loss": 4.5219,
|
|
"mean_token_accuracy": 0.2441157728433609,
|
|
"num_tokens": 16674206.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.344795989990234,
|
|
"epoch": 7.584921292460646,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00012239894036491833,
|
|
"loss": 4.5815,
|
|
"mean_token_accuracy": 0.2382705807685852,
|
|
"num_tokens": 16683977.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.334633302688599,
|
|
"epoch": 7.5890637945318975,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00012216426766002762,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.23404132276773454,
|
|
"num_tokens": 16693117.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.37777533531189,
|
|
"epoch": 7.593206296603149,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012192990324151079,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.24137212336063385,
|
|
"num_tokens": 16701631.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.410675525665283,
|
|
"epoch": 7.5973487986744,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00012169584758210635,
|
|
"loss": 4.6533,
|
|
"mean_token_accuracy": 0.2368814930319786,
|
|
"num_tokens": 16710337.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.326189279556274,
|
|
"epoch": 7.60149130074565,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00012146210115393025,
|
|
"loss": 4.5577,
|
|
"mean_token_accuracy": 0.24405269473791122,
|
|
"num_tokens": 16719046.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.386121988296509,
|
|
"epoch": 7.605633802816901,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00012122866442847455,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.23316006362438202,
|
|
"num_tokens": 16727860.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.392785263061524,
|
|
"epoch": 7.609776304888152,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.00012099553787660654,
|
|
"loss": 4.6639,
|
|
"mean_token_accuracy": 0.2391331672668457,
|
|
"num_tokens": 16737839.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.313677406311035,
|
|
"epoch": 7.613918806959403,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 0.00012076272196856808,
|
|
"loss": 4.5528,
|
|
"mean_token_accuracy": 0.23921243995428085,
|
|
"num_tokens": 16746171.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.37258620262146,
|
|
"epoch": 7.618061309030654,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001205302171739742,
|
|
"loss": 4.5333,
|
|
"mean_token_accuracy": 0.24552023708820342,
|
|
"num_tokens": 16755236.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.385955381393432,
|
|
"epoch": 7.6222038111019055,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00012029802396181256,
|
|
"loss": 4.5628,
|
|
"mean_token_accuracy": 0.24187612235546113,
|
|
"num_tokens": 16764126.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.357201957702637,
|
|
"epoch": 7.626346313173157,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00012006614280044225,
|
|
"loss": 4.613,
|
|
"mean_token_accuracy": 0.2490846946835518,
|
|
"num_tokens": 16772861.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.370921611785889,
|
|
"epoch": 7.630488815244408,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00011983457415759274,
|
|
"loss": 4.606,
|
|
"mean_token_accuracy": 0.2385077640414238,
|
|
"num_tokens": 16782119.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.430019474029541,
|
|
"epoch": 7.634631317315659,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 0.00011960331850036352,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.22989245057106017,
|
|
"num_tokens": 16790531.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.353761959075928,
|
|
"epoch": 7.63877381938691,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00011937237629522233,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.23915060758590698,
|
|
"num_tokens": 16799516.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.362230062484741,
|
|
"epoch": 7.642916321458161,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00011914174800800501,
|
|
"loss": 4.5786,
|
|
"mean_token_accuracy": 0.23670407980680466,
|
|
"num_tokens": 16807830.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.3949977397918705,
|
|
"epoch": 7.647058823529412,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00011891143410391387,
|
|
"loss": 4.6616,
|
|
"mean_token_accuracy": 0.23334141522645951,
|
|
"num_tokens": 16816987.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.324410772323608,
|
|
"epoch": 7.651201325600663,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00011868143504751732,
|
|
"loss": 4.4854,
|
|
"mean_token_accuracy": 0.2427896812558174,
|
|
"num_tokens": 16825723.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.40225510597229,
|
|
"epoch": 7.6553438276719135,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00011845175130274848,
|
|
"loss": 4.6076,
|
|
"mean_token_accuracy": 0.23954852372407914,
|
|
"num_tokens": 16835429.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.3901347637176515,
|
|
"epoch": 7.659486329743165,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011822238333290475,
|
|
"loss": 4.5491,
|
|
"mean_token_accuracy": 0.24678036272525788,
|
|
"num_tokens": 16844693.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.35869870185852,
|
|
"epoch": 7.663628831814416,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00011799333160064617,
|
|
"loss": 4.5779,
|
|
"mean_token_accuracy": 0.2378746584057808,
|
|
"num_tokens": 16853058.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.439568424224854,
|
|
"epoch": 7.667771333885667,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001177645965679953,
|
|
"loss": 4.6292,
|
|
"mean_token_accuracy": 0.22890978455543518,
|
|
"num_tokens": 16863017.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.3323915004730225,
|
|
"epoch": 7.671913835956918,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00011753617869633561,
|
|
"loss": 4.4972,
|
|
"mean_token_accuracy": 0.2476241484284401,
|
|
"num_tokens": 16872054.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.431376934051514,
|
|
"epoch": 7.676056338028169,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00011730807844641085,
|
|
"loss": 4.6458,
|
|
"mean_token_accuracy": 0.2358428105711937,
|
|
"num_tokens": 16881554.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.349488973617554,
|
|
"epoch": 7.68019884009942,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 0.00011708029627832431,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.23308860063552855,
|
|
"num_tokens": 16890050.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.409204483032227,
|
|
"epoch": 7.684341342170671,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00011685283265153732,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.23480950742959977,
|
|
"num_tokens": 16899298.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.4574988842010494,
|
|
"epoch": 7.688483844241922,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00011662568802486905,
|
|
"loss": 4.6626,
|
|
"mean_token_accuracy": 0.23217979669570923,
|
|
"num_tokens": 16908227.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.415662527084351,
|
|
"epoch": 7.692626346313173,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011639886285649489,
|
|
"loss": 4.6357,
|
|
"mean_token_accuracy": 0.23290325999259948,
|
|
"num_tokens": 16917708.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.333557653427124,
|
|
"epoch": 7.6967688483844245,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00011617235760394614,
|
|
"loss": 4.4751,
|
|
"mean_token_accuracy": 0.24976245015859605,
|
|
"num_tokens": 16926108.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.388310194015503,
|
|
"epoch": 7.700911350455675,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.0001159461727241085,
|
|
"loss": 4.5911,
|
|
"mean_token_accuracy": 0.23325285166502,
|
|
"num_tokens": 16935821.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.3461989402771,
|
|
"epoch": 7.705053852526927,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001157203086732217,
|
|
"loss": 4.642,
|
|
"mean_token_accuracy": 0.2362527072429657,
|
|
"num_tokens": 16944899.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.3444935321807865,
|
|
"epoch": 7.709196354598177,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00011549476590687811,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.2460354059934616,
|
|
"num_tokens": 16953745.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.4809776782989506,
|
|
"epoch": 7.713338856669428,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00011526954488002227,
|
|
"loss": 4.6706,
|
|
"mean_token_accuracy": 0.24023403972387314,
|
|
"num_tokens": 16962940.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.357692527770996,
|
|
"epoch": 7.717481358740679,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 0.00011504464604694953,
|
|
"loss": 4.5892,
|
|
"mean_token_accuracy": 0.23578887730836867,
|
|
"num_tokens": 16971322.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.409827089309692,
|
|
"epoch": 7.72162386081193,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011482006986130533,
|
|
"loss": 4.5267,
|
|
"mean_token_accuracy": 0.24672056287527083,
|
|
"num_tokens": 16980066.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.3698162078857425,
|
|
"epoch": 7.725766362883181,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00011459581677608453,
|
|
"loss": 4.5768,
|
|
"mean_token_accuracy": 0.24301660060882568,
|
|
"num_tokens": 16989202.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.344991445541382,
|
|
"epoch": 7.7299088649544325,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00011437188724362997,
|
|
"loss": 4.6221,
|
|
"mean_token_accuracy": 0.22714539021253585,
|
|
"num_tokens": 16999267.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.309905099868774,
|
|
"epoch": 7.734051367025684,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 0.00011414828171563214,
|
|
"loss": 4.5888,
|
|
"mean_token_accuracy": 0.24396019279956818,
|
|
"num_tokens": 17008252.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.351466226577759,
|
|
"epoch": 7.738193869096935,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00011392500064312773,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.23097996264696122,
|
|
"num_tokens": 17017568.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.405847597122192,
|
|
"epoch": 7.742336371168186,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 0.000113702044476499,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.23425201177597046,
|
|
"num_tokens": 17026206.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.361563062667846,
|
|
"epoch": 7.746478873239437,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011347941366547303,
|
|
"loss": 4.561,
|
|
"mean_token_accuracy": 0.2368785932660103,
|
|
"num_tokens": 17035114.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.4080198287963865,
|
|
"epoch": 7.750621375310688,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001132571086591204,
|
|
"loss": 4.6557,
|
|
"mean_token_accuracy": 0.2305152013897896,
|
|
"num_tokens": 17044459.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.3812541484832765,
|
|
"epoch": 7.754763877381938,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.0001130351299058547,
|
|
"loss": 4.6356,
|
|
"mean_token_accuracy": 0.22732425928115846,
|
|
"num_tokens": 17053985.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.351606655120849,
|
|
"epoch": 7.758906379453189,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011281347785343127,
|
|
"loss": 4.4629,
|
|
"mean_token_accuracy": 0.24610247164964677,
|
|
"num_tokens": 17063136.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.38593111038208,
|
|
"epoch": 7.7630488815244405,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00011259215294894647,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.23186769038438798,
|
|
"num_tokens": 17072423.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.361202621459961,
|
|
"epoch": 7.767191383595692,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00011237115563883693,
|
|
"loss": 4.5848,
|
|
"mean_token_accuracy": 0.23726729154586793,
|
|
"num_tokens": 17080578.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.372779083251953,
|
|
"epoch": 7.771333885666943,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00011215048636887825,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.2453882321715355,
|
|
"num_tokens": 17089995.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.32817759513855,
|
|
"epoch": 7.775476387738194,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001119301455841846,
|
|
"loss": 4.5143,
|
|
"mean_token_accuracy": 0.24361126124858856,
|
|
"num_tokens": 17099659.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.407952690124512,
|
|
"epoch": 7.779618889809445,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00011171013372920735,
|
|
"loss": 4.6245,
|
|
"mean_token_accuracy": 0.23877716362476348,
|
|
"num_tokens": 17109972.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.453830623626709,
|
|
"epoch": 7.783761391880696,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011149045124773441,
|
|
"loss": 4.6985,
|
|
"mean_token_accuracy": 0.22959160506725312,
|
|
"num_tokens": 17120288.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.408268880844116,
|
|
"epoch": 7.787903893951947,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00011127109858288945,
|
|
"loss": 4.6363,
|
|
"mean_token_accuracy": 0.24725847095251083,
|
|
"num_tokens": 17130577.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.417545938491822,
|
|
"epoch": 7.792046396023198,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00011105207617713065,
|
|
"loss": 4.7095,
|
|
"mean_token_accuracy": 0.22697378247976302,
|
|
"num_tokens": 17140782.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.302483606338501,
|
|
"epoch": 7.796188898094449,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011083338447225027,
|
|
"loss": 4.5767,
|
|
"mean_token_accuracy": 0.23998009264469147,
|
|
"num_tokens": 17150013.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.420140886306763,
|
|
"epoch": 7.8003314001657,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00011061502390937331,
|
|
"loss": 4.6204,
|
|
"mean_token_accuracy": 0.23281200379133224,
|
|
"num_tokens": 17159349.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.366073799133301,
|
|
"epoch": 7.804473902236952,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 0.0001103969949289568,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.23462104201316833,
|
|
"num_tokens": 17168063.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.417164707183838,
|
|
"epoch": 7.808616404308202,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00011017929797078919,
|
|
"loss": 4.6083,
|
|
"mean_token_accuracy": 0.22783102542161943,
|
|
"num_tokens": 17177087.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.397407531738281,
|
|
"epoch": 7.812758906379453,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00010996193347398886,
|
|
"loss": 4.5858,
|
|
"mean_token_accuracy": 0.24561947882175444,
|
|
"num_tokens": 17186875.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.3869102001190186,
|
|
"epoch": 7.816901408450704,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00010974490187700394,
|
|
"loss": 4.6205,
|
|
"mean_token_accuracy": 0.23523908704519272,
|
|
"num_tokens": 17195666.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.375324010848999,
|
|
"epoch": 7.821043910521955,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001095282036176107,
|
|
"loss": 4.5738,
|
|
"mean_token_accuracy": 0.236721533536911,
|
|
"num_tokens": 17205145.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.430977487564087,
|
|
"epoch": 7.825186412593206,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00010931183913291335,
|
|
"loss": 4.6173,
|
|
"mean_token_accuracy": 0.23458994626998902,
|
|
"num_tokens": 17214106.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.33274507522583,
|
|
"epoch": 7.829328914664457,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00010909580885934265,
|
|
"loss": 4.4848,
|
|
"mean_token_accuracy": 0.2540983587503433,
|
|
"num_tokens": 17223343.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.375152206420898,
|
|
"epoch": 7.8334714167357085,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00010888011323265517,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.22671249657869338,
|
|
"num_tokens": 17233528.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.327553844451904,
|
|
"epoch": 7.83761391880696,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00010866475268793275,
|
|
"loss": 4.5131,
|
|
"mean_token_accuracy": 0.2410602241754532,
|
|
"num_tokens": 17242026.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.329733228683471,
|
|
"epoch": 7.841756420878211,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00010844972765958096,
|
|
"loss": 4.5623,
|
|
"mean_token_accuracy": 0.24422430396080017,
|
|
"num_tokens": 17251203.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.294923210144043,
|
|
"epoch": 7.845898922949462,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00010823503858132894,
|
|
"loss": 4.468,
|
|
"mean_token_accuracy": 0.24950027763843535,
|
|
"num_tokens": 17260072.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.364843940734863,
|
|
"epoch": 7.850041425020713,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00010802068588622793,
|
|
"loss": 4.5898,
|
|
"mean_token_accuracy": 0.24622309058904648,
|
|
"num_tokens": 17269015.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.347899293899536,
|
|
"epoch": 7.854183927091963,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010780667000665067,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.24075209647417067,
|
|
"num_tokens": 17277721.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.361366605758667,
|
|
"epoch": 7.858326429163214,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010759299137429073,
|
|
"loss": 4.6223,
|
|
"mean_token_accuracy": 0.23815398514270783,
|
|
"num_tokens": 17286805.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.427087068557739,
|
|
"epoch": 7.862468931234465,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00010737965042016116,
|
|
"loss": 4.6886,
|
|
"mean_token_accuracy": 0.226504348218441,
|
|
"num_tokens": 17297577.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.379040479660034,
|
|
"epoch": 7.866611433305716,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00010716664757459404,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.23412017971277238,
|
|
"num_tokens": 17306620.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.3713596820831295,
|
|
"epoch": 7.8707539353769675,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00010695398326723938,
|
|
"loss": 4.6081,
|
|
"mean_token_accuracy": 0.2322966620326042,
|
|
"num_tokens": 17314796.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"epoch": 7.8707539353769675,
|
|
"eval_entropy": 5.195807394950883,
|
|
"eval_loss": 5.706310749053955,
|
|
"eval_mean_token_accuracy": 0.17075323869488132,
|
|
"eval_num_tokens": 17314796.0,
|
|
"eval_runtime": 2.2893,
|
|
"eval_samples_per_second": 1636.779,
|
|
"eval_steps_per_second": 204.87,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.384198093414307,
|
|
"epoch": 7.874896437448219,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 0.00010674165792706423,
|
|
"loss": 4.6333,
|
|
"mean_token_accuracy": 0.24373967796564103,
|
|
"num_tokens": 17324048.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.374878597259522,
|
|
"epoch": 7.87903893951947,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00010652967198235214,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.23792498409748078,
|
|
"num_tokens": 17333354.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.3523033618927,
|
|
"epoch": 7.883181441590721,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.0001063180258607018,
|
|
"loss": 4.5057,
|
|
"mean_token_accuracy": 0.25705979466438295,
|
|
"num_tokens": 17343026.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.323693132400512,
|
|
"epoch": 7.887323943661972,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 0.00010610671998902671,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.24409320205450058,
|
|
"num_tokens": 17351161.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.389847135543823,
|
|
"epoch": 7.891466445733223,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00010589575479355379,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.24228766411542893,
|
|
"num_tokens": 17360697.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.407340621948242,
|
|
"epoch": 7.895608947804474,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.00010568513069982289,
|
|
"loss": 4.6388,
|
|
"mean_token_accuracy": 0.23943895548582078,
|
|
"num_tokens": 17370303.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.3477864265441895,
|
|
"epoch": 7.899751449875725,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010547484813268594,
|
|
"loss": 4.5853,
|
|
"mean_token_accuracy": 0.2385518878698349,
|
|
"num_tokens": 17379557.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.358041429519654,
|
|
"epoch": 7.903893951946976,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00010526490751630568,
|
|
"loss": 4.6308,
|
|
"mean_token_accuracy": 0.24188313335180284,
|
|
"num_tokens": 17388206.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.426754903793335,
|
|
"epoch": 7.908036454018227,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010505530927415544,
|
|
"loss": 4.6808,
|
|
"mean_token_accuracy": 0.23337105363607408,
|
|
"num_tokens": 17398055.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.296615362167358,
|
|
"epoch": 7.912178956089478,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00010484605382901772,
|
|
"loss": 4.4786,
|
|
"mean_token_accuracy": 0.24192535132169724,
|
|
"num_tokens": 17407214.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.4174778938293455,
|
|
"epoch": 7.916321458160729,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00010463714160298354,
|
|
"loss": 4.6295,
|
|
"mean_token_accuracy": 0.23703147172927858,
|
|
"num_tokens": 17416447.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.400790166854859,
|
|
"epoch": 7.92046396023198,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 0.00010442857301745184,
|
|
"loss": 4.6227,
|
|
"mean_token_accuracy": 0.22679152041673661,
|
|
"num_tokens": 17424921.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.325470304489135,
|
|
"epoch": 7.924606462303231,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 0.0001042203484931281,
|
|
"loss": 4.4573,
|
|
"mean_token_accuracy": 0.24509802162647248,
|
|
"num_tokens": 17434425.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.329994010925293,
|
|
"epoch": 7.928748964374482,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 0.00010401246845002407,
|
|
"loss": 4.5671,
|
|
"mean_token_accuracy": 0.24316383004188538,
|
|
"num_tokens": 17443879.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.315007066726684,
|
|
"epoch": 7.932891466445733,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.00010380493330745641,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.24064242243766784,
|
|
"num_tokens": 17452276.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.334318733215332,
|
|
"epoch": 7.937033968516984,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 0.00010359774348404626,
|
|
"loss": 4.6159,
|
|
"mean_token_accuracy": 0.24079674780368804,
|
|
"num_tokens": 17460706.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.400369691848755,
|
|
"epoch": 7.9411764705882355,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 0.00010339089939771814,
|
|
"loss": 4.6343,
|
|
"mean_token_accuracy": 0.24299917966127396,
|
|
"num_tokens": 17469754.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.409340286254883,
|
|
"epoch": 7.945318972659487,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00010318440146569904,
|
|
"loss": 4.7344,
|
|
"mean_token_accuracy": 0.22147315740585327,
|
|
"num_tokens": 17480057.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.330471849441528,
|
|
"epoch": 7.949461474730738,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00010297825010451806,
|
|
"loss": 4.5625,
|
|
"mean_token_accuracy": 0.24238938242197036,
|
|
"num_tokens": 17490427.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.37815752029419,
|
|
"epoch": 7.953603976801988,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0001027724457300048,
|
|
"loss": 4.5872,
|
|
"mean_token_accuracy": 0.2277197062969208,
|
|
"num_tokens": 17499105.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.3760778427124025,
|
|
"epoch": 7.957746478873239,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010256698875728938,
|
|
"loss": 4.6427,
|
|
"mean_token_accuracy": 0.22734907120466233,
|
|
"num_tokens": 17508499.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.305395698547363,
|
|
"epoch": 7.96188898094449,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 0.00010236187960080084,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.2431729570031166,
|
|
"num_tokens": 17516885.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.348442602157593,
|
|
"epoch": 7.966031483015741,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 0.00010215711867426678,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.23949686735868453,
|
|
"num_tokens": 17524958.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.37509560585022,
|
|
"epoch": 7.970173985086992,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 0.00010195270639071243,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.23465617150068283,
|
|
"num_tokens": 17534185.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.379759693145752,
|
|
"epoch": 7.9743164871582435,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0001017486431624596,
|
|
"loss": 4.6012,
|
|
"mean_token_accuracy": 0.24060825109481812,
|
|
"num_tokens": 17542696.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.398105669021606,
|
|
"epoch": 7.978458989229495,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 0.00010154492940112624,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.2509047448635101,
|
|
"num_tokens": 17552751.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.453883790969849,
|
|
"epoch": 7.982601491300746,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010134156551762519,
|
|
"loss": 4.6155,
|
|
"mean_token_accuracy": 0.23366608172655107,
|
|
"num_tokens": 17561973.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.417593240737915,
|
|
"epoch": 7.986743993371997,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 0.00010113855192216359,
|
|
"loss": 4.6646,
|
|
"mean_token_accuracy": 0.22802543342113496,
|
|
"num_tokens": 17571238.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.401760482788086,
|
|
"epoch": 7.990886495443248,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 0.00010093588902424217,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.24109666794538498,
|
|
"num_tokens": 17580189.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.359200525283813,
|
|
"epoch": 7.995028997514499,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00010073357723265398,
|
|
"loss": 4.64,
|
|
"mean_token_accuracy": 0.23255921006202698,
|
|
"num_tokens": 17590051.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.401599168777466,
|
|
"epoch": 7.99917149958575,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 0.00010053161695548418,
|
|
"loss": 4.6107,
|
|
"mean_token_accuracy": 0.23906555771827698,
|
|
"num_tokens": 17599036.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.397087574005127,
|
|
"epoch": 8.003314001657001,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00010033000860010866,
|
|
"loss": 4.5105,
|
|
"mean_token_accuracy": 0.24870264530181885,
|
|
"num_tokens": 17608433.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.375066328048706,
|
|
"epoch": 8.007456503728251,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 0.0001001287525731934,
|
|
"loss": 4.5396,
|
|
"mean_token_accuracy": 0.24229668378829955,
|
|
"num_tokens": 17617696.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.388607406616211,
|
|
"epoch": 8.011599005799503,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 9.992784928069397e-05,
|
|
"loss": 4.5642,
|
|
"mean_token_accuracy": 0.239173424243927,
|
|
"num_tokens": 17626619.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.37886061668396,
|
|
"epoch": 8.015741507870754,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 9.972729912785411e-05,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.25568399876356124,
|
|
"num_tokens": 17635306.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.333650350570679,
|
|
"epoch": 8.019884009942006,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 9.95271025192055e-05,
|
|
"loss": 4.4355,
|
|
"mean_token_accuracy": 0.2542230635881424,
|
|
"num_tokens": 17643526.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.408865022659302,
|
|
"epoch": 8.024026512013256,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 9.93272598585665e-05,
|
|
"loss": 4.6154,
|
|
"mean_token_accuracy": 0.23299770355224608,
|
|
"num_tokens": 17652474.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.360271263122558,
|
|
"epoch": 8.028169014084508,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.912777154904171e-05,
|
|
"loss": 4.5463,
|
|
"mean_token_accuracy": 0.24317206293344498,
|
|
"num_tokens": 17662025.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.26003623008728,
|
|
"epoch": 8.032311516155758,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 9.89286379930207e-05,
|
|
"loss": 4.4633,
|
|
"mean_token_accuracy": 0.25363629311323166,
|
|
"num_tokens": 17670908.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.327250671386719,
|
|
"epoch": 8.036454018227008,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.872985959217779e-05,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.251982381939888,
|
|
"num_tokens": 17681242.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.338528156280518,
|
|
"epoch": 8.04059652029826,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 9.853143674747053e-05,
|
|
"loss": 4.4447,
|
|
"mean_token_accuracy": 0.25127510726451874,
|
|
"num_tokens": 17689816.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.3733484745025635,
|
|
"epoch": 8.04473902236951,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.833336985913965e-05,
|
|
"loss": 4.5271,
|
|
"mean_token_accuracy": 0.2487008273601532,
|
|
"num_tokens": 17699251.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.389735841751099,
|
|
"epoch": 8.048881524440763,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.813565932670767e-05,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.25063595175743103,
|
|
"num_tokens": 17708906.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.420936632156372,
|
|
"epoch": 8.053024026512013,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.793830554897826e-05,
|
|
"loss": 4.5603,
|
|
"mean_token_accuracy": 0.2405978634953499,
|
|
"num_tokens": 17718071.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.337154293060303,
|
|
"epoch": 8.057166528583265,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.774130892403566e-05,
|
|
"loss": 4.4638,
|
|
"mean_token_accuracy": 0.2549301952123642,
|
|
"num_tokens": 17727690.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.328612279891968,
|
|
"epoch": 8.061309030654515,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 9.754466984924348e-05,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.250596296787262,
|
|
"num_tokens": 17735934.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.323670196533203,
|
|
"epoch": 8.065451532725767,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 9.734838872124432e-05,
|
|
"loss": 4.4603,
|
|
"mean_token_accuracy": 0.25013976246118547,
|
|
"num_tokens": 17744323.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.280493068695068,
|
|
"epoch": 8.069594034797017,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.715246593595859e-05,
|
|
"loss": 4.4462,
|
|
"mean_token_accuracy": 0.2556710198521614,
|
|
"num_tokens": 17753335.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.303632593154907,
|
|
"epoch": 8.07373653686827,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 9.695690188858408e-05,
|
|
"loss": 4.5179,
|
|
"mean_token_accuracy": 0.24594072848558426,
|
|
"num_tokens": 17761952.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.401737546920776,
|
|
"epoch": 8.07787903893952,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 9.676169697359469e-05,
|
|
"loss": 4.5866,
|
|
"mean_token_accuracy": 0.24217255860567094,
|
|
"num_tokens": 17771341.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.299386072158813,
|
|
"epoch": 8.08202154101077,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.656685158474018e-05,
|
|
"loss": 4.4579,
|
|
"mean_token_accuracy": 0.2538116559386253,
|
|
"num_tokens": 17780289.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.36434645652771,
|
|
"epoch": 8.086164043082022,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 9.63723661150449e-05,
|
|
"loss": 4.5389,
|
|
"mean_token_accuracy": 0.24315210729837416,
|
|
"num_tokens": 17789317.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.42515459060669,
|
|
"epoch": 8.090306545153272,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 9.617824095680742e-05,
|
|
"loss": 4.6049,
|
|
"mean_token_accuracy": 0.23983444273471832,
|
|
"num_tokens": 17797875.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.3375153064727785,
|
|
"epoch": 8.094449047224524,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 9.598447650159931e-05,
|
|
"loss": 4.5473,
|
|
"mean_token_accuracy": 0.24043136984109878,
|
|
"num_tokens": 17806603.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.455809211730957,
|
|
"epoch": 8.098591549295774,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 9.579107314026459e-05,
|
|
"loss": 4.6046,
|
|
"mean_token_accuracy": 0.23089144229888917,
|
|
"num_tokens": 17815747.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.385101699829102,
|
|
"epoch": 8.102734051367026,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 9.559803126291911e-05,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.24374106973409654,
|
|
"num_tokens": 17824568.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.422874402999878,
|
|
"epoch": 8.106876553438276,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.540535125894931e-05,
|
|
"loss": 4.5646,
|
|
"mean_token_accuracy": 0.2520934954285622,
|
|
"num_tokens": 17834244.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.3469822883605955,
|
|
"epoch": 8.111019055509528,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 9.521303351701193e-05,
|
|
"loss": 4.4707,
|
|
"mean_token_accuracy": 0.2468368262052536,
|
|
"num_tokens": 17843285.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.42300009727478,
|
|
"epoch": 8.115161557580779,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.502107842503282e-05,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.248809714615345,
|
|
"num_tokens": 17852379.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.364935874938965,
|
|
"epoch": 8.11930405965203,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.48294863702063e-05,
|
|
"loss": 4.4873,
|
|
"mean_token_accuracy": 0.2602342590689659,
|
|
"num_tokens": 17861948.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.361537790298462,
|
|
"epoch": 8.12344656172328,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.463825773899465e-05,
|
|
"loss": 4.465,
|
|
"mean_token_accuracy": 0.2519824579358101,
|
|
"num_tokens": 17870445.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.410823488235474,
|
|
"epoch": 8.127589063794533,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 9.444739291712673e-05,
|
|
"loss": 4.5396,
|
|
"mean_token_accuracy": 0.25779161006212237,
|
|
"num_tokens": 17879380.0,
|
|
"step": 9810
|
|
},
|
|
{
|
|
"entropy": 5.36061053276062,
|
|
"epoch": 8.131731565865783,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.425689228959791e-05,
|
|
"loss": 4.5431,
|
|
"mean_token_accuracy": 0.24801456332206726,
|
|
"num_tokens": 17888631.0,
|
|
"step": 9815
|
|
},
|
|
{
|
|
"entropy": 5.349468803405761,
|
|
"epoch": 8.135874067937033,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.406675624066868e-05,
|
|
"loss": 4.485,
|
|
"mean_token_accuracy": 0.24566220343112946,
|
|
"num_tokens": 17898541.0,
|
|
"step": 9820
|
|
},
|
|
{
|
|
"entropy": 5.365914297103882,
|
|
"epoch": 8.140016570008285,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 9.38769851538642e-05,
|
|
"loss": 4.5089,
|
|
"mean_token_accuracy": 0.24751509577035904,
|
|
"num_tokens": 17906664.0,
|
|
"step": 9825
|
|
},
|
|
{
|
|
"entropy": 5.337427043914795,
|
|
"epoch": 8.144159072079535,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 9.368757941197356e-05,
|
|
"loss": 4.5135,
|
|
"mean_token_accuracy": 0.24569728076457978,
|
|
"num_tokens": 17916201.0,
|
|
"step": 9830
|
|
},
|
|
{
|
|
"entropy": 5.397465372085572,
|
|
"epoch": 8.148301574150787,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.34985393970488e-05,
|
|
"loss": 4.5338,
|
|
"mean_token_accuracy": 0.24453563392162322,
|
|
"num_tokens": 17925700.0,
|
|
"step": 9835
|
|
},
|
|
{
|
|
"entropy": 5.313456773757935,
|
|
"epoch": 8.152444076222038,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 9.330986549040432e-05,
|
|
"loss": 4.4968,
|
|
"mean_token_accuracy": 0.2479489415884018,
|
|
"num_tokens": 17934293.0,
|
|
"step": 9840
|
|
},
|
|
{
|
|
"entropy": 5.3205718994140625,
|
|
"epoch": 8.15658657829329,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.312155807261602e-05,
|
|
"loss": 4.5145,
|
|
"mean_token_accuracy": 0.24399951696395875,
|
|
"num_tokens": 17943541.0,
|
|
"step": 9845
|
|
},
|
|
{
|
|
"entropy": 5.413444995880127,
|
|
"epoch": 8.16072908036454,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 9.293361752352045e-05,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.2535242855548859,
|
|
"num_tokens": 17952616.0,
|
|
"step": 9850
|
|
},
|
|
{
|
|
"entropy": 5.3816522598266605,
|
|
"epoch": 8.164871582435792,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.274604422221433e-05,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.2477547362446785,
|
|
"num_tokens": 17961414.0,
|
|
"step": 9855
|
|
},
|
|
{
|
|
"entropy": 5.401419639587402,
|
|
"epoch": 8.169014084507042,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 9.255883854705344e-05,
|
|
"loss": 4.5578,
|
|
"mean_token_accuracy": 0.24420518279075623,
|
|
"num_tokens": 17972077.0,
|
|
"step": 9860
|
|
},
|
|
{
|
|
"entropy": 5.377471971511841,
|
|
"epoch": 8.173156586578294,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 9.237200087565217e-05,
|
|
"loss": 4.5246,
|
|
"mean_token_accuracy": 0.24838614761829375,
|
|
"num_tokens": 17980303.0,
|
|
"step": 9865
|
|
},
|
|
{
|
|
"entropy": 5.440533018112182,
|
|
"epoch": 8.177299088649544,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 9.218553158488238e-05,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.2438330978155136,
|
|
"num_tokens": 17990410.0,
|
|
"step": 9870
|
|
},
|
|
{
|
|
"entropy": 5.347458028793335,
|
|
"epoch": 8.181441590720794,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 9.199943105087319e-05,
|
|
"loss": 4.4577,
|
|
"mean_token_accuracy": 0.25606369227170944,
|
|
"num_tokens": 17998931.0,
|
|
"step": 9875
|
|
},
|
|
{
|
|
"entropy": 5.3542581558227536,
|
|
"epoch": 8.185584092792046,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.181369964900957e-05,
|
|
"loss": 4.5068,
|
|
"mean_token_accuracy": 0.2523238345980644,
|
|
"num_tokens": 18007853.0,
|
|
"step": 9880
|
|
},
|
|
{
|
|
"entropy": 5.338401889801025,
|
|
"epoch": 8.189726594863297,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 9.162833775393209e-05,
|
|
"loss": 4.4798,
|
|
"mean_token_accuracy": 0.2511543810367584,
|
|
"num_tokens": 18016517.0,
|
|
"step": 9885
|
|
},
|
|
{
|
|
"entropy": 5.391319990158081,
|
|
"epoch": 8.193869096934549,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 9.1443345739536e-05,
|
|
"loss": 4.5766,
|
|
"mean_token_accuracy": 0.24527695327997207,
|
|
"num_tokens": 18025057.0,
|
|
"step": 9890
|
|
},
|
|
{
|
|
"entropy": 5.366326332092285,
|
|
"epoch": 8.198011599005799,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 9.12587239789703e-05,
|
|
"loss": 4.5661,
|
|
"mean_token_accuracy": 0.24108184576034547,
|
|
"num_tokens": 18034371.0,
|
|
"step": 9895
|
|
},
|
|
{
|
|
"entropy": 5.31302285194397,
|
|
"epoch": 8.202154101077051,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.10744728446374e-05,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.24818196296691894,
|
|
"num_tokens": 18043354.0,
|
|
"step": 9900
|
|
},
|
|
{
|
|
"entropy": 5.320017099380493,
|
|
"epoch": 8.206296603148301,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 9.089059270819187e-05,
|
|
"loss": 4.4841,
|
|
"mean_token_accuracy": 0.24484689384698868,
|
|
"num_tokens": 18051879.0,
|
|
"step": 9905
|
|
},
|
|
{
|
|
"entropy": 5.430904054641724,
|
|
"epoch": 8.210439105219553,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.070708394054005e-05,
|
|
"loss": 4.5587,
|
|
"mean_token_accuracy": 0.24408431351184845,
|
|
"num_tokens": 18062011.0,
|
|
"step": 9910
|
|
},
|
|
{
|
|
"entropy": 5.435532808303833,
|
|
"epoch": 8.214581607290803,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.052394691183921e-05,
|
|
"loss": 4.6233,
|
|
"mean_token_accuracy": 0.23413968980312347,
|
|
"num_tokens": 18071692.0,
|
|
"step": 9915
|
|
},
|
|
{
|
|
"entropy": 5.313306570053101,
|
|
"epoch": 8.218724109362055,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 9.03411819914967e-05,
|
|
"loss": 4.467,
|
|
"mean_token_accuracy": 0.2453225553035736,
|
|
"num_tokens": 18080646.0,
|
|
"step": 9920
|
|
},
|
|
{
|
|
"entropy": 5.343155336380005,
|
|
"epoch": 8.222866611433306,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 9.015878954816941e-05,
|
|
"loss": 4.4747,
|
|
"mean_token_accuracy": 0.24871653765439988,
|
|
"num_tokens": 18088788.0,
|
|
"step": 9925
|
|
},
|
|
{
|
|
"entropy": 5.382840585708618,
|
|
"epoch": 8.227009113504558,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 8.997676994976281e-05,
|
|
"loss": 4.5269,
|
|
"mean_token_accuracy": 0.23924959748983382,
|
|
"num_tokens": 18098319.0,
|
|
"step": 9930
|
|
},
|
|
{
|
|
"entropy": 5.358247375488281,
|
|
"epoch": 8.231151615575808,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.979512356343023e-05,
|
|
"loss": 4.5716,
|
|
"mean_token_accuracy": 0.24656253904104233,
|
|
"num_tokens": 18107740.0,
|
|
"step": 9935
|
|
},
|
|
{
|
|
"entropy": 5.368626117706299,
|
|
"epoch": 8.235294117647058,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 8.961385075557243e-05,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.2351240485906601,
|
|
"num_tokens": 18117762.0,
|
|
"step": 9940
|
|
},
|
|
{
|
|
"entropy": 5.314665174484253,
|
|
"epoch": 8.23943661971831,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 8.943295189183632e-05,
|
|
"loss": 4.4337,
|
|
"mean_token_accuracy": 0.254423525929451,
|
|
"num_tokens": 18126212.0,
|
|
"step": 9945
|
|
},
|
|
{
|
|
"entropy": 5.406507158279419,
|
|
"epoch": 8.24357912178956,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.925242733711484e-05,
|
|
"loss": 4.5851,
|
|
"mean_token_accuracy": 0.24186000227928162,
|
|
"num_tokens": 18135622.0,
|
|
"step": 9950
|
|
},
|
|
{
|
|
"entropy": 5.393651533126831,
|
|
"epoch": 8.247721623860812,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.90722774555456e-05,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.2398001104593277,
|
|
"num_tokens": 18144768.0,
|
|
"step": 9955
|
|
},
|
|
{
|
|
"entropy": 5.377536964416504,
|
|
"epoch": 8.251864125932062,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 8.889250261051063e-05,
|
|
"loss": 4.5799,
|
|
"mean_token_accuracy": 0.24715314507484437,
|
|
"num_tokens": 18155107.0,
|
|
"step": 9960
|
|
},
|
|
{
|
|
"entropy": 5.353028631210327,
|
|
"epoch": 8.256006628003314,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 8.871310316463554e-05,
|
|
"loss": 4.537,
|
|
"mean_token_accuracy": 0.2496013656258583,
|
|
"num_tokens": 18164064.0,
|
|
"step": 9965
|
|
},
|
|
{
|
|
"entropy": 5.323932647705078,
|
|
"epoch": 8.260149130074565,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 8.853407947978845e-05,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.23361928015947342,
|
|
"num_tokens": 18172714.0,
|
|
"step": 9970
|
|
},
|
|
{
|
|
"entropy": 5.327693891525269,
|
|
"epoch": 8.264291632145817,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.835543191707982e-05,
|
|
"loss": 4.5263,
|
|
"mean_token_accuracy": 0.24132412374019624,
|
|
"num_tokens": 18182158.0,
|
|
"step": 9975
|
|
},
|
|
{
|
|
"entropy": 5.3757164478302,
|
|
"epoch": 8.268434134217067,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 8.81771608368613e-05,
|
|
"loss": 4.5296,
|
|
"mean_token_accuracy": 0.23964994251728058,
|
|
"num_tokens": 18190605.0,
|
|
"step": 9980
|
|
},
|
|
{
|
|
"entropy": 5.4056432247161865,
|
|
"epoch": 8.272576636288319,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.799926659872507e-05,
|
|
"loss": 4.6774,
|
|
"mean_token_accuracy": 0.22619114220142364,
|
|
"num_tokens": 18199992.0,
|
|
"step": 9985
|
|
},
|
|
{
|
|
"entropy": 5.4320320129394535,
|
|
"epoch": 8.276719138359569,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 8.782174956150335e-05,
|
|
"loss": 4.5631,
|
|
"mean_token_accuracy": 0.24496908932924272,
|
|
"num_tokens": 18208641.0,
|
|
"step": 9990
|
|
},
|
|
{
|
|
"entropy": 5.390999698638916,
|
|
"epoch": 8.280861640430821,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.764461008326723e-05,
|
|
"loss": 4.5486,
|
|
"mean_token_accuracy": 0.2448657423257828,
|
|
"num_tokens": 18218355.0,
|
|
"step": 9995
|
|
},
|
|
{
|
|
"entropy": 5.376265954971314,
|
|
"epoch": 8.285004142502071,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.746784852132661e-05,
|
|
"loss": 4.5445,
|
|
"mean_token_accuracy": 0.24335553497076035,
|
|
"num_tokens": 18227217.0,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"epoch": 8.285004142502071,
|
|
"eval_entropy": 5.231542894326802,
|
|
"eval_loss": 5.713065147399902,
|
|
"eval_mean_token_accuracy": 0.17023465053231984,
|
|
"eval_num_tokens": 18227217.0,
|
|
"eval_runtime": 2.1038,
|
|
"eval_samples_per_second": 1781.101,
|
|
"eval_steps_per_second": 222.935,
|
|
"step": 10000
|
|
},
|
|
{
|
|
"entropy": 5.3508241176605225,
|
|
"epoch": 8.289146644573322,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.729146523222877e-05,
|
|
"loss": 4.4932,
|
|
"mean_token_accuracy": 0.24565423280000687,
|
|
"num_tokens": 18236410.0,
|
|
"step": 10005
|
|
},
|
|
{
|
|
"entropy": 5.378200531005859,
|
|
"epoch": 8.293289146644574,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 8.711546057175804e-05,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.2447373762726784,
|
|
"num_tokens": 18244626.0,
|
|
"step": 10010
|
|
},
|
|
{
|
|
"entropy": 5.43381667137146,
|
|
"epoch": 8.297431648715824,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 8.69398348949351e-05,
|
|
"loss": 4.5769,
|
|
"mean_token_accuracy": 0.24278405606746672,
|
|
"num_tokens": 18253938.0,
|
|
"step": 10015
|
|
},
|
|
{
|
|
"entropy": 5.344224214553833,
|
|
"epoch": 8.301574150787076,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 8.676458855601612e-05,
|
|
"loss": 4.5459,
|
|
"mean_token_accuracy": 0.24142624586820602,
|
|
"num_tokens": 18262674.0,
|
|
"step": 10020
|
|
},
|
|
{
|
|
"entropy": 5.403616619110108,
|
|
"epoch": 8.305716652858326,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.658972190849215e-05,
|
|
"loss": 4.6035,
|
|
"mean_token_accuracy": 0.24293648898601533,
|
|
"num_tokens": 18272558.0,
|
|
"step": 10025
|
|
},
|
|
{
|
|
"entropy": 5.456557416915894,
|
|
"epoch": 8.309859154929578,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 8.641523530508827e-05,
|
|
"loss": 4.6421,
|
|
"mean_token_accuracy": 0.24141709506511688,
|
|
"num_tokens": 18282522.0,
|
|
"step": 10030
|
|
},
|
|
{
|
|
"entropy": 5.4183331489562985,
|
|
"epoch": 8.314001657000828,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.624112909776314e-05,
|
|
"loss": 4.5307,
|
|
"mean_token_accuracy": 0.24181173741817474,
|
|
"num_tokens": 18290933.0,
|
|
"step": 10035
|
|
},
|
|
{
|
|
"entropy": 5.365574312210083,
|
|
"epoch": 8.31814415907208,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.606740363770788e-05,
|
|
"loss": 4.5225,
|
|
"mean_token_accuracy": 0.2396170124411583,
|
|
"num_tokens": 18300705.0,
|
|
"step": 10040
|
|
},
|
|
{
|
|
"entropy": 5.370649242401123,
|
|
"epoch": 8.32228666114333,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 8.589405927534571e-05,
|
|
"loss": 4.5198,
|
|
"mean_token_accuracy": 0.2495922178030014,
|
|
"num_tokens": 18309889.0,
|
|
"step": 10045
|
|
},
|
|
{
|
|
"entropy": 5.376449155807495,
|
|
"epoch": 8.326429163214582,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.57210963603313e-05,
|
|
"loss": 4.5521,
|
|
"mean_token_accuracy": 0.2426110863685608,
|
|
"num_tokens": 18319282.0,
|
|
"step": 10050
|
|
},
|
|
{
|
|
"entropy": 5.402587509155273,
|
|
"epoch": 8.330571665285833,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 8.554851524154961e-05,
|
|
"loss": 4.6023,
|
|
"mean_token_accuracy": 0.24022258222103118,
|
|
"num_tokens": 18328713.0,
|
|
"step": 10055
|
|
},
|
|
{
|
|
"entropy": 5.347217178344726,
|
|
"epoch": 8.334714167357085,
|
|
"grad_norm": 1.6796875,
|
|
"learning_rate": 8.537631626711573e-05,
|
|
"loss": 4.4588,
|
|
"mean_token_accuracy": 0.249611034989357,
|
|
"num_tokens": 18337262.0,
|
|
"step": 10060
|
|
},
|
|
{
|
|
"entropy": 5.401508474349976,
|
|
"epoch": 8.338856669428335,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.520449978437372e-05,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.2444845497608185,
|
|
"num_tokens": 18346699.0,
|
|
"step": 10065
|
|
},
|
|
{
|
|
"entropy": 5.313845634460449,
|
|
"epoch": 8.342999171499585,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 8.50330661398962e-05,
|
|
"loss": 4.492,
|
|
"mean_token_accuracy": 0.24203478693962097,
|
|
"num_tokens": 18355466.0,
|
|
"step": 10070
|
|
},
|
|
{
|
|
"entropy": 5.343691730499268,
|
|
"epoch": 8.347141673570837,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.486201567948363e-05,
|
|
"loss": 4.4937,
|
|
"mean_token_accuracy": 0.24564718157052995,
|
|
"num_tokens": 18363988.0,
|
|
"step": 10075
|
|
},
|
|
{
|
|
"entropy": 5.4246148586273195,
|
|
"epoch": 8.351284175642087,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 8.469134874816342e-05,
|
|
"loss": 4.6289,
|
|
"mean_token_accuracy": 0.23769551366567612,
|
|
"num_tokens": 18373784.0,
|
|
"step": 10080
|
|
},
|
|
{
|
|
"entropy": 5.385478448867798,
|
|
"epoch": 8.35542667771334,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 8.45210656901895e-05,
|
|
"loss": 4.4969,
|
|
"mean_token_accuracy": 0.24037808626890184,
|
|
"num_tokens": 18382929.0,
|
|
"step": 10085
|
|
},
|
|
{
|
|
"entropy": 5.432168292999267,
|
|
"epoch": 8.35956917978459,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 8.435116684904136e-05,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.24814670979976655,
|
|
"num_tokens": 18392399.0,
|
|
"step": 10090
|
|
},
|
|
{
|
|
"entropy": 5.43607611656189,
|
|
"epoch": 8.363711681855841,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.418165256742346e-05,
|
|
"loss": 4.6685,
|
|
"mean_token_accuracy": 0.2312287747859955,
|
|
"num_tokens": 18402255.0,
|
|
"step": 10095
|
|
},
|
|
{
|
|
"entropy": 5.38588433265686,
|
|
"epoch": 8.367854183927092,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 8.401252318726473e-05,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.2465193286538124,
|
|
"num_tokens": 18411677.0,
|
|
"step": 10100
|
|
},
|
|
{
|
|
"entropy": 5.318342590332032,
|
|
"epoch": 8.371996685998344,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 8.384377904971753e-05,
|
|
"loss": 4.4997,
|
|
"mean_token_accuracy": 0.24247432351112366,
|
|
"num_tokens": 18420332.0,
|
|
"step": 10105
|
|
},
|
|
{
|
|
"entropy": 5.273746395111084,
|
|
"epoch": 8.376139188069594,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.367542049515733e-05,
|
|
"loss": 4.4253,
|
|
"mean_token_accuracy": 0.25137111693620684,
|
|
"num_tokens": 18429542.0,
|
|
"step": 10110
|
|
},
|
|
{
|
|
"entropy": 5.404547595977784,
|
|
"epoch": 8.380281690140846,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 8.350744786318168e-05,
|
|
"loss": 4.5325,
|
|
"mean_token_accuracy": 0.2559408277273178,
|
|
"num_tokens": 18439064.0,
|
|
"step": 10115
|
|
},
|
|
{
|
|
"entropy": 5.358681774139404,
|
|
"epoch": 8.384424192212096,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.33398614926097e-05,
|
|
"loss": 4.5608,
|
|
"mean_token_accuracy": 0.23884975016117097,
|
|
"num_tokens": 18449001.0,
|
|
"step": 10120
|
|
},
|
|
{
|
|
"entropy": 5.327129268646241,
|
|
"epoch": 8.388566694283346,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.317266172148145e-05,
|
|
"loss": 4.5226,
|
|
"mean_token_accuracy": 0.2458814799785614,
|
|
"num_tokens": 18458105.0,
|
|
"step": 10125
|
|
},
|
|
{
|
|
"entropy": 5.381231594085693,
|
|
"epoch": 8.392709196354598,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 8.300584888705709e-05,
|
|
"loss": 4.5588,
|
|
"mean_token_accuracy": 0.23882461339235306,
|
|
"num_tokens": 18466975.0,
|
|
"step": 10130
|
|
},
|
|
{
|
|
"entropy": 5.2864670753479,
|
|
"epoch": 8.396851698425849,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.283942332581644e-05,
|
|
"loss": 4.438,
|
|
"mean_token_accuracy": 0.2567633897066116,
|
|
"num_tokens": 18475543.0,
|
|
"step": 10135
|
|
},
|
|
{
|
|
"entropy": 5.276262044906616,
|
|
"epoch": 8.4009942004971,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 8.267338537345792e-05,
|
|
"loss": 4.4039,
|
|
"mean_token_accuracy": 0.2522984355688095,
|
|
"num_tokens": 18484399.0,
|
|
"step": 10140
|
|
},
|
|
{
|
|
"entropy": 5.304746198654175,
|
|
"epoch": 8.40513670256835,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.250773536489833e-05,
|
|
"loss": 4.5447,
|
|
"mean_token_accuracy": 0.2410188376903534,
|
|
"num_tokens": 18493168.0,
|
|
"step": 10145
|
|
},
|
|
{
|
|
"entropy": 5.269788455963135,
|
|
"epoch": 8.409279204639603,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 8.234247363427174e-05,
|
|
"loss": 4.5111,
|
|
"mean_token_accuracy": 0.24225541949272156,
|
|
"num_tokens": 18502624.0,
|
|
"step": 10150
|
|
},
|
|
{
|
|
"entropy": 5.3541748046875,
|
|
"epoch": 8.413421706710853,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 8.217760051492926e-05,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.24848205000162124,
|
|
"num_tokens": 18510990.0,
|
|
"step": 10155
|
|
},
|
|
{
|
|
"entropy": 5.322845458984375,
|
|
"epoch": 8.417564208782105,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 8.201311633943788e-05,
|
|
"loss": 4.4836,
|
|
"mean_token_accuracy": 0.24463153630495071,
|
|
"num_tokens": 18519490.0,
|
|
"step": 10160
|
|
},
|
|
{
|
|
"entropy": 5.365434360504151,
|
|
"epoch": 8.421706710853355,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 8.184902143958013e-05,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.2443913146853447,
|
|
"num_tokens": 18528827.0,
|
|
"step": 10165
|
|
},
|
|
{
|
|
"entropy": 5.291196727752686,
|
|
"epoch": 8.425849212924607,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 8.168531614635347e-05,
|
|
"loss": 4.5231,
|
|
"mean_token_accuracy": 0.24562112390995025,
|
|
"num_tokens": 18537592.0,
|
|
"step": 10170
|
|
},
|
|
{
|
|
"entropy": 5.388156938552856,
|
|
"epoch": 8.429991714995857,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 8.152200078996924e-05,
|
|
"loss": 4.605,
|
|
"mean_token_accuracy": 0.24461397528648376,
|
|
"num_tokens": 18547253.0,
|
|
"step": 10175
|
|
},
|
|
{
|
|
"entropy": 5.332802820205688,
|
|
"epoch": 8.434134217067108,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 8.135907569985248e-05,
|
|
"loss": 4.5478,
|
|
"mean_token_accuracy": 0.24092343896627427,
|
|
"num_tokens": 18556658.0,
|
|
"step": 10180
|
|
},
|
|
{
|
|
"entropy": 5.348485612869263,
|
|
"epoch": 8.43827671913836,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 8.119654120464077e-05,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.2419227108359337,
|
|
"num_tokens": 18565594.0,
|
|
"step": 10185
|
|
},
|
|
{
|
|
"entropy": 5.3653329372406,
|
|
"epoch": 8.44241922120961,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 8.103439763218411e-05,
|
|
"loss": 4.552,
|
|
"mean_token_accuracy": 0.24338310211896896,
|
|
"num_tokens": 18574033.0,
|
|
"step": 10190
|
|
},
|
|
{
|
|
"entropy": 5.350409984588623,
|
|
"epoch": 8.446561723280862,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 8.087264530954362e-05,
|
|
"loss": 4.5225,
|
|
"mean_token_accuracy": 0.247879821062088,
|
|
"num_tokens": 18583064.0,
|
|
"step": 10195
|
|
},
|
|
{
|
|
"entropy": 5.496421861648559,
|
|
"epoch": 8.450704225352112,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 8.071128456299159e-05,
|
|
"loss": 4.6144,
|
|
"mean_token_accuracy": 0.23647497296333314,
|
|
"num_tokens": 18591910.0,
|
|
"step": 10200
|
|
},
|
|
{
|
|
"entropy": 5.4357733726501465,
|
|
"epoch": 8.454846727423364,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 8.055031571801013e-05,
|
|
"loss": 4.5568,
|
|
"mean_token_accuracy": 0.24229709953069686,
|
|
"num_tokens": 18600880.0,
|
|
"step": 10205
|
|
},
|
|
{
|
|
"entropy": 5.4725946426391605,
|
|
"epoch": 8.458989229494614,
|
|
"grad_norm": 1.640625,
|
|
"learning_rate": 8.038973909929112e-05,
|
|
"loss": 4.7383,
|
|
"mean_token_accuracy": 0.22970105707645416,
|
|
"num_tokens": 18610407.0,
|
|
"step": 10210
|
|
},
|
|
{
|
|
"entropy": 5.363434314727783,
|
|
"epoch": 8.463131731565866,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 8.022955503073502e-05,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.24405353665351867,
|
|
"num_tokens": 18620166.0,
|
|
"step": 10215
|
|
},
|
|
{
|
|
"entropy": 5.350539255142212,
|
|
"epoch": 8.467274233637117,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 8.006976383545071e-05,
|
|
"loss": 4.4962,
|
|
"mean_token_accuracy": 0.24021266549825668,
|
|
"num_tokens": 18628851.0,
|
|
"step": 10220
|
|
},
|
|
{
|
|
"entropy": 5.345687580108643,
|
|
"epoch": 8.471416735708369,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.991036583575448e-05,
|
|
"loss": 4.5554,
|
|
"mean_token_accuracy": 0.2449299082159996,
|
|
"num_tokens": 18637921.0,
|
|
"step": 10225
|
|
},
|
|
{
|
|
"entropy": 5.381419897079468,
|
|
"epoch": 8.475559237779619,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.975136135316941e-05,
|
|
"loss": 4.4892,
|
|
"mean_token_accuracy": 0.24954739063978196,
|
|
"num_tokens": 18647291.0,
|
|
"step": 10230
|
|
},
|
|
{
|
|
"entropy": 5.310716581344605,
|
|
"epoch": 8.47970173985087,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 7.959275070842502e-05,
|
|
"loss": 4.4951,
|
|
"mean_token_accuracy": 0.24814511686563492,
|
|
"num_tokens": 18656252.0,
|
|
"step": 10235
|
|
},
|
|
{
|
|
"entropy": 5.304321670532227,
|
|
"epoch": 8.483844241922121,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.943453422145626e-05,
|
|
"loss": 4.5108,
|
|
"mean_token_accuracy": 0.2522063091397285,
|
|
"num_tokens": 18666199.0,
|
|
"step": 10240
|
|
},
|
|
{
|
|
"entropy": 5.417251300811768,
|
|
"epoch": 8.487986743993371,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.927671221140317e-05,
|
|
"loss": 4.5936,
|
|
"mean_token_accuracy": 0.2424902141094208,
|
|
"num_tokens": 18675573.0,
|
|
"step": 10245
|
|
},
|
|
{
|
|
"entropy": 5.406660795211792,
|
|
"epoch": 8.492129246064623,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.911928499660986e-05,
|
|
"loss": 4.5358,
|
|
"mean_token_accuracy": 0.24683964997529984,
|
|
"num_tokens": 18684627.0,
|
|
"step": 10250
|
|
},
|
|
{
|
|
"entropy": 5.409447717666626,
|
|
"epoch": 8.496271748135873,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.896225289462426e-05,
|
|
"loss": 4.5474,
|
|
"mean_token_accuracy": 0.2375546544790268,
|
|
"num_tokens": 18694287.0,
|
|
"step": 10255
|
|
},
|
|
{
|
|
"entropy": 5.359805679321289,
|
|
"epoch": 8.500414250207125,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.880561622219735e-05,
|
|
"loss": 4.5436,
|
|
"mean_token_accuracy": 0.23827444314956664,
|
|
"num_tokens": 18704014.0,
|
|
"step": 10260
|
|
},
|
|
{
|
|
"entropy": 5.362731409072876,
|
|
"epoch": 8.504556752278376,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.864937529528232e-05,
|
|
"loss": 4.5434,
|
|
"mean_token_accuracy": 0.24462969303131105,
|
|
"num_tokens": 18713030.0,
|
|
"step": 10265
|
|
},
|
|
{
|
|
"entropy": 5.3813958168029785,
|
|
"epoch": 8.508699254349628,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.849353042903428e-05,
|
|
"loss": 4.5618,
|
|
"mean_token_accuracy": 0.24866679310798645,
|
|
"num_tokens": 18721911.0,
|
|
"step": 10270
|
|
},
|
|
{
|
|
"entropy": 5.359049320220947,
|
|
"epoch": 8.512841756420878,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.833808193780934e-05,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.25346015244722364,
|
|
"num_tokens": 18730688.0,
|
|
"step": 10275
|
|
},
|
|
{
|
|
"entropy": 5.4061986923217775,
|
|
"epoch": 8.51698425849213,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.818303013516401e-05,
|
|
"loss": 4.6028,
|
|
"mean_token_accuracy": 0.24053773432970046,
|
|
"num_tokens": 18740214.0,
|
|
"step": 10280
|
|
},
|
|
{
|
|
"entropy": 5.341454648971558,
|
|
"epoch": 8.52112676056338,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 7.802837533385482e-05,
|
|
"loss": 4.5479,
|
|
"mean_token_accuracy": 0.24133697897195816,
|
|
"num_tokens": 18748837.0,
|
|
"step": 10285
|
|
},
|
|
{
|
|
"entropy": 5.32238450050354,
|
|
"epoch": 8.525269262634632,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 7.787411784583733e-05,
|
|
"loss": 4.4173,
|
|
"mean_token_accuracy": 0.2556320831179619,
|
|
"num_tokens": 18757482.0,
|
|
"step": 10290
|
|
},
|
|
{
|
|
"entropy": 5.269917011260986,
|
|
"epoch": 8.529411764705882,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 7.772025798226582e-05,
|
|
"loss": 4.5013,
|
|
"mean_token_accuracy": 0.24335521310567856,
|
|
"num_tokens": 18766326.0,
|
|
"step": 10295
|
|
},
|
|
{
|
|
"entropy": 5.465238904953003,
|
|
"epoch": 8.533554266777134,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.756679605349241e-05,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.2384398475289345,
|
|
"num_tokens": 18774287.0,
|
|
"step": 10300
|
|
},
|
|
{
|
|
"entropy": 5.386168575286865,
|
|
"epoch": 8.537696768848384,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.741373236906658e-05,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.24043544828891755,
|
|
"num_tokens": 18785172.0,
|
|
"step": 10305
|
|
},
|
|
{
|
|
"entropy": 5.330443286895752,
|
|
"epoch": 8.541839270919635,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 7.726106723773452e-05,
|
|
"loss": 4.5831,
|
|
"mean_token_accuracy": 0.2403014898300171,
|
|
"num_tokens": 18794294.0,
|
|
"step": 10310
|
|
},
|
|
{
|
|
"entropy": 5.391012477874756,
|
|
"epoch": 8.545981772990887,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 7.710880096743845e-05,
|
|
"loss": 4.5878,
|
|
"mean_token_accuracy": 0.24422425776720047,
|
|
"num_tokens": 18803108.0,
|
|
"step": 10315
|
|
},
|
|
{
|
|
"entropy": 5.362746524810791,
|
|
"epoch": 8.550124275062137,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 7.695693386531612e-05,
|
|
"loss": 4.5312,
|
|
"mean_token_accuracy": 0.24395540058612825,
|
|
"num_tokens": 18811215.0,
|
|
"step": 10320
|
|
},
|
|
{
|
|
"entropy": 5.385398864746094,
|
|
"epoch": 8.554266777133389,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 7.680546623770001e-05,
|
|
"loss": 4.6335,
|
|
"mean_token_accuracy": 0.22869537472724916,
|
|
"num_tokens": 18820796.0,
|
|
"step": 10325
|
|
},
|
|
{
|
|
"entropy": 5.496550893783569,
|
|
"epoch": 8.55840927920464,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.665439839011701e-05,
|
|
"loss": 4.6727,
|
|
"mean_token_accuracy": 0.22541955411434172,
|
|
"num_tokens": 18830673.0,
|
|
"step": 10330
|
|
},
|
|
{
|
|
"entropy": 5.357355833053589,
|
|
"epoch": 8.562551781275891,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 7.650373062728735e-05,
|
|
"loss": 4.5467,
|
|
"mean_token_accuracy": 0.249116912484169,
|
|
"num_tokens": 18839898.0,
|
|
"step": 10335
|
|
},
|
|
{
|
|
"entropy": 5.379422044754028,
|
|
"epoch": 8.566694283347141,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.635346325312437e-05,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.24783595502376557,
|
|
"num_tokens": 18848380.0,
|
|
"step": 10340
|
|
},
|
|
{
|
|
"entropy": 5.3442771434783936,
|
|
"epoch": 8.570836785418393,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.62035965707339e-05,
|
|
"loss": 4.4978,
|
|
"mean_token_accuracy": 0.24356687664985657,
|
|
"num_tokens": 18857157.0,
|
|
"step": 10345
|
|
},
|
|
{
|
|
"entropy": 5.385423374176026,
|
|
"epoch": 8.574979287489644,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 7.605413088241325e-05,
|
|
"loss": 4.553,
|
|
"mean_token_accuracy": 0.2445417121052742,
|
|
"num_tokens": 18866544.0,
|
|
"step": 10350
|
|
},
|
|
{
|
|
"entropy": 5.380229806900024,
|
|
"epoch": 8.579121789560896,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 7.59050664896512e-05,
|
|
"loss": 4.5866,
|
|
"mean_token_accuracy": 0.2381325200200081,
|
|
"num_tokens": 18876052.0,
|
|
"step": 10355
|
|
},
|
|
{
|
|
"entropy": 5.34817910194397,
|
|
"epoch": 8.583264291632146,
|
|
"grad_norm": 1.6953125,
|
|
"learning_rate": 7.575640369312684e-05,
|
|
"loss": 4.4755,
|
|
"mean_token_accuracy": 0.2476791962981224,
|
|
"num_tokens": 18885141.0,
|
|
"step": 10360
|
|
},
|
|
{
|
|
"entropy": 5.3416296482086185,
|
|
"epoch": 8.587406793703398,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 7.560814279270928e-05,
|
|
"loss": 4.4643,
|
|
"mean_token_accuracy": 0.25731768012046813,
|
|
"num_tokens": 18893108.0,
|
|
"step": 10365
|
|
},
|
|
{
|
|
"entropy": 5.375852775573731,
|
|
"epoch": 8.591549295774648,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.5460284087457e-05,
|
|
"loss": 4.5517,
|
|
"mean_token_accuracy": 0.24867779314517974,
|
|
"num_tokens": 18901436.0,
|
|
"step": 10370
|
|
},
|
|
{
|
|
"entropy": 5.364243030548096,
|
|
"epoch": 8.595691797845898,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.53128278756171e-05,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.2513952672481537,
|
|
"num_tokens": 18910057.0,
|
|
"step": 10375
|
|
},
|
|
{
|
|
"entropy": 5.253724813461304,
|
|
"epoch": 8.59983429991715,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.516577445462493e-05,
|
|
"loss": 4.4006,
|
|
"mean_token_accuracy": 0.2550272658467293,
|
|
"num_tokens": 18918270.0,
|
|
"step": 10380
|
|
},
|
|
{
|
|
"entropy": 5.40306544303894,
|
|
"epoch": 8.6039768019884,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.501912412110331e-05,
|
|
"loss": 4.5994,
|
|
"mean_token_accuracy": 0.23827319145202636,
|
|
"num_tokens": 18928202.0,
|
|
"step": 10385
|
|
},
|
|
{
|
|
"entropy": 5.328025054931641,
|
|
"epoch": 8.608119304059652,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 7.487287717086193e-05,
|
|
"loss": 4.5643,
|
|
"mean_token_accuracy": 0.2457289904356003,
|
|
"num_tokens": 18937837.0,
|
|
"step": 10390
|
|
},
|
|
{
|
|
"entropy": 5.377071189880371,
|
|
"epoch": 8.612261806130903,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 7.472703389889695e-05,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.24841716438531875,
|
|
"num_tokens": 18946391.0,
|
|
"step": 10395
|
|
},
|
|
{
|
|
"entropy": 5.374834775924683,
|
|
"epoch": 8.616404308202155,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.458159459939007e-05,
|
|
"loss": 4.5379,
|
|
"mean_token_accuracy": 0.2469432160258293,
|
|
"num_tokens": 18955269.0,
|
|
"step": 10400
|
|
},
|
|
{
|
|
"entropy": 5.367851591110229,
|
|
"epoch": 8.620546810273405,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.443655956570842e-05,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.2544187054038048,
|
|
"num_tokens": 18964030.0,
|
|
"step": 10405
|
|
},
|
|
{
|
|
"entropy": 5.335626125335693,
|
|
"epoch": 8.624689312344657,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.429192909040339e-05,
|
|
"loss": 4.5063,
|
|
"mean_token_accuracy": 0.24623495042324067,
|
|
"num_tokens": 18973690.0,
|
|
"step": 10410
|
|
},
|
|
{
|
|
"entropy": 5.360391235351562,
|
|
"epoch": 8.628831814415907,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 7.414770346521043e-05,
|
|
"loss": 4.4938,
|
|
"mean_token_accuracy": 0.24970951676368713,
|
|
"num_tokens": 18981339.0,
|
|
"step": 10415
|
|
},
|
|
{
|
|
"entropy": 5.371539783477783,
|
|
"epoch": 8.632974316487159,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 7.400388298104851e-05,
|
|
"loss": 4.5185,
|
|
"mean_token_accuracy": 0.2384280428290367,
|
|
"num_tokens": 18990141.0,
|
|
"step": 10420
|
|
},
|
|
{
|
|
"entropy": 5.300366353988648,
|
|
"epoch": 8.63711681855841,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.386046792801911e-05,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.254979345202446,
|
|
"num_tokens": 18999217.0,
|
|
"step": 10425
|
|
},
|
|
{
|
|
"entropy": 5.375014734268189,
|
|
"epoch": 8.64125932062966,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 7.371745859540622e-05,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.24780423641204835,
|
|
"num_tokens": 19008554.0,
|
|
"step": 10430
|
|
},
|
|
{
|
|
"entropy": 5.320042133331299,
|
|
"epoch": 8.645401822700912,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 7.357485527167522e-05,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.2506758078932762,
|
|
"num_tokens": 19018159.0,
|
|
"step": 10435
|
|
},
|
|
{
|
|
"entropy": 5.352187013626098,
|
|
"epoch": 8.649544324772162,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 7.343265824447254e-05,
|
|
"loss": 4.5007,
|
|
"mean_token_accuracy": 0.24615297913551332,
|
|
"num_tokens": 19026985.0,
|
|
"step": 10440
|
|
},
|
|
{
|
|
"entropy": 5.380755519866943,
|
|
"epoch": 8.653686826843414,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 7.329086780062522e-05,
|
|
"loss": 4.5632,
|
|
"mean_token_accuracy": 0.23772212117910385,
|
|
"num_tokens": 19036745.0,
|
|
"step": 10445
|
|
},
|
|
{
|
|
"entropy": 5.340994548797608,
|
|
"epoch": 8.657829328914664,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 7.314948422613998e-05,
|
|
"loss": 4.5067,
|
|
"mean_token_accuracy": 0.25171423703432083,
|
|
"num_tokens": 19045200.0,
|
|
"step": 10450
|
|
},
|
|
{
|
|
"entropy": 5.390359115600586,
|
|
"epoch": 8.661971830985916,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 7.30085078062031e-05,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.25147320330142975,
|
|
"num_tokens": 19054102.0,
|
|
"step": 10455
|
|
},
|
|
{
|
|
"entropy": 5.369068050384522,
|
|
"epoch": 8.666114333057166,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 7.286793882517922e-05,
|
|
"loss": 4.6061,
|
|
"mean_token_accuracy": 0.23955277651548385,
|
|
"num_tokens": 19062895.0,
|
|
"step": 10460
|
|
},
|
|
{
|
|
"entropy": 5.303682422637939,
|
|
"epoch": 8.670256835128418,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.272777756661152e-05,
|
|
"loss": 4.4622,
|
|
"mean_token_accuracy": 0.2545920416712761,
|
|
"num_tokens": 19071523.0,
|
|
"step": 10465
|
|
},
|
|
{
|
|
"entropy": 5.3231957912445065,
|
|
"epoch": 8.674399337199668,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.258802431322047e-05,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.24183994382619858,
|
|
"num_tokens": 19080765.0,
|
|
"step": 10470
|
|
},
|
|
{
|
|
"entropy": 5.400327968597412,
|
|
"epoch": 8.67854183927092,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.244867934690364e-05,
|
|
"loss": 4.5673,
|
|
"mean_token_accuracy": 0.23524621427059172,
|
|
"num_tokens": 19089871.0,
|
|
"step": 10475
|
|
},
|
|
{
|
|
"entropy": 5.321598529815674,
|
|
"epoch": 8.68268434134217,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.230974294873513e-05,
|
|
"loss": 4.4912,
|
|
"mean_token_accuracy": 0.24065618366003036,
|
|
"num_tokens": 19098928.0,
|
|
"step": 10480
|
|
},
|
|
{
|
|
"entropy": 5.394476652145386,
|
|
"epoch": 8.68682684341342,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.217121539896476e-05,
|
|
"loss": 4.5966,
|
|
"mean_token_accuracy": 0.23767090886831282,
|
|
"num_tokens": 19107795.0,
|
|
"step": 10485
|
|
},
|
|
{
|
|
"entropy": 5.475055837631226,
|
|
"epoch": 8.690969345484673,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 7.203309697701784e-05,
|
|
"loss": 4.6272,
|
|
"mean_token_accuracy": 0.23176246881484985,
|
|
"num_tokens": 19117060.0,
|
|
"step": 10490
|
|
},
|
|
{
|
|
"entropy": 5.364302015304565,
|
|
"epoch": 8.695111847555923,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.189538796149424e-05,
|
|
"loss": 4.5496,
|
|
"mean_token_accuracy": 0.23837143927812576,
|
|
"num_tokens": 19126876.0,
|
|
"step": 10495
|
|
},
|
|
{
|
|
"entropy": 5.465447473526001,
|
|
"epoch": 8.699254349627175,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.175808863016806e-05,
|
|
"loss": 4.6228,
|
|
"mean_token_accuracy": 0.23851541578769683,
|
|
"num_tokens": 19136888.0,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"epoch": 8.699254349627175,
|
|
"eval_entropy": 5.21480117118689,
|
|
"eval_loss": 5.71254825592041,
|
|
"eval_mean_token_accuracy": 0.17057680481596033,
|
|
"eval_num_tokens": 19136888.0,
|
|
"eval_runtime": 2.3153,
|
|
"eval_samples_per_second": 1618.35,
|
|
"eval_steps_per_second": 202.564,
|
|
"step": 10500
|
|
},
|
|
{
|
|
"entropy": 5.390359258651733,
|
|
"epoch": 8.703396851698425,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.162119925998714e-05,
|
|
"loss": 4.5882,
|
|
"mean_token_accuracy": 0.23602674752473832,
|
|
"num_tokens": 19146727.0,
|
|
"step": 10505
|
|
},
|
|
{
|
|
"entropy": 5.342617988586426,
|
|
"epoch": 8.707539353769677,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 7.148472012707225e-05,
|
|
"loss": 4.5118,
|
|
"mean_token_accuracy": 0.24703780710697174,
|
|
"num_tokens": 19157322.0,
|
|
"step": 10510
|
|
},
|
|
{
|
|
"entropy": 5.302326202392578,
|
|
"epoch": 8.711681855840927,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 7.134865150671676e-05,
|
|
"loss": 4.5151,
|
|
"mean_token_accuracy": 0.2465771481394768,
|
|
"num_tokens": 19166302.0,
|
|
"step": 10515
|
|
},
|
|
{
|
|
"entropy": 5.410491800308227,
|
|
"epoch": 8.71582435791218,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 7.121299367338593e-05,
|
|
"loss": 4.5543,
|
|
"mean_token_accuracy": 0.24432154148817062,
|
|
"num_tokens": 19174883.0,
|
|
"step": 10520
|
|
},
|
|
{
|
|
"entropy": 5.34002652168274,
|
|
"epoch": 8.71996685998343,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 7.107774690071635e-05,
|
|
"loss": 4.4699,
|
|
"mean_token_accuracy": 0.2471254974603653,
|
|
"num_tokens": 19184410.0,
|
|
"step": 10525
|
|
},
|
|
{
|
|
"entropy": 5.392217397689819,
|
|
"epoch": 8.724109362054682,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.094291146151568e-05,
|
|
"loss": 4.5725,
|
|
"mean_token_accuracy": 0.2467815101146698,
|
|
"num_tokens": 19193559.0,
|
|
"step": 10530
|
|
},
|
|
{
|
|
"entropy": 5.43098816871643,
|
|
"epoch": 8.728251864125932,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 7.080848762776159e-05,
|
|
"loss": 4.6006,
|
|
"mean_token_accuracy": 0.24730242937803268,
|
|
"num_tokens": 19202520.0,
|
|
"step": 10535
|
|
},
|
|
{
|
|
"entropy": 5.315717601776123,
|
|
"epoch": 8.732394366197184,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.067447567060178e-05,
|
|
"loss": 4.5154,
|
|
"mean_token_accuracy": 0.2426963895559311,
|
|
"num_tokens": 19212357.0,
|
|
"step": 10540
|
|
},
|
|
{
|
|
"entropy": 5.400158548355103,
|
|
"epoch": 8.736536868268434,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.054087586035295e-05,
|
|
"loss": 4.5709,
|
|
"mean_token_accuracy": 0.23718283623456954,
|
|
"num_tokens": 19222069.0,
|
|
"step": 10545
|
|
},
|
|
{
|
|
"entropy": 5.428431701660156,
|
|
"epoch": 8.740679370339684,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.040768846650046e-05,
|
|
"loss": 4.6196,
|
|
"mean_token_accuracy": 0.23535627573728563,
|
|
"num_tokens": 19232274.0,
|
|
"step": 10550
|
|
},
|
|
{
|
|
"entropy": 5.409516859054565,
|
|
"epoch": 8.744821872410936,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 7.027491375769795e-05,
|
|
"loss": 4.6093,
|
|
"mean_token_accuracy": 0.24138641804456712,
|
|
"num_tokens": 19241877.0,
|
|
"step": 10555
|
|
},
|
|
{
|
|
"entropy": 5.361130285263061,
|
|
"epoch": 8.748964374482187,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 7.014255200176643e-05,
|
|
"loss": 4.4907,
|
|
"mean_token_accuracy": 0.24837044924497603,
|
|
"num_tokens": 19250229.0,
|
|
"step": 10560
|
|
},
|
|
{
|
|
"entropy": 5.3312201499938965,
|
|
"epoch": 8.753106876553439,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 7.001060346569408e-05,
|
|
"loss": 4.5298,
|
|
"mean_token_accuracy": 0.2423752501606941,
|
|
"num_tokens": 19259061.0,
|
|
"step": 10565
|
|
},
|
|
{
|
|
"entropy": 5.4276533126831055,
|
|
"epoch": 8.757249378624689,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 6.987906841563552e-05,
|
|
"loss": 4.5993,
|
|
"mean_token_accuracy": 0.23747799396514893,
|
|
"num_tokens": 19268262.0,
|
|
"step": 10570
|
|
},
|
|
{
|
|
"entropy": 5.344149923324585,
|
|
"epoch": 8.76139188069594,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.974794711691125e-05,
|
|
"loss": 4.5568,
|
|
"mean_token_accuracy": 0.24659899324178697,
|
|
"num_tokens": 19276444.0,
|
|
"step": 10575
|
|
},
|
|
{
|
|
"entropy": 5.386319398880005,
|
|
"epoch": 8.765534382767191,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.961723983400733e-05,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.24001515060663223,
|
|
"num_tokens": 19286384.0,
|
|
"step": 10580
|
|
},
|
|
{
|
|
"entropy": 5.324071407318115,
|
|
"epoch": 8.769676884838443,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 6.948694683057456e-05,
|
|
"loss": 4.5487,
|
|
"mean_token_accuracy": 0.24007519334554672,
|
|
"num_tokens": 19295251.0,
|
|
"step": 10585
|
|
},
|
|
{
|
|
"entropy": 5.377282762527466,
|
|
"epoch": 8.773819386909693,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.935706836942826e-05,
|
|
"loss": 4.5436,
|
|
"mean_token_accuracy": 0.24331608414649963,
|
|
"num_tokens": 19304288.0,
|
|
"step": 10590
|
|
},
|
|
{
|
|
"entropy": 5.410712337493896,
|
|
"epoch": 8.777961888980945,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.922760471254738e-05,
|
|
"loss": 4.5508,
|
|
"mean_token_accuracy": 0.2444557249546051,
|
|
"num_tokens": 19312269.0,
|
|
"step": 10595
|
|
},
|
|
{
|
|
"entropy": 5.267954015731812,
|
|
"epoch": 8.782104391052195,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.909855612107437e-05,
|
|
"loss": 4.4501,
|
|
"mean_token_accuracy": 0.25947941541671754,
|
|
"num_tokens": 19320856.0,
|
|
"step": 10600
|
|
},
|
|
{
|
|
"entropy": 5.328185272216797,
|
|
"epoch": 8.786246893123447,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 6.896992285531424e-05,
|
|
"loss": 4.5362,
|
|
"mean_token_accuracy": 0.24958906769752504,
|
|
"num_tokens": 19329427.0,
|
|
"step": 10605
|
|
},
|
|
{
|
|
"entropy": 5.294426393508911,
|
|
"epoch": 8.790389395194698,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.884170517473444e-05,
|
|
"loss": 4.5457,
|
|
"mean_token_accuracy": 0.24920751303434371,
|
|
"num_tokens": 19337772.0,
|
|
"step": 10610
|
|
},
|
|
{
|
|
"entropy": 5.437910079956055,
|
|
"epoch": 8.794531897265948,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.871390333796398e-05,
|
|
"loss": 4.6031,
|
|
"mean_token_accuracy": 0.2478273943066597,
|
|
"num_tokens": 19346693.0,
|
|
"step": 10615
|
|
},
|
|
{
|
|
"entropy": 5.363340139389038,
|
|
"epoch": 8.7986743993372,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.85865176027931e-05,
|
|
"loss": 4.5265,
|
|
"mean_token_accuracy": 0.23944059163331985,
|
|
"num_tokens": 19355606.0,
|
|
"step": 10620
|
|
},
|
|
{
|
|
"entropy": 5.347836256027222,
|
|
"epoch": 8.80281690140845,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.845954822617284e-05,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2429955780506134,
|
|
"num_tokens": 19365552.0,
|
|
"step": 10625
|
|
},
|
|
{
|
|
"entropy": 5.3769361019134525,
|
|
"epoch": 8.806959403479702,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 6.833299546421423e-05,
|
|
"loss": 4.5965,
|
|
"mean_token_accuracy": 0.2329386442899704,
|
|
"num_tokens": 19374869.0,
|
|
"step": 10630
|
|
},
|
|
{
|
|
"entropy": 5.377849960327149,
|
|
"epoch": 8.811101905550952,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.820685957218808e-05,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.2411442592740059,
|
|
"num_tokens": 19384609.0,
|
|
"step": 10635
|
|
},
|
|
{
|
|
"entropy": 5.324924039840698,
|
|
"epoch": 8.815244407622204,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.80811408045242e-05,
|
|
"loss": 4.5014,
|
|
"mean_token_accuracy": 0.2462746098637581,
|
|
"num_tokens": 19392618.0,
|
|
"step": 10640
|
|
},
|
|
{
|
|
"entropy": 5.514871215820312,
|
|
"epoch": 8.819386909693455,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 6.795583941481113e-05,
|
|
"loss": 4.6185,
|
|
"mean_token_accuracy": 0.2343808799982071,
|
|
"num_tokens": 19402341.0,
|
|
"step": 10645
|
|
},
|
|
{
|
|
"entropy": 5.388099288940429,
|
|
"epoch": 8.823529411764707,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.783095565579546e-05,
|
|
"loss": 4.5619,
|
|
"mean_token_accuracy": 0.24175271540880203,
|
|
"num_tokens": 19411834.0,
|
|
"step": 10650
|
|
},
|
|
{
|
|
"entropy": 5.324990940093994,
|
|
"epoch": 8.827671913835957,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 6.77064897793814e-05,
|
|
"loss": 4.4777,
|
|
"mean_token_accuracy": 0.2530103474855423,
|
|
"num_tokens": 19420820.0,
|
|
"step": 10655
|
|
},
|
|
{
|
|
"entropy": 5.400853443145752,
|
|
"epoch": 8.831814415907209,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.758244203663015e-05,
|
|
"loss": 4.6282,
|
|
"mean_token_accuracy": 0.22977739423513413,
|
|
"num_tokens": 19430321.0,
|
|
"step": 10660
|
|
},
|
|
{
|
|
"entropy": 5.315697050094604,
|
|
"epoch": 8.835956917978459,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 6.745881267775967e-05,
|
|
"loss": 4.5285,
|
|
"mean_token_accuracy": 0.24551725387573242,
|
|
"num_tokens": 19439134.0,
|
|
"step": 10665
|
|
},
|
|
{
|
|
"entropy": 5.3531492233276365,
|
|
"epoch": 8.840099420049711,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.733560195214384e-05,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.25044656097888945,
|
|
"num_tokens": 19448503.0,
|
|
"step": 10670
|
|
},
|
|
{
|
|
"entropy": 5.41177339553833,
|
|
"epoch": 8.844241922120961,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.721281010831209e-05,
|
|
"loss": 4.6362,
|
|
"mean_token_accuracy": 0.23885320872068405,
|
|
"num_tokens": 19458423.0,
|
|
"step": 10675
|
|
},
|
|
{
|
|
"entropy": 5.3208842277526855,
|
|
"epoch": 8.848384424192211,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 6.709043739394909e-05,
|
|
"loss": 4.5148,
|
|
"mean_token_accuracy": 0.24247035831212999,
|
|
"num_tokens": 19467346.0,
|
|
"step": 10680
|
|
},
|
|
{
|
|
"entropy": 5.36693115234375,
|
|
"epoch": 8.852526926263463,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.696848405589389e-05,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.24232504963874818,
|
|
"num_tokens": 19476659.0,
|
|
"step": 10685
|
|
},
|
|
{
|
|
"entropy": 5.337271308898925,
|
|
"epoch": 8.856669428334714,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.68469503401398e-05,
|
|
"loss": 4.4941,
|
|
"mean_token_accuracy": 0.2502406597137451,
|
|
"num_tokens": 19486036.0,
|
|
"step": 10690
|
|
},
|
|
{
|
|
"entropy": 5.3446776390075685,
|
|
"epoch": 8.860811930405966,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.672583649183346e-05,
|
|
"loss": 4.5483,
|
|
"mean_token_accuracy": 0.2421737089753151,
|
|
"num_tokens": 19494964.0,
|
|
"step": 10695
|
|
},
|
|
{
|
|
"entropy": 5.3169715881347654,
|
|
"epoch": 8.864954432477216,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.66051427552749e-05,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.24027561843395234,
|
|
"num_tokens": 19503293.0,
|
|
"step": 10700
|
|
},
|
|
{
|
|
"entropy": 5.325210094451904,
|
|
"epoch": 8.869096934548468,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.648486937391651e-05,
|
|
"loss": 4.5152,
|
|
"mean_token_accuracy": 0.24711860418319703,
|
|
"num_tokens": 19512286.0,
|
|
"step": 10705
|
|
},
|
|
{
|
|
"entropy": 5.493726825714111,
|
|
"epoch": 8.873239436619718,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.636501659036278e-05,
|
|
"loss": 4.6752,
|
|
"mean_token_accuracy": 0.23742722123861312,
|
|
"num_tokens": 19522244.0,
|
|
"step": 10710
|
|
},
|
|
{
|
|
"entropy": 5.439410209655762,
|
|
"epoch": 8.87738193869097,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 6.624558464636999e-05,
|
|
"loss": 4.6094,
|
|
"mean_token_accuracy": 0.23802047371864318,
|
|
"num_tokens": 19531811.0,
|
|
"step": 10715
|
|
},
|
|
{
|
|
"entropy": 5.404070043563843,
|
|
"epoch": 8.88152444076222,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 6.612657378284528e-05,
|
|
"loss": 4.6345,
|
|
"mean_token_accuracy": 0.23221200257539748,
|
|
"num_tokens": 19541569.0,
|
|
"step": 10720
|
|
},
|
|
{
|
|
"entropy": 5.343942928314209,
|
|
"epoch": 8.885666942833472,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.600798423984671e-05,
|
|
"loss": 4.5305,
|
|
"mean_token_accuracy": 0.24478141516447066,
|
|
"num_tokens": 19549904.0,
|
|
"step": 10725
|
|
},
|
|
{
|
|
"entropy": 5.321377515792847,
|
|
"epoch": 8.889809444904722,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.588981625658227e-05,
|
|
"loss": 4.485,
|
|
"mean_token_accuracy": 0.24588562846183776,
|
|
"num_tokens": 19558804.0,
|
|
"step": 10730
|
|
},
|
|
{
|
|
"entropy": 5.362775087356567,
|
|
"epoch": 8.893951946975973,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 6.577207007140969e-05,
|
|
"loss": 4.4909,
|
|
"mean_token_accuracy": 0.24923284202814103,
|
|
"num_tokens": 19567060.0,
|
|
"step": 10735
|
|
},
|
|
{
|
|
"entropy": 5.3493311405181885,
|
|
"epoch": 8.898094449047225,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 6.565474592183594e-05,
|
|
"loss": 4.5797,
|
|
"mean_token_accuracy": 0.237199804186821,
|
|
"num_tokens": 19576813.0,
|
|
"step": 10740
|
|
},
|
|
{
|
|
"entropy": 5.310680627822876,
|
|
"epoch": 8.902236951118475,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 6.553784404451656e-05,
|
|
"loss": 4.5047,
|
|
"mean_token_accuracy": 0.24972727298736572,
|
|
"num_tokens": 19585551.0,
|
|
"step": 10745
|
|
},
|
|
{
|
|
"entropy": 5.359276580810547,
|
|
"epoch": 8.906379453189727,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.542136467525555e-05,
|
|
"loss": 4.5526,
|
|
"mean_token_accuracy": 0.24442278891801833,
|
|
"num_tokens": 19595085.0,
|
|
"step": 10750
|
|
},
|
|
{
|
|
"entropy": 5.375267505645752,
|
|
"epoch": 8.910521955260977,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 6.530530804900441e-05,
|
|
"loss": 4.5061,
|
|
"mean_token_accuracy": 0.24973611533641815,
|
|
"num_tokens": 19603260.0,
|
|
"step": 10755
|
|
},
|
|
{
|
|
"entropy": 5.398684072494507,
|
|
"epoch": 8.91466445733223,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.518967439986209e-05,
|
|
"loss": 4.58,
|
|
"mean_token_accuracy": 0.24211370944976807,
|
|
"num_tokens": 19611608.0,
|
|
"step": 10760
|
|
},
|
|
{
|
|
"entropy": 5.351131391525269,
|
|
"epoch": 8.91880695940348,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.507446396107429e-05,
|
|
"loss": 4.4666,
|
|
"mean_token_accuracy": 0.24617619514465333,
|
|
"num_tokens": 19620214.0,
|
|
"step": 10765
|
|
},
|
|
{
|
|
"entropy": 5.369394397735595,
|
|
"epoch": 8.922949461474731,
|
|
"grad_norm": 1.7109375,
|
|
"learning_rate": 6.495967696503303e-05,
|
|
"loss": 4.5377,
|
|
"mean_token_accuracy": 0.2491861954331398,
|
|
"num_tokens": 19629227.0,
|
|
"step": 10770
|
|
},
|
|
{
|
|
"entropy": 5.4199357509613035,
|
|
"epoch": 8.927091963545982,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.484531364327629e-05,
|
|
"loss": 4.5787,
|
|
"mean_token_accuracy": 0.24244130551815032,
|
|
"num_tokens": 19638348.0,
|
|
"step": 10775
|
|
},
|
|
{
|
|
"entropy": 5.335587120056152,
|
|
"epoch": 8.931234465617234,
|
|
"grad_norm": 1.7734375,
|
|
"learning_rate": 6.473137422648728e-05,
|
|
"loss": 4.4574,
|
|
"mean_token_accuracy": 0.25719529390335083,
|
|
"num_tokens": 19646480.0,
|
|
"step": 10780
|
|
},
|
|
{
|
|
"entropy": 5.382263565063477,
|
|
"epoch": 8.935376967688484,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.461785894449434e-05,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.24143922477960586,
|
|
"num_tokens": 19656188.0,
|
|
"step": 10785
|
|
},
|
|
{
|
|
"entropy": 5.306941556930542,
|
|
"epoch": 8.939519469759734,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.45047680262702e-05,
|
|
"loss": 4.5702,
|
|
"mean_token_accuracy": 0.23687696009874343,
|
|
"num_tokens": 19664849.0,
|
|
"step": 10790
|
|
},
|
|
{
|
|
"entropy": 5.387145853042602,
|
|
"epoch": 8.943661971830986,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.439210169993153e-05,
|
|
"loss": 4.5347,
|
|
"mean_token_accuracy": 0.24652182161808014,
|
|
"num_tokens": 19675104.0,
|
|
"step": 10795
|
|
},
|
|
{
|
|
"entropy": 5.3526740074157715,
|
|
"epoch": 8.947804473902236,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.427986019273873e-05,
|
|
"loss": 4.5651,
|
|
"mean_token_accuracy": 0.23626333326101304,
|
|
"num_tokens": 19685009.0,
|
|
"step": 10800
|
|
},
|
|
{
|
|
"entropy": 5.362779045104981,
|
|
"epoch": 8.951946975973488,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 6.416804373109507e-05,
|
|
"loss": 4.5731,
|
|
"mean_token_accuracy": 0.24072375446557998,
|
|
"num_tokens": 19694190.0,
|
|
"step": 10805
|
|
},
|
|
{
|
|
"entropy": 5.311274814605713,
|
|
"epoch": 8.956089478044738,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.405665254054666e-05,
|
|
"loss": 4.5546,
|
|
"mean_token_accuracy": 0.23343597501516342,
|
|
"num_tokens": 19703571.0,
|
|
"step": 10810
|
|
},
|
|
{
|
|
"entropy": 5.372973108291626,
|
|
"epoch": 8.96023198011599,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.394568684578165e-05,
|
|
"loss": 4.5211,
|
|
"mean_token_accuracy": 0.24804731458425522,
|
|
"num_tokens": 19713365.0,
|
|
"step": 10815
|
|
},
|
|
{
|
|
"entropy": 5.466772079467773,
|
|
"epoch": 8.96437448218724,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 6.383514687063e-05,
|
|
"loss": 4.6538,
|
|
"mean_token_accuracy": 0.2411112368106842,
|
|
"num_tokens": 19722535.0,
|
|
"step": 10820
|
|
},
|
|
{
|
|
"entropy": 5.273637342453003,
|
|
"epoch": 8.968516984258493,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 6.372503283806291e-05,
|
|
"loss": 4.4776,
|
|
"mean_token_accuracy": 0.25824333876371386,
|
|
"num_tokens": 19731563.0,
|
|
"step": 10825
|
|
},
|
|
{
|
|
"entropy": 5.384742021560669,
|
|
"epoch": 8.972659486329743,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.36153449701924e-05,
|
|
"loss": 4.6188,
|
|
"mean_token_accuracy": 0.24186867326498032,
|
|
"num_tokens": 19741093.0,
|
|
"step": 10830
|
|
},
|
|
{
|
|
"entropy": 5.377748298645019,
|
|
"epoch": 8.976801988400995,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.350608348827096e-05,
|
|
"loss": 4.5635,
|
|
"mean_token_accuracy": 0.24396042078733443,
|
|
"num_tokens": 19749489.0,
|
|
"step": 10835
|
|
},
|
|
{
|
|
"entropy": 5.361280107498169,
|
|
"epoch": 8.980944490472245,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.339724861269085e-05,
|
|
"loss": 4.5607,
|
|
"mean_token_accuracy": 0.2396802246570587,
|
|
"num_tokens": 19758745.0,
|
|
"step": 10840
|
|
},
|
|
{
|
|
"entropy": 5.4085227966308596,
|
|
"epoch": 8.985086992543497,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.328884056298393e-05,
|
|
"loss": 4.6208,
|
|
"mean_token_accuracy": 0.2353546589612961,
|
|
"num_tokens": 19767713.0,
|
|
"step": 10845
|
|
},
|
|
{
|
|
"entropy": 5.336814022064209,
|
|
"epoch": 8.989229494614747,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.31808595578211e-05,
|
|
"loss": 4.5719,
|
|
"mean_token_accuracy": 0.24699053466320037,
|
|
"num_tokens": 19777236.0,
|
|
"step": 10850
|
|
},
|
|
{
|
|
"entropy": 5.3367890357971195,
|
|
"epoch": 8.993371996685998,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 6.307330581501183e-05,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.2501660227775574,
|
|
"num_tokens": 19785981.0,
|
|
"step": 10855
|
|
},
|
|
{
|
|
"entropy": 5.355890321731567,
|
|
"epoch": 8.99751449875725,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 6.29661795515038e-05,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.24268113672733307,
|
|
"num_tokens": 19795046.0,
|
|
"step": 10860
|
|
},
|
|
{
|
|
"entropy": 5.455114555358887,
|
|
"epoch": 9.0016570008285,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 6.285948098338238e-05,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.23488045781850814,
|
|
"num_tokens": 19803108.0,
|
|
"step": 10865
|
|
},
|
|
{
|
|
"entropy": 5.4368494033813475,
|
|
"epoch": 9.005799502899752,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 6.27532103258702e-05,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.24439057856798171,
|
|
"num_tokens": 19812751.0,
|
|
"step": 10870
|
|
},
|
|
{
|
|
"entropy": 5.413991165161133,
|
|
"epoch": 9.009942004971002,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.26473677933269e-05,
|
|
"loss": 4.5491,
|
|
"mean_token_accuracy": 0.24872785061597824,
|
|
"num_tokens": 19821634.0,
|
|
"step": 10875
|
|
},
|
|
{
|
|
"entropy": 5.356666707992554,
|
|
"epoch": 9.014084507042254,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 6.254195359924827e-05,
|
|
"loss": 4.4964,
|
|
"mean_token_accuracy": 0.25335092544555665,
|
|
"num_tokens": 19830760.0,
|
|
"step": 10880
|
|
},
|
|
{
|
|
"entropy": 5.295748043060303,
|
|
"epoch": 9.018227009113504,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.24369679562664e-05,
|
|
"loss": 4.407,
|
|
"mean_token_accuracy": 0.2575793042778969,
|
|
"num_tokens": 19839463.0,
|
|
"step": 10885
|
|
},
|
|
{
|
|
"entropy": 5.33272967338562,
|
|
"epoch": 9.022369511184756,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 6.233241107614875e-05,
|
|
"loss": 4.467,
|
|
"mean_token_accuracy": 0.26022769659757616,
|
|
"num_tokens": 19848256.0,
|
|
"step": 10890
|
|
},
|
|
{
|
|
"entropy": 5.384660625457764,
|
|
"epoch": 9.026512013256006,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.222828316979798e-05,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.2488069489598274,
|
|
"num_tokens": 19857572.0,
|
|
"step": 10895
|
|
},
|
|
{
|
|
"entropy": 5.350844049453736,
|
|
"epoch": 9.030654515327258,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.212458444725146e-05,
|
|
"loss": 4.5365,
|
|
"mean_token_accuracy": 0.2433128222823143,
|
|
"num_tokens": 19866825.0,
|
|
"step": 10900
|
|
},
|
|
{
|
|
"entropy": 5.459282159805298,
|
|
"epoch": 9.034797017398509,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.202131511768079e-05,
|
|
"loss": 4.6467,
|
|
"mean_token_accuracy": 0.2389314979314804,
|
|
"num_tokens": 19875970.0,
|
|
"step": 10905
|
|
},
|
|
{
|
|
"entropy": 5.363461971282959,
|
|
"epoch": 9.03893951946976,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.19184753893916e-05,
|
|
"loss": 4.5035,
|
|
"mean_token_accuracy": 0.24734800159931183,
|
|
"num_tokens": 19884910.0,
|
|
"step": 10910
|
|
},
|
|
{
|
|
"entropy": 5.4074197769165036,
|
|
"epoch": 9.04308202154101,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.181606546982274e-05,
|
|
"loss": 4.5624,
|
|
"mean_token_accuracy": 0.242459674179554,
|
|
"num_tokens": 19894838.0,
|
|
"step": 10915
|
|
},
|
|
{
|
|
"entropy": 5.458126497268677,
|
|
"epoch": 9.047224523612261,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.171408556554633e-05,
|
|
"loss": 4.6493,
|
|
"mean_token_accuracy": 0.23512547165155412,
|
|
"num_tokens": 19904809.0,
|
|
"step": 10920
|
|
},
|
|
{
|
|
"entropy": 5.299647521972656,
|
|
"epoch": 9.051367025683513,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.16125358822669e-05,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.2548012673854828,
|
|
"num_tokens": 19913549.0,
|
|
"step": 10925
|
|
},
|
|
{
|
|
"entropy": 5.327856826782226,
|
|
"epoch": 9.055509527754763,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 6.151141662482126e-05,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.2523758336901665,
|
|
"num_tokens": 19922572.0,
|
|
"step": 10930
|
|
},
|
|
{
|
|
"entropy": 5.416527366638183,
|
|
"epoch": 9.059652029826015,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.141072799717805e-05,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.2364077866077423,
|
|
"num_tokens": 19932058.0,
|
|
"step": 10935
|
|
},
|
|
{
|
|
"entropy": 5.282618474960327,
|
|
"epoch": 9.063794531897265,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.131047020243717e-05,
|
|
"loss": 4.4514,
|
|
"mean_token_accuracy": 0.25616891831159594,
|
|
"num_tokens": 19940406.0,
|
|
"step": 10940
|
|
},
|
|
{
|
|
"entropy": 5.353671407699585,
|
|
"epoch": 9.067937033968517,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.121064344282962e-05,
|
|
"loss": 4.5077,
|
|
"mean_token_accuracy": 0.24752259254455566,
|
|
"num_tokens": 19949181.0,
|
|
"step": 10945
|
|
},
|
|
{
|
|
"entropy": 5.41296615600586,
|
|
"epoch": 9.072079536039768,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.111124791971687e-05,
|
|
"loss": 4.5727,
|
|
"mean_token_accuracy": 0.23995108306407928,
|
|
"num_tokens": 19958159.0,
|
|
"step": 10950
|
|
},
|
|
{
|
|
"entropy": 5.340942144393921,
|
|
"epoch": 9.07622203811102,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 6.1012283833590465e-05,
|
|
"loss": 4.5123,
|
|
"mean_token_accuracy": 0.24541157782077788,
|
|
"num_tokens": 19967614.0,
|
|
"step": 10955
|
|
},
|
|
{
|
|
"entropy": 5.3413975715637205,
|
|
"epoch": 9.08036454018227,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 6.091375138407189e-05,
|
|
"loss": 4.4988,
|
|
"mean_token_accuracy": 0.252067269384861,
|
|
"num_tokens": 19977697.0,
|
|
"step": 10960
|
|
},
|
|
{
|
|
"entropy": 5.460159492492676,
|
|
"epoch": 9.084507042253522,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 6.0815650769911774e-05,
|
|
"loss": 4.5923,
|
|
"mean_token_accuracy": 0.23988382518291473,
|
|
"num_tokens": 19986152.0,
|
|
"step": 10965
|
|
},
|
|
{
|
|
"entropy": 5.390202474594116,
|
|
"epoch": 9.088649544324772,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 6.0717982188989884e-05,
|
|
"loss": 4.5387,
|
|
"mean_token_accuracy": 0.23216845840215683,
|
|
"num_tokens": 19995904.0,
|
|
"step": 10970
|
|
},
|
|
{
|
|
"entropy": 5.3476762771606445,
|
|
"epoch": 9.092792046396022,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 6.062074583831432e-05,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.2501545950770378,
|
|
"num_tokens": 20005516.0,
|
|
"step": 10975
|
|
},
|
|
{
|
|
"entropy": 5.329339694976807,
|
|
"epoch": 9.096934548467274,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.052394191402145e-05,
|
|
"loss": 4.486,
|
|
"mean_token_accuracy": 0.24782122522592545,
|
|
"num_tokens": 20014183.0,
|
|
"step": 10980
|
|
},
|
|
{
|
|
"entropy": 5.354713392257691,
|
|
"epoch": 9.101077050538525,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.042757061137545e-05,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.24396902322769165,
|
|
"num_tokens": 20023537.0,
|
|
"step": 10985
|
|
},
|
|
{
|
|
"entropy": 5.459105587005615,
|
|
"epoch": 9.105219552609777,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 6.033163212476762e-05,
|
|
"loss": 4.6051,
|
|
"mean_token_accuracy": 0.24059031307697296,
|
|
"num_tokens": 20032639.0,
|
|
"step": 10990
|
|
},
|
|
{
|
|
"entropy": 5.389468193054199,
|
|
"epoch": 9.109362054681027,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 6.023612664771651e-05,
|
|
"loss": 4.558,
|
|
"mean_token_accuracy": 0.252620267868042,
|
|
"num_tokens": 20041273.0,
|
|
"step": 10995
|
|
},
|
|
{
|
|
"entropy": 5.431494903564453,
|
|
"epoch": 9.113504556752279,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 6.014105437286705e-05,
|
|
"loss": 4.4759,
|
|
"mean_token_accuracy": 0.2506009712815285,
|
|
"num_tokens": 20049730.0,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"epoch": 9.113504556752279,
|
|
"eval_entropy": 5.203860301198736,
|
|
"eval_loss": 5.713740825653076,
|
|
"eval_mean_token_accuracy": 0.17083108823881474,
|
|
"eval_num_tokens": 20049730.0,
|
|
"eval_runtime": 2.1071,
|
|
"eval_samples_per_second": 1778.301,
|
|
"eval_steps_per_second": 222.584,
|
|
"step": 11000
|
|
},
|
|
{
|
|
"entropy": 5.395301151275635,
|
|
"epoch": 9.117647058823529,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 6.0046415491990355e-05,
|
|
"loss": 4.5207,
|
|
"mean_token_accuracy": 0.2605585098266602,
|
|
"num_tokens": 20059151.0,
|
|
"step": 11005
|
|
},
|
|
{
|
|
"entropy": 5.364123392105102,
|
|
"epoch": 9.121789560894781,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.99522101959835e-05,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.2470742031931877,
|
|
"num_tokens": 20068389.0,
|
|
"step": 11010
|
|
},
|
|
{
|
|
"entropy": 5.471275424957275,
|
|
"epoch": 9.125932062966031,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.9858438674868744e-05,
|
|
"loss": 4.6022,
|
|
"mean_token_accuracy": 0.24401771128177643,
|
|
"num_tokens": 20077794.0,
|
|
"step": 11015
|
|
},
|
|
{
|
|
"entropy": 5.372765588760376,
|
|
"epoch": 9.130074565037283,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.976510111779359e-05,
|
|
"loss": 4.4979,
|
|
"mean_token_accuracy": 0.2470611125230789,
|
|
"num_tokens": 20086641.0,
|
|
"step": 11020
|
|
},
|
|
{
|
|
"entropy": 5.351373767852783,
|
|
"epoch": 9.134217067108533,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.9672197713030044e-05,
|
|
"loss": 4.5212,
|
|
"mean_token_accuracy": 0.2475714787840843,
|
|
"num_tokens": 20095746.0,
|
|
"step": 11025
|
|
},
|
|
{
|
|
"entropy": 5.308516359329223,
|
|
"epoch": 9.138359569179785,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.9579728647974416e-05,
|
|
"loss": 4.5302,
|
|
"mean_token_accuracy": 0.25114922523498534,
|
|
"num_tokens": 20105381.0,
|
|
"step": 11030
|
|
},
|
|
{
|
|
"entropy": 5.328987073898316,
|
|
"epoch": 9.142502071251036,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.948769410914694e-05,
|
|
"loss": 4.4671,
|
|
"mean_token_accuracy": 0.250366373360157,
|
|
"num_tokens": 20114543.0,
|
|
"step": 11035
|
|
},
|
|
{
|
|
"entropy": 5.303188467025757,
|
|
"epoch": 9.146644573322286,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.939609428219131e-05,
|
|
"loss": 4.5039,
|
|
"mean_token_accuracy": 0.24850960373878478,
|
|
"num_tokens": 20123528.0,
|
|
"step": 11040
|
|
},
|
|
{
|
|
"entropy": 5.324607467651367,
|
|
"epoch": 9.150787075393538,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.930492935187446e-05,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.25365816950798037,
|
|
"num_tokens": 20132619.0,
|
|
"step": 11045
|
|
},
|
|
{
|
|
"entropy": 5.353727102279663,
|
|
"epoch": 9.154929577464788,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.921419950208592e-05,
|
|
"loss": 4.4605,
|
|
"mean_token_accuracy": 0.25790291279554367,
|
|
"num_tokens": 20140938.0,
|
|
"step": 11050
|
|
},
|
|
{
|
|
"entropy": 5.406233882904052,
|
|
"epoch": 9.15907207953604,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.912390491583776e-05,
|
|
"loss": 4.5378,
|
|
"mean_token_accuracy": 0.24344915449619292,
|
|
"num_tokens": 20149925.0,
|
|
"step": 11055
|
|
},
|
|
{
|
|
"entropy": 5.320320653915405,
|
|
"epoch": 9.16321458160729,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.9034045775264016e-05,
|
|
"loss": 4.4922,
|
|
"mean_token_accuracy": 0.25482448786497114,
|
|
"num_tokens": 20158487.0,
|
|
"step": 11060
|
|
},
|
|
{
|
|
"entropy": 5.45740385055542,
|
|
"epoch": 9.167357083678542,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.894462226162042e-05,
|
|
"loss": 4.6595,
|
|
"mean_token_accuracy": 0.23566072136163713,
|
|
"num_tokens": 20168185.0,
|
|
"step": 11065
|
|
},
|
|
{
|
|
"entropy": 5.346451044082642,
|
|
"epoch": 9.171499585749793,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.8855634555283954e-05,
|
|
"loss": 4.5094,
|
|
"mean_token_accuracy": 0.25603205561637876,
|
|
"num_tokens": 20176629.0,
|
|
"step": 11070
|
|
},
|
|
{
|
|
"entropy": 5.315811109542847,
|
|
"epoch": 9.175642087821045,
|
|
"grad_norm": 1.71875,
|
|
"learning_rate": 5.876708283575254e-05,
|
|
"loss": 4.4088,
|
|
"mean_token_accuracy": 0.25607401728630064,
|
|
"num_tokens": 20185269.0,
|
|
"step": 11075
|
|
},
|
|
{
|
|
"entropy": 5.3595751285552975,
|
|
"epoch": 9.179784589892295,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.867896728164468e-05,
|
|
"loss": 4.517,
|
|
"mean_token_accuracy": 0.2397010490298271,
|
|
"num_tokens": 20194414.0,
|
|
"step": 11080
|
|
},
|
|
{
|
|
"entropy": 5.349236679077149,
|
|
"epoch": 9.183927091963547,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.859128807069905e-05,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.24396539628505706,
|
|
"num_tokens": 20203139.0,
|
|
"step": 11085
|
|
},
|
|
{
|
|
"entropy": 5.329089546203614,
|
|
"epoch": 9.188069594034797,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.8504045379774246e-05,
|
|
"loss": 4.4701,
|
|
"mean_token_accuracy": 0.247181336581707,
|
|
"num_tokens": 20211767.0,
|
|
"step": 11090
|
|
},
|
|
{
|
|
"entropy": 5.323103952407837,
|
|
"epoch": 9.192212096106047,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.841723938484826e-05,
|
|
"loss": 4.5016,
|
|
"mean_token_accuracy": 0.24900311827659607,
|
|
"num_tokens": 20219916.0,
|
|
"step": 11095
|
|
},
|
|
{
|
|
"entropy": 5.306069278717041,
|
|
"epoch": 9.1963545981773,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.833087026101834e-05,
|
|
"loss": 4.5166,
|
|
"mean_token_accuracy": 0.24974364340305327,
|
|
"num_tokens": 20229082.0,
|
|
"step": 11100
|
|
},
|
|
{
|
|
"entropy": 5.378958797454834,
|
|
"epoch": 9.20049710024855,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.824493818250034e-05,
|
|
"loss": 4.6072,
|
|
"mean_token_accuracy": 0.23317480981349945,
|
|
"num_tokens": 20238758.0,
|
|
"step": 11105
|
|
},
|
|
{
|
|
"entropy": 5.331934928894043,
|
|
"epoch": 9.204639602319801,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.815944332262878e-05,
|
|
"loss": 4.483,
|
|
"mean_token_accuracy": 0.2514406397938728,
|
|
"num_tokens": 20248308.0,
|
|
"step": 11110
|
|
},
|
|
{
|
|
"entropy": 5.316699695587158,
|
|
"epoch": 9.208782104391052,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.8074385853856035e-05,
|
|
"loss": 4.3534,
|
|
"mean_token_accuracy": 0.2571008548140526,
|
|
"num_tokens": 20257282.0,
|
|
"step": 11115
|
|
},
|
|
{
|
|
"entropy": 5.38381781578064,
|
|
"epoch": 9.212924606462304,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.7989765947752384e-05,
|
|
"loss": 4.5571,
|
|
"mean_token_accuracy": 0.2450488805770874,
|
|
"num_tokens": 20267680.0,
|
|
"step": 11120
|
|
},
|
|
{
|
|
"entropy": 5.421346187591553,
|
|
"epoch": 9.217067108533554,
|
|
"grad_norm": 1.796875,
|
|
"learning_rate": 5.790558377500537e-05,
|
|
"loss": 4.5665,
|
|
"mean_token_accuracy": 0.24455181360244752,
|
|
"num_tokens": 20276679.0,
|
|
"step": 11125
|
|
},
|
|
{
|
|
"entropy": 5.328466796875,
|
|
"epoch": 9.221209610604806,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.7821839505419636e-05,
|
|
"loss": 4.4354,
|
|
"mean_token_accuracy": 0.25132142156362536,
|
|
"num_tokens": 20285287.0,
|
|
"step": 11130
|
|
},
|
|
{
|
|
"entropy": 5.422858667373657,
|
|
"epoch": 9.225352112676056,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.773853330791659e-05,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.24332577735185623,
|
|
"num_tokens": 20294558.0,
|
|
"step": 11135
|
|
},
|
|
{
|
|
"entropy": 5.346093654632568,
|
|
"epoch": 9.229494614747308,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.765566535053383e-05,
|
|
"loss": 4.5334,
|
|
"mean_token_accuracy": 0.249077770113945,
|
|
"num_tokens": 20303451.0,
|
|
"step": 11140
|
|
},
|
|
{
|
|
"entropy": 5.342402791976928,
|
|
"epoch": 9.233637116818558,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.757323580042519e-05,
|
|
"loss": 4.4894,
|
|
"mean_token_accuracy": 0.24335692673921586,
|
|
"num_tokens": 20312210.0,
|
|
"step": 11145
|
|
},
|
|
{
|
|
"entropy": 5.344110536575317,
|
|
"epoch": 9.23777961888981,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.7491244823860026e-05,
|
|
"loss": 4.5344,
|
|
"mean_token_accuracy": 0.2561978667974472,
|
|
"num_tokens": 20321636.0,
|
|
"step": 11150
|
|
},
|
|
{
|
|
"entropy": 5.244318199157715,
|
|
"epoch": 9.24192212096106,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.7409692586223105e-05,
|
|
"loss": 4.4017,
|
|
"mean_token_accuracy": 0.2568577706813812,
|
|
"num_tokens": 20330210.0,
|
|
"step": 11155
|
|
},
|
|
{
|
|
"entropy": 5.334996938705444,
|
|
"epoch": 9.24606462303231,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.7328579252014204e-05,
|
|
"loss": 4.5032,
|
|
"mean_token_accuracy": 0.2416616052389145,
|
|
"num_tokens": 20338992.0,
|
|
"step": 11160
|
|
},
|
|
{
|
|
"entropy": 5.325828790664673,
|
|
"epoch": 9.250207125103563,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.724790498484778e-05,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.24636233150959014,
|
|
"num_tokens": 20347645.0,
|
|
"step": 11165
|
|
},
|
|
{
|
|
"entropy": 5.317667436599732,
|
|
"epoch": 9.254349627174813,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.7167669947452654e-05,
|
|
"loss": 4.4697,
|
|
"mean_token_accuracy": 0.2570079371333122,
|
|
"num_tokens": 20355415.0,
|
|
"step": 11170
|
|
},
|
|
{
|
|
"entropy": 5.3640666007995605,
|
|
"epoch": 9.258492129246065,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.708787430167163e-05,
|
|
"loss": 4.4961,
|
|
"mean_token_accuracy": 0.25568542927503585,
|
|
"num_tokens": 20365238.0,
|
|
"step": 11175
|
|
},
|
|
{
|
|
"entropy": 5.399002361297607,
|
|
"epoch": 9.262634631317315,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.700851820846129e-05,
|
|
"loss": 4.5167,
|
|
"mean_token_accuracy": 0.2524569183588028,
|
|
"num_tokens": 20374522.0,
|
|
"step": 11180
|
|
},
|
|
{
|
|
"entropy": 5.399986648559571,
|
|
"epoch": 9.266777133388567,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.69296018278915e-05,
|
|
"loss": 4.5027,
|
|
"mean_token_accuracy": 0.24697856605052948,
|
|
"num_tokens": 20383449.0,
|
|
"step": 11185
|
|
},
|
|
{
|
|
"entropy": 5.350671482086182,
|
|
"epoch": 9.270919635459817,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.685112531914531e-05,
|
|
"loss": 4.5113,
|
|
"mean_token_accuracy": 0.24052478969097138,
|
|
"num_tokens": 20392236.0,
|
|
"step": 11190
|
|
},
|
|
{
|
|
"entropy": 5.3138525009155275,
|
|
"epoch": 9.27506213753107,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.677308884051833e-05,
|
|
"loss": 4.4711,
|
|
"mean_token_accuracy": 0.2427891194820404,
|
|
"num_tokens": 20401416.0,
|
|
"step": 11195
|
|
},
|
|
{
|
|
"entropy": 5.3863489627838135,
|
|
"epoch": 9.27920463960232,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.669549254941865e-05,
|
|
"loss": 4.5153,
|
|
"mean_token_accuracy": 0.2551788955926895,
|
|
"num_tokens": 20410136.0,
|
|
"step": 11200
|
|
},
|
|
{
|
|
"entropy": 5.3263904571533205,
|
|
"epoch": 9.283347141673572,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.661833660236657e-05,
|
|
"loss": 4.4899,
|
|
"mean_token_accuracy": 0.24968332350254058,
|
|
"num_tokens": 20419527.0,
|
|
"step": 11205
|
|
},
|
|
{
|
|
"entropy": 5.329418134689331,
|
|
"epoch": 9.287489643744822,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.6541621154993956e-05,
|
|
"loss": 4.508,
|
|
"mean_token_accuracy": 0.25147112756967543,
|
|
"num_tokens": 20428540.0,
|
|
"step": 11210
|
|
},
|
|
{
|
|
"entropy": 5.380512428283692,
|
|
"epoch": 9.291632145816074,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.646534636204434e-05,
|
|
"loss": 4.4695,
|
|
"mean_token_accuracy": 0.2572668805718422,
|
|
"num_tokens": 20437979.0,
|
|
"step": 11215
|
|
},
|
|
{
|
|
"entropy": 5.4409161567687985,
|
|
"epoch": 9.295774647887324,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.6389512377372245e-05,
|
|
"loss": 4.6091,
|
|
"mean_token_accuracy": 0.241894194483757,
|
|
"num_tokens": 20447352.0,
|
|
"step": 11220
|
|
},
|
|
{
|
|
"entropy": 5.338595581054688,
|
|
"epoch": 9.299917149958574,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.6314119353943155e-05,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.23827020972967147,
|
|
"num_tokens": 20456085.0,
|
|
"step": 11225
|
|
},
|
|
{
|
|
"entropy": 5.307044267654419,
|
|
"epoch": 9.304059652029826,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.6239167443833004e-05,
|
|
"loss": 4.399,
|
|
"mean_token_accuracy": 0.2597416892647743,
|
|
"num_tokens": 20464629.0,
|
|
"step": 11230
|
|
},
|
|
{
|
|
"entropy": 5.388040542602539,
|
|
"epoch": 9.308202154101076,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.6164656798227973e-05,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.2467937707901001,
|
|
"num_tokens": 20473525.0,
|
|
"step": 11235
|
|
},
|
|
{
|
|
"entropy": 5.449045419692993,
|
|
"epoch": 9.312344656172328,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.6090587567424247e-05,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.23594920933246613,
|
|
"num_tokens": 20482444.0,
|
|
"step": 11240
|
|
},
|
|
{
|
|
"entropy": 5.3672384262084964,
|
|
"epoch": 9.316487158243579,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.60169599008275e-05,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.24438742101192473,
|
|
"num_tokens": 20490824.0,
|
|
"step": 11245
|
|
},
|
|
{
|
|
"entropy": 5.322297430038452,
|
|
"epoch": 9.32062966031483,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.594377394695277e-05,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.24704592078924179,
|
|
"num_tokens": 20499935.0,
|
|
"step": 11250
|
|
},
|
|
{
|
|
"entropy": 5.369363927841187,
|
|
"epoch": 9.32477216238608,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.587102985342416e-05,
|
|
"loss": 4.5213,
|
|
"mean_token_accuracy": 0.25166441649198534,
|
|
"num_tokens": 20508833.0,
|
|
"step": 11255
|
|
},
|
|
{
|
|
"entropy": 5.342498302459717,
|
|
"epoch": 9.328914664457333,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.579872776697443e-05,
|
|
"loss": 4.5046,
|
|
"mean_token_accuracy": 0.24233926087617874,
|
|
"num_tokens": 20516960.0,
|
|
"step": 11260
|
|
},
|
|
{
|
|
"entropy": 5.367656564712524,
|
|
"epoch": 9.333057166528583,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.572686783344483e-05,
|
|
"loss": 4.4801,
|
|
"mean_token_accuracy": 0.2575399652123451,
|
|
"num_tokens": 20526009.0,
|
|
"step": 11265
|
|
},
|
|
{
|
|
"entropy": 5.377683353424072,
|
|
"epoch": 9.337199668599835,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.565545019778468e-05,
|
|
"loss": 4.534,
|
|
"mean_token_accuracy": 0.24566157758235932,
|
|
"num_tokens": 20534684.0,
|
|
"step": 11270
|
|
},
|
|
{
|
|
"entropy": 5.342058372497559,
|
|
"epoch": 9.341342170671085,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.558447500405111e-05,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.24899577349424362,
|
|
"num_tokens": 20543429.0,
|
|
"step": 11275
|
|
},
|
|
{
|
|
"entropy": 5.373324012756347,
|
|
"epoch": 9.345484672742336,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.5513942395408883e-05,
|
|
"loss": 4.4812,
|
|
"mean_token_accuracy": 0.24757155627012253,
|
|
"num_tokens": 20552928.0,
|
|
"step": 11280
|
|
},
|
|
{
|
|
"entropy": 5.3119957447052,
|
|
"epoch": 9.349627174813588,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.544385251412998e-05,
|
|
"loss": 4.4881,
|
|
"mean_token_accuracy": 0.2497639074921608,
|
|
"num_tokens": 20562133.0,
|
|
"step": 11285
|
|
},
|
|
{
|
|
"entropy": 5.324808025360108,
|
|
"epoch": 9.353769676884838,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.537420550159335e-05,
|
|
"loss": 4.5208,
|
|
"mean_token_accuracy": 0.24159959554672242,
|
|
"num_tokens": 20571901.0,
|
|
"step": 11290
|
|
},
|
|
{
|
|
"entropy": 5.369680309295655,
|
|
"epoch": 9.35791217895609,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.530500149828463e-05,
|
|
"loss": 4.5537,
|
|
"mean_token_accuracy": 0.24539411962032318,
|
|
"num_tokens": 20581503.0,
|
|
"step": 11295
|
|
},
|
|
{
|
|
"entropy": 5.356932735443115,
|
|
"epoch": 9.36205468102734,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.523624064379585e-05,
|
|
"loss": 4.5659,
|
|
"mean_token_accuracy": 0.23520461916923524,
|
|
"num_tokens": 20590338.0,
|
|
"step": 11300
|
|
},
|
|
{
|
|
"entropy": 5.358993768692017,
|
|
"epoch": 9.366197183098592,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.516792307682516e-05,
|
|
"loss": 4.5629,
|
|
"mean_token_accuracy": 0.2453669548034668,
|
|
"num_tokens": 20599305.0,
|
|
"step": 11305
|
|
},
|
|
{
|
|
"entropy": 5.30262303352356,
|
|
"epoch": 9.370339685169842,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.510004893517655e-05,
|
|
"loss": 4.4665,
|
|
"mean_token_accuracy": 0.25664637982845306,
|
|
"num_tokens": 20608043.0,
|
|
"step": 11310
|
|
},
|
|
{
|
|
"entropy": 5.334803104400635,
|
|
"epoch": 9.374482187241094,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.503261835575965e-05,
|
|
"loss": 4.5436,
|
|
"mean_token_accuracy": 0.24554742723703385,
|
|
"num_tokens": 20617121.0,
|
|
"step": 11315
|
|
},
|
|
{
|
|
"entropy": 5.354681968688965,
|
|
"epoch": 9.378624689312344,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.4965631474589205e-05,
|
|
"loss": 4.5048,
|
|
"mean_token_accuracy": 0.24630842804908754,
|
|
"num_tokens": 20625935.0,
|
|
"step": 11320
|
|
},
|
|
{
|
|
"entropy": 5.341200113296509,
|
|
"epoch": 9.382767191383596,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.4899088426785145e-05,
|
|
"loss": 4.4587,
|
|
"mean_token_accuracy": 0.2515927627682686,
|
|
"num_tokens": 20635606.0,
|
|
"step": 11325
|
|
},
|
|
{
|
|
"entropy": 5.33123025894165,
|
|
"epoch": 9.386909693454847,
|
|
"grad_norm": 1.75,
|
|
"learning_rate": 5.4832989346572046e-05,
|
|
"loss": 4.452,
|
|
"mean_token_accuracy": 0.25959134101867676,
|
|
"num_tokens": 20644254.0,
|
|
"step": 11330
|
|
},
|
|
{
|
|
"entropy": 5.388541746139526,
|
|
"epoch": 9.391052195526099,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.476733436727895e-05,
|
|
"loss": 4.522,
|
|
"mean_token_accuracy": 0.23916723281145097,
|
|
"num_tokens": 20653157.0,
|
|
"step": 11335
|
|
},
|
|
{
|
|
"entropy": 5.362478590011596,
|
|
"epoch": 9.395194697597349,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.47021236213392e-05,
|
|
"loss": 4.488,
|
|
"mean_token_accuracy": 0.25158932656049726,
|
|
"num_tokens": 20662169.0,
|
|
"step": 11340
|
|
},
|
|
{
|
|
"entropy": 5.354816818237305,
|
|
"epoch": 9.399337199668599,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.463735724028991e-05,
|
|
"loss": 4.5538,
|
|
"mean_token_accuracy": 0.23962764143943788,
|
|
"num_tokens": 20671915.0,
|
|
"step": 11345
|
|
},
|
|
{
|
|
"entropy": 5.3598065853118895,
|
|
"epoch": 9.403479701739851,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.457303535477202e-05,
|
|
"loss": 4.5465,
|
|
"mean_token_accuracy": 0.2547251760959625,
|
|
"num_tokens": 20681157.0,
|
|
"step": 11350
|
|
},
|
|
{
|
|
"entropy": 5.349321126937866,
|
|
"epoch": 9.407622203811101,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.450915809452976e-05,
|
|
"loss": 4.5124,
|
|
"mean_token_accuracy": 0.24891739338636398,
|
|
"num_tokens": 20690972.0,
|
|
"step": 11355
|
|
},
|
|
{
|
|
"entropy": 5.395678997039795,
|
|
"epoch": 9.411764705882353,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.444572558841053e-05,
|
|
"loss": 4.602,
|
|
"mean_token_accuracy": 0.24337243139743805,
|
|
"num_tokens": 20700250.0,
|
|
"step": 11360
|
|
},
|
|
{
|
|
"entropy": 5.309518718719483,
|
|
"epoch": 9.415907207953603,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.4382737964364674e-05,
|
|
"loss": 4.4451,
|
|
"mean_token_accuracy": 0.2507553264498711,
|
|
"num_tokens": 20708965.0,
|
|
"step": 11365
|
|
},
|
|
{
|
|
"entropy": 5.346716213226318,
|
|
"epoch": 9.420049710024855,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.432019534944507e-05,
|
|
"loss": 4.4856,
|
|
"mean_token_accuracy": 0.25327764749526976,
|
|
"num_tokens": 20717750.0,
|
|
"step": 11370
|
|
},
|
|
{
|
|
"entropy": 5.426984882354736,
|
|
"epoch": 9.424192212096106,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.4258097869807054e-05,
|
|
"loss": 4.616,
|
|
"mean_token_accuracy": 0.23463350683450698,
|
|
"num_tokens": 20727904.0,
|
|
"step": 11375
|
|
},
|
|
{
|
|
"entropy": 5.443246746063233,
|
|
"epoch": 9.428334714167358,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.4196445650708e-05,
|
|
"loss": 4.6074,
|
|
"mean_token_accuracy": 0.2438860923051834,
|
|
"num_tokens": 20737550.0,
|
|
"step": 11380
|
|
},
|
|
{
|
|
"entropy": 5.352163505554199,
|
|
"epoch": 9.432477216238608,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.4135238816507154e-05,
|
|
"loss": 4.5252,
|
|
"mean_token_accuracy": 0.2478283688426018,
|
|
"num_tokens": 20747126.0,
|
|
"step": 11385
|
|
},
|
|
{
|
|
"entropy": 5.39880952835083,
|
|
"epoch": 9.43661971830986,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.407447749066542e-05,
|
|
"loss": 4.5633,
|
|
"mean_token_accuracy": 0.24558413177728652,
|
|
"num_tokens": 20755366.0,
|
|
"step": 11390
|
|
},
|
|
{
|
|
"entropy": 5.432702732086182,
|
|
"epoch": 9.44076222038111,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.401416179574502e-05,
|
|
"loss": 4.4876,
|
|
"mean_token_accuracy": 0.25576176643371584,
|
|
"num_tokens": 20764277.0,
|
|
"step": 11395
|
|
},
|
|
{
|
|
"entropy": 5.32876763343811,
|
|
"epoch": 9.44490472245236,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.395429185340929e-05,
|
|
"loss": 4.417,
|
|
"mean_token_accuracy": 0.26852446645498274,
|
|
"num_tokens": 20772839.0,
|
|
"step": 11400
|
|
},
|
|
{
|
|
"entropy": 5.36781325340271,
|
|
"epoch": 9.449047224523612,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.389486778442248e-05,
|
|
"loss": 4.5183,
|
|
"mean_token_accuracy": 0.2490229681134224,
|
|
"num_tokens": 20782135.0,
|
|
"step": 11405
|
|
},
|
|
{
|
|
"entropy": 5.367950105667115,
|
|
"epoch": 9.453189726594863,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.3835889708649374e-05,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.24563224166631697,
|
|
"num_tokens": 20790746.0,
|
|
"step": 11410
|
|
},
|
|
{
|
|
"entropy": 5.391159248352051,
|
|
"epoch": 9.457332228666115,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.3777357745055276e-05,
|
|
"loss": 4.5669,
|
|
"mean_token_accuracy": 0.24226678907871246,
|
|
"num_tokens": 20800260.0,
|
|
"step": 11415
|
|
},
|
|
{
|
|
"entropy": 5.371519756317139,
|
|
"epoch": 9.461474730737365,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.371927201170547e-05,
|
|
"loss": 4.5572,
|
|
"mean_token_accuracy": 0.24245287030935286,
|
|
"num_tokens": 20809168.0,
|
|
"step": 11420
|
|
},
|
|
{
|
|
"entropy": 5.426420879364014,
|
|
"epoch": 9.465617232808617,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.3661632625765284e-05,
|
|
"loss": 4.6284,
|
|
"mean_token_accuracy": 0.23111584037542343,
|
|
"num_tokens": 20819697.0,
|
|
"step": 11425
|
|
},
|
|
{
|
|
"entropy": 5.347937536239624,
|
|
"epoch": 9.469759734879867,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.360443970349965e-05,
|
|
"loss": 4.4661,
|
|
"mean_token_accuracy": 0.25135899186134336,
|
|
"num_tokens": 20828836.0,
|
|
"step": 11430
|
|
},
|
|
{
|
|
"entropy": 5.398262786865234,
|
|
"epoch": 9.473902236951119,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.3547693360272904e-05,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.23725306689739228,
|
|
"num_tokens": 20838176.0,
|
|
"step": 11435
|
|
},
|
|
{
|
|
"entropy": 5.345471143722534,
|
|
"epoch": 9.47804473902237,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.349139371054865e-05,
|
|
"loss": 4.5522,
|
|
"mean_token_accuracy": 0.2436929315328598,
|
|
"num_tokens": 20848110.0,
|
|
"step": 11440
|
|
},
|
|
{
|
|
"entropy": 5.354112434387207,
|
|
"epoch": 9.482187241093621,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.343554086788945e-05,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.25373906046152117,
|
|
"num_tokens": 20856680.0,
|
|
"step": 11445
|
|
},
|
|
{
|
|
"entropy": 5.346868324279785,
|
|
"epoch": 9.486329743164871,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.338013494495658e-05,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.2390081524848938,
|
|
"num_tokens": 20865099.0,
|
|
"step": 11450
|
|
},
|
|
{
|
|
"entropy": 5.377876949310303,
|
|
"epoch": 9.490472245236123,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.3325176053509826e-05,
|
|
"loss": 4.5658,
|
|
"mean_token_accuracy": 0.2450117811560631,
|
|
"num_tokens": 20874134.0,
|
|
"step": 11455
|
|
},
|
|
{
|
|
"entropy": 5.369621133804321,
|
|
"epoch": 9.494614747307374,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.3270664304407256e-05,
|
|
"loss": 4.5009,
|
|
"mean_token_accuracy": 0.2524899929761887,
|
|
"num_tokens": 20883136.0,
|
|
"step": 11460
|
|
},
|
|
{
|
|
"entropy": 5.341934251785278,
|
|
"epoch": 9.498757249378624,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.32165998076051e-05,
|
|
"loss": 4.5142,
|
|
"mean_token_accuracy": 0.23969170302152634,
|
|
"num_tokens": 20891028.0,
|
|
"step": 11465
|
|
},
|
|
{
|
|
"entropy": 5.313600158691406,
|
|
"epoch": 9.502899751449876,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.316298267215728e-05,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.24374132752418518,
|
|
"num_tokens": 20900471.0,
|
|
"step": 11470
|
|
},
|
|
{
|
|
"entropy": 5.35675950050354,
|
|
"epoch": 9.507042253521126,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.310981300621547e-05,
|
|
"loss": 4.512,
|
|
"mean_token_accuracy": 0.24074027836322784,
|
|
"num_tokens": 20909854.0,
|
|
"step": 11475
|
|
},
|
|
{
|
|
"entropy": 5.3591667175292965,
|
|
"epoch": 9.511184755592378,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.305709091702865e-05,
|
|
"loss": 4.5261,
|
|
"mean_token_accuracy": 0.23594023585319518,
|
|
"num_tokens": 20918457.0,
|
|
"step": 11480
|
|
},
|
|
{
|
|
"entropy": 5.391288900375367,
|
|
"epoch": 9.515327257663628,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.30048165109431e-05,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.24189797639846802,
|
|
"num_tokens": 20928194.0,
|
|
"step": 11485
|
|
},
|
|
{
|
|
"entropy": 5.34065351486206,
|
|
"epoch": 9.51946975973488,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.295298989340196e-05,
|
|
"loss": 4.4784,
|
|
"mean_token_accuracy": 0.24825086891651155,
|
|
"num_tokens": 20938674.0,
|
|
"step": 11490
|
|
},
|
|
{
|
|
"entropy": 5.381717729568481,
|
|
"epoch": 9.52361226180613,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.290161116894518e-05,
|
|
"loss": 4.5363,
|
|
"mean_token_accuracy": 0.24679649472236634,
|
|
"num_tokens": 20947168.0,
|
|
"step": 11495
|
|
},
|
|
{
|
|
"entropy": 5.395696640014648,
|
|
"epoch": 9.527754763877383,
|
|
"grad_norm": 1.6484375,
|
|
"learning_rate": 5.285068044120927e-05,
|
|
"loss": 4.5579,
|
|
"mean_token_accuracy": 0.2449420675635338,
|
|
"num_tokens": 20956075.0,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"epoch": 9.527754763877383,
|
|
"eval_entropy": 5.199900722707004,
|
|
"eval_loss": 5.714817523956299,
|
|
"eval_mean_token_accuracy": 0.17063408001844307,
|
|
"eval_num_tokens": 20956075.0,
|
|
"eval_runtime": 2.2988,
|
|
"eval_samples_per_second": 1629.967,
|
|
"eval_steps_per_second": 204.018,
|
|
"step": 11500
|
|
},
|
|
{
|
|
"entropy": 5.403750991821289,
|
|
"epoch": 9.531897265948633,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.280019781292707e-05,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.24029452353715897,
|
|
"num_tokens": 20966187.0,
|
|
"step": 11505
|
|
},
|
|
{
|
|
"entropy": 5.417087507247925,
|
|
"epoch": 9.536039768019885,
|
|
"grad_norm": 1.6640625,
|
|
"learning_rate": 5.27501633859276e-05,
|
|
"loss": 4.5177,
|
|
"mean_token_accuracy": 0.25219099372625353,
|
|
"num_tokens": 20975865.0,
|
|
"step": 11510
|
|
},
|
|
{
|
|
"entropy": 5.290107393264771,
|
|
"epoch": 9.540182270091135,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.270057726113572e-05,
|
|
"loss": 4.4531,
|
|
"mean_token_accuracy": 0.2565054550766945,
|
|
"num_tokens": 20984907.0,
|
|
"step": 11515
|
|
},
|
|
{
|
|
"entropy": 5.352996587753296,
|
|
"epoch": 9.544324772162387,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.265143953857205e-05,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.2433927670121193,
|
|
"num_tokens": 20993915.0,
|
|
"step": 11520
|
|
},
|
|
{
|
|
"entropy": 5.36097936630249,
|
|
"epoch": 9.548467274233637,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.2602750317352814e-05,
|
|
"loss": 4.5135,
|
|
"mean_token_accuracy": 0.2472039356827736,
|
|
"num_tokens": 21002971.0,
|
|
"step": 11525
|
|
},
|
|
{
|
|
"entropy": 5.306515645980835,
|
|
"epoch": 9.552609776304887,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.25545096956894e-05,
|
|
"loss": 4.5074,
|
|
"mean_token_accuracy": 0.24945305287837982,
|
|
"num_tokens": 21012543.0,
|
|
"step": 11530
|
|
},
|
|
{
|
|
"entropy": 5.335815715789795,
|
|
"epoch": 9.55675227837614,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.250671777088849e-05,
|
|
"loss": 4.4598,
|
|
"mean_token_accuracy": 0.2457922324538231,
|
|
"num_tokens": 21021618.0,
|
|
"step": 11535
|
|
},
|
|
{
|
|
"entropy": 5.301400995254516,
|
|
"epoch": 9.56089478044739,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.245937463935159e-05,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.24398385882377624,
|
|
"num_tokens": 21030872.0,
|
|
"step": 11540
|
|
},
|
|
{
|
|
"entropy": 5.319888973236084,
|
|
"epoch": 9.565037282518642,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.241248039657496e-05,
|
|
"loss": 4.4903,
|
|
"mean_token_accuracy": 0.2474053680896759,
|
|
"num_tokens": 21039313.0,
|
|
"step": 11545
|
|
},
|
|
{
|
|
"entropy": 5.330932569503784,
|
|
"epoch": 9.569179784589892,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.236603513714943e-05,
|
|
"loss": 4.4377,
|
|
"mean_token_accuracy": 0.25019763857126237,
|
|
"num_tokens": 21048766.0,
|
|
"step": 11550
|
|
},
|
|
{
|
|
"entropy": 5.35186505317688,
|
|
"epoch": 9.573322286661144,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.232003895476016e-05,
|
|
"loss": 4.5264,
|
|
"mean_token_accuracy": 0.2542310580611229,
|
|
"num_tokens": 21058335.0,
|
|
"step": 11555
|
|
},
|
|
{
|
|
"entropy": 5.369032573699951,
|
|
"epoch": 9.577464788732394,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.227449194218648e-05,
|
|
"loss": 4.5531,
|
|
"mean_token_accuracy": 0.24706733226776123,
|
|
"num_tokens": 21066643.0,
|
|
"step": 11560
|
|
},
|
|
{
|
|
"entropy": 5.265188550949096,
|
|
"epoch": 9.581607290803646,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.222939419130167e-05,
|
|
"loss": 4.4062,
|
|
"mean_token_accuracy": 0.2610414758324623,
|
|
"num_tokens": 21075455.0,
|
|
"step": 11565
|
|
},
|
|
{
|
|
"entropy": 5.363347578048706,
|
|
"epoch": 9.585749792874896,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.218474579307282e-05,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.24461253136396408,
|
|
"num_tokens": 21085517.0,
|
|
"step": 11570
|
|
},
|
|
{
|
|
"entropy": 5.3757004737854,
|
|
"epoch": 9.589892294946148,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.214054683756069e-05,
|
|
"loss": 4.545,
|
|
"mean_token_accuracy": 0.2508238270878792,
|
|
"num_tokens": 21094469.0,
|
|
"step": 11575
|
|
},
|
|
{
|
|
"entropy": 5.419743156433105,
|
|
"epoch": 9.594034797017398,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.2096797413919344e-05,
|
|
"loss": 4.5539,
|
|
"mean_token_accuracy": 0.2414895385503769,
|
|
"num_tokens": 21104257.0,
|
|
"step": 11580
|
|
},
|
|
{
|
|
"entropy": 5.261117696762085,
|
|
"epoch": 9.59817729908865,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.205349761039613e-05,
|
|
"loss": 4.4049,
|
|
"mean_token_accuracy": 0.25863145887851713,
|
|
"num_tokens": 21112887.0,
|
|
"step": 11585
|
|
},
|
|
{
|
|
"entropy": 5.308302688598633,
|
|
"epoch": 9.6023198011599,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.201064751433156e-05,
|
|
"loss": 4.4756,
|
|
"mean_token_accuracy": 0.25426406115293504,
|
|
"num_tokens": 21121686.0,
|
|
"step": 11590
|
|
},
|
|
{
|
|
"entropy": 5.338034582138062,
|
|
"epoch": 9.606462303231151,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.19682472121589e-05,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.242756450176239,
|
|
"num_tokens": 21131291.0,
|
|
"step": 11595
|
|
},
|
|
{
|
|
"entropy": 5.3455695629119875,
|
|
"epoch": 9.610604805302403,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.192629678940421e-05,
|
|
"loss": 4.5097,
|
|
"mean_token_accuracy": 0.24333312064409257,
|
|
"num_tokens": 21140203.0,
|
|
"step": 11600
|
|
},
|
|
{
|
|
"entropy": 5.341963577270508,
|
|
"epoch": 9.614747307373653,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.188479633068607e-05,
|
|
"loss": 4.5301,
|
|
"mean_token_accuracy": 0.2525183141231537,
|
|
"num_tokens": 21148897.0,
|
|
"step": 11605
|
|
},
|
|
{
|
|
"entropy": 5.3873497486114506,
|
|
"epoch": 9.618889809444905,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.1843745919715485e-05,
|
|
"loss": 4.5493,
|
|
"mean_token_accuracy": 0.24275353252887727,
|
|
"num_tokens": 21157756.0,
|
|
"step": 11610
|
|
},
|
|
{
|
|
"entropy": 5.348913908004761,
|
|
"epoch": 9.623032311516155,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.180314563929555e-05,
|
|
"loss": 4.5205,
|
|
"mean_token_accuracy": 0.2446885034441948,
|
|
"num_tokens": 21167344.0,
|
|
"step": 11615
|
|
},
|
|
{
|
|
"entropy": 5.348416185379028,
|
|
"epoch": 9.627174813587407,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.176299557132151e-05,
|
|
"loss": 4.5647,
|
|
"mean_token_accuracy": 0.24460791945457458,
|
|
"num_tokens": 21176835.0,
|
|
"step": 11620
|
|
},
|
|
{
|
|
"entropy": 5.322459650039673,
|
|
"epoch": 9.631317315658658,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.172329579678042e-05,
|
|
"loss": 4.4004,
|
|
"mean_token_accuracy": 0.2558755472302437,
|
|
"num_tokens": 21186161.0,
|
|
"step": 11625
|
|
},
|
|
{
|
|
"entropy": 5.3969659328460695,
|
|
"epoch": 9.63545981772991,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.168404639575108e-05,
|
|
"loss": 4.5366,
|
|
"mean_token_accuracy": 0.2491963431239128,
|
|
"num_tokens": 21195428.0,
|
|
"step": 11630
|
|
},
|
|
{
|
|
"entropy": 5.404337406158447,
|
|
"epoch": 9.63960231980116,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.1645247447403826e-05,
|
|
"loss": 4.5385,
|
|
"mean_token_accuracy": 0.24814700782299043,
|
|
"num_tokens": 21203541.0,
|
|
"step": 11635
|
|
},
|
|
{
|
|
"entropy": 5.375848436355591,
|
|
"epoch": 9.64374482187241,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.1606899030000355e-05,
|
|
"loss": 4.5171,
|
|
"mean_token_accuracy": 0.2510072350502014,
|
|
"num_tokens": 21213092.0,
|
|
"step": 11640
|
|
},
|
|
{
|
|
"entropy": 5.299872875213623,
|
|
"epoch": 9.647887323943662,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.156900122089365e-05,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.24988388419151306,
|
|
"num_tokens": 21222427.0,
|
|
"step": 11645
|
|
},
|
|
{
|
|
"entropy": 5.381472444534301,
|
|
"epoch": 9.652029826014912,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.153155409652768e-05,
|
|
"loss": 4.5382,
|
|
"mean_token_accuracy": 0.24434215277433396,
|
|
"num_tokens": 21231253.0,
|
|
"step": 11650
|
|
},
|
|
{
|
|
"entropy": 5.340226650238037,
|
|
"epoch": 9.656172328086164,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.1494557732437435e-05,
|
|
"loss": 4.5854,
|
|
"mean_token_accuracy": 0.2406971871852875,
|
|
"num_tokens": 21240522.0,
|
|
"step": 11655
|
|
},
|
|
{
|
|
"entropy": 5.346747970581054,
|
|
"epoch": 9.660314830157414,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.14580122032486e-05,
|
|
"loss": 4.4791,
|
|
"mean_token_accuracy": 0.2571608886122704,
|
|
"num_tokens": 21250354.0,
|
|
"step": 11660
|
|
},
|
|
{
|
|
"entropy": 5.394043731689453,
|
|
"epoch": 9.664457332228666,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.142191758267751e-05,
|
|
"loss": 4.5203,
|
|
"mean_token_accuracy": 0.24580604285001756,
|
|
"num_tokens": 21259098.0,
|
|
"step": 11665
|
|
},
|
|
{
|
|
"entropy": 5.38980884552002,
|
|
"epoch": 9.668599834299917,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.138627394353095e-05,
|
|
"loss": 4.5771,
|
|
"mean_token_accuracy": 0.24224605709314345,
|
|
"num_tokens": 21267592.0,
|
|
"step": 11670
|
|
},
|
|
{
|
|
"entropy": 5.363176393508911,
|
|
"epoch": 9.672742336371169,
|
|
"grad_norm": 1.6015625,
|
|
"learning_rate": 5.135108135770603e-05,
|
|
"loss": 4.5423,
|
|
"mean_token_accuracy": 0.24919192790985106,
|
|
"num_tokens": 21276991.0,
|
|
"step": 11675
|
|
},
|
|
{
|
|
"entropy": 5.302528190612793,
|
|
"epoch": 9.676884838442419,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.131633989619008e-05,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.24873420000076293,
|
|
"num_tokens": 21286403.0,
|
|
"step": 11680
|
|
},
|
|
{
|
|
"entropy": 5.3596532344818115,
|
|
"epoch": 9.68102734051367,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.12820496290604e-05,
|
|
"loss": 4.5235,
|
|
"mean_token_accuracy": 0.24145499169826506,
|
|
"num_tokens": 21296433.0,
|
|
"step": 11685
|
|
},
|
|
{
|
|
"entropy": 5.359499216079712,
|
|
"epoch": 9.685169842584921,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.124821062548417e-05,
|
|
"loss": 4.5802,
|
|
"mean_token_accuracy": 0.24360184520483016,
|
|
"num_tokens": 21306074.0,
|
|
"step": 11690
|
|
},
|
|
{
|
|
"entropy": 5.385470199584961,
|
|
"epoch": 9.689312344656173,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.121482295371841e-05,
|
|
"loss": 4.5732,
|
|
"mean_token_accuracy": 0.24226777255535126,
|
|
"num_tokens": 21316235.0,
|
|
"step": 11695
|
|
},
|
|
{
|
|
"entropy": 5.380599498748779,
|
|
"epoch": 9.693454846727423,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.1181886681109676e-05,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.2338566854596138,
|
|
"num_tokens": 21326738.0,
|
|
"step": 11700
|
|
},
|
|
{
|
|
"entropy": 5.356602048873901,
|
|
"epoch": 9.697597348798674,
|
|
"grad_norm": 1.5703125,
|
|
"learning_rate": 5.1149401874094035e-05,
|
|
"loss": 4.5098,
|
|
"mean_token_accuracy": 0.2508057951927185,
|
|
"num_tokens": 21337557.0,
|
|
"step": 11705
|
|
},
|
|
{
|
|
"entropy": 5.369354486465454,
|
|
"epoch": 9.701739850869926,
|
|
"grad_norm": 1.5390625,
|
|
"learning_rate": 5.111736859819692e-05,
|
|
"loss": 4.49,
|
|
"mean_token_accuracy": 0.24905331432819366,
|
|
"num_tokens": 21347179.0,
|
|
"step": 11710
|
|
},
|
|
{
|
|
"entropy": 5.3175225257873535,
|
|
"epoch": 9.705882352941176,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.10857869180329e-05,
|
|
"loss": 4.4733,
|
|
"mean_token_accuracy": 0.2532088577747345,
|
|
"num_tokens": 21356544.0,
|
|
"step": 11715
|
|
},
|
|
{
|
|
"entropy": 5.353564691543579,
|
|
"epoch": 9.710024855012428,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.105465689730571e-05,
|
|
"loss": 4.5164,
|
|
"mean_token_accuracy": 0.25355417728424073,
|
|
"num_tokens": 21365985.0,
|
|
"step": 11720
|
|
},
|
|
{
|
|
"entropy": 5.333876466751098,
|
|
"epoch": 9.714167357083678,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.1023978598808e-05,
|
|
"loss": 4.4989,
|
|
"mean_token_accuracy": 0.2539276495575905,
|
|
"num_tokens": 21375758.0,
|
|
"step": 11725
|
|
},
|
|
{
|
|
"entropy": 5.2824784278869625,
|
|
"epoch": 9.71830985915493,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.09937520844212e-05,
|
|
"loss": 4.4652,
|
|
"mean_token_accuracy": 0.2583946019411087,
|
|
"num_tokens": 21383714.0,
|
|
"step": 11730
|
|
},
|
|
{
|
|
"entropy": 5.333975410461425,
|
|
"epoch": 9.72245236122618,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.0963977415115586e-05,
|
|
"loss": 4.5407,
|
|
"mean_token_accuracy": 0.24490050226449966,
|
|
"num_tokens": 21393261.0,
|
|
"step": 11735
|
|
},
|
|
{
|
|
"entropy": 5.327459526062012,
|
|
"epoch": 9.726594863297432,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.0934654650949854e-05,
|
|
"loss": 4.5005,
|
|
"mean_token_accuracy": 0.24632731825113297,
|
|
"num_tokens": 21402071.0,
|
|
"step": 11740
|
|
},
|
|
{
|
|
"entropy": 5.397180366516113,
|
|
"epoch": 9.730737365368682,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.090578385107121e-05,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.24504420012235642,
|
|
"num_tokens": 21411165.0,
|
|
"step": 11745
|
|
},
|
|
{
|
|
"entropy": 5.298572778701782,
|
|
"epoch": 9.734879867439934,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.0877365073715285e-05,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.24821553379297256,
|
|
"num_tokens": 21420641.0,
|
|
"step": 11750
|
|
},
|
|
{
|
|
"entropy": 5.398961687088013,
|
|
"epoch": 9.739022369511185,
|
|
"grad_norm": 1.5859375,
|
|
"learning_rate": 5.0849398376205797e-05,
|
|
"loss": 4.4908,
|
|
"mean_token_accuracy": 0.24859348088502883,
|
|
"num_tokens": 21429293.0,
|
|
"step": 11755
|
|
},
|
|
{
|
|
"entropy": 5.345803833007812,
|
|
"epoch": 9.743164871582437,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.082188381495463e-05,
|
|
"loss": 4.5073,
|
|
"mean_token_accuracy": 0.2441974624991417,
|
|
"num_tokens": 21438978.0,
|
|
"step": 11760
|
|
},
|
|
{
|
|
"entropy": 5.370188283920288,
|
|
"epoch": 9.747307373653687,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.0794821445461716e-05,
|
|
"loss": 4.4977,
|
|
"mean_token_accuracy": 0.2455075740814209,
|
|
"num_tokens": 21447321.0,
|
|
"step": 11765
|
|
},
|
|
{
|
|
"entropy": 5.329946613311767,
|
|
"epoch": 9.751449875724937,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.076821132231474e-05,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.24282742887735367,
|
|
"num_tokens": 21456221.0,
|
|
"step": 11770
|
|
},
|
|
{
|
|
"entropy": 5.365112400054931,
|
|
"epoch": 9.755592377796189,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.074205349918927e-05,
|
|
"loss": 4.5642,
|
|
"mean_token_accuracy": 0.2419198751449585,
|
|
"num_tokens": 21466123.0,
|
|
"step": 11775
|
|
},
|
|
{
|
|
"entropy": 5.373586225509643,
|
|
"epoch": 9.75973487986744,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.071634802884852e-05,
|
|
"loss": 4.549,
|
|
"mean_token_accuracy": 0.23700004816055298,
|
|
"num_tokens": 21476033.0,
|
|
"step": 11780
|
|
},
|
|
{
|
|
"entropy": 5.316982841491699,
|
|
"epoch": 9.763877381938691,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.0691094963143157e-05,
|
|
"loss": 4.4725,
|
|
"mean_token_accuracy": 0.24412640035152436,
|
|
"num_tokens": 21484393.0,
|
|
"step": 11785
|
|
},
|
|
{
|
|
"entropy": 5.401791572570801,
|
|
"epoch": 9.768019884009941,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.066629435301143e-05,
|
|
"loss": 4.566,
|
|
"mean_token_accuracy": 0.24286849200725555,
|
|
"num_tokens": 21493045.0,
|
|
"step": 11790
|
|
},
|
|
{
|
|
"entropy": 5.334913921356201,
|
|
"epoch": 9.772162386081193,
|
|
"grad_norm": 1.8515625,
|
|
"learning_rate": 5.0641946248478876e-05,
|
|
"loss": 4.4999,
|
|
"mean_token_accuracy": 0.24145723581314088,
|
|
"num_tokens": 21500913.0,
|
|
"step": 11795
|
|
},
|
|
{
|
|
"entropy": 5.286413621902466,
|
|
"epoch": 9.776304888152444,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.061805069865827e-05,
|
|
"loss": 4.4108,
|
|
"mean_token_accuracy": 0.25777134746313096,
|
|
"num_tokens": 21509444.0,
|
|
"step": 11800
|
|
},
|
|
{
|
|
"entropy": 5.399254179000854,
|
|
"epoch": 9.780447390223696,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.059460775174955e-05,
|
|
"loss": 4.5051,
|
|
"mean_token_accuracy": 0.25022095143795015,
|
|
"num_tokens": 21518805.0,
|
|
"step": 11805
|
|
},
|
|
{
|
|
"entropy": 5.336067390441895,
|
|
"epoch": 9.784589892294946,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.057161745503972e-05,
|
|
"loss": 4.5156,
|
|
"mean_token_accuracy": 0.2471814349293709,
|
|
"num_tokens": 21527354.0,
|
|
"step": 11810
|
|
},
|
|
{
|
|
"entropy": 5.454104900360107,
|
|
"epoch": 9.788732394366198,
|
|
"grad_norm": 1.7421875,
|
|
"learning_rate": 5.0549079854902665e-05,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.24743632823228837,
|
|
"num_tokens": 21537045.0,
|
|
"step": 11815
|
|
},
|
|
{
|
|
"entropy": 5.384345293045044,
|
|
"epoch": 9.792874896437448,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.052699499679925e-05,
|
|
"loss": 4.576,
|
|
"mean_token_accuracy": 0.2428390622138977,
|
|
"num_tokens": 21545975.0,
|
|
"step": 11820
|
|
},
|
|
{
|
|
"entropy": 5.385251808166504,
|
|
"epoch": 9.7970173985087,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.050536292527702e-05,
|
|
"loss": 4.5565,
|
|
"mean_token_accuracy": 0.23443491011857986,
|
|
"num_tokens": 21555309.0,
|
|
"step": 11825
|
|
},
|
|
{
|
|
"entropy": 5.353777456283569,
|
|
"epoch": 9.80115990057995,
|
|
"grad_norm": 1.5078125,
|
|
"learning_rate": 5.0484183683970235e-05,
|
|
"loss": 4.5334,
|
|
"mean_token_accuracy": 0.2476756602525711,
|
|
"num_tokens": 21565044.0,
|
|
"step": 11830
|
|
},
|
|
{
|
|
"entropy": 5.402905559539795,
|
|
"epoch": 9.8053024026512,
|
|
"grad_norm": 1.6875,
|
|
"learning_rate": 5.046345731559973e-05,
|
|
"loss": 4.5703,
|
|
"mean_token_accuracy": 0.2497891366481781,
|
|
"num_tokens": 21574158.0,
|
|
"step": 11835
|
|
},
|
|
{
|
|
"entropy": 5.3962822437286375,
|
|
"epoch": 9.809444904722453,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.044318386197286e-05,
|
|
"loss": 4.6235,
|
|
"mean_token_accuracy": 0.23485233187675475,
|
|
"num_tokens": 21584371.0,
|
|
"step": 11840
|
|
},
|
|
{
|
|
"entropy": 5.288153791427613,
|
|
"epoch": 9.813587406793703,
|
|
"grad_norm": 1.65625,
|
|
"learning_rate": 5.042336336398341e-05,
|
|
"loss": 4.4503,
|
|
"mean_token_accuracy": 0.2443375527858734,
|
|
"num_tokens": 21592693.0,
|
|
"step": 11845
|
|
},
|
|
{
|
|
"entropy": 5.410258531570435,
|
|
"epoch": 9.817729908864955,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.040399586161144e-05,
|
|
"loss": 4.6179,
|
|
"mean_token_accuracy": 0.23836424201726913,
|
|
"num_tokens": 21601952.0,
|
|
"step": 11850
|
|
},
|
|
{
|
|
"entropy": 5.382032680511474,
|
|
"epoch": 9.821872410936205,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.038508139392338e-05,
|
|
"loss": 4.5749,
|
|
"mean_token_accuracy": 0.23903208076953888,
|
|
"num_tokens": 21611493.0,
|
|
"step": 11855
|
|
},
|
|
{
|
|
"entropy": 5.396424150466919,
|
|
"epoch": 9.826014913007457,
|
|
"grad_norm": 1.609375,
|
|
"learning_rate": 5.0366619999071734e-05,
|
|
"loss": 4.5676,
|
|
"mean_token_accuracy": 0.2455991268157959,
|
|
"num_tokens": 21619698.0,
|
|
"step": 11860
|
|
},
|
|
{
|
|
"entropy": 5.397511434555054,
|
|
"epoch": 9.830157415078707,
|
|
"grad_norm": 1.59375,
|
|
"learning_rate": 5.0348611714295205e-05,
|
|
"loss": 4.5233,
|
|
"mean_token_accuracy": 0.2524207875132561,
|
|
"num_tokens": 21628789.0,
|
|
"step": 11865
|
|
},
|
|
{
|
|
"entropy": 5.342144727706909,
|
|
"epoch": 9.83429991714996,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.03310565759184e-05,
|
|
"loss": 4.5231,
|
|
"mean_token_accuracy": 0.2544507786631584,
|
|
"num_tokens": 21637928.0,
|
|
"step": 11870
|
|
},
|
|
{
|
|
"entropy": 5.361765432357788,
|
|
"epoch": 9.83844241922121,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.0313954619351996e-05,
|
|
"loss": 4.5616,
|
|
"mean_token_accuracy": 0.23837174624204635,
|
|
"num_tokens": 21646500.0,
|
|
"step": 11875
|
|
},
|
|
{
|
|
"entropy": 5.40775465965271,
|
|
"epoch": 9.842584921292461,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.029730587909253e-05,
|
|
"loss": 4.5879,
|
|
"mean_token_accuracy": 0.2496271938085556,
|
|
"num_tokens": 21655356.0,
|
|
"step": 11880
|
|
},
|
|
{
|
|
"entropy": 5.387443923950196,
|
|
"epoch": 9.846727423363712,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.028111038872228e-05,
|
|
"loss": 4.5294,
|
|
"mean_token_accuracy": 0.24442889392375947,
|
|
"num_tokens": 21664860.0,
|
|
"step": 11885
|
|
},
|
|
{
|
|
"entropy": 5.388371276855469,
|
|
"epoch": 9.850869925434964,
|
|
"grad_norm": 1.671875,
|
|
"learning_rate": 5.026536818090935e-05,
|
|
"loss": 4.5174,
|
|
"mean_token_accuracy": 0.23954141438007354,
|
|
"num_tokens": 21673638.0,
|
|
"step": 11890
|
|
},
|
|
{
|
|
"entropy": 5.354574298858642,
|
|
"epoch": 9.855012427506214,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.0250079287407486e-05,
|
|
"loss": 4.5121,
|
|
"mean_token_accuracy": 0.25032917112112046,
|
|
"num_tokens": 21682708.0,
|
|
"step": 11895
|
|
},
|
|
{
|
|
"entropy": 5.385973882675171,
|
|
"epoch": 9.859154929577464,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.023524373905606e-05,
|
|
"loss": 4.5036,
|
|
"mean_token_accuracy": 0.24748046398162843,
|
|
"num_tokens": 21692162.0,
|
|
"step": 11900
|
|
},
|
|
{
|
|
"entropy": 5.338633298873901,
|
|
"epoch": 9.863297431648716,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.0220861565779966e-05,
|
|
"loss": 4.4633,
|
|
"mean_token_accuracy": 0.25350971817970275,
|
|
"num_tokens": 21700956.0,
|
|
"step": 11905
|
|
},
|
|
{
|
|
"entropy": 5.386845684051513,
|
|
"epoch": 9.867439933719966,
|
|
"grad_norm": 1.6328125,
|
|
"learning_rate": 5.020693279658967e-05,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.24235139638185502,
|
|
"num_tokens": 21709603.0,
|
|
"step": 11910
|
|
},
|
|
{
|
|
"entropy": 5.323772382736206,
|
|
"epoch": 9.871582435791218,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.0193457459580984e-05,
|
|
"loss": 4.4928,
|
|
"mean_token_accuracy": 0.24985019862651825,
|
|
"num_tokens": 21718858.0,
|
|
"step": 11915
|
|
},
|
|
{
|
|
"entropy": 5.323409795761108,
|
|
"epoch": 9.875724937862469,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.0180435581935156e-05,
|
|
"loss": 4.4875,
|
|
"mean_token_accuracy": 0.24939571171998978,
|
|
"num_tokens": 21727863.0,
|
|
"step": 11920
|
|
},
|
|
{
|
|
"entropy": 5.433860778808594,
|
|
"epoch": 9.87986743993372,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 5.0167867189918727e-05,
|
|
"loss": 4.5404,
|
|
"mean_token_accuracy": 0.24613020867109298,
|
|
"num_tokens": 21736408.0,
|
|
"step": 11925
|
|
},
|
|
{
|
|
"entropy": 5.436592388153076,
|
|
"epoch": 9.88400994200497,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.015575230888351e-05,
|
|
"loss": 4.557,
|
|
"mean_token_accuracy": 0.23790005296468736,
|
|
"num_tokens": 21745643.0,
|
|
"step": 11930
|
|
},
|
|
{
|
|
"entropy": 5.425812005996704,
|
|
"epoch": 9.888152444076223,
|
|
"grad_norm": 1.625,
|
|
"learning_rate": 5.014409096326654e-05,
|
|
"loss": 4.6408,
|
|
"mean_token_accuracy": 0.23458787351846694,
|
|
"num_tokens": 21754768.0,
|
|
"step": 11935
|
|
},
|
|
{
|
|
"entropy": 5.31319637298584,
|
|
"epoch": 9.892294946147473,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.0132883176590055e-05,
|
|
"loss": 4.4666,
|
|
"mean_token_accuracy": 0.25435350090265274,
|
|
"num_tokens": 21764105.0,
|
|
"step": 11940
|
|
},
|
|
{
|
|
"entropy": 5.290935134887695,
|
|
"epoch": 9.896437448218723,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.0122128971461365e-05,
|
|
"loss": 4.4723,
|
|
"mean_token_accuracy": 0.250810070335865,
|
|
"num_tokens": 21773913.0,
|
|
"step": 11945
|
|
},
|
|
{
|
|
"entropy": 5.334908390045166,
|
|
"epoch": 9.900579950289975,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 5.011182836957287e-05,
|
|
"loss": 4.5132,
|
|
"mean_token_accuracy": 0.24708617627620696,
|
|
"num_tokens": 21783460.0,
|
|
"step": 11950
|
|
},
|
|
{
|
|
"entropy": 5.35028042793274,
|
|
"epoch": 9.904722452361225,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.010198139170204e-05,
|
|
"loss": 4.5598,
|
|
"mean_token_accuracy": 0.24685394018888474,
|
|
"num_tokens": 21792642.0,
|
|
"step": 11955
|
|
},
|
|
{
|
|
"entropy": 5.396007919311524,
|
|
"epoch": 9.908864954432477,
|
|
"grad_norm": 1.6171875,
|
|
"learning_rate": 5.009258805771126e-05,
|
|
"loss": 4.5242,
|
|
"mean_token_accuracy": 0.2480783134698868,
|
|
"num_tokens": 21801580.0,
|
|
"step": 11960
|
|
},
|
|
{
|
|
"entropy": 5.456486082077026,
|
|
"epoch": 9.913007456503728,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 5.008364838654795e-05,
|
|
"loss": 4.6125,
|
|
"mean_token_accuracy": 0.23612190634012223,
|
|
"num_tokens": 21810608.0,
|
|
"step": 11965
|
|
},
|
|
{
|
|
"entropy": 5.4124990940094,
|
|
"epoch": 9.91714995857498,
|
|
"grad_norm": 1.5625,
|
|
"learning_rate": 5.007516239624437e-05,
|
|
"loss": 4.5681,
|
|
"mean_token_accuracy": 0.24108296930789946,
|
|
"num_tokens": 21819757.0,
|
|
"step": 11970
|
|
},
|
|
{
|
|
"entropy": 5.359110355377197,
|
|
"epoch": 9.92129246064623,
|
|
"grad_norm": 1.578125,
|
|
"learning_rate": 5.006713010391773e-05,
|
|
"loss": 4.5274,
|
|
"mean_token_accuracy": 0.24167913794517518,
|
|
"num_tokens": 21828148.0,
|
|
"step": 11975
|
|
},
|
|
{
|
|
"entropy": 5.322265148162842,
|
|
"epoch": 9.925434962717482,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.005955152577002e-05,
|
|
"loss": 4.5456,
|
|
"mean_token_accuracy": 0.2494572654366493,
|
|
"num_tokens": 21837341.0,
|
|
"step": 11980
|
|
},
|
|
{
|
|
"entropy": 5.310735559463501,
|
|
"epoch": 9.929577464788732,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.005242667708806e-05,
|
|
"loss": 4.4619,
|
|
"mean_token_accuracy": 0.25597904473543165,
|
|
"num_tokens": 21846963.0,
|
|
"step": 11985
|
|
},
|
|
{
|
|
"entropy": 5.371295404434204,
|
|
"epoch": 9.933719966859984,
|
|
"grad_norm": 1.765625,
|
|
"learning_rate": 5.0045755572243416e-05,
|
|
"loss": 4.5069,
|
|
"mean_token_accuracy": 0.25029153674840926,
|
|
"num_tokens": 21855673.0,
|
|
"step": 11990
|
|
},
|
|
{
|
|
"entropy": 5.391796827316284,
|
|
"epoch": 9.937862468931234,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.0039538224692496e-05,
|
|
"loss": 4.4771,
|
|
"mean_token_accuracy": 0.24942177087068557,
|
|
"num_tokens": 21864934.0,
|
|
"step": 11995
|
|
},
|
|
{
|
|
"entropy": 5.377738571166992,
|
|
"epoch": 9.942004971002486,
|
|
"grad_norm": 1.546875,
|
|
"learning_rate": 5.003377464697636e-05,
|
|
"loss": 4.5351,
|
|
"mean_token_accuracy": 0.24454951137304307,
|
|
"num_tokens": 21873289.0,
|
|
"step": 12000
|
|
},
|
|
{
|
|
"epoch": 9.942004971002486,
|
|
"eval_entropy": 5.208882144773439,
|
|
"eval_loss": 5.71541690826416,
|
|
"eval_mean_token_accuracy": 0.17075487968128628,
|
|
"eval_num_tokens": 21873289.0,
|
|
"eval_runtime": 2.12,
|
|
"eval_samples_per_second": 1767.468,
|
|
"eval_steps_per_second": 221.228,
|
|
"step": 12000
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 12060,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": false
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 4840469860423680.0,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|