c375242180
Model: fpadovani/isl-latn-100mb-after-ppt-Dp-10mb-ckpt500_seed455 Source: Original Platform
19754 lines
540 KiB
JSON
19754 lines
540 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 9.990320937340805,
|
|
"eval_steps": 1000,
|
|
"global_step": 9810,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"entropy": 7.044518566131591,
|
|
"epoch": 0.005094243504839531,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 2e-06,
|
|
"loss": 6.993,
|
|
"mean_token_accuracy": 0.09492013677954673,
|
|
"num_tokens": 12235.0,
|
|
"step": 5
|
|
},
|
|
{
|
|
"entropy": 7.07644681930542,
|
|
"epoch": 0.010188487009679063,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 4.5e-06,
|
|
"loss": 7.1362,
|
|
"mean_token_accuracy": 0.09126132428646087,
|
|
"num_tokens": 24341.0,
|
|
"step": 10
|
|
},
|
|
{
|
|
"entropy": 7.072799730300903,
|
|
"epoch": 0.015282730514518594,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 7e-06,
|
|
"loss": 6.9928,
|
|
"mean_token_accuracy": 0.10187065303325653,
|
|
"num_tokens": 34505.0,
|
|
"step": 15
|
|
},
|
|
{
|
|
"entropy": 7.125888061523438,
|
|
"epoch": 0.020376974019358125,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 9.5e-06,
|
|
"loss": 7.0829,
|
|
"mean_token_accuracy": 0.10146418437361718,
|
|
"num_tokens": 45816.0,
|
|
"step": 20
|
|
},
|
|
{
|
|
"entropy": 7.176222467422486,
|
|
"epoch": 0.02547121752419766,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 1.2e-05,
|
|
"loss": 7.1033,
|
|
"mean_token_accuracy": 0.09227820709347725,
|
|
"num_tokens": 57292.0,
|
|
"step": 25
|
|
},
|
|
{
|
|
"entropy": 7.191669178009033,
|
|
"epoch": 0.030565461029037188,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 1.4500000000000002e-05,
|
|
"loss": 6.9706,
|
|
"mean_token_accuracy": 0.10464787930250168,
|
|
"num_tokens": 70047.0,
|
|
"step": 30
|
|
},
|
|
{
|
|
"entropy": 7.173120975494385,
|
|
"epoch": 0.03565970453387672,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 1.7000000000000003e-05,
|
|
"loss": 6.8924,
|
|
"mean_token_accuracy": 0.10731507688760758,
|
|
"num_tokens": 82218.0,
|
|
"step": 35
|
|
},
|
|
{
|
|
"entropy": 7.1837273120880125,
|
|
"epoch": 0.04075394803871625,
|
|
"grad_norm": 0.8359375,
|
|
"learning_rate": 1.95e-05,
|
|
"loss": 6.9774,
|
|
"mean_token_accuracy": 0.10706076249480248,
|
|
"num_tokens": 94126.0,
|
|
"step": 40
|
|
},
|
|
{
|
|
"entropy": 7.132718229293824,
|
|
"epoch": 0.04584819154355578,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 2.2e-05,
|
|
"loss": 7.0128,
|
|
"mean_token_accuracy": 0.09793755188584327,
|
|
"num_tokens": 106527.0,
|
|
"step": 45
|
|
},
|
|
{
|
|
"entropy": 7.159356594085693,
|
|
"epoch": 0.05094243504839532,
|
|
"grad_norm": 0.87890625,
|
|
"learning_rate": 2.4500000000000003e-05,
|
|
"loss": 6.9901,
|
|
"mean_token_accuracy": 0.10278031975030899,
|
|
"num_tokens": 118284.0,
|
|
"step": 50
|
|
},
|
|
{
|
|
"entropy": 7.237170743942261,
|
|
"epoch": 0.056036678553234846,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 2.7e-05,
|
|
"loss": 7.0489,
|
|
"mean_token_accuracy": 0.09143339470028877,
|
|
"num_tokens": 129462.0,
|
|
"step": 55
|
|
},
|
|
{
|
|
"entropy": 7.230800580978394,
|
|
"epoch": 0.061130922058074376,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 2.95e-05,
|
|
"loss": 7.0246,
|
|
"mean_token_accuracy": 0.094233488291502,
|
|
"num_tokens": 140488.0,
|
|
"step": 60
|
|
},
|
|
{
|
|
"entropy": 7.194861650466919,
|
|
"epoch": 0.06622516556291391,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 3.2e-05,
|
|
"loss": 7.0597,
|
|
"mean_token_accuracy": 0.0934529423713684,
|
|
"num_tokens": 151931.0,
|
|
"step": 65
|
|
},
|
|
{
|
|
"entropy": 7.164480590820313,
|
|
"epoch": 0.07131940906775344,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 3.4500000000000005e-05,
|
|
"loss": 6.9843,
|
|
"mean_token_accuracy": 0.10014167577028274,
|
|
"num_tokens": 162824.0,
|
|
"step": 70
|
|
},
|
|
{
|
|
"entropy": 7.177510499954224,
|
|
"epoch": 0.07641365257259297,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 3.7e-05,
|
|
"loss": 6.9969,
|
|
"mean_token_accuracy": 0.09918644800782203,
|
|
"num_tokens": 173502.0,
|
|
"step": 75
|
|
},
|
|
{
|
|
"entropy": 7.232845878601074,
|
|
"epoch": 0.0815078960774325,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 3.95e-05,
|
|
"loss": 6.9813,
|
|
"mean_token_accuracy": 0.10139667466282845,
|
|
"num_tokens": 183899.0,
|
|
"step": 80
|
|
},
|
|
{
|
|
"entropy": 7.129962968826294,
|
|
"epoch": 0.08660213958227203,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 4.2000000000000004e-05,
|
|
"loss": 6.9268,
|
|
"mean_token_accuracy": 0.10928690582513809,
|
|
"num_tokens": 195359.0,
|
|
"step": 85
|
|
},
|
|
{
|
|
"entropy": 7.133749294281006,
|
|
"epoch": 0.09169638308711156,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 4.45e-05,
|
|
"loss": 6.9783,
|
|
"mean_token_accuracy": 0.10235027223825455,
|
|
"num_tokens": 206472.0,
|
|
"step": 90
|
|
},
|
|
{
|
|
"entropy": 7.171773624420166,
|
|
"epoch": 0.09679062659195109,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 4.7000000000000004e-05,
|
|
"loss": 6.9618,
|
|
"mean_token_accuracy": 0.1039932630956173,
|
|
"num_tokens": 217846.0,
|
|
"step": 95
|
|
},
|
|
{
|
|
"entropy": 7.125865650177002,
|
|
"epoch": 0.10188487009679063,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 4.9500000000000004e-05,
|
|
"loss": 6.8912,
|
|
"mean_token_accuracy": 0.10703418701887131,
|
|
"num_tokens": 229036.0,
|
|
"step": 100
|
|
},
|
|
{
|
|
"entropy": 7.243703031539917,
|
|
"epoch": 0.10697911360163016,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 5.2e-05,
|
|
"loss": 7.0957,
|
|
"mean_token_accuracy": 0.09529214948415757,
|
|
"num_tokens": 239838.0,
|
|
"step": 105
|
|
},
|
|
{
|
|
"entropy": 7.230321931838989,
|
|
"epoch": 0.11207335710646969,
|
|
"grad_norm": 0.86328125,
|
|
"learning_rate": 5.45e-05,
|
|
"loss": 7.0036,
|
|
"mean_token_accuracy": 0.10142878666520119,
|
|
"num_tokens": 252006.0,
|
|
"step": 110
|
|
},
|
|
{
|
|
"entropy": 7.1257548332214355,
|
|
"epoch": 0.11716760061130922,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 5.7e-05,
|
|
"loss": 6.9558,
|
|
"mean_token_accuracy": 0.10273786783218383,
|
|
"num_tokens": 264027.0,
|
|
"step": 115
|
|
},
|
|
{
|
|
"entropy": 7.194825267791748,
|
|
"epoch": 0.12226184411614875,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 5.9499999999999996e-05,
|
|
"loss": 6.938,
|
|
"mean_token_accuracy": 0.10348320975899697,
|
|
"num_tokens": 275156.0,
|
|
"step": 120
|
|
},
|
|
{
|
|
"entropy": 7.3084108352661135,
|
|
"epoch": 0.1273560876209883,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 6.2e-05,
|
|
"loss": 6.9773,
|
|
"mean_token_accuracy": 0.10230008214712143,
|
|
"num_tokens": 286240.0,
|
|
"step": 125
|
|
},
|
|
{
|
|
"entropy": 7.107938385009765,
|
|
"epoch": 0.13245033112582782,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 6.450000000000001e-05,
|
|
"loss": 7.0216,
|
|
"mean_token_accuracy": 0.09936515465378762,
|
|
"num_tokens": 298136.0,
|
|
"step": 130
|
|
},
|
|
{
|
|
"entropy": 7.191159009933472,
|
|
"epoch": 0.13754457463066735,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 6.7e-05,
|
|
"loss": 6.9527,
|
|
"mean_token_accuracy": 0.1035711295902729,
|
|
"num_tokens": 309682.0,
|
|
"step": 135
|
|
},
|
|
{
|
|
"entropy": 7.143428659439087,
|
|
"epoch": 0.14263881813550688,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 6.950000000000001e-05,
|
|
"loss": 6.9154,
|
|
"mean_token_accuracy": 0.11162546351552009,
|
|
"num_tokens": 321330.0,
|
|
"step": 140
|
|
},
|
|
{
|
|
"entropy": 7.213088083267212,
|
|
"epoch": 0.1477330616403464,
|
|
"grad_norm": 0.92578125,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 6.9336,
|
|
"mean_token_accuracy": 0.10514834746718407,
|
|
"num_tokens": 333364.0,
|
|
"step": 145
|
|
},
|
|
{
|
|
"entropy": 7.1018579483032225,
|
|
"epoch": 0.15282730514518594,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 7.45e-05,
|
|
"loss": 6.8841,
|
|
"mean_token_accuracy": 0.10978019163012505,
|
|
"num_tokens": 345994.0,
|
|
"step": 150
|
|
},
|
|
{
|
|
"entropy": 7.230183935165405,
|
|
"epoch": 0.15792154865002547,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 7.7e-05,
|
|
"loss": 6.9735,
|
|
"mean_token_accuracy": 0.10223098248243331,
|
|
"num_tokens": 357966.0,
|
|
"step": 155
|
|
},
|
|
{
|
|
"entropy": 7.25154333114624,
|
|
"epoch": 0.163015792154865,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 7.950000000000001e-05,
|
|
"loss": 6.9546,
|
|
"mean_token_accuracy": 0.10012312904000283,
|
|
"num_tokens": 368890.0,
|
|
"step": 160
|
|
},
|
|
{
|
|
"entropy": 7.190155982971191,
|
|
"epoch": 0.16811003565970453,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 8.2e-05,
|
|
"loss": 6.8739,
|
|
"mean_token_accuracy": 0.10893138274550437,
|
|
"num_tokens": 379995.0,
|
|
"step": 165
|
|
},
|
|
{
|
|
"entropy": 7.124640941619873,
|
|
"epoch": 0.17320427916454406,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.450000000000001e-05,
|
|
"loss": 6.9154,
|
|
"mean_token_accuracy": 0.10028746277093888,
|
|
"num_tokens": 392482.0,
|
|
"step": 170
|
|
},
|
|
{
|
|
"entropy": 7.157647562026978,
|
|
"epoch": 0.1782985226693836,
|
|
"grad_norm": 0.91796875,
|
|
"learning_rate": 8.7e-05,
|
|
"loss": 6.9532,
|
|
"mean_token_accuracy": 0.10032520517706871,
|
|
"num_tokens": 404318.0,
|
|
"step": 175
|
|
},
|
|
{
|
|
"entropy": 7.221301460266114,
|
|
"epoch": 0.18339276617422312,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 8.95e-05,
|
|
"loss": 6.9243,
|
|
"mean_token_accuracy": 0.10627947300672531,
|
|
"num_tokens": 416223.0,
|
|
"step": 180
|
|
},
|
|
{
|
|
"entropy": 7.171807718276978,
|
|
"epoch": 0.18848700967906265,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 9.2e-05,
|
|
"loss": 6.8954,
|
|
"mean_token_accuracy": 0.10836421623826027,
|
|
"num_tokens": 428375.0,
|
|
"step": 185
|
|
},
|
|
{
|
|
"entropy": 7.175302124023437,
|
|
"epoch": 0.19358125318390218,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.45e-05,
|
|
"loss": 6.9459,
|
|
"mean_token_accuracy": 0.10309424996376038,
|
|
"num_tokens": 442032.0,
|
|
"step": 190
|
|
},
|
|
{
|
|
"entropy": 7.174814701080322,
|
|
"epoch": 0.1986754966887417,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 9.7e-05,
|
|
"loss": 6.8798,
|
|
"mean_token_accuracy": 0.10339492037892342,
|
|
"num_tokens": 452898.0,
|
|
"step": 195
|
|
},
|
|
{
|
|
"entropy": 7.154580116271973,
|
|
"epoch": 0.20376974019358127,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 9.95e-05,
|
|
"loss": 6.9385,
|
|
"mean_token_accuracy": 0.10731036365032195,
|
|
"num_tokens": 465037.0,
|
|
"step": 200
|
|
},
|
|
{
|
|
"entropy": 7.2330575466156,
|
|
"epoch": 0.2088639836984208,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.000102,
|
|
"loss": 6.9432,
|
|
"mean_token_accuracy": 0.09682015776634216,
|
|
"num_tokens": 477816.0,
|
|
"step": 205
|
|
},
|
|
{
|
|
"entropy": 7.174437618255615,
|
|
"epoch": 0.21395822720326033,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00010449999999999999,
|
|
"loss": 7.0381,
|
|
"mean_token_accuracy": 0.1009465865790844,
|
|
"num_tokens": 489226.0,
|
|
"step": 210
|
|
},
|
|
{
|
|
"entropy": 7.253626441955566,
|
|
"epoch": 0.21905247070809986,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000107,
|
|
"loss": 6.9718,
|
|
"mean_token_accuracy": 0.10117456316947937,
|
|
"num_tokens": 501391.0,
|
|
"step": 215
|
|
},
|
|
{
|
|
"entropy": 7.217381477355957,
|
|
"epoch": 0.22414671421293939,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0001095,
|
|
"loss": 7.0043,
|
|
"mean_token_accuracy": 0.0970021516084671,
|
|
"num_tokens": 513755.0,
|
|
"step": 220
|
|
},
|
|
{
|
|
"entropy": 7.134067535400391,
|
|
"epoch": 0.22924095771777891,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000112,
|
|
"loss": 6.8867,
|
|
"mean_token_accuracy": 0.10816463977098464,
|
|
"num_tokens": 525814.0,
|
|
"step": 225
|
|
},
|
|
{
|
|
"entropy": 7.201694059371948,
|
|
"epoch": 0.23433520122261844,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001145,
|
|
"loss": 6.9078,
|
|
"mean_token_accuracy": 0.11500680074095726,
|
|
"num_tokens": 537982.0,
|
|
"step": 230
|
|
},
|
|
{
|
|
"entropy": 7.095086097717285,
|
|
"epoch": 0.23942944472745797,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00011700000000000001,
|
|
"loss": 6.8092,
|
|
"mean_token_accuracy": 0.11077843755483627,
|
|
"num_tokens": 549795.0,
|
|
"step": 235
|
|
},
|
|
{
|
|
"entropy": 7.057131576538086,
|
|
"epoch": 0.2445236882322975,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00011949999999999999,
|
|
"loss": 6.8448,
|
|
"mean_token_accuracy": 0.10624202638864517,
|
|
"num_tokens": 561704.0,
|
|
"step": 240
|
|
},
|
|
{
|
|
"entropy": 7.160128021240235,
|
|
"epoch": 0.24961793173713703,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000122,
|
|
"loss": 6.8942,
|
|
"mean_token_accuracy": 0.10151438117027282,
|
|
"num_tokens": 574736.0,
|
|
"step": 245
|
|
},
|
|
{
|
|
"entropy": 7.185756397247315,
|
|
"epoch": 0.2547121752419766,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0001245,
|
|
"loss": 6.9737,
|
|
"mean_token_accuracy": 0.10246768370270729,
|
|
"num_tokens": 586785.0,
|
|
"step": 250
|
|
},
|
|
{
|
|
"entropy": 7.114655065536499,
|
|
"epoch": 0.2598064187468161,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.000127,
|
|
"loss": 6.8574,
|
|
"mean_token_accuracy": 0.10742970556020737,
|
|
"num_tokens": 598738.0,
|
|
"step": 255
|
|
},
|
|
{
|
|
"entropy": 7.136599349975586,
|
|
"epoch": 0.26490066225165565,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001295,
|
|
"loss": 6.8983,
|
|
"mean_token_accuracy": 0.10753594040870666,
|
|
"num_tokens": 611431.0,
|
|
"step": 260
|
|
},
|
|
{
|
|
"entropy": 7.19928994178772,
|
|
"epoch": 0.26999490575649515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000132,
|
|
"loss": 6.9071,
|
|
"mean_token_accuracy": 0.10483545064926147,
|
|
"num_tokens": 623253.0,
|
|
"step": 265
|
|
},
|
|
{
|
|
"entropy": 7.116682386398315,
|
|
"epoch": 0.2750891492613347,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00013450000000000002,
|
|
"loss": 6.9065,
|
|
"mean_token_accuracy": 0.10133408531546592,
|
|
"num_tokens": 634663.0,
|
|
"step": 270
|
|
},
|
|
{
|
|
"entropy": 7.220209312438965,
|
|
"epoch": 0.2801833927661742,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00013700000000000002,
|
|
"loss": 6.8353,
|
|
"mean_token_accuracy": 0.11484303623437882,
|
|
"num_tokens": 644578.0,
|
|
"step": 275
|
|
},
|
|
{
|
|
"entropy": 7.124927711486817,
|
|
"epoch": 0.28527763627101377,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001395,
|
|
"loss": 6.9214,
|
|
"mean_token_accuracy": 0.10066071227192878,
|
|
"num_tokens": 656226.0,
|
|
"step": 280
|
|
},
|
|
{
|
|
"entropy": 7.117072820663452,
|
|
"epoch": 0.29037187977585327,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00014199999999999998,
|
|
"loss": 6.8502,
|
|
"mean_token_accuracy": 0.10427462831139564,
|
|
"num_tokens": 668863.0,
|
|
"step": 285
|
|
},
|
|
{
|
|
"entropy": 7.118947982788086,
|
|
"epoch": 0.2954661232806928,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0001445,
|
|
"loss": 6.8088,
|
|
"mean_token_accuracy": 0.10940986797213555,
|
|
"num_tokens": 679993.0,
|
|
"step": 290
|
|
},
|
|
{
|
|
"entropy": 7.157330179214478,
|
|
"epoch": 0.30056036678553233,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000147,
|
|
"loss": 6.8971,
|
|
"mean_token_accuracy": 0.10062931329011918,
|
|
"num_tokens": 692197.0,
|
|
"step": 295
|
|
},
|
|
{
|
|
"entropy": 7.231019306182861,
|
|
"epoch": 0.3056546102903719,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0001495,
|
|
"loss": 6.9478,
|
|
"mean_token_accuracy": 0.09776001274585724,
|
|
"num_tokens": 703363.0,
|
|
"step": 300
|
|
},
|
|
{
|
|
"entropy": 7.169440603256225,
|
|
"epoch": 0.3107488537952114,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000152,
|
|
"loss": 6.9333,
|
|
"mean_token_accuracy": 0.10456420406699181,
|
|
"num_tokens": 714335.0,
|
|
"step": 305
|
|
},
|
|
{
|
|
"entropy": 7.152110528945923,
|
|
"epoch": 0.31584309730005095,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00015450000000000001,
|
|
"loss": 6.9296,
|
|
"mean_token_accuracy": 0.10086682066321373,
|
|
"num_tokens": 726638.0,
|
|
"step": 310
|
|
},
|
|
{
|
|
"entropy": 7.169084215164185,
|
|
"epoch": 0.32093734080489045,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.000157,
|
|
"loss": 6.8097,
|
|
"mean_token_accuracy": 0.1081866279244423,
|
|
"num_tokens": 737115.0,
|
|
"step": 315
|
|
},
|
|
{
|
|
"entropy": 7.0811069965362545,
|
|
"epoch": 0.32603158430973,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0001595,
|
|
"loss": 6.8297,
|
|
"mean_token_accuracy": 0.1085408754646778,
|
|
"num_tokens": 748999.0,
|
|
"step": 320
|
|
},
|
|
{
|
|
"entropy": 7.146255779266357,
|
|
"epoch": 0.33112582781456956,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000162,
|
|
"loss": 6.8223,
|
|
"mean_token_accuracy": 0.10416458621621132,
|
|
"num_tokens": 759858.0,
|
|
"step": 325
|
|
},
|
|
{
|
|
"entropy": 7.081164216995239,
|
|
"epoch": 0.33622007131940906,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016450000000000001,
|
|
"loss": 6.7889,
|
|
"mean_token_accuracy": 0.10959977135062218,
|
|
"num_tokens": 770636.0,
|
|
"step": 330
|
|
},
|
|
{
|
|
"entropy": 7.057614755630493,
|
|
"epoch": 0.3413143148242486,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016700000000000002,
|
|
"loss": 6.865,
|
|
"mean_token_accuracy": 0.10254048258066177,
|
|
"num_tokens": 783221.0,
|
|
"step": 335
|
|
},
|
|
{
|
|
"entropy": 7.082399082183838,
|
|
"epoch": 0.3464085583290881,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016950000000000003,
|
|
"loss": 6.7952,
|
|
"mean_token_accuracy": 0.10752720311284066,
|
|
"num_tokens": 793548.0,
|
|
"step": 340
|
|
},
|
|
{
|
|
"entropy": 7.148776912689209,
|
|
"epoch": 0.3515028018339277,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017199999999999998,
|
|
"loss": 6.8156,
|
|
"mean_token_accuracy": 0.10141635611653328,
|
|
"num_tokens": 805553.0,
|
|
"step": 345
|
|
},
|
|
{
|
|
"entropy": 7.078239059448242,
|
|
"epoch": 0.3565970453387672,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00017449999999999999,
|
|
"loss": 6.8902,
|
|
"mean_token_accuracy": 0.09888725131750106,
|
|
"num_tokens": 818475.0,
|
|
"step": 350
|
|
},
|
|
{
|
|
"entropy": 7.004705142974854,
|
|
"epoch": 0.36169128884360674,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000177,
|
|
"loss": 6.7757,
|
|
"mean_token_accuracy": 0.11100321486592293,
|
|
"num_tokens": 830826.0,
|
|
"step": 355
|
|
},
|
|
{
|
|
"entropy": 7.182587623596191,
|
|
"epoch": 0.36678553234844624,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0001795,
|
|
"loss": 6.8619,
|
|
"mean_token_accuracy": 0.10591038465499877,
|
|
"num_tokens": 842850.0,
|
|
"step": 360
|
|
},
|
|
{
|
|
"entropy": 7.009341144561768,
|
|
"epoch": 0.3718797758532858,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000182,
|
|
"loss": 6.8421,
|
|
"mean_token_accuracy": 0.09876091927289962,
|
|
"num_tokens": 855954.0,
|
|
"step": 365
|
|
},
|
|
{
|
|
"entropy": 7.163160562515259,
|
|
"epoch": 0.3769740193581253,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0001845,
|
|
"loss": 6.9058,
|
|
"mean_token_accuracy": 0.10104744359850884,
|
|
"num_tokens": 867986.0,
|
|
"step": 370
|
|
},
|
|
{
|
|
"entropy": 7.08941912651062,
|
|
"epoch": 0.38206826286296486,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000187,
|
|
"loss": 6.829,
|
|
"mean_token_accuracy": 0.10875942558050156,
|
|
"num_tokens": 880063.0,
|
|
"step": 375
|
|
},
|
|
{
|
|
"entropy": 7.049508047103882,
|
|
"epoch": 0.38716250636780436,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0001895,
|
|
"loss": 6.8143,
|
|
"mean_token_accuracy": 0.10336368456482888,
|
|
"num_tokens": 893320.0,
|
|
"step": 380
|
|
},
|
|
{
|
|
"entropy": 7.012372732162476,
|
|
"epoch": 0.3922567498726439,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000192,
|
|
"loss": 6.7175,
|
|
"mean_token_accuracy": 0.11578772887587548,
|
|
"num_tokens": 905118.0,
|
|
"step": 385
|
|
},
|
|
{
|
|
"entropy": 7.087364292144775,
|
|
"epoch": 0.3973509933774834,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0001945,
|
|
"loss": 6.8228,
|
|
"mean_token_accuracy": 0.10489340797066689,
|
|
"num_tokens": 916403.0,
|
|
"step": 390
|
|
},
|
|
{
|
|
"entropy": 7.149967098236084,
|
|
"epoch": 0.402445236882323,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00019700000000000002,
|
|
"loss": 6.8766,
|
|
"mean_token_accuracy": 0.10522974282503128,
|
|
"num_tokens": 927811.0,
|
|
"step": 395
|
|
},
|
|
{
|
|
"entropy": 6.91042160987854,
|
|
"epoch": 0.40753948038716253,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019950000000000002,
|
|
"loss": 6.7217,
|
|
"mean_token_accuracy": 0.10639820843935013,
|
|
"num_tokens": 940095.0,
|
|
"step": 400
|
|
},
|
|
{
|
|
"entropy": 7.022790098190308,
|
|
"epoch": 0.41263372389200204,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000202,
|
|
"loss": 6.7787,
|
|
"mean_token_accuracy": 0.11006416901946067,
|
|
"num_tokens": 951985.0,
|
|
"step": 405
|
|
},
|
|
{
|
|
"entropy": 7.055878973007202,
|
|
"epoch": 0.4177279673968416,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00020449999999999998,
|
|
"loss": 6.7782,
|
|
"mean_token_accuracy": 0.11026687249541282,
|
|
"num_tokens": 963981.0,
|
|
"step": 410
|
|
},
|
|
{
|
|
"entropy": 7.1019713401794435,
|
|
"epoch": 0.4228222109016811,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000207,
|
|
"loss": 6.8659,
|
|
"mean_token_accuracy": 0.10093940123915672,
|
|
"num_tokens": 976389.0,
|
|
"step": 415
|
|
},
|
|
{
|
|
"entropy": 7.013764762878418,
|
|
"epoch": 0.42791645440652065,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002095,
|
|
"loss": 6.7817,
|
|
"mean_token_accuracy": 0.10758809745311737,
|
|
"num_tokens": 987712.0,
|
|
"step": 420
|
|
},
|
|
{
|
|
"entropy": 7.016055631637573,
|
|
"epoch": 0.43301069791136015,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000212,
|
|
"loss": 6.7678,
|
|
"mean_token_accuracy": 0.10572115927934647,
|
|
"num_tokens": 998407.0,
|
|
"step": 425
|
|
},
|
|
{
|
|
"entropy": 7.109854650497437,
|
|
"epoch": 0.4381049414161997,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002145,
|
|
"loss": 6.8343,
|
|
"mean_token_accuracy": 0.1021016150712967,
|
|
"num_tokens": 1010275.0,
|
|
"step": 430
|
|
},
|
|
{
|
|
"entropy": 7.032284593582153,
|
|
"epoch": 0.4431991849210392,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00021700000000000002,
|
|
"loss": 6.7488,
|
|
"mean_token_accuracy": 0.1083029642701149,
|
|
"num_tokens": 1022357.0,
|
|
"step": 435
|
|
},
|
|
{
|
|
"entropy": 6.910487174987793,
|
|
"epoch": 0.44829342842587877,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002195,
|
|
"loss": 6.6801,
|
|
"mean_token_accuracy": 0.1184845358133316,
|
|
"num_tokens": 1033751.0,
|
|
"step": 440
|
|
},
|
|
{
|
|
"entropy": 7.059388017654419,
|
|
"epoch": 0.4533876719307183,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.000222,
|
|
"loss": 6.7495,
|
|
"mean_token_accuracy": 0.11273220926523209,
|
|
"num_tokens": 1045464.0,
|
|
"step": 445
|
|
},
|
|
{
|
|
"entropy": 6.905271768569946,
|
|
"epoch": 0.45848191543555783,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002245,
|
|
"loss": 6.7088,
|
|
"mean_token_accuracy": 0.11199920400977134,
|
|
"num_tokens": 1057281.0,
|
|
"step": 450
|
|
},
|
|
{
|
|
"entropy": 7.027792119979859,
|
|
"epoch": 0.46357615894039733,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00022700000000000002,
|
|
"loss": 6.642,
|
|
"mean_token_accuracy": 0.11511161923408508,
|
|
"num_tokens": 1070169.0,
|
|
"step": 455
|
|
},
|
|
{
|
|
"entropy": 6.8752524852752686,
|
|
"epoch": 0.4686704024452369,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00022950000000000002,
|
|
"loss": 6.6888,
|
|
"mean_token_accuracy": 0.12004167884588242,
|
|
"num_tokens": 1081207.0,
|
|
"step": 460
|
|
},
|
|
{
|
|
"entropy": 6.927147293090821,
|
|
"epoch": 0.4737646459500764,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00023200000000000003,
|
|
"loss": 6.7989,
|
|
"mean_token_accuracy": 0.10520728453993797,
|
|
"num_tokens": 1093846.0,
|
|
"step": 465
|
|
},
|
|
{
|
|
"entropy": 7.048350286483765,
|
|
"epoch": 0.47885888945491595,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00023449999999999998,
|
|
"loss": 6.7787,
|
|
"mean_token_accuracy": 0.10956415981054306,
|
|
"num_tokens": 1106360.0,
|
|
"step": 470
|
|
},
|
|
{
|
|
"entropy": 6.9273552894592285,
|
|
"epoch": 0.48395313295975545,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000237,
|
|
"loss": 6.6489,
|
|
"mean_token_accuracy": 0.1187779150903225,
|
|
"num_tokens": 1118042.0,
|
|
"step": 475
|
|
},
|
|
{
|
|
"entropy": 6.917570686340332,
|
|
"epoch": 0.489047376464595,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002395,
|
|
"loss": 6.6714,
|
|
"mean_token_accuracy": 0.10860469713807105,
|
|
"num_tokens": 1129625.0,
|
|
"step": 480
|
|
},
|
|
{
|
|
"entropy": 6.9747683048248295,
|
|
"epoch": 0.49414161996943456,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000242,
|
|
"loss": 6.6961,
|
|
"mean_token_accuracy": 0.11883748769760132,
|
|
"num_tokens": 1140416.0,
|
|
"step": 485
|
|
},
|
|
{
|
|
"entropy": 6.994707870483398,
|
|
"epoch": 0.49923586347427407,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002445,
|
|
"loss": 6.6787,
|
|
"mean_token_accuracy": 0.11599407494068145,
|
|
"num_tokens": 1152273.0,
|
|
"step": 490
|
|
},
|
|
{
|
|
"entropy": 6.902123832702637,
|
|
"epoch": 0.5043301069791136,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000247,
|
|
"loss": 6.6208,
|
|
"mean_token_accuracy": 0.11468892842531205,
|
|
"num_tokens": 1163621.0,
|
|
"step": 495
|
|
},
|
|
{
|
|
"entropy": 6.947891044616699,
|
|
"epoch": 0.5094243504839532,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002495,
|
|
"loss": 6.7869,
|
|
"mean_token_accuracy": 0.1068939983844757,
|
|
"num_tokens": 1174445.0,
|
|
"step": 500
|
|
},
|
|
{
|
|
"entropy": 6.92851185798645,
|
|
"epoch": 0.5145185939887926,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000252,
|
|
"loss": 6.7171,
|
|
"mean_token_accuracy": 0.11412775367498398,
|
|
"num_tokens": 1187816.0,
|
|
"step": 505
|
|
},
|
|
{
|
|
"entropy": 6.922699451446533,
|
|
"epoch": 0.5196128374936322,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002545,
|
|
"loss": 6.5966,
|
|
"mean_token_accuracy": 0.1230049654841423,
|
|
"num_tokens": 1200523.0,
|
|
"step": 510
|
|
},
|
|
{
|
|
"entropy": 6.88109769821167,
|
|
"epoch": 0.5247070809984717,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000257,
|
|
"loss": 6.6693,
|
|
"mean_token_accuracy": 0.11688895672559738,
|
|
"num_tokens": 1211841.0,
|
|
"step": 515
|
|
},
|
|
{
|
|
"entropy": 6.85207200050354,
|
|
"epoch": 0.5298013245033113,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002595,
|
|
"loss": 6.6275,
|
|
"mean_token_accuracy": 0.1219951406121254,
|
|
"num_tokens": 1224076.0,
|
|
"step": 520
|
|
},
|
|
{
|
|
"entropy": 6.885891246795654,
|
|
"epoch": 0.5348955680081507,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000262,
|
|
"loss": 6.6764,
|
|
"mean_token_accuracy": 0.1159809947013855,
|
|
"num_tokens": 1236079.0,
|
|
"step": 525
|
|
},
|
|
{
|
|
"entropy": 6.935859680175781,
|
|
"epoch": 0.5399898115129903,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026450000000000003,
|
|
"loss": 6.6735,
|
|
"mean_token_accuracy": 0.11025876700878143,
|
|
"num_tokens": 1248922.0,
|
|
"step": 530
|
|
},
|
|
{
|
|
"entropy": 6.934536552429199,
|
|
"epoch": 0.5450840550178299,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00026700000000000004,
|
|
"loss": 6.685,
|
|
"mean_token_accuracy": 0.10967916175723076,
|
|
"num_tokens": 1260471.0,
|
|
"step": 535
|
|
},
|
|
{
|
|
"entropy": 6.866807699203491,
|
|
"epoch": 0.5501782985226694,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00026950000000000005,
|
|
"loss": 6.7325,
|
|
"mean_token_accuracy": 0.11336875557899476,
|
|
"num_tokens": 1272295.0,
|
|
"step": 540
|
|
},
|
|
{
|
|
"entropy": 6.961508083343506,
|
|
"epoch": 0.5552725420275089,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00027200000000000005,
|
|
"loss": 6.7008,
|
|
"mean_token_accuracy": 0.10831127315759659,
|
|
"num_tokens": 1285056.0,
|
|
"step": 545
|
|
},
|
|
{
|
|
"entropy": 6.934025669097901,
|
|
"epoch": 0.5603667855323484,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002745,
|
|
"loss": 6.6645,
|
|
"mean_token_accuracy": 0.1119805321097374,
|
|
"num_tokens": 1296371.0,
|
|
"step": 550
|
|
},
|
|
{
|
|
"entropy": 6.887786865234375,
|
|
"epoch": 0.565461029037188,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000277,
|
|
"loss": 6.6499,
|
|
"mean_token_accuracy": 0.12152763158082962,
|
|
"num_tokens": 1308428.0,
|
|
"step": 555
|
|
},
|
|
{
|
|
"entropy": 6.899425601959228,
|
|
"epoch": 0.5705552725420275,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0002795,
|
|
"loss": 6.7455,
|
|
"mean_token_accuracy": 0.1115893378853798,
|
|
"num_tokens": 1320586.0,
|
|
"step": 560
|
|
},
|
|
{
|
|
"entropy": 6.900220680236816,
|
|
"epoch": 0.5756495160468671,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00028199999999999997,
|
|
"loss": 6.7336,
|
|
"mean_token_accuracy": 0.10702209770679474,
|
|
"num_tokens": 1332162.0,
|
|
"step": 565
|
|
},
|
|
{
|
|
"entropy": 6.933666753768921,
|
|
"epoch": 0.5807437595517065,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002845,
|
|
"loss": 6.7132,
|
|
"mean_token_accuracy": 0.11646312922239303,
|
|
"num_tokens": 1343574.0,
|
|
"step": 570
|
|
},
|
|
{
|
|
"entropy": 6.876138305664062,
|
|
"epoch": 0.5858380030565461,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000287,
|
|
"loss": 6.5788,
|
|
"mean_token_accuracy": 0.113432015478611,
|
|
"num_tokens": 1353970.0,
|
|
"step": 575
|
|
},
|
|
{
|
|
"entropy": 6.9562897205352785,
|
|
"epoch": 0.5909322465613857,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002895,
|
|
"loss": 6.7187,
|
|
"mean_token_accuracy": 0.11172034293413162,
|
|
"num_tokens": 1366324.0,
|
|
"step": 580
|
|
},
|
|
{
|
|
"entropy": 6.93915491104126,
|
|
"epoch": 0.5960264900662252,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000292,
|
|
"loss": 6.7446,
|
|
"mean_token_accuracy": 0.11083488464355469,
|
|
"num_tokens": 1378778.0,
|
|
"step": 585
|
|
},
|
|
{
|
|
"entropy": 6.843048238754273,
|
|
"epoch": 0.6011207335710647,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002945,
|
|
"loss": 6.6485,
|
|
"mean_token_accuracy": 0.11136462986469269,
|
|
"num_tokens": 1390305.0,
|
|
"step": 590
|
|
},
|
|
{
|
|
"entropy": 6.851701068878174,
|
|
"epoch": 0.6062149770759042,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000297,
|
|
"loss": 6.6333,
|
|
"mean_token_accuracy": 0.12062104865908622,
|
|
"num_tokens": 1401122.0,
|
|
"step": 595
|
|
},
|
|
{
|
|
"entropy": 6.851728773117065,
|
|
"epoch": 0.6113092205807438,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002995,
|
|
"loss": 6.6369,
|
|
"mean_token_accuracy": 0.1119437888264656,
|
|
"num_tokens": 1413598.0,
|
|
"step": 600
|
|
},
|
|
{
|
|
"entropy": 6.8240314483642575,
|
|
"epoch": 0.6164034640855833,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000302,
|
|
"loss": 6.6199,
|
|
"mean_token_accuracy": 0.11327560693025589,
|
|
"num_tokens": 1425344.0,
|
|
"step": 605
|
|
},
|
|
{
|
|
"entropy": 6.848186206817627,
|
|
"epoch": 0.6214977075904228,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003045,
|
|
"loss": 6.6384,
|
|
"mean_token_accuracy": 0.11503277495503425,
|
|
"num_tokens": 1439096.0,
|
|
"step": 610
|
|
},
|
|
{
|
|
"entropy": 6.904638338088989,
|
|
"epoch": 0.6265919510952623,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000307,
|
|
"loss": 6.7713,
|
|
"mean_token_accuracy": 0.10886242017149925,
|
|
"num_tokens": 1451207.0,
|
|
"step": 615
|
|
},
|
|
{
|
|
"entropy": 6.877414178848267,
|
|
"epoch": 0.6316861946001019,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003095,
|
|
"loss": 6.6737,
|
|
"mean_token_accuracy": 0.1112053357064724,
|
|
"num_tokens": 1463404.0,
|
|
"step": 620
|
|
},
|
|
{
|
|
"entropy": 6.744198608398437,
|
|
"epoch": 0.6367804381049414,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000312,
|
|
"loss": 6.5379,
|
|
"mean_token_accuracy": 0.12282706797122955,
|
|
"num_tokens": 1474609.0,
|
|
"step": 625
|
|
},
|
|
{
|
|
"entropy": 6.912109327316284,
|
|
"epoch": 0.6418746816097809,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003145,
|
|
"loss": 6.7093,
|
|
"mean_token_accuracy": 0.11195330247282982,
|
|
"num_tokens": 1486323.0,
|
|
"step": 630
|
|
},
|
|
{
|
|
"entropy": 6.812345170974732,
|
|
"epoch": 0.6469689251146205,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 0.000317,
|
|
"loss": 6.5772,
|
|
"mean_token_accuracy": 0.11727494150400161,
|
|
"num_tokens": 1497325.0,
|
|
"step": 635
|
|
},
|
|
{
|
|
"entropy": 6.790488815307617,
|
|
"epoch": 0.65206316861946,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003195,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.1198957234621048,
|
|
"num_tokens": 1507329.0,
|
|
"step": 640
|
|
},
|
|
{
|
|
"entropy": 6.799358463287353,
|
|
"epoch": 0.6571574121242996,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000322,
|
|
"loss": 6.5975,
|
|
"mean_token_accuracy": 0.1194250911474228,
|
|
"num_tokens": 1518927.0,
|
|
"step": 645
|
|
},
|
|
{
|
|
"entropy": 6.782226657867431,
|
|
"epoch": 0.6622516556291391,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00032450000000000003,
|
|
"loss": 6.6371,
|
|
"mean_token_accuracy": 0.11219422966241836,
|
|
"num_tokens": 1529171.0,
|
|
"step": 650
|
|
},
|
|
{
|
|
"entropy": 6.951243925094604,
|
|
"epoch": 0.6673458991339786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00032700000000000003,
|
|
"loss": 6.6753,
|
|
"mean_token_accuracy": 0.11055781468749046,
|
|
"num_tokens": 1541295.0,
|
|
"step": 655
|
|
},
|
|
{
|
|
"entropy": 6.83675708770752,
|
|
"epoch": 0.6724401426388181,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00032950000000000004,
|
|
"loss": 6.6878,
|
|
"mean_token_accuracy": 0.10897862017154694,
|
|
"num_tokens": 1553865.0,
|
|
"step": 660
|
|
},
|
|
{
|
|
"entropy": 6.816014432907105,
|
|
"epoch": 0.6775343861436577,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033200000000000005,
|
|
"loss": 6.5663,
|
|
"mean_token_accuracy": 0.11735440343618393,
|
|
"num_tokens": 1565092.0,
|
|
"step": 665
|
|
},
|
|
{
|
|
"entropy": 6.822263717651367,
|
|
"epoch": 0.6826286296484972,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00033450000000000005,
|
|
"loss": 6.6335,
|
|
"mean_token_accuracy": 0.11954260692000389,
|
|
"num_tokens": 1576170.0,
|
|
"step": 670
|
|
},
|
|
{
|
|
"entropy": 6.819930934906006,
|
|
"epoch": 0.6877228731533367,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000337,
|
|
"loss": 6.5868,
|
|
"mean_token_accuracy": 0.11839340776205062,
|
|
"num_tokens": 1588121.0,
|
|
"step": 675
|
|
},
|
|
{
|
|
"entropy": 6.731348991394043,
|
|
"epoch": 0.6928171166581762,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003395,
|
|
"loss": 6.6231,
|
|
"mean_token_accuracy": 0.1168064221739769,
|
|
"num_tokens": 1601141.0,
|
|
"step": 680
|
|
},
|
|
{
|
|
"entropy": 6.750489807128906,
|
|
"epoch": 0.6979113601630158,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000342,
|
|
"loss": 6.5861,
|
|
"mean_token_accuracy": 0.11778726801276207,
|
|
"num_tokens": 1613188.0,
|
|
"step": 685
|
|
},
|
|
{
|
|
"entropy": 6.843847274780273,
|
|
"epoch": 0.7030056036678554,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034449999999999997,
|
|
"loss": 6.6027,
|
|
"mean_token_accuracy": 0.12430845946073532,
|
|
"num_tokens": 1625889.0,
|
|
"step": 690
|
|
},
|
|
{
|
|
"entropy": 6.780045652389527,
|
|
"epoch": 0.7080998471726948,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000347,
|
|
"loss": 6.5655,
|
|
"mean_token_accuracy": 0.1163877122104168,
|
|
"num_tokens": 1636350.0,
|
|
"step": 695
|
|
},
|
|
{
|
|
"entropy": 6.62624773979187,
|
|
"epoch": 0.7131940906775344,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003495,
|
|
"loss": 6.5472,
|
|
"mean_token_accuracy": 0.1218593180179596,
|
|
"num_tokens": 1648290.0,
|
|
"step": 700
|
|
},
|
|
{
|
|
"entropy": 6.788105869293213,
|
|
"epoch": 0.7182883341823739,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000352,
|
|
"loss": 6.4555,
|
|
"mean_token_accuracy": 0.12383097037672997,
|
|
"num_tokens": 1658781.0,
|
|
"step": 705
|
|
},
|
|
{
|
|
"entropy": 6.737675666809082,
|
|
"epoch": 0.7233825776872135,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003545,
|
|
"loss": 6.5874,
|
|
"mean_token_accuracy": 0.11333777979016305,
|
|
"num_tokens": 1671779.0,
|
|
"step": 710
|
|
},
|
|
{
|
|
"entropy": 6.791052627563476,
|
|
"epoch": 0.7284768211920529,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000357,
|
|
"loss": 6.5221,
|
|
"mean_token_accuracy": 0.12146528512239456,
|
|
"num_tokens": 1683821.0,
|
|
"step": 715
|
|
},
|
|
{
|
|
"entropy": 6.62400598526001,
|
|
"epoch": 0.7335710646968925,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003595,
|
|
"loss": 6.4923,
|
|
"mean_token_accuracy": 0.12247836142778397,
|
|
"num_tokens": 1695754.0,
|
|
"step": 720
|
|
},
|
|
{
|
|
"entropy": 6.735420274734497,
|
|
"epoch": 0.738665308201732,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.000362,
|
|
"loss": 6.6048,
|
|
"mean_token_accuracy": 0.11522219553589821,
|
|
"num_tokens": 1707398.0,
|
|
"step": 725
|
|
},
|
|
{
|
|
"entropy": 6.739327764511108,
|
|
"epoch": 0.7437595517065716,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003645,
|
|
"loss": 6.5239,
|
|
"mean_token_accuracy": 0.11949873492121696,
|
|
"num_tokens": 1719315.0,
|
|
"step": 730
|
|
},
|
|
{
|
|
"entropy": 6.7130818367004395,
|
|
"epoch": 0.7488537952114112,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.000367,
|
|
"loss": 6.5089,
|
|
"mean_token_accuracy": 0.11913193985819817,
|
|
"num_tokens": 1731406.0,
|
|
"step": 735
|
|
},
|
|
{
|
|
"entropy": 6.729084157943726,
|
|
"epoch": 0.7539480387162506,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003695,
|
|
"loss": 6.5829,
|
|
"mean_token_accuracy": 0.11685697734355927,
|
|
"num_tokens": 1744941.0,
|
|
"step": 740
|
|
},
|
|
{
|
|
"entropy": 6.678062200546265,
|
|
"epoch": 0.7590422822210902,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000372,
|
|
"loss": 6.5819,
|
|
"mean_token_accuracy": 0.11202071979641914,
|
|
"num_tokens": 1757824.0,
|
|
"step": 745
|
|
},
|
|
{
|
|
"entropy": 6.774014949798584,
|
|
"epoch": 0.7641365257259297,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003745,
|
|
"loss": 6.5827,
|
|
"mean_token_accuracy": 0.11595133021473884,
|
|
"num_tokens": 1770050.0,
|
|
"step": 750
|
|
},
|
|
{
|
|
"entropy": 6.656177711486817,
|
|
"epoch": 0.7692307692307693,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000377,
|
|
"loss": 6.5539,
|
|
"mean_token_accuracy": 0.11940988376736641,
|
|
"num_tokens": 1782083.0,
|
|
"step": 755
|
|
},
|
|
{
|
|
"entropy": 6.733289003372192,
|
|
"epoch": 0.7743250127356087,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003795,
|
|
"loss": 6.4976,
|
|
"mean_token_accuracy": 0.11968936026096344,
|
|
"num_tokens": 1792812.0,
|
|
"step": 760
|
|
},
|
|
{
|
|
"entropy": 6.62746295928955,
|
|
"epoch": 0.7794192562404483,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000382,
|
|
"loss": 6.4971,
|
|
"mean_token_accuracy": 0.11665747761726379,
|
|
"num_tokens": 1804724.0,
|
|
"step": 765
|
|
},
|
|
{
|
|
"entropy": 6.635995149612427,
|
|
"epoch": 0.7845134997452878,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003845,
|
|
"loss": 6.5212,
|
|
"mean_token_accuracy": 0.11737691909074784,
|
|
"num_tokens": 1817051.0,
|
|
"step": 770
|
|
},
|
|
{
|
|
"entropy": 6.7186009883880615,
|
|
"epoch": 0.7896077432501274,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00038700000000000003,
|
|
"loss": 6.5,
|
|
"mean_token_accuracy": 0.11847119778394699,
|
|
"num_tokens": 1828328.0,
|
|
"step": 775
|
|
},
|
|
{
|
|
"entropy": 6.57848711013794,
|
|
"epoch": 0.7947019867549668,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00038950000000000003,
|
|
"loss": 6.4701,
|
|
"mean_token_accuracy": 0.1233375109732151,
|
|
"num_tokens": 1840117.0,
|
|
"step": 780
|
|
},
|
|
{
|
|
"entropy": 6.669107103347779,
|
|
"epoch": 0.7997962302598064,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039200000000000004,
|
|
"loss": 6.4462,
|
|
"mean_token_accuracy": 0.12489347085356713,
|
|
"num_tokens": 1851097.0,
|
|
"step": 785
|
|
},
|
|
{
|
|
"entropy": 6.625661754608155,
|
|
"epoch": 0.804890473764646,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00039450000000000005,
|
|
"loss": 6.5077,
|
|
"mean_token_accuracy": 0.1241062693297863,
|
|
"num_tokens": 1862282.0,
|
|
"step": 790
|
|
},
|
|
{
|
|
"entropy": 6.711694717407227,
|
|
"epoch": 0.8099847172694855,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.00039700000000000005,
|
|
"loss": 6.4885,
|
|
"mean_token_accuracy": 0.12008807882666588,
|
|
"num_tokens": 1874936.0,
|
|
"step": 795
|
|
},
|
|
{
|
|
"entropy": 6.657589626312256,
|
|
"epoch": 0.8150789607743251,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003995,
|
|
"loss": 6.5164,
|
|
"mean_token_accuracy": 0.12074018567800522,
|
|
"num_tokens": 1887429.0,
|
|
"step": 800
|
|
},
|
|
{
|
|
"entropy": 6.609248161315918,
|
|
"epoch": 0.8201732042791645,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000402,
|
|
"loss": 6.495,
|
|
"mean_token_accuracy": 0.11515450328588486,
|
|
"num_tokens": 1899378.0,
|
|
"step": 805
|
|
},
|
|
{
|
|
"entropy": 6.573548364639282,
|
|
"epoch": 0.8252674477840041,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004045,
|
|
"loss": 6.4321,
|
|
"mean_token_accuracy": 0.12534051835536958,
|
|
"num_tokens": 1910723.0,
|
|
"step": 810
|
|
},
|
|
{
|
|
"entropy": 6.696687459945679,
|
|
"epoch": 0.8303616912888436,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040699999999999997,
|
|
"loss": 6.483,
|
|
"mean_token_accuracy": 0.12311445102095604,
|
|
"num_tokens": 1921913.0,
|
|
"step": 815
|
|
},
|
|
{
|
|
"entropy": 6.580182313919067,
|
|
"epoch": 0.8354559347936832,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004095,
|
|
"loss": 6.4802,
|
|
"mean_token_accuracy": 0.12698968648910522,
|
|
"num_tokens": 1934052.0,
|
|
"step": 820
|
|
},
|
|
{
|
|
"entropy": 6.595705938339234,
|
|
"epoch": 0.8405501782985226,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000412,
|
|
"loss": 6.5471,
|
|
"mean_token_accuracy": 0.12124906629323959,
|
|
"num_tokens": 1947512.0,
|
|
"step": 825
|
|
},
|
|
{
|
|
"entropy": 6.63047308921814,
|
|
"epoch": 0.8456444218033622,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004145,
|
|
"loss": 6.4808,
|
|
"mean_token_accuracy": 0.12023026198148727,
|
|
"num_tokens": 1959569.0,
|
|
"step": 830
|
|
},
|
|
{
|
|
"entropy": 6.630491256713867,
|
|
"epoch": 0.8507386653082017,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000417,
|
|
"loss": 6.4583,
|
|
"mean_token_accuracy": 0.12822288647294044,
|
|
"num_tokens": 1970159.0,
|
|
"step": 835
|
|
},
|
|
{
|
|
"entropy": 6.557434034347534,
|
|
"epoch": 0.8558329088130413,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004195,
|
|
"loss": 6.5458,
|
|
"mean_token_accuracy": 0.12084418758749962,
|
|
"num_tokens": 1982688.0,
|
|
"step": 840
|
|
},
|
|
{
|
|
"entropy": 6.6066173076629635,
|
|
"epoch": 0.8609271523178808,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.000422,
|
|
"loss": 6.437,
|
|
"mean_token_accuracy": 0.12091387584805488,
|
|
"num_tokens": 1993733.0,
|
|
"step": 845
|
|
},
|
|
{
|
|
"entropy": 6.671035385131836,
|
|
"epoch": 0.8660213958227203,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004245,
|
|
"loss": 6.497,
|
|
"mean_token_accuracy": 0.12560601383447648,
|
|
"num_tokens": 2004880.0,
|
|
"step": 850
|
|
},
|
|
{
|
|
"entropy": 6.506956005096436,
|
|
"epoch": 0.8711156393275599,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000427,
|
|
"loss": 6.4735,
|
|
"mean_token_accuracy": 0.12167876958847046,
|
|
"num_tokens": 2017018.0,
|
|
"step": 855
|
|
},
|
|
{
|
|
"entropy": 6.637276363372803,
|
|
"epoch": 0.8762098828323994,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004295,
|
|
"loss": 6.5467,
|
|
"mean_token_accuracy": 0.11587712764739991,
|
|
"num_tokens": 2028930.0,
|
|
"step": 860
|
|
},
|
|
{
|
|
"entropy": 6.596051549911499,
|
|
"epoch": 0.8813041263372389,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.000432,
|
|
"loss": 6.4726,
|
|
"mean_token_accuracy": 0.11901551336050034,
|
|
"num_tokens": 2039846.0,
|
|
"step": 865
|
|
},
|
|
{
|
|
"entropy": 6.633983707427978,
|
|
"epoch": 0.8863983698420784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004345,
|
|
"loss": 6.4729,
|
|
"mean_token_accuracy": 0.12403136044740677,
|
|
"num_tokens": 2051021.0,
|
|
"step": 870
|
|
},
|
|
{
|
|
"entropy": 6.65854320526123,
|
|
"epoch": 0.891492613346918,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.000437,
|
|
"loss": 6.5927,
|
|
"mean_token_accuracy": 0.11336434632539749,
|
|
"num_tokens": 2064862.0,
|
|
"step": 875
|
|
},
|
|
{
|
|
"entropy": 6.497711229324341,
|
|
"epoch": 0.8965868568517575,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004395,
|
|
"loss": 6.435,
|
|
"mean_token_accuracy": 0.12588154077529906,
|
|
"num_tokens": 2076316.0,
|
|
"step": 880
|
|
},
|
|
{
|
|
"entropy": 6.637341451644898,
|
|
"epoch": 0.9016811003565971,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000442,
|
|
"loss": 6.4642,
|
|
"mean_token_accuracy": 0.12097790688276291,
|
|
"num_tokens": 2088115.0,
|
|
"step": 885
|
|
},
|
|
{
|
|
"entropy": 6.72122859954834,
|
|
"epoch": 0.9067753438614365,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004445,
|
|
"loss": 6.6047,
|
|
"mean_token_accuracy": 0.1152612641453743,
|
|
"num_tokens": 2100665.0,
|
|
"step": 890
|
|
},
|
|
{
|
|
"entropy": 6.499973011016846,
|
|
"epoch": 0.9118695873662761,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000447,
|
|
"loss": 6.4103,
|
|
"mean_token_accuracy": 0.12955493479967117,
|
|
"num_tokens": 2112231.0,
|
|
"step": 895
|
|
},
|
|
{
|
|
"entropy": 6.561792182922363,
|
|
"epoch": 0.9169638308711157,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044950000000000003,
|
|
"loss": 6.3457,
|
|
"mean_token_accuracy": 0.13369542136788368,
|
|
"num_tokens": 2123920.0,
|
|
"step": 900
|
|
},
|
|
{
|
|
"entropy": 6.54530553817749,
|
|
"epoch": 0.9220580743759552,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045200000000000004,
|
|
"loss": 6.4631,
|
|
"mean_token_accuracy": 0.11725258454680443,
|
|
"num_tokens": 2135167.0,
|
|
"step": 905
|
|
},
|
|
{
|
|
"entropy": 6.622091150283813,
|
|
"epoch": 0.9271523178807947,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00045450000000000004,
|
|
"loss": 6.4621,
|
|
"mean_token_accuracy": 0.12155643627047538,
|
|
"num_tokens": 2146809.0,
|
|
"step": 910
|
|
},
|
|
{
|
|
"entropy": 6.567164516448974,
|
|
"epoch": 0.9322465613856342,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045700000000000005,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12437484413385391,
|
|
"num_tokens": 2157784.0,
|
|
"step": 915
|
|
},
|
|
{
|
|
"entropy": 6.522310543060303,
|
|
"epoch": 0.9373408048904738,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00045950000000000006,
|
|
"loss": 6.4747,
|
|
"mean_token_accuracy": 0.12132963612675667,
|
|
"num_tokens": 2169748.0,
|
|
"step": 920
|
|
},
|
|
{
|
|
"entropy": 6.603588724136353,
|
|
"epoch": 0.9424350483953133,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000462,
|
|
"loss": 6.487,
|
|
"mean_token_accuracy": 0.12010061740875244,
|
|
"num_tokens": 2182370.0,
|
|
"step": 925
|
|
},
|
|
{
|
|
"entropy": 6.457374954223633,
|
|
"epoch": 0.9475292919001528,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004645,
|
|
"loss": 6.4562,
|
|
"mean_token_accuracy": 0.11921827495098114,
|
|
"num_tokens": 2196043.0,
|
|
"step": 930
|
|
},
|
|
{
|
|
"entropy": 6.589722347259522,
|
|
"epoch": 0.9526235354049923,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000467,
|
|
"loss": 6.4824,
|
|
"mean_token_accuracy": 0.12165994271636009,
|
|
"num_tokens": 2207240.0,
|
|
"step": 935
|
|
},
|
|
{
|
|
"entropy": 6.645488262176514,
|
|
"epoch": 0.9577177789098319,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004695,
|
|
"loss": 6.4934,
|
|
"mean_token_accuracy": 0.1202242136001587,
|
|
"num_tokens": 2219078.0,
|
|
"step": 940
|
|
},
|
|
{
|
|
"entropy": 6.446953392028808,
|
|
"epoch": 0.9628120224146715,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.000472,
|
|
"loss": 6.4912,
|
|
"mean_token_accuracy": 0.12080769687891006,
|
|
"num_tokens": 2231434.0,
|
|
"step": 945
|
|
},
|
|
{
|
|
"entropy": 6.617646169662476,
|
|
"epoch": 0.9679062659195109,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004745,
|
|
"loss": 6.4011,
|
|
"mean_token_accuracy": 0.13057347685098647,
|
|
"num_tokens": 2241375.0,
|
|
"step": 950
|
|
},
|
|
{
|
|
"entropy": 6.455522108078003,
|
|
"epoch": 0.9730005094243505,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.000477,
|
|
"loss": 6.4403,
|
|
"mean_token_accuracy": 0.12370983511209488,
|
|
"num_tokens": 2253520.0,
|
|
"step": 955
|
|
},
|
|
{
|
|
"entropy": 6.472168827056885,
|
|
"epoch": 0.97809475292919,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004795,
|
|
"loss": 6.3584,
|
|
"mean_token_accuracy": 0.12518140971660613,
|
|
"num_tokens": 2264938.0,
|
|
"step": 960
|
|
},
|
|
{
|
|
"entropy": 6.437531042098999,
|
|
"epoch": 0.9831889964340296,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.000482,
|
|
"loss": 6.4799,
|
|
"mean_token_accuracy": 0.11748291850090027,
|
|
"num_tokens": 2277306.0,
|
|
"step": 965
|
|
},
|
|
{
|
|
"entropy": 6.539975261688232,
|
|
"epoch": 0.9882832399388691,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004845,
|
|
"loss": 6.3544,
|
|
"mean_token_accuracy": 0.11762910708785057,
|
|
"num_tokens": 2288766.0,
|
|
"step": 970
|
|
},
|
|
{
|
|
"entropy": 6.488857221603394,
|
|
"epoch": 0.9933774834437086,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.000487,
|
|
"loss": 6.3959,
|
|
"mean_token_accuracy": 0.12635208591818808,
|
|
"num_tokens": 2299487.0,
|
|
"step": 975
|
|
},
|
|
{
|
|
"entropy": 6.41902174949646,
|
|
"epoch": 0.9984717269485481,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004895,
|
|
"loss": 6.3324,
|
|
"mean_token_accuracy": 0.13361692279577256,
|
|
"num_tokens": 2311302.0,
|
|
"step": 980
|
|
},
|
|
{
|
|
"entropy": 6.477914651234944,
|
|
"epoch": 1.0030565461029037,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000492,
|
|
"loss": 6.3057,
|
|
"mean_token_accuracy": 0.12617213858498466,
|
|
"num_tokens": 2321410.0,
|
|
"step": 985
|
|
},
|
|
{
|
|
"entropy": 6.458166980743409,
|
|
"epoch": 1.0081507896077433,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004945,
|
|
"loss": 6.2389,
|
|
"mean_token_accuracy": 0.1335169292986393,
|
|
"num_tokens": 2332931.0,
|
|
"step": 990
|
|
},
|
|
{
|
|
"entropy": 6.449419021606445,
|
|
"epoch": 1.0132450331125828,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000497,
|
|
"loss": 6.2496,
|
|
"mean_token_accuracy": 0.13030336275696755,
|
|
"num_tokens": 2344207.0,
|
|
"step": 995
|
|
},
|
|
{
|
|
"entropy": 6.343480253219605,
|
|
"epoch": 1.0183392766174224,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004995,
|
|
"loss": 6.2018,
|
|
"mean_token_accuracy": 0.13757490888237953,
|
|
"num_tokens": 2356470.0,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 1.0183392766174224,
|
|
"eval_entropy": 6.176096528842125,
|
|
"eval_loss": 6.380763053894043,
|
|
"eval_mean_token_accuracy": 0.13155310050940808,
|
|
"eval_num_tokens": 2356470.0,
|
|
"eval_runtime": 2.7368,
|
|
"eval_samples_per_second": 1183.865,
|
|
"eval_steps_per_second": 147.983,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"entropy": 6.544700241088867,
|
|
"epoch": 1.0234335201222617,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999997711134041,
|
|
"loss": 6.2456,
|
|
"mean_token_accuracy": 0.129035347700119,
|
|
"num_tokens": 2368744.0,
|
|
"step": 1005
|
|
},
|
|
{
|
|
"entropy": 6.383368349075317,
|
|
"epoch": 1.0285277636271013,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004999988412624068,
|
|
"loss": 6.2642,
|
|
"mean_token_accuracy": 0.12989430651068687,
|
|
"num_tokens": 2380906.0,
|
|
"step": 1010
|
|
},
|
|
{
|
|
"entropy": 6.347857427597046,
|
|
"epoch": 1.0336220071319409,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004999971961445492,
|
|
"loss": 6.2064,
|
|
"mean_token_accuracy": 0.13972920179367065,
|
|
"num_tokens": 2392358.0,
|
|
"step": 1015
|
|
},
|
|
{
|
|
"entropy": 6.39717173576355,
|
|
"epoch": 1.0387162506367804,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004999948357650613,
|
|
"loss": 6.1755,
|
|
"mean_token_accuracy": 0.13360414057970046,
|
|
"num_tokens": 2405509.0,
|
|
"step": 1020
|
|
},
|
|
{
|
|
"entropy": 6.437627983093262,
|
|
"epoch": 1.04381049414162,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004999917601314468,
|
|
"loss": 6.2318,
|
|
"mean_token_accuracy": 0.12813753336668016,
|
|
"num_tokens": 2417890.0,
|
|
"step": 1025
|
|
},
|
|
{
|
|
"entropy": 6.364025545120239,
|
|
"epoch": 1.0489047376464595,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004999879692534828,
|
|
"loss": 6.2279,
|
|
"mean_token_accuracy": 0.12833043411374093,
|
|
"num_tokens": 2429739.0,
|
|
"step": 1030
|
|
},
|
|
{
|
|
"entropy": 6.4404607772827145,
|
|
"epoch": 1.053998981151299,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999834631432208,
|
|
"loss": 6.1682,
|
|
"mean_token_accuracy": 0.13368272110819818,
|
|
"num_tokens": 2441374.0,
|
|
"step": 1035
|
|
},
|
|
{
|
|
"entropy": 6.3169389247894285,
|
|
"epoch": 1.0590932246561386,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004999782418149852,
|
|
"loss": 6.1956,
|
|
"mean_token_accuracy": 0.12824264094233512,
|
|
"num_tokens": 2452914.0,
|
|
"step": 1040
|
|
},
|
|
{
|
|
"entropy": 6.3888952255249025,
|
|
"epoch": 1.064187468160978,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004999723052853747,
|
|
"loss": 6.2455,
|
|
"mean_token_accuracy": 0.13443526551127433,
|
|
"num_tokens": 2464970.0,
|
|
"step": 1045
|
|
},
|
|
{
|
|
"entropy": 6.4613734722137455,
|
|
"epoch": 1.0692817116658175,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004999656535732615,
|
|
"loss": 6.2936,
|
|
"mean_token_accuracy": 0.12898464128375053,
|
|
"num_tokens": 2477563.0,
|
|
"step": 1050
|
|
},
|
|
{
|
|
"entropy": 6.36776294708252,
|
|
"epoch": 1.074375955170657,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004999582866997913,
|
|
"loss": 6.1428,
|
|
"mean_token_accuracy": 0.13846859708428383,
|
|
"num_tokens": 2488767.0,
|
|
"step": 1055
|
|
},
|
|
{
|
|
"entropy": 6.33557538986206,
|
|
"epoch": 1.0794701986754967,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.000499950204688383,
|
|
"loss": 6.2054,
|
|
"mean_token_accuracy": 0.13428086042404175,
|
|
"num_tokens": 2500260.0,
|
|
"step": 1060
|
|
},
|
|
{
|
|
"entropy": 6.31670503616333,
|
|
"epoch": 1.0845644421803362,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004999414075647292,
|
|
"loss": 6.1406,
|
|
"mean_token_accuracy": 0.14031125232577324,
|
|
"num_tokens": 2511581.0,
|
|
"step": 1065
|
|
},
|
|
{
|
|
"entropy": 6.433043956756592,
|
|
"epoch": 1.0896586856851758,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499931895356796,
|
|
"loss": 6.325,
|
|
"mean_token_accuracy": 0.12882162407040595,
|
|
"num_tokens": 2524185.0,
|
|
"step": 1070
|
|
},
|
|
{
|
|
"entropy": 6.333220434188843,
|
|
"epoch": 1.0947529291900153,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004999216680948223,
|
|
"loss": 6.1196,
|
|
"mean_token_accuracy": 0.13699559718370438,
|
|
"num_tokens": 2535762.0,
|
|
"step": 1075
|
|
},
|
|
{
|
|
"entropy": 6.198199892044068,
|
|
"epoch": 1.0998471726948549,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004999107258113204,
|
|
"loss": 6.0817,
|
|
"mean_token_accuracy": 0.1548200875520706,
|
|
"num_tokens": 2547566.0,
|
|
"step": 1080
|
|
},
|
|
{
|
|
"entropy": 6.360767364501953,
|
|
"epoch": 1.1049414161996944,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004998990685410759,
|
|
"loss": 6.2467,
|
|
"mean_token_accuracy": 0.12859098017215728,
|
|
"num_tokens": 2559796.0,
|
|
"step": 1085
|
|
},
|
|
{
|
|
"entropy": 6.299922847747803,
|
|
"epoch": 1.110035659704534,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004998866963211465,
|
|
"loss": 6.1665,
|
|
"mean_token_accuracy": 0.13427353277802467,
|
|
"num_tokens": 2573137.0,
|
|
"step": 1090
|
|
},
|
|
{
|
|
"entropy": 6.396093559265137,
|
|
"epoch": 1.1151299032093733,
|
|
"grad_norm": 0.90625,
|
|
"learning_rate": 0.0004998736091908636,
|
|
"loss": 6.2108,
|
|
"mean_token_accuracy": 0.1331883393228054,
|
|
"num_tokens": 2586550.0,
|
|
"step": 1095
|
|
},
|
|
{
|
|
"entropy": 6.291216564178467,
|
|
"epoch": 1.1202241467142129,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004998598071918309,
|
|
"loss": 6.2358,
|
|
"mean_token_accuracy": 0.1343692310154438,
|
|
"num_tokens": 2597666.0,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"entropy": 6.35298638343811,
|
|
"epoch": 1.1253183902190524,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004998452903679246,
|
|
"loss": 6.1061,
|
|
"mean_token_accuracy": 0.1420112669467926,
|
|
"num_tokens": 2608518.0,
|
|
"step": 1105
|
|
},
|
|
{
|
|
"entropy": 6.290657424926758,
|
|
"epoch": 1.130412633723892,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004998300587652936,
|
|
"loss": 6.1938,
|
|
"mean_token_accuracy": 0.13614270687103272,
|
|
"num_tokens": 2619766.0,
|
|
"step": 1110
|
|
},
|
|
{
|
|
"entropy": 6.3322988986969,
|
|
"epoch": 1.1355068772287316,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004998141124323586,
|
|
"loss": 6.2521,
|
|
"mean_token_accuracy": 0.133444906771183,
|
|
"num_tokens": 2632473.0,
|
|
"step": 1115
|
|
},
|
|
{
|
|
"entropy": 6.341130352020263,
|
|
"epoch": 1.1406011207335711,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004997974514198126,
|
|
"loss": 6.1981,
|
|
"mean_token_accuracy": 0.13589926660060883,
|
|
"num_tokens": 2644059.0,
|
|
"step": 1120
|
|
},
|
|
{
|
|
"entropy": 6.261853885650635,
|
|
"epoch": 1.1456953642384107,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004997800757806209,
|
|
"loss": 6.1346,
|
|
"mean_token_accuracy": 0.1369706079363823,
|
|
"num_tokens": 2655168.0,
|
|
"step": 1125
|
|
},
|
|
{
|
|
"entropy": 6.423413324356079,
|
|
"epoch": 1.15078960774325,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004997619855700203,
|
|
"loss": 6.3038,
|
|
"mean_token_accuracy": 0.13099338263273239,
|
|
"num_tokens": 2665431.0,
|
|
"step": 1130
|
|
},
|
|
{
|
|
"entropy": 6.255408096313476,
|
|
"epoch": 1.1558838512480896,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000499743180845519,
|
|
"loss": 6.1735,
|
|
"mean_token_accuracy": 0.14822513610124588,
|
|
"num_tokens": 2676942.0,
|
|
"step": 1135
|
|
},
|
|
{
|
|
"entropy": 6.41400785446167,
|
|
"epoch": 1.1609780947529291,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000499723661666897,
|
|
"loss": 6.2384,
|
|
"mean_token_accuracy": 0.13193109929561614,
|
|
"num_tokens": 2688510.0,
|
|
"step": 1140
|
|
},
|
|
{
|
|
"entropy": 6.279343891143799,
|
|
"epoch": 1.1660723382577687,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004997034280962054,
|
|
"loss": 6.2299,
|
|
"mean_token_accuracy": 0.13077231124043465,
|
|
"num_tokens": 2702140.0,
|
|
"step": 1145
|
|
},
|
|
{
|
|
"entropy": 6.252119684219361,
|
|
"epoch": 1.1711665817626082,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004996824801977663,
|
|
"loss": 6.2019,
|
|
"mean_token_accuracy": 0.13781489580869674,
|
|
"num_tokens": 2714358.0,
|
|
"step": 1150
|
|
},
|
|
{
|
|
"entropy": 6.23788161277771,
|
|
"epoch": 1.1762608252674478,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004996608180381727,
|
|
"loss": 6.1201,
|
|
"mean_token_accuracy": 0.14271433502435685,
|
|
"num_tokens": 2725477.0,
|
|
"step": 1155
|
|
},
|
|
{
|
|
"entropy": 6.350845098495483,
|
|
"epoch": 1.1813550687722874,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.000499638441686288,
|
|
"loss": 6.2527,
|
|
"mean_token_accuracy": 0.1335478439927101,
|
|
"num_tokens": 2736696.0,
|
|
"step": 1160
|
|
},
|
|
{
|
|
"entropy": 6.2867883205413815,
|
|
"epoch": 1.186449312277127,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004996153512132462,
|
|
"loss": 6.1221,
|
|
"mean_token_accuracy": 0.14645155072212218,
|
|
"num_tokens": 2747655.0,
|
|
"step": 1165
|
|
},
|
|
{
|
|
"entropy": 6.297123384475708,
|
|
"epoch": 1.1915435557819665,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004995915466924517,
|
|
"loss": 6.1563,
|
|
"mean_token_accuracy": 0.13962377607822418,
|
|
"num_tokens": 2758955.0,
|
|
"step": 1170
|
|
},
|
|
{
|
|
"entropy": 6.230033016204834,
|
|
"epoch": 1.196637799286806,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004995670281995784,
|
|
"loss": 6.0908,
|
|
"mean_token_accuracy": 0.14304591119289398,
|
|
"num_tokens": 2770395.0,
|
|
"step": 1175
|
|
},
|
|
{
|
|
"entropy": 6.255457496643066,
|
|
"epoch": 1.2017320427916454,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995417958125703,
|
|
"loss": 6.1933,
|
|
"mean_token_accuracy": 0.13439659401774406,
|
|
"num_tokens": 2783043.0,
|
|
"step": 1180
|
|
},
|
|
{
|
|
"entropy": 6.337797737121582,
|
|
"epoch": 1.206826286296485,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004995158496116402,
|
|
"loss": 6.3264,
|
|
"mean_token_accuracy": 0.127481097728014,
|
|
"num_tokens": 2795937.0,
|
|
"step": 1185
|
|
},
|
|
{
|
|
"entropy": 6.308899641036987,
|
|
"epoch": 1.2119205298013245,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004994891896792712,
|
|
"loss": 6.2637,
|
|
"mean_token_accuracy": 0.13542621061205865,
|
|
"num_tokens": 2807812.0,
|
|
"step": 1190
|
|
},
|
|
{
|
|
"entropy": 6.2987548828125,
|
|
"epoch": 1.217014773306164,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004994618161002142,
|
|
"loss": 6.1658,
|
|
"mean_token_accuracy": 0.14131661579012872,
|
|
"num_tokens": 2819326.0,
|
|
"step": 1195
|
|
},
|
|
{
|
|
"entropy": 6.282303047180176,
|
|
"epoch": 1.2221090168110036,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004994337289614893,
|
|
"loss": 6.1073,
|
|
"mean_token_accuracy": 0.1444818675518036,
|
|
"num_tokens": 2830917.0,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"entropy": 6.239668369293213,
|
|
"epoch": 1.2272032603158431,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004994049283523854,
|
|
"loss": 6.2191,
|
|
"mean_token_accuracy": 0.13711530938744546,
|
|
"num_tokens": 2842828.0,
|
|
"step": 1205
|
|
},
|
|
{
|
|
"entropy": 6.2332727909088135,
|
|
"epoch": 1.2322975038206827,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004993754143644585,
|
|
"loss": 6.0111,
|
|
"mean_token_accuracy": 0.1447136551141739,
|
|
"num_tokens": 2854423.0,
|
|
"step": 1210
|
|
},
|
|
{
|
|
"entropy": 6.247496604919434,
|
|
"epoch": 1.237391747325522,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004993451870915333,
|
|
"loss": 6.25,
|
|
"mean_token_accuracy": 0.13692307323217393,
|
|
"num_tokens": 2866032.0,
|
|
"step": 1215
|
|
},
|
|
{
|
|
"entropy": 6.267179250717163,
|
|
"epoch": 1.2424859908303616,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004993142466297016,
|
|
"loss": 6.2069,
|
|
"mean_token_accuracy": 0.14005452692508696,
|
|
"num_tokens": 2877147.0,
|
|
"step": 1220
|
|
},
|
|
{
|
|
"entropy": 6.1810588359832765,
|
|
"epoch": 1.2475802343352012,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004992825930773228,
|
|
"loss": 6.1111,
|
|
"mean_token_accuracy": 0.14460208490490914,
|
|
"num_tokens": 2888723.0,
|
|
"step": 1225
|
|
},
|
|
{
|
|
"entropy": 6.332695770263672,
|
|
"epoch": 1.2526744778400407,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004992502265350224,
|
|
"loss": 6.1751,
|
|
"mean_token_accuracy": 0.1401965655386448,
|
|
"num_tokens": 2901158.0,
|
|
"step": 1230
|
|
},
|
|
{
|
|
"entropy": 6.209536743164063,
|
|
"epoch": 1.2577687213448803,
|
|
"grad_norm": 0.8984375,
|
|
"learning_rate": 0.0004992171471056933,
|
|
"loss": 6.1942,
|
|
"mean_token_accuracy": 0.1339487463235855,
|
|
"num_tokens": 2913303.0,
|
|
"step": 1235
|
|
},
|
|
{
|
|
"entropy": 6.271416187286377,
|
|
"epoch": 1.2628629648497198,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004991833548944945,
|
|
"loss": 6.1654,
|
|
"mean_token_accuracy": 0.13918142765760422,
|
|
"num_tokens": 2924036.0,
|
|
"step": 1240
|
|
},
|
|
{
|
|
"entropy": 6.281953620910644,
|
|
"epoch": 1.2679572083545594,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004991488500088505,
|
|
"loss": 6.2536,
|
|
"mean_token_accuracy": 0.13643498942255974,
|
|
"num_tokens": 2936031.0,
|
|
"step": 1245
|
|
},
|
|
{
|
|
"entropy": 6.252941751480103,
|
|
"epoch": 1.273051451859399,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004991136325584516,
|
|
"loss": 6.131,
|
|
"mean_token_accuracy": 0.13978536278009415,
|
|
"num_tokens": 2947707.0,
|
|
"step": 1250
|
|
},
|
|
{
|
|
"entropy": 6.175567770004273,
|
|
"epoch": 1.2781456953642385,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004990777026552536,
|
|
"loss": 6.1013,
|
|
"mean_token_accuracy": 0.13597095981240273,
|
|
"num_tokens": 2959212.0,
|
|
"step": 1255
|
|
},
|
|
{
|
|
"entropy": 6.2820676326751705,
|
|
"epoch": 1.283239938869078,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004990410604134769,
|
|
"loss": 6.1171,
|
|
"mean_token_accuracy": 0.13908737003803254,
|
|
"num_tokens": 2969323.0,
|
|
"step": 1260
|
|
},
|
|
{
|
|
"entropy": 6.256225967407227,
|
|
"epoch": 1.2883341823739174,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004990037059496064,
|
|
"loss": 6.2441,
|
|
"mean_token_accuracy": 0.1359136037528515,
|
|
"num_tokens": 2981194.0,
|
|
"step": 1265
|
|
},
|
|
{
|
|
"entropy": 6.2075563907623295,
|
|
"epoch": 1.293428425878757,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004989656393823913,
|
|
"loss": 6.1429,
|
|
"mean_token_accuracy": 0.13628118112683296,
|
|
"num_tokens": 2992373.0,
|
|
"step": 1270
|
|
},
|
|
{
|
|
"entropy": 6.2464573860168455,
|
|
"epoch": 1.2985226693835965,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004989268608328443,
|
|
"loss": 6.1413,
|
|
"mean_token_accuracy": 0.13936529606580733,
|
|
"num_tokens": 3004019.0,
|
|
"step": 1275
|
|
},
|
|
{
|
|
"entropy": 6.257597303390503,
|
|
"epoch": 1.303616912888436,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004988873704242418,
|
|
"loss": 6.1344,
|
|
"mean_token_accuracy": 0.13469365164637565,
|
|
"num_tokens": 3016393.0,
|
|
"step": 1280
|
|
},
|
|
{
|
|
"entropy": 6.1419703483581545,
|
|
"epoch": 1.3087111563932756,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004988471682821229,
|
|
"loss": 6.094,
|
|
"mean_token_accuracy": 0.14097152650356293,
|
|
"num_tokens": 3027062.0,
|
|
"step": 1285
|
|
},
|
|
{
|
|
"entropy": 6.198255729675293,
|
|
"epoch": 1.3138053998981152,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004988062545342894,
|
|
"loss": 6.0993,
|
|
"mean_token_accuracy": 0.13867894187569618,
|
|
"num_tokens": 3039500.0,
|
|
"step": 1290
|
|
},
|
|
{
|
|
"entropy": 6.1662756443023685,
|
|
"epoch": 1.3188996434029547,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004987646293108056,
|
|
"loss": 6.0745,
|
|
"mean_token_accuracy": 0.14618232995271682,
|
|
"num_tokens": 3049296.0,
|
|
"step": 1295
|
|
},
|
|
{
|
|
"entropy": 6.226655530929565,
|
|
"epoch": 1.323993886907794,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004987222927439967,
|
|
"loss": 6.081,
|
|
"mean_token_accuracy": 0.1461057871580124,
|
|
"num_tokens": 3059806.0,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"entropy": 6.330883550643921,
|
|
"epoch": 1.3290881304126336,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004986792449684504,
|
|
"loss": 6.2272,
|
|
"mean_token_accuracy": 0.13858062103390695,
|
|
"num_tokens": 3072769.0,
|
|
"step": 1305
|
|
},
|
|
{
|
|
"entropy": 6.121460962295532,
|
|
"epoch": 1.3341823739174732,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004986354861210144,
|
|
"loss": 6.1846,
|
|
"mean_token_accuracy": 0.13739702403545379,
|
|
"num_tokens": 3084547.0,
|
|
"step": 1310
|
|
},
|
|
{
|
|
"entropy": 6.328854990005493,
|
|
"epoch": 1.3392766174223127,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004985910163407973,
|
|
"loss": 6.1921,
|
|
"mean_token_accuracy": 0.135743211209774,
|
|
"num_tokens": 3095905.0,
|
|
"step": 1315
|
|
},
|
|
{
|
|
"entropy": 6.283027982711792,
|
|
"epoch": 1.3443708609271523,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004985458357691675,
|
|
"loss": 6.1809,
|
|
"mean_token_accuracy": 0.13586296737194062,
|
|
"num_tokens": 3106981.0,
|
|
"step": 1320
|
|
},
|
|
{
|
|
"entropy": 6.245007801055908,
|
|
"epoch": 1.3494651044319919,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004984999445497533,
|
|
"loss": 6.1544,
|
|
"mean_token_accuracy": 0.1399984285235405,
|
|
"num_tokens": 3117916.0,
|
|
"step": 1325
|
|
},
|
|
{
|
|
"entropy": 6.248331689834595,
|
|
"epoch": 1.3545593479368314,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000498453342828442,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.13796788901090623,
|
|
"num_tokens": 3129826.0,
|
|
"step": 1330
|
|
},
|
|
{
|
|
"entropy": 6.245303010940551,
|
|
"epoch": 1.359653591441671,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004984060307533794,
|
|
"loss": 6.2508,
|
|
"mean_token_accuracy": 0.13450490757822992,
|
|
"num_tokens": 3142543.0,
|
|
"step": 1335
|
|
},
|
|
{
|
|
"entropy": 6.177638387680053,
|
|
"epoch": 1.3647478349465105,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004983580084749698,
|
|
"loss": 6.1452,
|
|
"mean_token_accuracy": 0.14966057240962982,
|
|
"num_tokens": 3154192.0,
|
|
"step": 1340
|
|
},
|
|
{
|
|
"entropy": 6.176189279556274,
|
|
"epoch": 1.36984207845135,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000498309276145875,
|
|
"loss": 6.0717,
|
|
"mean_token_accuracy": 0.1437835745513439,
|
|
"num_tokens": 3166495.0,
|
|
"step": 1345
|
|
},
|
|
{
|
|
"entropy": 6.133072471618652,
|
|
"epoch": 1.3749363219561896,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004982598339210142,
|
|
"loss": 6.2128,
|
|
"mean_token_accuracy": 0.13311799317598344,
|
|
"num_tokens": 3177798.0,
|
|
"step": 1350
|
|
},
|
|
{
|
|
"entropy": 6.342384338378906,
|
|
"epoch": 1.380030565461029,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004982096819575631,
|
|
"loss": 6.1195,
|
|
"mean_token_accuracy": 0.14083297550678253,
|
|
"num_tokens": 3189625.0,
|
|
"step": 1355
|
|
},
|
|
{
|
|
"entropy": 6.084154319763184,
|
|
"epoch": 1.3851248089658685,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004981588204149538,
|
|
"loss": 6.1154,
|
|
"mean_token_accuracy": 0.14170270413160324,
|
|
"num_tokens": 3202247.0,
|
|
"step": 1360
|
|
},
|
|
{
|
|
"entropy": 6.206786727905273,
|
|
"epoch": 1.390219052470708,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004981072494548743,
|
|
"loss": 6.0851,
|
|
"mean_token_accuracy": 0.14271499440073968,
|
|
"num_tokens": 3214566.0,
|
|
"step": 1365
|
|
},
|
|
{
|
|
"entropy": 6.2440680980682375,
|
|
"epoch": 1.3953132959755477,
|
|
"grad_norm": 0.9453125,
|
|
"learning_rate": 0.0004980549692412676,
|
|
"loss": 6.2336,
|
|
"mean_token_accuracy": 0.13270484879612923,
|
|
"num_tokens": 3228692.0,
|
|
"step": 1370
|
|
},
|
|
{
|
|
"entropy": 6.225091123580933,
|
|
"epoch": 1.4004075394803872,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004980019799403313,
|
|
"loss": 6.186,
|
|
"mean_token_accuracy": 0.13683130368590354,
|
|
"num_tokens": 3240933.0,
|
|
"step": 1375
|
|
},
|
|
{
|
|
"entropy": 6.039432382583618,
|
|
"epoch": 1.4055017829852268,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004979482817205176,
|
|
"loss": 5.9728,
|
|
"mean_token_accuracy": 0.14688338935375214,
|
|
"num_tokens": 3252007.0,
|
|
"step": 1380
|
|
},
|
|
{
|
|
"entropy": 6.2535686016082765,
|
|
"epoch": 1.410596026490066,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004978938747525319,
|
|
"loss": 6.0697,
|
|
"mean_token_accuracy": 0.14190152511000634,
|
|
"num_tokens": 3262976.0,
|
|
"step": 1385
|
|
},
|
|
{
|
|
"entropy": 6.027432537078857,
|
|
"epoch": 1.4156902699949057,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004978387592093329,
|
|
"loss": 6.0479,
|
|
"mean_token_accuracy": 0.14016258120536804,
|
|
"num_tokens": 3274352.0,
|
|
"step": 1390
|
|
},
|
|
{
|
|
"entropy": 6.254658222198486,
|
|
"epoch": 1.4207845134997452,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004977829352661318,
|
|
"loss": 6.1054,
|
|
"mean_token_accuracy": 0.1417265459895134,
|
|
"num_tokens": 3287615.0,
|
|
"step": 1395
|
|
},
|
|
{
|
|
"entropy": 6.137201547622681,
|
|
"epoch": 1.4258787570045848,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004977264031003919,
|
|
"loss": 6.1241,
|
|
"mean_token_accuracy": 0.14106439501047136,
|
|
"num_tokens": 3300086.0,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"entropy": 6.068885850906372,
|
|
"epoch": 1.4309730005094243,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004976691628918278,
|
|
"loss": 5.9912,
|
|
"mean_token_accuracy": 0.14750742614269258,
|
|
"num_tokens": 3310961.0,
|
|
"step": 1405
|
|
},
|
|
{
|
|
"entropy": 6.203730583190918,
|
|
"epoch": 1.4360672440142639,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.000497611214822405,
|
|
"loss": 6.087,
|
|
"mean_token_accuracy": 0.1431759551167488,
|
|
"num_tokens": 3322077.0,
|
|
"step": 1410
|
|
},
|
|
{
|
|
"entropy": 6.143314933776855,
|
|
"epoch": 1.4411614875191034,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004975525590763393,
|
|
"loss": 6.1219,
|
|
"mean_token_accuracy": 0.14083698242902756,
|
|
"num_tokens": 3332725.0,
|
|
"step": 1415
|
|
},
|
|
{
|
|
"entropy": 6.216067600250244,
|
|
"epoch": 1.446255731023943,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000497493195840096,
|
|
"loss": 6.1492,
|
|
"mean_token_accuracy": 0.13391322121024132,
|
|
"num_tokens": 3344267.0,
|
|
"step": 1420
|
|
},
|
|
{
|
|
"entropy": 6.208370161056519,
|
|
"epoch": 1.4513499745287826,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004974331253023898,
|
|
"loss": 6.188,
|
|
"mean_token_accuracy": 0.14164203256368638,
|
|
"num_tokens": 3356947.0,
|
|
"step": 1425
|
|
},
|
|
{
|
|
"entropy": 6.214238500595092,
|
|
"epoch": 1.4564442180336221,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004973723476541836,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.14776080027222632,
|
|
"num_tokens": 3368934.0,
|
|
"step": 1430
|
|
},
|
|
{
|
|
"entropy": 6.135909748077393,
|
|
"epoch": 1.4615384615384617,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004973108630886885,
|
|
"loss": 6.2236,
|
|
"mean_token_accuracy": 0.1354803331196308,
|
|
"num_tokens": 3380806.0,
|
|
"step": 1435
|
|
},
|
|
{
|
|
"entropy": 6.254102373123169,
|
|
"epoch": 1.466632705043301,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004972486718013626,
|
|
"loss": 6.1562,
|
|
"mean_token_accuracy": 0.1398329481482506,
|
|
"num_tokens": 3393469.0,
|
|
"step": 1440
|
|
},
|
|
{
|
|
"entropy": 6.085903930664062,
|
|
"epoch": 1.4717269485481406,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004971857739899109,
|
|
"loss": 6.0091,
|
|
"mean_token_accuracy": 0.14970263689756394,
|
|
"num_tokens": 3405667.0,
|
|
"step": 1445
|
|
},
|
|
{
|
|
"entropy": 6.230799722671509,
|
|
"epoch": 1.4768211920529801,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004971221698542842,
|
|
"loss": 6.1771,
|
|
"mean_token_accuracy": 0.13638693392276763,
|
|
"num_tokens": 3417477.0,
|
|
"step": 1450
|
|
},
|
|
{
|
|
"entropy": 6.099519538879394,
|
|
"epoch": 1.4819154355578197,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004970578595966789,
|
|
"loss": 6.1185,
|
|
"mean_token_accuracy": 0.14716447964310647,
|
|
"num_tokens": 3429395.0,
|
|
"step": 1455
|
|
},
|
|
{
|
|
"entropy": 6.139642143249512,
|
|
"epoch": 1.4870096790626592,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004969928434215358,
|
|
"loss": 6.1276,
|
|
"mean_token_accuracy": 0.14418935626745225,
|
|
"num_tokens": 3441135.0,
|
|
"step": 1460
|
|
},
|
|
{
|
|
"entropy": 6.2753511428833,
|
|
"epoch": 1.4921039225674988,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004969271215355402,
|
|
"loss": 6.1673,
|
|
"mean_token_accuracy": 0.13607125505805015,
|
|
"num_tokens": 3453712.0,
|
|
"step": 1465
|
|
},
|
|
{
|
|
"entropy": 6.181782388687134,
|
|
"epoch": 1.4971981660723381,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.0004968606941476207,
|
|
"loss": 6.1342,
|
|
"mean_token_accuracy": 0.13905424997210503,
|
|
"num_tokens": 3466346.0,
|
|
"step": 1470
|
|
},
|
|
{
|
|
"entropy": 6.174712610244751,
|
|
"epoch": 1.5022924095771777,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004967935614689485,
|
|
"loss": 6.0985,
|
|
"mean_token_accuracy": 0.1439841754734516,
|
|
"num_tokens": 3478393.0,
|
|
"step": 1475
|
|
},
|
|
{
|
|
"entropy": 6.100687503814697,
|
|
"epoch": 1.5073866530820172,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004967257237129373,
|
|
"loss": 5.9825,
|
|
"mean_token_accuracy": 0.15523604303598404,
|
|
"num_tokens": 3489631.0,
|
|
"step": 1480
|
|
},
|
|
{
|
|
"entropy": 6.101812171936035,
|
|
"epoch": 1.5124808965868568,
|
|
"grad_norm": 0.8671875,
|
|
"learning_rate": 0.0004966571810952417,
|
|
"loss": 6.0101,
|
|
"mean_token_accuracy": 0.14085201621055604,
|
|
"num_tokens": 3502403.0,
|
|
"step": 1485
|
|
},
|
|
{
|
|
"entropy": 6.044900608062744,
|
|
"epoch": 1.5175751400916964,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004965879338337577,
|
|
"loss": 5.9947,
|
|
"mean_token_accuracy": 0.15054818540811538,
|
|
"num_tokens": 3513512.0,
|
|
"step": 1490
|
|
},
|
|
{
|
|
"entropy": 6.170858907699585,
|
|
"epoch": 1.522669383596536,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004965179821486205,
|
|
"loss": 6.1728,
|
|
"mean_token_accuracy": 0.13760660737752914,
|
|
"num_tokens": 3525670.0,
|
|
"step": 1495
|
|
},
|
|
{
|
|
"entropy": 6.141346740722656,
|
|
"epoch": 1.5277636271013755,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004964473262622054,
|
|
"loss": 6.0793,
|
|
"mean_token_accuracy": 0.1404211476445198,
|
|
"num_tokens": 3537634.0,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"entropy": 6.092041826248169,
|
|
"epoch": 1.532857870606215,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000496375966399126,
|
|
"loss": 6.0136,
|
|
"mean_token_accuracy": 0.1455122373998165,
|
|
"num_tokens": 3549344.0,
|
|
"step": 1505
|
|
},
|
|
{
|
|
"entropy": 6.159336233139038,
|
|
"epoch": 1.5379521141110546,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000496303902786234,
|
|
"loss": 6.1607,
|
|
"mean_token_accuracy": 0.14189588725566865,
|
|
"num_tokens": 3563193.0,
|
|
"step": 1510
|
|
},
|
|
{
|
|
"entropy": 6.0729227542877195,
|
|
"epoch": 1.5430463576158941,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004962311356526181,
|
|
"loss": 6.0882,
|
|
"mean_token_accuracy": 0.14001245200634002,
|
|
"num_tokens": 3574304.0,
|
|
"step": 1515
|
|
},
|
|
{
|
|
"entropy": 6.226966428756714,
|
|
"epoch": 1.5481406011207337,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004961576652296036,
|
|
"loss": 5.9942,
|
|
"mean_token_accuracy": 0.14970892891287804,
|
|
"num_tokens": 3586396.0,
|
|
"step": 1520
|
|
},
|
|
{
|
|
"entropy": 5.996706819534301,
|
|
"epoch": 1.5532348446255733,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004960834917507516,
|
|
"loss": 5.986,
|
|
"mean_token_accuracy": 0.1510669320821762,
|
|
"num_tokens": 3597945.0,
|
|
"step": 1525
|
|
},
|
|
{
|
|
"entropy": 6.161891603469849,
|
|
"epoch": 1.5583290881304126,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004960086154518578,
|
|
"loss": 6.0987,
|
|
"mean_token_accuracy": 0.14722763895988464,
|
|
"num_tokens": 3610378.0,
|
|
"step": 1530
|
|
},
|
|
{
|
|
"entropy": 6.076696491241455,
|
|
"epoch": 1.5634233316352522,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004959330365709528,
|
|
"loss": 6.0258,
|
|
"mean_token_accuracy": 0.1500461980700493,
|
|
"num_tokens": 3621768.0,
|
|
"step": 1535
|
|
},
|
|
{
|
|
"entropy": 6.105367517471313,
|
|
"epoch": 1.5685175751400917,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0004958567553483003,
|
|
"loss": 6.0417,
|
|
"mean_token_accuracy": 0.14288988560438157,
|
|
"num_tokens": 3634473.0,
|
|
"step": 1540
|
|
},
|
|
{
|
|
"entropy": 6.024158382415772,
|
|
"epoch": 1.5736118186449313,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004957797720263967,
|
|
"loss": 5.9167,
|
|
"mean_token_accuracy": 0.1528099149465561,
|
|
"num_tokens": 3644499.0,
|
|
"step": 1545
|
|
},
|
|
{
|
|
"entropy": 6.096716403961182,
|
|
"epoch": 1.5787060621497706,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004957020868499706,
|
|
"loss": 6.0055,
|
|
"mean_token_accuracy": 0.14677556455135346,
|
|
"num_tokens": 3655807.0,
|
|
"step": 1550
|
|
},
|
|
{
|
|
"entropy": 6.121523046493531,
|
|
"epoch": 1.5838003056546102,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004956237000659815,
|
|
"loss": 5.9407,
|
|
"mean_token_accuracy": 0.1559087172150612,
|
|
"num_tokens": 3667301.0,
|
|
"step": 1555
|
|
},
|
|
{
|
|
"entropy": 5.960540866851806,
|
|
"epoch": 1.5888945491594497,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004955446119236195,
|
|
"loss": 6.0787,
|
|
"mean_token_accuracy": 0.13644454255700111,
|
|
"num_tokens": 3679448.0,
|
|
"step": 1560
|
|
},
|
|
{
|
|
"entropy": 6.185535717010498,
|
|
"epoch": 1.5939887926642893,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004954648226743043,
|
|
"loss": 6.0217,
|
|
"mean_token_accuracy": 0.15028504878282548,
|
|
"num_tokens": 3690985.0,
|
|
"step": 1565
|
|
},
|
|
{
|
|
"entropy": 6.071138954162597,
|
|
"epoch": 1.5990830361691288,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004953843325716841,
|
|
"loss": 6.0883,
|
|
"mean_token_accuracy": 0.14665026739239692,
|
|
"num_tokens": 3703677.0,
|
|
"step": 1570
|
|
},
|
|
{
|
|
"entropy": 6.187681531906128,
|
|
"epoch": 1.6041772796739684,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0004953031418716356,
|
|
"loss": 6.0156,
|
|
"mean_token_accuracy": 0.15277430415153503,
|
|
"num_tokens": 3715429.0,
|
|
"step": 1575
|
|
},
|
|
{
|
|
"entropy": 6.00174241065979,
|
|
"epoch": 1.609271523178808,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.0004952212508322623,
|
|
"loss": 6.0722,
|
|
"mean_token_accuracy": 0.14784569218754767,
|
|
"num_tokens": 3727663.0,
|
|
"step": 1580
|
|
},
|
|
{
|
|
"entropy": 6.087293577194214,
|
|
"epoch": 1.6143657666836475,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004951386597138943,
|
|
"loss": 5.9923,
|
|
"mean_token_accuracy": 0.14931108802556992,
|
|
"num_tokens": 3739585.0,
|
|
"step": 1585
|
|
},
|
|
{
|
|
"entropy": 6.109324932098389,
|
|
"epoch": 1.619460010188487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004950553687790871,
|
|
"loss": 6.1311,
|
|
"mean_token_accuracy": 0.14180412590503694,
|
|
"num_tokens": 3751382.0,
|
|
"step": 1590
|
|
},
|
|
{
|
|
"entropy": 6.093611574172973,
|
|
"epoch": 1.6245542536933266,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004949713782926208,
|
|
"loss": 6.0117,
|
|
"mean_token_accuracy": 0.15391514897346498,
|
|
"num_tokens": 3762520.0,
|
|
"step": 1595
|
|
},
|
|
{
|
|
"entropy": 6.0834370136260985,
|
|
"epoch": 1.6296484971981662,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004948866885214996,
|
|
"loss": 5.9934,
|
|
"mean_token_accuracy": 0.15164291858673096,
|
|
"num_tokens": 3773821.0,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"entropy": 6.13722333908081,
|
|
"epoch": 1.6347427407030057,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004948012997349506,
|
|
"loss": 6.0664,
|
|
"mean_token_accuracy": 0.1453387849032879,
|
|
"num_tokens": 3785767.0,
|
|
"step": 1605
|
|
},
|
|
{
|
|
"entropy": 6.08644847869873,
|
|
"epoch": 1.6398369842078453,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004947152122044232,
|
|
"loss": 6.0955,
|
|
"mean_token_accuracy": 0.14098975509405137,
|
|
"num_tokens": 3796702.0,
|
|
"step": 1610
|
|
},
|
|
{
|
|
"entropy": 6.107085466384888,
|
|
"epoch": 1.6449312277126846,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004946284262035875,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.14310370981693268,
|
|
"num_tokens": 3808757.0,
|
|
"step": 1615
|
|
},
|
|
{
|
|
"entropy": 6.019505548477173,
|
|
"epoch": 1.6500254712175242,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000494540942008335,
|
|
"loss": 5.9833,
|
|
"mean_token_accuracy": 0.14864621683955193,
|
|
"num_tokens": 3819804.0,
|
|
"step": 1620
|
|
},
|
|
{
|
|
"entropy": 6.1659170627594,
|
|
"epoch": 1.6551197147223637,
|
|
"grad_norm": 0.90234375,
|
|
"learning_rate": 0.000494452759896776,
|
|
"loss": 6.0245,
|
|
"mean_token_accuracy": 0.14918728172779083,
|
|
"num_tokens": 3831877.0,
|
|
"step": 1625
|
|
},
|
|
{
|
|
"entropy": 6.029467582702637,
|
|
"epoch": 1.6602139582272033,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004943638801492396,
|
|
"loss": 5.9882,
|
|
"mean_token_accuracy": 0.14464981853961945,
|
|
"num_tokens": 3843356.0,
|
|
"step": 1630
|
|
},
|
|
{
|
|
"entropy": 6.087781381607056,
|
|
"epoch": 1.6653082017320426,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004942743030482728,
|
|
"loss": 6.0172,
|
|
"mean_token_accuracy": 0.14597421437501906,
|
|
"num_tokens": 3854779.0,
|
|
"step": 1635
|
|
},
|
|
{
|
|
"entropy": 6.019084644317627,
|
|
"epoch": 1.6704024452368822,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004941840288786397,
|
|
"loss": 5.9706,
|
|
"mean_token_accuracy": 0.15264465063810348,
|
|
"num_tokens": 3867309.0,
|
|
"step": 1640
|
|
},
|
|
{
|
|
"entropy": 6.110167121887207,
|
|
"epoch": 1.6754966887417218,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004940930579273198,
|
|
"loss": 6.0627,
|
|
"mean_token_accuracy": 0.14825674444437026,
|
|
"num_tokens": 3879341.0,
|
|
"step": 1645
|
|
},
|
|
{
|
|
"entropy": 6.112421607971191,
|
|
"epoch": 1.6805909322465613,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004940013904835079,
|
|
"loss": 5.9514,
|
|
"mean_token_accuracy": 0.15374316275119781,
|
|
"num_tokens": 3890639.0,
|
|
"step": 1650
|
|
},
|
|
{
|
|
"entropy": 6.03355040550232,
|
|
"epoch": 1.6856851757514009,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004939090268386132,
|
|
"loss": 6.0057,
|
|
"mean_token_accuracy": 0.1441144548356533,
|
|
"num_tokens": 3904185.0,
|
|
"step": 1655
|
|
},
|
|
{
|
|
"entropy": 6.034610319137573,
|
|
"epoch": 1.6907794192562404,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004938159672862578,
|
|
"loss": 5.9991,
|
|
"mean_token_accuracy": 0.14242151454091073,
|
|
"num_tokens": 3917137.0,
|
|
"step": 1660
|
|
},
|
|
{
|
|
"entropy": 6.073326921463012,
|
|
"epoch": 1.69587366276108,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004937222121222763,
|
|
"loss": 6.0352,
|
|
"mean_token_accuracy": 0.14397113993763924,
|
|
"num_tokens": 3929911.0,
|
|
"step": 1665
|
|
},
|
|
{
|
|
"entropy": 6.113371801376343,
|
|
"epoch": 1.7009679062659195,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004936277616447144,
|
|
"loss": 6.0705,
|
|
"mean_token_accuracy": 0.13673104122281074,
|
|
"num_tokens": 3941242.0,
|
|
"step": 1670
|
|
},
|
|
{
|
|
"entropy": 6.121015882492065,
|
|
"epoch": 1.706062149770759,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004935326161538281,
|
|
"loss": 6.032,
|
|
"mean_token_accuracy": 0.14769989401102065,
|
|
"num_tokens": 3952464.0,
|
|
"step": 1675
|
|
},
|
|
{
|
|
"entropy": 5.96496729850769,
|
|
"epoch": 1.7111563932755987,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004934367759520834,
|
|
"loss": 5.9828,
|
|
"mean_token_accuracy": 0.14930499494075775,
|
|
"num_tokens": 3965479.0,
|
|
"step": 1680
|
|
},
|
|
{
|
|
"entropy": 6.063432741165161,
|
|
"epoch": 1.7162506367804382,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004933402413441541,
|
|
"loss": 5.9945,
|
|
"mean_token_accuracy": 0.1519572079181671,
|
|
"num_tokens": 3978195.0,
|
|
"step": 1685
|
|
},
|
|
{
|
|
"entropy": 6.137292766571045,
|
|
"epoch": 1.7213448802852778,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004932430126369221,
|
|
"loss": 6.1009,
|
|
"mean_token_accuracy": 0.1380507230758667,
|
|
"num_tokens": 3989373.0,
|
|
"step": 1690
|
|
},
|
|
{
|
|
"entropy": 5.998342800140381,
|
|
"epoch": 1.7264391237901173,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004931450901394753,
|
|
"loss": 6.0126,
|
|
"mean_token_accuracy": 0.14947347193956376,
|
|
"num_tokens": 4000860.0,
|
|
"step": 1695
|
|
},
|
|
{
|
|
"entropy": 6.049466371536255,
|
|
"epoch": 1.7315333672949567,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004930464741631073,
|
|
"loss": 5.9871,
|
|
"mean_token_accuracy": 0.14549367874860764,
|
|
"num_tokens": 4012035.0,
|
|
"step": 1700
|
|
},
|
|
{
|
|
"entropy": 6.02332911491394,
|
|
"epoch": 1.7366276107997962,
|
|
"grad_norm": 0.921875,
|
|
"learning_rate": 0.0004929471650213167,
|
|
"loss": 5.9824,
|
|
"mean_token_accuracy": 0.14759661108255387,
|
|
"num_tokens": 4024490.0,
|
|
"step": 1705
|
|
},
|
|
{
|
|
"entropy": 6.1991688251495365,
|
|
"epoch": 1.7417218543046358,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004928471630298051,
|
|
"loss": 6.0864,
|
|
"mean_token_accuracy": 0.14478200078010559,
|
|
"num_tokens": 4036277.0,
|
|
"step": 1710
|
|
},
|
|
{
|
|
"entropy": 5.91363377571106,
|
|
"epoch": 1.7468160978094753,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004927464685064767,
|
|
"loss": 5.8765,
|
|
"mean_token_accuracy": 0.15802925825119019,
|
|
"num_tokens": 4047734.0,
|
|
"step": 1715
|
|
},
|
|
{
|
|
"entropy": 5.916611814498902,
|
|
"epoch": 1.7519103413143147,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004926450817714376,
|
|
"loss": 5.89,
|
|
"mean_token_accuracy": 0.15395067781209945,
|
|
"num_tokens": 4059037.0,
|
|
"step": 1720
|
|
},
|
|
{
|
|
"entropy": 5.992276859283447,
|
|
"epoch": 1.7570045848191542,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004925430031469941,
|
|
"loss": 5.9661,
|
|
"mean_token_accuracy": 0.14739770889282228,
|
|
"num_tokens": 4070795.0,
|
|
"step": 1725
|
|
},
|
|
{
|
|
"entropy": 6.04740948677063,
|
|
"epoch": 1.7620988283239938,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004924402329576522,
|
|
"loss": 5.815,
|
|
"mean_token_accuracy": 0.16750310882925987,
|
|
"num_tokens": 4082661.0,
|
|
"step": 1730
|
|
},
|
|
{
|
|
"entropy": 5.938603115081787,
|
|
"epoch": 1.7671930718288333,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004923367715301164,
|
|
"loss": 5.9348,
|
|
"mean_token_accuracy": 0.15013253837823867,
|
|
"num_tokens": 4093151.0,
|
|
"step": 1735
|
|
},
|
|
{
|
|
"entropy": 6.009731960296631,
|
|
"epoch": 1.772287315333673,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004922326191932882,
|
|
"loss": 6.0054,
|
|
"mean_token_accuracy": 0.14514800533652306,
|
|
"num_tokens": 4104380.0,
|
|
"step": 1740
|
|
},
|
|
{
|
|
"entropy": 6.031725835800171,
|
|
"epoch": 1.7773815588385125,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004921277762782661,
|
|
"loss": 5.9102,
|
|
"mean_token_accuracy": 0.1545369416475296,
|
|
"num_tokens": 4115506.0,
|
|
"step": 1745
|
|
},
|
|
{
|
|
"entropy": 6.058172130584717,
|
|
"epoch": 1.782475802343352,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004920222431183437,
|
|
"loss": 6.0688,
|
|
"mean_token_accuracy": 0.14753634482622147,
|
|
"num_tokens": 4126978.0,
|
|
"step": 1750
|
|
},
|
|
{
|
|
"entropy": 5.964846801757813,
|
|
"epoch": 1.7875700458481916,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004919160200490085,
|
|
"loss": 5.8791,
|
|
"mean_token_accuracy": 0.15507214069366454,
|
|
"num_tokens": 4137602.0,
|
|
"step": 1755
|
|
},
|
|
{
|
|
"entropy": 6.084032964706421,
|
|
"epoch": 1.7926642893530311,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004918091074079419,
|
|
"loss": 5.9777,
|
|
"mean_token_accuracy": 0.14689225256443023,
|
|
"num_tokens": 4148617.0,
|
|
"step": 1760
|
|
},
|
|
{
|
|
"entropy": 6.065905427932739,
|
|
"epoch": 1.7977585328578707,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004917015055350167,
|
|
"loss": 6.0774,
|
|
"mean_token_accuracy": 0.15037426650524138,
|
|
"num_tokens": 4162445.0,
|
|
"step": 1765
|
|
},
|
|
{
|
|
"entropy": 6.121287441253662,
|
|
"epoch": 1.8028527763627102,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004915932147722974,
|
|
"loss": 6.0552,
|
|
"mean_token_accuracy": 0.14733544141054153,
|
|
"num_tokens": 4175163.0,
|
|
"step": 1770
|
|
},
|
|
{
|
|
"entropy": 6.065502786636353,
|
|
"epoch": 1.8079470198675498,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004914842354640382,
|
|
"loss": 6.024,
|
|
"mean_token_accuracy": 0.14942564815282822,
|
|
"num_tokens": 4189159.0,
|
|
"step": 1775
|
|
},
|
|
{
|
|
"entropy": 6.119499826431275,
|
|
"epoch": 1.8130412633723894,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000491374567956682,
|
|
"loss": 6.1319,
|
|
"mean_token_accuracy": 0.1392667606472969,
|
|
"num_tokens": 4201989.0,
|
|
"step": 1780
|
|
},
|
|
{
|
|
"entropy": 5.982971239089966,
|
|
"epoch": 1.8181355068772287,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004912642125988597,
|
|
"loss": 5.9005,
|
|
"mean_token_accuracy": 0.15367604941129684,
|
|
"num_tokens": 4214982.0,
|
|
"step": 1785
|
|
},
|
|
{
|
|
"entropy": 5.979884243011474,
|
|
"epoch": 1.8232297503820682,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004911531697413888,
|
|
"loss": 5.8197,
|
|
"mean_token_accuracy": 0.15773751437664033,
|
|
"num_tokens": 4225932.0,
|
|
"step": 1790
|
|
},
|
|
{
|
|
"entropy": 6.0400148868560795,
|
|
"epoch": 1.8283239938869078,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004910414397372724,
|
|
"loss": 6.0547,
|
|
"mean_token_accuracy": 0.14175843968987464,
|
|
"num_tokens": 4238406.0,
|
|
"step": 1795
|
|
},
|
|
{
|
|
"entropy": 5.933195638656616,
|
|
"epoch": 1.8334182373917474,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004909290229416979,
|
|
"loss": 5.8468,
|
|
"mean_token_accuracy": 0.1593022346496582,
|
|
"num_tokens": 4249956.0,
|
|
"step": 1800
|
|
},
|
|
{
|
|
"entropy": 6.020194244384766,
|
|
"epoch": 1.8385124808965867,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.000490815919712036,
|
|
"loss": 5.9966,
|
|
"mean_token_accuracy": 0.1435801424086094,
|
|
"num_tokens": 4262367.0,
|
|
"step": 1805
|
|
},
|
|
{
|
|
"entropy": 6.0135705947875975,
|
|
"epoch": 1.8436067244014263,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004907021304078398,
|
|
"loss": 5.9858,
|
|
"mean_token_accuracy": 0.15024446249008178,
|
|
"num_tokens": 4273767.0,
|
|
"step": 1810
|
|
},
|
|
{
|
|
"entropy": 6.017576789855957,
|
|
"epoch": 1.8487009679062658,
|
|
"grad_norm": 0.91015625,
|
|
"learning_rate": 0.0004905876553908432,
|
|
"loss": 6.0099,
|
|
"mean_token_accuracy": 0.1527609795331955,
|
|
"num_tokens": 4285545.0,
|
|
"step": 1815
|
|
},
|
|
{
|
|
"entropy": 6.131746530532837,
|
|
"epoch": 1.8537952114111054,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004904724950249599,
|
|
"loss": 6.0007,
|
|
"mean_token_accuracy": 0.14292944744229316,
|
|
"num_tokens": 4296963.0,
|
|
"step": 1820
|
|
},
|
|
{
|
|
"entropy": 5.938863706588745,
|
|
"epoch": 1.858889454915945,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004903566496762824,
|
|
"loss": 5.8591,
|
|
"mean_token_accuracy": 0.1559537261724472,
|
|
"num_tokens": 4307724.0,
|
|
"step": 1825
|
|
},
|
|
{
|
|
"entropy": 5.979634141921997,
|
|
"epoch": 1.8639836984207845,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000490240119713081,
|
|
"loss": 5.9177,
|
|
"mean_token_accuracy": 0.15530329197645187,
|
|
"num_tokens": 4319153.0,
|
|
"step": 1830
|
|
},
|
|
{
|
|
"entropy": 5.925511264801026,
|
|
"epoch": 1.869077941925624,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004901229055058019,
|
|
"loss": 5.8893,
|
|
"mean_token_accuracy": 0.15859820544719697,
|
|
"num_tokens": 4330179.0,
|
|
"step": 1835
|
|
},
|
|
{
|
|
"entropy": 6.000934362411499,
|
|
"epoch": 1.8741721854304636,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004900050074270669,
|
|
"loss": 5.9061,
|
|
"mean_token_accuracy": 0.14837884306907653,
|
|
"num_tokens": 4340747.0,
|
|
"step": 1840
|
|
},
|
|
{
|
|
"entropy": 5.986407136917114,
|
|
"epoch": 1.8792664289353032,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004898864258516717,
|
|
"loss": 5.9356,
|
|
"mean_token_accuracy": 0.1507401555776596,
|
|
"num_tokens": 4352336.0,
|
|
"step": 1845
|
|
},
|
|
{
|
|
"entropy": 6.019035959243775,
|
|
"epoch": 1.8843606724401427,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004897671611565845,
|
|
"loss": 5.8585,
|
|
"mean_token_accuracy": 0.15450628101825714,
|
|
"num_tokens": 4363189.0,
|
|
"step": 1850
|
|
},
|
|
{
|
|
"entropy": 5.9605508804321286,
|
|
"epoch": 1.8894549159449823,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004896472137209457,
|
|
"loss": 6.0114,
|
|
"mean_token_accuracy": 0.15344889163970948,
|
|
"num_tokens": 4375946.0,
|
|
"step": 1855
|
|
},
|
|
{
|
|
"entropy": 6.0401444911956785,
|
|
"epoch": 1.8945491594498218,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004895265839260657,
|
|
"loss": 5.9645,
|
|
"mean_token_accuracy": 0.155985938757658,
|
|
"num_tokens": 4387543.0,
|
|
"step": 1860
|
|
},
|
|
{
|
|
"entropy": 5.9809211730957035,
|
|
"epoch": 1.8996434029546614,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004894052721554242,
|
|
"loss": 5.9741,
|
|
"mean_token_accuracy": 0.15067811906337739,
|
|
"num_tokens": 4399790.0,
|
|
"step": 1865
|
|
},
|
|
{
|
|
"entropy": 6.104261207580566,
|
|
"epoch": 1.9047376464595007,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004892832787946691,
|
|
"loss": 5.9982,
|
|
"mean_token_accuracy": 0.1496062770485878,
|
|
"num_tokens": 4411321.0,
|
|
"step": 1870
|
|
},
|
|
{
|
|
"entropy": 5.987740612030029,
|
|
"epoch": 1.9098318899643403,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004891606042316146,
|
|
"loss": 5.9341,
|
|
"mean_token_accuracy": 0.1538042575120926,
|
|
"num_tokens": 4422712.0,
|
|
"step": 1875
|
|
},
|
|
{
|
|
"entropy": 5.975160217285156,
|
|
"epoch": 1.9149261334691798,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004890372488562408,
|
|
"loss": 5.932,
|
|
"mean_token_accuracy": 0.14831314086914063,
|
|
"num_tokens": 4434941.0,
|
|
"step": 1880
|
|
},
|
|
{
|
|
"entropy": 6.033766174316407,
|
|
"epoch": 1.9200203769740194,
|
|
"grad_norm": 0.94140625,
|
|
"learning_rate": 0.0004889132130606921,
|
|
"loss": 5.9845,
|
|
"mean_token_accuracy": 0.15482763946056366,
|
|
"num_tokens": 4447440.0,
|
|
"step": 1885
|
|
},
|
|
{
|
|
"entropy": 5.95661187171936,
|
|
"epoch": 1.9251146204788587,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004887884972392758,
|
|
"loss": 5.9309,
|
|
"mean_token_accuracy": 0.15109919011592865,
|
|
"num_tokens": 4459086.0,
|
|
"step": 1890
|
|
},
|
|
{
|
|
"entropy": 6.010490274429321,
|
|
"epoch": 1.9302088639836983,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000488663101788461,
|
|
"loss": 5.9689,
|
|
"mean_token_accuracy": 0.15499186366796494,
|
|
"num_tokens": 4470463.0,
|
|
"step": 1895
|
|
},
|
|
{
|
|
"entropy": 5.906804370880127,
|
|
"epoch": 1.9353031074885378,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004885370271068773,
|
|
"loss": 5.9099,
|
|
"mean_token_accuracy": 0.15397028774023055,
|
|
"num_tokens": 4481266.0,
|
|
"step": 1900
|
|
},
|
|
{
|
|
"entropy": 5.9154823303222654,
|
|
"epoch": 1.9403973509933774,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004884102735953136,
|
|
"loss": 5.8761,
|
|
"mean_token_accuracy": 0.15611894503235818,
|
|
"num_tokens": 4493367.0,
|
|
"step": 1905
|
|
},
|
|
{
|
|
"entropy": 6.011291933059693,
|
|
"epoch": 1.945491594498217,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.000488282841656717,
|
|
"loss": 5.926,
|
|
"mean_token_accuracy": 0.1512049287557602,
|
|
"num_tokens": 4505317.0,
|
|
"step": 1910
|
|
},
|
|
{
|
|
"entropy": 5.954664707183838,
|
|
"epoch": 1.9505858380030565,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00048815473169619097,
|
|
"loss": 5.9456,
|
|
"mean_token_accuracy": 0.15357810258865356,
|
|
"num_tokens": 4516743.0,
|
|
"step": 1915
|
|
},
|
|
{
|
|
"entropy": 6.008725929260254,
|
|
"epoch": 1.955680081507896,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004880259441209945,
|
|
"loss": 5.9257,
|
|
"mean_token_accuracy": 0.15126045495271684,
|
|
"num_tokens": 4529467.0,
|
|
"step": 1920
|
|
},
|
|
{
|
|
"entropy": 5.895899724960327,
|
|
"epoch": 1.9607743250127356,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004878964793405408,
|
|
"loss": 5.8362,
|
|
"mean_token_accuracy": 0.16100727915763854,
|
|
"num_tokens": 4540648.0,
|
|
"step": 1925
|
|
},
|
|
{
|
|
"entropy": 5.9156656742095945,
|
|
"epoch": 1.9658685685175752,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048776633776639584,
|
|
"loss": 5.8651,
|
|
"mean_token_accuracy": 0.15492998957633972,
|
|
"num_tokens": 4552095.0,
|
|
"step": 1930
|
|
},
|
|
{
|
|
"entropy": 5.9102991104125975,
|
|
"epoch": 1.9709628120224147,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048763551981227703,
|
|
"loss": 5.8826,
|
|
"mean_token_accuracy": 0.15725963562726974,
|
|
"num_tokens": 4563286.0,
|
|
"step": 1935
|
|
},
|
|
{
|
|
"entropy": 6.079156112670899,
|
|
"epoch": 1.9760570555272543,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048750402589405224,
|
|
"loss": 5.9678,
|
|
"mean_token_accuracy": 0.1529908835887909,
|
|
"num_tokens": 4575313.0,
|
|
"step": 1940
|
|
},
|
|
{
|
|
"entropy": 5.919543361663818,
|
|
"epoch": 1.9811512990320939,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048737185642973784,
|
|
"loss": 5.9132,
|
|
"mean_token_accuracy": 0.15463192462921144,
|
|
"num_tokens": 4587155.0,
|
|
"step": 1945
|
|
},
|
|
{
|
|
"entropy": 6.0006670475006105,
|
|
"epoch": 1.9862455425369334,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000487239011839498,
|
|
"loss": 5.9488,
|
|
"mean_token_accuracy": 0.14793393164873123,
|
|
"num_tokens": 4598176.0,
|
|
"step": 1950
|
|
},
|
|
{
|
|
"entropy": 6.0277361392974855,
|
|
"epoch": 1.9913397860417728,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004871054925456431,
|
|
"loss": 5.9973,
|
|
"mean_token_accuracy": 0.1456962801516056,
|
|
"num_tokens": 4610004.0,
|
|
"step": 1955
|
|
},
|
|
{
|
|
"entropy": 5.978898000717163,
|
|
"epoch": 1.9964340295466123,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048697129897262833,
|
|
"loss": 5.915,
|
|
"mean_token_accuracy": 0.15651439279317855,
|
|
"num_tokens": 4620985.0,
|
|
"step": 1960
|
|
},
|
|
{
|
|
"entropy": 5.908947255876329,
|
|
"epoch": 2.001018848700968,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004868364315470523,
|
|
"loss": 5.7981,
|
|
"mean_token_accuracy": 0.16079486078686184,
|
|
"num_tokens": 4630550.0,
|
|
"step": 1965
|
|
},
|
|
{
|
|
"entropy": 5.945104932785034,
|
|
"epoch": 2.0061130922058075,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048670089069765594,
|
|
"loss": 5.5484,
|
|
"mean_token_accuracy": 0.16541721671819687,
|
|
"num_tokens": 4642173.0,
|
|
"step": 1970
|
|
},
|
|
{
|
|
"entropy": 5.870164632797241,
|
|
"epoch": 2.011207335710647,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004865646768553209,
|
|
"loss": 5.5773,
|
|
"mean_token_accuracy": 0.1712649866938591,
|
|
"num_tokens": 4654322.0,
|
|
"step": 1975
|
|
},
|
|
{
|
|
"entropy": 5.85951795578003,
|
|
"epoch": 2.0163015792154866,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004864277904530684,
|
|
"loss": 5.5786,
|
|
"mean_token_accuracy": 0.17355846911668776,
|
|
"num_tokens": 4665716.0,
|
|
"step": 1980
|
|
},
|
|
{
|
|
"entropy": 5.918148946762085,
|
|
"epoch": 2.021395822720326,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048629023192605747,
|
|
"loss": 5.6547,
|
|
"mean_token_accuracy": 0.16473341286182402,
|
|
"num_tokens": 4677148.0,
|
|
"step": 1985
|
|
},
|
|
{
|
|
"entropy": 5.90467095375061,
|
|
"epoch": 2.0264900662251657,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048615200171158395,
|
|
"loss": 5.5792,
|
|
"mean_token_accuracy": 0.16939278990030288,
|
|
"num_tokens": 4690855.0,
|
|
"step": 1990
|
|
},
|
|
{
|
|
"entropy": 5.819876480102539,
|
|
"epoch": 2.0315843097300053,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048601310024907904,
|
|
"loss": 5.5502,
|
|
"mean_token_accuracy": 0.16651132479310035,
|
|
"num_tokens": 4702933.0,
|
|
"step": 1995
|
|
},
|
|
{
|
|
"entropy": 5.930644941329956,
|
|
"epoch": 2.036678553234845,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.00048587352798010766,
|
|
"loss": 5.6341,
|
|
"mean_token_accuracy": 0.15964097529649734,
|
|
"num_tokens": 4715584.0,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 2.036678553234845,
|
|
"eval_entropy": 5.62031678447017,
|
|
"eval_loss": 5.969032287597656,
|
|
"eval_mean_token_accuracy": 0.15611327899458968,
|
|
"eval_num_tokens": 4715584.0,
|
|
"eval_runtime": 2.8116,
|
|
"eval_samples_per_second": 1152.365,
|
|
"eval_steps_per_second": 144.046,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"entropy": 5.818984031677246,
|
|
"epoch": 2.0417727967396844,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00048573328534836735,
|
|
"loss": 5.601,
|
|
"mean_token_accuracy": 0.1660971850156784,
|
|
"num_tokens": 4726197.0,
|
|
"step": 2005
|
|
},
|
|
{
|
|
"entropy": 5.900150442123413,
|
|
"epoch": 2.0468670402445235,
|
|
"grad_norm": 0.8828125,
|
|
"learning_rate": 0.0004855923727996866,
|
|
"loss": 5.5078,
|
|
"mean_token_accuracy": 0.17555468231439592,
|
|
"num_tokens": 4739238.0,
|
|
"step": 2010
|
|
},
|
|
{
|
|
"entropy": 5.8321984767913815,
|
|
"epoch": 2.051961283749363,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004854507907820237,
|
|
"loss": 5.5534,
|
|
"mean_token_accuracy": 0.1598127529025078,
|
|
"num_tokens": 4750658.0,
|
|
"step": 2015
|
|
},
|
|
{
|
|
"entropy": 5.900466394424439,
|
|
"epoch": 2.0570555272542026,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.00048530853974546495,
|
|
"loss": 5.6333,
|
|
"mean_token_accuracy": 0.1609639659523964,
|
|
"num_tokens": 4763193.0,
|
|
"step": 2020
|
|
},
|
|
{
|
|
"entropy": 5.955789375305176,
|
|
"epoch": 2.062149770759042,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004851656201422237,
|
|
"loss": 5.6704,
|
|
"mean_token_accuracy": 0.162435482442379,
|
|
"num_tokens": 4774701.0,
|
|
"step": 2025
|
|
},
|
|
{
|
|
"entropy": 5.880024576187134,
|
|
"epoch": 2.0672440142638817,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00048502203242663846,
|
|
"loss": 5.6025,
|
|
"mean_token_accuracy": 0.16102872639894486,
|
|
"num_tokens": 4786001.0,
|
|
"step": 2030
|
|
},
|
|
{
|
|
"entropy": 5.75847373008728,
|
|
"epoch": 2.0723382577687213,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048487777705517177,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.16628326326608658,
|
|
"num_tokens": 4797591.0,
|
|
"step": 2035
|
|
},
|
|
{
|
|
"entropy": 5.928161478042602,
|
|
"epoch": 2.077432501273561,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00048473285448640853,
|
|
"loss": 5.6475,
|
|
"mean_token_accuracy": 0.16663917750120164,
|
|
"num_tokens": 4809296.0,
|
|
"step": 2040
|
|
},
|
|
{
|
|
"entropy": 5.871248340606689,
|
|
"epoch": 2.0825267447784004,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.0004845872651810549,
|
|
"loss": 5.6275,
|
|
"mean_token_accuracy": 0.16441605389118194,
|
|
"num_tokens": 4821141.0,
|
|
"step": 2045
|
|
},
|
|
{
|
|
"entropy": 5.752266454696655,
|
|
"epoch": 2.08762098828324,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048444100960193617,
|
|
"loss": 5.4742,
|
|
"mean_token_accuracy": 0.17370279729366303,
|
|
"num_tokens": 4834043.0,
|
|
"step": 2050
|
|
},
|
|
{
|
|
"entropy": 5.828112459182739,
|
|
"epoch": 2.0927152317880795,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004842940882139961,
|
|
"loss": 5.5404,
|
|
"mean_token_accuracy": 0.16728458404541016,
|
|
"num_tokens": 4845686.0,
|
|
"step": 2055
|
|
},
|
|
{
|
|
"entropy": 5.815605974197387,
|
|
"epoch": 2.097809475292919,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.00048414650148429465,
|
|
"loss": 5.5796,
|
|
"mean_token_accuracy": 0.1687358096241951,
|
|
"num_tokens": 4857999.0,
|
|
"step": 2060
|
|
},
|
|
{
|
|
"entropy": 5.775838613510132,
|
|
"epoch": 2.1029037187977586,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00048399824988200747,
|
|
"loss": 5.5023,
|
|
"mean_token_accuracy": 0.1788402631878853,
|
|
"num_tokens": 4868955.0,
|
|
"step": 2065
|
|
},
|
|
{
|
|
"entropy": 5.832354497909546,
|
|
"epoch": 2.107997962302598,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00048384933387842313,
|
|
"loss": 5.5765,
|
|
"mean_token_accuracy": 0.16253895610570906,
|
|
"num_tokens": 4881283.0,
|
|
"step": 2070
|
|
},
|
|
{
|
|
"entropy": 5.747897052764893,
|
|
"epoch": 2.1130922058074377,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004836997539469429,
|
|
"loss": 5.5665,
|
|
"mean_token_accuracy": 0.16654192507267,
|
|
"num_tokens": 4892841.0,
|
|
"step": 2075
|
|
},
|
|
{
|
|
"entropy": 5.843785619735717,
|
|
"epoch": 2.1181864493122773,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00048354951056307814,
|
|
"loss": 5.6753,
|
|
"mean_token_accuracy": 0.1653669908642769,
|
|
"num_tokens": 4903926.0,
|
|
"step": 2080
|
|
},
|
|
{
|
|
"entropy": 5.847943210601807,
|
|
"epoch": 2.123280692817117,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048339860420444994,
|
|
"loss": 5.5915,
|
|
"mean_token_accuracy": 0.16666646897792817,
|
|
"num_tokens": 4917163.0,
|
|
"step": 2085
|
|
},
|
|
{
|
|
"entropy": 5.8208503246307375,
|
|
"epoch": 2.128374936321956,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048324703535078633,
|
|
"loss": 5.6041,
|
|
"mean_token_accuracy": 0.1606005996465683,
|
|
"num_tokens": 4930232.0,
|
|
"step": 2090
|
|
},
|
|
{
|
|
"entropy": 5.80724024772644,
|
|
"epoch": 2.1334691798267955,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00048309480448392185,
|
|
"loss": 5.578,
|
|
"mean_token_accuracy": 0.17210218608379363,
|
|
"num_tokens": 4941493.0,
|
|
"step": 2095
|
|
},
|
|
{
|
|
"entropy": 5.725574779510498,
|
|
"epoch": 2.138563423331635,
|
|
"grad_norm": 0.9765625,
|
|
"learning_rate": 0.0004829419120877954,
|
|
"loss": 5.5223,
|
|
"mean_token_accuracy": 0.17113063484430313,
|
|
"num_tokens": 4953781.0,
|
|
"step": 2100
|
|
},
|
|
{
|
|
"entropy": 5.865182256698608,
|
|
"epoch": 2.1436576668364746,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004827883586484488,
|
|
"loss": 5.6228,
|
|
"mean_token_accuracy": 0.16533854901790618,
|
|
"num_tokens": 4966265.0,
|
|
"step": 2105
|
|
},
|
|
{
|
|
"entropy": 5.8052679061889645,
|
|
"epoch": 2.148751910341314,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004826341446540254,
|
|
"loss": 5.639,
|
|
"mean_token_accuracy": 0.16439810246229172,
|
|
"num_tokens": 4977676.0,
|
|
"step": 2110
|
|
},
|
|
{
|
|
"entropy": 5.874921894073486,
|
|
"epoch": 2.1538461538461537,
|
|
"grad_norm": 0.9609375,
|
|
"learning_rate": 0.00048247927059476866,
|
|
"loss": 5.6343,
|
|
"mean_token_accuracy": 0.16010402143001556,
|
|
"num_tokens": 4990818.0,
|
|
"step": 2115
|
|
},
|
|
{
|
|
"entropy": 5.776369380950928,
|
|
"epoch": 2.1589403973509933,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00048232373696301985,
|
|
"loss": 5.6298,
|
|
"mean_token_accuracy": 0.1646338015794754,
|
|
"num_tokens": 5003175.0,
|
|
"step": 2120
|
|
},
|
|
{
|
|
"entropy": 5.88043475151062,
|
|
"epoch": 2.164034640855833,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00048216754425321734,
|
|
"loss": 5.591,
|
|
"mean_token_accuracy": 0.1656954288482666,
|
|
"num_tokens": 5014619.0,
|
|
"step": 2125
|
|
},
|
|
{
|
|
"entropy": 5.816552972793579,
|
|
"epoch": 2.1691288843606724,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004820106929618948,
|
|
"loss": 5.6167,
|
|
"mean_token_accuracy": 0.16424932479858398,
|
|
"num_tokens": 5026407.0,
|
|
"step": 2130
|
|
},
|
|
{
|
|
"entropy": 5.906729984283447,
|
|
"epoch": 2.174223127865512,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.00048185318358767926,
|
|
"loss": 5.7523,
|
|
"mean_token_accuracy": 0.15930672287940978,
|
|
"num_tokens": 5039479.0,
|
|
"step": 2135
|
|
},
|
|
{
|
|
"entropy": 5.767476320266724,
|
|
"epoch": 2.1793173713703515,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00048169501663129007,
|
|
"loss": 5.5966,
|
|
"mean_token_accuracy": 0.16930720806121827,
|
|
"num_tokens": 5052074.0,
|
|
"step": 2140
|
|
},
|
|
{
|
|
"entropy": 5.996895408630371,
|
|
"epoch": 2.184411614875191,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00048153619259553665,
|
|
"loss": 5.6824,
|
|
"mean_token_accuracy": 0.15677667707204818,
|
|
"num_tokens": 5064551.0,
|
|
"step": 2145
|
|
},
|
|
{
|
|
"entropy": 5.810957574844361,
|
|
"epoch": 2.1895058583800306,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00048137671198531765,
|
|
"loss": 5.5815,
|
|
"mean_token_accuracy": 0.1658017724752426,
|
|
"num_tokens": 5075616.0,
|
|
"step": 2150
|
|
},
|
|
{
|
|
"entropy": 5.760199737548828,
|
|
"epoch": 2.19460010188487,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00048121657530761857,
|
|
"loss": 5.6552,
|
|
"mean_token_accuracy": 0.16322747766971588,
|
|
"num_tokens": 5086531.0,
|
|
"step": 2155
|
|
},
|
|
{
|
|
"entropy": 5.922705745697021,
|
|
"epoch": 2.1996943453897098,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00048105578307151094,
|
|
"loss": 5.6916,
|
|
"mean_token_accuracy": 0.16097672730684282,
|
|
"num_tokens": 5097881.0,
|
|
"step": 2160
|
|
},
|
|
{
|
|
"entropy": 5.7204893112182615,
|
|
"epoch": 2.2047885888945493,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00048089433578814994,
|
|
"loss": 5.509,
|
|
"mean_token_accuracy": 0.16698236912488937,
|
|
"num_tokens": 5108511.0,
|
|
"step": 2165
|
|
},
|
|
{
|
|
"entropy": 5.797280120849609,
|
|
"epoch": 2.209882832399389,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004807322339707733,
|
|
"loss": 5.6006,
|
|
"mean_token_accuracy": 0.17074504047632216,
|
|
"num_tokens": 5119302.0,
|
|
"step": 2170
|
|
},
|
|
{
|
|
"entropy": 5.7944495677948,
|
|
"epoch": 2.214977075904228,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00048056947813469967,
|
|
"loss": 5.6876,
|
|
"mean_token_accuracy": 0.15859579518437386,
|
|
"num_tokens": 5131430.0,
|
|
"step": 2175
|
|
},
|
|
{
|
|
"entropy": 5.811315679550171,
|
|
"epoch": 2.220071319409068,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004804060687973264,
|
|
"loss": 5.6467,
|
|
"mean_token_accuracy": 0.1624533861875534,
|
|
"num_tokens": 5143449.0,
|
|
"step": 2180
|
|
},
|
|
{
|
|
"entropy": 5.841419410705567,
|
|
"epoch": 2.225165562913907,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004802420064781286,
|
|
"loss": 5.6163,
|
|
"mean_token_accuracy": 0.16900259554386138,
|
|
"num_tokens": 5155286.0,
|
|
"step": 2185
|
|
},
|
|
{
|
|
"entropy": 5.791315984725952,
|
|
"epoch": 2.2302598064187467,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004800772916986572,
|
|
"loss": 5.5697,
|
|
"mean_token_accuracy": 0.16355349421501159,
|
|
"num_tokens": 5167624.0,
|
|
"step": 2190
|
|
},
|
|
{
|
|
"entropy": 5.791861534118652,
|
|
"epoch": 2.235354049923586,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047991192498253715,
|
|
"loss": 5.5139,
|
|
"mean_token_accuracy": 0.17494232207536697,
|
|
"num_tokens": 5179206.0,
|
|
"step": 2195
|
|
},
|
|
{
|
|
"entropy": 5.741910982131958,
|
|
"epoch": 2.2404482934284258,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.000479745906855466,
|
|
"loss": 5.5742,
|
|
"mean_token_accuracy": 0.16768807172775269,
|
|
"num_tokens": 5190820.0,
|
|
"step": 2200
|
|
},
|
|
{
|
|
"entropy": 5.839303588867187,
|
|
"epoch": 2.2455425369332653,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00047957923784521206,
|
|
"loss": 5.6235,
|
|
"mean_token_accuracy": 0.16996713876724243,
|
|
"num_tokens": 5201308.0,
|
|
"step": 2205
|
|
},
|
|
{
|
|
"entropy": 5.734570646286011,
|
|
"epoch": 2.250636780438105,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004794119184816129,
|
|
"loss": 5.5304,
|
|
"mean_token_accuracy": 0.1717229664325714,
|
|
"num_tokens": 5213246.0,
|
|
"step": 2210
|
|
},
|
|
{
|
|
"entropy": 5.81427035331726,
|
|
"epoch": 2.2557310239429444,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004792439492965734,
|
|
"loss": 5.6367,
|
|
"mean_token_accuracy": 0.1608924999833107,
|
|
"num_tokens": 5225484.0,
|
|
"step": 2215
|
|
},
|
|
{
|
|
"entropy": 5.810764932632447,
|
|
"epoch": 2.260825267447784,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004790753308240642,
|
|
"loss": 5.6575,
|
|
"mean_token_accuracy": 0.1606771320104599,
|
|
"num_tokens": 5238728.0,
|
|
"step": 2220
|
|
},
|
|
{
|
|
"entropy": 5.8196601390838625,
|
|
"epoch": 2.2659195109526236,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004789060636001202,
|
|
"loss": 5.6638,
|
|
"mean_token_accuracy": 0.166461843252182,
|
|
"num_tokens": 5250130.0,
|
|
"step": 2225
|
|
},
|
|
{
|
|
"entropy": 5.808871412277222,
|
|
"epoch": 2.271013754457463,
|
|
"grad_norm": 0.9296875,
|
|
"learning_rate": 0.0004787361481628385,
|
|
"loss": 5.6044,
|
|
"mean_token_accuracy": 0.16343416571617125,
|
|
"num_tokens": 5262624.0,
|
|
"step": 2230
|
|
},
|
|
{
|
|
"entropy": 5.814700746536255,
|
|
"epoch": 2.2761079979623027,
|
|
"grad_norm": 0.953125,
|
|
"learning_rate": 0.0004785655850523769,
|
|
"loss": 5.6465,
|
|
"mean_token_accuracy": 0.1613625168800354,
|
|
"num_tokens": 5274914.0,
|
|
"step": 2235
|
|
},
|
|
{
|
|
"entropy": 5.738488388061524,
|
|
"epoch": 2.2812022414671422,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047839437481095223,
|
|
"loss": 5.5063,
|
|
"mean_token_accuracy": 0.17593536227941514,
|
|
"num_tokens": 5286836.0,
|
|
"step": 2240
|
|
},
|
|
{
|
|
"entropy": 5.6917564868927,
|
|
"epoch": 2.286296484971982,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00047822251798283836,
|
|
"loss": 5.522,
|
|
"mean_token_accuracy": 0.17000024020671844,
|
|
"num_tokens": 5297416.0,
|
|
"step": 2245
|
|
},
|
|
{
|
|
"entropy": 5.722369194030762,
|
|
"epoch": 2.2913907284768213,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004780500151143647,
|
|
"loss": 5.5034,
|
|
"mean_token_accuracy": 0.17222748398780824,
|
|
"num_tokens": 5307852.0,
|
|
"step": 2250
|
|
},
|
|
{
|
|
"entropy": 5.723336887359619,
|
|
"epoch": 2.296484971981661,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004778768667539147,
|
|
"loss": 5.6364,
|
|
"mean_token_accuracy": 0.16439990997314452,
|
|
"num_tokens": 5320500.0,
|
|
"step": 2255
|
|
},
|
|
{
|
|
"entropy": 5.797302150726319,
|
|
"epoch": 2.3015792154865,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00047770307345192326,
|
|
"loss": 5.5672,
|
|
"mean_token_accuracy": 0.16709809899330139,
|
|
"num_tokens": 5331867.0,
|
|
"step": 2260
|
|
},
|
|
{
|
|
"entropy": 5.750816011428833,
|
|
"epoch": 2.30667345899134,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00047752863576087603,
|
|
"loss": 5.5616,
|
|
"mean_token_accuracy": 0.1664021909236908,
|
|
"num_tokens": 5344181.0,
|
|
"step": 2265
|
|
},
|
|
{
|
|
"entropy": 5.7929909229278564,
|
|
"epoch": 2.311767702496179,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.000477353554235307,
|
|
"loss": 5.7328,
|
|
"mean_token_accuracy": 0.16328889578580857,
|
|
"num_tokens": 5356068.0,
|
|
"step": 2270
|
|
},
|
|
{
|
|
"entropy": 5.8103516578674315,
|
|
"epoch": 2.3168619460010187,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00047717782943179664,
|
|
"loss": 5.5684,
|
|
"mean_token_accuracy": 0.1686837702989578,
|
|
"num_tokens": 5367456.0,
|
|
"step": 2275
|
|
},
|
|
{
|
|
"entropy": 5.756494569778442,
|
|
"epoch": 2.3219561895058582,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004770014619089709,
|
|
"loss": 5.6092,
|
|
"mean_token_accuracy": 0.16871432214975357,
|
|
"num_tokens": 5379731.0,
|
|
"step": 2280
|
|
},
|
|
{
|
|
"entropy": 5.756763887405396,
|
|
"epoch": 2.327050433010698,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004768244522274985,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.16949952095746995,
|
|
"num_tokens": 5391809.0,
|
|
"step": 2285
|
|
},
|
|
{
|
|
"entropy": 5.724135637283325,
|
|
"epoch": 2.3321446765155374,
|
|
"grad_norm": 0.890625,
|
|
"learning_rate": 0.00047664680095008973,
|
|
"loss": 5.624,
|
|
"mean_token_accuracy": 0.16763131618499755,
|
|
"num_tokens": 5404341.0,
|
|
"step": 2290
|
|
},
|
|
{
|
|
"entropy": 5.779242038726807,
|
|
"epoch": 2.337238920020377,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004764685086414945,
|
|
"loss": 5.6168,
|
|
"mean_token_accuracy": 0.16189232468605042,
|
|
"num_tokens": 5415584.0,
|
|
"step": 2295
|
|
},
|
|
{
|
|
"entropy": 5.798492765426635,
|
|
"epoch": 2.3423331635252165,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00047628957586850053,
|
|
"loss": 5.6579,
|
|
"mean_token_accuracy": 0.16597485095262526,
|
|
"num_tokens": 5427980.0,
|
|
"step": 2300
|
|
},
|
|
{
|
|
"entropy": 5.86662712097168,
|
|
"epoch": 2.347427407030056,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004761100031999315,
|
|
"loss": 5.6361,
|
|
"mean_token_accuracy": 0.1711513876914978,
|
|
"num_tokens": 5439782.0,
|
|
"step": 2305
|
|
},
|
|
{
|
|
"entropy": 5.678351545333863,
|
|
"epoch": 2.3525216505348956,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004759297912066454,
|
|
"loss": 5.551,
|
|
"mean_token_accuracy": 0.16436320841312407,
|
|
"num_tokens": 5451715.0,
|
|
"step": 2310
|
|
},
|
|
{
|
|
"entropy": 5.730842161178589,
|
|
"epoch": 2.357615894039735,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047574894046153266,
|
|
"loss": 5.4998,
|
|
"mean_token_accuracy": 0.1749166339635849,
|
|
"num_tokens": 5462840.0,
|
|
"step": 2315
|
|
},
|
|
{
|
|
"entropy": 5.619156837463379,
|
|
"epoch": 2.3627101375445747,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004755674515395141,
|
|
"loss": 5.5056,
|
|
"mean_token_accuracy": 0.1761452615261078,
|
|
"num_tokens": 5474694.0,
|
|
"step": 2320
|
|
},
|
|
{
|
|
"entropy": 5.8200681686401365,
|
|
"epoch": 2.3678043810494143,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004753853250175395,
|
|
"loss": 5.6297,
|
|
"mean_token_accuracy": 0.15863382667303086,
|
|
"num_tokens": 5486292.0,
|
|
"step": 2325
|
|
},
|
|
{
|
|
"entropy": 5.758931732177734,
|
|
"epoch": 2.372898624554254,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00047520256147458545,
|
|
"loss": 5.5098,
|
|
"mean_token_accuracy": 0.17546423375606537,
|
|
"num_tokens": 5496799.0,
|
|
"step": 2330
|
|
},
|
|
{
|
|
"entropy": 5.729516172409058,
|
|
"epoch": 2.3779928680590934,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004750191614916536,
|
|
"loss": 5.6011,
|
|
"mean_token_accuracy": 0.1696643739938736,
|
|
"num_tokens": 5509520.0,
|
|
"step": 2335
|
|
},
|
|
{
|
|
"entropy": 5.7106858253479,
|
|
"epoch": 2.383087111563933,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.0004748351256517689,
|
|
"loss": 5.6461,
|
|
"mean_token_accuracy": 0.1626673683524132,
|
|
"num_tokens": 5521993.0,
|
|
"step": 2340
|
|
},
|
|
{
|
|
"entropy": 5.80874400138855,
|
|
"epoch": 2.388181355068772,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00047465045453997756,
|
|
"loss": 5.6138,
|
|
"mean_token_accuracy": 0.16498513668775558,
|
|
"num_tokens": 5533878.0,
|
|
"step": 2345
|
|
},
|
|
{
|
|
"entropy": 5.754479932785034,
|
|
"epoch": 2.393275598573612,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004744651487433455,
|
|
"loss": 5.6075,
|
|
"mean_token_accuracy": 0.1706341877579689,
|
|
"num_tokens": 5546492.0,
|
|
"step": 2350
|
|
},
|
|
{
|
|
"entropy": 5.823743581771851,
|
|
"epoch": 2.398369842078451,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004742792088509561,
|
|
"loss": 5.6373,
|
|
"mean_token_accuracy": 0.16473434418439864,
|
|
"num_tokens": 5557540.0,
|
|
"step": 2355
|
|
},
|
|
{
|
|
"entropy": 5.7825061798095705,
|
|
"epoch": 2.4034640855832907,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00047409263545390864,
|
|
"loss": 5.638,
|
|
"mean_token_accuracy": 0.16671781837940217,
|
|
"num_tokens": 5569118.0,
|
|
"step": 2360
|
|
},
|
|
{
|
|
"entropy": 5.760390710830689,
|
|
"epoch": 2.4085583290881303,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004739054291453162,
|
|
"loss": 5.6707,
|
|
"mean_token_accuracy": 0.1595264881849289,
|
|
"num_tokens": 5582738.0,
|
|
"step": 2365
|
|
},
|
|
{
|
|
"entropy": 5.718589115142822,
|
|
"epoch": 2.41365257259297,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00047371759052030395,
|
|
"loss": 5.5104,
|
|
"mean_token_accuracy": 0.17014646530151367,
|
|
"num_tokens": 5593941.0,
|
|
"step": 2370
|
|
},
|
|
{
|
|
"entropy": 5.775838613510132,
|
|
"epoch": 2.4187468160978094,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004735291201760072,
|
|
"loss": 5.6353,
|
|
"mean_token_accuracy": 0.16346013844013213,
|
|
"num_tokens": 5606473.0,
|
|
"step": 2375
|
|
},
|
|
{
|
|
"entropy": 5.7426496028900145,
|
|
"epoch": 2.423841059602649,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004733400187115694,
|
|
"loss": 5.515,
|
|
"mean_token_accuracy": 0.17410024553537368,
|
|
"num_tokens": 5617355.0,
|
|
"step": 2380
|
|
},
|
|
{
|
|
"entropy": 5.716971206665039,
|
|
"epoch": 2.4289353031074885,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004731502867281404,
|
|
"loss": 5.59,
|
|
"mean_token_accuracy": 0.16747244149446489,
|
|
"num_tokens": 5629062.0,
|
|
"step": 2385
|
|
},
|
|
{
|
|
"entropy": 5.813964700698852,
|
|
"epoch": 2.434029546612328,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00047295992482887435,
|
|
"loss": 5.6203,
|
|
"mean_token_accuracy": 0.16134635508060455,
|
|
"num_tokens": 5641529.0,
|
|
"step": 2390
|
|
},
|
|
{
|
|
"entropy": 5.774265432357788,
|
|
"epoch": 2.4391237901171676,
|
|
"grad_norm": 0.9375,
|
|
"learning_rate": 0.00047276893361892803,
|
|
"loss": 5.6608,
|
|
"mean_token_accuracy": 0.16629068851470946,
|
|
"num_tokens": 5654777.0,
|
|
"step": 2395
|
|
},
|
|
{
|
|
"entropy": 5.724766397476197,
|
|
"epoch": 2.444218033622007,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047257731370545865,
|
|
"loss": 5.6079,
|
|
"mean_token_accuracy": 0.16991823315620422,
|
|
"num_tokens": 5667208.0,
|
|
"step": 2400
|
|
},
|
|
{
|
|
"entropy": 5.6530890464782715,
|
|
"epoch": 2.4493122771268467,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004723850656976221,
|
|
"loss": 5.5402,
|
|
"mean_token_accuracy": 0.1727624788880348,
|
|
"num_tokens": 5679148.0,
|
|
"step": 2405
|
|
},
|
|
{
|
|
"entropy": 5.688948631286621,
|
|
"epoch": 2.4544065206316863,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004721921902065711,
|
|
"loss": 5.4202,
|
|
"mean_token_accuracy": 0.18155144155025482,
|
|
"num_tokens": 5690869.0,
|
|
"step": 2410
|
|
},
|
|
{
|
|
"entropy": 5.646128082275391,
|
|
"epoch": 2.459500764136526,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000471998687845453,
|
|
"loss": 5.5877,
|
|
"mean_token_accuracy": 0.17007255852222442,
|
|
"num_tokens": 5702939.0,
|
|
"step": 2415
|
|
},
|
|
{
|
|
"entropy": 5.814693021774292,
|
|
"epoch": 2.4645950076413654,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00047180455922940783,
|
|
"loss": 5.6114,
|
|
"mean_token_accuracy": 0.16709734946489335,
|
|
"num_tokens": 5714651.0,
|
|
"step": 2420
|
|
},
|
|
{
|
|
"entropy": 5.680844163894653,
|
|
"epoch": 2.469689251146205,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004716098049755668,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17117357403039932,
|
|
"num_tokens": 5725310.0,
|
|
"step": 2425
|
|
},
|
|
{
|
|
"entropy": 5.730017471313476,
|
|
"epoch": 2.474783494651044,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004714144257030497,
|
|
"loss": 5.6188,
|
|
"mean_token_accuracy": 0.1655963346362114,
|
|
"num_tokens": 5736357.0,
|
|
"step": 2430
|
|
},
|
|
{
|
|
"entropy": 5.731151962280274,
|
|
"epoch": 2.479877738155884,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004712184220329634,
|
|
"loss": 5.6485,
|
|
"mean_token_accuracy": 0.16924342662096023,
|
|
"num_tokens": 5748281.0,
|
|
"step": 2435
|
|
},
|
|
{
|
|
"entropy": 5.815793228149414,
|
|
"epoch": 2.484971981660723,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00047102179458839965,
|
|
"loss": 5.5926,
|
|
"mean_token_accuracy": 0.16823556274175644,
|
|
"num_tokens": 5758939.0,
|
|
"step": 2440
|
|
},
|
|
{
|
|
"entropy": 5.754806566238403,
|
|
"epoch": 2.4900662251655628,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004708245439944333,
|
|
"loss": 5.6032,
|
|
"mean_token_accuracy": 0.16816727072000504,
|
|
"num_tokens": 5769750.0,
|
|
"step": 2445
|
|
},
|
|
{
|
|
"entropy": 5.781820678710938,
|
|
"epoch": 2.4951604686704023,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00047062667087812007,
|
|
"loss": 5.609,
|
|
"mean_token_accuracy": 0.17051714658737183,
|
|
"num_tokens": 5781917.0,
|
|
"step": 2450
|
|
},
|
|
{
|
|
"entropy": 5.725583934783936,
|
|
"epoch": 2.500254712175242,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004704281758684946,
|
|
"loss": 5.5582,
|
|
"mean_token_accuracy": 0.1663421705365181,
|
|
"num_tokens": 5793665.0,
|
|
"step": 2455
|
|
},
|
|
{
|
|
"entropy": 5.79179630279541,
|
|
"epoch": 2.5053489556800814,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004702290595965686,
|
|
"loss": 5.6533,
|
|
"mean_token_accuracy": 0.164570951461792,
|
|
"num_tokens": 5806364.0,
|
|
"step": 2460
|
|
},
|
|
{
|
|
"entropy": 5.779351615905762,
|
|
"epoch": 2.510443199184921,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004700293226953288,
|
|
"loss": 5.6523,
|
|
"mean_token_accuracy": 0.16515175849199296,
|
|
"num_tokens": 5818693.0,
|
|
"step": 2465
|
|
},
|
|
{
|
|
"entropy": 5.598007869720459,
|
|
"epoch": 2.5155374426897605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004698289657997348,
|
|
"loss": 5.4234,
|
|
"mean_token_accuracy": 0.1817185491323471,
|
|
"num_tokens": 5828765.0,
|
|
"step": 2470
|
|
},
|
|
{
|
|
"entropy": 5.716284656524659,
|
|
"epoch": 2.5206316861946,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046962798954671727,
|
|
"loss": 5.5848,
|
|
"mean_token_accuracy": 0.16949136853218078,
|
|
"num_tokens": 5840196.0,
|
|
"step": 2475
|
|
},
|
|
{
|
|
"entropy": 5.71624174118042,
|
|
"epoch": 2.5257259296994397,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046942639457517565,
|
|
"loss": 5.5921,
|
|
"mean_token_accuracy": 0.17095975279808046,
|
|
"num_tokens": 5851117.0,
|
|
"step": 2480
|
|
},
|
|
{
|
|
"entropy": 5.702412509918213,
|
|
"epoch": 2.530820173204279,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004692241815259765,
|
|
"loss": 5.5666,
|
|
"mean_token_accuracy": 0.1720548614859581,
|
|
"num_tokens": 5862918.0,
|
|
"step": 2485
|
|
},
|
|
{
|
|
"entropy": 5.698266696929932,
|
|
"epoch": 2.5359144167091188,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000469021351041951,
|
|
"loss": 5.5909,
|
|
"mean_token_accuracy": 0.16819523870944977,
|
|
"num_tokens": 5875620.0,
|
|
"step": 2490
|
|
},
|
|
{
|
|
"entropy": 5.8046821594238285,
|
|
"epoch": 2.5410086602139583,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004688179037678933,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.16816546022891998,
|
|
"num_tokens": 5887113.0,
|
|
"step": 2495
|
|
},
|
|
{
|
|
"entropy": 5.7517413139343265,
|
|
"epoch": 2.546102903718798,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004686138403505582,
|
|
"loss": 5.6401,
|
|
"mean_token_accuracy": 0.16600019484758377,
|
|
"num_tokens": 5898707.0,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"entropy": 5.748650217056275,
|
|
"epoch": 2.5511971472236374,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046840916143865913,
|
|
"loss": 5.5659,
|
|
"mean_token_accuracy": 0.16834910959005356,
|
|
"num_tokens": 5909548.0,
|
|
"step": 2505
|
|
},
|
|
{
|
|
"entropy": 5.746601152420044,
|
|
"epoch": 2.556291390728477,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004682038676828666,
|
|
"loss": 5.5268,
|
|
"mean_token_accuracy": 0.17655671685934066,
|
|
"num_tokens": 5920750.0,
|
|
"step": 2510
|
|
},
|
|
{
|
|
"entropy": 5.699986267089844,
|
|
"epoch": 2.561385634233316,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046799795973580515,
|
|
"loss": 5.6674,
|
|
"mean_token_accuracy": 0.16529995203018188,
|
|
"num_tokens": 5932832.0,
|
|
"step": 2515
|
|
},
|
|
{
|
|
"entropy": 5.712204551696777,
|
|
"epoch": 2.566479877738156,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046779143825205217,
|
|
"loss": 5.5856,
|
|
"mean_token_accuracy": 0.16844226121902467,
|
|
"num_tokens": 5945644.0,
|
|
"step": 2520
|
|
},
|
|
{
|
|
"entropy": 5.71591591835022,
|
|
"epoch": 2.5715741212429952,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004675843038881354,
|
|
"loss": 5.5833,
|
|
"mean_token_accuracy": 0.1668347254395485,
|
|
"num_tokens": 5956760.0,
|
|
"step": 2525
|
|
},
|
|
{
|
|
"entropy": 5.749217176437378,
|
|
"epoch": 2.576668364747835,
|
|
"grad_norm": 0.93359375,
|
|
"learning_rate": 0.00046737655730253076,
|
|
"loss": 5.5851,
|
|
"mean_token_accuracy": 0.16941590309143068,
|
|
"num_tokens": 5969179.0,
|
|
"step": 2530
|
|
},
|
|
{
|
|
"entropy": 5.751673221588135,
|
|
"epoch": 2.5817626082526743,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00046716819915566067,
|
|
"loss": 5.6626,
|
|
"mean_token_accuracy": 0.16343993693590164,
|
|
"num_tokens": 5982051.0,
|
|
"step": 2535
|
|
},
|
|
{
|
|
"entropy": 5.858973407745362,
|
|
"epoch": 2.586856851757514,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046695923010989145,
|
|
"loss": 5.7064,
|
|
"mean_token_accuracy": 0.1570582315325737,
|
|
"num_tokens": 5994038.0,
|
|
"step": 2540
|
|
},
|
|
{
|
|
"entropy": 5.760682821273804,
|
|
"epoch": 2.5919510952623535,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00046674965082953157,
|
|
"loss": 5.6142,
|
|
"mean_token_accuracy": 0.1664024993777275,
|
|
"num_tokens": 6005356.0,
|
|
"step": 2545
|
|
},
|
|
{
|
|
"entropy": 5.748070144653321,
|
|
"epoch": 2.597045338767193,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00046653946198082943,
|
|
"loss": 5.6498,
|
|
"mean_token_accuracy": 0.16623507738113402,
|
|
"num_tokens": 6018477.0,
|
|
"step": 2550
|
|
},
|
|
{
|
|
"entropy": 5.688044548034668,
|
|
"epoch": 2.6021395822720326,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00046632866423197125,
|
|
"loss": 5.5644,
|
|
"mean_token_accuracy": 0.17507824599742888,
|
|
"num_tokens": 6029084.0,
|
|
"step": 2555
|
|
},
|
|
{
|
|
"entropy": 5.751237392425537,
|
|
"epoch": 2.607233825776872,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004661172582530788,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.1744393900036812,
|
|
"num_tokens": 6040271.0,
|
|
"step": 2560
|
|
},
|
|
{
|
|
"entropy": 5.617528438568115,
|
|
"epoch": 2.6123280692817117,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004659052447162076,
|
|
"loss": 5.4538,
|
|
"mean_token_accuracy": 0.18345775604248046,
|
|
"num_tokens": 6051278.0,
|
|
"step": 2565
|
|
},
|
|
{
|
|
"entropy": 5.655602598190308,
|
|
"epoch": 2.6174223127865512,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004656926242953445,
|
|
"loss": 5.6426,
|
|
"mean_token_accuracy": 0.16686174869537354,
|
|
"num_tokens": 6063397.0,
|
|
"step": 2570
|
|
},
|
|
{
|
|
"entropy": 5.782414865493775,
|
|
"epoch": 2.622516556291391,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004654793976664055,
|
|
"loss": 5.5511,
|
|
"mean_token_accuracy": 0.17096301466226577,
|
|
"num_tokens": 6075105.0,
|
|
"step": 2575
|
|
},
|
|
{
|
|
"entropy": 5.770709800720215,
|
|
"epoch": 2.6276107997962304,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046526556550723395,
|
|
"loss": 5.6077,
|
|
"mean_token_accuracy": 0.16690193563699723,
|
|
"num_tokens": 6086069.0,
|
|
"step": 2580
|
|
},
|
|
{
|
|
"entropy": 5.668476676940918,
|
|
"epoch": 2.63270504330107,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046505112849759794,
|
|
"loss": 5.5334,
|
|
"mean_token_accuracy": 0.17296285480260848,
|
|
"num_tokens": 6096997.0,
|
|
"step": 2585
|
|
},
|
|
{
|
|
"entropy": 5.6466419219970705,
|
|
"epoch": 2.6377992868059095,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00046483608731918855,
|
|
"loss": 5.5622,
|
|
"mean_token_accuracy": 0.17210524827241896,
|
|
"num_tokens": 6109510.0,
|
|
"step": 2590
|
|
},
|
|
{
|
|
"entropy": 5.721639251708984,
|
|
"epoch": 2.642893530310749,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00046462044265561735,
|
|
"loss": 5.4758,
|
|
"mean_token_accuracy": 0.17866286337375642,
|
|
"num_tokens": 6120111.0,
|
|
"step": 2595
|
|
},
|
|
{
|
|
"entropy": 5.725635290145874,
|
|
"epoch": 2.647987773815588,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00046440419519241455,
|
|
"loss": 5.6398,
|
|
"mean_token_accuracy": 0.1649184688925743,
|
|
"num_tokens": 6131558.0,
|
|
"step": 2600
|
|
},
|
|
{
|
|
"entropy": 5.738513660430908,
|
|
"epoch": 2.653082017320428,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0004641873456170265,
|
|
"loss": 5.5668,
|
|
"mean_token_accuracy": 0.1745607227087021,
|
|
"num_tokens": 6143687.0,
|
|
"step": 2605
|
|
},
|
|
{
|
|
"entropy": 5.821848821640015,
|
|
"epoch": 2.6581762608252673,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004639698946188137,
|
|
"loss": 5.6725,
|
|
"mean_token_accuracy": 0.16588608771562577,
|
|
"num_tokens": 6153692.0,
|
|
"step": 2610
|
|
},
|
|
{
|
|
"entropy": 5.730045890808105,
|
|
"epoch": 2.663270504330107,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004637518428890486,
|
|
"loss": 5.566,
|
|
"mean_token_accuracy": 0.17797428816556932,
|
|
"num_tokens": 6164689.0,
|
|
"step": 2615
|
|
},
|
|
{
|
|
"entropy": 5.699032831192016,
|
|
"epoch": 2.6683647478349464,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004635331911209133,
|
|
"loss": 5.6323,
|
|
"mean_token_accuracy": 0.16478496938943862,
|
|
"num_tokens": 6176720.0,
|
|
"step": 2620
|
|
},
|
|
{
|
|
"entropy": 5.7133537292480465,
|
|
"epoch": 2.673458991339786,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004633139400094974,
|
|
"loss": 5.5275,
|
|
"mean_token_accuracy": 0.17309380918741227,
|
|
"num_tokens": 6187745.0,
|
|
"step": 2625
|
|
},
|
|
{
|
|
"entropy": 5.686916875839233,
|
|
"epoch": 2.6785532348446255,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.000463094090251796,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.1765984982252121,
|
|
"num_tokens": 6200403.0,
|
|
"step": 2630
|
|
},
|
|
{
|
|
"entropy": 5.644669437408448,
|
|
"epoch": 2.683647478349465,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00046287364254670696,
|
|
"loss": 5.5541,
|
|
"mean_token_accuracy": 0.16958998441696166,
|
|
"num_tokens": 6211412.0,
|
|
"step": 2635
|
|
},
|
|
{
|
|
"entropy": 5.787599802017212,
|
|
"epoch": 2.6887417218543046,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004626525975950292,
|
|
"loss": 5.6695,
|
|
"mean_token_accuracy": 0.16274720877408982,
|
|
"num_tokens": 6222798.0,
|
|
"step": 2640
|
|
},
|
|
{
|
|
"entropy": 5.734703016281128,
|
|
"epoch": 2.693835965359144,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004624309560994603,
|
|
"loss": 5.5418,
|
|
"mean_token_accuracy": 0.17499985545873642,
|
|
"num_tokens": 6234846.0,
|
|
"step": 2645
|
|
},
|
|
{
|
|
"entropy": 5.692458200454712,
|
|
"epoch": 2.6989302088639837,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.0004622087187645942,
|
|
"loss": 5.5626,
|
|
"mean_token_accuracy": 0.16789343431591988,
|
|
"num_tokens": 6245771.0,
|
|
"step": 2650
|
|
},
|
|
{
|
|
"entropy": 5.6511680603027346,
|
|
"epoch": 2.7040244523688233,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004619858862969188,
|
|
"loss": 5.5038,
|
|
"mean_token_accuracy": 0.17768730074167252,
|
|
"num_tokens": 6258254.0,
|
|
"step": 2655
|
|
},
|
|
{
|
|
"entropy": 5.756880092620849,
|
|
"epoch": 2.709118695873663,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004617624594048143,
|
|
"loss": 5.5661,
|
|
"mean_token_accuracy": 0.16991113126277924,
|
|
"num_tokens": 6269383.0,
|
|
"step": 2660
|
|
},
|
|
{
|
|
"entropy": 5.807396936416626,
|
|
"epoch": 2.7142129393785024,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004615384387985504,
|
|
"loss": 5.5279,
|
|
"mean_token_accuracy": 0.17493753284215927,
|
|
"num_tokens": 6280275.0,
|
|
"step": 2665
|
|
},
|
|
{
|
|
"entropy": 5.601258277893066,
|
|
"epoch": 2.719307182883342,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.000461313825190284,
|
|
"loss": 5.5497,
|
|
"mean_token_accuracy": 0.1652575895190239,
|
|
"num_tokens": 6291760.0,
|
|
"step": 2670
|
|
},
|
|
{
|
|
"entropy": 5.6643720149993895,
|
|
"epoch": 2.7244014263881815,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004610886192940574,
|
|
"loss": 5.5138,
|
|
"mean_token_accuracy": 0.17513244450092316,
|
|
"num_tokens": 6303041.0,
|
|
"step": 2675
|
|
},
|
|
{
|
|
"entropy": 5.680649518966675,
|
|
"epoch": 2.729495669893021,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00046086282182579566,
|
|
"loss": 5.468,
|
|
"mean_token_accuracy": 0.177858167886734,
|
|
"num_tokens": 6313950.0,
|
|
"step": 2680
|
|
},
|
|
{
|
|
"entropy": 5.587852954864502,
|
|
"epoch": 2.73458991339786,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004606364335033045,
|
|
"loss": 5.6197,
|
|
"mean_token_accuracy": 0.17280302196741104,
|
|
"num_tokens": 6325830.0,
|
|
"step": 2685
|
|
},
|
|
{
|
|
"entropy": 5.832064008712768,
|
|
"epoch": 2.7396841569027,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00046040945504626787,
|
|
"loss": 5.649,
|
|
"mean_token_accuracy": 0.16793008893728256,
|
|
"num_tokens": 6337978.0,
|
|
"step": 2690
|
|
},
|
|
{
|
|
"entropy": 5.666331195831299,
|
|
"epoch": 2.7447784004075393,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00046018188717624576,
|
|
"loss": 5.5048,
|
|
"mean_token_accuracy": 0.17441839426755906,
|
|
"num_tokens": 6349623.0,
|
|
"step": 2695
|
|
},
|
|
{
|
|
"entropy": 5.606363725662232,
|
|
"epoch": 2.7498726439123793,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.000459953730616672,
|
|
"loss": 5.4751,
|
|
"mean_token_accuracy": 0.17461808919906616,
|
|
"num_tokens": 6361149.0,
|
|
"step": 2700
|
|
},
|
|
{
|
|
"entropy": 5.624794578552246,
|
|
"epoch": 2.7549668874172184,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045972498609285175,
|
|
"loss": 5.5114,
|
|
"mean_token_accuracy": 0.17174820154905318,
|
|
"num_tokens": 6372691.0,
|
|
"step": 2705
|
|
},
|
|
{
|
|
"entropy": 5.696760940551758,
|
|
"epoch": 2.760061130922058,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00045949565433195925,
|
|
"loss": 5.6292,
|
|
"mean_token_accuracy": 0.15939597636461258,
|
|
"num_tokens": 6385560.0,
|
|
"step": 2710
|
|
},
|
|
{
|
|
"entropy": 5.75138111114502,
|
|
"epoch": 2.7651553744268975,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00045926573606303576,
|
|
"loss": 5.5749,
|
|
"mean_token_accuracy": 0.16573688834905625,
|
|
"num_tokens": 6397227.0,
|
|
"step": 2715
|
|
},
|
|
{
|
|
"entropy": 5.742139291763306,
|
|
"epoch": 2.770249617931737,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00045903523201698684,
|
|
"loss": 5.5911,
|
|
"mean_token_accuracy": 0.16867348849773406,
|
|
"num_tokens": 6409906.0,
|
|
"step": 2720
|
|
},
|
|
{
|
|
"entropy": 5.766191387176514,
|
|
"epoch": 2.7753438614365766,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004588041429265803,
|
|
"loss": 5.5517,
|
|
"mean_token_accuracy": 0.16983173936605453,
|
|
"num_tokens": 6421922.0,
|
|
"step": 2725
|
|
},
|
|
{
|
|
"entropy": 5.676415681838989,
|
|
"epoch": 2.780438104941416,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004585724695264436,
|
|
"loss": 5.6116,
|
|
"mean_token_accuracy": 0.1660709023475647,
|
|
"num_tokens": 6433135.0,
|
|
"step": 2730
|
|
},
|
|
{
|
|
"entropy": 5.7621002197265625,
|
|
"epoch": 2.7855323484462557,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045834021255306223,
|
|
"loss": 5.6099,
|
|
"mean_token_accuracy": 0.1651996046304703,
|
|
"num_tokens": 6444399.0,
|
|
"step": 2735
|
|
},
|
|
{
|
|
"entropy": 5.748862266540527,
|
|
"epoch": 2.7906265919510953,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004581073727447762,
|
|
"loss": 5.6505,
|
|
"mean_token_accuracy": 0.1635200247168541,
|
|
"num_tokens": 6456227.0,
|
|
"step": 2740
|
|
},
|
|
{
|
|
"entropy": 5.689176321029663,
|
|
"epoch": 2.795720835455935,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004578739508417788,
|
|
"loss": 5.553,
|
|
"mean_token_accuracy": 0.17098861634731294,
|
|
"num_tokens": 6468622.0,
|
|
"step": 2745
|
|
},
|
|
{
|
|
"entropy": 5.697390842437744,
|
|
"epoch": 2.8008150789607744,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004576399475861137,
|
|
"loss": 5.6043,
|
|
"mean_token_accuracy": 0.16807106435298919,
|
|
"num_tokens": 6480408.0,
|
|
"step": 2750
|
|
},
|
|
{
|
|
"entropy": 5.71913161277771,
|
|
"epoch": 2.805909322465614,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004574053637216724,
|
|
"loss": 5.5255,
|
|
"mean_token_accuracy": 0.17133117020130156,
|
|
"num_tokens": 6492864.0,
|
|
"step": 2755
|
|
},
|
|
{
|
|
"entropy": 5.600292348861695,
|
|
"epoch": 2.8110035659704535,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004571701999941926,
|
|
"loss": 5.447,
|
|
"mean_token_accuracy": 0.17601710855960845,
|
|
"num_tokens": 6504103.0,
|
|
"step": 2760
|
|
},
|
|
{
|
|
"entropy": 5.72335729598999,
|
|
"epoch": 2.816097809475293,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.000456934457151255,
|
|
"loss": 5.6189,
|
|
"mean_token_accuracy": 0.16324349641799926,
|
|
"num_tokens": 6516560.0,
|
|
"step": 2765
|
|
},
|
|
{
|
|
"entropy": 5.620775604248047,
|
|
"epoch": 2.821192052980132,
|
|
"grad_norm": 0.98828125,
|
|
"learning_rate": 0.00045669813594228137,
|
|
"loss": 5.5689,
|
|
"mean_token_accuracy": 0.1696472182869911,
|
|
"num_tokens": 6530002.0,
|
|
"step": 2770
|
|
},
|
|
{
|
|
"entropy": 5.723550462722779,
|
|
"epoch": 2.826286296484972,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00045646123711853235,
|
|
"loss": 5.5703,
|
|
"mean_token_accuracy": 0.1710247129201889,
|
|
"num_tokens": 6542454.0,
|
|
"step": 2775
|
|
},
|
|
{
|
|
"entropy": 5.577154636383057,
|
|
"epoch": 2.8313805399898113,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00045622376143310435,
|
|
"loss": 5.5084,
|
|
"mean_token_accuracy": 0.17757378816604613,
|
|
"num_tokens": 6553385.0,
|
|
"step": 2780
|
|
},
|
|
{
|
|
"entropy": 5.698977088928222,
|
|
"epoch": 2.8364747834946513,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00045598570964092817,
|
|
"loss": 5.5105,
|
|
"mean_token_accuracy": 0.17238980084657668,
|
|
"num_tokens": 6564385.0,
|
|
"step": 2785
|
|
},
|
|
{
|
|
"entropy": 5.653533697128296,
|
|
"epoch": 2.8415690269994904,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00045574708249876547,
|
|
"loss": 5.5065,
|
|
"mean_token_accuracy": 0.17230129092931748,
|
|
"num_tokens": 6575369.0,
|
|
"step": 2790
|
|
},
|
|
{
|
|
"entropy": 5.696118783950806,
|
|
"epoch": 2.84666327050433,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045550788076520736,
|
|
"loss": 5.5799,
|
|
"mean_token_accuracy": 0.16681847721338272,
|
|
"num_tokens": 6587173.0,
|
|
"step": 2795
|
|
},
|
|
{
|
|
"entropy": 5.770565414428711,
|
|
"epoch": 2.8517575140091695,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004552681052006713,
|
|
"loss": 5.6447,
|
|
"mean_token_accuracy": 0.16493052691221238,
|
|
"num_tokens": 6598919.0,
|
|
"step": 2800
|
|
},
|
|
{
|
|
"entropy": 5.700059938430786,
|
|
"epoch": 2.856851757514009,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004550277565673992,
|
|
"loss": 5.5952,
|
|
"mean_token_accuracy": 0.1692450761795044,
|
|
"num_tokens": 6610353.0,
|
|
"step": 2805
|
|
},
|
|
{
|
|
"entropy": 5.6513769149780275,
|
|
"epoch": 2.8619460010188487,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00045478683562945457,
|
|
"loss": 5.5433,
|
|
"mean_token_accuracy": 0.17437132745981215,
|
|
"num_tokens": 6622420.0,
|
|
"step": 2810
|
|
},
|
|
{
|
|
"entropy": 5.763458251953125,
|
|
"epoch": 2.867040244523688,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004545453431527202,
|
|
"loss": 5.5752,
|
|
"mean_token_accuracy": 0.16620224118232726,
|
|
"num_tokens": 6634234.0,
|
|
"step": 2815
|
|
},
|
|
{
|
|
"entropy": 5.752091741561889,
|
|
"epoch": 2.8721344880285278,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.000454303279904896,
|
|
"loss": 5.6764,
|
|
"mean_token_accuracy": 0.1649190068244934,
|
|
"num_tokens": 6648272.0,
|
|
"step": 2820
|
|
},
|
|
{
|
|
"entropy": 5.67063422203064,
|
|
"epoch": 2.8772287315333673,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00045406064665549624,
|
|
"loss": 5.51,
|
|
"mean_token_accuracy": 0.1764917865395546,
|
|
"num_tokens": 6660114.0,
|
|
"step": 2825
|
|
},
|
|
{
|
|
"entropy": 5.702568817138672,
|
|
"epoch": 2.882322975038207,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004538174441758471,
|
|
"loss": 5.5603,
|
|
"mean_token_accuracy": 0.1660371392965317,
|
|
"num_tokens": 6670433.0,
|
|
"step": 2830
|
|
},
|
|
{
|
|
"entropy": 5.561418724060059,
|
|
"epoch": 2.8874172185430464,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00045357367323908463,
|
|
"loss": 5.4965,
|
|
"mean_token_accuracy": 0.1765263319015503,
|
|
"num_tokens": 6681918.0,
|
|
"step": 2835
|
|
},
|
|
{
|
|
"entropy": 5.8111371994018555,
|
|
"epoch": 2.892511462047886,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045332933462015156,
|
|
"loss": 5.6034,
|
|
"mean_token_accuracy": 0.1653100550174713,
|
|
"num_tokens": 6692681.0,
|
|
"step": 2840
|
|
},
|
|
{
|
|
"entropy": 5.676050043106079,
|
|
"epoch": 2.8976057055527256,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004530844290957957,
|
|
"loss": 5.5709,
|
|
"mean_token_accuracy": 0.16507604271173476,
|
|
"num_tokens": 6704454.0,
|
|
"step": 2845
|
|
},
|
|
{
|
|
"entropy": 5.707255125045776,
|
|
"epoch": 2.902699949057565,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00045283895744456694,
|
|
"loss": 5.5462,
|
|
"mean_token_accuracy": 0.1656055971980095,
|
|
"num_tokens": 6718226.0,
|
|
"step": 2850
|
|
},
|
|
{
|
|
"entropy": 5.618920516967774,
|
|
"epoch": 2.9077941925624042,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00045259292044681456,
|
|
"loss": 5.503,
|
|
"mean_token_accuracy": 0.17829408198595048,
|
|
"num_tokens": 6730507.0,
|
|
"step": 2855
|
|
},
|
|
{
|
|
"entropy": 5.661051607131958,
|
|
"epoch": 2.9128884360672442,
|
|
"grad_norm": 0.984375,
|
|
"learning_rate": 0.0004523463188846855,
|
|
"loss": 5.5569,
|
|
"mean_token_accuracy": 0.16910663843154908,
|
|
"num_tokens": 6743312.0,
|
|
"step": 2860
|
|
},
|
|
{
|
|
"entropy": 5.619609403610229,
|
|
"epoch": 2.9179826795720833,
|
|
"grad_norm": 0.95703125,
|
|
"learning_rate": 0.0004520991535421211,
|
|
"loss": 5.5532,
|
|
"mean_token_accuracy": 0.17489729076623917,
|
|
"num_tokens": 6757945.0,
|
|
"step": 2865
|
|
},
|
|
{
|
|
"entropy": 5.707130575180054,
|
|
"epoch": 2.9230769230769234,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0004518514252048552,
|
|
"loss": 5.5982,
|
|
"mean_token_accuracy": 0.1614573195576668,
|
|
"num_tokens": 6770995.0,
|
|
"step": 2870
|
|
},
|
|
{
|
|
"entropy": 5.688896751403808,
|
|
"epoch": 2.9281711665817625,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004516031346604112,
|
|
"loss": 5.5097,
|
|
"mean_token_accuracy": 0.17259131819009782,
|
|
"num_tokens": 6782117.0,
|
|
"step": 2875
|
|
},
|
|
{
|
|
"entropy": 5.613061618804932,
|
|
"epoch": 2.933265410086602,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0004513542826980999,
|
|
"loss": 5.6155,
|
|
"mean_token_accuracy": 0.16592106968164444,
|
|
"num_tokens": 6795932.0,
|
|
"step": 2880
|
|
},
|
|
{
|
|
"entropy": 5.778715896606445,
|
|
"epoch": 2.9383596535914416,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004511048701090167,
|
|
"loss": 5.5071,
|
|
"mean_token_accuracy": 0.17740725725889206,
|
|
"num_tokens": 6805708.0,
|
|
"step": 2885
|
|
},
|
|
{
|
|
"entropy": 5.677082109451294,
|
|
"epoch": 2.943453897096281,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004508548976860392,
|
|
"loss": 5.5664,
|
|
"mean_token_accuracy": 0.16885116696357727,
|
|
"num_tokens": 6816964.0,
|
|
"step": 2890
|
|
},
|
|
{
|
|
"entropy": 5.74324221611023,
|
|
"epoch": 2.9485481406011207,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.000450604366223825,
|
|
"loss": 5.6029,
|
|
"mean_token_accuracy": 0.16539741307497025,
|
|
"num_tokens": 6828330.0,
|
|
"step": 2895
|
|
},
|
|
{
|
|
"entropy": 5.676993703842163,
|
|
"epoch": 2.9536423841059603,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00045035327651880846,
|
|
"loss": 5.5803,
|
|
"mean_token_accuracy": 0.1668591395020485,
|
|
"num_tokens": 6839860.0,
|
|
"step": 2900
|
|
},
|
|
{
|
|
"entropy": 5.698193550109863,
|
|
"epoch": 2.9587366276108,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00045010162936919896,
|
|
"loss": 5.5302,
|
|
"mean_token_accuracy": 0.17305754870176315,
|
|
"num_tokens": 6850453.0,
|
|
"step": 2905
|
|
},
|
|
{
|
|
"entropy": 5.620525979995728,
|
|
"epoch": 2.9638308711156394,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004498494255749776,
|
|
"loss": 5.5215,
|
|
"mean_token_accuracy": 0.17544011920690536,
|
|
"num_tokens": 6861661.0,
|
|
"step": 2910
|
|
},
|
|
{
|
|
"entropy": 5.680759716033935,
|
|
"epoch": 2.968925114620479,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004495966659378954,
|
|
"loss": 5.5733,
|
|
"mean_token_accuracy": 0.16637389808893205,
|
|
"num_tokens": 6873474.0,
|
|
"step": 2915
|
|
},
|
|
{
|
|
"entropy": 5.704854440689087,
|
|
"epoch": 2.9740193581253185,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044934335126147016,
|
|
"loss": 5.5253,
|
|
"mean_token_accuracy": 0.17334222048521042,
|
|
"num_tokens": 6885761.0,
|
|
"step": 2920
|
|
},
|
|
{
|
|
"entropy": 5.658196449279785,
|
|
"epoch": 2.979113601630158,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004490894823509843,
|
|
"loss": 5.5551,
|
|
"mean_token_accuracy": 0.1653917744755745,
|
|
"num_tokens": 6895911.0,
|
|
"step": 2925
|
|
},
|
|
{
|
|
"entropy": 5.674737739562988,
|
|
"epoch": 2.9842078451349976,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004488350600134819,
|
|
"loss": 5.4932,
|
|
"mean_token_accuracy": 0.17815617918968202,
|
|
"num_tokens": 6907431.0,
|
|
"step": 2930
|
|
},
|
|
{
|
|
"entropy": 5.640310478210449,
|
|
"epoch": 2.989302088639837,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004485800850577667,
|
|
"loss": 5.5604,
|
|
"mean_token_accuracy": 0.17894753068685532,
|
|
"num_tokens": 6919007.0,
|
|
"step": 2935
|
|
},
|
|
{
|
|
"entropy": 5.745733547210693,
|
|
"epoch": 2.9943963321446763,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004483245582943989,
|
|
"loss": 5.5695,
|
|
"mean_token_accuracy": 0.17720169126987456,
|
|
"num_tokens": 6930194.0,
|
|
"step": 2940
|
|
},
|
|
{
|
|
"entropy": 5.655760669708252,
|
|
"epoch": 2.9994905756495163,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044806848053569314,
|
|
"loss": 5.5319,
|
|
"mean_token_accuracy": 0.17353491336107255,
|
|
"num_tokens": 6941276.0,
|
|
"step": 2945
|
|
},
|
|
{
|
|
"entropy": 5.6295300589667425,
|
|
"epoch": 3.0040753948038716,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00044781185259571544,
|
|
"loss": 5.2705,
|
|
"mean_token_accuracy": 0.19175558785597482,
|
|
"num_tokens": 6952351.0,
|
|
"step": 2950
|
|
},
|
|
{
|
|
"entropy": 5.7189483642578125,
|
|
"epoch": 3.009169638308711,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0004475546752902811,
|
|
"loss": 5.2839,
|
|
"mean_token_accuracy": 0.1852574020624161,
|
|
"num_tokens": 6965052.0,
|
|
"step": 2955
|
|
},
|
|
{
|
|
"entropy": 5.553421831130981,
|
|
"epoch": 3.0142638818135508,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00044729694943695155,
|
|
"loss": 5.1492,
|
|
"mean_token_accuracy": 0.18978555649518966,
|
|
"num_tokens": 6976662.0,
|
|
"step": 2960
|
|
},
|
|
{
|
|
"entropy": 5.652298164367676,
|
|
"epoch": 3.0193581253183903,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004470386758550321,
|
|
"loss": 5.2359,
|
|
"mean_token_accuracy": 0.18836504220962524,
|
|
"num_tokens": 6989787.0,
|
|
"step": 2965
|
|
},
|
|
{
|
|
"entropy": 5.623361349105835,
|
|
"epoch": 3.02445236882323,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004467798553655695,
|
|
"loss": 5.1504,
|
|
"mean_token_accuracy": 0.1876479685306549,
|
|
"num_tokens": 7000866.0,
|
|
"step": 2970
|
|
},
|
|
{
|
|
"entropy": 5.643063926696778,
|
|
"epoch": 3.0295466123280694,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000446520488791349,
|
|
"loss": 5.2655,
|
|
"mean_token_accuracy": 0.18362555503845215,
|
|
"num_tokens": 7012862.0,
|
|
"step": 2975
|
|
},
|
|
{
|
|
"entropy": 5.644259786605835,
|
|
"epoch": 3.034640855832909,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004462605769568915,
|
|
"loss": 5.2276,
|
|
"mean_token_accuracy": 0.185024493932724,
|
|
"num_tokens": 7025434.0,
|
|
"step": 2980
|
|
},
|
|
{
|
|
"entropy": 5.656643486022949,
|
|
"epoch": 3.0397350993377485,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004460001206884519,
|
|
"loss": 5.2497,
|
|
"mean_token_accuracy": 0.18152078241109848,
|
|
"num_tokens": 7037458.0,
|
|
"step": 2985
|
|
},
|
|
{
|
|
"entropy": 5.628327131271362,
|
|
"epoch": 3.0448293428425877,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004457391208140155,
|
|
"loss": 5.2122,
|
|
"mean_token_accuracy": 0.19196427315473558,
|
|
"num_tokens": 7049493.0,
|
|
"step": 2990
|
|
},
|
|
{
|
|
"entropy": 5.568745374679565,
|
|
"epoch": 3.049923586347427,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0004454775781632955,
|
|
"loss": 5.2348,
|
|
"mean_token_accuracy": 0.18303260207176208,
|
|
"num_tokens": 7059824.0,
|
|
"step": 2995
|
|
},
|
|
{
|
|
"entropy": 5.575043821334839,
|
|
"epoch": 3.0550178298522668,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044521549356773096,
|
|
"loss": 5.1722,
|
|
"mean_token_accuracy": 0.19056803435087205,
|
|
"num_tokens": 7070604.0,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 3.0550178298522668,
|
|
"eval_entropy": 5.41912328225595,
|
|
"eval_loss": 5.802611351013184,
|
|
"eval_mean_token_accuracy": 0.16801401122852608,
|
|
"eval_num_tokens": 7070604.0,
|
|
"eval_runtime": 2.6304,
|
|
"eval_samples_per_second": 1231.749,
|
|
"eval_steps_per_second": 153.969,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"entropy": 5.549645948410034,
|
|
"epoch": 3.0601120733571063,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004449528678604836,
|
|
"loss": 5.2267,
|
|
"mean_token_accuracy": 0.19194868505001067,
|
|
"num_tokens": 7083166.0,
|
|
"step": 3005
|
|
},
|
|
{
|
|
"entropy": 5.647813034057617,
|
|
"epoch": 3.065206316861946,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004446897018764353,
|
|
"loss": 5.2645,
|
|
"mean_token_accuracy": 0.18351886421442032,
|
|
"num_tokens": 7094749.0,
|
|
"step": 3010
|
|
},
|
|
{
|
|
"entropy": 5.535325145721435,
|
|
"epoch": 3.0703005603667854,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044442599645218566,
|
|
"loss": 5.2032,
|
|
"mean_token_accuracy": 0.18788442611694336,
|
|
"num_tokens": 7105635.0,
|
|
"step": 3015
|
|
},
|
|
{
|
|
"entropy": 5.582348203659057,
|
|
"epoch": 3.075394803871625,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00044416175242604887,
|
|
"loss": 5.2397,
|
|
"mean_token_accuracy": 0.18711521625518798,
|
|
"num_tokens": 7116972.0,
|
|
"step": 3020
|
|
},
|
|
{
|
|
"entropy": 5.534614610671997,
|
|
"epoch": 3.0804890473764646,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.0004438969706380514,
|
|
"loss": 5.1372,
|
|
"mean_token_accuracy": 0.1940589502453804,
|
|
"num_tokens": 7128085.0,
|
|
"step": 3025
|
|
},
|
|
{
|
|
"entropy": 5.55422887802124,
|
|
"epoch": 3.085583290881304,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00044363165192992947,
|
|
"loss": 5.22,
|
|
"mean_token_accuracy": 0.18709764629602432,
|
|
"num_tokens": 7139587.0,
|
|
"step": 3030
|
|
},
|
|
{
|
|
"entropy": 5.624648761749268,
|
|
"epoch": 3.0906775343861437,
|
|
"grad_norm": 0.94921875,
|
|
"learning_rate": 0.0004433657971451259,
|
|
"loss": 5.3577,
|
|
"mean_token_accuracy": 0.1773369863629341,
|
|
"num_tokens": 7152227.0,
|
|
"step": 3035
|
|
},
|
|
{
|
|
"entropy": 5.590989065170288,
|
|
"epoch": 3.0957717778909832,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00044309940712878774,
|
|
"loss": 5.2476,
|
|
"mean_token_accuracy": 0.18567178547382354,
|
|
"num_tokens": 7164203.0,
|
|
"step": 3040
|
|
},
|
|
{
|
|
"entropy": 5.6232305526733395,
|
|
"epoch": 3.100866021395823,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004428324827277637,
|
|
"loss": 5.2678,
|
|
"mean_token_accuracy": 0.18688521832227706,
|
|
"num_tokens": 7175678.0,
|
|
"step": 3045
|
|
},
|
|
{
|
|
"entropy": 5.555017471313477,
|
|
"epoch": 3.1059602649006623,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.000442565024790601,
|
|
"loss": 5.1825,
|
|
"mean_token_accuracy": 0.19310928881168365,
|
|
"num_tokens": 7187482.0,
|
|
"step": 3050
|
|
},
|
|
{
|
|
"entropy": 5.595922327041626,
|
|
"epoch": 3.111054508405502,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00044229703416754333,
|
|
"loss": 5.2407,
|
|
"mean_token_accuracy": 0.18290614187717438,
|
|
"num_tokens": 7199198.0,
|
|
"step": 3055
|
|
},
|
|
{
|
|
"entropy": 5.567435169219971,
|
|
"epoch": 3.1161487519103415,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004420285117105275,
|
|
"loss": 5.2139,
|
|
"mean_token_accuracy": 0.18910220563411712,
|
|
"num_tokens": 7209877.0,
|
|
"step": 3060
|
|
},
|
|
{
|
|
"entropy": 5.560028409957885,
|
|
"epoch": 3.121242995415181,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044175945827318097,
|
|
"loss": 5.2295,
|
|
"mean_token_accuracy": 0.18325708657503129,
|
|
"num_tokens": 7221838.0,
|
|
"step": 3065
|
|
},
|
|
{
|
|
"entropy": 5.5731603622436525,
|
|
"epoch": 3.1263372389200206,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00044148987471081933,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.18593316972255708,
|
|
"num_tokens": 7233675.0,
|
|
"step": 3070
|
|
},
|
|
{
|
|
"entropy": 5.511419582366943,
|
|
"epoch": 3.13143148242486,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00044121976188044357,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.1963437870144844,
|
|
"num_tokens": 7243888.0,
|
|
"step": 3075
|
|
},
|
|
{
|
|
"entropy": 5.505173444747925,
|
|
"epoch": 3.1365257259296992,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004409491206407367,
|
|
"loss": 5.227,
|
|
"mean_token_accuracy": 0.1918903186917305,
|
|
"num_tokens": 7256157.0,
|
|
"step": 3080
|
|
},
|
|
{
|
|
"entropy": 5.595214414596557,
|
|
"epoch": 3.141619969434539,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004406779518520622,
|
|
"loss": 5.2609,
|
|
"mean_token_accuracy": 0.18385710567235947,
|
|
"num_tokens": 7268270.0,
|
|
"step": 3085
|
|
},
|
|
{
|
|
"entropy": 5.591922044754028,
|
|
"epoch": 3.1467142129393784,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00044040625637646006,
|
|
"loss": 5.2835,
|
|
"mean_token_accuracy": 0.18403848111629487,
|
|
"num_tokens": 7281031.0,
|
|
"step": 3090
|
|
},
|
|
{
|
|
"entropy": 5.579939556121826,
|
|
"epoch": 3.151808456444218,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0004401340350776449,
|
|
"loss": 5.1745,
|
|
"mean_token_accuracy": 0.19447211027145386,
|
|
"num_tokens": 7291891.0,
|
|
"step": 3095
|
|
},
|
|
{
|
|
"entropy": 5.560171222686767,
|
|
"epoch": 3.1569026999490575,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00043986128882100286,
|
|
"loss": 5.259,
|
|
"mean_token_accuracy": 0.18227914720773697,
|
|
"num_tokens": 7303329.0,
|
|
"step": 3100
|
|
},
|
|
{
|
|
"entropy": 5.559073162078858,
|
|
"epoch": 3.161996943453897,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043958801847358874,
|
|
"loss": 5.2156,
|
|
"mean_token_accuracy": 0.19535838514566423,
|
|
"num_tokens": 7315517.0,
|
|
"step": 3105
|
|
},
|
|
{
|
|
"entropy": 5.535176849365234,
|
|
"epoch": 3.1670911869587366,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043931422490412376,
|
|
"loss": 5.1833,
|
|
"mean_token_accuracy": 0.18914204686880112,
|
|
"num_tokens": 7325795.0,
|
|
"step": 3110
|
|
},
|
|
{
|
|
"entropy": 5.525053834915161,
|
|
"epoch": 3.172185430463576,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043903990898299213,
|
|
"loss": 5.1523,
|
|
"mean_token_accuracy": 0.19022974967956544,
|
|
"num_tokens": 7337587.0,
|
|
"step": 3115
|
|
},
|
|
{
|
|
"entropy": 5.55363245010376,
|
|
"epoch": 3.1772796739684157,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00043876507158223865,
|
|
"loss": 5.2131,
|
|
"mean_token_accuracy": 0.18002987205982207,
|
|
"num_tokens": 7349806.0,
|
|
"step": 3120
|
|
},
|
|
{
|
|
"entropy": 5.607295417785645,
|
|
"epoch": 3.1823739174732553,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004384897135755663,
|
|
"loss": 5.284,
|
|
"mean_token_accuracy": 0.1749339669942856,
|
|
"num_tokens": 7362544.0,
|
|
"step": 3125
|
|
},
|
|
{
|
|
"entropy": 5.486460590362549,
|
|
"epoch": 3.187468160978095,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00043821383583833237,
|
|
"loss": 5.1578,
|
|
"mean_token_accuracy": 0.19121076613664628,
|
|
"num_tokens": 7374931.0,
|
|
"step": 3130
|
|
},
|
|
{
|
|
"entropy": 5.54609432220459,
|
|
"epoch": 3.1925624044829344,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004379374392475468,
|
|
"loss": 5.2103,
|
|
"mean_token_accuracy": 0.1884954646229744,
|
|
"num_tokens": 7385609.0,
|
|
"step": 3135
|
|
},
|
|
{
|
|
"entropy": 5.526780891418457,
|
|
"epoch": 3.197656647987774,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004376605246818691,
|
|
"loss": 5.2279,
|
|
"mean_token_accuracy": 0.1913060203194618,
|
|
"num_tokens": 7396492.0,
|
|
"step": 3140
|
|
},
|
|
{
|
|
"entropy": 5.473161888122559,
|
|
"epoch": 3.2027508914926135,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.000437383093021605,
|
|
"loss": 5.1392,
|
|
"mean_token_accuracy": 0.19311400204896928,
|
|
"num_tokens": 7409319.0,
|
|
"step": 3145
|
|
},
|
|
{
|
|
"entropy": 5.551324892044067,
|
|
"epoch": 3.207845134997453,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004371051451487042,
|
|
"loss": 5.2308,
|
|
"mean_token_accuracy": 0.18624562323093413,
|
|
"num_tokens": 7420395.0,
|
|
"step": 3150
|
|
},
|
|
{
|
|
"entropy": 5.551702928543091,
|
|
"epoch": 3.2129393785022926,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043682668194675766,
|
|
"loss": 5.2729,
|
|
"mean_token_accuracy": 0.18115414381027223,
|
|
"num_tokens": 7432949.0,
|
|
"step": 3155
|
|
},
|
|
{
|
|
"entropy": 5.546800374984741,
|
|
"epoch": 3.218033622007132,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004365477043009943,
|
|
"loss": 5.2102,
|
|
"mean_token_accuracy": 0.1954928919672966,
|
|
"num_tokens": 7444849.0,
|
|
"step": 3160
|
|
},
|
|
{
|
|
"entropy": 5.518239450454712,
|
|
"epoch": 3.2231278655119713,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00043626821309827846,
|
|
"loss": 5.2735,
|
|
"mean_token_accuracy": 0.18236422836780547,
|
|
"num_tokens": 7455736.0,
|
|
"step": 3165
|
|
},
|
|
{
|
|
"entropy": 5.531206226348877,
|
|
"epoch": 3.228222109016811,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00043598820922710727,
|
|
"loss": 5.1918,
|
|
"mean_token_accuracy": 0.18918709307909012,
|
|
"num_tokens": 7466711.0,
|
|
"step": 3170
|
|
},
|
|
{
|
|
"entropy": 5.596329593658448,
|
|
"epoch": 3.2333163525216504,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00043570769357760737,
|
|
"loss": 5.2326,
|
|
"mean_token_accuracy": 0.1849576413631439,
|
|
"num_tokens": 7478159.0,
|
|
"step": 3175
|
|
},
|
|
{
|
|
"entropy": 5.507494068145752,
|
|
"epoch": 3.23841059602649,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00043542666704153257,
|
|
"loss": 5.2151,
|
|
"mean_token_accuracy": 0.1875947281718254,
|
|
"num_tokens": 7488657.0,
|
|
"step": 3180
|
|
},
|
|
{
|
|
"entropy": 5.575895643234253,
|
|
"epoch": 3.2435048395313295,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004351451305122605,
|
|
"loss": 5.3198,
|
|
"mean_token_accuracy": 0.18274757266044617,
|
|
"num_tokens": 7499949.0,
|
|
"step": 3185
|
|
},
|
|
{
|
|
"entropy": 5.4866578578948975,
|
|
"epoch": 3.248599083036169,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00043486308488479045,
|
|
"loss": 5.1208,
|
|
"mean_token_accuracy": 0.19846710711717605,
|
|
"num_tokens": 7511013.0,
|
|
"step": 3190
|
|
},
|
|
{
|
|
"entropy": 5.507602882385254,
|
|
"epoch": 3.2536933265410086,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004345805310557397,
|
|
"loss": 5.254,
|
|
"mean_token_accuracy": 0.18965618163347245,
|
|
"num_tokens": 7522325.0,
|
|
"step": 3195
|
|
},
|
|
{
|
|
"entropy": 5.522290658950806,
|
|
"epoch": 3.258787570045848,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004342974699233412,
|
|
"loss": 5.2616,
|
|
"mean_token_accuracy": 0.18798030614852906,
|
|
"num_tokens": 7534249.0,
|
|
"step": 3200
|
|
},
|
|
{
|
|
"entropy": 5.615851545333863,
|
|
"epoch": 3.2638818135506877,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00043401390238744094,
|
|
"loss": 5.2922,
|
|
"mean_token_accuracy": 0.1917358934879303,
|
|
"num_tokens": 7545472.0,
|
|
"step": 3205
|
|
},
|
|
{
|
|
"entropy": 5.6475578308105465,
|
|
"epoch": 3.2689760570555273,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0004337298293494943,
|
|
"loss": 5.3503,
|
|
"mean_token_accuracy": 0.17914826422929764,
|
|
"num_tokens": 7557188.0,
|
|
"step": 3210
|
|
},
|
|
{
|
|
"entropy": 5.503152227401733,
|
|
"epoch": 3.274070300560367,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043344525171256395,
|
|
"loss": 5.2696,
|
|
"mean_token_accuracy": 0.18903056383132935,
|
|
"num_tokens": 7569464.0,
|
|
"step": 3215
|
|
},
|
|
{
|
|
"entropy": 5.588636445999145,
|
|
"epoch": 3.2791645440652064,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0004331601703813165,
|
|
"loss": 5.3027,
|
|
"mean_token_accuracy": 0.18719593435525894,
|
|
"num_tokens": 7581314.0,
|
|
"step": 3220
|
|
},
|
|
{
|
|
"entropy": 5.58220157623291,
|
|
"epoch": 3.284258787570046,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004328745862620198,
|
|
"loss": 5.2865,
|
|
"mean_token_accuracy": 0.18556614518165587,
|
|
"num_tokens": 7593419.0,
|
|
"step": 3225
|
|
},
|
|
{
|
|
"entropy": 5.525010967254639,
|
|
"epoch": 3.2893530310748855,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004325885002625403,
|
|
"loss": 5.265,
|
|
"mean_token_accuracy": 0.1853649988770485,
|
|
"num_tokens": 7604952.0,
|
|
"step": 3230
|
|
},
|
|
{
|
|
"entropy": 5.524147415161133,
|
|
"epoch": 3.294447274579725,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.0004323019132923396,
|
|
"loss": 5.179,
|
|
"mean_token_accuracy": 0.19637303054332733,
|
|
"num_tokens": 7616634.0,
|
|
"step": 3235
|
|
},
|
|
{
|
|
"entropy": 5.529120206832886,
|
|
"epoch": 3.299541518084564,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.0004320148262624719,
|
|
"loss": 5.315,
|
|
"mean_token_accuracy": 0.1807047724723816,
|
|
"num_tokens": 7628628.0,
|
|
"step": 3240
|
|
},
|
|
{
|
|
"entropy": 5.5997724533081055,
|
|
"epoch": 3.304635761589404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004317272400855814,
|
|
"loss": 5.2143,
|
|
"mean_token_accuracy": 0.1913510262966156,
|
|
"num_tokens": 7639211.0,
|
|
"step": 3245
|
|
},
|
|
{
|
|
"entropy": 5.510351467132568,
|
|
"epoch": 3.3097300050942433,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00043143915567589875,
|
|
"loss": 5.1926,
|
|
"mean_token_accuracy": 0.1907353952527046,
|
|
"num_tokens": 7649985.0,
|
|
"step": 3250
|
|
},
|
|
{
|
|
"entropy": 5.554406833648682,
|
|
"epoch": 3.314824248599083,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004311505739492385,
|
|
"loss": 5.2963,
|
|
"mean_token_accuracy": 0.18120518326759338,
|
|
"num_tokens": 7661280.0,
|
|
"step": 3255
|
|
},
|
|
{
|
|
"entropy": 5.500691652297974,
|
|
"epoch": 3.3199184921039224,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00043086149582299637,
|
|
"loss": 5.2951,
|
|
"mean_token_accuracy": 0.18794802874326705,
|
|
"num_tokens": 7674588.0,
|
|
"step": 3260
|
|
},
|
|
{
|
|
"entropy": 5.5257158279418945,
|
|
"epoch": 3.325012735608762,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00043057192221614604,
|
|
"loss": 5.2436,
|
|
"mean_token_accuracy": 0.19492722153663636,
|
|
"num_tokens": 7687481.0,
|
|
"step": 3265
|
|
},
|
|
{
|
|
"entropy": 5.550112056732178,
|
|
"epoch": 3.3301069791136015,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00043028185404923614,
|
|
"loss": 5.3324,
|
|
"mean_token_accuracy": 0.18479032069444656,
|
|
"num_tokens": 7699536.0,
|
|
"step": 3270
|
|
},
|
|
{
|
|
"entropy": 5.4930661678314205,
|
|
"epoch": 3.335201222618441,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004299912922443877,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.1854267880320549,
|
|
"num_tokens": 7711135.0,
|
|
"step": 3275
|
|
},
|
|
{
|
|
"entropy": 5.599230003356934,
|
|
"epoch": 3.3402954661232807,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0004297002377252908,
|
|
"loss": 5.2672,
|
|
"mean_token_accuracy": 0.1876937687397003,
|
|
"num_tokens": 7722385.0,
|
|
"step": 3280
|
|
},
|
|
{
|
|
"entropy": 5.445849323272705,
|
|
"epoch": 3.34538970962812,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00042940869141720224,
|
|
"loss": 5.2481,
|
|
"mean_token_accuracy": 0.1830771028995514,
|
|
"num_tokens": 7735177.0,
|
|
"step": 3285
|
|
},
|
|
{
|
|
"entropy": 5.567160320281983,
|
|
"epoch": 3.3504839531329598,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004291166542469418,
|
|
"loss": 5.2593,
|
|
"mean_token_accuracy": 0.18152090013027192,
|
|
"num_tokens": 7747245.0,
|
|
"step": 3290
|
|
},
|
|
{
|
|
"entropy": 5.595096158981323,
|
|
"epoch": 3.3555781966377993,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00042882412714288987,
|
|
"loss": 5.308,
|
|
"mean_token_accuracy": 0.17754118889570236,
|
|
"num_tokens": 7759267.0,
|
|
"step": 3295
|
|
},
|
|
{
|
|
"entropy": 5.528456544876098,
|
|
"epoch": 3.360672440142639,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00042853111103498433,
|
|
"loss": 5.2574,
|
|
"mean_token_accuracy": 0.18005041033029556,
|
|
"num_tokens": 7769973.0,
|
|
"step": 3300
|
|
},
|
|
{
|
|
"entropy": 5.599979305267334,
|
|
"epoch": 3.3657666836474784,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00042823760685471756,
|
|
"loss": 5.2051,
|
|
"mean_token_accuracy": 0.20038224160671234,
|
|
"num_tokens": 7780249.0,
|
|
"step": 3305
|
|
},
|
|
{
|
|
"entropy": 5.536495351791382,
|
|
"epoch": 3.370860927152318,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0004279436155351336,
|
|
"loss": 5.2336,
|
|
"mean_token_accuracy": 0.19291678369045256,
|
|
"num_tokens": 7792240.0,
|
|
"step": 3310
|
|
},
|
|
{
|
|
"entropy": 5.542982673645019,
|
|
"epoch": 3.3759551706571576,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004276491380108251,
|
|
"loss": 5.25,
|
|
"mean_token_accuracy": 0.1897607624530792,
|
|
"num_tokens": 7804996.0,
|
|
"step": 3315
|
|
},
|
|
{
|
|
"entropy": 5.567085075378418,
|
|
"epoch": 3.381049414161997,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004273541752179301,
|
|
"loss": 5.2852,
|
|
"mean_token_accuracy": 0.18530684411525727,
|
|
"num_tokens": 7816980.0,
|
|
"step": 3320
|
|
},
|
|
{
|
|
"entropy": 5.522735977172852,
|
|
"epoch": 3.3861436576668362,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00042705872809412955,
|
|
"loss": 5.3132,
|
|
"mean_token_accuracy": 0.18165917992591857,
|
|
"num_tokens": 7829401.0,
|
|
"step": 3325
|
|
},
|
|
{
|
|
"entropy": 5.573167753219605,
|
|
"epoch": 3.3912379011716762,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00042676279757864404,
|
|
"loss": 5.3148,
|
|
"mean_token_accuracy": 0.18630436509847642,
|
|
"num_tokens": 7843526.0,
|
|
"step": 3330
|
|
},
|
|
{
|
|
"entropy": 5.461372423171997,
|
|
"epoch": 3.3963321446765153,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00042646638461223076,
|
|
"loss": 5.1266,
|
|
"mean_token_accuracy": 0.2008480742573738,
|
|
"num_tokens": 7854393.0,
|
|
"step": 3335
|
|
},
|
|
{
|
|
"entropy": 5.481348848342895,
|
|
"epoch": 3.401426388181355,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004261694901371807,
|
|
"loss": 5.1767,
|
|
"mean_token_accuracy": 0.19258477091789244,
|
|
"num_tokens": 7864891.0,
|
|
"step": 3340
|
|
},
|
|
{
|
|
"entropy": 5.54749116897583,
|
|
"epoch": 3.4065206316861945,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0004258721150973155,
|
|
"loss": 5.249,
|
|
"mean_token_accuracy": 0.18663021326065063,
|
|
"num_tokens": 7875170.0,
|
|
"step": 3345
|
|
},
|
|
{
|
|
"entropy": 5.470050239562989,
|
|
"epoch": 3.411614875191034,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.0004255742604379845,
|
|
"loss": 5.2738,
|
|
"mean_token_accuracy": 0.1832395762205124,
|
|
"num_tokens": 7887605.0,
|
|
"step": 3350
|
|
},
|
|
{
|
|
"entropy": 5.551709842681885,
|
|
"epoch": 3.4167091186958736,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004252759271060618,
|
|
"loss": 5.2636,
|
|
"mean_token_accuracy": 0.1873095452785492,
|
|
"num_tokens": 7899463.0,
|
|
"step": 3355
|
|
},
|
|
{
|
|
"entropy": 5.555735349655151,
|
|
"epoch": 3.421803362200713,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00042497711604994314,
|
|
"loss": 5.2894,
|
|
"mean_token_accuracy": 0.17790587842464448,
|
|
"num_tokens": 7911897.0,
|
|
"step": 3360
|
|
},
|
|
{
|
|
"entropy": 5.496140956878662,
|
|
"epoch": 3.4268976057055527,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00042467782821954306,
|
|
"loss": 5.1786,
|
|
"mean_token_accuracy": 0.19111656844615937,
|
|
"num_tokens": 7922687.0,
|
|
"step": 3365
|
|
},
|
|
{
|
|
"entropy": 5.540413665771484,
|
|
"epoch": 3.4319918492103922,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00042437806456629154,
|
|
"loss": 5.2782,
|
|
"mean_token_accuracy": 0.18167845010757447,
|
|
"num_tokens": 7935604.0,
|
|
"step": 3370
|
|
},
|
|
{
|
|
"entropy": 5.476236295700073,
|
|
"epoch": 3.437086092715232,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004240778260431311,
|
|
"loss": 5.3414,
|
|
"mean_token_accuracy": 0.18040297478437423,
|
|
"num_tokens": 7949083.0,
|
|
"step": 3375
|
|
},
|
|
{
|
|
"entropy": 5.540979433059692,
|
|
"epoch": 3.4421803362200714,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004237771136045144,
|
|
"loss": 5.2463,
|
|
"mean_token_accuracy": 0.19353851526975632,
|
|
"num_tokens": 7962311.0,
|
|
"step": 3380
|
|
},
|
|
{
|
|
"entropy": 5.4643883228302,
|
|
"epoch": 3.447274579724911,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0004234759282064001,
|
|
"loss": 5.2112,
|
|
"mean_token_accuracy": 0.18630488961935043,
|
|
"num_tokens": 7973531.0,
|
|
"step": 3385
|
|
},
|
|
{
|
|
"entropy": 5.515484094619751,
|
|
"epoch": 3.4523688232297505,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004231742708062508,
|
|
"loss": 5.2013,
|
|
"mean_token_accuracy": 0.18727425038814544,
|
|
"num_tokens": 7985927.0,
|
|
"step": 3390
|
|
},
|
|
{
|
|
"entropy": 5.534226512908935,
|
|
"epoch": 3.45746306673459,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004228721423630292,
|
|
"loss": 5.2815,
|
|
"mean_token_accuracy": 0.18395535796880721,
|
|
"num_tokens": 7997528.0,
|
|
"step": 3395
|
|
},
|
|
{
|
|
"entropy": 5.561530447006225,
|
|
"epoch": 3.4625573102394296,
|
|
"grad_norm": 0.9921875,
|
|
"learning_rate": 0.0004225695438371958,
|
|
"loss": 5.2214,
|
|
"mean_token_accuracy": 0.1905212089419365,
|
|
"num_tokens": 8010217.0,
|
|
"step": 3400
|
|
},
|
|
{
|
|
"entropy": 5.488284683227539,
|
|
"epoch": 3.467651553744269,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004222664761907052,
|
|
"loss": 5.241,
|
|
"mean_token_accuracy": 0.19406666308641435,
|
|
"num_tokens": 8021261.0,
|
|
"step": 3405
|
|
},
|
|
{
|
|
"entropy": 5.516406059265137,
|
|
"epoch": 3.4727457972491087,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0004219629403870035,
|
|
"loss": 5.2943,
|
|
"mean_token_accuracy": 0.18987954705953597,
|
|
"num_tokens": 8034044.0,
|
|
"step": 3410
|
|
},
|
|
{
|
|
"entropy": 5.47275390625,
|
|
"epoch": 3.4778400407539483,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042165893739102504,
|
|
"loss": 5.2243,
|
|
"mean_token_accuracy": 0.19283309876918792,
|
|
"num_tokens": 8045312.0,
|
|
"step": 3415
|
|
},
|
|
{
|
|
"entropy": 5.528399705886841,
|
|
"epoch": 3.4829342842587874,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00042135446816918927,
|
|
"loss": 5.2285,
|
|
"mean_token_accuracy": 0.18459081202745437,
|
|
"num_tokens": 8057800.0,
|
|
"step": 3420
|
|
},
|
|
{
|
|
"entropy": 5.562664413452149,
|
|
"epoch": 3.488028527763627,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00042104953368939785,
|
|
"loss": 5.3129,
|
|
"mean_token_accuracy": 0.1794852212071419,
|
|
"num_tokens": 8069051.0,
|
|
"step": 3425
|
|
},
|
|
{
|
|
"entropy": 5.499901056289673,
|
|
"epoch": 3.4931227712684665,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0004207441349210315,
|
|
"loss": 5.2524,
|
|
"mean_token_accuracy": 0.1841778576374054,
|
|
"num_tokens": 8080810.0,
|
|
"step": 3430
|
|
},
|
|
{
|
|
"entropy": 5.474960803985596,
|
|
"epoch": 3.498217014773306,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00042043827283494667,
|
|
"loss": 5.2093,
|
|
"mean_token_accuracy": 0.19234214574098588,
|
|
"num_tokens": 8092421.0,
|
|
"step": 3435
|
|
},
|
|
{
|
|
"entropy": 5.5256407260894775,
|
|
"epoch": 3.5033112582781456,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0004201319484034731,
|
|
"loss": 5.2707,
|
|
"mean_token_accuracy": 0.18090263456106187,
|
|
"num_tokens": 8105384.0,
|
|
"step": 3440
|
|
},
|
|
{
|
|
"entropy": 5.569704055786133,
|
|
"epoch": 3.508405501782985,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00041982516260040994,
|
|
"loss": 5.3885,
|
|
"mean_token_accuracy": 0.17901989221572875,
|
|
"num_tokens": 8118280.0,
|
|
"step": 3445
|
|
},
|
|
{
|
|
"entropy": 5.550126409530639,
|
|
"epoch": 3.5134997452878247,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00041951791640102326,
|
|
"loss": 5.2955,
|
|
"mean_token_accuracy": 0.1825642094016075,
|
|
"num_tokens": 8129841.0,
|
|
"step": 3450
|
|
},
|
|
{
|
|
"entropy": 5.541914701461792,
|
|
"epoch": 3.5185939887926643,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004192102107820426,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.19020104110240937,
|
|
"num_tokens": 8142222.0,
|
|
"step": 3455
|
|
},
|
|
{
|
|
"entropy": 5.545864582061768,
|
|
"epoch": 3.523688232297504,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00041890204672165803,
|
|
"loss": 5.1869,
|
|
"mean_token_accuracy": 0.19447728544473647,
|
|
"num_tokens": 8152770.0,
|
|
"step": 3460
|
|
},
|
|
{
|
|
"entropy": 5.4374126434326175,
|
|
"epoch": 3.5287824758023434,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.00041859342519951696,
|
|
"loss": 5.199,
|
|
"mean_token_accuracy": 0.19057296365499496,
|
|
"num_tokens": 8165599.0,
|
|
"step": 3465
|
|
},
|
|
{
|
|
"entropy": 5.513079404830933,
|
|
"epoch": 3.533876719307183,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004182843471967212,
|
|
"loss": 5.2937,
|
|
"mean_token_accuracy": 0.18325041681528093,
|
|
"num_tokens": 8177829.0,
|
|
"step": 3470
|
|
},
|
|
{
|
|
"entropy": 5.625329065322876,
|
|
"epoch": 3.5389709628120225,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00041797481369582355,
|
|
"loss": 5.3018,
|
|
"mean_token_accuracy": 0.18605799078941346,
|
|
"num_tokens": 8190148.0,
|
|
"step": 3475
|
|
},
|
|
{
|
|
"entropy": 5.439789342880249,
|
|
"epoch": 3.544065206316862,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041766482568082486,
|
|
"loss": 5.2702,
|
|
"mean_token_accuracy": 0.18337605148553848,
|
|
"num_tokens": 8202072.0,
|
|
"step": 3480
|
|
},
|
|
{
|
|
"entropy": 5.576718997955322,
|
|
"epoch": 3.5491594498217016,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0004173543841371709,
|
|
"loss": 5.2525,
|
|
"mean_token_accuracy": 0.18726011365652084,
|
|
"num_tokens": 8213460.0,
|
|
"step": 3485
|
|
},
|
|
{
|
|
"entropy": 5.511715078353882,
|
|
"epoch": 3.554253693326541,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0004170434900517492,
|
|
"loss": 5.2118,
|
|
"mean_token_accuracy": 0.18626902848482133,
|
|
"num_tokens": 8225418.0,
|
|
"step": 3490
|
|
},
|
|
{
|
|
"entropy": 5.442403078079224,
|
|
"epoch": 3.5593479368313803,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041673214441288595,
|
|
"loss": 5.2007,
|
|
"mean_token_accuracy": 0.18773033916950227,
|
|
"num_tokens": 8236832.0,
|
|
"step": 3495
|
|
},
|
|
{
|
|
"entropy": 5.542816495895385,
|
|
"epoch": 3.5644421803362203,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0004164203482103426,
|
|
"loss": 5.2808,
|
|
"mean_token_accuracy": 0.1896682783961296,
|
|
"num_tokens": 8248655.0,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"entropy": 5.488878345489502,
|
|
"epoch": 3.5695364238410594,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004161081024353132,
|
|
"loss": 5.2439,
|
|
"mean_token_accuracy": 0.1865382358431816,
|
|
"num_tokens": 8260171.0,
|
|
"step": 3505
|
|
},
|
|
{
|
|
"entropy": 5.509292793273926,
|
|
"epoch": 3.5746306673458994,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00041579540808042096,
|
|
"loss": 5.2592,
|
|
"mean_token_accuracy": 0.18486162573099135,
|
|
"num_tokens": 8273402.0,
|
|
"step": 3510
|
|
},
|
|
{
|
|
"entropy": 5.525865793228149,
|
|
"epoch": 3.5797249108507385,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000415482266139715,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.1889800727367401,
|
|
"num_tokens": 8287594.0,
|
|
"step": 3515
|
|
},
|
|
{
|
|
"entropy": 5.521311569213867,
|
|
"epoch": 3.584819154355578,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0004151686776086673,
|
|
"loss": 5.2498,
|
|
"mean_token_accuracy": 0.1874385416507721,
|
|
"num_tokens": 8299171.0,
|
|
"step": 3520
|
|
},
|
|
{
|
|
"entropy": 5.508975267410278,
|
|
"epoch": 3.5899133978604176,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00041485464348416963,
|
|
"loss": 5.1943,
|
|
"mean_token_accuracy": 0.18564485162496566,
|
|
"num_tokens": 8310956.0,
|
|
"step": 3525
|
|
},
|
|
{
|
|
"entropy": 5.503564929962158,
|
|
"epoch": 3.595007641365257,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041454016476453017,
|
|
"loss": 5.272,
|
|
"mean_token_accuracy": 0.18728419542312622,
|
|
"num_tokens": 8322773.0,
|
|
"step": 3530
|
|
},
|
|
{
|
|
"entropy": 5.5208375453948975,
|
|
"epoch": 3.6001018848700967,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00041422524244947066,
|
|
"loss": 5.2505,
|
|
"mean_token_accuracy": 0.18359238058328628,
|
|
"num_tokens": 8334215.0,
|
|
"step": 3535
|
|
},
|
|
{
|
|
"entropy": 5.41510796546936,
|
|
"epoch": 3.6051961283749363,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0004139098775401228,
|
|
"loss": 5.1581,
|
|
"mean_token_accuracy": 0.2015395551919937,
|
|
"num_tokens": 8345051.0,
|
|
"step": 3540
|
|
},
|
|
{
|
|
"entropy": 5.518462467193603,
|
|
"epoch": 3.610290371879776,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00041359407103902556,
|
|
"loss": 5.3041,
|
|
"mean_token_accuracy": 0.18473822623491287,
|
|
"num_tokens": 8357730.0,
|
|
"step": 3545
|
|
},
|
|
{
|
|
"entropy": 5.52494797706604,
|
|
"epoch": 3.6153846153846154,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004132778239501214,
|
|
"loss": 5.2587,
|
|
"mean_token_accuracy": 0.18364583998918532,
|
|
"num_tokens": 8369656.0,
|
|
"step": 3550
|
|
},
|
|
{
|
|
"entropy": 5.5314170837402346,
|
|
"epoch": 3.620478858889455,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00041296113727875346,
|
|
"loss": 5.2691,
|
|
"mean_token_accuracy": 0.187174428999424,
|
|
"num_tokens": 8381112.0,
|
|
"step": 3555
|
|
},
|
|
{
|
|
"entropy": 5.5272698402404785,
|
|
"epoch": 3.6255731023942945,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00041264401203166266,
|
|
"loss": 5.2299,
|
|
"mean_token_accuracy": 0.18929228484630584,
|
|
"num_tokens": 8393248.0,
|
|
"step": 3560
|
|
},
|
|
{
|
|
"entropy": 5.430791330337525,
|
|
"epoch": 3.630667345899134,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00041232644921698357,
|
|
"loss": 5.2376,
|
|
"mean_token_accuracy": 0.18975220918655394,
|
|
"num_tokens": 8403976.0,
|
|
"step": 3565
|
|
},
|
|
{
|
|
"entropy": 5.616153335571289,
|
|
"epoch": 3.6357615894039736,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004120084498442425,
|
|
"loss": 5.3229,
|
|
"mean_token_accuracy": 0.17662625312805175,
|
|
"num_tokens": 8416068.0,
|
|
"step": 3570
|
|
},
|
|
{
|
|
"entropy": 5.534983062744141,
|
|
"epoch": 3.640855832908813,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.00041169001492435275,
|
|
"loss": 5.239,
|
|
"mean_token_accuracy": 0.18605359196662902,
|
|
"num_tokens": 8428822.0,
|
|
"step": 3575
|
|
},
|
|
{
|
|
"entropy": 5.437550973892212,
|
|
"epoch": 3.6459500764136523,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0004113711454696128,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.188331900537014,
|
|
"num_tokens": 8440888.0,
|
|
"step": 3580
|
|
},
|
|
{
|
|
"entropy": 5.576711416244507,
|
|
"epoch": 3.6510443199184923,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00041105184249370236,
|
|
"loss": 5.2183,
|
|
"mean_token_accuracy": 0.192132468521595,
|
|
"num_tokens": 8452734.0,
|
|
"step": 3585
|
|
},
|
|
{
|
|
"entropy": 5.401757669448853,
|
|
"epoch": 3.6561385634233314,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0004107321070116792,
|
|
"loss": 5.2469,
|
|
"mean_token_accuracy": 0.19269947111606597,
|
|
"num_tokens": 8463472.0,
|
|
"step": 3590
|
|
},
|
|
{
|
|
"entropy": 5.483456325531006,
|
|
"epoch": 3.6612328069281714,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00041041194003997616,
|
|
"loss": 5.2337,
|
|
"mean_token_accuracy": 0.18678512722253798,
|
|
"num_tokens": 8475205.0,
|
|
"step": 3595
|
|
},
|
|
{
|
|
"entropy": 5.476074504852295,
|
|
"epoch": 3.6663270504330105,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00041009134259639766,
|
|
"loss": 5.1606,
|
|
"mean_token_accuracy": 0.2060258686542511,
|
|
"num_tokens": 8486376.0,
|
|
"step": 3600
|
|
},
|
|
{
|
|
"entropy": 5.4377318859100345,
|
|
"epoch": 3.67142129393785,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0004097703157001166,
|
|
"loss": 5.2791,
|
|
"mean_token_accuracy": 0.18568421453237532,
|
|
"num_tokens": 8498507.0,
|
|
"step": 3605
|
|
},
|
|
{
|
|
"entropy": 5.516147184371948,
|
|
"epoch": 3.6765155374426897,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0004094488603716712,
|
|
"loss": 5.2842,
|
|
"mean_token_accuracy": 0.1896775558590889,
|
|
"num_tokens": 8509675.0,
|
|
"step": 3610
|
|
},
|
|
{
|
|
"entropy": 5.468469905853271,
|
|
"epoch": 3.681609780947529,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0004091269776329614,
|
|
"loss": 5.2325,
|
|
"mean_token_accuracy": 0.190626423060894,
|
|
"num_tokens": 8520606.0,
|
|
"step": 3615
|
|
},
|
|
{
|
|
"entropy": 5.528071928024292,
|
|
"epoch": 3.6867040244523688,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004088046685072462,
|
|
"loss": 5.2967,
|
|
"mean_token_accuracy": 0.17715199142694474,
|
|
"num_tokens": 8532115.0,
|
|
"step": 3620
|
|
},
|
|
{
|
|
"entropy": 5.458847332000732,
|
|
"epoch": 3.6917982679572083,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00040848193401914,
|
|
"loss": 5.1734,
|
|
"mean_token_accuracy": 0.1924549773335457,
|
|
"num_tokens": 8543875.0,
|
|
"step": 3625
|
|
},
|
|
{
|
|
"entropy": 5.506938552856445,
|
|
"epoch": 3.696892511462048,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00040815877519460923,
|
|
"loss": 5.2784,
|
|
"mean_token_accuracy": 0.18663368374109268,
|
|
"num_tokens": 8555293.0,
|
|
"step": 3630
|
|
},
|
|
{
|
|
"entropy": 5.561899614334107,
|
|
"epoch": 3.7019867549668874,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00040783519306096934,
|
|
"loss": 5.2296,
|
|
"mean_token_accuracy": 0.18472584784030915,
|
|
"num_tokens": 8567353.0,
|
|
"step": 3635
|
|
},
|
|
{
|
|
"entropy": 5.39827299118042,
|
|
"epoch": 3.707080998471727,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0004075111886468817,
|
|
"loss": 5.2389,
|
|
"mean_token_accuracy": 0.1947633996605873,
|
|
"num_tokens": 8578973.0,
|
|
"step": 3640
|
|
},
|
|
{
|
|
"entropy": 5.418034267425537,
|
|
"epoch": 3.7121752419765666,
|
|
"grad_norm": 1.0390625,
|
|
"learning_rate": 0.00040718676298234975,
|
|
"loss": 5.2286,
|
|
"mean_token_accuracy": 0.1891040861606598,
|
|
"num_tokens": 8590770.0,
|
|
"step": 3645
|
|
},
|
|
{
|
|
"entropy": 5.598950004577636,
|
|
"epoch": 3.717269485481406,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00040686191709871637,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.186395862698555,
|
|
"num_tokens": 8602483.0,
|
|
"step": 3650
|
|
},
|
|
{
|
|
"entropy": 5.5492682456970215,
|
|
"epoch": 3.7223637289862457,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0004065366520286601,
|
|
"loss": 5.3589,
|
|
"mean_token_accuracy": 0.1785549193620682,
|
|
"num_tokens": 8613859.0,
|
|
"step": 3655
|
|
},
|
|
{
|
|
"entropy": 5.419504117965698,
|
|
"epoch": 3.7274579724910852,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0004062109688061921,
|
|
"loss": 5.1896,
|
|
"mean_token_accuracy": 0.19611713886260987,
|
|
"num_tokens": 8625988.0,
|
|
"step": 3660
|
|
},
|
|
{
|
|
"entropy": 5.516335535049438,
|
|
"epoch": 3.7325522159959243,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040588486846665316,
|
|
"loss": 5.2307,
|
|
"mean_token_accuracy": 0.1934867724776268,
|
|
"num_tokens": 8637777.0,
|
|
"step": 3665
|
|
},
|
|
{
|
|
"entropy": 5.492888689041138,
|
|
"epoch": 3.7376464595007644,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0004055583520467096,
|
|
"loss": 5.2769,
|
|
"mean_token_accuracy": 0.1850634515285492,
|
|
"num_tokens": 8648888.0,
|
|
"step": 3670
|
|
},
|
|
{
|
|
"entropy": 5.57908992767334,
|
|
"epoch": 3.7427407030056035,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00040523142058435064,
|
|
"loss": 5.2907,
|
|
"mean_token_accuracy": 0.1873990163207054,
|
|
"num_tokens": 8661530.0,
|
|
"step": 3675
|
|
},
|
|
{
|
|
"entropy": 5.464709615707397,
|
|
"epoch": 3.7478349465104435,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00040490407511888495,
|
|
"loss": 5.2031,
|
|
"mean_token_accuracy": 0.1941288873553276,
|
|
"num_tokens": 8672246.0,
|
|
"step": 3680
|
|
},
|
|
{
|
|
"entropy": 5.426874494552612,
|
|
"epoch": 3.7529291900152826,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004045763166909374,
|
|
"loss": 5.1978,
|
|
"mean_token_accuracy": 0.20026761144399643,
|
|
"num_tokens": 8683621.0,
|
|
"step": 3685
|
|
},
|
|
{
|
|
"entropy": 5.513602352142334,
|
|
"epoch": 3.758023433520122,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0004042481463424453,
|
|
"loss": 5.2819,
|
|
"mean_token_accuracy": 0.18913469314575196,
|
|
"num_tokens": 8695411.0,
|
|
"step": 3690
|
|
},
|
|
{
|
|
"entropy": 5.5545814037323,
|
|
"epoch": 3.7631176770249617,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0004039195651166558,
|
|
"loss": 5.2622,
|
|
"mean_token_accuracy": 0.18592415004968643,
|
|
"num_tokens": 8706754.0,
|
|
"step": 3695
|
|
},
|
|
{
|
|
"entropy": 5.468422842025757,
|
|
"epoch": 3.7682119205298013,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0004035905740581222,
|
|
"loss": 5.2677,
|
|
"mean_token_accuracy": 0.185578353703022,
|
|
"num_tokens": 8718608.0,
|
|
"step": 3700
|
|
},
|
|
{
|
|
"entropy": 5.568784236907959,
|
|
"epoch": 3.773306164034641,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00040326117421270055,
|
|
"loss": 5.3254,
|
|
"mean_token_accuracy": 0.18522879481315613,
|
|
"num_tokens": 8731542.0,
|
|
"step": 3705
|
|
},
|
|
{
|
|
"entropy": 5.528738641738892,
|
|
"epoch": 3.7784004075394804,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004029313666275463,
|
|
"loss": 5.3597,
|
|
"mean_token_accuracy": 0.17645610719919205,
|
|
"num_tokens": 8744531.0,
|
|
"step": 3710
|
|
},
|
|
{
|
|
"entropy": 5.468981552124023,
|
|
"epoch": 3.78349465104432,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0004026011523511112,
|
|
"loss": 5.2849,
|
|
"mean_token_accuracy": 0.18441477715969085,
|
|
"num_tokens": 8756807.0,
|
|
"step": 3715
|
|
},
|
|
{
|
|
"entropy": 5.47030348777771,
|
|
"epoch": 3.7885888945491595,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00040227053243314015,
|
|
"loss": 5.1461,
|
|
"mean_token_accuracy": 0.19421147406101227,
|
|
"num_tokens": 8767687.0,
|
|
"step": 3720
|
|
},
|
|
{
|
|
"entropy": 5.39888825416565,
|
|
"epoch": 3.793683138053999,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004019395079246672,
|
|
"loss": 5.1934,
|
|
"mean_token_accuracy": 0.19167042374610901,
|
|
"num_tokens": 8778662.0,
|
|
"step": 3725
|
|
},
|
|
{
|
|
"entropy": 5.544881296157837,
|
|
"epoch": 3.7987773815588386,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.00040160807987801265,
|
|
"loss": 5.2821,
|
|
"mean_token_accuracy": 0.1814683273434639,
|
|
"num_tokens": 8791801.0,
|
|
"step": 3730
|
|
},
|
|
{
|
|
"entropy": 5.420738220214844,
|
|
"epoch": 3.803871625063678,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00040127624934677966,
|
|
"loss": 5.208,
|
|
"mean_token_accuracy": 0.19865028858184813,
|
|
"num_tokens": 8804404.0,
|
|
"step": 3735
|
|
},
|
|
{
|
|
"entropy": 5.537355709075928,
|
|
"epoch": 3.8089658685685177,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.000400944017385851,
|
|
"loss": 5.2926,
|
|
"mean_token_accuracy": 0.17979726940393448,
|
|
"num_tokens": 8816862.0,
|
|
"step": 3740
|
|
},
|
|
{
|
|
"entropy": 5.56112961769104,
|
|
"epoch": 3.8140601120733573,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00040061138505138546,
|
|
"loss": 5.2244,
|
|
"mean_token_accuracy": 0.1937735751271248,
|
|
"num_tokens": 8827579.0,
|
|
"step": 3745
|
|
},
|
|
{
|
|
"entropy": 5.470252895355225,
|
|
"epoch": 3.8191543555781964,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0004002783534008147,
|
|
"loss": 5.2228,
|
|
"mean_token_accuracy": 0.1811963737010956,
|
|
"num_tokens": 8839191.0,
|
|
"step": 3750
|
|
},
|
|
{
|
|
"entropy": 5.483394384384155,
|
|
"epoch": 3.8242485990830364,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00039994492349283966,
|
|
"loss": 5.2695,
|
|
"mean_token_accuracy": 0.19081393182277678,
|
|
"num_tokens": 8851936.0,
|
|
"step": 3755
|
|
},
|
|
{
|
|
"entropy": 5.4727373123168945,
|
|
"epoch": 3.8293428425878755,
|
|
"grad_norm": 0.96484375,
|
|
"learning_rate": 0.0003996110963874274,
|
|
"loss": 5.2751,
|
|
"mean_token_accuracy": 0.186391943693161,
|
|
"num_tokens": 8863575.0,
|
|
"step": 3760
|
|
},
|
|
{
|
|
"entropy": 5.491970539093018,
|
|
"epoch": 3.8344370860927155,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00039927687314580783,
|
|
"loss": 5.2298,
|
|
"mean_token_accuracy": 0.19174681305885316,
|
|
"num_tokens": 8874015.0,
|
|
"step": 3765
|
|
},
|
|
{
|
|
"entropy": 5.407588148117066,
|
|
"epoch": 3.8395313295975546,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039894225483047,
|
|
"loss": 5.1358,
|
|
"mean_token_accuracy": 0.19729458540678024,
|
|
"num_tokens": 8885373.0,
|
|
"step": 3770
|
|
},
|
|
{
|
|
"entropy": 5.436512517929077,
|
|
"epoch": 3.844625573102394,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003986072425051587,
|
|
"loss": 5.1827,
|
|
"mean_token_accuracy": 0.189084729552269,
|
|
"num_tokens": 8898238.0,
|
|
"step": 3775
|
|
},
|
|
{
|
|
"entropy": 5.512228155136109,
|
|
"epoch": 3.8497198166072337,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039827183723487156,
|
|
"loss": 5.3088,
|
|
"mean_token_accuracy": 0.1816224992275238,
|
|
"num_tokens": 8910832.0,
|
|
"step": 3780
|
|
},
|
|
{
|
|
"entropy": 5.378589153289795,
|
|
"epoch": 3.8548140601120733,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039793604008585536,
|
|
"loss": 5.2078,
|
|
"mean_token_accuracy": 0.19663746356964112,
|
|
"num_tokens": 8923064.0,
|
|
"step": 3785
|
|
},
|
|
{
|
|
"entropy": 5.4635009765625,
|
|
"epoch": 3.859908303616913,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003975998521256026,
|
|
"loss": 5.2515,
|
|
"mean_token_accuracy": 0.19014426916837693,
|
|
"num_tokens": 8935871.0,
|
|
"step": 3790
|
|
},
|
|
{
|
|
"entropy": 5.534381103515625,
|
|
"epoch": 3.8650025471217524,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000397263274422848,
|
|
"loss": 5.3266,
|
|
"mean_token_accuracy": 0.17764779478311538,
|
|
"num_tokens": 8948170.0,
|
|
"step": 3795
|
|
},
|
|
{
|
|
"entropy": 5.550649785995484,
|
|
"epoch": 3.870096790626592,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003969263080475657,
|
|
"loss": 5.2314,
|
|
"mean_token_accuracy": 0.19125903397798538,
|
|
"num_tokens": 8959804.0,
|
|
"step": 3800
|
|
},
|
|
{
|
|
"entropy": 5.502713394165039,
|
|
"epoch": 3.8751910341314315,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00039658895407096483,
|
|
"loss": 5.2444,
|
|
"mean_token_accuracy": 0.1908938929438591,
|
|
"num_tokens": 8971732.0,
|
|
"step": 3805
|
|
},
|
|
{
|
|
"entropy": 5.461979722976684,
|
|
"epoch": 3.880285277636271,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003962512135654871,
|
|
"loss": 5.215,
|
|
"mean_token_accuracy": 0.19535126090049743,
|
|
"num_tokens": 8982084.0,
|
|
"step": 3810
|
|
},
|
|
{
|
|
"entropy": 5.397824001312256,
|
|
"epoch": 3.8853795211411106,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00039591308760480293,
|
|
"loss": 5.2059,
|
|
"mean_token_accuracy": 0.18994577676057817,
|
|
"num_tokens": 8993165.0,
|
|
"step": 3815
|
|
},
|
|
{
|
|
"entropy": 5.515556478500367,
|
|
"epoch": 3.89047376464595,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00039557457726380803,
|
|
"loss": 5.2184,
|
|
"mean_token_accuracy": 0.195502308011055,
|
|
"num_tokens": 9004496.0,
|
|
"step": 3820
|
|
},
|
|
{
|
|
"entropy": 5.538780927658081,
|
|
"epoch": 3.8955680081507897,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00039523568361862007,
|
|
"loss": 5.3244,
|
|
"mean_token_accuracy": 0.1835426300764084,
|
|
"num_tokens": 9015643.0,
|
|
"step": 3825
|
|
},
|
|
{
|
|
"entropy": 5.461220121383667,
|
|
"epoch": 3.9006622516556293,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00039489640774657527,
|
|
"loss": 5.1584,
|
|
"mean_token_accuracy": 0.19543965756893159,
|
|
"num_tokens": 9027469.0,
|
|
"step": 3830
|
|
},
|
|
{
|
|
"entropy": 5.631522130966187,
|
|
"epoch": 3.9057564951604684,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00039455675072622485,
|
|
"loss": 5.4902,
|
|
"mean_token_accuracy": 0.17203960716724395,
|
|
"num_tokens": 9041908.0,
|
|
"step": 3835
|
|
},
|
|
{
|
|
"entropy": 5.4944297790527346,
|
|
"epoch": 3.9108507386653084,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003942167136373317,
|
|
"loss": 5.2694,
|
|
"mean_token_accuracy": 0.1795383408665657,
|
|
"num_tokens": 9053467.0,
|
|
"step": 3840
|
|
},
|
|
{
|
|
"entropy": 5.45777325630188,
|
|
"epoch": 3.9159449821701475,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003938762975608671,
|
|
"loss": 5.2547,
|
|
"mean_token_accuracy": 0.19381844997406006,
|
|
"num_tokens": 9064339.0,
|
|
"step": 3845
|
|
},
|
|
{
|
|
"entropy": 5.498428583145142,
|
|
"epoch": 3.9210392256749875,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003935355035790071,
|
|
"loss": 5.3093,
|
|
"mean_token_accuracy": 0.1896309196949005,
|
|
"num_tokens": 9076842.0,
|
|
"step": 3850
|
|
},
|
|
{
|
|
"entropy": 5.508812952041626,
|
|
"epoch": 3.9261334691798266,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00039319433277512866,
|
|
"loss": 5.2573,
|
|
"mean_token_accuracy": 0.1900939166545868,
|
|
"num_tokens": 9089558.0,
|
|
"step": 3855
|
|
},
|
|
{
|
|
"entropy": 5.54724349975586,
|
|
"epoch": 3.931227712684666,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00039285278623380746,
|
|
"loss": 5.2818,
|
|
"mean_token_accuracy": 0.1825125426054001,
|
|
"num_tokens": 9100266.0,
|
|
"step": 3860
|
|
},
|
|
{
|
|
"entropy": 5.536986923217773,
|
|
"epoch": 3.9363219561895058,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00039251086504081285,
|
|
"loss": 5.3187,
|
|
"mean_token_accuracy": 0.18152401745319366,
|
|
"num_tokens": 9112821.0,
|
|
"step": 3865
|
|
},
|
|
{
|
|
"entropy": 5.5278558254241945,
|
|
"epoch": 3.9414161996943453,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00039216857028310576,
|
|
"loss": 5.314,
|
|
"mean_token_accuracy": 0.17746179401874543,
|
|
"num_tokens": 9123559.0,
|
|
"step": 3870
|
|
},
|
|
{
|
|
"entropy": 5.5341661930084225,
|
|
"epoch": 3.946510443199185,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003918259030488342,
|
|
"loss": 5.2446,
|
|
"mean_token_accuracy": 0.19009119272232056,
|
|
"num_tokens": 9134707.0,
|
|
"step": 3875
|
|
},
|
|
{
|
|
"entropy": 5.516203212738037,
|
|
"epoch": 3.9516046867040244,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039148286442733073,
|
|
"loss": 5.1927,
|
|
"mean_token_accuracy": 0.1919657051563263,
|
|
"num_tokens": 9146101.0,
|
|
"step": 3880
|
|
},
|
|
{
|
|
"entropy": 5.407664966583252,
|
|
"epoch": 3.956698930208864,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003911394555091083,
|
|
"loss": 5.231,
|
|
"mean_token_accuracy": 0.18863639384508132,
|
|
"num_tokens": 9157394.0,
|
|
"step": 3885
|
|
},
|
|
{
|
|
"entropy": 5.455411291122436,
|
|
"epoch": 3.9617931737137035,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00039079567738585703,
|
|
"loss": 5.1821,
|
|
"mean_token_accuracy": 0.19024809300899506,
|
|
"num_tokens": 9168851.0,
|
|
"step": 3890
|
|
},
|
|
{
|
|
"entropy": 5.420403385162354,
|
|
"epoch": 3.966887417218543,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003904515311504407,
|
|
"loss": 5.266,
|
|
"mean_token_accuracy": 0.18814214915037156,
|
|
"num_tokens": 9180754.0,
|
|
"step": 3895
|
|
},
|
|
{
|
|
"entropy": 5.512432527542114,
|
|
"epoch": 3.9719816607233827,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00039010701789689344,
|
|
"loss": 5.217,
|
|
"mean_token_accuracy": 0.18813476711511612,
|
|
"num_tokens": 9191472.0,
|
|
"step": 3900
|
|
},
|
|
{
|
|
"entropy": 5.5274131298065186,
|
|
"epoch": 3.977075904228222,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003897621387204161,
|
|
"loss": 5.2487,
|
|
"mean_token_accuracy": 0.18681145161390306,
|
|
"num_tokens": 9202761.0,
|
|
"step": 3905
|
|
},
|
|
{
|
|
"entropy": 5.483681058883667,
|
|
"epoch": 3.9821701477330618,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.0003894168947173727,
|
|
"loss": 5.2887,
|
|
"mean_token_accuracy": 0.18652074933052062,
|
|
"num_tokens": 9214980.0,
|
|
"step": 3910
|
|
},
|
|
{
|
|
"entropy": 5.582879972457886,
|
|
"epoch": 3.9872643912379013,
|
|
"grad_norm": 0.98046875,
|
|
"learning_rate": 0.00038907128698528705,
|
|
"loss": 5.3682,
|
|
"mean_token_accuracy": 0.17961732745170594,
|
|
"num_tokens": 9227715.0,
|
|
"step": 3915
|
|
},
|
|
{
|
|
"entropy": 5.613658332824707,
|
|
"epoch": 3.9923586347427404,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003887253166228394,
|
|
"loss": 5.3189,
|
|
"mean_token_accuracy": 0.18346491008996962,
|
|
"num_tokens": 9239994.0,
|
|
"step": 3920
|
|
},
|
|
{
|
|
"entropy": 5.4605425834655765,
|
|
"epoch": 3.9974528782475804,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00038837898472986247,
|
|
"loss": 5.2174,
|
|
"mean_token_accuracy": 0.1947176441550255,
|
|
"num_tokens": 9250950.0,
|
|
"step": 3925
|
|
},
|
|
{
|
|
"entropy": 5.400463898976644,
|
|
"epoch": 4.002037697401936,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00038803229240733886,
|
|
"loss": 5.0589,
|
|
"mean_token_accuracy": 0.2039177401198281,
|
|
"num_tokens": 9260873.0,
|
|
"step": 3930
|
|
},
|
|
{
|
|
"entropy": 5.412091779708862,
|
|
"epoch": 4.007131940906775,
|
|
"grad_norm": 0.97265625,
|
|
"learning_rate": 0.0003876852407573962,
|
|
"loss": 4.8795,
|
|
"mean_token_accuracy": 0.20995136052370073,
|
|
"num_tokens": 9273272.0,
|
|
"step": 3935
|
|
},
|
|
{
|
|
"entropy": 5.468007755279541,
|
|
"epoch": 4.012226184411615,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000387337830883305,
|
|
"loss": 4.9742,
|
|
"mean_token_accuracy": 0.20957242995500563,
|
|
"num_tokens": 9284616.0,
|
|
"step": 3940
|
|
},
|
|
{
|
|
"entropy": 5.499238300323486,
|
|
"epoch": 4.017320427916454,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003869900638894743,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.20340884774923323,
|
|
"num_tokens": 9296284.0,
|
|
"step": 3945
|
|
},
|
|
{
|
|
"entropy": 5.468540143966675,
|
|
"epoch": 4.022414671421294,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.00038664194088144867,
|
|
"loss": 4.9631,
|
|
"mean_token_accuracy": 0.2030803680419922,
|
|
"num_tokens": 9308654.0,
|
|
"step": 3950
|
|
},
|
|
{
|
|
"entropy": 5.408632469177246,
|
|
"epoch": 4.027508914926133,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.000386293462965904,
|
|
"loss": 4.8771,
|
|
"mean_token_accuracy": 0.20919120609760283,
|
|
"num_tokens": 9320311.0,
|
|
"step": 3955
|
|
},
|
|
{
|
|
"entropy": 5.437016344070434,
|
|
"epoch": 4.032603158430973,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003859446312506449,
|
|
"loss": 4.9524,
|
|
"mean_token_accuracy": 0.20371827483177185,
|
|
"num_tokens": 9332859.0,
|
|
"step": 3960
|
|
},
|
|
{
|
|
"entropy": 5.388468408584595,
|
|
"epoch": 4.037697401935812,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003855954468446003,
|
|
"loss": 4.9063,
|
|
"mean_token_accuracy": 0.20431233793497086,
|
|
"num_tokens": 9344365.0,
|
|
"step": 3965
|
|
},
|
|
{
|
|
"entropy": 5.427544116973877,
|
|
"epoch": 4.042791645440652,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00038524591085782063,
|
|
"loss": 4.9088,
|
|
"mean_token_accuracy": 0.20859533548355103,
|
|
"num_tokens": 9357099.0,
|
|
"step": 3970
|
|
},
|
|
{
|
|
"entropy": 5.442325067520142,
|
|
"epoch": 4.047885888945491,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003848960244014738,
|
|
"loss": 4.9335,
|
|
"mean_token_accuracy": 0.21040388345718383,
|
|
"num_tokens": 9368764.0,
|
|
"step": 3975
|
|
},
|
|
{
|
|
"entropy": 5.329502248764038,
|
|
"epoch": 4.052980132450331,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0003845457885878421,
|
|
"loss": 4.9191,
|
|
"mean_token_accuracy": 0.21028400659561158,
|
|
"num_tokens": 9380853.0,
|
|
"step": 3980
|
|
},
|
|
{
|
|
"entropy": 5.448209953308106,
|
|
"epoch": 4.0580743759551705,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003841952045303179,
|
|
"loss": 4.9592,
|
|
"mean_token_accuracy": 0.2060717061161995,
|
|
"num_tokens": 9393137.0,
|
|
"step": 3985
|
|
},
|
|
{
|
|
"entropy": 5.4685770034790036,
|
|
"epoch": 4.0631686194600105,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003838442733434013,
|
|
"loss": 4.9299,
|
|
"mean_token_accuracy": 0.2060433492064476,
|
|
"num_tokens": 9404966.0,
|
|
"step": 3990
|
|
},
|
|
{
|
|
"entropy": 5.3884618282318115,
|
|
"epoch": 4.06826286296485,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00038349299614269544,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.20057457238435744,
|
|
"num_tokens": 9417258.0,
|
|
"step": 3995
|
|
},
|
|
{
|
|
"entropy": 5.483215808868408,
|
|
"epoch": 4.07335710646969,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003831413740449037,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.20822958648204803,
|
|
"num_tokens": 9428281.0,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 4.07335710646969,
|
|
"eval_entropy": 5.2528078196961205,
|
|
"eval_loss": 5.71898078918457,
|
|
"eval_mean_token_accuracy": 0.17490717739234735,
|
|
"eval_num_tokens": 9428281.0,
|
|
"eval_runtime": 2.6333,
|
|
"eval_samples_per_second": 1230.393,
|
|
"eval_steps_per_second": 153.799,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"entropy": 5.334121370315552,
|
|
"epoch": 4.078451349974529,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003827894081678255,
|
|
"loss": 4.9259,
|
|
"mean_token_accuracy": 0.2099289447069168,
|
|
"num_tokens": 9440355.0,
|
|
"step": 4005
|
|
},
|
|
{
|
|
"entropy": 5.400337791442871,
|
|
"epoch": 4.083545593479369,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003824370996303538,
|
|
"loss": 4.9341,
|
|
"mean_token_accuracy": 0.20776019096374512,
|
|
"num_tokens": 9451752.0,
|
|
"step": 4010
|
|
},
|
|
{
|
|
"entropy": 5.42243127822876,
|
|
"epoch": 4.088639836984208,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00038208444955247005,
|
|
"loss": 4.9616,
|
|
"mean_token_accuracy": 0.2075841248035431,
|
|
"num_tokens": 9463794.0,
|
|
"step": 4015
|
|
},
|
|
{
|
|
"entropy": 5.3176172256469725,
|
|
"epoch": 4.093734080489047,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003817314590552421,
|
|
"loss": 4.8666,
|
|
"mean_token_accuracy": 0.21592865139245987,
|
|
"num_tokens": 9476035.0,
|
|
"step": 4020
|
|
},
|
|
{
|
|
"entropy": 5.382970237731934,
|
|
"epoch": 4.098828323993887,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00038137812926081986,
|
|
"loss": 4.9423,
|
|
"mean_token_accuracy": 0.2027551755309105,
|
|
"num_tokens": 9488590.0,
|
|
"step": 4025
|
|
},
|
|
{
|
|
"entropy": 5.443391036987305,
|
|
"epoch": 4.103922567498726,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003810244612924314,
|
|
"loss": 4.9894,
|
|
"mean_token_accuracy": 0.20310055762529372,
|
|
"num_tokens": 9500211.0,
|
|
"step": 4030
|
|
},
|
|
{
|
|
"entropy": 5.470500469207764,
|
|
"epoch": 4.109016811003566,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003806704562743805,
|
|
"loss": 5.0542,
|
|
"mean_token_accuracy": 0.19425401985645294,
|
|
"num_tokens": 9513635.0,
|
|
"step": 4035
|
|
},
|
|
{
|
|
"entropy": 5.451704645156861,
|
|
"epoch": 4.114111054508405,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003803161153320418,
|
|
"loss": 4.9213,
|
|
"mean_token_accuracy": 0.21072042882442474,
|
|
"num_tokens": 9527466.0,
|
|
"step": 4040
|
|
},
|
|
{
|
|
"entropy": 5.395625066757202,
|
|
"epoch": 4.119205298013245,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00037996143959185847,
|
|
"loss": 4.9038,
|
|
"mean_token_accuracy": 0.21320422291755675,
|
|
"num_tokens": 9537478.0,
|
|
"step": 4045
|
|
},
|
|
{
|
|
"entropy": 5.357009792327881,
|
|
"epoch": 4.124299541518084,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037960643018133743,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.20286102443933487,
|
|
"num_tokens": 9549645.0,
|
|
"step": 4050
|
|
},
|
|
{
|
|
"entropy": 5.390327024459839,
|
|
"epoch": 4.129393785022924,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00037925108822904667,
|
|
"loss": 4.9085,
|
|
"mean_token_accuracy": 0.21244561672210693,
|
|
"num_tokens": 9561681.0,
|
|
"step": 4055
|
|
},
|
|
{
|
|
"entropy": 5.335243654251099,
|
|
"epoch": 4.134488028527763,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003788954148646112,
|
|
"loss": 4.8876,
|
|
"mean_token_accuracy": 0.21486562341451645,
|
|
"num_tokens": 9573087.0,
|
|
"step": 4060
|
|
},
|
|
{
|
|
"entropy": 5.394258499145508,
|
|
"epoch": 4.139582272032603,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037853941121870964,
|
|
"loss": 4.946,
|
|
"mean_token_accuracy": 0.20178547948598863,
|
|
"num_tokens": 9584662.0,
|
|
"step": 4065
|
|
},
|
|
{
|
|
"entropy": 5.41005687713623,
|
|
"epoch": 4.1446765155374425,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003781830784230704,
|
|
"loss": 4.9677,
|
|
"mean_token_accuracy": 0.21099502891302108,
|
|
"num_tokens": 9595609.0,
|
|
"step": 4070
|
|
},
|
|
{
|
|
"entropy": 5.31538143157959,
|
|
"epoch": 4.1497707590422825,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00037782641761046856,
|
|
"loss": 4.8296,
|
|
"mean_token_accuracy": 0.21703800857067107,
|
|
"num_tokens": 9607424.0,
|
|
"step": 4075
|
|
},
|
|
{
|
|
"entropy": 5.30844898223877,
|
|
"epoch": 4.154865002547122,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00037746942991472157,
|
|
"loss": 4.9279,
|
|
"mean_token_accuracy": 0.20276256501674653,
|
|
"num_tokens": 9618054.0,
|
|
"step": 4080
|
|
},
|
|
{
|
|
"entropy": 5.398105478286743,
|
|
"epoch": 4.159959246051962,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00037711211647068637,
|
|
"loss": 4.9912,
|
|
"mean_token_accuracy": 0.2059895858168602,
|
|
"num_tokens": 9629936.0,
|
|
"step": 4085
|
|
},
|
|
{
|
|
"entropy": 5.410961866378784,
|
|
"epoch": 4.165053489556801,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00037675447841425535,
|
|
"loss": 4.9813,
|
|
"mean_token_accuracy": 0.20578383654356003,
|
|
"num_tokens": 9642670.0,
|
|
"step": 4090
|
|
},
|
|
{
|
|
"entropy": 5.415990352630615,
|
|
"epoch": 4.170147733061641,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.00037639651688235276,
|
|
"loss": 4.9313,
|
|
"mean_token_accuracy": 0.20855591148138047,
|
|
"num_tokens": 9653800.0,
|
|
"step": 4095
|
|
},
|
|
{
|
|
"entropy": 5.449858713150024,
|
|
"epoch": 4.17524197656648,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003760382330129312,
|
|
"loss": 4.958,
|
|
"mean_token_accuracy": 0.19954887330532073,
|
|
"num_tokens": 9663814.0,
|
|
"step": 4100
|
|
},
|
|
{
|
|
"entropy": 5.385032701492309,
|
|
"epoch": 4.180336220071319,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.000375679627944968,
|
|
"loss": 4.9857,
|
|
"mean_token_accuracy": 0.20684558153152466,
|
|
"num_tokens": 9676385.0,
|
|
"step": 4105
|
|
},
|
|
{
|
|
"entropy": 5.388202047348022,
|
|
"epoch": 4.185430463576159,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003753207028184617,
|
|
"loss": 4.9439,
|
|
"mean_token_accuracy": 0.2065659373998642,
|
|
"num_tokens": 9688225.0,
|
|
"step": 4110
|
|
},
|
|
{
|
|
"entropy": 5.330829811096192,
|
|
"epoch": 4.190524707080998,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000374961458774428,
|
|
"loss": 4.9278,
|
|
"mean_token_accuracy": 0.21576284915208815,
|
|
"num_tokens": 9702026.0,
|
|
"step": 4115
|
|
},
|
|
{
|
|
"entropy": 5.334141969680786,
|
|
"epoch": 4.195618950585838,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003746018969548966,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.20839795470237732,
|
|
"num_tokens": 9713991.0,
|
|
"step": 4120
|
|
},
|
|
{
|
|
"entropy": 5.4243885517120365,
|
|
"epoch": 4.200713194090677,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003742420185029075,
|
|
"loss": 4.9356,
|
|
"mean_token_accuracy": 0.20499588698148727,
|
|
"num_tokens": 9724809.0,
|
|
"step": 4125
|
|
},
|
|
{
|
|
"entropy": 5.393321228027344,
|
|
"epoch": 4.205807437595517,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0003738818245625072,
|
|
"loss": 5.0277,
|
|
"mean_token_accuracy": 0.2023368090391159,
|
|
"num_tokens": 9737350.0,
|
|
"step": 4130
|
|
},
|
|
{
|
|
"entropy": 5.4059350967407225,
|
|
"epoch": 4.210901681100356,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000373521316278745,
|
|
"loss": 5.035,
|
|
"mean_token_accuracy": 0.19505523443222045,
|
|
"num_tokens": 9749092.0,
|
|
"step": 4135
|
|
},
|
|
{
|
|
"entropy": 5.447250652313232,
|
|
"epoch": 4.215995924605196,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003731604947976695,
|
|
"loss": 4.9889,
|
|
"mean_token_accuracy": 0.20426835417747496,
|
|
"num_tokens": 9763016.0,
|
|
"step": 4140
|
|
},
|
|
{
|
|
"entropy": 5.411228895187378,
|
|
"epoch": 4.2210901681100355,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003727993612663253,
|
|
"loss": 4.9741,
|
|
"mean_token_accuracy": 0.1985449016094208,
|
|
"num_tokens": 9775019.0,
|
|
"step": 4145
|
|
},
|
|
{
|
|
"entropy": 5.3405862808227536,
|
|
"epoch": 4.2261844116148755,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00037243791683274865,
|
|
"loss": 4.9028,
|
|
"mean_token_accuracy": 0.21674509346485138,
|
|
"num_tokens": 9786385.0,
|
|
"step": 4150
|
|
},
|
|
{
|
|
"entropy": 5.387220478057861,
|
|
"epoch": 4.231278655119715,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003720761626459641,
|
|
"loss": 4.9865,
|
|
"mean_token_accuracy": 0.2009310394525528,
|
|
"num_tokens": 9797498.0,
|
|
"step": 4155
|
|
},
|
|
{
|
|
"entropy": 5.314464807510376,
|
|
"epoch": 4.236372898624555,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003717140998559812,
|
|
"loss": 4.9567,
|
|
"mean_token_accuracy": 0.20965381264686583,
|
|
"num_tokens": 9810654.0,
|
|
"step": 4160
|
|
},
|
|
{
|
|
"entropy": 5.342091798782349,
|
|
"epoch": 4.241467142129394,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00037135172961379035,
|
|
"loss": 4.8704,
|
|
"mean_token_accuracy": 0.21303260922431946,
|
|
"num_tokens": 9821169.0,
|
|
"step": 4165
|
|
},
|
|
{
|
|
"entropy": 5.383513069152832,
|
|
"epoch": 4.246561385634234,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003709890530713594,
|
|
"loss": 4.9929,
|
|
"mean_token_accuracy": 0.20989613085985184,
|
|
"num_tokens": 9832933.0,
|
|
"step": 4170
|
|
},
|
|
{
|
|
"entropy": 5.428200960159302,
|
|
"epoch": 4.251655629139073,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0003706260713816298,
|
|
"loss": 5.0628,
|
|
"mean_token_accuracy": 0.20300799906253814,
|
|
"num_tokens": 9844530.0,
|
|
"step": 4175
|
|
},
|
|
{
|
|
"entropy": 5.35450234413147,
|
|
"epoch": 4.256749872643912,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00037026278569851325,
|
|
"loss": 4.9706,
|
|
"mean_token_accuracy": 0.2075749769806862,
|
|
"num_tokens": 9856056.0,
|
|
"step": 4180
|
|
},
|
|
{
|
|
"entropy": 5.465550184249878,
|
|
"epoch": 4.261844116148752,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003698991971768877,
|
|
"loss": 5.0592,
|
|
"mean_token_accuracy": 0.19689694941043853,
|
|
"num_tokens": 9867534.0,
|
|
"step": 4185
|
|
},
|
|
{
|
|
"entropy": 5.436143159866333,
|
|
"epoch": 4.266938359653591,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003695353069725939,
|
|
"loss": 5.0101,
|
|
"mean_token_accuracy": 0.20069162398576737,
|
|
"num_tokens": 9879990.0,
|
|
"step": 4190
|
|
},
|
|
{
|
|
"entropy": 5.389627075195312,
|
|
"epoch": 4.272032603158431,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036917111624243143,
|
|
"loss": 5.0216,
|
|
"mean_token_accuracy": 0.19771742075681686,
|
|
"num_tokens": 9891835.0,
|
|
"step": 4195
|
|
},
|
|
{
|
|
"entropy": 5.394179964065552,
|
|
"epoch": 4.27712684666327,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00036880662614415574,
|
|
"loss": 4.8991,
|
|
"mean_token_accuracy": 0.21036533266305923,
|
|
"num_tokens": 9903940.0,
|
|
"step": 4200
|
|
},
|
|
{
|
|
"entropy": 5.399506425857544,
|
|
"epoch": 4.28222109016811,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00036844183783647333,
|
|
"loss": 4.9963,
|
|
"mean_token_accuracy": 0.20380606800317763,
|
|
"num_tokens": 9915249.0,
|
|
"step": 4205
|
|
},
|
|
{
|
|
"entropy": 5.349196529388427,
|
|
"epoch": 4.287315333672949,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00036807675247903915,
|
|
"loss": 4.9708,
|
|
"mean_token_accuracy": 0.2027221918106079,
|
|
"num_tokens": 9926840.0,
|
|
"step": 4210
|
|
},
|
|
{
|
|
"entropy": 5.425161457061767,
|
|
"epoch": 4.292409577177789,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003677113712324522,
|
|
"loss": 4.9376,
|
|
"mean_token_accuracy": 0.2072252795100212,
|
|
"num_tokens": 9937156.0,
|
|
"step": 4215
|
|
},
|
|
{
|
|
"entropy": 5.354344987869263,
|
|
"epoch": 4.297503820682628,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036734569525825243,
|
|
"loss": 4.9974,
|
|
"mean_token_accuracy": 0.20379908233880997,
|
|
"num_tokens": 9949802.0,
|
|
"step": 4220
|
|
},
|
|
{
|
|
"entropy": 5.432075929641724,
|
|
"epoch": 4.302598064187468,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003669797257189163,
|
|
"loss": 4.9909,
|
|
"mean_token_accuracy": 0.20238550901412963,
|
|
"num_tokens": 9961988.0,
|
|
"step": 4225
|
|
},
|
|
{
|
|
"entropy": 5.385130929946899,
|
|
"epoch": 4.3076923076923075,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00036661346377785397,
|
|
"loss": 4.9478,
|
|
"mean_token_accuracy": 0.20352658927440642,
|
|
"num_tokens": 9972834.0,
|
|
"step": 4230
|
|
},
|
|
{
|
|
"entropy": 5.388716220855713,
|
|
"epoch": 4.3127865511971475,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003662469105994046,
|
|
"loss": 4.8867,
|
|
"mean_token_accuracy": 0.21646392792463304,
|
|
"num_tokens": 9983579.0,
|
|
"step": 4235
|
|
},
|
|
{
|
|
"entropy": 5.388222789764404,
|
|
"epoch": 4.317880794701987,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00036588006734883377,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.19778597503900527,
|
|
"num_tokens": 9995647.0,
|
|
"step": 4240
|
|
},
|
|
{
|
|
"entropy": 5.4532790184021,
|
|
"epoch": 4.322975038206827,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036551293519232865,
|
|
"loss": 5.0723,
|
|
"mean_token_accuracy": 0.19774525612592697,
|
|
"num_tokens": 10007551.0,
|
|
"step": 4245
|
|
},
|
|
{
|
|
"entropy": 5.357536458969117,
|
|
"epoch": 4.328069281711666,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003651455152969954,
|
|
"loss": 4.9269,
|
|
"mean_token_accuracy": 0.20842873752117158,
|
|
"num_tokens": 10018032.0,
|
|
"step": 4250
|
|
},
|
|
{
|
|
"entropy": 5.388945913314819,
|
|
"epoch": 4.333163525216506,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00036477780883085423,
|
|
"loss": 4.9934,
|
|
"mean_token_accuracy": 0.20314803570508957,
|
|
"num_tokens": 10029834.0,
|
|
"step": 4255
|
|
},
|
|
{
|
|
"entropy": 5.38863787651062,
|
|
"epoch": 4.338257768721345,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00036440981696283695,
|
|
"loss": 5.0085,
|
|
"mean_token_accuracy": 0.20113157778978347,
|
|
"num_tokens": 10042035.0,
|
|
"step": 4260
|
|
},
|
|
{
|
|
"entropy": 5.384350252151489,
|
|
"epoch": 4.343352012226184,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00036404154086278236,
|
|
"loss": 5.0409,
|
|
"mean_token_accuracy": 0.20243170559406282,
|
|
"num_tokens": 10053483.0,
|
|
"step": 4265
|
|
},
|
|
{
|
|
"entropy": 5.3216699123382565,
|
|
"epoch": 4.348446255731024,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.000363672981701433,
|
|
"loss": 4.8988,
|
|
"mean_token_accuracy": 0.20944433957338332,
|
|
"num_tokens": 10065082.0,
|
|
"step": 4270
|
|
},
|
|
{
|
|
"entropy": 5.422236347198487,
|
|
"epoch": 4.353540499235863,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.00036330414065043087,
|
|
"loss": 4.9285,
|
|
"mean_token_accuracy": 0.195896278321743,
|
|
"num_tokens": 10076555.0,
|
|
"step": 4275
|
|
},
|
|
{
|
|
"entropy": 5.3773151397705075,
|
|
"epoch": 4.358634742740703,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00036293501888231465,
|
|
"loss": 4.9512,
|
|
"mean_token_accuracy": 0.20499715209007263,
|
|
"num_tokens": 10087351.0,
|
|
"step": 4280
|
|
},
|
|
{
|
|
"entropy": 5.325433254241943,
|
|
"epoch": 4.363728986245542,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00036256561757051493,
|
|
"loss": 4.9184,
|
|
"mean_token_accuracy": 0.20934373289346694,
|
|
"num_tokens": 10097685.0,
|
|
"step": 4285
|
|
},
|
|
{
|
|
"entropy": 5.373467254638672,
|
|
"epoch": 4.368823229750382,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0003621959378893514,
|
|
"loss": 4.998,
|
|
"mean_token_accuracy": 0.20558019429445268,
|
|
"num_tokens": 10108792.0,
|
|
"step": 4290
|
|
},
|
|
{
|
|
"entropy": 5.337361907958984,
|
|
"epoch": 4.373917473255221,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003618259810140281,
|
|
"loss": 5.0119,
|
|
"mean_token_accuracy": 0.19760541766881942,
|
|
"num_tokens": 10120303.0,
|
|
"step": 4295
|
|
},
|
|
{
|
|
"entropy": 5.420765209197998,
|
|
"epoch": 4.379011716760061,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036145574812063093,
|
|
"loss": 5.0722,
|
|
"mean_token_accuracy": 0.20024311691522598,
|
|
"num_tokens": 10132444.0,
|
|
"step": 4300
|
|
},
|
|
{
|
|
"entropy": 5.393250179290772,
|
|
"epoch": 4.3841059602649,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003610852403861227,
|
|
"loss": 4.9344,
|
|
"mean_token_accuracy": 0.21444665044546127,
|
|
"num_tokens": 10144054.0,
|
|
"step": 4305
|
|
},
|
|
{
|
|
"entropy": 5.356891775131226,
|
|
"epoch": 4.38920020376974,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00036071445898834043,
|
|
"loss": 4.9587,
|
|
"mean_token_accuracy": 0.2083532139658928,
|
|
"num_tokens": 10154741.0,
|
|
"step": 4310
|
|
},
|
|
{
|
|
"entropy": 5.40045166015625,
|
|
"epoch": 4.3942944472745795,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.00036034340510599053,
|
|
"loss": 4.9465,
|
|
"mean_token_accuracy": 0.20449927747249602,
|
|
"num_tokens": 10166851.0,
|
|
"step": 4315
|
|
},
|
|
{
|
|
"entropy": 5.3616042137146,
|
|
"epoch": 4.3993886907794195,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035997207991864604,
|
|
"loss": 5.015,
|
|
"mean_token_accuracy": 0.20864261984825133,
|
|
"num_tokens": 10178051.0,
|
|
"step": 4320
|
|
},
|
|
{
|
|
"entropy": 5.384256219863891,
|
|
"epoch": 4.404482934284259,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00035960048460674244,
|
|
"loss": 5.0176,
|
|
"mean_token_accuracy": 0.2015497162938118,
|
|
"num_tokens": 10190175.0,
|
|
"step": 4325
|
|
},
|
|
{
|
|
"entropy": 5.502070713043213,
|
|
"epoch": 4.409577177789099,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00035922862035157394,
|
|
"loss": 5.0785,
|
|
"mean_token_accuracy": 0.1935903862118721,
|
|
"num_tokens": 10201903.0,
|
|
"step": 4330
|
|
},
|
|
{
|
|
"entropy": 5.478650522232056,
|
|
"epoch": 4.414671421293938,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0003588564883352895,
|
|
"loss": 5.0917,
|
|
"mean_token_accuracy": 0.19496793895959855,
|
|
"num_tokens": 10214690.0,
|
|
"step": 4335
|
|
},
|
|
{
|
|
"entropy": 5.420401382446289,
|
|
"epoch": 4.419765664798778,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003584840897408895,
|
|
"loss": 5.0231,
|
|
"mean_token_accuracy": 0.20504108369350432,
|
|
"num_tokens": 10227470.0,
|
|
"step": 4340
|
|
},
|
|
{
|
|
"entropy": 5.377492666244507,
|
|
"epoch": 4.424859908303617,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003581114257522216,
|
|
"loss": 4.9662,
|
|
"mean_token_accuracy": 0.20441031605005264,
|
|
"num_tokens": 10239027.0,
|
|
"step": 4345
|
|
},
|
|
{
|
|
"entropy": 5.380789470672608,
|
|
"epoch": 4.429954151808456,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035773849755397737,
|
|
"loss": 5.0331,
|
|
"mean_token_accuracy": 0.19571729898452758,
|
|
"num_tokens": 10250683.0,
|
|
"step": 4350
|
|
},
|
|
{
|
|
"entropy": 5.386296224594116,
|
|
"epoch": 4.435048395313296,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00035736530633168805,
|
|
"loss": 4.9871,
|
|
"mean_token_accuracy": 0.20306555926799774,
|
|
"num_tokens": 10261538.0,
|
|
"step": 4355
|
|
},
|
|
{
|
|
"entropy": 5.456331205368042,
|
|
"epoch": 4.440142638818136,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0003569918532717212,
|
|
"loss": 5.0735,
|
|
"mean_token_accuracy": 0.19826265126466752,
|
|
"num_tokens": 10274232.0,
|
|
"step": 4360
|
|
},
|
|
{
|
|
"entropy": 5.396418333053589,
|
|
"epoch": 4.445236882322975,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035661813956127677,
|
|
"loss": 4.961,
|
|
"mean_token_accuracy": 0.20622898191213607,
|
|
"num_tokens": 10285370.0,
|
|
"step": 4365
|
|
},
|
|
{
|
|
"entropy": 5.314302158355713,
|
|
"epoch": 4.450331125827814,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00035624416638838313,
|
|
"loss": 4.9173,
|
|
"mean_token_accuracy": 0.2147225558757782,
|
|
"num_tokens": 10296825.0,
|
|
"step": 4370
|
|
},
|
|
{
|
|
"entropy": 5.383023452758789,
|
|
"epoch": 4.455425369332654,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003558699349418937,
|
|
"loss": 4.9396,
|
|
"mean_token_accuracy": 0.21320160925388337,
|
|
"num_tokens": 10308881.0,
|
|
"step": 4375
|
|
},
|
|
{
|
|
"entropy": 5.340534257888794,
|
|
"epoch": 4.460519612837493,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003554954464114827,
|
|
"loss": 4.9626,
|
|
"mean_token_accuracy": 0.20979908108711243,
|
|
"num_tokens": 10321084.0,
|
|
"step": 4380
|
|
},
|
|
{
|
|
"entropy": 5.3027280330657955,
|
|
"epoch": 4.465613856342333,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00035512070198764185,
|
|
"loss": 4.9989,
|
|
"mean_token_accuracy": 0.20408383309841155,
|
|
"num_tokens": 10332148.0,
|
|
"step": 4385
|
|
},
|
|
{
|
|
"entropy": 5.447972011566162,
|
|
"epoch": 4.470708099847172,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00035474570286167626,
|
|
"loss": 4.9947,
|
|
"mean_token_accuracy": 0.20294334143400192,
|
|
"num_tokens": 10343732.0,
|
|
"step": 4390
|
|
},
|
|
{
|
|
"entropy": 5.375225067138672,
|
|
"epoch": 4.475802343352012,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003543704502257006,
|
|
"loss": 4.9701,
|
|
"mean_token_accuracy": 0.2101227581501007,
|
|
"num_tokens": 10355661.0,
|
|
"step": 4395
|
|
},
|
|
{
|
|
"entropy": 5.411555624008178,
|
|
"epoch": 4.4808965868568515,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035399494527263566,
|
|
"loss": 4.9559,
|
|
"mean_token_accuracy": 0.20685625821352005,
|
|
"num_tokens": 10366218.0,
|
|
"step": 4400
|
|
},
|
|
{
|
|
"entropy": 5.4456281661987305,
|
|
"epoch": 4.4859908303616916,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003536191891962043,
|
|
"loss": 5.1295,
|
|
"mean_token_accuracy": 0.1927549123764038,
|
|
"num_tokens": 10378691.0,
|
|
"step": 4405
|
|
},
|
|
{
|
|
"entropy": 5.389416790008545,
|
|
"epoch": 4.491085073866531,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003532431831909276,
|
|
"loss": 5.0844,
|
|
"mean_token_accuracy": 0.1987747073173523,
|
|
"num_tokens": 10390097.0,
|
|
"step": 4410
|
|
},
|
|
{
|
|
"entropy": 5.44255633354187,
|
|
"epoch": 4.496179317371371,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00035286692845212114,
|
|
"loss": 4.9983,
|
|
"mean_token_accuracy": 0.2044207900762558,
|
|
"num_tokens": 10401516.0,
|
|
"step": 4415
|
|
},
|
|
{
|
|
"entropy": 5.302566289901733,
|
|
"epoch": 4.50127356087621,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00035249042617589135,
|
|
"loss": 4.9673,
|
|
"mean_token_accuracy": 0.21074131727218628,
|
|
"num_tokens": 10413629.0,
|
|
"step": 4420
|
|
},
|
|
{
|
|
"entropy": 5.354274272918701,
|
|
"epoch": 4.50636780438105,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0003521136775591315,
|
|
"loss": 4.9998,
|
|
"mean_token_accuracy": 0.20107096135616304,
|
|
"num_tokens": 10427451.0,
|
|
"step": 4425
|
|
},
|
|
{
|
|
"entropy": 5.406290864944458,
|
|
"epoch": 4.511462047885889,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.000351736683799518,
|
|
"loss": 4.966,
|
|
"mean_token_accuracy": 0.20640997141599654,
|
|
"num_tokens": 10438979.0,
|
|
"step": 4430
|
|
},
|
|
{
|
|
"entropy": 5.325797700881958,
|
|
"epoch": 4.516556291390728,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00035135944609550654,
|
|
"loss": 4.9082,
|
|
"mean_token_accuracy": 0.2163403555750847,
|
|
"num_tokens": 10450208.0,
|
|
"step": 4435
|
|
},
|
|
{
|
|
"entropy": 5.392451763153076,
|
|
"epoch": 4.521650534895568,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00035098196564632825,
|
|
"loss": 4.9988,
|
|
"mean_token_accuracy": 0.20537536293268205,
|
|
"num_tokens": 10461249.0,
|
|
"step": 4440
|
|
},
|
|
{
|
|
"entropy": 5.340795564651489,
|
|
"epoch": 4.526744778400408,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00035060424365198603,
|
|
"loss": 4.9402,
|
|
"mean_token_accuracy": 0.20808505713939668,
|
|
"num_tokens": 10473222.0,
|
|
"step": 4445
|
|
},
|
|
{
|
|
"entropy": 5.419239950180054,
|
|
"epoch": 4.531839021905247,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0003502262813132507,
|
|
"loss": 5.0526,
|
|
"mean_token_accuracy": 0.19598182886838914,
|
|
"num_tokens": 10485302.0,
|
|
"step": 4450
|
|
},
|
|
{
|
|
"entropy": 5.363297939300537,
|
|
"epoch": 4.536933265410086,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034984807983165695,
|
|
"loss": 5.0707,
|
|
"mean_token_accuracy": 0.19928496181964875,
|
|
"num_tokens": 10498377.0,
|
|
"step": 4455
|
|
},
|
|
{
|
|
"entropy": 5.456932878494262,
|
|
"epoch": 4.542027508914926,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003494696404094998,
|
|
"loss": 5.0133,
|
|
"mean_token_accuracy": 0.20056600123643875,
|
|
"num_tokens": 10510216.0,
|
|
"step": 4460
|
|
},
|
|
{
|
|
"entropy": 5.408827686309815,
|
|
"epoch": 4.547121752419765,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00034909096424983073,
|
|
"loss": 4.9521,
|
|
"mean_token_accuracy": 0.20502671897411345,
|
|
"num_tokens": 10522152.0,
|
|
"step": 4465
|
|
},
|
|
{
|
|
"entropy": 5.30216875076294,
|
|
"epoch": 4.552215995924605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003487120525564537,
|
|
"loss": 5.0063,
|
|
"mean_token_accuracy": 0.2053257554769516,
|
|
"num_tokens": 10534380.0,
|
|
"step": 4470
|
|
},
|
|
{
|
|
"entropy": 5.440784311294555,
|
|
"epoch": 4.5573102394294445,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003483329065339216,
|
|
"loss": 5.0695,
|
|
"mean_token_accuracy": 0.19319222122430801,
|
|
"num_tokens": 10545623.0,
|
|
"step": 4475
|
|
},
|
|
{
|
|
"entropy": 5.4275370121002195,
|
|
"epoch": 4.5624044829342845,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0003479535273875319,
|
|
"loss": 5.0417,
|
|
"mean_token_accuracy": 0.2057182624936104,
|
|
"num_tokens": 10557626.0,
|
|
"step": 4480
|
|
},
|
|
{
|
|
"entropy": 5.338424825668335,
|
|
"epoch": 4.567498726439124,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00034757391632332364,
|
|
"loss": 4.9678,
|
|
"mean_token_accuracy": 0.2016713559627533,
|
|
"num_tokens": 10569002.0,
|
|
"step": 4485
|
|
},
|
|
{
|
|
"entropy": 5.345268869400025,
|
|
"epoch": 4.572592969943964,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00034719407454807274,
|
|
"loss": 4.9877,
|
|
"mean_token_accuracy": 0.204143126308918,
|
|
"num_tokens": 10581458.0,
|
|
"step": 4490
|
|
},
|
|
{
|
|
"entropy": 5.328644466400147,
|
|
"epoch": 4.577687213448803,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0003468140032692887,
|
|
"loss": 4.9549,
|
|
"mean_token_accuracy": 0.20389237999916077,
|
|
"num_tokens": 10593157.0,
|
|
"step": 4495
|
|
},
|
|
{
|
|
"entropy": 5.388764762878418,
|
|
"epoch": 4.582781456953643,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0003464337036952105,
|
|
"loss": 4.9713,
|
|
"mean_token_accuracy": 0.204342257976532,
|
|
"num_tokens": 10603504.0,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"entropy": 5.448671150207519,
|
|
"epoch": 4.587875700458482,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00034605317703480313,
|
|
"loss": 5.0961,
|
|
"mean_token_accuracy": 0.19769959300756454,
|
|
"num_tokens": 10617186.0,
|
|
"step": 4505
|
|
},
|
|
{
|
|
"entropy": 5.452953195571899,
|
|
"epoch": 4.592969943963322,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003456724244977533,
|
|
"loss": 5.0046,
|
|
"mean_token_accuracy": 0.203036929666996,
|
|
"num_tokens": 10629871.0,
|
|
"step": 4510
|
|
},
|
|
{
|
|
"entropy": 5.367894077301026,
|
|
"epoch": 4.598064187468161,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003452914472944656,
|
|
"loss": 5.0135,
|
|
"mean_token_accuracy": 0.20484152287244797,
|
|
"num_tokens": 10641461.0,
|
|
"step": 4515
|
|
},
|
|
{
|
|
"entropy": 5.37530026435852,
|
|
"epoch": 4.603158430973,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003449102466360591,
|
|
"loss": 4.968,
|
|
"mean_token_accuracy": 0.20721325427293777,
|
|
"num_tokens": 10652811.0,
|
|
"step": 4520
|
|
},
|
|
{
|
|
"entropy": 5.3583005428314205,
|
|
"epoch": 4.60825267447784,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003445288237343632,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.20314985066652297,
|
|
"num_tokens": 10663624.0,
|
|
"step": 4525
|
|
},
|
|
{
|
|
"entropy": 5.393222332000732,
|
|
"epoch": 4.61334691798268,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00034414717980191375,
|
|
"loss": 5.0072,
|
|
"mean_token_accuracy": 0.1996378481388092,
|
|
"num_tokens": 10675317.0,
|
|
"step": 4530
|
|
},
|
|
{
|
|
"entropy": 5.367097854614258,
|
|
"epoch": 4.618441161487519,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00034376531605194915,
|
|
"loss": 4.9868,
|
|
"mean_token_accuracy": 0.2128213733434677,
|
|
"num_tokens": 10686343.0,
|
|
"step": 4535
|
|
},
|
|
{
|
|
"entropy": 5.468174743652344,
|
|
"epoch": 4.623535404992358,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003433832336984068,
|
|
"loss": 5.1039,
|
|
"mean_token_accuracy": 0.1936369225382805,
|
|
"num_tokens": 10697688.0,
|
|
"step": 4540
|
|
},
|
|
{
|
|
"entropy": 5.41770305633545,
|
|
"epoch": 4.628629648497198,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003430009339559189,
|
|
"loss": 4.9476,
|
|
"mean_token_accuracy": 0.20681630522012712,
|
|
"num_tokens": 10707840.0,
|
|
"step": 4545
|
|
},
|
|
{
|
|
"entropy": 5.380983161926269,
|
|
"epoch": 4.633723892002037,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003426184180398087,
|
|
"loss": 5.0347,
|
|
"mean_token_accuracy": 0.20371325612068175,
|
|
"num_tokens": 10719702.0,
|
|
"step": 4550
|
|
},
|
|
{
|
|
"entropy": 5.2961469173431395,
|
|
"epoch": 4.638818135506877,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003422356871660868,
|
|
"loss": 4.8936,
|
|
"mean_token_accuracy": 0.20777104347944259,
|
|
"num_tokens": 10731040.0,
|
|
"step": 4555
|
|
},
|
|
{
|
|
"entropy": 5.396471738815308,
|
|
"epoch": 4.6439123790117165,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00034185274255144705,
|
|
"loss": 5.0226,
|
|
"mean_token_accuracy": 0.2017626315355301,
|
|
"num_tokens": 10743009.0,
|
|
"step": 4560
|
|
},
|
|
{
|
|
"entropy": 5.4289984703063965,
|
|
"epoch": 4.6490066225165565,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003414695854132629,
|
|
"loss": 5.0718,
|
|
"mean_token_accuracy": 0.19916653037071227,
|
|
"num_tokens": 10754030.0,
|
|
"step": 4565
|
|
},
|
|
{
|
|
"entropy": 5.349284029006958,
|
|
"epoch": 4.654100866021396,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003410862169695831,
|
|
"loss": 4.9636,
|
|
"mean_token_accuracy": 0.21300530582666397,
|
|
"num_tokens": 10765512.0,
|
|
"step": 4570
|
|
},
|
|
{
|
|
"entropy": 5.404683303833008,
|
|
"epoch": 4.659195109526236,
|
|
"grad_norm": 1.0078125,
|
|
"learning_rate": 0.0003407026384391284,
|
|
"loss": 5.0767,
|
|
"mean_token_accuracy": 0.19347753375768661,
|
|
"num_tokens": 10778694.0,
|
|
"step": 4575
|
|
},
|
|
{
|
|
"entropy": 5.326197576522827,
|
|
"epoch": 4.664289353031075,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003403188510412874,
|
|
"loss": 4.9192,
|
|
"mean_token_accuracy": 0.21128104925155639,
|
|
"num_tokens": 10789458.0,
|
|
"step": 4580
|
|
},
|
|
{
|
|
"entropy": 5.41142053604126,
|
|
"epoch": 4.669383596535915,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00033993485599611266,
|
|
"loss": 4.9789,
|
|
"mean_token_accuracy": 0.2041890650987625,
|
|
"num_tokens": 10801932.0,
|
|
"step": 4585
|
|
},
|
|
{
|
|
"entropy": 5.301593065261841,
|
|
"epoch": 4.674477840040754,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00033955065452431684,
|
|
"loss": 4.9853,
|
|
"mean_token_accuracy": 0.2084544777870178,
|
|
"num_tokens": 10814907.0,
|
|
"step": 4590
|
|
},
|
|
{
|
|
"entropy": 5.355861711502075,
|
|
"epoch": 4.679572083545594,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00033916624784726865,
|
|
"loss": 4.9504,
|
|
"mean_token_accuracy": 0.20707277059555054,
|
|
"num_tokens": 10825707.0,
|
|
"step": 4595
|
|
},
|
|
{
|
|
"entropy": 5.320301723480225,
|
|
"epoch": 4.684666327050433,
|
|
"grad_norm": 1.0234375,
|
|
"learning_rate": 0.00033878163718698945,
|
|
"loss": 5.0211,
|
|
"mean_token_accuracy": 0.20104035288095473,
|
|
"num_tokens": 10839498.0,
|
|
"step": 4600
|
|
},
|
|
{
|
|
"entropy": 5.4754210948944095,
|
|
"epoch": 4.689760570555272,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033839682376614875,
|
|
"loss": 5.0825,
|
|
"mean_token_accuracy": 0.19706505089998244,
|
|
"num_tokens": 10851507.0,
|
|
"step": 4605
|
|
},
|
|
{
|
|
"entropy": 5.419159603118897,
|
|
"epoch": 4.694854814060112,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.00033801180880806115,
|
|
"loss": 5.0245,
|
|
"mean_token_accuracy": 0.2015688583254814,
|
|
"num_tokens": 10863437.0,
|
|
"step": 4610
|
|
},
|
|
{
|
|
"entropy": 5.3770678520202635,
|
|
"epoch": 4.699949057564952,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003376265935366812,
|
|
"loss": 5.0015,
|
|
"mean_token_accuracy": 0.2092454731464386,
|
|
"num_tokens": 10875499.0,
|
|
"step": 4615
|
|
},
|
|
{
|
|
"entropy": 5.37080078125,
|
|
"epoch": 4.705043301069791,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003372411791766008,
|
|
"loss": 4.9843,
|
|
"mean_token_accuracy": 0.20272751450538634,
|
|
"num_tokens": 10886006.0,
|
|
"step": 4620
|
|
},
|
|
{
|
|
"entropy": 5.361112880706787,
|
|
"epoch": 4.71013754457463,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00033685556695304446,
|
|
"loss": 4.9876,
|
|
"mean_token_accuracy": 0.2015311151742935,
|
|
"num_tokens": 10899258.0,
|
|
"step": 4625
|
|
},
|
|
{
|
|
"entropy": 5.391425037384034,
|
|
"epoch": 4.71523178807947,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00033646975809186597,
|
|
"loss": 5.0321,
|
|
"mean_token_accuracy": 0.1984802544116974,
|
|
"num_tokens": 10910672.0,
|
|
"step": 4630
|
|
},
|
|
{
|
|
"entropy": 5.480038452148437,
|
|
"epoch": 4.720326031584309,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003360837538195439,
|
|
"loss": 5.0798,
|
|
"mean_token_accuracy": 0.19933039993047713,
|
|
"num_tokens": 10923087.0,
|
|
"step": 4635
|
|
},
|
|
{
|
|
"entropy": 5.36871223449707,
|
|
"epoch": 4.725420275089149,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003356975553631782,
|
|
"loss": 5.0042,
|
|
"mean_token_accuracy": 0.20500523895025252,
|
|
"num_tokens": 10935715.0,
|
|
"step": 4640
|
|
},
|
|
{
|
|
"entropy": 5.404748964309692,
|
|
"epoch": 4.7305145185939885,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00033531116395048614,
|
|
"loss": 5.0131,
|
|
"mean_token_accuracy": 0.20223248600959778,
|
|
"num_tokens": 10946016.0,
|
|
"step": 4645
|
|
},
|
|
{
|
|
"entropy": 5.407647752761841,
|
|
"epoch": 4.7356087620988285,
|
|
"grad_norm": 1.0625,
|
|
"learning_rate": 0.0003349245808097985,
|
|
"loss": 4.9808,
|
|
"mean_token_accuracy": 0.20233923196792603,
|
|
"num_tokens": 10958733.0,
|
|
"step": 4650
|
|
},
|
|
{
|
|
"entropy": 5.425910472869873,
|
|
"epoch": 4.740703005603668,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003345378071700553,
|
|
"loss": 5.0256,
|
|
"mean_token_accuracy": 0.2084519237279892,
|
|
"num_tokens": 10970519.0,
|
|
"step": 4655
|
|
},
|
|
{
|
|
"entropy": 5.324759101867675,
|
|
"epoch": 4.745797249108508,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003341508442608022,
|
|
"loss": 4.9797,
|
|
"mean_token_accuracy": 0.20335644334554673,
|
|
"num_tokens": 10981420.0,
|
|
"step": 4660
|
|
},
|
|
{
|
|
"entropy": 5.386528348922729,
|
|
"epoch": 4.750891492613347,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003337636933121867,
|
|
"loss": 5.119,
|
|
"mean_token_accuracy": 0.19502317011356354,
|
|
"num_tokens": 10993735.0,
|
|
"step": 4665
|
|
},
|
|
{
|
|
"entropy": 5.3809366703033445,
|
|
"epoch": 4.755985736118187,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0003333763555549541,
|
|
"loss": 4.9055,
|
|
"mean_token_accuracy": 0.21494016498327256,
|
|
"num_tokens": 11004077.0,
|
|
"step": 4670
|
|
},
|
|
{
|
|
"entropy": 5.370249795913696,
|
|
"epoch": 4.761079979623026,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003329888322204434,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.201298488676548,
|
|
"num_tokens": 11015478.0,
|
|
"step": 4675
|
|
},
|
|
{
|
|
"entropy": 5.412536573410034,
|
|
"epoch": 4.766174223127866,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00033260112454058344,
|
|
"loss": 5.0048,
|
|
"mean_token_accuracy": 0.20294886380434035,
|
|
"num_tokens": 11026785.0,
|
|
"step": 4680
|
|
},
|
|
{
|
|
"entropy": 5.413317918777466,
|
|
"epoch": 4.771268466632705,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00033221323374788946,
|
|
"loss": 5.0372,
|
|
"mean_token_accuracy": 0.2008432701230049,
|
|
"num_tokens": 11037616.0,
|
|
"step": 4685
|
|
},
|
|
{
|
|
"entropy": 5.366420602798462,
|
|
"epoch": 4.776362710137544,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00033182516107545864,
|
|
"loss": 5.1061,
|
|
"mean_token_accuracy": 0.19299721866846084,
|
|
"num_tokens": 11049565.0,
|
|
"step": 4690
|
|
},
|
|
{
|
|
"entropy": 5.388197612762451,
|
|
"epoch": 4.781456953642384,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00033143690775696606,
|
|
"loss": 4.9368,
|
|
"mean_token_accuracy": 0.20900121331214905,
|
|
"num_tokens": 11061456.0,
|
|
"step": 4695
|
|
},
|
|
{
|
|
"entropy": 5.259316778182983,
|
|
"epoch": 4.786551197147224,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003310484750266616,
|
|
"loss": 4.936,
|
|
"mean_token_accuracy": 0.21499007791280747,
|
|
"num_tokens": 11074206.0,
|
|
"step": 4700
|
|
},
|
|
{
|
|
"entropy": 5.361646842956543,
|
|
"epoch": 4.791645440652063,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00033065986411936506,
|
|
"loss": 5.0206,
|
|
"mean_token_accuracy": 0.2068053290247917,
|
|
"num_tokens": 11086550.0,
|
|
"step": 4705
|
|
},
|
|
{
|
|
"entropy": 5.479002904891968,
|
|
"epoch": 4.796739684156902,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0003302710762704629,
|
|
"loss": 5.0644,
|
|
"mean_token_accuracy": 0.19607826173305512,
|
|
"num_tokens": 11098616.0,
|
|
"step": 4710
|
|
},
|
|
{
|
|
"entropy": 5.368695449829102,
|
|
"epoch": 4.801833927661742,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000329882112715904,
|
|
"loss": 5.018,
|
|
"mean_token_accuracy": 0.20273400247097015,
|
|
"num_tokens": 11109015.0,
|
|
"step": 4715
|
|
},
|
|
{
|
|
"entropy": 5.344677972793579,
|
|
"epoch": 4.806928171166581,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032949297469219563,
|
|
"loss": 4.96,
|
|
"mean_token_accuracy": 0.20712306946516038,
|
|
"num_tokens": 11120694.0,
|
|
"step": 4720
|
|
},
|
|
{
|
|
"entropy": 5.3833473205566404,
|
|
"epoch": 4.8120224146714214,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00032910366343639997,
|
|
"loss": 5.0049,
|
|
"mean_token_accuracy": 0.19764655381441115,
|
|
"num_tokens": 11131646.0,
|
|
"step": 4725
|
|
},
|
|
{
|
|
"entropy": 5.494243860244751,
|
|
"epoch": 4.817116658176261,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00032871418018612993,
|
|
"loss": 5.087,
|
|
"mean_token_accuracy": 0.19481184035539628,
|
|
"num_tokens": 11143786.0,
|
|
"step": 4730
|
|
},
|
|
{
|
|
"entropy": 5.399050521850586,
|
|
"epoch": 4.822210901681101,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003283245261795448,
|
|
"loss": 5.0035,
|
|
"mean_token_accuracy": 0.20237109959125518,
|
|
"num_tokens": 11155505.0,
|
|
"step": 4735
|
|
},
|
|
{
|
|
"entropy": 5.303896760940551,
|
|
"epoch": 4.82730514518594,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003279347026553472,
|
|
"loss": 5.0118,
|
|
"mean_token_accuracy": 0.20138293653726577,
|
|
"num_tokens": 11167719.0,
|
|
"step": 4740
|
|
},
|
|
{
|
|
"entropy": 5.439955234527588,
|
|
"epoch": 4.83239938869078,
|
|
"grad_norm": 0.96875,
|
|
"learning_rate": 0.0003275447108527782,
|
|
"loss": 5.0893,
|
|
"mean_token_accuracy": 0.19383734911680223,
|
|
"num_tokens": 11180289.0,
|
|
"step": 4745
|
|
},
|
|
{
|
|
"entropy": 5.406141996383667,
|
|
"epoch": 4.837493632195619,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0003271545520116141,
|
|
"loss": 5.0266,
|
|
"mean_token_accuracy": 0.20277864784002303,
|
|
"num_tokens": 11192657.0,
|
|
"step": 4750
|
|
},
|
|
{
|
|
"entropy": 5.388931655883789,
|
|
"epoch": 4.842587875700459,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003267642273721621,
|
|
"loss": 5.0281,
|
|
"mean_token_accuracy": 0.2058450847864151,
|
|
"num_tokens": 11203822.0,
|
|
"step": 4755
|
|
},
|
|
{
|
|
"entropy": 5.4053487300872805,
|
|
"epoch": 4.847682119205298,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00032637373817525657,
|
|
"loss": 5.049,
|
|
"mean_token_accuracy": 0.20506763309240342,
|
|
"num_tokens": 11215504.0,
|
|
"step": 4760
|
|
},
|
|
{
|
|
"entropy": 5.3778135776519775,
|
|
"epoch": 4.852776362710138,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003259830856622547,
|
|
"loss": 4.959,
|
|
"mean_token_accuracy": 0.21285818219184877,
|
|
"num_tokens": 11225905.0,
|
|
"step": 4765
|
|
},
|
|
{
|
|
"entropy": 5.321655225753784,
|
|
"epoch": 4.857870606214977,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00032559227107503344,
|
|
"loss": 4.9757,
|
|
"mean_token_accuracy": 0.2082709938287735,
|
|
"num_tokens": 11237396.0,
|
|
"step": 4770
|
|
},
|
|
{
|
|
"entropy": 5.433521413803101,
|
|
"epoch": 4.862964849719816,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00032520129565598435,
|
|
"loss": 5.0352,
|
|
"mean_token_accuracy": 0.202737520635128,
|
|
"num_tokens": 11247693.0,
|
|
"step": 4775
|
|
},
|
|
{
|
|
"entropy": 5.369568157196045,
|
|
"epoch": 4.868059093224656,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0003248101606480106,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.20194458216428757,
|
|
"num_tokens": 11257716.0,
|
|
"step": 4780
|
|
},
|
|
{
|
|
"entropy": 5.352374839782715,
|
|
"epoch": 4.873153336729496,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003244188672945228,
|
|
"loss": 4.9609,
|
|
"mean_token_accuracy": 0.20623071640729904,
|
|
"num_tokens": 11269427.0,
|
|
"step": 4785
|
|
},
|
|
{
|
|
"entropy": 5.362681102752686,
|
|
"epoch": 4.878247580234335,
|
|
"grad_norm": 1.0,
|
|
"learning_rate": 0.00032402741683943456,
|
|
"loss": 4.9932,
|
|
"mean_token_accuracy": 0.2119578540325165,
|
|
"num_tokens": 11281758.0,
|
|
"step": 4790
|
|
},
|
|
{
|
|
"entropy": 5.360690975189209,
|
|
"epoch": 4.883341823739174,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0003236358105271593,
|
|
"loss": 5.0351,
|
|
"mean_token_accuracy": 0.2019821286201477,
|
|
"num_tokens": 11292926.0,
|
|
"step": 4795
|
|
},
|
|
{
|
|
"entropy": 5.425464105606079,
|
|
"epoch": 4.888436067244014,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003232440496026055,
|
|
"loss": 5.095,
|
|
"mean_token_accuracy": 0.19756797552108765,
|
|
"num_tokens": 11306022.0,
|
|
"step": 4800
|
|
},
|
|
{
|
|
"entropy": 5.390896797180176,
|
|
"epoch": 4.8935303107488535,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003228521353111736,
|
|
"loss": 4.9925,
|
|
"mean_token_accuracy": 0.20667598843574525,
|
|
"num_tokens": 11318252.0,
|
|
"step": 4805
|
|
},
|
|
{
|
|
"entropy": 5.382144165039063,
|
|
"epoch": 4.8986245542536935,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003224600688987513,
|
|
"loss": 4.9699,
|
|
"mean_token_accuracy": 0.21315983682870865,
|
|
"num_tokens": 11330604.0,
|
|
"step": 4810
|
|
},
|
|
{
|
|
"entropy": 5.392085981369019,
|
|
"epoch": 4.903718797758533,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003220678516117099,
|
|
"loss": 5.0141,
|
|
"mean_token_accuracy": 0.20325611978769303,
|
|
"num_tokens": 11343020.0,
|
|
"step": 4815
|
|
},
|
|
{
|
|
"entropy": 5.418543863296509,
|
|
"epoch": 4.908813041263373,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00032167548469690045,
|
|
"loss": 5.0744,
|
|
"mean_token_accuracy": 0.19584080278873445,
|
|
"num_tokens": 11354727.0,
|
|
"step": 4820
|
|
},
|
|
{
|
|
"entropy": 5.397195720672608,
|
|
"epoch": 4.913907284768212,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003212829694016496,
|
|
"loss": 5.0591,
|
|
"mean_token_accuracy": 0.20102609246969222,
|
|
"num_tokens": 11366437.0,
|
|
"step": 4825
|
|
},
|
|
{
|
|
"entropy": 5.297625494003296,
|
|
"epoch": 4.919001528273052,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0003208903069737557,
|
|
"loss": 4.9479,
|
|
"mean_token_accuracy": 0.20803475975990296,
|
|
"num_tokens": 11379877.0,
|
|
"step": 4830
|
|
},
|
|
{
|
|
"entropy": 5.354777050018311,
|
|
"epoch": 4.924095771777891,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003204974986614848,
|
|
"loss": 4.9856,
|
|
"mean_token_accuracy": 0.2076582670211792,
|
|
"num_tokens": 11392113.0,
|
|
"step": 4835
|
|
},
|
|
{
|
|
"entropy": 5.433166408538819,
|
|
"epoch": 4.929190015282731,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00032010454571356677,
|
|
"loss": 5.0507,
|
|
"mean_token_accuracy": 0.19755857139825822,
|
|
"num_tokens": 11404790.0,
|
|
"step": 4840
|
|
},
|
|
{
|
|
"entropy": 5.398066186904908,
|
|
"epoch": 4.93428425878757,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003197114493791913,
|
|
"loss": 5.0034,
|
|
"mean_token_accuracy": 0.20378225445747375,
|
|
"num_tokens": 11417515.0,
|
|
"step": 4845
|
|
},
|
|
{
|
|
"entropy": 5.284646654129029,
|
|
"epoch": 4.93937850229241,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00031931821090800365,
|
|
"loss": 4.9566,
|
|
"mean_token_accuracy": 0.21543115228414536,
|
|
"num_tokens": 11430188.0,
|
|
"step": 4850
|
|
},
|
|
{
|
|
"entropy": 5.288576602935791,
|
|
"epoch": 4.944472745797249,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00031892483155010145,
|
|
"loss": 4.8901,
|
|
"mean_token_accuracy": 0.21230482310056686,
|
|
"num_tokens": 11442648.0,
|
|
"step": 4855
|
|
},
|
|
{
|
|
"entropy": 5.359285163879394,
|
|
"epoch": 4.949566989302088,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0003185313125560295,
|
|
"loss": 4.9596,
|
|
"mean_token_accuracy": 0.21309040486812592,
|
|
"num_tokens": 11453587.0,
|
|
"step": 4860
|
|
},
|
|
{
|
|
"entropy": 5.358058071136474,
|
|
"epoch": 4.954661232806928,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00031813765517677727,
|
|
"loss": 4.9035,
|
|
"mean_token_accuracy": 0.206657712161541,
|
|
"num_tokens": 11464476.0,
|
|
"step": 4865
|
|
},
|
|
{
|
|
"entropy": 5.3797372341156,
|
|
"epoch": 4.959755476311768,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0003177438606637736,
|
|
"loss": 5.0255,
|
|
"mean_token_accuracy": 0.19901310950517653,
|
|
"num_tokens": 11476907.0,
|
|
"step": 4870
|
|
},
|
|
{
|
|
"entropy": 5.274873495101929,
|
|
"epoch": 4.964849719816607,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003173499302688834,
|
|
"loss": 4.9155,
|
|
"mean_token_accuracy": 0.21434779465198517,
|
|
"num_tokens": 11488392.0,
|
|
"step": 4875
|
|
},
|
|
{
|
|
"entropy": 5.330209350585937,
|
|
"epoch": 4.969943963321446,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00031695586524440364,
|
|
"loss": 4.9599,
|
|
"mean_token_accuracy": 0.20472506135702134,
|
|
"num_tokens": 11499882.0,
|
|
"step": 4880
|
|
},
|
|
{
|
|
"entropy": 5.367196035385132,
|
|
"epoch": 4.975038206826286,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0003165616668430592,
|
|
"loss": 5.0705,
|
|
"mean_token_accuracy": 0.19970313012599944,
|
|
"num_tokens": 11511669.0,
|
|
"step": 4885
|
|
},
|
|
{
|
|
"entropy": 5.377557325363159,
|
|
"epoch": 4.9801324503311255,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00031616733631799907,
|
|
"loss": 4.9766,
|
|
"mean_token_accuracy": 0.2068626970052719,
|
|
"num_tokens": 11523850.0,
|
|
"step": 4890
|
|
},
|
|
{
|
|
"entropy": 5.250976800918579,
|
|
"epoch": 4.9852266938359655,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00031577287492279217,
|
|
"loss": 4.9295,
|
|
"mean_token_accuracy": 0.21211882531642914,
|
|
"num_tokens": 11535295.0,
|
|
"step": 4895
|
|
},
|
|
{
|
|
"entropy": 5.430858755111695,
|
|
"epoch": 4.990320937340805,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003153782839114233,
|
|
"loss": 5.0713,
|
|
"mean_token_accuracy": 0.19593069106340408,
|
|
"num_tokens": 11546304.0,
|
|
"step": 4900
|
|
},
|
|
{
|
|
"entropy": 5.447435092926026,
|
|
"epoch": 4.995415180845645,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.00031498356453828967,
|
|
"loss": 5.118,
|
|
"mean_token_accuracy": 0.2000979170203209,
|
|
"num_tokens": 11558886.0,
|
|
"step": 4905
|
|
},
|
|
{
|
|
"entropy": 5.422902743021647,
|
|
"epoch": 5.0,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 0.0003145887180581963,
|
|
"loss": 5.0937,
|
|
"mean_token_accuracy": 0.19380197260114881,
|
|
"num_tokens": 11570380.0,
|
|
"step": 4910
|
|
},
|
|
{
|
|
"entropy": 5.352080535888672,
|
|
"epoch": 5.005094243504839,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003141937457263523,
|
|
"loss": 4.6996,
|
|
"mean_token_accuracy": 0.22583072930574416,
|
|
"num_tokens": 11581170.0,
|
|
"step": 4915
|
|
},
|
|
{
|
|
"entropy": 5.3861891746521,
|
|
"epoch": 5.010188487009679,
|
|
"grad_norm": 1.015625,
|
|
"learning_rate": 0.0003137986487983668,
|
|
"loss": 4.8267,
|
|
"mean_token_accuracy": 0.2132161185145378,
|
|
"num_tokens": 11594407.0,
|
|
"step": 4920
|
|
},
|
|
{
|
|
"entropy": 5.357200336456299,
|
|
"epoch": 5.015282730514518,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00031340342853024533,
|
|
"loss": 4.742,
|
|
"mean_token_accuracy": 0.2204134076833725,
|
|
"num_tokens": 11607159.0,
|
|
"step": 4925
|
|
},
|
|
{
|
|
"entropy": 5.340716457366943,
|
|
"epoch": 5.020376974019358,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0003130080861783851,
|
|
"loss": 4.7146,
|
|
"mean_token_accuracy": 0.22381511628627776,
|
|
"num_tokens": 11617692.0,
|
|
"step": 4930
|
|
},
|
|
{
|
|
"entropy": 5.339341545104981,
|
|
"epoch": 5.025471217524197,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0003126126229995717,
|
|
"loss": 4.8051,
|
|
"mean_token_accuracy": 0.22085677534341813,
|
|
"num_tokens": 11629679.0,
|
|
"step": 4935
|
|
},
|
|
{
|
|
"entropy": 5.294214820861816,
|
|
"epoch": 5.030565461029037,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003122170402509747,
|
|
"loss": 4.6893,
|
|
"mean_token_accuracy": 0.22438325136899948,
|
|
"num_tokens": 11642507.0,
|
|
"step": 4940
|
|
},
|
|
{
|
|
"entropy": 5.334340000152588,
|
|
"epoch": 5.0356597045338765,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0003118213391901439,
|
|
"loss": 4.7244,
|
|
"mean_token_accuracy": 0.22341739386320114,
|
|
"num_tokens": 11654709.0,
|
|
"step": 4945
|
|
},
|
|
{
|
|
"entropy": 5.247434139251709,
|
|
"epoch": 5.0407539480387165,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000311425521075005,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.22077375799417495,
|
|
"num_tokens": 11666266.0,
|
|
"step": 4950
|
|
},
|
|
{
|
|
"entropy": 5.270362472534179,
|
|
"epoch": 5.045848191543556,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0003110295871638561,
|
|
"loss": 4.6631,
|
|
"mean_token_accuracy": 0.22793119251728058,
|
|
"num_tokens": 11677844.0,
|
|
"step": 4955
|
|
},
|
|
{
|
|
"entropy": 5.352112674713135,
|
|
"epoch": 5.050942435048396,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0003106335387153632,
|
|
"loss": 4.7894,
|
|
"mean_token_accuracy": 0.22013246566057204,
|
|
"num_tokens": 11689202.0,
|
|
"step": 4960
|
|
},
|
|
{
|
|
"entropy": 5.34426908493042,
|
|
"epoch": 5.056036678553235,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0003102373769885565,
|
|
"loss": 4.7587,
|
|
"mean_token_accuracy": 0.21880360394716264,
|
|
"num_tokens": 11700155.0,
|
|
"step": 4965
|
|
},
|
|
{
|
|
"entropy": 5.238502788543701,
|
|
"epoch": 5.061130922058075,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0003098411032428262,
|
|
"loss": 4.6999,
|
|
"mean_token_accuracy": 0.22623772621154786,
|
|
"num_tokens": 11712463.0,
|
|
"step": 4970
|
|
},
|
|
{
|
|
"entropy": 5.327230978012085,
|
|
"epoch": 5.066225165562914,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00030944471873791876,
|
|
"loss": 4.7726,
|
|
"mean_token_accuracy": 0.217424413561821,
|
|
"num_tokens": 11724373.0,
|
|
"step": 4975
|
|
},
|
|
{
|
|
"entropy": 5.359502744674683,
|
|
"epoch": 5.071319409067754,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0003090482247339326,
|
|
"loss": 4.7609,
|
|
"mean_token_accuracy": 0.22949107736349106,
|
|
"num_tokens": 11736394.0,
|
|
"step": 4980
|
|
},
|
|
{
|
|
"entropy": 5.3265351295471195,
|
|
"epoch": 5.076413652572593,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0003086516224913144,
|
|
"loss": 4.7323,
|
|
"mean_token_accuracy": 0.2229645311832428,
|
|
"num_tokens": 11747895.0,
|
|
"step": 4985
|
|
},
|
|
{
|
|
"entropy": 5.357536363601684,
|
|
"epoch": 5.081507896077433,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0003082549132708548,
|
|
"loss": 4.7728,
|
|
"mean_token_accuracy": 0.21757092028856279,
|
|
"num_tokens": 11761287.0,
|
|
"step": 4990
|
|
},
|
|
{
|
|
"entropy": 5.246567678451538,
|
|
"epoch": 5.086602139582272,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00030785809833368456,
|
|
"loss": 4.7431,
|
|
"mean_token_accuracy": 0.22550234645605088,
|
|
"num_tokens": 11773033.0,
|
|
"step": 4995
|
|
},
|
|
{
|
|
"entropy": 5.290670394897461,
|
|
"epoch": 5.091696383087111,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00030746117894127047,
|
|
"loss": 4.7672,
|
|
"mean_token_accuracy": 0.22372525334358215,
|
|
"num_tokens": 11785101.0,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 5.091696383087111,
|
|
"eval_entropy": 5.176929809429027,
|
|
"eval_loss": 5.652852535247803,
|
|
"eval_mean_token_accuracy": 0.18061496757062864,
|
|
"eval_num_tokens": 11785101.0,
|
|
"eval_runtime": 2.6242,
|
|
"eval_samples_per_second": 1234.67,
|
|
"eval_steps_per_second": 154.334,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"entropy": 5.345091819763184,
|
|
"epoch": 5.096790626591951,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00030706415635541143,
|
|
"loss": 4.7712,
|
|
"mean_token_accuracy": 0.22448007762432098,
|
|
"num_tokens": 11797032.0,
|
|
"step": 5005
|
|
},
|
|
{
|
|
"entropy": 5.30574312210083,
|
|
"epoch": 5.10188487009679,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0003066670318382344,
|
|
"loss": 4.6823,
|
|
"mean_token_accuracy": 0.2271655336022377,
|
|
"num_tokens": 11807120.0,
|
|
"step": 5010
|
|
},
|
|
{
|
|
"entropy": 5.296036624908448,
|
|
"epoch": 5.10697911360163,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0003062698066521903,
|
|
"loss": 4.7214,
|
|
"mean_token_accuracy": 0.22745058685541153,
|
|
"num_tokens": 11818781.0,
|
|
"step": 5015
|
|
},
|
|
{
|
|
"entropy": 5.360927677154541,
|
|
"epoch": 5.112073357106469,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0003058724820600503,
|
|
"loss": 4.7423,
|
|
"mean_token_accuracy": 0.21792110353708266,
|
|
"num_tokens": 11829486.0,
|
|
"step": 5020
|
|
},
|
|
{
|
|
"entropy": 5.2078657150268555,
|
|
"epoch": 5.117167600611309,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00030547505932490115,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.22808048874139786,
|
|
"num_tokens": 11842678.0,
|
|
"step": 5025
|
|
},
|
|
{
|
|
"entropy": 5.335958099365234,
|
|
"epoch": 5.1222618441161485,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003050775397101421,
|
|
"loss": 4.771,
|
|
"mean_token_accuracy": 0.2167415976524353,
|
|
"num_tokens": 11854378.0,
|
|
"step": 5030
|
|
},
|
|
{
|
|
"entropy": 5.324215936660766,
|
|
"epoch": 5.1273560876209885,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003046799244794799,
|
|
"loss": 4.7352,
|
|
"mean_token_accuracy": 0.222627092897892,
|
|
"num_tokens": 11866545.0,
|
|
"step": 5035
|
|
},
|
|
{
|
|
"entropy": 5.348083257675171,
|
|
"epoch": 5.132450331125828,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0003042822148969257,
|
|
"loss": 4.8776,
|
|
"mean_token_accuracy": 0.20950710028409958,
|
|
"num_tokens": 11878908.0,
|
|
"step": 5040
|
|
},
|
|
{
|
|
"entropy": 5.3620987892150875,
|
|
"epoch": 5.137544574630668,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00030388441222679017,
|
|
"loss": 4.7639,
|
|
"mean_token_accuracy": 0.2186336562037468,
|
|
"num_tokens": 11892243.0,
|
|
"step": 5045
|
|
},
|
|
{
|
|
"entropy": 5.272714233398437,
|
|
"epoch": 5.142638818135507,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00030348651773368047,
|
|
"loss": 4.7331,
|
|
"mean_token_accuracy": 0.22093216329813004,
|
|
"num_tokens": 11904704.0,
|
|
"step": 5050
|
|
},
|
|
{
|
|
"entropy": 5.289368724822998,
|
|
"epoch": 5.147733061640347,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00030308853268249487,
|
|
"loss": 4.7491,
|
|
"mean_token_accuracy": 0.2269238129258156,
|
|
"num_tokens": 11916108.0,
|
|
"step": 5055
|
|
},
|
|
{
|
|
"entropy": 5.299552536010742,
|
|
"epoch": 5.152827305145186,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00030269045833842027,
|
|
"loss": 4.708,
|
|
"mean_token_accuracy": 0.227940933406353,
|
|
"num_tokens": 11927782.0,
|
|
"step": 5060
|
|
},
|
|
{
|
|
"entropy": 5.309333467483521,
|
|
"epoch": 5.157921548650026,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00030229229596692703,
|
|
"loss": 4.65,
|
|
"mean_token_accuracy": 0.2357498973608017,
|
|
"num_tokens": 11937290.0,
|
|
"step": 5065
|
|
},
|
|
{
|
|
"entropy": 5.366444778442383,
|
|
"epoch": 5.163015792154865,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00030189404683376547,
|
|
"loss": 4.8471,
|
|
"mean_token_accuracy": 0.21700279712677,
|
|
"num_tokens": 11949286.0,
|
|
"step": 5070
|
|
},
|
|
{
|
|
"entropy": 5.298268222808838,
|
|
"epoch": 5.168110035659705,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0003014957122049617,
|
|
"loss": 4.7711,
|
|
"mean_token_accuracy": 0.22733518481254578,
|
|
"num_tokens": 11960021.0,
|
|
"step": 5075
|
|
},
|
|
{
|
|
"entropy": 5.403427457809448,
|
|
"epoch": 5.173204279164544,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0003010972933468136,
|
|
"loss": 4.8059,
|
|
"mean_token_accuracy": 0.21236783415079116,
|
|
"num_tokens": 11971638.0,
|
|
"step": 5080
|
|
},
|
|
{
|
|
"entropy": 5.282622289657593,
|
|
"epoch": 5.178298522669383,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0003006987915258867,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.2232246533036232,
|
|
"num_tokens": 11984315.0,
|
|
"step": 5085
|
|
},
|
|
{
|
|
"entropy": 5.379745149612427,
|
|
"epoch": 5.183392766174223,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00030030020800901066,
|
|
"loss": 4.811,
|
|
"mean_token_accuracy": 0.21322886496782303,
|
|
"num_tokens": 11995775.0,
|
|
"step": 5090
|
|
},
|
|
{
|
|
"entropy": 5.256829071044922,
|
|
"epoch": 5.188487009679062,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00029990154406327435,
|
|
"loss": 4.7058,
|
|
"mean_token_accuracy": 0.22380207777023314,
|
|
"num_tokens": 12007121.0,
|
|
"step": 5095
|
|
},
|
|
{
|
|
"entropy": 5.310078573226929,
|
|
"epoch": 5.193581253183902,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002995028009560228,
|
|
"loss": 4.7634,
|
|
"mean_token_accuracy": 0.22085724174976348,
|
|
"num_tokens": 12018346.0,
|
|
"step": 5100
|
|
},
|
|
{
|
|
"entropy": 5.257878112792969,
|
|
"epoch": 5.198675496688741,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00029910397995485213,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.22789659798145295,
|
|
"num_tokens": 12029237.0,
|
|
"step": 5105
|
|
},
|
|
{
|
|
"entropy": 5.335200691223145,
|
|
"epoch": 5.203769740193581,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00029870508232760667,
|
|
"loss": 4.8345,
|
|
"mean_token_accuracy": 0.21218325942754745,
|
|
"num_tokens": 12041116.0,
|
|
"step": 5110
|
|
},
|
|
{
|
|
"entropy": 5.240345239639282,
|
|
"epoch": 5.2088639836984205,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00029830610934237394,
|
|
"loss": 4.7124,
|
|
"mean_token_accuracy": 0.224171943962574,
|
|
"num_tokens": 12052677.0,
|
|
"step": 5115
|
|
},
|
|
{
|
|
"entropy": 5.383189058303833,
|
|
"epoch": 5.2139582272032605,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00029790706226748124,
|
|
"loss": 4.8094,
|
|
"mean_token_accuracy": 0.2120413824915886,
|
|
"num_tokens": 12064749.0,
|
|
"step": 5120
|
|
},
|
|
{
|
|
"entropy": 5.327667093276977,
|
|
"epoch": 5.2190524707081,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00029750794237149125,
|
|
"loss": 4.7904,
|
|
"mean_token_accuracy": 0.21829205602407456,
|
|
"num_tokens": 12076679.0,
|
|
"step": 5125
|
|
},
|
|
{
|
|
"entropy": 5.279372882843018,
|
|
"epoch": 5.22414671421294,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00029710875092319827,
|
|
"loss": 4.733,
|
|
"mean_token_accuracy": 0.22172516584396362,
|
|
"num_tokens": 12088047.0,
|
|
"step": 5130
|
|
},
|
|
{
|
|
"entropy": 5.3574989318847654,
|
|
"epoch": 5.229240957717779,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.000296709489191624,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.21157287806272507,
|
|
"num_tokens": 12099846.0,
|
|
"step": 5135
|
|
},
|
|
{
|
|
"entropy": 5.369092988967895,
|
|
"epoch": 5.234335201222619,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002963101584460136,
|
|
"loss": 4.8216,
|
|
"mean_token_accuracy": 0.21310691088438033,
|
|
"num_tokens": 12111719.0,
|
|
"step": 5140
|
|
},
|
|
{
|
|
"entropy": 5.323548126220703,
|
|
"epoch": 5.239429444727458,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002959107599558315,
|
|
"loss": 4.7275,
|
|
"mean_token_accuracy": 0.22620878219604493,
|
|
"num_tokens": 12123225.0,
|
|
"step": 5145
|
|
},
|
|
{
|
|
"entropy": 5.269704866409302,
|
|
"epoch": 5.244523688232298,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0002955112949907576,
|
|
"loss": 4.735,
|
|
"mean_token_accuracy": 0.22648628950119018,
|
|
"num_tokens": 12134681.0,
|
|
"step": 5150
|
|
},
|
|
{
|
|
"entropy": 5.237067174911499,
|
|
"epoch": 5.249617931737137,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00029511176482068327,
|
|
"loss": 4.6656,
|
|
"mean_token_accuracy": 0.2307213604450226,
|
|
"num_tokens": 12147109.0,
|
|
"step": 5155
|
|
},
|
|
{
|
|
"entropy": 5.330927848815918,
|
|
"epoch": 5.254712175241977,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00029471217071570685,
|
|
"loss": 4.7752,
|
|
"mean_token_accuracy": 0.2226114422082901,
|
|
"num_tokens": 12158637.0,
|
|
"step": 5160
|
|
},
|
|
{
|
|
"entropy": 5.328795671463013,
|
|
"epoch": 5.259806418746816,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002943125139461301,
|
|
"loss": 4.7597,
|
|
"mean_token_accuracy": 0.22266752123832703,
|
|
"num_tokens": 12169777.0,
|
|
"step": 5165
|
|
},
|
|
{
|
|
"entropy": 5.31660041809082,
|
|
"epoch": 5.264900662251655,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002939127957824541,
|
|
"loss": 4.7562,
|
|
"mean_token_accuracy": 0.22243620604276657,
|
|
"num_tokens": 12180985.0,
|
|
"step": 5170
|
|
},
|
|
{
|
|
"entropy": 5.317618370056152,
|
|
"epoch": 5.269994905756495,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00029351301749537485,
|
|
"loss": 4.7824,
|
|
"mean_token_accuracy": 0.21676531285047532,
|
|
"num_tokens": 12192790.0,
|
|
"step": 5175
|
|
},
|
|
{
|
|
"entropy": 5.342991495132447,
|
|
"epoch": 5.275089149261334,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002931131803557796,
|
|
"loss": 4.7579,
|
|
"mean_token_accuracy": 0.22048269957304,
|
|
"num_tokens": 12204802.0,
|
|
"step": 5180
|
|
},
|
|
{
|
|
"entropy": 5.202065372467041,
|
|
"epoch": 5.280183392766174,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00029271328563474275,
|
|
"loss": 4.7202,
|
|
"mean_token_accuracy": 0.2293684408068657,
|
|
"num_tokens": 12216021.0,
|
|
"step": 5185
|
|
},
|
|
{
|
|
"entropy": 5.289933156967163,
|
|
"epoch": 5.285277636271013,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00029231333460352175,
|
|
"loss": 4.6717,
|
|
"mean_token_accuracy": 0.22737237960100173,
|
|
"num_tokens": 12227209.0,
|
|
"step": 5190
|
|
},
|
|
{
|
|
"entropy": 5.263871145248413,
|
|
"epoch": 5.290371879775853,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002919133285335529,
|
|
"loss": 4.7057,
|
|
"mean_token_accuracy": 0.2234347254037857,
|
|
"num_tokens": 12238160.0,
|
|
"step": 5195
|
|
},
|
|
{
|
|
"entropy": 5.299736452102661,
|
|
"epoch": 5.2954661232806925,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002915132686964476,
|
|
"loss": 4.739,
|
|
"mean_token_accuracy": 0.2210393100976944,
|
|
"num_tokens": 12249383.0,
|
|
"step": 5200
|
|
},
|
|
{
|
|
"entropy": 5.283786058425903,
|
|
"epoch": 5.3005603667855326,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002911131563639883,
|
|
"loss": 4.7361,
|
|
"mean_token_accuracy": 0.22883862406015396,
|
|
"num_tokens": 12260552.0,
|
|
"step": 5205
|
|
},
|
|
{
|
|
"entropy": 5.330094861984253,
|
|
"epoch": 5.305654610290372,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00029071299280812395,
|
|
"loss": 4.8492,
|
|
"mean_token_accuracy": 0.21319890022277832,
|
|
"num_tokens": 12272937.0,
|
|
"step": 5210
|
|
},
|
|
{
|
|
"entropy": 5.305624341964721,
|
|
"epoch": 5.310748853795212,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002903127793009667,
|
|
"loss": 4.7849,
|
|
"mean_token_accuracy": 0.21620476394891738,
|
|
"num_tokens": 12283771.0,
|
|
"step": 5215
|
|
},
|
|
{
|
|
"entropy": 5.300009679794312,
|
|
"epoch": 5.315843097300051,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002899125171147872,
|
|
"loss": 4.7829,
|
|
"mean_token_accuracy": 0.2223973348736763,
|
|
"num_tokens": 12294918.0,
|
|
"step": 5220
|
|
},
|
|
{
|
|
"entropy": 5.322295808792115,
|
|
"epoch": 5.320937340804891,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002895122075220113,
|
|
"loss": 4.835,
|
|
"mean_token_accuracy": 0.2152709186077118,
|
|
"num_tokens": 12306700.0,
|
|
"step": 5225
|
|
},
|
|
{
|
|
"entropy": 5.291075658798218,
|
|
"epoch": 5.32603158430973,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002891118517952151,
|
|
"loss": 4.7266,
|
|
"mean_token_accuracy": 0.2202738642692566,
|
|
"num_tokens": 12318163.0,
|
|
"step": 5230
|
|
},
|
|
{
|
|
"entropy": 5.308155679702759,
|
|
"epoch": 5.33112582781457,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002887114512071215,
|
|
"loss": 4.8828,
|
|
"mean_token_accuracy": 0.21380746513605117,
|
|
"num_tokens": 12331440.0,
|
|
"step": 5235
|
|
},
|
|
{
|
|
"entropy": 5.37018985748291,
|
|
"epoch": 5.336220071319409,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.000288311007030596,
|
|
"loss": 4.8847,
|
|
"mean_token_accuracy": 0.21251877695322036,
|
|
"num_tokens": 12344298.0,
|
|
"step": 5240
|
|
},
|
|
{
|
|
"entropy": 5.351928281784057,
|
|
"epoch": 5.341314314824249,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002879105205386429,
|
|
"loss": 4.7766,
|
|
"mean_token_accuracy": 0.21665124744176864,
|
|
"num_tokens": 12356279.0,
|
|
"step": 5245
|
|
},
|
|
{
|
|
"entropy": 5.301804637908935,
|
|
"epoch": 5.346408558329088,
|
|
"grad_norm": 1.0546875,
|
|
"learning_rate": 0.0002875099930044007,
|
|
"loss": 4.7669,
|
|
"mean_token_accuracy": 0.22617137730121611,
|
|
"num_tokens": 12368991.0,
|
|
"step": 5250
|
|
},
|
|
{
|
|
"entropy": 5.302726697921753,
|
|
"epoch": 5.351502801833927,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00028710942570113853,
|
|
"loss": 4.7455,
|
|
"mean_token_accuracy": 0.2233827993273735,
|
|
"num_tokens": 12381222.0,
|
|
"step": 5255
|
|
},
|
|
{
|
|
"entropy": 5.232884407043457,
|
|
"epoch": 5.356597045338767,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00028670881990225177,
|
|
"loss": 4.6701,
|
|
"mean_token_accuracy": 0.22990489453077317,
|
|
"num_tokens": 12393310.0,
|
|
"step": 5260
|
|
},
|
|
{
|
|
"entropy": 5.211752462387085,
|
|
"epoch": 5.361691288843606,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002863081768812585,
|
|
"loss": 4.7097,
|
|
"mean_token_accuracy": 0.2247814267873764,
|
|
"num_tokens": 12405061.0,
|
|
"step": 5265
|
|
},
|
|
{
|
|
"entropy": 5.33771858215332,
|
|
"epoch": 5.366785532348446,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002859074979117949,
|
|
"loss": 4.8305,
|
|
"mean_token_accuracy": 0.21847476959228515,
|
|
"num_tokens": 12416733.0,
|
|
"step": 5270
|
|
},
|
|
{
|
|
"entropy": 5.315059614181519,
|
|
"epoch": 5.3718797758532855,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002855067842676115,
|
|
"loss": 4.7484,
|
|
"mean_token_accuracy": 0.2282280996441841,
|
|
"num_tokens": 12429564.0,
|
|
"step": 5275
|
|
},
|
|
{
|
|
"entropy": 5.278658151626587,
|
|
"epoch": 5.3769740193581255,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00028510603722256897,
|
|
"loss": 4.7514,
|
|
"mean_token_accuracy": 0.21913171112537383,
|
|
"num_tokens": 12441032.0,
|
|
"step": 5280
|
|
},
|
|
{
|
|
"entropy": 5.324036026000977,
|
|
"epoch": 5.382068262862965,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028470525805063425,
|
|
"loss": 4.8897,
|
|
"mean_token_accuracy": 0.2117917388677597,
|
|
"num_tokens": 12453512.0,
|
|
"step": 5285
|
|
},
|
|
{
|
|
"entropy": 5.3357585906982425,
|
|
"epoch": 5.387162506367805,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00028430444802587647,
|
|
"loss": 4.8165,
|
|
"mean_token_accuracy": 0.2157785564661026,
|
|
"num_tokens": 12466134.0,
|
|
"step": 5290
|
|
},
|
|
{
|
|
"entropy": 5.370906114578247,
|
|
"epoch": 5.392256749872644,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00028390360842246265,
|
|
"loss": 4.8409,
|
|
"mean_token_accuracy": 0.21409149318933487,
|
|
"num_tokens": 12478092.0,
|
|
"step": 5295
|
|
},
|
|
{
|
|
"entropy": 5.299875783920288,
|
|
"epoch": 5.397350993377484,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.000283502740514654,
|
|
"loss": 4.8082,
|
|
"mean_token_accuracy": 0.2191591128706932,
|
|
"num_tokens": 12489846.0,
|
|
"step": 5300
|
|
},
|
|
{
|
|
"entropy": 5.297913980484009,
|
|
"epoch": 5.402445236882323,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002831018455768016,
|
|
"loss": 4.7654,
|
|
"mean_token_accuracy": 0.22125112861394883,
|
|
"num_tokens": 12501181.0,
|
|
"step": 5305
|
|
},
|
|
{
|
|
"entropy": 5.388188600540161,
|
|
"epoch": 5.407539480387163,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002827009248833427,
|
|
"loss": 4.8213,
|
|
"mean_token_accuracy": 0.21842779219150543,
|
|
"num_tokens": 12513546.0,
|
|
"step": 5310
|
|
},
|
|
{
|
|
"entropy": 5.3726646900177,
|
|
"epoch": 5.412633723892002,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00028229997970879604,
|
|
"loss": 4.891,
|
|
"mean_token_accuracy": 0.2102529749274254,
|
|
"num_tokens": 12526063.0,
|
|
"step": 5315
|
|
},
|
|
{
|
|
"entropy": 5.2699024200439455,
|
|
"epoch": 5.417727967396842,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002818990113277584,
|
|
"loss": 4.7578,
|
|
"mean_token_accuracy": 0.21960590928792953,
|
|
"num_tokens": 12537855.0,
|
|
"step": 5320
|
|
},
|
|
{
|
|
"entropy": 5.293085527420044,
|
|
"epoch": 5.422822210901681,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002814980210149005,
|
|
"loss": 4.7893,
|
|
"mean_token_accuracy": 0.21680165082216263,
|
|
"num_tokens": 12549789.0,
|
|
"step": 5325
|
|
},
|
|
{
|
|
"entropy": 5.347575759887695,
|
|
"epoch": 5.427916454406521,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00028109701004496254,
|
|
"loss": 4.827,
|
|
"mean_token_accuracy": 0.21282076090574265,
|
|
"num_tokens": 12562298.0,
|
|
"step": 5330
|
|
},
|
|
{
|
|
"entropy": 5.253691959381103,
|
|
"epoch": 5.43301069791136,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00028069597969275023,
|
|
"loss": 4.6885,
|
|
"mean_token_accuracy": 0.22793179601430893,
|
|
"num_tokens": 12574511.0,
|
|
"step": 5335
|
|
},
|
|
{
|
|
"entropy": 5.310761976242065,
|
|
"epoch": 5.438104941416199,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002802949312331314,
|
|
"loss": 4.7701,
|
|
"mean_token_accuracy": 0.2228243574500084,
|
|
"num_tokens": 12586008.0,
|
|
"step": 5340
|
|
},
|
|
{
|
|
"entropy": 5.247701597213745,
|
|
"epoch": 5.443199184921039,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.000279893865941031,
|
|
"loss": 4.7526,
|
|
"mean_token_accuracy": 0.22387887239456178,
|
|
"num_tokens": 12597882.0,
|
|
"step": 5345
|
|
},
|
|
{
|
|
"entropy": 5.2803243637084964,
|
|
"epoch": 5.448293428425878,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002794927850914278,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.2192904010415077,
|
|
"num_tokens": 12609346.0,
|
|
"step": 5350
|
|
},
|
|
{
|
|
"entropy": 5.29275221824646,
|
|
"epoch": 5.453387671930718,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0002790916899593496,
|
|
"loss": 4.7464,
|
|
"mean_token_accuracy": 0.22498622238636018,
|
|
"num_tokens": 12621023.0,
|
|
"step": 5355
|
|
},
|
|
{
|
|
"entropy": 5.281299209594726,
|
|
"epoch": 5.4584819154355575,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002786905818198702,
|
|
"loss": 4.7507,
|
|
"mean_token_accuracy": 0.22403040230274202,
|
|
"num_tokens": 12631806.0,
|
|
"step": 5360
|
|
},
|
|
{
|
|
"entropy": 5.286287307739258,
|
|
"epoch": 5.4635761589403975,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002782894619481042,
|
|
"loss": 4.7876,
|
|
"mean_token_accuracy": 0.21939586251974105,
|
|
"num_tokens": 12641969.0,
|
|
"step": 5365
|
|
},
|
|
{
|
|
"entropy": 5.388695478439331,
|
|
"epoch": 5.468670402445237,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.000277888331619204,
|
|
"loss": 4.8634,
|
|
"mean_token_accuracy": 0.2076227605342865,
|
|
"num_tokens": 12653891.0,
|
|
"step": 5370
|
|
},
|
|
{
|
|
"entropy": 5.329965877532959,
|
|
"epoch": 5.473764645950077,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.0002774871921083546,
|
|
"loss": 4.7619,
|
|
"mean_token_accuracy": 0.22461912781000137,
|
|
"num_tokens": 12666422.0,
|
|
"step": 5375
|
|
},
|
|
{
|
|
"entropy": 5.296063470840454,
|
|
"epoch": 5.478858889454916,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002770860446907708,
|
|
"loss": 4.7665,
|
|
"mean_token_accuracy": 0.2241215690970421,
|
|
"num_tokens": 12677622.0,
|
|
"step": 5380
|
|
},
|
|
{
|
|
"entropy": 5.312583494186401,
|
|
"epoch": 5.483953132959756,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002766848906416922,
|
|
"loss": 4.8271,
|
|
"mean_token_accuracy": 0.2179318055510521,
|
|
"num_tokens": 12688096.0,
|
|
"step": 5385
|
|
},
|
|
{
|
|
"entropy": 5.3307273387908936,
|
|
"epoch": 5.489047376464595,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00027628373123637977,
|
|
"loss": 4.7813,
|
|
"mean_token_accuracy": 0.22128760069608688,
|
|
"num_tokens": 12701054.0,
|
|
"step": 5390
|
|
},
|
|
{
|
|
"entropy": 5.370690727233887,
|
|
"epoch": 5.494141619969435,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.000275882567750111,
|
|
"loss": 4.8327,
|
|
"mean_token_accuracy": 0.21734288483858108,
|
|
"num_tokens": 12712329.0,
|
|
"step": 5395
|
|
},
|
|
{
|
|
"entropy": 5.267995166778564,
|
|
"epoch": 5.499235863474274,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002754814014581769,
|
|
"loss": 4.7243,
|
|
"mean_token_accuracy": 0.2324063241481781,
|
|
"num_tokens": 12723472.0,
|
|
"step": 5400
|
|
},
|
|
{
|
|
"entropy": 5.267073917388916,
|
|
"epoch": 5.504330106979114,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002750802336358771,
|
|
"loss": 4.7012,
|
|
"mean_token_accuracy": 0.230333112180233,
|
|
"num_tokens": 12734707.0,
|
|
"step": 5405
|
|
},
|
|
{
|
|
"entropy": 5.291806173324585,
|
|
"epoch": 5.509424350483953,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00027467906555851614,
|
|
"loss": 4.7056,
|
|
"mean_token_accuracy": 0.22460830509662627,
|
|
"num_tokens": 12745073.0,
|
|
"step": 5410
|
|
},
|
|
{
|
|
"entropy": 5.2970630645751955,
|
|
"epoch": 5.514518593988793,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002742778985013994,
|
|
"loss": 4.7877,
|
|
"mean_token_accuracy": 0.2213443025946617,
|
|
"num_tokens": 12757401.0,
|
|
"step": 5415
|
|
},
|
|
{
|
|
"entropy": 5.282443046569824,
|
|
"epoch": 5.519612837493632,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0002738767337398292,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22317015677690505,
|
|
"num_tokens": 12768811.0,
|
|
"step": 5420
|
|
},
|
|
{
|
|
"entropy": 5.371711301803589,
|
|
"epoch": 5.524707080998471,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002734755725491,
|
|
"loss": 4.9048,
|
|
"mean_token_accuracy": 0.20948395878076553,
|
|
"num_tokens": 12782344.0,
|
|
"step": 5425
|
|
},
|
|
{
|
|
"entropy": 5.361355352401733,
|
|
"epoch": 5.529801324503311,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002730744162044955,
|
|
"loss": 4.7969,
|
|
"mean_token_accuracy": 0.21680393368005751,
|
|
"num_tokens": 12795164.0,
|
|
"step": 5430
|
|
},
|
|
{
|
|
"entropy": 5.334631538391113,
|
|
"epoch": 5.53489556800815,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00027267326598128373,
|
|
"loss": 4.8523,
|
|
"mean_token_accuracy": 0.2090735226869583,
|
|
"num_tokens": 12807824.0,
|
|
"step": 5435
|
|
},
|
|
{
|
|
"entropy": 5.307574701309204,
|
|
"epoch": 5.53998981151299,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00027227212315471337,
|
|
"loss": 4.7239,
|
|
"mean_token_accuracy": 0.2197732299566269,
|
|
"num_tokens": 12819230.0,
|
|
"step": 5440
|
|
},
|
|
{
|
|
"entropy": 5.270747566223145,
|
|
"epoch": 5.5450840550178295,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00027187098900000945,
|
|
"loss": 4.7779,
|
|
"mean_token_accuracy": 0.22965211868286134,
|
|
"num_tokens": 12830023.0,
|
|
"step": 5445
|
|
},
|
|
{
|
|
"entropy": 5.2959784984588625,
|
|
"epoch": 5.5501782985226695,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00027146986479236954,
|
|
"loss": 4.8535,
|
|
"mean_token_accuracy": 0.2181740954518318,
|
|
"num_tokens": 12841860.0,
|
|
"step": 5450
|
|
},
|
|
{
|
|
"entropy": 5.301433515548706,
|
|
"epoch": 5.555272542027509,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002710687518069595,
|
|
"loss": 4.718,
|
|
"mean_token_accuracy": 0.230163836479187,
|
|
"num_tokens": 12853296.0,
|
|
"step": 5455
|
|
},
|
|
{
|
|
"entropy": 5.281148481369018,
|
|
"epoch": 5.560366785532349,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002706676513189097,
|
|
"loss": 4.7288,
|
|
"mean_token_accuracy": 0.23077665269374847,
|
|
"num_tokens": 12865137.0,
|
|
"step": 5460
|
|
},
|
|
{
|
|
"entropy": 5.259906911849976,
|
|
"epoch": 5.565461029037188,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0002702665646033105,
|
|
"loss": 4.8039,
|
|
"mean_token_accuracy": 0.21835279911756517,
|
|
"num_tokens": 12877928.0,
|
|
"step": 5465
|
|
},
|
|
{
|
|
"entropy": 5.338911819458008,
|
|
"epoch": 5.570555272542028,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002698654929352087,
|
|
"loss": 4.8017,
|
|
"mean_token_accuracy": 0.22001161128282548,
|
|
"num_tokens": 12890474.0,
|
|
"step": 5470
|
|
},
|
|
{
|
|
"entropy": 5.411423206329346,
|
|
"epoch": 5.575649516046867,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002694644375896031,
|
|
"loss": 4.8488,
|
|
"mean_token_accuracy": 0.21217204481363297,
|
|
"num_tokens": 12902156.0,
|
|
"step": 5475
|
|
},
|
|
{
|
|
"entropy": 5.328145456314087,
|
|
"epoch": 5.580743759551707,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00026906339984144077,
|
|
"loss": 4.7857,
|
|
"mean_token_accuracy": 0.21617941856384276,
|
|
"num_tokens": 12914489.0,
|
|
"step": 5480
|
|
},
|
|
{
|
|
"entropy": 5.312273359298706,
|
|
"epoch": 5.585838003056546,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002686623809656128,
|
|
"loss": 4.7809,
|
|
"mean_token_accuracy": 0.2294939637184143,
|
|
"num_tokens": 12924967.0,
|
|
"step": 5485
|
|
},
|
|
{
|
|
"entropy": 5.245684623718262,
|
|
"epoch": 5.590932246561386,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00026826138223695026,
|
|
"loss": 4.8034,
|
|
"mean_token_accuracy": 0.21877288967370986,
|
|
"num_tokens": 12937794.0,
|
|
"step": 5490
|
|
},
|
|
{
|
|
"entropy": 5.219638776779175,
|
|
"epoch": 5.596026490066225,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0002678604049302201,
|
|
"loss": 4.7746,
|
|
"mean_token_accuracy": 0.2243422672152519,
|
|
"num_tokens": 12949186.0,
|
|
"step": 5495
|
|
},
|
|
{
|
|
"entropy": 5.296114158630371,
|
|
"epoch": 5.601120733571065,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00026745945032012126,
|
|
"loss": 4.7947,
|
|
"mean_token_accuracy": 0.21570215821266175,
|
|
"num_tokens": 12961651.0,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"entropy": 5.287897443771362,
|
|
"epoch": 5.606214977075904,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00026705851968128046,
|
|
"loss": 4.7642,
|
|
"mean_token_accuracy": 0.22394537925720215,
|
|
"num_tokens": 12974485.0,
|
|
"step": 5505
|
|
},
|
|
{
|
|
"entropy": 5.286743307113648,
|
|
"epoch": 5.611309220580743,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00026665761428824837,
|
|
"loss": 4.8536,
|
|
"mean_token_accuracy": 0.21406717896461486,
|
|
"num_tokens": 12987152.0,
|
|
"step": 5510
|
|
},
|
|
{
|
|
"entropy": 5.30659818649292,
|
|
"epoch": 5.616403464085583,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00026625673541549525,
|
|
"loss": 4.7808,
|
|
"mean_token_accuracy": 0.2280205875635147,
|
|
"num_tokens": 12998860.0,
|
|
"step": 5515
|
|
},
|
|
{
|
|
"entropy": 5.328375816345215,
|
|
"epoch": 5.621497707590422,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026585588433740697,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.21779752075672149,
|
|
"num_tokens": 13011320.0,
|
|
"step": 5520
|
|
},
|
|
{
|
|
"entropy": 5.301912927627564,
|
|
"epoch": 5.6265919510952624,
|
|
"grad_norm": 1.046875,
|
|
"learning_rate": 0.0002654550623282813,
|
|
"loss": 4.8508,
|
|
"mean_token_accuracy": 0.22082321494817733,
|
|
"num_tokens": 13023371.0,
|
|
"step": 5525
|
|
},
|
|
{
|
|
"entropy": 5.333499622344971,
|
|
"epoch": 5.631686194600102,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00026505427066232353,
|
|
"loss": 4.7598,
|
|
"mean_token_accuracy": 0.22505124062299728,
|
|
"num_tokens": 13034926.0,
|
|
"step": 5530
|
|
},
|
|
{
|
|
"entropy": 5.280611276626587,
|
|
"epoch": 5.636780438104942,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002646535106136423,
|
|
"loss": 4.7603,
|
|
"mean_token_accuracy": 0.22835413813591005,
|
|
"num_tokens": 13045928.0,
|
|
"step": 5535
|
|
},
|
|
{
|
|
"entropy": 5.236199522018433,
|
|
"epoch": 5.641874681609781,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0002642527834562459,
|
|
"loss": 4.7871,
|
|
"mean_token_accuracy": 0.22636783719062806,
|
|
"num_tokens": 13057368.0,
|
|
"step": 5540
|
|
},
|
|
{
|
|
"entropy": 5.236182594299317,
|
|
"epoch": 5.646968925114621,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002638520904640381,
|
|
"loss": 4.6748,
|
|
"mean_token_accuracy": 0.2309649258852005,
|
|
"num_tokens": 13068833.0,
|
|
"step": 5545
|
|
},
|
|
{
|
|
"entropy": 5.330357360839844,
|
|
"epoch": 5.65206316861946,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002634514329108138,
|
|
"loss": 4.8146,
|
|
"mean_token_accuracy": 0.21276101022958754,
|
|
"num_tokens": 13080735.0,
|
|
"step": 5550
|
|
},
|
|
{
|
|
"entropy": 5.25678243637085,
|
|
"epoch": 5.6571574121243,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002630508120702557,
|
|
"loss": 4.702,
|
|
"mean_token_accuracy": 0.23218899220228195,
|
|
"num_tokens": 13091985.0,
|
|
"step": 5555
|
|
},
|
|
{
|
|
"entropy": 5.293676376342773,
|
|
"epoch": 5.662251655629139,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002626502292159292,
|
|
"loss": 4.8318,
|
|
"mean_token_accuracy": 0.21790169477462767,
|
|
"num_tokens": 13104126.0,
|
|
"step": 5560
|
|
},
|
|
{
|
|
"entropy": 5.315334272384644,
|
|
"epoch": 5.667345899133979,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002622496856212795,
|
|
"loss": 4.7675,
|
|
"mean_token_accuracy": 0.2207478925585747,
|
|
"num_tokens": 13115311.0,
|
|
"step": 5565
|
|
},
|
|
{
|
|
"entropy": 5.244106578826904,
|
|
"epoch": 5.672440142638818,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002618491825596267,
|
|
"loss": 4.7791,
|
|
"mean_token_accuracy": 0.22373220771551133,
|
|
"num_tokens": 13127610.0,
|
|
"step": 5570
|
|
},
|
|
{
|
|
"entropy": 5.2876183032989506,
|
|
"epoch": 5.677534386143658,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002614487213041621,
|
|
"loss": 4.7679,
|
|
"mean_token_accuracy": 0.22118800431489943,
|
|
"num_tokens": 13140405.0,
|
|
"step": 5575
|
|
},
|
|
{
|
|
"entropy": 5.296089839935303,
|
|
"epoch": 5.682628629648497,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0002610483031279441,
|
|
"loss": 4.8006,
|
|
"mean_token_accuracy": 0.21934620589017867,
|
|
"num_tokens": 13153471.0,
|
|
"step": 5580
|
|
},
|
|
{
|
|
"entropy": 5.328262138366699,
|
|
"epoch": 5.687722873153337,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00026064792930389406,
|
|
"loss": 4.9178,
|
|
"mean_token_accuracy": 0.2119997188448906,
|
|
"num_tokens": 13167361.0,
|
|
"step": 5585
|
|
},
|
|
{
|
|
"entropy": 5.3454270362854,
|
|
"epoch": 5.692817116658176,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002602476011047926,
|
|
"loss": 4.8367,
|
|
"mean_token_accuracy": 0.213324898481369,
|
|
"num_tokens": 13178936.0,
|
|
"step": 5590
|
|
},
|
|
{
|
|
"entropy": 5.434294271469116,
|
|
"epoch": 5.697911360163015,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00025984731980327496,
|
|
"loss": 4.8184,
|
|
"mean_token_accuracy": 0.22080253362655639,
|
|
"num_tokens": 13191338.0,
|
|
"step": 5595
|
|
},
|
|
{
|
|
"entropy": 5.3029749393463135,
|
|
"epoch": 5.703005603667855,
|
|
"grad_norm": 1.03125,
|
|
"learning_rate": 0.00025944708667182754,
|
|
"loss": 4.798,
|
|
"mean_token_accuracy": 0.2171729475259781,
|
|
"num_tokens": 13203360.0,
|
|
"step": 5600
|
|
},
|
|
{
|
|
"entropy": 5.223143005371094,
|
|
"epoch": 5.7080998471726945,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002590469029827836,
|
|
"loss": 4.7311,
|
|
"mean_token_accuracy": 0.22322602421045304,
|
|
"num_tokens": 13215291.0,
|
|
"step": 5605
|
|
},
|
|
{
|
|
"entropy": 5.262010097503662,
|
|
"epoch": 5.7131940906775345,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.0002586467700083191,
|
|
"loss": 4.7561,
|
|
"mean_token_accuracy": 0.22530186474323272,
|
|
"num_tokens": 13227064.0,
|
|
"step": 5610
|
|
},
|
|
{
|
|
"entropy": 5.3148942470550535,
|
|
"epoch": 5.718288334182374,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00025824668902044883,
|
|
"loss": 4.8198,
|
|
"mean_token_accuracy": 0.2244748890399933,
|
|
"num_tokens": 13238913.0,
|
|
"step": 5615
|
|
},
|
|
{
|
|
"entropy": 5.294612026214599,
|
|
"epoch": 5.723382577687214,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00025784666129102254,
|
|
"loss": 4.8178,
|
|
"mean_token_accuracy": 0.21966160237789153,
|
|
"num_tokens": 13251037.0,
|
|
"step": 5620
|
|
},
|
|
{
|
|
"entropy": 5.352958393096924,
|
|
"epoch": 5.728476821192053,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002574466880917201,
|
|
"loss": 4.7762,
|
|
"mean_token_accuracy": 0.21837465167045594,
|
|
"num_tokens": 13261959.0,
|
|
"step": 5625
|
|
},
|
|
{
|
|
"entropy": 5.3159407615661625,
|
|
"epoch": 5.733571064696893,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00025704677069404854,
|
|
"loss": 4.8717,
|
|
"mean_token_accuracy": 0.2136336848139763,
|
|
"num_tokens": 13273010.0,
|
|
"step": 5630
|
|
},
|
|
{
|
|
"entropy": 5.310901069641114,
|
|
"epoch": 5.738665308201732,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00025664691036933745,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.2177631750702858,
|
|
"num_tokens": 13285159.0,
|
|
"step": 5635
|
|
},
|
|
{
|
|
"entropy": 5.250322008132935,
|
|
"epoch": 5.743759551706572,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00025624710838873476,
|
|
"loss": 4.7599,
|
|
"mean_token_accuracy": 0.21686694920063018,
|
|
"num_tokens": 13297894.0,
|
|
"step": 5640
|
|
},
|
|
{
|
|
"entropy": 5.256682825088501,
|
|
"epoch": 5.748853795211411,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002558473660232031,
|
|
"loss": 4.7021,
|
|
"mean_token_accuracy": 0.23804741352796555,
|
|
"num_tokens": 13308858.0,
|
|
"step": 5645
|
|
},
|
|
{
|
|
"entropy": 5.309435606002808,
|
|
"epoch": 5.753948038716251,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00025544768454351547,
|
|
"loss": 4.7909,
|
|
"mean_token_accuracy": 0.21521701365709306,
|
|
"num_tokens": 13320423.0,
|
|
"step": 5650
|
|
},
|
|
{
|
|
"entropy": 5.284757852554321,
|
|
"epoch": 5.75904228222109,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00025504806522025147,
|
|
"loss": 4.6994,
|
|
"mean_token_accuracy": 0.2253235325217247,
|
|
"num_tokens": 13332270.0,
|
|
"step": 5655
|
|
},
|
|
{
|
|
"entropy": 5.232186365127563,
|
|
"epoch": 5.76413652572593,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00025464850932379305,
|
|
"loss": 4.7033,
|
|
"mean_token_accuracy": 0.22820765674114227,
|
|
"num_tokens": 13344305.0,
|
|
"step": 5660
|
|
},
|
|
{
|
|
"entropy": 5.295166778564453,
|
|
"epoch": 5.769230769230769,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002542490181243203,
|
|
"loss": 4.8028,
|
|
"mean_token_accuracy": 0.223968043923378,
|
|
"num_tokens": 13355776.0,
|
|
"step": 5665
|
|
},
|
|
{
|
|
"entropy": 5.266491079330445,
|
|
"epoch": 5.774325012735609,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.000253849592891808,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.2218480110168457,
|
|
"num_tokens": 13367771.0,
|
|
"step": 5670
|
|
},
|
|
{
|
|
"entropy": 5.247437429428101,
|
|
"epoch": 5.779419256240448,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00025345023489602104,
|
|
"loss": 4.7488,
|
|
"mean_token_accuracy": 0.2223634973168373,
|
|
"num_tokens": 13379621.0,
|
|
"step": 5675
|
|
},
|
|
{
|
|
"entropy": 5.266488981246948,
|
|
"epoch": 5.784513499745287,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00025305094540651045,
|
|
"loss": 4.7592,
|
|
"mean_token_accuracy": 0.22653041183948516,
|
|
"num_tokens": 13391432.0,
|
|
"step": 5680
|
|
},
|
|
{
|
|
"entropy": 5.353699207305908,
|
|
"epoch": 5.789607743250127,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00025265172569260974,
|
|
"loss": 4.8613,
|
|
"mean_token_accuracy": 0.21004354059696198,
|
|
"num_tokens": 13404225.0,
|
|
"step": 5685
|
|
},
|
|
{
|
|
"entropy": 5.3144982814788815,
|
|
"epoch": 5.7947019867549665,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0002522525770234304,
|
|
"loss": 4.8072,
|
|
"mean_token_accuracy": 0.2184618279337883,
|
|
"num_tokens": 13417073.0,
|
|
"step": 5690
|
|
},
|
|
{
|
|
"entropy": 5.25388126373291,
|
|
"epoch": 5.7997962302598065,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002518535006678582,
|
|
"loss": 4.8127,
|
|
"mean_token_accuracy": 0.2228015899658203,
|
|
"num_tokens": 13429582.0,
|
|
"step": 5695
|
|
},
|
|
{
|
|
"entropy": 5.30713849067688,
|
|
"epoch": 5.804890473764646,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00025145449789454907,
|
|
"loss": 4.7521,
|
|
"mean_token_accuracy": 0.22233100086450577,
|
|
"num_tokens": 13441198.0,
|
|
"step": 5700
|
|
},
|
|
{
|
|
"entropy": 5.256593084335327,
|
|
"epoch": 5.809984717269486,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002510555699719246,
|
|
"loss": 4.7164,
|
|
"mean_token_accuracy": 0.22646549940109253,
|
|
"num_tokens": 13451786.0,
|
|
"step": 5705
|
|
},
|
|
{
|
|
"entropy": 5.272791481018066,
|
|
"epoch": 5.815078960774325,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.0002506567181681691,
|
|
"loss": 4.7606,
|
|
"mean_token_accuracy": 0.22452133893966675,
|
|
"num_tokens": 13463769.0,
|
|
"step": 5710
|
|
},
|
|
{
|
|
"entropy": 5.307537364959717,
|
|
"epoch": 5.820173204279165,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.0002502579437512243,
|
|
"loss": 4.762,
|
|
"mean_token_accuracy": 0.2250681698322296,
|
|
"num_tokens": 13476240.0,
|
|
"step": 5715
|
|
},
|
|
{
|
|
"entropy": 5.312796783447266,
|
|
"epoch": 5.825267447784004,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.0002498592479887863,
|
|
"loss": 4.7648,
|
|
"mean_token_accuracy": 0.2125743418931961,
|
|
"num_tokens": 13488718.0,
|
|
"step": 5720
|
|
},
|
|
{
|
|
"entropy": 5.224211645126343,
|
|
"epoch": 5.830361691288844,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00024946063214830106,
|
|
"loss": 4.6783,
|
|
"mean_token_accuracy": 0.22388290464878083,
|
|
"num_tokens": 13500029.0,
|
|
"step": 5725
|
|
},
|
|
{
|
|
"entropy": 5.2977344512939455,
|
|
"epoch": 5.835455934793683,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00024906209749696036,
|
|
"loss": 4.7056,
|
|
"mean_token_accuracy": 0.2274518072605133,
|
|
"num_tokens": 13512301.0,
|
|
"step": 5730
|
|
},
|
|
{
|
|
"entropy": 5.2626677513122555,
|
|
"epoch": 5.840550178298523,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00024866364530169797,
|
|
"loss": 4.766,
|
|
"mean_token_accuracy": 0.22554901987314224,
|
|
"num_tokens": 13524110.0,
|
|
"step": 5735
|
|
},
|
|
{
|
|
"entropy": 5.252031707763672,
|
|
"epoch": 5.845644421803362,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.0002482652768291857,
|
|
"loss": 4.7327,
|
|
"mean_token_accuracy": 0.22435745298862458,
|
|
"num_tokens": 13536003.0,
|
|
"step": 5740
|
|
},
|
|
{
|
|
"entropy": 5.328643178939819,
|
|
"epoch": 5.850738665308202,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002478669933458288,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.21311584264039993,
|
|
"num_tokens": 13547139.0,
|
|
"step": 5745
|
|
},
|
|
{
|
|
"entropy": 5.251488447189331,
|
|
"epoch": 5.855832908813041,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002474687961177626,
|
|
"loss": 4.7451,
|
|
"mean_token_accuracy": 0.22237400114536285,
|
|
"num_tokens": 13558228.0,
|
|
"step": 5750
|
|
},
|
|
{
|
|
"entropy": 5.338308477401734,
|
|
"epoch": 5.860927152317881,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00024707068641084836,
|
|
"loss": 4.8331,
|
|
"mean_token_accuracy": 0.21152447611093522,
|
|
"num_tokens": 13571107.0,
|
|
"step": 5755
|
|
},
|
|
{
|
|
"entropy": 5.257913970947266,
|
|
"epoch": 5.86602139582272,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.0002466726654906688,
|
|
"loss": 4.7441,
|
|
"mean_token_accuracy": 0.2264036625623703,
|
|
"num_tokens": 13581848.0,
|
|
"step": 5760
|
|
},
|
|
{
|
|
"entropy": 5.278368520736694,
|
|
"epoch": 5.871115639327559,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0002462747346225246,
|
|
"loss": 4.7482,
|
|
"mean_token_accuracy": 0.22340274900197982,
|
|
"num_tokens": 13592660.0,
|
|
"step": 5765
|
|
},
|
|
{
|
|
"entropy": 5.300762748718261,
|
|
"epoch": 5.876209882832399,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002458768950714302,
|
|
"loss": 4.7348,
|
|
"mean_token_accuracy": 0.23033428341150283,
|
|
"num_tokens": 13603313.0,
|
|
"step": 5770
|
|
},
|
|
{
|
|
"entropy": 5.243822431564331,
|
|
"epoch": 5.8813041263372385,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00024547914810210946,
|
|
"loss": 4.781,
|
|
"mean_token_accuracy": 0.22086782455444337,
|
|
"num_tokens": 13614043.0,
|
|
"step": 5775
|
|
},
|
|
{
|
|
"entropy": 5.230408763885498,
|
|
"epoch": 5.8863983698420785,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00024508149497899233,
|
|
"loss": 4.7139,
|
|
"mean_token_accuracy": 0.22588173747062684,
|
|
"num_tokens": 13625428.0,
|
|
"step": 5780
|
|
},
|
|
{
|
|
"entropy": 5.311870050430298,
|
|
"epoch": 5.891492613346918,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00024468393696621006,
|
|
"loss": 4.8529,
|
|
"mean_token_accuracy": 0.2098719835281372,
|
|
"num_tokens": 13639180.0,
|
|
"step": 5785
|
|
},
|
|
{
|
|
"entropy": 5.212547540664673,
|
|
"epoch": 5.896586856851758,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00024428647532759177,
|
|
"loss": 4.7201,
|
|
"mean_token_accuracy": 0.22399423271417618,
|
|
"num_tokens": 13651276.0,
|
|
"step": 5790
|
|
},
|
|
{
|
|
"entropy": 5.22181806564331,
|
|
"epoch": 5.901681100356597,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00024388911132666003,
|
|
"loss": 4.6402,
|
|
"mean_token_accuracy": 0.23102436363697051,
|
|
"num_tokens": 13661993.0,
|
|
"step": 5795
|
|
},
|
|
{
|
|
"entropy": 5.2030723094940186,
|
|
"epoch": 5.906775343861437,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0002434918462266273,
|
|
"loss": 4.7017,
|
|
"mean_token_accuracy": 0.23769403845071793,
|
|
"num_tokens": 13671965.0,
|
|
"step": 5800
|
|
},
|
|
{
|
|
"entropy": 5.265958547592163,
|
|
"epoch": 5.911869587366276,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00024309468129039125,
|
|
"loss": 4.8015,
|
|
"mean_token_accuracy": 0.2206607222557068,
|
|
"num_tokens": 13684320.0,
|
|
"step": 5805
|
|
},
|
|
{
|
|
"entropy": 5.256334590911865,
|
|
"epoch": 5.916963830871116,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00024269761778053156,
|
|
"loss": 4.7199,
|
|
"mean_token_accuracy": 0.2260288640856743,
|
|
"num_tokens": 13695414.0,
|
|
"step": 5810
|
|
},
|
|
{
|
|
"entropy": 5.295837879180908,
|
|
"epoch": 5.922058074375955,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.0002423006569593052,
|
|
"loss": 4.7487,
|
|
"mean_token_accuracy": 0.22317033112049103,
|
|
"num_tokens": 13706873.0,
|
|
"step": 5815
|
|
},
|
|
{
|
|
"entropy": 5.306176853179932,
|
|
"epoch": 5.927152317880795,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00024190380008864276,
|
|
"loss": 4.8145,
|
|
"mean_token_accuracy": 0.21714632958173752,
|
|
"num_tokens": 13717324.0,
|
|
"step": 5820
|
|
},
|
|
{
|
|
"entropy": 5.3102906227111815,
|
|
"epoch": 5.932246561385634,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00024150704843014427,
|
|
"loss": 4.7754,
|
|
"mean_token_accuracy": 0.21306584626436234,
|
|
"num_tokens": 13727524.0,
|
|
"step": 5825
|
|
},
|
|
{
|
|
"entropy": 5.355812311172485,
|
|
"epoch": 5.937340804890474,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002411104032450755,
|
|
"loss": 4.8614,
|
|
"mean_token_accuracy": 0.21791372448205948,
|
|
"num_tokens": 13739467.0,
|
|
"step": 5830
|
|
},
|
|
{
|
|
"entropy": 5.336037635803223,
|
|
"epoch": 5.942435048395313,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00024071386579436354,
|
|
"loss": 4.8512,
|
|
"mean_token_accuracy": 0.21377304047346116,
|
|
"num_tokens": 13750449.0,
|
|
"step": 5835
|
|
},
|
|
{
|
|
"entropy": 5.294056987762451,
|
|
"epoch": 5.947529291900153,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00024031743733859325,
|
|
"loss": 4.8289,
|
|
"mean_token_accuracy": 0.2179929420351982,
|
|
"num_tokens": 13762823.0,
|
|
"step": 5840
|
|
},
|
|
{
|
|
"entropy": 5.333105134963989,
|
|
"epoch": 5.952623535404992,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002399211191380027,
|
|
"loss": 4.8443,
|
|
"mean_token_accuracy": 0.21801107227802277,
|
|
"num_tokens": 13775153.0,
|
|
"step": 5845
|
|
},
|
|
{
|
|
"entropy": 5.268996381759644,
|
|
"epoch": 5.9577177789098315,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002395249124524797,
|
|
"loss": 4.7375,
|
|
"mean_token_accuracy": 0.22713783085346223,
|
|
"num_tokens": 13786946.0,
|
|
"step": 5850
|
|
},
|
|
{
|
|
"entropy": 5.360491847991943,
|
|
"epoch": 5.9628120224146715,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023912881854155733,
|
|
"loss": 4.8066,
|
|
"mean_token_accuracy": 0.21541520655155183,
|
|
"num_tokens": 13798136.0,
|
|
"step": 5855
|
|
},
|
|
{
|
|
"entropy": 5.281224727630615,
|
|
"epoch": 5.967906265919511,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00023873283866441048,
|
|
"loss": 4.7428,
|
|
"mean_token_accuracy": 0.22801063060760499,
|
|
"num_tokens": 13809534.0,
|
|
"step": 5860
|
|
},
|
|
{
|
|
"entropy": 5.24911789894104,
|
|
"epoch": 5.973000509424351,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00023833697407985117,
|
|
"loss": 4.7567,
|
|
"mean_token_accuracy": 0.2233858123421669,
|
|
"num_tokens": 13820349.0,
|
|
"step": 5865
|
|
},
|
|
{
|
|
"entropy": 5.314219284057617,
|
|
"epoch": 5.97809475292919,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00023794122604632505,
|
|
"loss": 4.7568,
|
|
"mean_token_accuracy": 0.219663342833519,
|
|
"num_tokens": 13832010.0,
|
|
"step": 5870
|
|
},
|
|
{
|
|
"entropy": 5.3239655017852785,
|
|
"epoch": 5.98318899643403,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00023754559582190744,
|
|
"loss": 4.8375,
|
|
"mean_token_accuracy": 0.22173663824796677,
|
|
"num_tokens": 13844980.0,
|
|
"step": 5875
|
|
},
|
|
{
|
|
"entropy": 5.259063816070556,
|
|
"epoch": 5.988283239938869,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.0002371500846642989,
|
|
"loss": 4.7296,
|
|
"mean_token_accuracy": 0.23068881332874297,
|
|
"num_tokens": 13857213.0,
|
|
"step": 5880
|
|
},
|
|
{
|
|
"entropy": 5.287585735321045,
|
|
"epoch": 5.993377483443709,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00023675469383082148,
|
|
"loss": 4.8397,
|
|
"mean_token_accuracy": 0.21165750324726104,
|
|
"num_tokens": 13869604.0,
|
|
"step": 5885
|
|
},
|
|
{
|
|
"entropy": 5.312543821334839,
|
|
"epoch": 5.998471726948548,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00023635942457841497,
|
|
"loss": 4.7858,
|
|
"mean_token_accuracy": 0.22233413457870482,
|
|
"num_tokens": 13880776.0,
|
|
"step": 5890
|
|
},
|
|
{
|
|
"entropy": 5.352667861514622,
|
|
"epoch": 6.003056546102903,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00023596427816363242,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.22662288281652662,
|
|
"num_tokens": 13890728.0,
|
|
"step": 5895
|
|
},
|
|
{
|
|
"entropy": 5.353891611099243,
|
|
"epoch": 6.008150789607743,
|
|
"grad_norm": 1.0703125,
|
|
"learning_rate": 0.0002355692558426365,
|
|
"loss": 4.6463,
|
|
"mean_token_accuracy": 0.22967582643032075,
|
|
"num_tokens": 13904609.0,
|
|
"step": 5900
|
|
},
|
|
{
|
|
"entropy": 5.2303088188171385,
|
|
"epoch": 6.013245033112582,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.00023517435887119526,
|
|
"loss": 4.5192,
|
|
"mean_token_accuracy": 0.2420562759041786,
|
|
"num_tokens": 13915307.0,
|
|
"step": 5905
|
|
},
|
|
{
|
|
"entropy": 5.312505674362183,
|
|
"epoch": 6.018339276617422,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00023477958850467835,
|
|
"loss": 4.6106,
|
|
"mean_token_accuracy": 0.22558785527944564,
|
|
"num_tokens": 13927108.0,
|
|
"step": 5910
|
|
},
|
|
{
|
|
"entropy": 5.31612458229065,
|
|
"epoch": 6.0234335201222615,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0002343849459980531,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.2379576399922371,
|
|
"num_tokens": 13937873.0,
|
|
"step": 5915
|
|
},
|
|
{
|
|
"entropy": 5.246957302093506,
|
|
"epoch": 6.0285277636271015,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00023399043260588,
|
|
"loss": 4.5541,
|
|
"mean_token_accuracy": 0.2411657303571701,
|
|
"num_tokens": 13948824.0,
|
|
"step": 5920
|
|
},
|
|
{
|
|
"entropy": 5.251957988739013,
|
|
"epoch": 6.033622007131941,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00023359604958230945,
|
|
"loss": 4.5435,
|
|
"mean_token_accuracy": 0.23843134492635726,
|
|
"num_tokens": 13961042.0,
|
|
"step": 5925
|
|
},
|
|
{
|
|
"entropy": 5.291650867462158,
|
|
"epoch": 6.038716250636781,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00023320179818107735,
|
|
"loss": 4.6166,
|
|
"mean_token_accuracy": 0.23145660310983657,
|
|
"num_tokens": 13972365.0,
|
|
"step": 5930
|
|
},
|
|
{
|
|
"entropy": 5.32455096244812,
|
|
"epoch": 6.04381049414162,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00023280767965550087,
|
|
"loss": 4.6244,
|
|
"mean_token_accuracy": 0.23238019794225692,
|
|
"num_tokens": 13984476.0,
|
|
"step": 5935
|
|
},
|
|
{
|
|
"entropy": 5.316651916503906,
|
|
"epoch": 6.04890473764646,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00023241369525847522,
|
|
"loss": 4.5879,
|
|
"mean_token_accuracy": 0.23598203361034392,
|
|
"num_tokens": 13995758.0,
|
|
"step": 5940
|
|
},
|
|
{
|
|
"entropy": 5.179515075683594,
|
|
"epoch": 6.053998981151299,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00023201984624246887,
|
|
"loss": 4.4896,
|
|
"mean_token_accuracy": 0.24375175833702087,
|
|
"num_tokens": 14007648.0,
|
|
"step": 5945
|
|
},
|
|
{
|
|
"entropy": 5.295164489746094,
|
|
"epoch": 6.059093224656139,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00023162613385951998,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.23549052625894545,
|
|
"num_tokens": 14018679.0,
|
|
"step": 5950
|
|
},
|
|
{
|
|
"entropy": 5.2487951755523685,
|
|
"epoch": 6.064187468160978,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00023123255936123254,
|
|
"loss": 4.5491,
|
|
"mean_token_accuracy": 0.2427803635597229,
|
|
"num_tokens": 14030407.0,
|
|
"step": 5955
|
|
},
|
|
{
|
|
"entropy": 5.270629978179931,
|
|
"epoch": 6.069281711665818,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00023083912399877204,
|
|
"loss": 4.5605,
|
|
"mean_token_accuracy": 0.23953815400600434,
|
|
"num_tokens": 14043215.0,
|
|
"step": 5960
|
|
},
|
|
{
|
|
"entropy": 5.229679965972901,
|
|
"epoch": 6.074375955170657,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00023044582902286177,
|
|
"loss": 4.5821,
|
|
"mean_token_accuracy": 0.24248876422643661,
|
|
"num_tokens": 14055601.0,
|
|
"step": 5965
|
|
},
|
|
{
|
|
"entropy": 5.2677459716796875,
|
|
"epoch": 6.079470198675497,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00023005267568377847,
|
|
"loss": 4.5721,
|
|
"mean_token_accuracy": 0.24079903811216355,
|
|
"num_tokens": 14068688.0,
|
|
"step": 5970
|
|
},
|
|
{
|
|
"entropy": 5.187048625946045,
|
|
"epoch": 6.084564442180336,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00022965966523134912,
|
|
"loss": 4.4621,
|
|
"mean_token_accuracy": 0.2494901016354561,
|
|
"num_tokens": 14079757.0,
|
|
"step": 5975
|
|
},
|
|
{
|
|
"entropy": 5.261288070678711,
|
|
"epoch": 6.089658685685175,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.000229266798914946,
|
|
"loss": 4.6658,
|
|
"mean_token_accuracy": 0.22468416541814804,
|
|
"num_tokens": 14093095.0,
|
|
"step": 5980
|
|
},
|
|
{
|
|
"entropy": 5.281835508346558,
|
|
"epoch": 6.094752929190015,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0002288740779834833,
|
|
"loss": 4.5112,
|
|
"mean_token_accuracy": 0.2397424414753914,
|
|
"num_tokens": 14104094.0,
|
|
"step": 5985
|
|
},
|
|
{
|
|
"entropy": 5.319218397140503,
|
|
"epoch": 6.099847172694854,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00022848150368541314,
|
|
"loss": 4.6542,
|
|
"mean_token_accuracy": 0.22848523557186126,
|
|
"num_tokens": 14115172.0,
|
|
"step": 5990
|
|
},
|
|
{
|
|
"entropy": 5.27338809967041,
|
|
"epoch": 6.104941416199694,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0002280890772687214,
|
|
"loss": 4.6736,
|
|
"mean_token_accuracy": 0.2282232016324997,
|
|
"num_tokens": 14128360.0,
|
|
"step": 5995
|
|
},
|
|
{
|
|
"entropy": 5.276223230361938,
|
|
"epoch": 6.1100356597045336,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00022769679998092398,
|
|
"loss": 4.6257,
|
|
"mean_token_accuracy": 0.2378454640507698,
|
|
"num_tokens": 14140567.0,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 6.1100356597045336,
|
|
"eval_entropy": 5.092029078212785,
|
|
"eval_loss": 5.626843452453613,
|
|
"eval_mean_token_accuracy": 0.18404974698284526,
|
|
"eval_num_tokens": 14140567.0,
|
|
"eval_runtime": 2.6212,
|
|
"eval_samples_per_second": 1236.086,
|
|
"eval_steps_per_second": 154.511,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"entropy": 5.25570273399353,
|
|
"epoch": 6.1151299032093736,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00022730467306906248,
|
|
"loss": 4.5341,
|
|
"mean_token_accuracy": 0.24218552112579345,
|
|
"num_tokens": 14151531.0,
|
|
"step": 6005
|
|
},
|
|
{
|
|
"entropy": 5.244127988815308,
|
|
"epoch": 6.120224146714213,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002269126977797007,
|
|
"loss": 4.5832,
|
|
"mean_token_accuracy": 0.2402649015188217,
|
|
"num_tokens": 14164244.0,
|
|
"step": 6010
|
|
},
|
|
{
|
|
"entropy": 5.249430894851685,
|
|
"epoch": 6.125318390219053,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0002265208753589203,
|
|
"loss": 4.5342,
|
|
"mean_token_accuracy": 0.2435235857963562,
|
|
"num_tokens": 14175956.0,
|
|
"step": 6015
|
|
},
|
|
{
|
|
"entropy": 5.267321586608887,
|
|
"epoch": 6.130412633723892,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.00022612920705231699,
|
|
"loss": 4.6379,
|
|
"mean_token_accuracy": 0.23051260858774186,
|
|
"num_tokens": 14187694.0,
|
|
"step": 6020
|
|
},
|
|
{
|
|
"entropy": 5.236322402954102,
|
|
"epoch": 6.135506877228732,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0002257376941049965,
|
|
"loss": 4.582,
|
|
"mean_token_accuracy": 0.23816405534744262,
|
|
"num_tokens": 14200320.0,
|
|
"step": 6025
|
|
},
|
|
{
|
|
"entropy": 5.302865982055664,
|
|
"epoch": 6.140601120733571,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00022534633776157077,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.23589931130409242,
|
|
"num_tokens": 14212937.0,
|
|
"step": 6030
|
|
},
|
|
{
|
|
"entropy": 5.196243238449097,
|
|
"epoch": 6.145695364238411,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002249551392661539,
|
|
"loss": 4.5636,
|
|
"mean_token_accuracy": 0.2395859956741333,
|
|
"num_tokens": 14224366.0,
|
|
"step": 6035
|
|
},
|
|
{
|
|
"entropy": 5.275334072113037,
|
|
"epoch": 6.15078960774325,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.0002245640998623581,
|
|
"loss": 4.6181,
|
|
"mean_token_accuracy": 0.22982030659914016,
|
|
"num_tokens": 14236453.0,
|
|
"step": 6040
|
|
},
|
|
{
|
|
"entropy": 5.387181663513184,
|
|
"epoch": 6.15588385124809,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00022417322079328994,
|
|
"loss": 4.7518,
|
|
"mean_token_accuracy": 0.22657473385334015,
|
|
"num_tokens": 14248401.0,
|
|
"step": 6045
|
|
},
|
|
{
|
|
"entropy": 5.253670358657837,
|
|
"epoch": 6.160978094752929,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00022378250330154614,
|
|
"loss": 4.5758,
|
|
"mean_token_accuracy": 0.23740445524454118,
|
|
"num_tokens": 14260782.0,
|
|
"step": 6050
|
|
},
|
|
{
|
|
"entropy": 5.1595871925354,
|
|
"epoch": 6.166072338257769,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00022339194862921007,
|
|
"loss": 4.5156,
|
|
"mean_token_accuracy": 0.24553609043359756,
|
|
"num_tokens": 14271843.0,
|
|
"step": 6055
|
|
},
|
|
{
|
|
"entropy": 5.393774604797363,
|
|
"epoch": 6.171166581762608,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022300155801784717,
|
|
"loss": 4.6694,
|
|
"mean_token_accuracy": 0.23187096565961837,
|
|
"num_tokens": 14282991.0,
|
|
"step": 6060
|
|
},
|
|
{
|
|
"entropy": 5.364721250534058,
|
|
"epoch": 6.176260825267448,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00022261133270850143,
|
|
"loss": 4.706,
|
|
"mean_token_accuracy": 0.23060808032751084,
|
|
"num_tokens": 14295176.0,
|
|
"step": 6065
|
|
},
|
|
{
|
|
"entropy": 5.21379828453064,
|
|
"epoch": 6.181355068772287,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00022222127394169145,
|
|
"loss": 4.5556,
|
|
"mean_token_accuracy": 0.24118054509162903,
|
|
"num_tokens": 14306140.0,
|
|
"step": 6070
|
|
},
|
|
{
|
|
"entropy": 5.290681791305542,
|
|
"epoch": 6.1864493122771265,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00022183138295740624,
|
|
"loss": 4.624,
|
|
"mean_token_accuracy": 0.23900386691093445,
|
|
"num_tokens": 14317843.0,
|
|
"step": 6075
|
|
},
|
|
{
|
|
"entropy": 5.23520793914795,
|
|
"epoch": 6.1915435557819665,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00022144166099510155,
|
|
"loss": 4.541,
|
|
"mean_token_accuracy": 0.24085042774677276,
|
|
"num_tokens": 14330081.0,
|
|
"step": 6080
|
|
},
|
|
{
|
|
"entropy": 5.225043821334839,
|
|
"epoch": 6.196637799286806,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00022105210929369585,
|
|
"loss": 4.5859,
|
|
"mean_token_accuracy": 0.24171138554811478,
|
|
"num_tokens": 14342544.0,
|
|
"step": 6085
|
|
},
|
|
{
|
|
"entropy": 5.253908395767212,
|
|
"epoch": 6.201732042791646,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0002206627290915662,
|
|
"loss": 4.5976,
|
|
"mean_token_accuracy": 0.2370877206325531,
|
|
"num_tokens": 14354610.0,
|
|
"step": 6090
|
|
},
|
|
{
|
|
"entropy": 5.282559442520141,
|
|
"epoch": 6.206826286296485,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00022027352162654464,
|
|
"loss": 4.6382,
|
|
"mean_token_accuracy": 0.23915766179561615,
|
|
"num_tokens": 14367127.0,
|
|
"step": 6095
|
|
},
|
|
{
|
|
"entropy": 5.318455743789673,
|
|
"epoch": 6.211920529801325,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00021988448813591388,
|
|
"loss": 4.6965,
|
|
"mean_token_accuracy": 0.22747922390699388,
|
|
"num_tokens": 14378754.0,
|
|
"step": 6100
|
|
},
|
|
{
|
|
"entropy": 5.30064435005188,
|
|
"epoch": 6.217014773306164,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00021949562985640377,
|
|
"loss": 4.6055,
|
|
"mean_token_accuracy": 0.2322421982884407,
|
|
"num_tokens": 14391020.0,
|
|
"step": 6105
|
|
},
|
|
{
|
|
"entropy": 5.217644739151001,
|
|
"epoch": 6.222109016811004,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.000219106948024187,
|
|
"loss": 4.5452,
|
|
"mean_token_accuracy": 0.24653885066509246,
|
|
"num_tokens": 14401810.0,
|
|
"step": 6110
|
|
},
|
|
{
|
|
"entropy": 5.306078863143921,
|
|
"epoch": 6.227203260315843,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00021871844387487548,
|
|
"loss": 4.6268,
|
|
"mean_token_accuracy": 0.232207028567791,
|
|
"num_tokens": 14413219.0,
|
|
"step": 6115
|
|
},
|
|
{
|
|
"entropy": 5.268886423110962,
|
|
"epoch": 6.232297503820683,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0002183301186435162,
|
|
"loss": 4.6097,
|
|
"mean_token_accuracy": 0.23455535173416137,
|
|
"num_tokens": 14424473.0,
|
|
"step": 6120
|
|
},
|
|
{
|
|
"entropy": 5.285400104522705,
|
|
"epoch": 6.237391747325522,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00021794197356458733,
|
|
"loss": 4.6271,
|
|
"mean_token_accuracy": 0.23617507070302962,
|
|
"num_tokens": 14435314.0,
|
|
"step": 6125
|
|
},
|
|
{
|
|
"entropy": 5.242933940887451,
|
|
"epoch": 6.242485990830362,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00021755400987199448,
|
|
"loss": 4.5975,
|
|
"mean_token_accuracy": 0.2354305550456047,
|
|
"num_tokens": 14447637.0,
|
|
"step": 6130
|
|
},
|
|
{
|
|
"entropy": 5.2119098663330075,
|
|
"epoch": 6.247580234335201,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0002171662287990665,
|
|
"loss": 4.5317,
|
|
"mean_token_accuracy": 0.24056178331375122,
|
|
"num_tokens": 14458253.0,
|
|
"step": 6135
|
|
},
|
|
{
|
|
"entropy": 5.189319133758545,
|
|
"epoch": 6.252674477840041,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00021677863157855176,
|
|
"loss": 4.6013,
|
|
"mean_token_accuracy": 0.24068537205457688,
|
|
"num_tokens": 14471595.0,
|
|
"step": 6140
|
|
},
|
|
{
|
|
"entropy": 5.218044757843018,
|
|
"epoch": 6.25776872134488,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00021639121944261403,
|
|
"loss": 4.5825,
|
|
"mean_token_accuracy": 0.24002439826726912,
|
|
"num_tokens": 14483909.0,
|
|
"step": 6145
|
|
},
|
|
{
|
|
"entropy": 5.2829793930053714,
|
|
"epoch": 6.26286296484972,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00021600399362282897,
|
|
"loss": 4.5842,
|
|
"mean_token_accuracy": 0.24301208704710006,
|
|
"num_tokens": 14495015.0,
|
|
"step": 6150
|
|
},
|
|
{
|
|
"entropy": 5.235400199890137,
|
|
"epoch": 6.267957208354559,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00021561695535017968,
|
|
"loss": 4.6198,
|
|
"mean_token_accuracy": 0.2266019880771637,
|
|
"num_tokens": 14506637.0,
|
|
"step": 6155
|
|
},
|
|
{
|
|
"entropy": 5.231473541259765,
|
|
"epoch": 6.2730514518593985,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00021523010585505325,
|
|
"loss": 4.6455,
|
|
"mean_token_accuracy": 0.22885604351758956,
|
|
"num_tokens": 14518137.0,
|
|
"step": 6160
|
|
},
|
|
{
|
|
"entropy": 5.281656646728516,
|
|
"epoch": 6.2781456953642385,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00021484344636723646,
|
|
"loss": 4.6291,
|
|
"mean_token_accuracy": 0.2325434312224388,
|
|
"num_tokens": 14530262.0,
|
|
"step": 6165
|
|
},
|
|
{
|
|
"entropy": 5.237823867797852,
|
|
"epoch": 6.283239938869078,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00021445697811591226,
|
|
"loss": 4.5406,
|
|
"mean_token_accuracy": 0.2353981241583824,
|
|
"num_tokens": 14541218.0,
|
|
"step": 6170
|
|
},
|
|
{
|
|
"entropy": 5.202445220947266,
|
|
"epoch": 6.288334182373918,
|
|
"grad_norm": 1.078125,
|
|
"learning_rate": 0.00021407070232965558,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.23879321813583373,
|
|
"num_tokens": 14552766.0,
|
|
"step": 6175
|
|
},
|
|
{
|
|
"entropy": 5.227270650863647,
|
|
"epoch": 6.293428425878757,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00021368462023642953,
|
|
"loss": 4.543,
|
|
"mean_token_accuracy": 0.24090542942285537,
|
|
"num_tokens": 14564320.0,
|
|
"step": 6180
|
|
},
|
|
{
|
|
"entropy": 5.275514698028564,
|
|
"epoch": 6.298522669383597,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00021329873306358117,
|
|
"loss": 4.6163,
|
|
"mean_token_accuracy": 0.23324487805366517,
|
|
"num_tokens": 14577209.0,
|
|
"step": 6185
|
|
},
|
|
{
|
|
"entropy": 5.2151830196380615,
|
|
"epoch": 6.303616912888436,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00021291304203783845,
|
|
"loss": 4.5455,
|
|
"mean_token_accuracy": 0.2393171787261963,
|
|
"num_tokens": 14588541.0,
|
|
"step": 6190
|
|
},
|
|
{
|
|
"entropy": 5.194303703308106,
|
|
"epoch": 6.308711156393276,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00021252754838530535,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.23722363710403443,
|
|
"num_tokens": 14599485.0,
|
|
"step": 6195
|
|
},
|
|
{
|
|
"entropy": 5.307109069824219,
|
|
"epoch": 6.313805399898115,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00021214225333145875,
|
|
"loss": 4.6495,
|
|
"mean_token_accuracy": 0.23045611530542373,
|
|
"num_tokens": 14611153.0,
|
|
"step": 6200
|
|
},
|
|
{
|
|
"entropy": 5.320126581192016,
|
|
"epoch": 6.318899643402955,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00021175715810114378,
|
|
"loss": 4.6613,
|
|
"mean_token_accuracy": 0.23034108728170394,
|
|
"num_tokens": 14623299.0,
|
|
"step": 6205
|
|
},
|
|
{
|
|
"entropy": 5.21284966468811,
|
|
"epoch": 6.323993886907794,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00021137226391857068,
|
|
"loss": 4.6202,
|
|
"mean_token_accuracy": 0.23383547216653824,
|
|
"num_tokens": 14635361.0,
|
|
"step": 6210
|
|
},
|
|
{
|
|
"entropy": 5.24827470779419,
|
|
"epoch": 6.329088130412634,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00021098757200731032,
|
|
"loss": 4.6633,
|
|
"mean_token_accuracy": 0.23175787329673767,
|
|
"num_tokens": 14647902.0,
|
|
"step": 6215
|
|
},
|
|
{
|
|
"entropy": 5.245434904098511,
|
|
"epoch": 6.334182373917473,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0002106030835902909,
|
|
"loss": 4.5776,
|
|
"mean_token_accuracy": 0.23705221116542816,
|
|
"num_tokens": 14658527.0,
|
|
"step": 6220
|
|
},
|
|
{
|
|
"entropy": 5.239424514770508,
|
|
"epoch": 6.339276617422313,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0002102187998897932,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.23461729437112808,
|
|
"num_tokens": 14670892.0,
|
|
"step": 6225
|
|
},
|
|
{
|
|
"entropy": 5.183607959747315,
|
|
"epoch": 6.344370860927152,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.0002098347221274477,
|
|
"loss": 4.6093,
|
|
"mean_token_accuracy": 0.23286683857440948,
|
|
"num_tokens": 14682924.0,
|
|
"step": 6230
|
|
},
|
|
{
|
|
"entropy": 5.256091690063476,
|
|
"epoch": 6.349465104431992,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0002094508515242298,
|
|
"loss": 4.6368,
|
|
"mean_token_accuracy": 0.22894270569086075,
|
|
"num_tokens": 14695518.0,
|
|
"step": 6235
|
|
},
|
|
{
|
|
"entropy": 5.332412004470825,
|
|
"epoch": 6.354559347936831,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00020906718930045675,
|
|
"loss": 4.6799,
|
|
"mean_token_accuracy": 0.2284263327717781,
|
|
"num_tokens": 14707526.0,
|
|
"step": 6240
|
|
},
|
|
{
|
|
"entropy": 5.239914131164551,
|
|
"epoch": 6.3596535914416705,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000208683736675783,
|
|
"loss": 4.5311,
|
|
"mean_token_accuracy": 0.24441600739955902,
|
|
"num_tokens": 14717997.0,
|
|
"step": 6245
|
|
},
|
|
{
|
|
"entropy": 5.2511878490448,
|
|
"epoch": 6.3647478349465105,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00020830049486919694,
|
|
"loss": 4.6726,
|
|
"mean_token_accuracy": 0.2325667068362236,
|
|
"num_tokens": 14729503.0,
|
|
"step": 6250
|
|
},
|
|
{
|
|
"entropy": 5.221254920959472,
|
|
"epoch": 6.36984207845135,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020791746509901665,
|
|
"loss": 4.5817,
|
|
"mean_token_accuracy": 0.23928830474615098,
|
|
"num_tokens": 14740885.0,
|
|
"step": 6255
|
|
},
|
|
{
|
|
"entropy": 5.242957878112793,
|
|
"epoch": 6.37493632195619,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00020753464858288634,
|
|
"loss": 4.6182,
|
|
"mean_token_accuracy": 0.23588707894086838,
|
|
"num_tokens": 14754009.0,
|
|
"step": 6260
|
|
},
|
|
{
|
|
"entropy": 5.32646541595459,
|
|
"epoch": 6.380030565461029,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00020715204653777187,
|
|
"loss": 4.615,
|
|
"mean_token_accuracy": 0.2325052484869957,
|
|
"num_tokens": 14766874.0,
|
|
"step": 6265
|
|
},
|
|
{
|
|
"entropy": 5.223163843154907,
|
|
"epoch": 6.385124808965869,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002067696601799577,
|
|
"loss": 4.5894,
|
|
"mean_token_accuracy": 0.23755850791931152,
|
|
"num_tokens": 14778605.0,
|
|
"step": 6270
|
|
},
|
|
{
|
|
"entropy": 5.29304518699646,
|
|
"epoch": 6.390219052470708,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00020638749072504243,
|
|
"loss": 4.6548,
|
|
"mean_token_accuracy": 0.23851436525583267,
|
|
"num_tokens": 14791283.0,
|
|
"step": 6275
|
|
},
|
|
{
|
|
"entropy": 5.259409809112549,
|
|
"epoch": 6.395313295975548,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00020600553938793527,
|
|
"loss": 4.5906,
|
|
"mean_token_accuracy": 0.23823248893022536,
|
|
"num_tokens": 14802451.0,
|
|
"step": 6280
|
|
},
|
|
{
|
|
"entropy": 5.283213567733765,
|
|
"epoch": 6.400407539480387,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00020562380738285187,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.2333314150571823,
|
|
"num_tokens": 14814378.0,
|
|
"step": 6285
|
|
},
|
|
{
|
|
"entropy": 5.258265829086303,
|
|
"epoch": 6.405501782985227,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0002052422959233108,
|
|
"loss": 4.5598,
|
|
"mean_token_accuracy": 0.240922050178051,
|
|
"num_tokens": 14826040.0,
|
|
"step": 6290
|
|
},
|
|
{
|
|
"entropy": 5.243125104904175,
|
|
"epoch": 6.410596026490066,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.0002048610062221294,
|
|
"loss": 4.584,
|
|
"mean_token_accuracy": 0.2460327833890915,
|
|
"num_tokens": 14838651.0,
|
|
"step": 6295
|
|
},
|
|
{
|
|
"entropy": 5.262886667251587,
|
|
"epoch": 6.415690269994906,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00020447993949142008,
|
|
"loss": 4.608,
|
|
"mean_token_accuracy": 0.2376937061548233,
|
|
"num_tokens": 14850182.0,
|
|
"step": 6300
|
|
},
|
|
{
|
|
"entropy": 5.246709394454956,
|
|
"epoch": 6.420784513499745,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00020409909694258643,
|
|
"loss": 4.5642,
|
|
"mean_token_accuracy": 0.2386277735233307,
|
|
"num_tokens": 14861295.0,
|
|
"step": 6305
|
|
},
|
|
{
|
|
"entropy": 5.162877607345581,
|
|
"epoch": 6.425878757004585,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0002037184797863193,
|
|
"loss": 4.6053,
|
|
"mean_token_accuracy": 0.23553865998983384,
|
|
"num_tokens": 14872746.0,
|
|
"step": 6310
|
|
},
|
|
{
|
|
"entropy": 5.231845188140869,
|
|
"epoch": 6.430973000509424,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00020333808923259317,
|
|
"loss": 4.5864,
|
|
"mean_token_accuracy": 0.23998784869909287,
|
|
"num_tokens": 14884056.0,
|
|
"step": 6315
|
|
},
|
|
{
|
|
"entropy": 5.281853151321411,
|
|
"epoch": 6.436067244014264,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00020295792649066208,
|
|
"loss": 4.5391,
|
|
"mean_token_accuracy": 0.24549755603075027,
|
|
"num_tokens": 14894781.0,
|
|
"step": 6320
|
|
},
|
|
{
|
|
"entropy": 5.271557903289795,
|
|
"epoch": 6.4411614875191034,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0002025779927690558,
|
|
"loss": 4.6475,
|
|
"mean_token_accuracy": 0.22888028919696807,
|
|
"num_tokens": 14907492.0,
|
|
"step": 6325
|
|
},
|
|
{
|
|
"entropy": 5.2121683120727536,
|
|
"epoch": 6.446255731023943,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0002021982892755762,
|
|
"loss": 4.585,
|
|
"mean_token_accuracy": 0.23839462250471116,
|
|
"num_tokens": 14919483.0,
|
|
"step": 6330
|
|
},
|
|
{
|
|
"entropy": 5.178761911392212,
|
|
"epoch": 6.451349974528783,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00020181881721729306,
|
|
"loss": 4.5397,
|
|
"mean_token_accuracy": 0.23821633607149123,
|
|
"num_tokens": 14930932.0,
|
|
"step": 6335
|
|
},
|
|
{
|
|
"entropy": 5.256073236465454,
|
|
"epoch": 6.456444218033622,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00020143957780054063,
|
|
"loss": 4.5991,
|
|
"mean_token_accuracy": 0.23871883749961853,
|
|
"num_tokens": 14942293.0,
|
|
"step": 6340
|
|
},
|
|
{
|
|
"entropy": 5.2402972221374515,
|
|
"epoch": 6.461538461538462,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00020106057223091345,
|
|
"loss": 4.528,
|
|
"mean_token_accuracy": 0.2496757686138153,
|
|
"num_tokens": 14954295.0,
|
|
"step": 6345
|
|
},
|
|
{
|
|
"entropy": 5.227844667434693,
|
|
"epoch": 6.466632705043301,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00020068180171326267,
|
|
"loss": 4.5639,
|
|
"mean_token_accuracy": 0.23756729811429977,
|
|
"num_tokens": 14966209.0,
|
|
"step": 6350
|
|
},
|
|
{
|
|
"entropy": 5.19215874671936,
|
|
"epoch": 6.471726948548141,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00020030326745169237,
|
|
"loss": 4.5638,
|
|
"mean_token_accuracy": 0.24043401926755906,
|
|
"num_tokens": 14977747.0,
|
|
"step": 6355
|
|
},
|
|
{
|
|
"entropy": 5.264079523086548,
|
|
"epoch": 6.47682119205298,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00019992497064955534,
|
|
"loss": 4.5427,
|
|
"mean_token_accuracy": 0.2392398163676262,
|
|
"num_tokens": 14989988.0,
|
|
"step": 6360
|
|
},
|
|
{
|
|
"entropy": 5.283825969696045,
|
|
"epoch": 6.48191543555782,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00019954691250944977,
|
|
"loss": 4.5735,
|
|
"mean_token_accuracy": 0.23902252316474915,
|
|
"num_tokens": 15000093.0,
|
|
"step": 6365
|
|
},
|
|
{
|
|
"entropy": 5.255082988739014,
|
|
"epoch": 6.487009679062659,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00019916909423321494,
|
|
"loss": 4.6614,
|
|
"mean_token_accuracy": 0.22764452993869783,
|
|
"num_tokens": 15011876.0,
|
|
"step": 6370
|
|
},
|
|
{
|
|
"entropy": 5.243281841278076,
|
|
"epoch": 6.492103922567499,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001987915170219277,
|
|
"loss": 4.6338,
|
|
"mean_token_accuracy": 0.2384423866868019,
|
|
"num_tokens": 15023880.0,
|
|
"step": 6375
|
|
},
|
|
{
|
|
"entropy": 5.22277684211731,
|
|
"epoch": 6.497198166072338,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001984141820758985,
|
|
"loss": 4.5364,
|
|
"mean_token_accuracy": 0.24419787526130676,
|
|
"num_tokens": 15036067.0,
|
|
"step": 6380
|
|
},
|
|
{
|
|
"entropy": 5.268504571914673,
|
|
"epoch": 6.502292409577178,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00019803709059466762,
|
|
"loss": 4.5818,
|
|
"mean_token_accuracy": 0.23702444434165953,
|
|
"num_tokens": 15048239.0,
|
|
"step": 6385
|
|
},
|
|
{
|
|
"entropy": 5.243440008163452,
|
|
"epoch": 6.507386653082017,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00019766024377700138,
|
|
"loss": 4.5755,
|
|
"mean_token_accuracy": 0.24318187981843947,
|
|
"num_tokens": 15059610.0,
|
|
"step": 6390
|
|
},
|
|
{
|
|
"entropy": 5.146708393096924,
|
|
"epoch": 6.512480896586856,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001972836428208885,
|
|
"loss": 4.5095,
|
|
"mean_token_accuracy": 0.2499005153775215,
|
|
"num_tokens": 15070475.0,
|
|
"step": 6395
|
|
},
|
|
{
|
|
"entropy": 5.171033430099487,
|
|
"epoch": 6.517575140091696,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00019690728892353578,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.23567583709955214,
|
|
"num_tokens": 15081543.0,
|
|
"step": 6400
|
|
},
|
|
{
|
|
"entropy": 5.270627021789551,
|
|
"epoch": 6.522669383596536,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019653118328136494,
|
|
"loss": 4.6373,
|
|
"mean_token_accuracy": 0.23054626435041428,
|
|
"num_tokens": 15092934.0,
|
|
"step": 6405
|
|
},
|
|
{
|
|
"entropy": 5.246941709518433,
|
|
"epoch": 6.5277636271013755,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00019615532709000829,
|
|
"loss": 4.6009,
|
|
"mean_token_accuracy": 0.23372982293367386,
|
|
"num_tokens": 15105568.0,
|
|
"step": 6410
|
|
},
|
|
{
|
|
"entropy": 5.216909742355346,
|
|
"epoch": 6.532857870606215,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00019577972154430524,
|
|
"loss": 4.5946,
|
|
"mean_token_accuracy": 0.23926339596509932,
|
|
"num_tokens": 15117095.0,
|
|
"step": 6415
|
|
},
|
|
{
|
|
"entropy": 5.255966234207153,
|
|
"epoch": 6.537952114111055,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00019540436783829852,
|
|
"loss": 4.6617,
|
|
"mean_token_accuracy": 0.22325661778450012,
|
|
"num_tokens": 15130113.0,
|
|
"step": 6420
|
|
},
|
|
{
|
|
"entropy": 5.258799886703491,
|
|
"epoch": 6.543046357615894,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00019502926716522985,
|
|
"loss": 4.5819,
|
|
"mean_token_accuracy": 0.23652006536722184,
|
|
"num_tokens": 15142389.0,
|
|
"step": 6425
|
|
},
|
|
{
|
|
"entropy": 5.322343587875366,
|
|
"epoch": 6.548140601120734,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00019465442071753703,
|
|
"loss": 4.67,
|
|
"mean_token_accuracy": 0.22114169001579284,
|
|
"num_tokens": 15153941.0,
|
|
"step": 6430
|
|
},
|
|
{
|
|
"entropy": 5.289221286773682,
|
|
"epoch": 6.553234844625573,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001942798296868495,
|
|
"loss": 4.6187,
|
|
"mean_token_accuracy": 0.23529271632432938,
|
|
"num_tokens": 15164832.0,
|
|
"step": 6435
|
|
},
|
|
{
|
|
"entropy": 5.259476995468139,
|
|
"epoch": 6.558329088130413,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001939054952639846,
|
|
"loss": 4.5706,
|
|
"mean_token_accuracy": 0.23828672766685485,
|
|
"num_tokens": 15176372.0,
|
|
"step": 6440
|
|
},
|
|
{
|
|
"entropy": 5.189549255371094,
|
|
"epoch": 6.563423331635252,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.0001935314186389442,
|
|
"loss": 4.6004,
|
|
"mean_token_accuracy": 0.23784951120615005,
|
|
"num_tokens": 15186694.0,
|
|
"step": 6445
|
|
},
|
|
{
|
|
"entropy": 5.211086797714233,
|
|
"epoch": 6.568517575140092,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00019315760100091034,
|
|
"loss": 4.5939,
|
|
"mean_token_accuracy": 0.24035464376211166,
|
|
"num_tokens": 15198024.0,
|
|
"step": 6450
|
|
},
|
|
{
|
|
"entropy": 5.246069526672363,
|
|
"epoch": 6.573611818644931,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00019278404353824198,
|
|
"loss": 4.6378,
|
|
"mean_token_accuracy": 0.22827987968921662,
|
|
"num_tokens": 15209803.0,
|
|
"step": 6455
|
|
},
|
|
{
|
|
"entropy": 5.254315996170044,
|
|
"epoch": 6.578706062149771,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019241074743847093,
|
|
"loss": 4.5967,
|
|
"mean_token_accuracy": 0.23704150170087815,
|
|
"num_tokens": 15222130.0,
|
|
"step": 6460
|
|
},
|
|
{
|
|
"entropy": 5.272055006027221,
|
|
"epoch": 6.58380030565461,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.000192037713888298,
|
|
"loss": 4.6024,
|
|
"mean_token_accuracy": 0.23968682438135147,
|
|
"num_tokens": 15233682.0,
|
|
"step": 6465
|
|
},
|
|
{
|
|
"entropy": 5.1964684009552,
|
|
"epoch": 6.58889454915945,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00019166494407358949,
|
|
"loss": 4.5657,
|
|
"mean_token_accuracy": 0.23917303532361983,
|
|
"num_tokens": 15246087.0,
|
|
"step": 6470
|
|
},
|
|
{
|
|
"entropy": 5.301876354217529,
|
|
"epoch": 6.593988792664289,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00019129243917937323,
|
|
"loss": 4.6646,
|
|
"mean_token_accuracy": 0.22842931747436523,
|
|
"num_tokens": 15257042.0,
|
|
"step": 6475
|
|
},
|
|
{
|
|
"entropy": 5.318726491928101,
|
|
"epoch": 6.599083036169128,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00019092020038983498,
|
|
"loss": 4.6921,
|
|
"mean_token_accuracy": 0.22854942381381987,
|
|
"num_tokens": 15269720.0,
|
|
"step": 6480
|
|
},
|
|
{
|
|
"entropy": 5.241196584701538,
|
|
"epoch": 6.604177279673968,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001905482288883144,
|
|
"loss": 4.6224,
|
|
"mean_token_accuracy": 0.23202327489852906,
|
|
"num_tokens": 15280915.0,
|
|
"step": 6485
|
|
},
|
|
{
|
|
"entropy": 5.179924011230469,
|
|
"epoch": 6.609271523178808,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00019017652585730154,
|
|
"loss": 4.5194,
|
|
"mean_token_accuracy": 0.24685799330472946,
|
|
"num_tokens": 15291624.0,
|
|
"step": 6490
|
|
},
|
|
{
|
|
"entropy": 5.191037130355835,
|
|
"epoch": 6.6143657666836475,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001898050924784331,
|
|
"loss": 4.5959,
|
|
"mean_token_accuracy": 0.24287493228912355,
|
|
"num_tokens": 15302797.0,
|
|
"step": 6495
|
|
},
|
|
{
|
|
"entropy": 5.2102437019348145,
|
|
"epoch": 6.619460010188487,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001894339299324883,
|
|
"loss": 4.575,
|
|
"mean_token_accuracy": 0.24364232867956162,
|
|
"num_tokens": 15314180.0,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"entropy": 5.242644834518432,
|
|
"epoch": 6.624554253693327,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00018906303939938545,
|
|
"loss": 4.5711,
|
|
"mean_token_accuracy": 0.23621332049369811,
|
|
"num_tokens": 15326130.0,
|
|
"step": 6505
|
|
},
|
|
{
|
|
"entropy": 5.237757349014283,
|
|
"epoch": 6.629648497198166,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00018869242205817843,
|
|
"loss": 4.5732,
|
|
"mean_token_accuracy": 0.23165685534477234,
|
|
"num_tokens": 15337580.0,
|
|
"step": 6510
|
|
},
|
|
{
|
|
"entropy": 5.274597835540772,
|
|
"epoch": 6.634742740703006,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018832207908705225,
|
|
"loss": 4.6139,
|
|
"mean_token_accuracy": 0.2371380254626274,
|
|
"num_tokens": 15348413.0,
|
|
"step": 6515
|
|
},
|
|
{
|
|
"entropy": 5.230300760269165,
|
|
"epoch": 6.639836984207845,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00018795201166331993,
|
|
"loss": 4.581,
|
|
"mean_token_accuracy": 0.23855713605880738,
|
|
"num_tokens": 15362458.0,
|
|
"step": 6520
|
|
},
|
|
{
|
|
"entropy": 5.16133451461792,
|
|
"epoch": 6.644931227712685,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00018758222096341848,
|
|
"loss": 4.5413,
|
|
"mean_token_accuracy": 0.24797563254833221,
|
|
"num_tokens": 15374687.0,
|
|
"step": 6525
|
|
},
|
|
{
|
|
"entropy": 5.20191650390625,
|
|
"epoch": 6.650025471217524,
|
|
"grad_norm": 1.0859375,
|
|
"learning_rate": 0.00018721270816290527,
|
|
"loss": 4.5672,
|
|
"mean_token_accuracy": 0.24225663840770723,
|
|
"num_tokens": 15386352.0,
|
|
"step": 6530
|
|
},
|
|
{
|
|
"entropy": 5.242433977127075,
|
|
"epoch": 6.655119714722364,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 0.0001868434744364541,
|
|
"loss": 4.6843,
|
|
"mean_token_accuracy": 0.23009085208177565,
|
|
"num_tokens": 15400326.0,
|
|
"step": 6535
|
|
},
|
|
{
|
|
"entropy": 5.282994079589844,
|
|
"epoch": 6.660213958227203,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00018647452095785179,
|
|
"loss": 4.6651,
|
|
"mean_token_accuracy": 0.22913432121276855,
|
|
"num_tokens": 15412620.0,
|
|
"step": 6540
|
|
},
|
|
{
|
|
"entropy": 5.166972208023071,
|
|
"epoch": 6.665308201732043,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00018610584889999394,
|
|
"loss": 4.5189,
|
|
"mean_token_accuracy": 0.24773543775081636,
|
|
"num_tokens": 15425608.0,
|
|
"step": 6545
|
|
},
|
|
{
|
|
"entropy": 5.261667108535766,
|
|
"epoch": 6.670402445236882,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00018573745943488185,
|
|
"loss": 4.6183,
|
|
"mean_token_accuracy": 0.23176311552524567,
|
|
"num_tokens": 15437586.0,
|
|
"step": 6550
|
|
},
|
|
{
|
|
"entropy": 5.265309858322143,
|
|
"epoch": 6.675496688741722,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001853693537336183,
|
|
"loss": 4.5606,
|
|
"mean_token_accuracy": 0.23952620774507521,
|
|
"num_tokens": 15448900.0,
|
|
"step": 6555
|
|
},
|
|
{
|
|
"entropy": 5.1848390102386475,
|
|
"epoch": 6.680590932246561,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00018500153296640404,
|
|
"loss": 4.6162,
|
|
"mean_token_accuracy": 0.23551806509494783,
|
|
"num_tokens": 15460658.0,
|
|
"step": 6560
|
|
},
|
|
{
|
|
"entropy": 5.242435026168823,
|
|
"epoch": 6.6856851757514,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00018463399830253397,
|
|
"loss": 4.6578,
|
|
"mean_token_accuracy": 0.23444321006536484,
|
|
"num_tokens": 15471632.0,
|
|
"step": 6565
|
|
},
|
|
{
|
|
"entropy": 5.2090247631072994,
|
|
"epoch": 6.69077941925624,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00018426675091039364,
|
|
"loss": 4.5144,
|
|
"mean_token_accuracy": 0.2452710822224617,
|
|
"num_tokens": 15482955.0,
|
|
"step": 6570
|
|
},
|
|
{
|
|
"entropy": 5.316719961166382,
|
|
"epoch": 6.69587366276108,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00018389979195745497,
|
|
"loss": 4.6898,
|
|
"mean_token_accuracy": 0.23152721226215361,
|
|
"num_tokens": 15495597.0,
|
|
"step": 6575
|
|
},
|
|
{
|
|
"entropy": 5.286507081985474,
|
|
"epoch": 6.7009679062659195,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001835331226102736,
|
|
"loss": 4.548,
|
|
"mean_token_accuracy": 0.24217864573001863,
|
|
"num_tokens": 15506393.0,
|
|
"step": 6580
|
|
},
|
|
{
|
|
"entropy": 5.249615716934204,
|
|
"epoch": 6.706062149770759,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00018316674403448375,
|
|
"loss": 4.5908,
|
|
"mean_token_accuracy": 0.24208148717880248,
|
|
"num_tokens": 15518681.0,
|
|
"step": 6585
|
|
},
|
|
{
|
|
"entropy": 5.367230749130249,
|
|
"epoch": 6.711156393275599,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.0001828006573947958,
|
|
"loss": 4.7702,
|
|
"mean_token_accuracy": 0.21971745789051056,
|
|
"num_tokens": 15531768.0,
|
|
"step": 6590
|
|
},
|
|
{
|
|
"entropy": 5.237047100067139,
|
|
"epoch": 6.716250636780438,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00018243486385499192,
|
|
"loss": 4.5086,
|
|
"mean_token_accuracy": 0.24655313342809676,
|
|
"num_tokens": 15542904.0,
|
|
"step": 6595
|
|
},
|
|
{
|
|
"entropy": 5.199960374832154,
|
|
"epoch": 6.721344880285278,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00018206936457792255,
|
|
"loss": 4.55,
|
|
"mean_token_accuracy": 0.2388886973261833,
|
|
"num_tokens": 15553503.0,
|
|
"step": 6600
|
|
},
|
|
{
|
|
"entropy": 5.2121819972991945,
|
|
"epoch": 6.726439123790117,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001817041607255026,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.24272289574146272,
|
|
"num_tokens": 15565430.0,
|
|
"step": 6605
|
|
},
|
|
{
|
|
"entropy": 5.2486683368682865,
|
|
"epoch": 6.731533367294957,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00018133925345870794,
|
|
"loss": 4.6249,
|
|
"mean_token_accuracy": 0.229489703476429,
|
|
"num_tokens": 15577815.0,
|
|
"step": 6610
|
|
},
|
|
{
|
|
"entropy": 5.300646734237671,
|
|
"epoch": 6.736627610799796,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00018097464393757157,
|
|
"loss": 4.6509,
|
|
"mean_token_accuracy": 0.23556012958288192,
|
|
"num_tokens": 15590529.0,
|
|
"step": 6615
|
|
},
|
|
{
|
|
"entropy": 5.240964269638061,
|
|
"epoch": 6.741721854304636,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00018061033332117987,
|
|
"loss": 4.592,
|
|
"mean_token_accuracy": 0.24048420488834382,
|
|
"num_tokens": 15602929.0,
|
|
"step": 6620
|
|
},
|
|
{
|
|
"entropy": 5.240704202651978,
|
|
"epoch": 6.746816097809475,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00018024632276766905,
|
|
"loss": 4.6234,
|
|
"mean_token_accuracy": 0.23449254631996155,
|
|
"num_tokens": 15615208.0,
|
|
"step": 6625
|
|
},
|
|
{
|
|
"entropy": 5.2331263542175295,
|
|
"epoch": 6.751910341314315,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00017988261343422152,
|
|
"loss": 4.6522,
|
|
"mean_token_accuracy": 0.23167694211006165,
|
|
"num_tokens": 15626247.0,
|
|
"step": 6630
|
|
},
|
|
{
|
|
"entropy": 5.290399885177612,
|
|
"epoch": 6.757004584819154,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00017951920647706204,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.23429806381464005,
|
|
"num_tokens": 15636833.0,
|
|
"step": 6635
|
|
},
|
|
{
|
|
"entropy": 5.18348331451416,
|
|
"epoch": 6.762098828323994,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.000179156103051454,
|
|
"loss": 4.5555,
|
|
"mean_token_accuracy": 0.2400551974773407,
|
|
"num_tokens": 15648565.0,
|
|
"step": 6640
|
|
},
|
|
{
|
|
"entropy": 5.2465414047241214,
|
|
"epoch": 6.767193071828833,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001787933043116962,
|
|
"loss": 4.6781,
|
|
"mean_token_accuracy": 0.23543750047683715,
|
|
"num_tokens": 15660184.0,
|
|
"step": 6645
|
|
},
|
|
{
|
|
"entropy": 5.206048202514649,
|
|
"epoch": 6.7722873153336725,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017843081141111856,
|
|
"loss": 4.5808,
|
|
"mean_token_accuracy": 0.2382212296128273,
|
|
"num_tokens": 15672150.0,
|
|
"step": 6650
|
|
},
|
|
{
|
|
"entropy": 5.167838144302368,
|
|
"epoch": 6.7773815588385125,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00017806862550207887,
|
|
"loss": 4.5539,
|
|
"mean_token_accuracy": 0.24117597192525864,
|
|
"num_tokens": 15683190.0,
|
|
"step": 6655
|
|
},
|
|
{
|
|
"entropy": 5.228303146362305,
|
|
"epoch": 6.7824758023433525,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017770674773595884,
|
|
"loss": 4.5949,
|
|
"mean_token_accuracy": 0.24345898926258086,
|
|
"num_tokens": 15694934.0,
|
|
"step": 6660
|
|
},
|
|
{
|
|
"entropy": 5.296906852722168,
|
|
"epoch": 6.787570045848192,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00017734517926316085,
|
|
"loss": 4.633,
|
|
"mean_token_accuracy": 0.2368286669254303,
|
|
"num_tokens": 15707284.0,
|
|
"step": 6665
|
|
},
|
|
{
|
|
"entropy": 5.277854967117309,
|
|
"epoch": 6.792664289353031,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00017698392123310385,
|
|
"loss": 4.5917,
|
|
"mean_token_accuracy": 0.23780136108398436,
|
|
"num_tokens": 15719411.0,
|
|
"step": 6670
|
|
},
|
|
{
|
|
"entropy": 5.32468090057373,
|
|
"epoch": 6.797758532857871,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001766229747942199,
|
|
"loss": 4.6367,
|
|
"mean_token_accuracy": 0.23655249178409576,
|
|
"num_tokens": 15732482.0,
|
|
"step": 6675
|
|
},
|
|
{
|
|
"entropy": 5.251971292495727,
|
|
"epoch": 6.80285277636271,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00017626234109395072,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.22985827028751374,
|
|
"num_tokens": 15744196.0,
|
|
"step": 6680
|
|
},
|
|
{
|
|
"entropy": 5.349596071243286,
|
|
"epoch": 6.80794701986755,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00017590202127874366,
|
|
"loss": 4.7242,
|
|
"mean_token_accuracy": 0.23124358654022217,
|
|
"num_tokens": 15756020.0,
|
|
"step": 6685
|
|
},
|
|
{
|
|
"entropy": 5.287883710861206,
|
|
"epoch": 6.813041263372389,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00017554201649404828,
|
|
"loss": 4.6592,
|
|
"mean_token_accuracy": 0.22743131667375566,
|
|
"num_tokens": 15767177.0,
|
|
"step": 6690
|
|
},
|
|
{
|
|
"entropy": 5.163661670684815,
|
|
"epoch": 6.818135506877229,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00017518232788431255,
|
|
"loss": 4.5564,
|
|
"mean_token_accuracy": 0.23722367137670516,
|
|
"num_tokens": 15778747.0,
|
|
"step": 6695
|
|
},
|
|
{
|
|
"entropy": 5.242040634155273,
|
|
"epoch": 6.823229750382068,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001748229565929796,
|
|
"loss": 4.5692,
|
|
"mean_token_accuracy": 0.2390548124909401,
|
|
"num_tokens": 15790493.0,
|
|
"step": 6700
|
|
},
|
|
{
|
|
"entropy": 5.209767818450928,
|
|
"epoch": 6.828323993886908,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001744639037624835,
|
|
"loss": 4.5411,
|
|
"mean_token_accuracy": 0.2444687992334366,
|
|
"num_tokens": 15802564.0,
|
|
"step": 6705
|
|
},
|
|
{
|
|
"entropy": 5.2448906898498535,
|
|
"epoch": 6.833418237391747,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00017410517053424623,
|
|
"loss": 4.6078,
|
|
"mean_token_accuracy": 0.22938505858182906,
|
|
"num_tokens": 15814302.0,
|
|
"step": 6710
|
|
},
|
|
{
|
|
"entropy": 5.187287044525147,
|
|
"epoch": 6.838512480896587,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00017374675804867343,
|
|
"loss": 4.5248,
|
|
"mean_token_accuracy": 0.24558065384626387,
|
|
"num_tokens": 15826230.0,
|
|
"step": 6715
|
|
},
|
|
{
|
|
"entropy": 5.3390905380249025,
|
|
"epoch": 6.843606724401426,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017338866744515146,
|
|
"loss": 4.7049,
|
|
"mean_token_accuracy": 0.22077261060476303,
|
|
"num_tokens": 15837852.0,
|
|
"step": 6720
|
|
},
|
|
{
|
|
"entropy": 5.243156003952026,
|
|
"epoch": 6.848700967906266,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00017303089986204324,
|
|
"loss": 4.5931,
|
|
"mean_token_accuracy": 0.2343250796198845,
|
|
"num_tokens": 15849570.0,
|
|
"step": 6725
|
|
},
|
|
{
|
|
"entropy": 5.246264028549194,
|
|
"epoch": 6.853795211411105,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00017267345643668479,
|
|
"loss": 4.6176,
|
|
"mean_token_accuracy": 0.2418099582195282,
|
|
"num_tokens": 15861120.0,
|
|
"step": 6730
|
|
},
|
|
{
|
|
"entropy": 5.251173400878907,
|
|
"epoch": 6.8588894549159445,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00017231633830538156,
|
|
"loss": 4.6303,
|
|
"mean_token_accuracy": 0.23349590897560119,
|
|
"num_tokens": 15872848.0,
|
|
"step": 6735
|
|
},
|
|
{
|
|
"entropy": 5.305468797683716,
|
|
"epoch": 6.8639836984207845,
|
|
"grad_norm": 1.09375,
|
|
"learning_rate": 0.00017195954660340534,
|
|
"loss": 4.6611,
|
|
"mean_token_accuracy": 0.23480531573295593,
|
|
"num_tokens": 15885264.0,
|
|
"step": 6740
|
|
},
|
|
{
|
|
"entropy": 5.329664421081543,
|
|
"epoch": 6.8690779419256245,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00017160308246498963,
|
|
"loss": 4.6479,
|
|
"mean_token_accuracy": 0.23084095865488052,
|
|
"num_tokens": 15898164.0,
|
|
"step": 6745
|
|
},
|
|
{
|
|
"entropy": 5.261679983139038,
|
|
"epoch": 6.874172185430464,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00017124694702332687,
|
|
"loss": 4.6131,
|
|
"mean_token_accuracy": 0.23567635118961333,
|
|
"num_tokens": 15909894.0,
|
|
"step": 6750
|
|
},
|
|
{
|
|
"entropy": 5.254143857955933,
|
|
"epoch": 6.879266428935303,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00017089114141056457,
|
|
"loss": 4.6394,
|
|
"mean_token_accuracy": 0.2319847136735916,
|
|
"num_tokens": 15922678.0,
|
|
"step": 6755
|
|
},
|
|
{
|
|
"entropy": 5.299294281005859,
|
|
"epoch": 6.884360672440143,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00017053566675780186,
|
|
"loss": 4.5945,
|
|
"mean_token_accuracy": 0.2379731848835945,
|
|
"num_tokens": 15933120.0,
|
|
"step": 6760
|
|
},
|
|
{
|
|
"entropy": 5.2746161937713625,
|
|
"epoch": 6.889454915944982,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00017018052419508556,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.23720818758010864,
|
|
"num_tokens": 15944480.0,
|
|
"step": 6765
|
|
},
|
|
{
|
|
"entropy": 5.315499925613404,
|
|
"epoch": 6.894549159449822,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001698257148514068,
|
|
"loss": 4.6073,
|
|
"mean_token_accuracy": 0.23078937083482742,
|
|
"num_tokens": 15956092.0,
|
|
"step": 6770
|
|
},
|
|
{
|
|
"entropy": 5.227525520324707,
|
|
"epoch": 6.899643402954661,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016947123985469736,
|
|
"loss": 4.5214,
|
|
"mean_token_accuracy": 0.24081469774246217,
|
|
"num_tokens": 15966684.0,
|
|
"step": 6775
|
|
},
|
|
{
|
|
"entropy": 5.202942323684693,
|
|
"epoch": 6.904737646459501,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.0001691171003318266,
|
|
"loss": 4.5969,
|
|
"mean_token_accuracy": 0.24045392870903015,
|
|
"num_tokens": 15978953.0,
|
|
"step": 6780
|
|
},
|
|
{
|
|
"entropy": 5.164789390563965,
|
|
"epoch": 6.90983188996434,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016876329740859666,
|
|
"loss": 4.5935,
|
|
"mean_token_accuracy": 0.24412939846515655,
|
|
"num_tokens": 15990559.0,
|
|
"step": 6785
|
|
},
|
|
{
|
|
"entropy": 5.2247035026550295,
|
|
"epoch": 6.91492613346918,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001684098322097402,
|
|
"loss": 4.6184,
|
|
"mean_token_accuracy": 0.23472400456666948,
|
|
"num_tokens": 16002932.0,
|
|
"step": 6790
|
|
},
|
|
{
|
|
"entropy": 5.312981367111206,
|
|
"epoch": 6.920020376974019,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00016805670585891597,
|
|
"loss": 4.6625,
|
|
"mean_token_accuracy": 0.23044908940792083,
|
|
"num_tokens": 16013764.0,
|
|
"step": 6795
|
|
},
|
|
{
|
|
"entropy": 5.272630596160889,
|
|
"epoch": 6.925114620478859,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00016770391947870577,
|
|
"loss": 4.559,
|
|
"mean_token_accuracy": 0.2423972576856613,
|
|
"num_tokens": 16025207.0,
|
|
"step": 6800
|
|
},
|
|
{
|
|
"entropy": 5.22313232421875,
|
|
"epoch": 6.930208863983698,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00016735147419061054,
|
|
"loss": 4.5614,
|
|
"mean_token_accuracy": 0.23583130687475204,
|
|
"num_tokens": 16036181.0,
|
|
"step": 6805
|
|
},
|
|
{
|
|
"entropy": 5.237149238586426,
|
|
"epoch": 6.935303107488538,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016699937111504682,
|
|
"loss": 4.5752,
|
|
"mean_token_accuracy": 0.23812053650617598,
|
|
"num_tokens": 16048458.0,
|
|
"step": 6810
|
|
},
|
|
{
|
|
"entropy": 5.248747968673706,
|
|
"epoch": 6.940397350993377,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00016664761137134316,
|
|
"loss": 4.5251,
|
|
"mean_token_accuracy": 0.24226316958665847,
|
|
"num_tokens": 16059664.0,
|
|
"step": 6815
|
|
},
|
|
{
|
|
"entropy": 5.291439580917358,
|
|
"epoch": 6.945491594498217,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00016629619607773716,
|
|
"loss": 4.6597,
|
|
"mean_token_accuracy": 0.2339625760912895,
|
|
"num_tokens": 16070273.0,
|
|
"step": 6820
|
|
},
|
|
{
|
|
"entropy": 5.293359804153442,
|
|
"epoch": 6.9505858380030565,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00016594512635137082,
|
|
"loss": 4.6112,
|
|
"mean_token_accuracy": 0.23434137403964997,
|
|
"num_tokens": 16083222.0,
|
|
"step": 6825
|
|
},
|
|
{
|
|
"entropy": 5.233603382110596,
|
|
"epoch": 6.9556800815078965,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00016559440330828775,
|
|
"loss": 4.6093,
|
|
"mean_token_accuracy": 0.23881654888391496,
|
|
"num_tokens": 16094876.0,
|
|
"step": 6830
|
|
},
|
|
{
|
|
"entropy": 5.24044828414917,
|
|
"epoch": 6.960774325012736,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00016524402806342985,
|
|
"loss": 4.6172,
|
|
"mean_token_accuracy": 0.23820284903049468,
|
|
"num_tokens": 16106959.0,
|
|
"step": 6835
|
|
},
|
|
{
|
|
"entropy": 5.262356328964233,
|
|
"epoch": 6.965868568517575,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00016489400173063295,
|
|
"loss": 4.6819,
|
|
"mean_token_accuracy": 0.2297210142016411,
|
|
"num_tokens": 16118959.0,
|
|
"step": 6840
|
|
},
|
|
{
|
|
"entropy": 5.292751502990723,
|
|
"epoch": 6.970962812022415,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00016454432542262383,
|
|
"loss": 4.5896,
|
|
"mean_token_accuracy": 0.23582089096307754,
|
|
"num_tokens": 16130970.0,
|
|
"step": 6845
|
|
},
|
|
{
|
|
"entropy": 5.184649896621704,
|
|
"epoch": 6.976057055527254,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00016419500025101653,
|
|
"loss": 4.5533,
|
|
"mean_token_accuracy": 0.24161106199026108,
|
|
"num_tokens": 16142676.0,
|
|
"step": 6850
|
|
},
|
|
{
|
|
"entropy": 5.238132095336914,
|
|
"epoch": 6.981151299032094,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 0.00016384602732630877,
|
|
"loss": 4.6325,
|
|
"mean_token_accuracy": 0.23505216240882873,
|
|
"num_tokens": 16155916.0,
|
|
"step": 6855
|
|
},
|
|
{
|
|
"entropy": 5.296580457687378,
|
|
"epoch": 6.986245542536933,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.0001634974077578788,
|
|
"loss": 4.6322,
|
|
"mean_token_accuracy": 0.23093676418066025,
|
|
"num_tokens": 16166573.0,
|
|
"step": 6860
|
|
},
|
|
{
|
|
"entropy": 5.322878456115722,
|
|
"epoch": 6.991339786041773,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016314914265398115,
|
|
"loss": 4.6624,
|
|
"mean_token_accuracy": 0.23015258610248565,
|
|
"num_tokens": 16178264.0,
|
|
"step": 6865
|
|
},
|
|
{
|
|
"entropy": 5.27853798866272,
|
|
"epoch": 6.996434029546612,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00016280123312174363,
|
|
"loss": 4.6447,
|
|
"mean_token_accuracy": 0.23749837130308152,
|
|
"num_tokens": 16189481.0,
|
|
"step": 6870
|
|
},
|
|
{
|
|
"entropy": 5.234822114308675,
|
|
"epoch": 7.0010188487009675,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016245368026716393,
|
|
"loss": 4.6655,
|
|
"mean_token_accuracy": 0.22865616116258833,
|
|
"num_tokens": 16200809.0,
|
|
"step": 6875
|
|
},
|
|
{
|
|
"entropy": 5.214908313751221,
|
|
"epoch": 7.0061130922058075,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00016210648519510563,
|
|
"loss": 4.3719,
|
|
"mean_token_accuracy": 0.25332349836826323,
|
|
"num_tokens": 16212394.0,
|
|
"step": 6880
|
|
},
|
|
{
|
|
"entropy": 5.230849313735962,
|
|
"epoch": 7.011207335710647,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 0.0001617596490092949,
|
|
"loss": 4.3399,
|
|
"mean_token_accuracy": 0.25948885828256607,
|
|
"num_tokens": 16222533.0,
|
|
"step": 6885
|
|
},
|
|
{
|
|
"entropy": 5.192682981491089,
|
|
"epoch": 7.016301579215487,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00016141317281231723,
|
|
"loss": 4.4196,
|
|
"mean_token_accuracy": 0.2567686215043068,
|
|
"num_tokens": 16233554.0,
|
|
"step": 6890
|
|
},
|
|
{
|
|
"entropy": 5.210714101791382,
|
|
"epoch": 7.021395822720326,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001610670577056134,
|
|
"loss": 4.4593,
|
|
"mean_token_accuracy": 0.24862244725227356,
|
|
"num_tokens": 16245032.0,
|
|
"step": 6895
|
|
},
|
|
{
|
|
"entropy": 5.157873916625976,
|
|
"epoch": 7.026490066225166,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00016072130478947684,
|
|
"loss": 4.3199,
|
|
"mean_token_accuracy": 0.2705102935433388,
|
|
"num_tokens": 16255924.0,
|
|
"step": 6900
|
|
},
|
|
{
|
|
"entropy": 5.261100769042969,
|
|
"epoch": 7.031584309730005,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016037591516304884,
|
|
"loss": 4.518,
|
|
"mean_token_accuracy": 0.2452048733830452,
|
|
"num_tokens": 16267377.0,
|
|
"step": 6905
|
|
},
|
|
{
|
|
"entropy": 5.210540866851806,
|
|
"epoch": 7.036678553234845,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00016003088992431628,
|
|
"loss": 4.4193,
|
|
"mean_token_accuracy": 0.25431921780109407,
|
|
"num_tokens": 16279157.0,
|
|
"step": 6910
|
|
},
|
|
{
|
|
"entropy": 5.267416620254517,
|
|
"epoch": 7.041772796739684,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001596862301701077,
|
|
"loss": 4.53,
|
|
"mean_token_accuracy": 0.24249509274959563,
|
|
"num_tokens": 16291567.0,
|
|
"step": 6915
|
|
},
|
|
{
|
|
"entropy": 5.298155975341797,
|
|
"epoch": 7.046867040244524,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00015934193699608951,
|
|
"loss": 4.5047,
|
|
"mean_token_accuracy": 0.2420162633061409,
|
|
"num_tokens": 16302086.0,
|
|
"step": 6920
|
|
},
|
|
{
|
|
"entropy": 5.228708124160766,
|
|
"epoch": 7.051961283749363,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00015899801149676294,
|
|
"loss": 4.4271,
|
|
"mean_token_accuracy": 0.2572023689746857,
|
|
"num_tokens": 16312790.0,
|
|
"step": 6925
|
|
},
|
|
{
|
|
"entropy": 5.239817714691162,
|
|
"epoch": 7.057055527254203,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00015865445476546025,
|
|
"loss": 4.4596,
|
|
"mean_token_accuracy": 0.25067670047283175,
|
|
"num_tokens": 16323600.0,
|
|
"step": 6930
|
|
},
|
|
{
|
|
"entropy": 5.323778915405273,
|
|
"epoch": 7.062149770759042,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00015831126789434165,
|
|
"loss": 4.5589,
|
|
"mean_token_accuracy": 0.23931304216384888,
|
|
"num_tokens": 16335683.0,
|
|
"step": 6935
|
|
},
|
|
{
|
|
"entropy": 5.221188545227051,
|
|
"epoch": 7.067244014263882,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015796845197439137,
|
|
"loss": 4.4772,
|
|
"mean_token_accuracy": 0.2533941611647606,
|
|
"num_tokens": 16347416.0,
|
|
"step": 6940
|
|
},
|
|
{
|
|
"entropy": 5.236729907989502,
|
|
"epoch": 7.072338257768721,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00015762600809541432,
|
|
"loss": 4.4623,
|
|
"mean_token_accuracy": 0.2505215957760811,
|
|
"num_tokens": 16358999.0,
|
|
"step": 6945
|
|
},
|
|
{
|
|
"entropy": 5.243441820144653,
|
|
"epoch": 7.077432501273561,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001572839373460328,
|
|
"loss": 4.4321,
|
|
"mean_token_accuracy": 0.2532246530056,
|
|
"num_tokens": 16369558.0,
|
|
"step": 6950
|
|
},
|
|
{
|
|
"entropy": 5.2662557601928714,
|
|
"epoch": 7.0825267447784,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 0.00015694224081368307,
|
|
"loss": 4.4548,
|
|
"mean_token_accuracy": 0.24727822095155716,
|
|
"num_tokens": 16380911.0,
|
|
"step": 6955
|
|
},
|
|
{
|
|
"entropy": 5.191625785827637,
|
|
"epoch": 7.0876209882832395,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001566009195846116,
|
|
"loss": 4.4012,
|
|
"mean_token_accuracy": 0.2625259757041931,
|
|
"num_tokens": 16393160.0,
|
|
"step": 6960
|
|
},
|
|
{
|
|
"entropy": 5.206611204147339,
|
|
"epoch": 7.0927152317880795,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015625997474387178,
|
|
"loss": 4.3774,
|
|
"mean_token_accuracy": 0.2555388256907463,
|
|
"num_tokens": 16403632.0,
|
|
"step": 6965
|
|
},
|
|
{
|
|
"entropy": 5.167124319076538,
|
|
"epoch": 7.097809475292919,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00015591940737532046,
|
|
"loss": 4.3952,
|
|
"mean_token_accuracy": 0.25555350035429003,
|
|
"num_tokens": 16415970.0,
|
|
"step": 6970
|
|
},
|
|
{
|
|
"entropy": 5.183048248291016,
|
|
"epoch": 7.102903718797759,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00015557921856161467,
|
|
"loss": 4.5128,
|
|
"mean_token_accuracy": 0.24808067679405213,
|
|
"num_tokens": 16428056.0,
|
|
"step": 6975
|
|
},
|
|
{
|
|
"entropy": 5.196497058868408,
|
|
"epoch": 7.107997962302598,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015523940938420795,
|
|
"loss": 4.4053,
|
|
"mean_token_accuracy": 0.25447417199611666,
|
|
"num_tokens": 16438770.0,
|
|
"step": 6980
|
|
},
|
|
{
|
|
"entropy": 5.261960029602051,
|
|
"epoch": 7.113092205807438,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.00015489998092334684,
|
|
"loss": 4.4598,
|
|
"mean_token_accuracy": 0.25061320066452025,
|
|
"num_tokens": 16449319.0,
|
|
"step": 6985
|
|
},
|
|
{
|
|
"entropy": 5.227363395690918,
|
|
"epoch": 7.118186449312277,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001545609342580676,
|
|
"loss": 4.5003,
|
|
"mean_token_accuracy": 0.24593233168125153,
|
|
"num_tokens": 16462282.0,
|
|
"step": 6990
|
|
},
|
|
{
|
|
"entropy": 5.17362380027771,
|
|
"epoch": 7.123280692817117,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00015422227046619304,
|
|
"loss": 4.4459,
|
|
"mean_token_accuracy": 0.2537954658269882,
|
|
"num_tokens": 16475803.0,
|
|
"step": 6995
|
|
},
|
|
{
|
|
"entropy": 5.204595470428467,
|
|
"epoch": 7.128374936321956,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00015388399062432856,
|
|
"loss": 4.4264,
|
|
"mean_token_accuracy": 0.25351720601320266,
|
|
"num_tokens": 16487683.0,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 7.128374936321956,
|
|
"eval_entropy": 5.108521198932036,
|
|
"eval_loss": 5.6067891120910645,
|
|
"eval_mean_token_accuracy": 0.1859386075793961,
|
|
"eval_num_tokens": 16487683.0,
|
|
"eval_runtime": 2.812,
|
|
"eval_samples_per_second": 1152.224,
|
|
"eval_steps_per_second": 144.028,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"entropy": 5.311827945709228,
|
|
"epoch": 7.133469179826796,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00015354609580785916,
|
|
"loss": 4.482,
|
|
"mean_token_accuracy": 0.24705770164728164,
|
|
"num_tokens": 16499699.0,
|
|
"step": 7005
|
|
},
|
|
{
|
|
"entropy": 5.237821435928344,
|
|
"epoch": 7.138563423331635,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00015320858709094563,
|
|
"loss": 4.496,
|
|
"mean_token_accuracy": 0.24689701050519944,
|
|
"num_tokens": 16511861.0,
|
|
"step": 7010
|
|
},
|
|
{
|
|
"entropy": 5.174914121627808,
|
|
"epoch": 7.143657666836475,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00015287146554652164,
|
|
"loss": 4.4809,
|
|
"mean_token_accuracy": 0.2445608675479889,
|
|
"num_tokens": 16524869.0,
|
|
"step": 7015
|
|
},
|
|
{
|
|
"entropy": 5.219668912887573,
|
|
"epoch": 7.148751910341314,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.0001525347322462899,
|
|
"loss": 4.4781,
|
|
"mean_token_accuracy": 0.24345687329769133,
|
|
"num_tokens": 16537530.0,
|
|
"step": 7020
|
|
},
|
|
{
|
|
"entropy": 5.263413953781128,
|
|
"epoch": 7.153846153846154,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00015219838826071872,
|
|
"loss": 4.5437,
|
|
"mean_token_accuracy": 0.24499007165431977,
|
|
"num_tokens": 16549097.0,
|
|
"step": 7025
|
|
},
|
|
{
|
|
"entropy": 5.319189929962159,
|
|
"epoch": 7.158940397350993,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015186243465903918,
|
|
"loss": 4.5873,
|
|
"mean_token_accuracy": 0.23882181197404861,
|
|
"num_tokens": 16561526.0,
|
|
"step": 7030
|
|
},
|
|
{
|
|
"entropy": 5.206654405593872,
|
|
"epoch": 7.164034640855833,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.000151526872509241,
|
|
"loss": 4.4568,
|
|
"mean_token_accuracy": 0.25476928651332853,
|
|
"num_tokens": 16573131.0,
|
|
"step": 7035
|
|
},
|
|
{
|
|
"entropy": 5.289799404144287,
|
|
"epoch": 7.169128884360672,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00015119170287806967,
|
|
"loss": 4.5981,
|
|
"mean_token_accuracy": 0.23796476423740387,
|
|
"num_tokens": 16585353.0,
|
|
"step": 7040
|
|
},
|
|
{
|
|
"entropy": 5.18173885345459,
|
|
"epoch": 7.1742231278655115,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00015085692683102276,
|
|
"loss": 4.4519,
|
|
"mean_token_accuracy": 0.2498021513223648,
|
|
"num_tokens": 16598270.0,
|
|
"step": 7045
|
|
},
|
|
{
|
|
"entropy": 5.23644642829895,
|
|
"epoch": 7.1793173713703515,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015052254543234666,
|
|
"loss": 4.5147,
|
|
"mean_token_accuracy": 0.2571840450167656,
|
|
"num_tokens": 16610125.0,
|
|
"step": 7050
|
|
},
|
|
{
|
|
"entropy": 5.253902769088745,
|
|
"epoch": 7.184411614875191,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00015018855974503338,
|
|
"loss": 4.525,
|
|
"mean_token_accuracy": 0.24417686760425567,
|
|
"num_tokens": 16622087.0,
|
|
"step": 7055
|
|
},
|
|
{
|
|
"entropy": 5.210110759735107,
|
|
"epoch": 7.189505858380031,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00014985497083081672,
|
|
"loss": 4.4485,
|
|
"mean_token_accuracy": 0.2557422578334808,
|
|
"num_tokens": 16633582.0,
|
|
"step": 7060
|
|
},
|
|
{
|
|
"entropy": 5.27029185295105,
|
|
"epoch": 7.19460010188487,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.0001495217797501691,
|
|
"loss": 4.5446,
|
|
"mean_token_accuracy": 0.24474254101514817,
|
|
"num_tokens": 16644919.0,
|
|
"step": 7065
|
|
},
|
|
{
|
|
"entropy": 5.268561315536499,
|
|
"epoch": 7.19969434538971,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00014918898756229853,
|
|
"loss": 4.5728,
|
|
"mean_token_accuracy": 0.23650306463241577,
|
|
"num_tokens": 16658731.0,
|
|
"step": 7070
|
|
},
|
|
{
|
|
"entropy": 5.225019550323486,
|
|
"epoch": 7.204788588894549,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00014885659532514473,
|
|
"loss": 4.465,
|
|
"mean_token_accuracy": 0.24969328045845032,
|
|
"num_tokens": 16670593.0,
|
|
"step": 7075
|
|
},
|
|
{
|
|
"entropy": 5.2282483100891115,
|
|
"epoch": 7.209882832399389,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00014852460409537605,
|
|
"loss": 4.4482,
|
|
"mean_token_accuracy": 0.25090937316417694,
|
|
"num_tokens": 16682818.0,
|
|
"step": 7080
|
|
},
|
|
{
|
|
"entropy": 5.226267910003662,
|
|
"epoch": 7.214977075904228,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014819301492838594,
|
|
"loss": 4.4947,
|
|
"mean_token_accuracy": 0.23780039995908736,
|
|
"num_tokens": 16694587.0,
|
|
"step": 7085
|
|
},
|
|
{
|
|
"entropy": 5.217632150650024,
|
|
"epoch": 7.220071319409068,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 0.00014786182887828998,
|
|
"loss": 4.5004,
|
|
"mean_token_accuracy": 0.2483433797955513,
|
|
"num_tokens": 16705031.0,
|
|
"step": 7090
|
|
},
|
|
{
|
|
"entropy": 5.191191291809082,
|
|
"epoch": 7.225165562913907,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00014753104699792192,
|
|
"loss": 4.4226,
|
|
"mean_token_accuracy": 0.25648751854896545,
|
|
"num_tokens": 16716377.0,
|
|
"step": 7095
|
|
},
|
|
{
|
|
"entropy": 5.244422769546508,
|
|
"epoch": 7.230259806418747,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.0001472006703388309,
|
|
"loss": 4.4888,
|
|
"mean_token_accuracy": 0.24385376125574112,
|
|
"num_tokens": 16728739.0,
|
|
"step": 7100
|
|
},
|
|
{
|
|
"entropy": 5.241468524932861,
|
|
"epoch": 7.235354049923586,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001468706999512776,
|
|
"loss": 4.4547,
|
|
"mean_token_accuracy": 0.2539277091622353,
|
|
"num_tokens": 16740207.0,
|
|
"step": 7105
|
|
},
|
|
{
|
|
"entropy": 5.259920597076416,
|
|
"epoch": 7.240448293428426,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00014654113688423158,
|
|
"loss": 4.5159,
|
|
"mean_token_accuracy": 0.2447134807705879,
|
|
"num_tokens": 16753433.0,
|
|
"step": 7110
|
|
},
|
|
{
|
|
"entropy": 5.245884370803833,
|
|
"epoch": 7.245542536933265,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014621198218536718,
|
|
"loss": 4.4958,
|
|
"mean_token_accuracy": 0.25203664153814315,
|
|
"num_tokens": 16765532.0,
|
|
"step": 7115
|
|
},
|
|
{
|
|
"entropy": 5.235752964019776,
|
|
"epoch": 7.250636780438105,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00014588323690106064,
|
|
"loss": 4.4769,
|
|
"mean_token_accuracy": 0.24856966435909272,
|
|
"num_tokens": 16776793.0,
|
|
"step": 7120
|
|
},
|
|
{
|
|
"entropy": 5.150251579284668,
|
|
"epoch": 7.2557310239429444,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00014555490207638673,
|
|
"loss": 4.3804,
|
|
"mean_token_accuracy": 0.26017558574676514,
|
|
"num_tokens": 16787538.0,
|
|
"step": 7125
|
|
},
|
|
{
|
|
"entropy": 5.215769720077515,
|
|
"epoch": 7.260825267447784,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014522697875511543,
|
|
"loss": 4.5154,
|
|
"mean_token_accuracy": 0.24551741480827333,
|
|
"num_tokens": 16799684.0,
|
|
"step": 7130
|
|
},
|
|
{
|
|
"entropy": 5.236591482162476,
|
|
"epoch": 7.265919510952624,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00014489946797970838,
|
|
"loss": 4.4556,
|
|
"mean_token_accuracy": 0.24887409806251526,
|
|
"num_tokens": 16811437.0,
|
|
"step": 7135
|
|
},
|
|
{
|
|
"entropy": 5.244764280319214,
|
|
"epoch": 7.271013754457463,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.000144572370791316,
|
|
"loss": 4.5178,
|
|
"mean_token_accuracy": 0.24648959189653397,
|
|
"num_tokens": 16824174.0,
|
|
"step": 7140
|
|
},
|
|
{
|
|
"entropy": 5.211141681671142,
|
|
"epoch": 7.276107997962303,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00014424568822977356,
|
|
"loss": 4.4073,
|
|
"mean_token_accuracy": 0.25169835090637205,
|
|
"num_tokens": 16835949.0,
|
|
"step": 7145
|
|
},
|
|
{
|
|
"entropy": 5.195258569717407,
|
|
"epoch": 7.281202241467142,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001439194213335986,
|
|
"loss": 4.4517,
|
|
"mean_token_accuracy": 0.2523092418909073,
|
|
"num_tokens": 16848017.0,
|
|
"step": 7150
|
|
},
|
|
{
|
|
"entropy": 5.240725088119507,
|
|
"epoch": 7.286296484971982,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00014359357113998705,
|
|
"loss": 4.5287,
|
|
"mean_token_accuracy": 0.2442638710141182,
|
|
"num_tokens": 16860998.0,
|
|
"step": 7155
|
|
},
|
|
{
|
|
"entropy": 5.252740859985352,
|
|
"epoch": 7.291390728476821,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00014326813868481032,
|
|
"loss": 4.4924,
|
|
"mean_token_accuracy": 0.24489855617284775,
|
|
"num_tokens": 16870726.0,
|
|
"step": 7160
|
|
},
|
|
{
|
|
"entropy": 5.201711130142212,
|
|
"epoch": 7.296484971981661,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.0001429431250026116,
|
|
"loss": 4.3793,
|
|
"mean_token_accuracy": 0.26116151064634324,
|
|
"num_tokens": 16881082.0,
|
|
"step": 7165
|
|
},
|
|
{
|
|
"entropy": 5.166771793365479,
|
|
"epoch": 7.3015792154865,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00014261853112660302,
|
|
"loss": 4.367,
|
|
"mean_token_accuracy": 0.264911749958992,
|
|
"num_tokens": 16893406.0,
|
|
"step": 7170
|
|
},
|
|
{
|
|
"entropy": 5.138424491882324,
|
|
"epoch": 7.30667345899134,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00014229435808866213,
|
|
"loss": 4.3635,
|
|
"mean_token_accuracy": 0.26347038298845293,
|
|
"num_tokens": 16904916.0,
|
|
"step": 7175
|
|
},
|
|
{
|
|
"entropy": 5.2029694557189945,
|
|
"epoch": 7.311767702496179,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00014197060691932857,
|
|
"loss": 4.4908,
|
|
"mean_token_accuracy": 0.2415615886449814,
|
|
"num_tokens": 16916155.0,
|
|
"step": 7180
|
|
},
|
|
{
|
|
"entropy": 5.219705724716187,
|
|
"epoch": 7.316861946001019,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001416472786478009,
|
|
"loss": 4.4811,
|
|
"mean_token_accuracy": 0.2451704263687134,
|
|
"num_tokens": 16929415.0,
|
|
"step": 7185
|
|
},
|
|
{
|
|
"entropy": 5.253823757171631,
|
|
"epoch": 7.321956189505858,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00014132437430193324,
|
|
"loss": 4.4861,
|
|
"mean_token_accuracy": 0.24588023275136947,
|
|
"num_tokens": 16941348.0,
|
|
"step": 7190
|
|
},
|
|
{
|
|
"entropy": 5.2274720668792725,
|
|
"epoch": 7.327050433010698,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00014100189490823213,
|
|
"loss": 4.5024,
|
|
"mean_token_accuracy": 0.2366440549492836,
|
|
"num_tokens": 16951832.0,
|
|
"step": 7195
|
|
},
|
|
{
|
|
"entropy": 5.293424606323242,
|
|
"epoch": 7.332144676515537,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.0001406798414918532,
|
|
"loss": 4.5704,
|
|
"mean_token_accuracy": 0.2367715135216713,
|
|
"num_tokens": 16964095.0,
|
|
"step": 7200
|
|
},
|
|
{
|
|
"entropy": 5.187577438354492,
|
|
"epoch": 7.337238920020377,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00014035821507659777,
|
|
"loss": 4.4306,
|
|
"mean_token_accuracy": 0.25230236500501635,
|
|
"num_tokens": 16975706.0,
|
|
"step": 7205
|
|
},
|
|
{
|
|
"entropy": 5.112560796737671,
|
|
"epoch": 7.3423331635252165,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00014003701668491007,
|
|
"loss": 4.4171,
|
|
"mean_token_accuracy": 0.25388338416814804,
|
|
"num_tokens": 16986921.0,
|
|
"step": 7210
|
|
},
|
|
{
|
|
"entropy": 5.220257806777954,
|
|
"epoch": 7.347427407030056,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00013971624733787326,
|
|
"loss": 4.4668,
|
|
"mean_token_accuracy": 0.24629946798086166,
|
|
"num_tokens": 16999435.0,
|
|
"step": 7215
|
|
},
|
|
{
|
|
"entropy": 5.222437477111816,
|
|
"epoch": 7.352521650534896,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013939590805520677,
|
|
"loss": 4.5328,
|
|
"mean_token_accuracy": 0.24515562355518342,
|
|
"num_tokens": 17012416.0,
|
|
"step": 7220
|
|
},
|
|
{
|
|
"entropy": 5.186233472824097,
|
|
"epoch": 7.357615894039735,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00013907599985526288,
|
|
"loss": 4.3983,
|
|
"mean_token_accuracy": 0.25528205633163453,
|
|
"num_tokens": 17023737.0,
|
|
"step": 7225
|
|
},
|
|
{
|
|
"entropy": 5.2355725288391115,
|
|
"epoch": 7.362710137544575,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 0.00013875652375502334,
|
|
"loss": 4.5566,
|
|
"mean_token_accuracy": 0.24426442831754686,
|
|
"num_tokens": 17036217.0,
|
|
"step": 7230
|
|
},
|
|
{
|
|
"entropy": 5.179762744903565,
|
|
"epoch": 7.367804381049414,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00013843748077009644,
|
|
"loss": 4.4352,
|
|
"mean_token_accuracy": 0.2539132282137871,
|
|
"num_tokens": 17048962.0,
|
|
"step": 7235
|
|
},
|
|
{
|
|
"entropy": 5.247820901870727,
|
|
"epoch": 7.372898624554254,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001381188719147134,
|
|
"loss": 4.5394,
|
|
"mean_token_accuracy": 0.24306199252605437,
|
|
"num_tokens": 17059942.0,
|
|
"step": 7240
|
|
},
|
|
{
|
|
"entropy": 5.26726803779602,
|
|
"epoch": 7.377992868059093,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 0.0001378006982017255,
|
|
"loss": 4.4937,
|
|
"mean_token_accuracy": 0.24294374138116837,
|
|
"num_tokens": 17070924.0,
|
|
"step": 7245
|
|
},
|
|
{
|
|
"entropy": 5.221755456924439,
|
|
"epoch": 7.383087111563933,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00013748296064260073,
|
|
"loss": 4.4758,
|
|
"mean_token_accuracy": 0.25054381638765333,
|
|
"num_tokens": 17083751.0,
|
|
"step": 7250
|
|
},
|
|
{
|
|
"entropy": 5.237550258636475,
|
|
"epoch": 7.388181355068772,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.0001371656602474205,
|
|
"loss": 4.4933,
|
|
"mean_token_accuracy": 0.25176291167736053,
|
|
"num_tokens": 17097138.0,
|
|
"step": 7255
|
|
},
|
|
{
|
|
"entropy": 5.222109937667847,
|
|
"epoch": 7.393275598573612,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00013684879802487642,
|
|
"loss": 4.5126,
|
|
"mean_token_accuracy": 0.2461598828434944,
|
|
"num_tokens": 17108947.0,
|
|
"step": 7260
|
|
},
|
|
{
|
|
"entropy": 5.1722273349761965,
|
|
"epoch": 7.398369842078451,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00013653237498226727,
|
|
"loss": 4.4415,
|
|
"mean_token_accuracy": 0.25162440091371535,
|
|
"num_tokens": 17120143.0,
|
|
"step": 7265
|
|
},
|
|
{
|
|
"entropy": 5.2063640594482425,
|
|
"epoch": 7.403464085583291,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00013621639212549558,
|
|
"loss": 4.5114,
|
|
"mean_token_accuracy": 0.24476519376039504,
|
|
"num_tokens": 17131433.0,
|
|
"step": 7270
|
|
},
|
|
{
|
|
"entropy": 5.281140422821045,
|
|
"epoch": 7.40855832908813,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00013590085045906463,
|
|
"loss": 4.5388,
|
|
"mean_token_accuracy": 0.24224649220705033,
|
|
"num_tokens": 17142865.0,
|
|
"step": 7275
|
|
},
|
|
{
|
|
"entropy": 5.275493907928467,
|
|
"epoch": 7.41365257259297,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013558575098607505,
|
|
"loss": 4.5356,
|
|
"mean_token_accuracy": 0.2452898070216179,
|
|
"num_tokens": 17155514.0,
|
|
"step": 7280
|
|
},
|
|
{
|
|
"entropy": 5.214653730392456,
|
|
"epoch": 7.418746816097809,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013527109470822196,
|
|
"loss": 4.3953,
|
|
"mean_token_accuracy": 0.25822453051805494,
|
|
"num_tokens": 17166781.0,
|
|
"step": 7285
|
|
},
|
|
{
|
|
"entropy": 5.290101099014282,
|
|
"epoch": 7.423841059602649,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.0001349568826257914,
|
|
"loss": 4.516,
|
|
"mean_token_accuracy": 0.24112863838672638,
|
|
"num_tokens": 17178064.0,
|
|
"step": 7290
|
|
},
|
|
{
|
|
"entropy": 5.241773271560669,
|
|
"epoch": 7.4289353031074885,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.0001346431157376573,
|
|
"loss": 4.5273,
|
|
"mean_token_accuracy": 0.2461179882287979,
|
|
"num_tokens": 17190333.0,
|
|
"step": 7295
|
|
},
|
|
{
|
|
"entropy": 5.228379964828491,
|
|
"epoch": 7.434029546612328,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.0001343297950412784,
|
|
"loss": 4.511,
|
|
"mean_token_accuracy": 0.24939713180065154,
|
|
"num_tokens": 17202120.0,
|
|
"step": 7300
|
|
},
|
|
{
|
|
"entropy": 5.181284999847412,
|
|
"epoch": 7.439123790117168,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.000134016921532695,
|
|
"loss": 4.4679,
|
|
"mean_token_accuracy": 0.2506625324487686,
|
|
"num_tokens": 17214692.0,
|
|
"step": 7305
|
|
},
|
|
{
|
|
"entropy": 5.163906764984131,
|
|
"epoch": 7.444218033622007,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00013370449620652583,
|
|
"loss": 4.3761,
|
|
"mean_token_accuracy": 0.24873684495687484,
|
|
"num_tokens": 17225175.0,
|
|
"step": 7310
|
|
},
|
|
{
|
|
"entropy": 5.230840063095092,
|
|
"epoch": 7.449312277126847,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.00013339252005596476,
|
|
"loss": 4.4824,
|
|
"mean_token_accuracy": 0.2492770180106163,
|
|
"num_tokens": 17237980.0,
|
|
"step": 7315
|
|
},
|
|
{
|
|
"entropy": 5.197075414657593,
|
|
"epoch": 7.454406520631686,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00013308099407277765,
|
|
"loss": 4.3899,
|
|
"mean_token_accuracy": 0.2583774223923683,
|
|
"num_tokens": 17249475.0,
|
|
"step": 7320
|
|
},
|
|
{
|
|
"entropy": 5.263677787780762,
|
|
"epoch": 7.459500764136526,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 0.00013276991924729976,
|
|
"loss": 4.5574,
|
|
"mean_token_accuracy": 0.24328235387802125,
|
|
"num_tokens": 17261058.0,
|
|
"step": 7325
|
|
},
|
|
{
|
|
"entropy": 5.151742649078369,
|
|
"epoch": 7.464595007641365,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00013245929656843154,
|
|
"loss": 4.4063,
|
|
"mean_token_accuracy": 0.2500901609659195,
|
|
"num_tokens": 17272335.0,
|
|
"step": 7330
|
|
},
|
|
{
|
|
"entropy": 5.212367296218872,
|
|
"epoch": 7.469689251146205,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00013214912702363645,
|
|
"loss": 4.4905,
|
|
"mean_token_accuracy": 0.24879868179559708,
|
|
"num_tokens": 17283570.0,
|
|
"step": 7335
|
|
},
|
|
{
|
|
"entropy": 5.2076253414154055,
|
|
"epoch": 7.474783494651044,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001318394115989372,
|
|
"loss": 4.4644,
|
|
"mean_token_accuracy": 0.25436193197965623,
|
|
"num_tokens": 17294363.0,
|
|
"step": 7340
|
|
},
|
|
{
|
|
"entropy": 5.2262485980987545,
|
|
"epoch": 7.479877738155884,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00013153015127891326,
|
|
"loss": 4.5525,
|
|
"mean_token_accuracy": 0.24367516189813615,
|
|
"num_tokens": 17306929.0,
|
|
"step": 7345
|
|
},
|
|
{
|
|
"entropy": 5.211608505249023,
|
|
"epoch": 7.484971981660723,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 0.00013122134704669682,
|
|
"loss": 4.4626,
|
|
"mean_token_accuracy": 0.2540006935596466,
|
|
"num_tokens": 17317984.0,
|
|
"step": 7350
|
|
},
|
|
{
|
|
"entropy": 5.219876956939697,
|
|
"epoch": 7.490066225165563,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.0001309129998839705,
|
|
"loss": 4.5209,
|
|
"mean_token_accuracy": 0.24670668095350265,
|
|
"num_tokens": 17331069.0,
|
|
"step": 7355
|
|
},
|
|
{
|
|
"entropy": 5.215260362625122,
|
|
"epoch": 7.495160468670402,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 0.00013060511077096372,
|
|
"loss": 4.4954,
|
|
"mean_token_accuracy": 0.2442785918712616,
|
|
"num_tokens": 17343572.0,
|
|
"step": 7360
|
|
},
|
|
{
|
|
"entropy": 5.282609510421753,
|
|
"epoch": 7.500254712175242,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00013029768068645003,
|
|
"loss": 4.5408,
|
|
"mean_token_accuracy": 0.24054456055164336,
|
|
"num_tokens": 17356136.0,
|
|
"step": 7365
|
|
},
|
|
{
|
|
"entropy": 5.2737654685974125,
|
|
"epoch": 7.505348955680081,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00012999071060774354,
|
|
"loss": 4.4941,
|
|
"mean_token_accuracy": 0.2462587609887123,
|
|
"num_tokens": 17367692.0,
|
|
"step": 7370
|
|
},
|
|
{
|
|
"entropy": 5.139848375320435,
|
|
"epoch": 7.510443199184921,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.000129684201510696,
|
|
"loss": 4.4147,
|
|
"mean_token_accuracy": 0.24866240173578263,
|
|
"num_tokens": 17380753.0,
|
|
"step": 7375
|
|
},
|
|
{
|
|
"entropy": 5.181377744674682,
|
|
"epoch": 7.5155374426897605,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00012937815436969368,
|
|
"loss": 4.4412,
|
|
"mean_token_accuracy": 0.2543517768383026,
|
|
"num_tokens": 17392353.0,
|
|
"step": 7380
|
|
},
|
|
{
|
|
"entropy": 5.278961277008056,
|
|
"epoch": 7.5206316861946,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00012907257015765466,
|
|
"loss": 4.5023,
|
|
"mean_token_accuracy": 0.24370977133512498,
|
|
"num_tokens": 17404503.0,
|
|
"step": 7385
|
|
},
|
|
{
|
|
"entropy": 5.2459968566894535,
|
|
"epoch": 7.52572592969944,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00012876744984602486,
|
|
"loss": 4.5193,
|
|
"mean_token_accuracy": 0.2430834412574768,
|
|
"num_tokens": 17416685.0,
|
|
"step": 7390
|
|
},
|
|
{
|
|
"entropy": 5.190151119232178,
|
|
"epoch": 7.53082017320428,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00012846279440477577,
|
|
"loss": 4.5118,
|
|
"mean_token_accuracy": 0.24641124457120894,
|
|
"num_tokens": 17427950.0,
|
|
"step": 7395
|
|
},
|
|
{
|
|
"entropy": 5.222418785095215,
|
|
"epoch": 7.535914416709119,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001281586048024009,
|
|
"loss": 4.4654,
|
|
"mean_token_accuracy": 0.24903523921966553,
|
|
"num_tokens": 17439007.0,
|
|
"step": 7400
|
|
},
|
|
{
|
|
"entropy": 5.184920692443848,
|
|
"epoch": 7.541008660213958,
|
|
"grad_norm": 1.1015625,
|
|
"learning_rate": 0.00012785488200591316,
|
|
"loss": 4.4368,
|
|
"mean_token_accuracy": 0.2572574019432068,
|
|
"num_tokens": 17450881.0,
|
|
"step": 7405
|
|
},
|
|
{
|
|
"entropy": 5.196303462982177,
|
|
"epoch": 7.546102903718798,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.0001275516269808412,
|
|
"loss": 4.4627,
|
|
"mean_token_accuracy": 0.2525940671563148,
|
|
"num_tokens": 17461836.0,
|
|
"step": 7410
|
|
},
|
|
{
|
|
"entropy": 5.130426692962646,
|
|
"epoch": 7.551197147223637,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00012724884069122678,
|
|
"loss": 4.3755,
|
|
"mean_token_accuracy": 0.26358903050422666,
|
|
"num_tokens": 17473128.0,
|
|
"step": 7415
|
|
},
|
|
{
|
|
"entropy": 5.210389518737793,
|
|
"epoch": 7.556291390728477,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00012694652409962144,
|
|
"loss": 4.4953,
|
|
"mean_token_accuracy": 0.24744086116552352,
|
|
"num_tokens": 17484838.0,
|
|
"step": 7420
|
|
},
|
|
{
|
|
"entropy": 5.28792028427124,
|
|
"epoch": 7.561385634233316,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001266446781670838,
|
|
"loss": 4.5512,
|
|
"mean_token_accuracy": 0.24591612219810485,
|
|
"num_tokens": 17495679.0,
|
|
"step": 7425
|
|
},
|
|
{
|
|
"entropy": 5.207336568832398,
|
|
"epoch": 7.566479877738156,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00012634330385317592,
|
|
"loss": 4.474,
|
|
"mean_token_accuracy": 0.25010829567909243,
|
|
"num_tokens": 17507794.0,
|
|
"step": 7430
|
|
},
|
|
{
|
|
"entropy": 5.266295528411865,
|
|
"epoch": 7.571574121242995,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.0001260424021159608,
|
|
"loss": 4.547,
|
|
"mean_token_accuracy": 0.23663731962442397,
|
|
"num_tokens": 17520621.0,
|
|
"step": 7435
|
|
},
|
|
{
|
|
"entropy": 5.185838413238526,
|
|
"epoch": 7.576668364747835,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00012574197391199916,
|
|
"loss": 4.4862,
|
|
"mean_token_accuracy": 0.2488825649023056,
|
|
"num_tokens": 17532042.0,
|
|
"step": 7440
|
|
},
|
|
{
|
|
"entropy": 5.274714231491089,
|
|
"epoch": 7.581762608252674,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00012544202019634638,
|
|
"loss": 4.5667,
|
|
"mean_token_accuracy": 0.2359732434153557,
|
|
"num_tokens": 17544843.0,
|
|
"step": 7445
|
|
},
|
|
{
|
|
"entropy": 5.173145437240601,
|
|
"epoch": 7.586856851757514,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00012514254192254925,
|
|
"loss": 4.3784,
|
|
"mean_token_accuracy": 0.2576137199997902,
|
|
"num_tokens": 17555715.0,
|
|
"step": 7450
|
|
},
|
|
{
|
|
"entropy": 5.215708160400391,
|
|
"epoch": 7.5919510952623535,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00012484354004264333,
|
|
"loss": 4.4725,
|
|
"mean_token_accuracy": 0.24569547921419144,
|
|
"num_tokens": 17566785.0,
|
|
"step": 7455
|
|
},
|
|
{
|
|
"entropy": 5.186607551574707,
|
|
"epoch": 7.5970453387671935,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00012454501550714962,
|
|
"loss": 4.4471,
|
|
"mean_token_accuracy": 0.254772412776947,
|
|
"num_tokens": 17579174.0,
|
|
"step": 7460
|
|
},
|
|
{
|
|
"entropy": 5.248232650756836,
|
|
"epoch": 7.602139582272033,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00012424696926507188,
|
|
"loss": 4.4832,
|
|
"mean_token_accuracy": 0.24681483805179597,
|
|
"num_tokens": 17591049.0,
|
|
"step": 7465
|
|
},
|
|
{
|
|
"entropy": 5.215922260284424,
|
|
"epoch": 7.607233825776872,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00012394940226389303,
|
|
"loss": 4.4789,
|
|
"mean_token_accuracy": 0.24777912795543672,
|
|
"num_tokens": 17601725.0,
|
|
"step": 7470
|
|
},
|
|
{
|
|
"entropy": 5.213147449493408,
|
|
"epoch": 7.612328069281712,
|
|
"grad_norm": 1.109375,
|
|
"learning_rate": 0.0001236523154495726,
|
|
"loss": 4.5532,
|
|
"mean_token_accuracy": 0.24172252416610718,
|
|
"num_tokens": 17615192.0,
|
|
"step": 7475
|
|
},
|
|
{
|
|
"entropy": 5.183976364135742,
|
|
"epoch": 7.617422312786552,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00012335570976654395,
|
|
"loss": 4.4276,
|
|
"mean_token_accuracy": 0.2548325628042221,
|
|
"num_tokens": 17625743.0,
|
|
"step": 7480
|
|
},
|
|
{
|
|
"entropy": 5.203971910476684,
|
|
"epoch": 7.622516556291391,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00012305958615771052,
|
|
"loss": 4.4612,
|
|
"mean_token_accuracy": 0.25198039412498474,
|
|
"num_tokens": 17637439.0,
|
|
"step": 7485
|
|
},
|
|
{
|
|
"entropy": 5.202105569839477,
|
|
"epoch": 7.62761079979623,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00012276394556444338,
|
|
"loss": 4.5239,
|
|
"mean_token_accuracy": 0.24911118447780609,
|
|
"num_tokens": 17649129.0,
|
|
"step": 7490
|
|
},
|
|
{
|
|
"entropy": 5.121450471878052,
|
|
"epoch": 7.63270504330107,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.0001224687889265782,
|
|
"loss": 4.4219,
|
|
"mean_token_accuracy": 0.25728510320186615,
|
|
"num_tokens": 17660827.0,
|
|
"step": 7495
|
|
},
|
|
{
|
|
"entropy": 5.2697991847991945,
|
|
"epoch": 7.637799286805909,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.00012217411718241195,
|
|
"loss": 4.4988,
|
|
"mean_token_accuracy": 0.2447270855307579,
|
|
"num_tokens": 17672074.0,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"entropy": 5.275542545318603,
|
|
"epoch": 7.642893530310749,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.0001218799312687005,
|
|
"loss": 4.5122,
|
|
"mean_token_accuracy": 0.23995315730571748,
|
|
"num_tokens": 17683292.0,
|
|
"step": 7505
|
|
},
|
|
{
|
|
"entropy": 5.237659120559693,
|
|
"epoch": 7.647987773815588,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00012158623212065485,
|
|
"loss": 4.5313,
|
|
"mean_token_accuracy": 0.24494230300188063,
|
|
"num_tokens": 17696641.0,
|
|
"step": 7510
|
|
},
|
|
{
|
|
"entropy": 5.213913536071777,
|
|
"epoch": 7.653082017320428,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 0.00012129302067193875,
|
|
"loss": 4.4918,
|
|
"mean_token_accuracy": 0.24963215738534927,
|
|
"num_tokens": 17708082.0,
|
|
"step": 7515
|
|
},
|
|
{
|
|
"entropy": 5.212946271896362,
|
|
"epoch": 7.658176260825267,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00012100029785466572,
|
|
"loss": 4.4654,
|
|
"mean_token_accuracy": 0.252736833691597,
|
|
"num_tokens": 17719204.0,
|
|
"step": 7520
|
|
},
|
|
{
|
|
"entropy": 5.208316230773926,
|
|
"epoch": 7.663270504330107,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 0.00012070806459939576,
|
|
"loss": 4.4609,
|
|
"mean_token_accuracy": 0.25296022444963456,
|
|
"num_tokens": 17731847.0,
|
|
"step": 7525
|
|
},
|
|
{
|
|
"entropy": 5.236167669296265,
|
|
"epoch": 7.668364747834946,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00012041632183513258,
|
|
"loss": 4.5093,
|
|
"mean_token_accuracy": 0.24775006175041198,
|
|
"num_tokens": 17744848.0,
|
|
"step": 7530
|
|
},
|
|
{
|
|
"entropy": 5.218022155761719,
|
|
"epoch": 7.673458991339786,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.00012012507048932059,
|
|
"loss": 4.4639,
|
|
"mean_token_accuracy": 0.24958536475896836,
|
|
"num_tokens": 17755736.0,
|
|
"step": 7535
|
|
},
|
|
{
|
|
"entropy": 5.198501014709473,
|
|
"epoch": 7.6785532348446255,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00011983431148784217,
|
|
"loss": 4.5176,
|
|
"mean_token_accuracy": 0.24980874955654145,
|
|
"num_tokens": 17766956.0,
|
|
"step": 7540
|
|
},
|
|
{
|
|
"entropy": 5.219933319091797,
|
|
"epoch": 7.6836474783494655,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 0.00011954404575501445,
|
|
"loss": 4.4805,
|
|
"mean_token_accuracy": 0.24726129174232483,
|
|
"num_tokens": 17778776.0,
|
|
"step": 7545
|
|
},
|
|
{
|
|
"entropy": 5.212337255477905,
|
|
"epoch": 7.688741721854305,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 0.0001192542742135863,
|
|
"loss": 4.4497,
|
|
"mean_token_accuracy": 0.25291958898305894,
|
|
"num_tokens": 17791369.0,
|
|
"step": 7550
|
|
},
|
|
{
|
|
"entropy": 5.188727378845215,
|
|
"epoch": 7.693835965359144,
|
|
"grad_norm": 1.1328125,
|
|
"learning_rate": 0.0001189649977847357,
|
|
"loss": 4.4565,
|
|
"mean_token_accuracy": 0.25265884548425677,
|
|
"num_tokens": 17802966.0,
|
|
"step": 7555
|
|
},
|
|
{
|
|
"entropy": 5.231284952163696,
|
|
"epoch": 7.698930208863984,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00011867621738806684,
|
|
"loss": 4.4556,
|
|
"mean_token_accuracy": 0.25565880388021467,
|
|
"num_tokens": 17815880.0,
|
|
"step": 7560
|
|
},
|
|
{
|
|
"entropy": 5.253887748718261,
|
|
"epoch": 7.704024452368824,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00011838793394160681,
|
|
"loss": 4.5037,
|
|
"mean_token_accuracy": 0.2480195105075836,
|
|
"num_tokens": 17827093.0,
|
|
"step": 7565
|
|
},
|
|
{
|
|
"entropy": 5.239623022079468,
|
|
"epoch": 7.709118695873663,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.000118100148361803,
|
|
"loss": 4.4532,
|
|
"mean_token_accuracy": 0.24880526661872865,
|
|
"num_tokens": 17838516.0,
|
|
"step": 7570
|
|
},
|
|
{
|
|
"entropy": 5.215308332443238,
|
|
"epoch": 7.714212939378502,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00011781286156351995,
|
|
"loss": 4.5091,
|
|
"mean_token_accuracy": 0.24756460636854172,
|
|
"num_tokens": 17851130.0,
|
|
"step": 7575
|
|
},
|
|
{
|
|
"entropy": 5.223705005645752,
|
|
"epoch": 7.719307182883342,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00011752607446003685,
|
|
"loss": 4.4858,
|
|
"mean_token_accuracy": 0.248725526034832,
|
|
"num_tokens": 17862981.0,
|
|
"step": 7580
|
|
},
|
|
{
|
|
"entropy": 5.269415664672851,
|
|
"epoch": 7.724401426388181,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00011723978796304424,
|
|
"loss": 4.4512,
|
|
"mean_token_accuracy": 0.24748954325914382,
|
|
"num_tokens": 17875215.0,
|
|
"step": 7585
|
|
},
|
|
{
|
|
"entropy": 5.212552261352539,
|
|
"epoch": 7.729495669893021,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00011695400298264102,
|
|
"loss": 4.5394,
|
|
"mean_token_accuracy": 0.23866590857505798,
|
|
"num_tokens": 17887035.0,
|
|
"step": 7590
|
|
},
|
|
{
|
|
"entropy": 5.137506818771362,
|
|
"epoch": 7.73458991339786,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011666872042733217,
|
|
"loss": 4.4089,
|
|
"mean_token_accuracy": 0.25420629382133486,
|
|
"num_tokens": 17899116.0,
|
|
"step": 7595
|
|
},
|
|
{
|
|
"entropy": 5.221938610076904,
|
|
"epoch": 7.7396841569027,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 0.00011638394120402527,
|
|
"loss": 4.4753,
|
|
"mean_token_accuracy": 0.25017881840467454,
|
|
"num_tokens": 17910750.0,
|
|
"step": 7600
|
|
},
|
|
{
|
|
"entropy": 5.227229595184326,
|
|
"epoch": 7.744778400407539,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011609966621802775,
|
|
"loss": 4.4666,
|
|
"mean_token_accuracy": 0.25089489221572875,
|
|
"num_tokens": 17922132.0,
|
|
"step": 7605
|
|
},
|
|
{
|
|
"entropy": 5.317099571228027,
|
|
"epoch": 7.749872643912379,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 0.0001158158963730442,
|
|
"loss": 4.5622,
|
|
"mean_token_accuracy": 0.2449432671070099,
|
|
"num_tokens": 17933710.0,
|
|
"step": 7610
|
|
},
|
|
{
|
|
"entropy": 5.2599657535552975,
|
|
"epoch": 7.754966887417218,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00011553263257117329,
|
|
"loss": 4.5846,
|
|
"mean_token_accuracy": 0.2386517658829689,
|
|
"num_tokens": 17946064.0,
|
|
"step": 7615
|
|
},
|
|
{
|
|
"entropy": 5.215897035598755,
|
|
"epoch": 7.760061130922058,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001152498757129051,
|
|
"loss": 4.5061,
|
|
"mean_token_accuracy": 0.24843507409095764,
|
|
"num_tokens": 17958100.0,
|
|
"step": 7620
|
|
},
|
|
{
|
|
"entropy": 5.202504873275757,
|
|
"epoch": 7.7651553744268975,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00011496762669711816,
|
|
"loss": 4.4777,
|
|
"mean_token_accuracy": 0.2535253196954727,
|
|
"num_tokens": 17970974.0,
|
|
"step": 7625
|
|
},
|
|
{
|
|
"entropy": 5.289047145843506,
|
|
"epoch": 7.7702496179317375,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 0.00011468588642107627,
|
|
"loss": 4.5861,
|
|
"mean_token_accuracy": 0.2418184608221054,
|
|
"num_tokens": 17983822.0,
|
|
"step": 7630
|
|
},
|
|
{
|
|
"entropy": 5.239374589920044,
|
|
"epoch": 7.775343861436577,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00011440465578042639,
|
|
"loss": 4.5226,
|
|
"mean_token_accuracy": 0.24092212468385696,
|
|
"num_tokens": 17996527.0,
|
|
"step": 7635
|
|
},
|
|
{
|
|
"entropy": 5.257705497741699,
|
|
"epoch": 7.780438104941416,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00011412393566919507,
|
|
"loss": 4.5087,
|
|
"mean_token_accuracy": 0.24618381261825562,
|
|
"num_tokens": 18008624.0,
|
|
"step": 7640
|
|
},
|
|
{
|
|
"entropy": 5.242985725402832,
|
|
"epoch": 7.785532348446256,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00011384372697978604,
|
|
"loss": 4.5012,
|
|
"mean_token_accuracy": 0.24632367342710496,
|
|
"num_tokens": 18019965.0,
|
|
"step": 7645
|
|
},
|
|
{
|
|
"entropy": 5.18924355506897,
|
|
"epoch": 7.790626591951096,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00011356403060297709,
|
|
"loss": 4.4649,
|
|
"mean_token_accuracy": 0.24804221987724304,
|
|
"num_tokens": 18032767.0,
|
|
"step": 7650
|
|
},
|
|
{
|
|
"entropy": 5.211838054656982,
|
|
"epoch": 7.795720835455935,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011328484742791747,
|
|
"loss": 4.5,
|
|
"mean_token_accuracy": 0.2465629443526268,
|
|
"num_tokens": 18045068.0,
|
|
"step": 7655
|
|
},
|
|
{
|
|
"entropy": 5.235693120956421,
|
|
"epoch": 7.800815078960774,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.00011300617834212505,
|
|
"loss": 4.4787,
|
|
"mean_token_accuracy": 0.24931267350912095,
|
|
"num_tokens": 18056985.0,
|
|
"step": 7660
|
|
},
|
|
{
|
|
"entropy": 5.2677978515625,
|
|
"epoch": 7.805909322465614,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00011272802423148338,
|
|
"loss": 4.5668,
|
|
"mean_token_accuracy": 0.2384687766432762,
|
|
"num_tokens": 18068585.0,
|
|
"step": 7665
|
|
},
|
|
{
|
|
"entropy": 5.171484136581421,
|
|
"epoch": 7.811003565970453,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 0.0001124503859802386,
|
|
"loss": 4.4453,
|
|
"mean_token_accuracy": 0.2560416266322136,
|
|
"num_tokens": 18080451.0,
|
|
"step": 7670
|
|
},
|
|
{
|
|
"entropy": 5.258579730987549,
|
|
"epoch": 7.816097809475293,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00011217326447099748,
|
|
"loss": 4.5149,
|
|
"mean_token_accuracy": 0.2457113966345787,
|
|
"num_tokens": 18091045.0,
|
|
"step": 7675
|
|
},
|
|
{
|
|
"entropy": 5.212411689758301,
|
|
"epoch": 7.821192052980132,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00011189666058472372,
|
|
"loss": 4.4594,
|
|
"mean_token_accuracy": 0.24576255381107331,
|
|
"num_tokens": 18103403.0,
|
|
"step": 7680
|
|
},
|
|
{
|
|
"entropy": 5.185942506790161,
|
|
"epoch": 7.826286296484972,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00011162057520073559,
|
|
"loss": 4.5348,
|
|
"mean_token_accuracy": 0.24119848012924194,
|
|
"num_tokens": 18115024.0,
|
|
"step": 7685
|
|
},
|
|
{
|
|
"entropy": 5.193650341033935,
|
|
"epoch": 7.831380539989811,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 0.00011134500919670298,
|
|
"loss": 4.3851,
|
|
"mean_token_accuracy": 0.2594183534383774,
|
|
"num_tokens": 18126570.0,
|
|
"step": 7690
|
|
},
|
|
{
|
|
"entropy": 5.292917251586914,
|
|
"epoch": 7.836474783494651,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00011106996344864492,
|
|
"loss": 4.5243,
|
|
"mean_token_accuracy": 0.24023627042770385,
|
|
"num_tokens": 18137000.0,
|
|
"step": 7695
|
|
},
|
|
{
|
|
"entropy": 5.2078780174255375,
|
|
"epoch": 7.84156902699949,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.0001107954388309263,
|
|
"loss": 4.4385,
|
|
"mean_token_accuracy": 0.24780807495117188,
|
|
"num_tokens": 18149692.0,
|
|
"step": 7700
|
|
},
|
|
{
|
|
"entropy": 5.254333019256592,
|
|
"epoch": 7.84666327050433,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00011052143621625552,
|
|
"loss": 4.5451,
|
|
"mean_token_accuracy": 0.23929301798343658,
|
|
"num_tokens": 18161408.0,
|
|
"step": 7705
|
|
},
|
|
{
|
|
"entropy": 5.206493091583252,
|
|
"epoch": 7.8517575140091695,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.0001102479564756813,
|
|
"loss": 4.43,
|
|
"mean_token_accuracy": 0.25351258665323256,
|
|
"num_tokens": 18172585.0,
|
|
"step": 7710
|
|
},
|
|
{
|
|
"entropy": 5.279753875732422,
|
|
"epoch": 7.8568517575140095,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00010997500047859046,
|
|
"loss": 4.6054,
|
|
"mean_token_accuracy": 0.23771266192197799,
|
|
"num_tokens": 18185233.0,
|
|
"step": 7715
|
|
},
|
|
{
|
|
"entropy": 5.253861331939698,
|
|
"epoch": 7.861946001018849,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 0.00010970256909270468,
|
|
"loss": 4.515,
|
|
"mean_token_accuracy": 0.24304765164852143,
|
|
"num_tokens": 18199060.0,
|
|
"step": 7720
|
|
},
|
|
{
|
|
"entropy": 5.21439642906189,
|
|
"epoch": 7.867040244523688,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00010943066318407794,
|
|
"loss": 4.4937,
|
|
"mean_token_accuracy": 0.24273545145988465,
|
|
"num_tokens": 18211612.0,
|
|
"step": 7725
|
|
},
|
|
{
|
|
"entropy": 5.210781049728394,
|
|
"epoch": 7.872134488028528,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 0.00010915928361709364,
|
|
"loss": 4.5014,
|
|
"mean_token_accuracy": 0.24403632283210755,
|
|
"num_tokens": 18223878.0,
|
|
"step": 7730
|
|
},
|
|
{
|
|
"entropy": 5.252370119094849,
|
|
"epoch": 7.877228731533368,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.00010888843125446221,
|
|
"loss": 4.4718,
|
|
"mean_token_accuracy": 0.25131566673517225,
|
|
"num_tokens": 18235720.0,
|
|
"step": 7735
|
|
},
|
|
{
|
|
"entropy": 5.197298955917359,
|
|
"epoch": 7.882322975038207,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010861810695721786,
|
|
"loss": 4.4289,
|
|
"mean_token_accuracy": 0.2561774879693985,
|
|
"num_tokens": 18245612.0,
|
|
"step": 7740
|
|
},
|
|
{
|
|
"entropy": 5.315625190734863,
|
|
"epoch": 7.887417218543046,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 0.00010834831158471628,
|
|
"loss": 4.5396,
|
|
"mean_token_accuracy": 0.23777572065591812,
|
|
"num_tokens": 18258029.0,
|
|
"step": 7745
|
|
},
|
|
{
|
|
"entropy": 5.255504989624024,
|
|
"epoch": 7.892511462047886,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.0001080790459946314,
|
|
"loss": 4.432,
|
|
"mean_token_accuracy": 0.25268457382917403,
|
|
"num_tokens": 18269953.0,
|
|
"step": 7750
|
|
},
|
|
{
|
|
"entropy": 5.263616991043091,
|
|
"epoch": 7.897605705552725,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 0.00010781031104295338,
|
|
"loss": 4.5617,
|
|
"mean_token_accuracy": 0.24028398245573043,
|
|
"num_tokens": 18282022.0,
|
|
"step": 7755
|
|
},
|
|
{
|
|
"entropy": 5.236017847061158,
|
|
"epoch": 7.902699949057565,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010754210758398525,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.2510830819606781,
|
|
"num_tokens": 18293941.0,
|
|
"step": 7760
|
|
},
|
|
{
|
|
"entropy": 5.17886118888855,
|
|
"epoch": 7.907794192562404,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00010727443647034049,
|
|
"loss": 4.4118,
|
|
"mean_token_accuracy": 0.251865616440773,
|
|
"num_tokens": 18305202.0,
|
|
"step": 7765
|
|
},
|
|
{
|
|
"entropy": 5.216768360137939,
|
|
"epoch": 7.912888436067244,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 0.00010700729855294022,
|
|
"loss": 4.4828,
|
|
"mean_token_accuracy": 0.2542563259601593,
|
|
"num_tokens": 18314649.0,
|
|
"step": 7770
|
|
},
|
|
{
|
|
"entropy": 5.267251300811767,
|
|
"epoch": 7.917982679572083,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 0.0001067406946810107,
|
|
"loss": 4.4941,
|
|
"mean_token_accuracy": 0.244268436729908,
|
|
"num_tokens": 18325682.0,
|
|
"step": 7775
|
|
},
|
|
{
|
|
"entropy": 5.2218865871429445,
|
|
"epoch": 7.923076923076923,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.0001064746257020803,
|
|
"loss": 4.4856,
|
|
"mean_token_accuracy": 0.2550613358616829,
|
|
"num_tokens": 18336670.0,
|
|
"step": 7780
|
|
},
|
|
{
|
|
"entropy": 5.236203002929687,
|
|
"epoch": 7.9281711665817625,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 0.00010620909246197705,
|
|
"loss": 4.4889,
|
|
"mean_token_accuracy": 0.24833985716104506,
|
|
"num_tokens": 18348766.0,
|
|
"step": 7785
|
|
},
|
|
{
|
|
"entropy": 5.219201612472534,
|
|
"epoch": 7.9332654100866025,
|
|
"grad_norm": 0.99609375,
|
|
"learning_rate": 0.00010594409580482585,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.24481591880321502,
|
|
"num_tokens": 18361649.0,
|
|
"step": 7790
|
|
},
|
|
{
|
|
"entropy": 5.223743963241577,
|
|
"epoch": 7.938359653591442,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 0.00010567963657304581,
|
|
"loss": 4.5099,
|
|
"mean_token_accuracy": 0.24483627080917358,
|
|
"num_tokens": 18373807.0,
|
|
"step": 7795
|
|
},
|
|
{
|
|
"entropy": 5.190727853775025,
|
|
"epoch": 7.943453897096282,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 0.00010541571560734761,
|
|
"loss": 4.4519,
|
|
"mean_token_accuracy": 0.2525549978017807,
|
|
"num_tokens": 18385682.0,
|
|
"step": 7800
|
|
},
|
|
{
|
|
"entropy": 5.236370372772217,
|
|
"epoch": 7.948548140601121,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.00010515233374673074,
|
|
"loss": 4.5315,
|
|
"mean_token_accuracy": 0.24428019374608995,
|
|
"num_tokens": 18398347.0,
|
|
"step": 7805
|
|
},
|
|
{
|
|
"entropy": 5.236452531814575,
|
|
"epoch": 7.95364238410596,
|
|
"grad_norm": 1.1484375,
|
|
"learning_rate": 0.00010488949182848093,
|
|
"loss": 4.4743,
|
|
"mean_token_accuracy": 0.24955035299062728,
|
|
"num_tokens": 18410850.0,
|
|
"step": 7810
|
|
},
|
|
{
|
|
"entropy": 5.259849548339844,
|
|
"epoch": 7.9587366276108,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00010462719068816747,
|
|
"loss": 4.4306,
|
|
"mean_token_accuracy": 0.2525710850954056,
|
|
"num_tokens": 18421753.0,
|
|
"step": 7815
|
|
},
|
|
{
|
|
"entropy": 5.1813005924224855,
|
|
"epoch": 7.96383087111564,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 0.00010436543115964048,
|
|
"loss": 4.4771,
|
|
"mean_token_accuracy": 0.2541292056441307,
|
|
"num_tokens": 18431719.0,
|
|
"step": 7820
|
|
},
|
|
{
|
|
"entropy": 5.0980723857879635,
|
|
"epoch": 7.968925114620479,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 0.00010410421407502833,
|
|
"loss": 4.3323,
|
|
"mean_token_accuracy": 0.26853873282670976,
|
|
"num_tokens": 18442537.0,
|
|
"step": 7825
|
|
},
|
|
{
|
|
"entropy": 5.232654476165772,
|
|
"epoch": 7.974019358125318,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 0.0001038435402647349,
|
|
"loss": 4.5068,
|
|
"mean_token_accuracy": 0.2499462589621544,
|
|
"num_tokens": 18455347.0,
|
|
"step": 7830
|
|
},
|
|
{
|
|
"entropy": 5.1253398895263675,
|
|
"epoch": 7.979113601630158,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 0.00010358341055743709,
|
|
"loss": 4.4263,
|
|
"mean_token_accuracy": 0.257177996635437,
|
|
"num_tokens": 18466820.0,
|
|
"step": 7835
|
|
},
|
|
{
|
|
"entropy": 5.230501651763916,
|
|
"epoch": 7.984207845134997,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 0.00010332382578008212,
|
|
"loss": 4.4897,
|
|
"mean_token_accuracy": 0.24601019620895387,
|
|
"num_tokens": 18477574.0,
|
|
"step": 7840
|
|
},
|
|
{
|
|
"entropy": 5.22273621559143,
|
|
"epoch": 7.989302088639837,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010306478675788478,
|
|
"loss": 4.4955,
|
|
"mean_token_accuracy": 0.2429514065384865,
|
|
"num_tokens": 18488955.0,
|
|
"step": 7845
|
|
},
|
|
{
|
|
"entropy": 5.1640502452850345,
|
|
"epoch": 7.994396332144676,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 0.00010280629431432511,
|
|
"loss": 4.384,
|
|
"mean_token_accuracy": 0.2543271318078041,
|
|
"num_tokens": 18499688.0,
|
|
"step": 7850
|
|
},
|
|
{
|
|
"entropy": 5.18080849647522,
|
|
"epoch": 7.999490575649516,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 0.0001025483492711454,
|
|
"loss": 4.423,
|
|
"mean_token_accuracy": 0.24798837006092073,
|
|
"num_tokens": 18511432.0,
|
|
"step": 7855
|
|
},
|
|
{
|
|
"entropy": 5.212876743740505,
|
|
"epoch": 8.004075394803872,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 0.00010229095244834782,
|
|
"loss": 4.399,
|
|
"mean_token_accuracy": 0.2627514799435933,
|
|
"num_tokens": 18521520.0,
|
|
"step": 7860
|
|
},
|
|
{
|
|
"entropy": 5.170367908477783,
|
|
"epoch": 8.00916963830871,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 0.00010203410466419183,
|
|
"loss": 4.3373,
|
|
"mean_token_accuracy": 0.2632194682955742,
|
|
"num_tokens": 18533250.0,
|
|
"step": 7865
|
|
},
|
|
{
|
|
"entropy": 5.208305549621582,
|
|
"epoch": 8.01426388181355,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00010177780673519138,
|
|
"loss": 4.4313,
|
|
"mean_token_accuracy": 0.2527763769030571,
|
|
"num_tokens": 18545148.0,
|
|
"step": 7870
|
|
},
|
|
{
|
|
"entropy": 5.294559621810913,
|
|
"epoch": 8.01935812531839,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 0.00010152205947611253,
|
|
"loss": 4.4484,
|
|
"mean_token_accuracy": 0.24693625122308732,
|
|
"num_tokens": 18558504.0,
|
|
"step": 7875
|
|
},
|
|
{
|
|
"entropy": 5.262330436706543,
|
|
"epoch": 8.02445236882323,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 0.00010126686369997076,
|
|
"loss": 4.4706,
|
|
"mean_token_accuracy": 0.2561426594853401,
|
|
"num_tokens": 18570867.0,
|
|
"step": 7880
|
|
},
|
|
{
|
|
"entropy": 5.234389114379883,
|
|
"epoch": 8.029546612328069,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 0.00010101222021802836,
|
|
"loss": 4.4677,
|
|
"mean_token_accuracy": 0.24648934304714204,
|
|
"num_tokens": 18584056.0,
|
|
"step": 7885
|
|
},
|
|
{
|
|
"entropy": 5.266378498077392,
|
|
"epoch": 8.034640855832908,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 0.000100758129839792,
|
|
"loss": 4.4508,
|
|
"mean_token_accuracy": 0.24953366219997405,
|
|
"num_tokens": 18595719.0,
|
|
"step": 7890
|
|
},
|
|
{
|
|
"entropy": 5.251543140411377,
|
|
"epoch": 8.039735099337749,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 0.00010050459337300988,
|
|
"loss": 4.4152,
|
|
"mean_token_accuracy": 0.2546901285648346,
|
|
"num_tokens": 18608436.0,
|
|
"step": 7895
|
|
},
|
|
{
|
|
"entropy": 5.232252931594848,
|
|
"epoch": 8.044829342842588,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 0.00010025161162366945,
|
|
"loss": 4.4367,
|
|
"mean_token_accuracy": 0.24960875660181045,
|
|
"num_tokens": 18619481.0,
|
|
"step": 7900
|
|
},
|
|
{
|
|
"entropy": 5.246986007690429,
|
|
"epoch": 8.049923586347427,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 9.999918539599465e-05,
|
|
"loss": 4.4049,
|
|
"mean_token_accuracy": 0.2606176808476448,
|
|
"num_tokens": 18631952.0,
|
|
"step": 7905
|
|
},
|
|
{
|
|
"entropy": 5.16799840927124,
|
|
"epoch": 8.055017829852266,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 9.974731549244347e-05,
|
|
"loss": 4.4095,
|
|
"mean_token_accuracy": 0.26044474691152575,
|
|
"num_tokens": 18645076.0,
|
|
"step": 7910
|
|
},
|
|
{
|
|
"entropy": 5.226918697357178,
|
|
"epoch": 8.060112073357107,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 9.949600271370536e-05,
|
|
"loss": 4.4199,
|
|
"mean_token_accuracy": 0.2591342657804489,
|
|
"num_tokens": 18657806.0,
|
|
"step": 7915
|
|
},
|
|
{
|
|
"entropy": 5.255883836746216,
|
|
"epoch": 8.065206316861946,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 9.924524785869866e-05,
|
|
"loss": 4.4225,
|
|
"mean_token_accuracy": 0.25190163403749466,
|
|
"num_tokens": 18669883.0,
|
|
"step": 7920
|
|
},
|
|
{
|
|
"entropy": 5.258478403091431,
|
|
"epoch": 8.070300560366785,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 9.899505172456796e-05,
|
|
"loss": 4.4607,
|
|
"mean_token_accuracy": 0.2550795659422874,
|
|
"num_tokens": 18682720.0,
|
|
"step": 7925
|
|
},
|
|
{
|
|
"entropy": 5.244602108001709,
|
|
"epoch": 8.075394803871625,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 9.874541510668205e-05,
|
|
"loss": 4.3691,
|
|
"mean_token_accuracy": 0.2624358534812927,
|
|
"num_tokens": 18692944.0,
|
|
"step": 7930
|
|
},
|
|
{
|
|
"entropy": 5.152872610092163,
|
|
"epoch": 8.080489047376465,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.849633879863066e-05,
|
|
"loss": 4.2932,
|
|
"mean_token_accuracy": 0.2675817683339119,
|
|
"num_tokens": 18704268.0,
|
|
"step": 7935
|
|
},
|
|
{
|
|
"entropy": 5.2555217266082765,
|
|
"epoch": 8.085583290881305,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 9.824782359222245e-05,
|
|
"loss": 4.4659,
|
|
"mean_token_accuracy": 0.24986083805561066,
|
|
"num_tokens": 18715481.0,
|
|
"step": 7940
|
|
},
|
|
{
|
|
"entropy": 5.165865278244018,
|
|
"epoch": 8.090677534386144,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 9.799987027748236e-05,
|
|
"loss": 4.3614,
|
|
"mean_token_accuracy": 0.2569147929549217,
|
|
"num_tokens": 18727458.0,
|
|
"step": 7945
|
|
},
|
|
{
|
|
"entropy": 5.192503213882446,
|
|
"epoch": 8.095771777890983,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.775247964264904e-05,
|
|
"loss": 4.3869,
|
|
"mean_token_accuracy": 0.25502635091543197,
|
|
"num_tokens": 18739312.0,
|
|
"step": 7950
|
|
},
|
|
{
|
|
"entropy": 5.20078296661377,
|
|
"epoch": 8.100866021395822,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 9.750565247417245e-05,
|
|
"loss": 4.3994,
|
|
"mean_token_accuracy": 0.25959380269050597,
|
|
"num_tokens": 18751502.0,
|
|
"step": 7955
|
|
},
|
|
{
|
|
"entropy": 5.128681182861328,
|
|
"epoch": 8.105960264900663,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.725938955671124e-05,
|
|
"loss": 4.3092,
|
|
"mean_token_accuracy": 0.26871801912784576,
|
|
"num_tokens": 18762324.0,
|
|
"step": 7960
|
|
},
|
|
{
|
|
"entropy": 5.25728759765625,
|
|
"epoch": 8.111054508405502,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 9.701369167313031e-05,
|
|
"loss": 4.4413,
|
|
"mean_token_accuracy": 0.2536597490310669,
|
|
"num_tokens": 18774554.0,
|
|
"step": 7965
|
|
},
|
|
{
|
|
"entropy": 5.285425519943237,
|
|
"epoch": 8.116148751910341,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 9.676855960449846e-05,
|
|
"loss": 4.4669,
|
|
"mean_token_accuracy": 0.24578340202569962,
|
|
"num_tokens": 18786449.0,
|
|
"step": 7970
|
|
},
|
|
{
|
|
"entropy": 5.191692924499511,
|
|
"epoch": 8.12124299541518,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 9.652399413008566e-05,
|
|
"loss": 4.351,
|
|
"mean_token_accuracy": 0.25736864656209946,
|
|
"num_tokens": 18797180.0,
|
|
"step": 7975
|
|
},
|
|
{
|
|
"entropy": 5.196920347213745,
|
|
"epoch": 8.126337238920021,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.627999602736068e-05,
|
|
"loss": 4.3811,
|
|
"mean_token_accuracy": 0.2556339502334595,
|
|
"num_tokens": 18808675.0,
|
|
"step": 7980
|
|
},
|
|
{
|
|
"entropy": 5.175684309005737,
|
|
"epoch": 8.13143148242486,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 9.603656607198863e-05,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.2571969136595726,
|
|
"num_tokens": 18819908.0,
|
|
"step": 7985
|
|
},
|
|
{
|
|
"entropy": 5.191578960418701,
|
|
"epoch": 8.1365257259297,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 9.579370503782856e-05,
|
|
"loss": 4.3251,
|
|
"mean_token_accuracy": 0.26136478781700134,
|
|
"num_tokens": 18831123.0,
|
|
"step": 7990
|
|
},
|
|
{
|
|
"entropy": 5.293052673339844,
|
|
"epoch": 8.141619969434538,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 9.55514136969309e-05,
|
|
"loss": 4.504,
|
|
"mean_token_accuracy": 0.24645178467035295,
|
|
"num_tokens": 18844133.0,
|
|
"step": 7995
|
|
},
|
|
{
|
|
"entropy": 5.234008264541626,
|
|
"epoch": 8.14671421293938,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.5309692819535e-05,
|
|
"loss": 4.497,
|
|
"mean_token_accuracy": 0.2448787659406662,
|
|
"num_tokens": 18856552.0,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 8.14671421293938,
|
|
"eval_entropy": 5.077100639578737,
|
|
"eval_loss": 5.594245433807373,
|
|
"eval_mean_token_accuracy": 0.18762290818087848,
|
|
"eval_num_tokens": 18856552.0,
|
|
"eval_runtime": 2.6345,
|
|
"eval_samples_per_second": 1229.835,
|
|
"eval_steps_per_second": 153.729,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"entropy": 5.207015895843506,
|
|
"epoch": 8.151808456444218,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 9.506854317406666e-05,
|
|
"loss": 4.3551,
|
|
"mean_token_accuracy": 0.2624026358127594,
|
|
"num_tokens": 18868102.0,
|
|
"step": 8005
|
|
},
|
|
{
|
|
"entropy": 5.265316534042358,
|
|
"epoch": 8.156902699949057,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.482796552713599e-05,
|
|
"loss": 4.4398,
|
|
"mean_token_accuracy": 0.2502106472849846,
|
|
"num_tokens": 18879411.0,
|
|
"step": 8010
|
|
},
|
|
{
|
|
"entropy": 5.199387788772583,
|
|
"epoch": 8.161996943453897,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 9.458796064353445e-05,
|
|
"loss": 4.3905,
|
|
"mean_token_accuracy": 0.2537953585386276,
|
|
"num_tokens": 18891393.0,
|
|
"step": 8015
|
|
},
|
|
{
|
|
"entropy": 5.1174558162689205,
|
|
"epoch": 8.167091186958737,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.434852928623286e-05,
|
|
"loss": 4.2726,
|
|
"mean_token_accuracy": 0.27895749658346175,
|
|
"num_tokens": 18902665.0,
|
|
"step": 8020
|
|
},
|
|
{
|
|
"entropy": 5.257316827774048,
|
|
"epoch": 8.172185430463577,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 9.410967221637876e-05,
|
|
"loss": 4.432,
|
|
"mean_token_accuracy": 0.2491871565580368,
|
|
"num_tokens": 18914467.0,
|
|
"step": 8025
|
|
},
|
|
{
|
|
"entropy": 5.1874229431152346,
|
|
"epoch": 8.177279673968416,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 9.387139019329403e-05,
|
|
"loss": 4.3909,
|
|
"mean_token_accuracy": 0.253550261259079,
|
|
"num_tokens": 18927134.0,
|
|
"step": 8030
|
|
},
|
|
{
|
|
"entropy": 5.200128221511841,
|
|
"epoch": 8.182373917473255,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 9.36336839744725e-05,
|
|
"loss": 4.373,
|
|
"mean_token_accuracy": 0.2592673569917679,
|
|
"num_tokens": 18939989.0,
|
|
"step": 8035
|
|
},
|
|
{
|
|
"entropy": 5.18563437461853,
|
|
"epoch": 8.187468160978094,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.339655431557747e-05,
|
|
"loss": 4.4395,
|
|
"mean_token_accuracy": 0.24771714955568314,
|
|
"num_tokens": 18952391.0,
|
|
"step": 8040
|
|
},
|
|
{
|
|
"entropy": 5.228435897827149,
|
|
"epoch": 8.192562404482935,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 9.316000197043957e-05,
|
|
"loss": 4.4036,
|
|
"mean_token_accuracy": 0.2570898786187172,
|
|
"num_tokens": 18963897.0,
|
|
"step": 8045
|
|
},
|
|
{
|
|
"entropy": 5.212658309936524,
|
|
"epoch": 8.197656647987774,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.292402769105392e-05,
|
|
"loss": 4.3827,
|
|
"mean_token_accuracy": 0.25598845183849334,
|
|
"num_tokens": 18975630.0,
|
|
"step": 8050
|
|
},
|
|
{
|
|
"entropy": 5.216674184799194,
|
|
"epoch": 8.202750891492613,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 9.268863222757812e-05,
|
|
"loss": 4.3553,
|
|
"mean_token_accuracy": 0.2646022617816925,
|
|
"num_tokens": 18987131.0,
|
|
"step": 8055
|
|
},
|
|
{
|
|
"entropy": 5.2022261142730715,
|
|
"epoch": 8.207845134997452,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.245381632832969e-05,
|
|
"loss": 4.4456,
|
|
"mean_token_accuracy": 0.24947960674762726,
|
|
"num_tokens": 18998681.0,
|
|
"step": 8060
|
|
},
|
|
{
|
|
"entropy": 5.210027360916138,
|
|
"epoch": 8.212939378502293,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 9.22195807397837e-05,
|
|
"loss": 4.4382,
|
|
"mean_token_accuracy": 0.2458454579114914,
|
|
"num_tokens": 19009919.0,
|
|
"step": 8065
|
|
},
|
|
{
|
|
"entropy": 5.289632415771484,
|
|
"epoch": 8.218033622007132,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 9.198592620657046e-05,
|
|
"loss": 4.5184,
|
|
"mean_token_accuracy": 0.2422059580683708,
|
|
"num_tokens": 19023047.0,
|
|
"step": 8070
|
|
},
|
|
{
|
|
"entropy": 5.1744935512542725,
|
|
"epoch": 8.223127865511971,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 9.175285347147306e-05,
|
|
"loss": 4.366,
|
|
"mean_token_accuracy": 0.26041876524686813,
|
|
"num_tokens": 19034605.0,
|
|
"step": 8075
|
|
},
|
|
{
|
|
"entropy": 5.282374715805053,
|
|
"epoch": 8.22822210901681,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 9.15203632754251e-05,
|
|
"loss": 4.5088,
|
|
"mean_token_accuracy": 0.2492244154214859,
|
|
"num_tokens": 19048211.0,
|
|
"step": 8080
|
|
},
|
|
{
|
|
"entropy": 5.294217205047607,
|
|
"epoch": 8.233316352521651,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 9.12884563575084e-05,
|
|
"loss": 4.457,
|
|
"mean_token_accuracy": 0.2438663884997368,
|
|
"num_tokens": 19059870.0,
|
|
"step": 8085
|
|
},
|
|
{
|
|
"entropy": 5.221915626525879,
|
|
"epoch": 8.23841059602649,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 9.105713345495042e-05,
|
|
"loss": 4.3667,
|
|
"mean_token_accuracy": 0.261153943836689,
|
|
"num_tokens": 19070097.0,
|
|
"step": 8090
|
|
},
|
|
{
|
|
"entropy": 5.2211943626403805,
|
|
"epoch": 8.24350483953133,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 9.082639530312209e-05,
|
|
"loss": 4.3948,
|
|
"mean_token_accuracy": 0.25964377373456954,
|
|
"num_tokens": 19081834.0,
|
|
"step": 8095
|
|
},
|
|
{
|
|
"entropy": 5.1546224594116214,
|
|
"epoch": 8.248599083036169,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 9.059624263553535e-05,
|
|
"loss": 4.3381,
|
|
"mean_token_accuracy": 0.2709822624921799,
|
|
"num_tokens": 19093653.0,
|
|
"step": 8100
|
|
},
|
|
{
|
|
"entropy": 5.210613203048706,
|
|
"epoch": 8.25369332654101,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 9.036667618384113e-05,
|
|
"loss": 4.3889,
|
|
"mean_token_accuracy": 0.26003829687833785,
|
|
"num_tokens": 19105451.0,
|
|
"step": 8105
|
|
},
|
|
{
|
|
"entropy": 5.193431425094604,
|
|
"epoch": 8.258787570045849,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 9.013769667782648e-05,
|
|
"loss": 4.4015,
|
|
"mean_token_accuracy": 0.2604737788438797,
|
|
"num_tokens": 19117420.0,
|
|
"step": 8110
|
|
},
|
|
{
|
|
"entropy": 5.225330400466919,
|
|
"epoch": 8.263881813550688,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.990930484541281e-05,
|
|
"loss": 4.4406,
|
|
"mean_token_accuracy": 0.24819042831659316,
|
|
"num_tokens": 19129880.0,
|
|
"step": 8115
|
|
},
|
|
{
|
|
"entropy": 5.199733448028565,
|
|
"epoch": 8.268976057055527,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 8.968150141265311e-05,
|
|
"loss": 4.4018,
|
|
"mean_token_accuracy": 0.2624943196773529,
|
|
"num_tokens": 19142368.0,
|
|
"step": 8120
|
|
},
|
|
{
|
|
"entropy": 5.290169382095337,
|
|
"epoch": 8.274070300560366,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.945428710373013e-05,
|
|
"loss": 4.5279,
|
|
"mean_token_accuracy": 0.24188842475414277,
|
|
"num_tokens": 19154753.0,
|
|
"step": 8125
|
|
},
|
|
{
|
|
"entropy": 5.170179796218872,
|
|
"epoch": 8.279164544065207,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.922766264095359e-05,
|
|
"loss": 4.3788,
|
|
"mean_token_accuracy": 0.2654466986656189,
|
|
"num_tokens": 19166733.0,
|
|
"step": 8130
|
|
},
|
|
{
|
|
"entropy": 5.253220891952514,
|
|
"epoch": 8.284258787570046,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 8.900162874475815e-05,
|
|
"loss": 4.488,
|
|
"mean_token_accuracy": 0.24881697744131087,
|
|
"num_tokens": 19179979.0,
|
|
"step": 8135
|
|
},
|
|
{
|
|
"entropy": 5.207594394683838,
|
|
"epoch": 8.289353031074885,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 8.877618613370105e-05,
|
|
"loss": 4.3343,
|
|
"mean_token_accuracy": 0.25855151414871214,
|
|
"num_tokens": 19191047.0,
|
|
"step": 8140
|
|
},
|
|
{
|
|
"entropy": 5.2722372055053714,
|
|
"epoch": 8.294447274579724,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 8.85513355244601e-05,
|
|
"loss": 4.4347,
|
|
"mean_token_accuracy": 0.25461510121822356,
|
|
"num_tokens": 19202277.0,
|
|
"step": 8145
|
|
},
|
|
{
|
|
"entropy": 5.220308017730713,
|
|
"epoch": 8.299541518084565,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 8.83270776318307e-05,
|
|
"loss": 4.4408,
|
|
"mean_token_accuracy": 0.2516616299748421,
|
|
"num_tokens": 19213697.0,
|
|
"step": 8150
|
|
},
|
|
{
|
|
"entropy": 5.22165699005127,
|
|
"epoch": 8.304635761589404,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 8.810341316872434e-05,
|
|
"loss": 4.4382,
|
|
"mean_token_accuracy": 0.25761224031448365,
|
|
"num_tokens": 19227095.0,
|
|
"step": 8155
|
|
},
|
|
{
|
|
"entropy": 5.225188970565796,
|
|
"epoch": 8.309730005094243,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.788034284616582e-05,
|
|
"loss": 4.4122,
|
|
"mean_token_accuracy": 0.2485600993037224,
|
|
"num_tokens": 19238631.0,
|
|
"step": 8160
|
|
},
|
|
{
|
|
"entropy": 5.242132902145386,
|
|
"epoch": 8.314824248599082,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.765786737329144e-05,
|
|
"loss": 4.4079,
|
|
"mean_token_accuracy": 0.25343666821718214,
|
|
"num_tokens": 19250242.0,
|
|
"step": 8165
|
|
},
|
|
{
|
|
"entropy": 5.271002912521363,
|
|
"epoch": 8.319918492103923,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 8.743598745734627e-05,
|
|
"loss": 4.4463,
|
|
"mean_token_accuracy": 0.2492522194981575,
|
|
"num_tokens": 19261626.0,
|
|
"step": 8170
|
|
},
|
|
{
|
|
"entropy": 5.246882629394531,
|
|
"epoch": 8.325012735608762,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 8.72147038036821e-05,
|
|
"loss": 4.4153,
|
|
"mean_token_accuracy": 0.25843764245510104,
|
|
"num_tokens": 19273232.0,
|
|
"step": 8175
|
|
},
|
|
{
|
|
"entropy": 5.220718908309936,
|
|
"epoch": 8.330106979113602,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 8.69940171157553e-05,
|
|
"loss": 4.3901,
|
|
"mean_token_accuracy": 0.2575685754418373,
|
|
"num_tokens": 19284252.0,
|
|
"step": 8180
|
|
},
|
|
{
|
|
"entropy": 5.250506830215454,
|
|
"epoch": 8.33520122261844,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 8.67739280951246e-05,
|
|
"loss": 4.4603,
|
|
"mean_token_accuracy": 0.2520360127091408,
|
|
"num_tokens": 19297523.0,
|
|
"step": 8185
|
|
},
|
|
{
|
|
"entropy": 5.2020790576934814,
|
|
"epoch": 8.340295466123282,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 8.65544374414485e-05,
|
|
"loss": 4.33,
|
|
"mean_token_accuracy": 0.2702233448624611,
|
|
"num_tokens": 19307557.0,
|
|
"step": 8190
|
|
},
|
|
{
|
|
"entropy": 5.182909250259399,
|
|
"epoch": 8.34538970962812,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 8.633554585248345e-05,
|
|
"loss": 4.4262,
|
|
"mean_token_accuracy": 0.2576553702354431,
|
|
"num_tokens": 19319877.0,
|
|
"step": 8195
|
|
},
|
|
{
|
|
"entropy": 5.233027362823487,
|
|
"epoch": 8.35048395313296,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 8.611725402408152e-05,
|
|
"loss": 4.3764,
|
|
"mean_token_accuracy": 0.26584427505731584,
|
|
"num_tokens": 19330992.0,
|
|
"step": 8200
|
|
},
|
|
{
|
|
"entropy": 5.166229772567749,
|
|
"epoch": 8.355578196637799,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 8.589956265018814e-05,
|
|
"loss": 4.3925,
|
|
"mean_token_accuracy": 0.25021439641714094,
|
|
"num_tokens": 19343903.0,
|
|
"step": 8205
|
|
},
|
|
{
|
|
"entropy": 5.126675319671631,
|
|
"epoch": 8.360672440142638,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.568247242283983e-05,
|
|
"loss": 4.3685,
|
|
"mean_token_accuracy": 0.25971196591854095,
|
|
"num_tokens": 19356765.0,
|
|
"step": 8210
|
|
},
|
|
{
|
|
"entropy": 5.19633903503418,
|
|
"epoch": 8.365766683647479,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 8.54659840321621e-05,
|
|
"loss": 4.3921,
|
|
"mean_token_accuracy": 0.25742596089839936,
|
|
"num_tokens": 19368306.0,
|
|
"step": 8215
|
|
},
|
|
{
|
|
"entropy": 5.244538068771362,
|
|
"epoch": 8.370860927152318,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.525009816636725e-05,
|
|
"loss": 4.434,
|
|
"mean_token_accuracy": 0.24999849796295165,
|
|
"num_tokens": 19379752.0,
|
|
"step": 8220
|
|
},
|
|
{
|
|
"entropy": 5.177130699157715,
|
|
"epoch": 8.375955170657157,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.503481551175232e-05,
|
|
"loss": 4.3704,
|
|
"mean_token_accuracy": 0.26247081607580186,
|
|
"num_tokens": 19391105.0,
|
|
"step": 8225
|
|
},
|
|
{
|
|
"entropy": 5.186350965499878,
|
|
"epoch": 8.381049414161996,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 8.482013675269645e-05,
|
|
"loss": 4.3351,
|
|
"mean_token_accuracy": 0.2650257840752602,
|
|
"num_tokens": 19401309.0,
|
|
"step": 8230
|
|
},
|
|
{
|
|
"entropy": 5.1940234184265135,
|
|
"epoch": 8.386143657666837,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 8.460606257165915e-05,
|
|
"loss": 4.3558,
|
|
"mean_token_accuracy": 0.25850729644298553,
|
|
"num_tokens": 19412746.0,
|
|
"step": 8235
|
|
},
|
|
{
|
|
"entropy": 5.212782859802246,
|
|
"epoch": 8.391237901171676,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 8.439259364917809e-05,
|
|
"loss": 4.4208,
|
|
"mean_token_accuracy": 0.25422161519527436,
|
|
"num_tokens": 19425285.0,
|
|
"step": 8240
|
|
},
|
|
{
|
|
"entropy": 5.265093183517456,
|
|
"epoch": 8.396332144676515,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.417973066386674e-05,
|
|
"loss": 4.4192,
|
|
"mean_token_accuracy": 0.25493681728839873,
|
|
"num_tokens": 19436243.0,
|
|
"step": 8245
|
|
},
|
|
{
|
|
"entropy": 5.169210052490234,
|
|
"epoch": 8.401426388181354,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 8.396747429241225e-05,
|
|
"loss": 4.3792,
|
|
"mean_token_accuracy": 0.25501230359077454,
|
|
"num_tokens": 19448618.0,
|
|
"step": 8250
|
|
},
|
|
{
|
|
"entropy": 5.242181968688965,
|
|
"epoch": 8.406520631686195,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.375582520957349e-05,
|
|
"loss": 4.4183,
|
|
"mean_token_accuracy": 0.25601886212825775,
|
|
"num_tokens": 19460129.0,
|
|
"step": 8255
|
|
},
|
|
{
|
|
"entropy": 5.204541349411011,
|
|
"epoch": 8.411614875191034,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 8.354478408817862e-05,
|
|
"loss": 4.3813,
|
|
"mean_token_accuracy": 0.2535302072763443,
|
|
"num_tokens": 19472294.0,
|
|
"step": 8260
|
|
},
|
|
{
|
|
"entropy": 5.216324090957642,
|
|
"epoch": 8.416709118695874,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 8.333435159912332e-05,
|
|
"loss": 4.4297,
|
|
"mean_token_accuracy": 0.2508873075246811,
|
|
"num_tokens": 19483558.0,
|
|
"step": 8265
|
|
},
|
|
{
|
|
"entropy": 5.1375635147094725,
|
|
"epoch": 8.421803362200713,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.31245284113682e-05,
|
|
"loss": 4.3647,
|
|
"mean_token_accuracy": 0.2533500105142593,
|
|
"num_tokens": 19495212.0,
|
|
"step": 8270
|
|
},
|
|
{
|
|
"entropy": 5.200586271286011,
|
|
"epoch": 8.426897605705554,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 8.291531519193695e-05,
|
|
"loss": 4.4046,
|
|
"mean_token_accuracy": 0.26348225176334383,
|
|
"num_tokens": 19506643.0,
|
|
"step": 8275
|
|
},
|
|
{
|
|
"entropy": 5.256568193435669,
|
|
"epoch": 8.431991849210393,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 8.270671260591445e-05,
|
|
"loss": 4.4401,
|
|
"mean_token_accuracy": 0.24926785826683046,
|
|
"num_tokens": 19518458.0,
|
|
"step": 8280
|
|
},
|
|
{
|
|
"entropy": 5.220511960983276,
|
|
"epoch": 8.437086092715232,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 8.249872131644404e-05,
|
|
"loss": 4.4123,
|
|
"mean_token_accuracy": 0.2528562664985657,
|
|
"num_tokens": 19529547.0,
|
|
"step": 8285
|
|
},
|
|
{
|
|
"entropy": 5.192099094390869,
|
|
"epoch": 8.442180336220071,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 8.229134198472593e-05,
|
|
"loss": 4.4275,
|
|
"mean_token_accuracy": 0.25550498217344286,
|
|
"num_tokens": 19541498.0,
|
|
"step": 8290
|
|
},
|
|
{
|
|
"entropy": 5.195864725112915,
|
|
"epoch": 8.44727457972491,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 8.208457527001493e-05,
|
|
"loss": 4.4154,
|
|
"mean_token_accuracy": 0.2491795986890793,
|
|
"num_tokens": 19552569.0,
|
|
"step": 8295
|
|
},
|
|
{
|
|
"entropy": 5.172547483444214,
|
|
"epoch": 8.452368823229751,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 8.187842182961836e-05,
|
|
"loss": 4.3719,
|
|
"mean_token_accuracy": 0.26341812014579774,
|
|
"num_tokens": 19565061.0,
|
|
"step": 8300
|
|
},
|
|
{
|
|
"entropy": 5.233201599121093,
|
|
"epoch": 8.45746306673459,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 8.167288231889394e-05,
|
|
"loss": 4.3642,
|
|
"mean_token_accuracy": 0.26251173913478854,
|
|
"num_tokens": 19576057.0,
|
|
"step": 8305
|
|
},
|
|
{
|
|
"entropy": 5.224852275848389,
|
|
"epoch": 8.46255731023943,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 8.14679573912476e-05,
|
|
"loss": 4.4765,
|
|
"mean_token_accuracy": 0.2521491631865501,
|
|
"num_tokens": 19587388.0,
|
|
"step": 8310
|
|
},
|
|
{
|
|
"entropy": 5.152918481826783,
|
|
"epoch": 8.467651553744268,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 8.126364769813163e-05,
|
|
"loss": 4.353,
|
|
"mean_token_accuracy": 0.26177607774734496,
|
|
"num_tokens": 19598856.0,
|
|
"step": 8315
|
|
},
|
|
{
|
|
"entropy": 5.205292415618897,
|
|
"epoch": 8.47274579724911,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 8.105995388904262e-05,
|
|
"loss": 4.3888,
|
|
"mean_token_accuracy": 0.2590299710631371,
|
|
"num_tokens": 19608923.0,
|
|
"step": 8320
|
|
},
|
|
{
|
|
"entropy": 5.2323511123657225,
|
|
"epoch": 8.477840040753948,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.085687661151905e-05,
|
|
"loss": 4.4275,
|
|
"mean_token_accuracy": 0.252460615336895,
|
|
"num_tokens": 19620780.0,
|
|
"step": 8325
|
|
},
|
|
{
|
|
"entropy": 5.257882738113404,
|
|
"epoch": 8.482934284258787,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 8.065441651113964e-05,
|
|
"loss": 4.498,
|
|
"mean_token_accuracy": 0.2509799897670746,
|
|
"num_tokens": 19633926.0,
|
|
"step": 8330
|
|
},
|
|
{
|
|
"entropy": 5.201118421554566,
|
|
"epoch": 8.488028527763626,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 8.045257423152094e-05,
|
|
"loss": 4.358,
|
|
"mean_token_accuracy": 0.25993348360061647,
|
|
"num_tokens": 19645069.0,
|
|
"step": 8335
|
|
},
|
|
{
|
|
"entropy": 5.194742870330811,
|
|
"epoch": 8.493122771268467,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 8.025135041431566e-05,
|
|
"loss": 4.3293,
|
|
"mean_token_accuracy": 0.2655282557010651,
|
|
"num_tokens": 19655981.0,
|
|
"step": 8340
|
|
},
|
|
{
|
|
"entropy": 5.2534592628479,
|
|
"epoch": 8.498217014773306,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 8.005074569921037e-05,
|
|
"loss": 4.4438,
|
|
"mean_token_accuracy": 0.25254461616277696,
|
|
"num_tokens": 19667490.0,
|
|
"step": 8345
|
|
},
|
|
{
|
|
"entropy": 5.187024211883545,
|
|
"epoch": 8.503311258278146,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.985076072392328e-05,
|
|
"loss": 4.3592,
|
|
"mean_token_accuracy": 0.2677153617143631,
|
|
"num_tokens": 19679947.0,
|
|
"step": 8350
|
|
},
|
|
{
|
|
"entropy": 5.232099199295044,
|
|
"epoch": 8.508405501782985,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.965139612420283e-05,
|
|
"loss": 4.4113,
|
|
"mean_token_accuracy": 0.25496979653835294,
|
|
"num_tokens": 19692287.0,
|
|
"step": 8355
|
|
},
|
|
{
|
|
"entropy": 5.156962537765503,
|
|
"epoch": 8.513499745287824,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 7.945265253382508e-05,
|
|
"loss": 4.3706,
|
|
"mean_token_accuracy": 0.2595013365149498,
|
|
"num_tokens": 19702805.0,
|
|
"step": 8360
|
|
},
|
|
{
|
|
"entropy": 5.264308595657349,
|
|
"epoch": 8.518593988792665,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 7.925453058459199e-05,
|
|
"loss": 4.429,
|
|
"mean_token_accuracy": 0.25389222949743273,
|
|
"num_tokens": 19713612.0,
|
|
"step": 8365
|
|
},
|
|
{
|
|
"entropy": 5.1207071304321286,
|
|
"epoch": 8.523688232297504,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.905703090632933e-05,
|
|
"loss": 4.3525,
|
|
"mean_token_accuracy": 0.2580442577600479,
|
|
"num_tokens": 19724595.0,
|
|
"step": 8370
|
|
},
|
|
{
|
|
"entropy": 5.2373316287994385,
|
|
"epoch": 8.528782475802343,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.886015412688458e-05,
|
|
"loss": 4.4142,
|
|
"mean_token_accuracy": 0.25091210901737215,
|
|
"num_tokens": 19735249.0,
|
|
"step": 8375
|
|
},
|
|
{
|
|
"entropy": 5.248967170715332,
|
|
"epoch": 8.533876719307182,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.866390087212523e-05,
|
|
"loss": 4.4907,
|
|
"mean_token_accuracy": 0.2485371023416519,
|
|
"num_tokens": 19747309.0,
|
|
"step": 8380
|
|
},
|
|
{
|
|
"entropy": 5.250783443450928,
|
|
"epoch": 8.538970962812023,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 7.846827176593649e-05,
|
|
"loss": 4.4656,
|
|
"mean_token_accuracy": 0.2514189913868904,
|
|
"num_tokens": 19759331.0,
|
|
"step": 8385
|
|
},
|
|
{
|
|
"entropy": 5.269998550415039,
|
|
"epoch": 8.544065206316862,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.827326743021925e-05,
|
|
"loss": 4.4875,
|
|
"mean_token_accuracy": 0.2486674889922142,
|
|
"num_tokens": 19772869.0,
|
|
"step": 8390
|
|
},
|
|
{
|
|
"entropy": 5.159806776046753,
|
|
"epoch": 8.549159449821701,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 7.807888848488861e-05,
|
|
"loss": 4.3618,
|
|
"mean_token_accuracy": 0.2583601847290993,
|
|
"num_tokens": 19784332.0,
|
|
"step": 8395
|
|
},
|
|
{
|
|
"entropy": 5.249140501022339,
|
|
"epoch": 8.55425369332654,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.788513554787133e-05,
|
|
"loss": 4.4784,
|
|
"mean_token_accuracy": 0.24726563394069673,
|
|
"num_tokens": 19797522.0,
|
|
"step": 8400
|
|
},
|
|
{
|
|
"entropy": 5.229262113571167,
|
|
"epoch": 8.559347936831381,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.769200923510415e-05,
|
|
"loss": 4.3877,
|
|
"mean_token_accuracy": 0.2608815297484398,
|
|
"num_tokens": 19808274.0,
|
|
"step": 8405
|
|
},
|
|
{
|
|
"entropy": 5.20469856262207,
|
|
"epoch": 8.56444218033622,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 7.749951016053179e-05,
|
|
"loss": 4.399,
|
|
"mean_token_accuracy": 0.2575840547680855,
|
|
"num_tokens": 19819283.0,
|
|
"step": 8410
|
|
},
|
|
{
|
|
"entropy": 5.1712666034698485,
|
|
"epoch": 8.56953642384106,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.730763893610498e-05,
|
|
"loss": 4.3637,
|
|
"mean_token_accuracy": 0.26191810369491575,
|
|
"num_tokens": 19831814.0,
|
|
"step": 8415
|
|
},
|
|
{
|
|
"entropy": 5.235497760772705,
|
|
"epoch": 8.574630667345899,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 7.711639617177857e-05,
|
|
"loss": 4.437,
|
|
"mean_token_accuracy": 0.259568390250206,
|
|
"num_tokens": 19844157.0,
|
|
"step": 8420
|
|
},
|
|
{
|
|
"entropy": 5.213024568557739,
|
|
"epoch": 8.57972491085074,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 7.692578247550957e-05,
|
|
"loss": 4.3877,
|
|
"mean_token_accuracy": 0.25871473401784895,
|
|
"num_tokens": 19855267.0,
|
|
"step": 8425
|
|
},
|
|
{
|
|
"entropy": 5.19557933807373,
|
|
"epoch": 8.584819154355579,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 7.673579845325503e-05,
|
|
"loss": 4.3105,
|
|
"mean_token_accuracy": 0.26077857464551923,
|
|
"num_tokens": 19866220.0,
|
|
"step": 8430
|
|
},
|
|
{
|
|
"entropy": 5.305164003372193,
|
|
"epoch": 8.589913397860418,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.654644470897048e-05,
|
|
"loss": 4.494,
|
|
"mean_token_accuracy": 0.23968929946422576,
|
|
"num_tokens": 19878802.0,
|
|
"step": 8435
|
|
},
|
|
{
|
|
"entropy": 5.160498857498169,
|
|
"epoch": 8.595007641365257,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.63577218446077e-05,
|
|
"loss": 4.3239,
|
|
"mean_token_accuracy": 0.2617769479751587,
|
|
"num_tokens": 19889685.0,
|
|
"step": 8440
|
|
},
|
|
{
|
|
"entropy": 5.20502290725708,
|
|
"epoch": 8.600101884870096,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.616963046011292e-05,
|
|
"loss": 4.4253,
|
|
"mean_token_accuracy": 0.2513566493988037,
|
|
"num_tokens": 19901539.0,
|
|
"step": 8445
|
|
},
|
|
{
|
|
"entropy": 5.203465270996094,
|
|
"epoch": 8.605196128374937,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.598217115342492e-05,
|
|
"loss": 4.4235,
|
|
"mean_token_accuracy": 0.26214692294597625,
|
|
"num_tokens": 19913917.0,
|
|
"step": 8450
|
|
},
|
|
{
|
|
"entropy": 5.201966190338135,
|
|
"epoch": 8.610290371879776,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.579534452047319e-05,
|
|
"loss": 4.3937,
|
|
"mean_token_accuracy": 0.256053526699543,
|
|
"num_tokens": 19923770.0,
|
|
"step": 8455
|
|
},
|
|
{
|
|
"entropy": 5.2600280284881595,
|
|
"epoch": 8.615384615384615,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.560915115517583e-05,
|
|
"loss": 4.4885,
|
|
"mean_token_accuracy": 0.2437465414404869,
|
|
"num_tokens": 19936904.0,
|
|
"step": 8460
|
|
},
|
|
{
|
|
"entropy": 5.234633159637451,
|
|
"epoch": 8.620478858889454,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 7.542359164943794e-05,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.26338472217321396,
|
|
"num_tokens": 19948765.0,
|
|
"step": 8465
|
|
},
|
|
{
|
|
"entropy": 5.201424026489258,
|
|
"epoch": 8.625573102394295,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.523866659314936e-05,
|
|
"loss": 4.3823,
|
|
"mean_token_accuracy": 0.2566379100084305,
|
|
"num_tokens": 19960886.0,
|
|
"step": 8470
|
|
},
|
|
{
|
|
"entropy": 5.25702223777771,
|
|
"epoch": 8.630667345899134,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 7.505437657418331e-05,
|
|
"loss": 4.4734,
|
|
"mean_token_accuracy": 0.24782723784446717,
|
|
"num_tokens": 19973008.0,
|
|
"step": 8475
|
|
},
|
|
{
|
|
"entropy": 5.1704038143157955,
|
|
"epoch": 8.635761589403973,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 7.487072217839408e-05,
|
|
"loss": 4.3615,
|
|
"mean_token_accuracy": 0.25538657456636427,
|
|
"num_tokens": 19984457.0,
|
|
"step": 8480
|
|
},
|
|
{
|
|
"entropy": 5.1929600715637205,
|
|
"epoch": 8.640855832908812,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.468770398961537e-05,
|
|
"loss": 4.4091,
|
|
"mean_token_accuracy": 0.25644245445728303,
|
|
"num_tokens": 19997029.0,
|
|
"step": 8485
|
|
},
|
|
{
|
|
"entropy": 5.205749607086181,
|
|
"epoch": 8.645950076413653,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.450532258965828e-05,
|
|
"loss": 4.3737,
|
|
"mean_token_accuracy": 0.2573028042912483,
|
|
"num_tokens": 20010066.0,
|
|
"step": 8490
|
|
},
|
|
{
|
|
"entropy": 5.208020639419556,
|
|
"epoch": 8.651044319918492,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 7.432357855830985e-05,
|
|
"loss": 4.4402,
|
|
"mean_token_accuracy": 0.25854917913675307,
|
|
"num_tokens": 20022374.0,
|
|
"step": 8495
|
|
},
|
|
{
|
|
"entropy": 5.250616407394409,
|
|
"epoch": 8.656138563423331,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 7.41424724733306e-05,
|
|
"loss": 4.5053,
|
|
"mean_token_accuracy": 0.2470548316836357,
|
|
"num_tokens": 20035474.0,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"entropy": 5.256374931335449,
|
|
"epoch": 8.66123280692817,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.39620049104533e-05,
|
|
"loss": 4.4374,
|
|
"mean_token_accuracy": 0.25193609297275543,
|
|
"num_tokens": 20048593.0,
|
|
"step": 8505
|
|
},
|
|
{
|
|
"entropy": 5.206871747970581,
|
|
"epoch": 8.666327050433011,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.378217644338065e-05,
|
|
"loss": 4.4361,
|
|
"mean_token_accuracy": 0.2574691414833069,
|
|
"num_tokens": 20059672.0,
|
|
"step": 8510
|
|
},
|
|
{
|
|
"entropy": 5.192845630645752,
|
|
"epoch": 8.67142129393785,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 7.360298764378383e-05,
|
|
"loss": 4.3758,
|
|
"mean_token_accuracy": 0.26650281697511674,
|
|
"num_tokens": 20071167.0,
|
|
"step": 8515
|
|
},
|
|
{
|
|
"entropy": 5.2097734928131105,
|
|
"epoch": 8.67651553744269,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.34244390813005e-05,
|
|
"loss": 4.3695,
|
|
"mean_token_accuracy": 0.262425471842289,
|
|
"num_tokens": 20083898.0,
|
|
"step": 8520
|
|
},
|
|
{
|
|
"entropy": 5.231379079818725,
|
|
"epoch": 8.681609780947529,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 7.3246531323533e-05,
|
|
"loss": 4.4677,
|
|
"mean_token_accuracy": 0.24699113219976426,
|
|
"num_tokens": 20097467.0,
|
|
"step": 8525
|
|
},
|
|
{
|
|
"entropy": 5.159650564193726,
|
|
"epoch": 8.686704024452368,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 7.306926493604653e-05,
|
|
"loss": 4.3456,
|
|
"mean_token_accuracy": 0.26225638687610625,
|
|
"num_tokens": 20109157.0,
|
|
"step": 8530
|
|
},
|
|
{
|
|
"entropy": 5.269064903259277,
|
|
"epoch": 8.691798267957209,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 7.289264048236749e-05,
|
|
"loss": 4.4757,
|
|
"mean_token_accuracy": 0.25061369985342025,
|
|
"num_tokens": 20121356.0,
|
|
"step": 8535
|
|
},
|
|
{
|
|
"entropy": 5.271158456802368,
|
|
"epoch": 8.696892511462048,
|
|
"grad_norm": 1.15625,
|
|
"learning_rate": 7.271665852398149e-05,
|
|
"loss": 4.4959,
|
|
"mean_token_accuracy": 0.24603502154350282,
|
|
"num_tokens": 20134312.0,
|
|
"step": 8540
|
|
},
|
|
{
|
|
"entropy": 5.182823133468628,
|
|
"epoch": 8.701986754966887,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.254131962033168e-05,
|
|
"loss": 4.3894,
|
|
"mean_token_accuracy": 0.25573298186063764,
|
|
"num_tokens": 20145958.0,
|
|
"step": 8545
|
|
},
|
|
{
|
|
"entropy": 5.194972038269043,
|
|
"epoch": 8.707080998471726,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 7.236662432881696e-05,
|
|
"loss": 4.4263,
|
|
"mean_token_accuracy": 0.2578968614339828,
|
|
"num_tokens": 20157829.0,
|
|
"step": 8550
|
|
},
|
|
{
|
|
"entropy": 5.203566217422486,
|
|
"epoch": 8.712175241976567,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.219257320479024e-05,
|
|
"loss": 4.3923,
|
|
"mean_token_accuracy": 0.25162970274686813,
|
|
"num_tokens": 20169255.0,
|
|
"step": 8555
|
|
},
|
|
{
|
|
"entropy": 5.220033407211304,
|
|
"epoch": 8.717269485481406,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 7.201916680155657e-05,
|
|
"loss": 4.4428,
|
|
"mean_token_accuracy": 0.256075419485569,
|
|
"num_tokens": 20181691.0,
|
|
"step": 8560
|
|
},
|
|
{
|
|
"entropy": 5.235145902633667,
|
|
"epoch": 8.722363728986245,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 7.184640567037143e-05,
|
|
"loss": 4.4302,
|
|
"mean_token_accuracy": 0.25249173790216445,
|
|
"num_tokens": 20193587.0,
|
|
"step": 8565
|
|
},
|
|
{
|
|
"entropy": 5.194381189346314,
|
|
"epoch": 8.727457972491084,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 7.167429036043907e-05,
|
|
"loss": 4.4172,
|
|
"mean_token_accuracy": 0.258729949593544,
|
|
"num_tokens": 20204631.0,
|
|
"step": 8570
|
|
},
|
|
{
|
|
"entropy": 5.24463996887207,
|
|
"epoch": 8.732552215995925,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.150282141891068e-05,
|
|
"loss": 4.4054,
|
|
"mean_token_accuracy": 0.2555371105670929,
|
|
"num_tokens": 20215446.0,
|
|
"step": 8575
|
|
},
|
|
{
|
|
"entropy": 5.2477418899536135,
|
|
"epoch": 8.737646459500764,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 7.133199939088262e-05,
|
|
"loss": 4.4538,
|
|
"mean_token_accuracy": 0.2508231684565544,
|
|
"num_tokens": 20227898.0,
|
|
"step": 8580
|
|
},
|
|
{
|
|
"entropy": 5.185159063339233,
|
|
"epoch": 8.742740703005603,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 7.116182481939467e-05,
|
|
"loss": 4.3307,
|
|
"mean_token_accuracy": 0.25671042650938036,
|
|
"num_tokens": 20237665.0,
|
|
"step": 8585
|
|
},
|
|
{
|
|
"entropy": 5.2588643550872805,
|
|
"epoch": 8.747834946510443,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 7.099229824542852e-05,
|
|
"loss": 4.4628,
|
|
"mean_token_accuracy": 0.24181690216064453,
|
|
"num_tokens": 20249735.0,
|
|
"step": 8590
|
|
},
|
|
{
|
|
"entropy": 5.259453916549683,
|
|
"epoch": 8.752929190015283,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.082342020790573e-05,
|
|
"loss": 4.4097,
|
|
"mean_token_accuracy": 0.25679154992103576,
|
|
"num_tokens": 20262084.0,
|
|
"step": 8595
|
|
},
|
|
{
|
|
"entropy": 5.25430703163147,
|
|
"epoch": 8.758023433520123,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 7.065519124368625e-05,
|
|
"loss": 4.4353,
|
|
"mean_token_accuracy": 0.25579536259174346,
|
|
"num_tokens": 20272964.0,
|
|
"step": 8600
|
|
},
|
|
{
|
|
"entropy": 5.2043647289276125,
|
|
"epoch": 8.763117677024962,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.048761188756654e-05,
|
|
"loss": 4.3512,
|
|
"mean_token_accuracy": 0.26086242496967316,
|
|
"num_tokens": 20283007.0,
|
|
"step": 8605
|
|
},
|
|
{
|
|
"entropy": 5.234430932998658,
|
|
"epoch": 8.7682119205298,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 7.032068267227822e-05,
|
|
"loss": 4.4049,
|
|
"mean_token_accuracy": 0.24884989261627197,
|
|
"num_tokens": 20293589.0,
|
|
"step": 8610
|
|
},
|
|
{
|
|
"entropy": 5.251255035400391,
|
|
"epoch": 8.77330616403464,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 7.015440412848586e-05,
|
|
"loss": 4.4009,
|
|
"mean_token_accuracy": 0.2616489797830582,
|
|
"num_tokens": 20304607.0,
|
|
"step": 8615
|
|
},
|
|
{
|
|
"entropy": 5.199900150299072,
|
|
"epoch": 8.77840040753948,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.99887767847857e-05,
|
|
"loss": 4.4364,
|
|
"mean_token_accuracy": 0.24797792136669158,
|
|
"num_tokens": 20316420.0,
|
|
"step": 8620
|
|
},
|
|
{
|
|
"entropy": 5.227585315704346,
|
|
"epoch": 8.78349465104432,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.982380116770374e-05,
|
|
"loss": 4.4239,
|
|
"mean_token_accuracy": 0.25665908604860305,
|
|
"num_tokens": 20327341.0,
|
|
"step": 8625
|
|
},
|
|
{
|
|
"entropy": 5.203475618362427,
|
|
"epoch": 8.788588894549159,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.965947780169421e-05,
|
|
"loss": 4.3961,
|
|
"mean_token_accuracy": 0.25500279664993286,
|
|
"num_tokens": 20339813.0,
|
|
"step": 8630
|
|
},
|
|
{
|
|
"entropy": 5.224259233474731,
|
|
"epoch": 8.793683138053998,
|
|
"grad_norm": 1.4765625,
|
|
"learning_rate": 6.949580720913785e-05,
|
|
"loss": 4.4239,
|
|
"mean_token_accuracy": 0.25127229690551756,
|
|
"num_tokens": 20350466.0,
|
|
"step": 8635
|
|
},
|
|
{
|
|
"entropy": 5.252585172653198,
|
|
"epoch": 8.798777381558839,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.933278991034024e-05,
|
|
"loss": 4.3692,
|
|
"mean_token_accuracy": 0.2550459817051888,
|
|
"num_tokens": 20361032.0,
|
|
"step": 8640
|
|
},
|
|
{
|
|
"entropy": 5.200505876541138,
|
|
"epoch": 8.803871625063678,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.917042642353008e-05,
|
|
"loss": 4.4385,
|
|
"mean_token_accuracy": 0.25515947192907334,
|
|
"num_tokens": 20373537.0,
|
|
"step": 8645
|
|
},
|
|
{
|
|
"entropy": 5.1498736381530765,
|
|
"epoch": 8.808965868568517,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.900871726485777e-05,
|
|
"loss": 4.3256,
|
|
"mean_token_accuracy": 0.27054002583026887,
|
|
"num_tokens": 20383479.0,
|
|
"step": 8650
|
|
},
|
|
{
|
|
"entropy": 5.127578067779541,
|
|
"epoch": 8.814060112073356,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.884766294839347e-05,
|
|
"loss": 4.351,
|
|
"mean_token_accuracy": 0.2648137599229813,
|
|
"num_tokens": 20396073.0,
|
|
"step": 8655
|
|
},
|
|
{
|
|
"entropy": 5.232300043106079,
|
|
"epoch": 8.819154355578197,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.868726398612569e-05,
|
|
"loss": 4.4672,
|
|
"mean_token_accuracy": 0.25189497172832487,
|
|
"num_tokens": 20407104.0,
|
|
"step": 8660
|
|
},
|
|
{
|
|
"entropy": 5.234809303283692,
|
|
"epoch": 8.824248599083036,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.852752088795952e-05,
|
|
"loss": 4.3701,
|
|
"mean_token_accuracy": 0.25457704812288284,
|
|
"num_tokens": 20418783.0,
|
|
"step": 8665
|
|
},
|
|
{
|
|
"entropy": 5.232605075836181,
|
|
"epoch": 8.829342842587875,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.836843416171513e-05,
|
|
"loss": 4.4571,
|
|
"mean_token_accuracy": 0.25719336569309237,
|
|
"num_tokens": 20431161.0,
|
|
"step": 8670
|
|
},
|
|
{
|
|
"entropy": 5.233617210388184,
|
|
"epoch": 8.834437086092715,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.821000431312607e-05,
|
|
"loss": 4.4262,
|
|
"mean_token_accuracy": 0.24919672459363937,
|
|
"num_tokens": 20442432.0,
|
|
"step": 8675
|
|
},
|
|
{
|
|
"entropy": 5.194341039657592,
|
|
"epoch": 8.839531329597555,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.805223184583771e-05,
|
|
"loss": 4.3877,
|
|
"mean_token_accuracy": 0.25854365676641466,
|
|
"num_tokens": 20454052.0,
|
|
"step": 8680
|
|
},
|
|
{
|
|
"entropy": 5.225655460357666,
|
|
"epoch": 8.844625573102395,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 6.789511726140551e-05,
|
|
"loss": 4.4262,
|
|
"mean_token_accuracy": 0.25493750274181365,
|
|
"num_tokens": 20466019.0,
|
|
"step": 8685
|
|
},
|
|
{
|
|
"entropy": 5.258459377288818,
|
|
"epoch": 8.849719816607234,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 6.773866105929373e-05,
|
|
"loss": 4.4371,
|
|
"mean_token_accuracy": 0.24877557903528214,
|
|
"num_tokens": 20477554.0,
|
|
"step": 8690
|
|
},
|
|
{
|
|
"entropy": 5.154375696182251,
|
|
"epoch": 8.854814060112073,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 6.75828637368735e-05,
|
|
"loss": 4.3334,
|
|
"mean_token_accuracy": 0.2684327602386475,
|
|
"num_tokens": 20490833.0,
|
|
"step": 8695
|
|
},
|
|
{
|
|
"entropy": 5.214060974121094,
|
|
"epoch": 8.859908303616912,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.742772578942143e-05,
|
|
"loss": 4.353,
|
|
"mean_token_accuracy": 0.26347709000110625,
|
|
"num_tokens": 20502398.0,
|
|
"step": 8700
|
|
},
|
|
{
|
|
"entropy": 5.193084049224853,
|
|
"epoch": 8.865002547121753,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.727324771011795e-05,
|
|
"loss": 4.4137,
|
|
"mean_token_accuracy": 0.25194750130176546,
|
|
"num_tokens": 20513955.0,
|
|
"step": 8705
|
|
},
|
|
{
|
|
"entropy": 5.139570665359497,
|
|
"epoch": 8.870096790626592,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.711942999004583e-05,
|
|
"loss": 4.3475,
|
|
"mean_token_accuracy": 0.26415534019470216,
|
|
"num_tokens": 20525862.0,
|
|
"step": 8710
|
|
},
|
|
{
|
|
"entropy": 5.098649692535401,
|
|
"epoch": 8.875191034131431,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.696627311818858e-05,
|
|
"loss": 4.3156,
|
|
"mean_token_accuracy": 0.2634911581873894,
|
|
"num_tokens": 20536354.0,
|
|
"step": 8715
|
|
},
|
|
{
|
|
"entropy": 5.227933931350708,
|
|
"epoch": 8.880285277636272,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.681377758142884e-05,
|
|
"loss": 4.432,
|
|
"mean_token_accuracy": 0.24913150519132615,
|
|
"num_tokens": 20547353.0,
|
|
"step": 8720
|
|
},
|
|
{
|
|
"entropy": 5.2130800724029545,
|
|
"epoch": 8.885379521141111,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 6.666194386454684e-05,
|
|
"loss": 4.4101,
|
|
"mean_token_accuracy": 0.2656326413154602,
|
|
"num_tokens": 20559839.0,
|
|
"step": 8725
|
|
},
|
|
{
|
|
"entropy": 5.210846281051635,
|
|
"epoch": 8.89047376464595,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.651077245021909e-05,
|
|
"loss": 4.4163,
|
|
"mean_token_accuracy": 0.25699454843997954,
|
|
"num_tokens": 20570531.0,
|
|
"step": 8730
|
|
},
|
|
{
|
|
"entropy": 5.226452970504761,
|
|
"epoch": 8.89556800815079,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.636026381901643e-05,
|
|
"loss": 4.4686,
|
|
"mean_token_accuracy": 0.24565807729959488,
|
|
"num_tokens": 20582756.0,
|
|
"step": 8735
|
|
},
|
|
{
|
|
"entropy": 5.237590694427491,
|
|
"epoch": 8.900662251655628,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 6.621041844940287e-05,
|
|
"loss": 4.4345,
|
|
"mean_token_accuracy": 0.25013113468885423,
|
|
"num_tokens": 20593746.0,
|
|
"step": 8740
|
|
},
|
|
{
|
|
"entropy": 5.216076183319092,
|
|
"epoch": 8.90575649516047,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.60612368177338e-05,
|
|
"loss": 4.4229,
|
|
"mean_token_accuracy": 0.255722650885582,
|
|
"num_tokens": 20605373.0,
|
|
"step": 8745
|
|
},
|
|
{
|
|
"entropy": 5.17930121421814,
|
|
"epoch": 8.910850738665308,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.591271939825477e-05,
|
|
"loss": 4.3049,
|
|
"mean_token_accuracy": 0.26837404519319535,
|
|
"num_tokens": 20616513.0,
|
|
"step": 8750
|
|
},
|
|
{
|
|
"entropy": 5.235896873474121,
|
|
"epoch": 8.915944982170148,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.576486666309962e-05,
|
|
"loss": 4.4845,
|
|
"mean_token_accuracy": 0.24385268688201905,
|
|
"num_tokens": 20628412.0,
|
|
"step": 8755
|
|
},
|
|
{
|
|
"entropy": 5.227724409103393,
|
|
"epoch": 8.921039225674987,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 6.561767908228934e-05,
|
|
"loss": 4.4348,
|
|
"mean_token_accuracy": 0.24813160449266433,
|
|
"num_tokens": 20640633.0,
|
|
"step": 8760
|
|
},
|
|
{
|
|
"entropy": 5.1378415584564205,
|
|
"epoch": 8.926133469179828,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 6.547115712373024e-05,
|
|
"loss": 4.2553,
|
|
"mean_token_accuracy": 0.2753877818584442,
|
|
"num_tokens": 20652397.0,
|
|
"step": 8765
|
|
},
|
|
{
|
|
"entropy": 5.218485021591187,
|
|
"epoch": 8.931227712684667,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 6.532530125321283e-05,
|
|
"loss": 4.4242,
|
|
"mean_token_accuracy": 0.2511327341198921,
|
|
"num_tokens": 20663666.0,
|
|
"step": 8770
|
|
},
|
|
{
|
|
"entropy": 5.171006441116333,
|
|
"epoch": 8.936321956189506,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 6.518011193440999e-05,
|
|
"loss": 4.3672,
|
|
"mean_token_accuracy": 0.265215790271759,
|
|
"num_tokens": 20676255.0,
|
|
"step": 8775
|
|
},
|
|
{
|
|
"entropy": 5.178696060180664,
|
|
"epoch": 8.941416199694345,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.50355896288757e-05,
|
|
"loss": 4.2997,
|
|
"mean_token_accuracy": 0.25909541696310046,
|
|
"num_tokens": 20686655.0,
|
|
"step": 8780
|
|
},
|
|
{
|
|
"entropy": 5.130416917800903,
|
|
"epoch": 8.946510443199184,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 6.489173479604351e-05,
|
|
"loss": 4.3447,
|
|
"mean_token_accuracy": 0.2604434430599213,
|
|
"num_tokens": 20698120.0,
|
|
"step": 8785
|
|
},
|
|
{
|
|
"entropy": 5.1892250061035154,
|
|
"epoch": 8.951604686704025,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.474854789322504e-05,
|
|
"loss": 4.315,
|
|
"mean_token_accuracy": 0.2649980843067169,
|
|
"num_tokens": 20709971.0,
|
|
"step": 8790
|
|
},
|
|
{
|
|
"entropy": 5.176808595657349,
|
|
"epoch": 8.956698930208864,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.460602937560866e-05,
|
|
"loss": 4.4277,
|
|
"mean_token_accuracy": 0.25308414548635483,
|
|
"num_tokens": 20722280.0,
|
|
"step": 8795
|
|
},
|
|
{
|
|
"entropy": 5.230150413513184,
|
|
"epoch": 8.961793173713703,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 6.446417969625789e-05,
|
|
"loss": 4.4739,
|
|
"mean_token_accuracy": 0.24796498715877532,
|
|
"num_tokens": 20734563.0,
|
|
"step": 8800
|
|
},
|
|
{
|
|
"entropy": 5.171231031417847,
|
|
"epoch": 8.966887417218544,
|
|
"grad_norm": 1.46875,
|
|
"learning_rate": 6.432299930611005e-05,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.2597656473517418,
|
|
"num_tokens": 20746781.0,
|
|
"step": 8805
|
|
},
|
|
{
|
|
"entropy": 5.164869737625122,
|
|
"epoch": 8.971981660723383,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.418248865397487e-05,
|
|
"loss": 4.4069,
|
|
"mean_token_accuracy": 0.2585511773824692,
|
|
"num_tokens": 20759133.0,
|
|
"step": 8810
|
|
},
|
|
{
|
|
"entropy": 5.165286874771118,
|
|
"epoch": 8.977075904228222,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.404264818653287e-05,
|
|
"loss": 4.3572,
|
|
"mean_token_accuracy": 0.2637692093849182,
|
|
"num_tokens": 20770118.0,
|
|
"step": 8815
|
|
},
|
|
{
|
|
"entropy": 5.198671817779541,
|
|
"epoch": 8.982170147733061,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 6.390347834833413e-05,
|
|
"loss": 4.5057,
|
|
"mean_token_accuracy": 0.24540615677833558,
|
|
"num_tokens": 20783129.0,
|
|
"step": 8820
|
|
},
|
|
{
|
|
"entropy": 5.2210746765136715,
|
|
"epoch": 8.9872643912379,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 6.37649795817968e-05,
|
|
"loss": 4.4103,
|
|
"mean_token_accuracy": 0.2569925054907799,
|
|
"num_tokens": 20794386.0,
|
|
"step": 8825
|
|
},
|
|
{
|
|
"entropy": 5.227028226852417,
|
|
"epoch": 8.992358634742741,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.362715232720575e-05,
|
|
"loss": 4.4781,
|
|
"mean_token_accuracy": 0.25647672861814497,
|
|
"num_tokens": 20807025.0,
|
|
"step": 8830
|
|
},
|
|
{
|
|
"entropy": 5.149193859100341,
|
|
"epoch": 8.99745287824758,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.348999702271107e-05,
|
|
"loss": 4.3375,
|
|
"mean_token_accuracy": 0.2643095001578331,
|
|
"num_tokens": 20820105.0,
|
|
"step": 8835
|
|
},
|
|
{
|
|
"entropy": 5.232809437645806,
|
|
"epoch": 9.002037697401935,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.335351410432671e-05,
|
|
"loss": 4.4872,
|
|
"mean_token_accuracy": 0.253092701236407,
|
|
"num_tokens": 20831292.0,
|
|
"step": 8840
|
|
},
|
|
{
|
|
"entropy": 5.250685310363769,
|
|
"epoch": 9.007131940906776,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.321770400592925e-05,
|
|
"loss": 4.3752,
|
|
"mean_token_accuracy": 0.2606182023882866,
|
|
"num_tokens": 20842805.0,
|
|
"step": 8845
|
|
},
|
|
{
|
|
"entropy": 5.216523122787476,
|
|
"epoch": 9.012226184411615,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.308256715925628e-05,
|
|
"loss": 4.3883,
|
|
"mean_token_accuracy": 0.25354238897562026,
|
|
"num_tokens": 20854510.0,
|
|
"step": 8850
|
|
},
|
|
{
|
|
"entropy": 5.18562536239624,
|
|
"epoch": 9.017320427916454,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 6.294810399390513e-05,
|
|
"loss": 4.3433,
|
|
"mean_token_accuracy": 0.2686587795615196,
|
|
"num_tokens": 20866225.0,
|
|
"step": 8855
|
|
},
|
|
{
|
|
"entropy": 5.178036260604858,
|
|
"epoch": 9.022414671421293,
|
|
"grad_norm": 1.125,
|
|
"learning_rate": 6.281431493733156e-05,
|
|
"loss": 4.3717,
|
|
"mean_token_accuracy": 0.25998311787843703,
|
|
"num_tokens": 20879281.0,
|
|
"step": 8860
|
|
},
|
|
{
|
|
"entropy": 5.21397385597229,
|
|
"epoch": 9.027508914926134,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 6.268120041484836e-05,
|
|
"loss": 4.3936,
|
|
"mean_token_accuracy": 0.2597770348191261,
|
|
"num_tokens": 20890668.0,
|
|
"step": 8865
|
|
},
|
|
{
|
|
"entropy": 5.233232069015503,
|
|
"epoch": 9.032603158430973,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 6.25487608496239e-05,
|
|
"loss": 4.4233,
|
|
"mean_token_accuracy": 0.2510700061917305,
|
|
"num_tokens": 20902814.0,
|
|
"step": 8870
|
|
},
|
|
{
|
|
"entropy": 5.184152412414551,
|
|
"epoch": 9.037697401935812,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.241699666268097e-05,
|
|
"loss": 4.3564,
|
|
"mean_token_accuracy": 0.26223355531692505,
|
|
"num_tokens": 20914285.0,
|
|
"step": 8875
|
|
},
|
|
{
|
|
"entropy": 5.266164255142212,
|
|
"epoch": 9.042791645440651,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 6.228590827289527e-05,
|
|
"loss": 4.4941,
|
|
"mean_token_accuracy": 0.24310793429613115,
|
|
"num_tokens": 20926480.0,
|
|
"step": 8880
|
|
},
|
|
{
|
|
"entropy": 5.224509572982788,
|
|
"epoch": 9.047885888945492,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 6.215549609699426e-05,
|
|
"loss": 4.3685,
|
|
"mean_token_accuracy": 0.2532721057534218,
|
|
"num_tokens": 20939060.0,
|
|
"step": 8885
|
|
},
|
|
{
|
|
"entropy": 5.263015174865723,
|
|
"epoch": 9.052980132450331,
|
|
"grad_norm": 1.5546875,
|
|
"learning_rate": 6.202576054955563e-05,
|
|
"loss": 4.4165,
|
|
"mean_token_accuracy": 0.25268497318029404,
|
|
"num_tokens": 20950596.0,
|
|
"step": 8890
|
|
},
|
|
{
|
|
"entropy": 5.226540660858154,
|
|
"epoch": 9.05807437595517,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 6.18967020430061e-05,
|
|
"loss": 4.348,
|
|
"mean_token_accuracy": 0.26496854424476624,
|
|
"num_tokens": 20962442.0,
|
|
"step": 8895
|
|
},
|
|
{
|
|
"entropy": 5.15069055557251,
|
|
"epoch": 9.06316861946001,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 6.176832098762012e-05,
|
|
"loss": 4.2778,
|
|
"mean_token_accuracy": 0.272835935652256,
|
|
"num_tokens": 20974299.0,
|
|
"step": 8900
|
|
},
|
|
{
|
|
"entropy": 5.20871205329895,
|
|
"epoch": 9.06826286296485,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 6.164061779151858e-05,
|
|
"loss": 4.4077,
|
|
"mean_token_accuracy": 0.2598338767886162,
|
|
"num_tokens": 20986349.0,
|
|
"step": 8905
|
|
},
|
|
{
|
|
"entropy": 5.173646354675293,
|
|
"epoch": 9.07335710646969,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 6.151359286066732e-05,
|
|
"loss": 4.3732,
|
|
"mean_token_accuracy": 0.2516819849610329,
|
|
"num_tokens": 20998078.0,
|
|
"step": 8910
|
|
},
|
|
{
|
|
"entropy": 5.155437755584717,
|
|
"epoch": 9.078451349974529,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 6.138724659887613e-05,
|
|
"loss": 4.3069,
|
|
"mean_token_accuracy": 0.26310726851224897,
|
|
"num_tokens": 21010475.0,
|
|
"step": 8915
|
|
},
|
|
{
|
|
"entropy": 5.18981294631958,
|
|
"epoch": 9.083545593479368,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 6.126157940779722e-05,
|
|
"loss": 4.3631,
|
|
"mean_token_accuracy": 0.26371544450521467,
|
|
"num_tokens": 21022923.0,
|
|
"step": 8920
|
|
},
|
|
{
|
|
"entropy": 5.162095165252685,
|
|
"epoch": 9.088639836984207,
|
|
"grad_norm": 1.1796875,
|
|
"learning_rate": 6.113659168692418e-05,
|
|
"loss": 4.3892,
|
|
"mean_token_accuracy": 0.25775319933891294,
|
|
"num_tokens": 21034894.0,
|
|
"step": 8925
|
|
},
|
|
{
|
|
"entropy": 5.218870210647583,
|
|
"epoch": 9.093734080489048,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.1012283833590465e-05,
|
|
"loss": 4.3334,
|
|
"mean_token_accuracy": 0.26205272823572157,
|
|
"num_tokens": 21045435.0,
|
|
"step": 8930
|
|
},
|
|
{
|
|
"entropy": 5.248729419708252,
|
|
"epoch": 9.098828323993887,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 6.0888656242968255e-05,
|
|
"loss": 4.3902,
|
|
"mean_token_accuracy": 0.2549844175577164,
|
|
"num_tokens": 21057187.0,
|
|
"step": 8935
|
|
},
|
|
{
|
|
"entropy": 5.250536632537842,
|
|
"epoch": 9.103922567498726,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.0765709308067216e-05,
|
|
"loss": 4.4413,
|
|
"mean_token_accuracy": 0.24638024121522903,
|
|
"num_tokens": 21068862.0,
|
|
"step": 8940
|
|
},
|
|
{
|
|
"entropy": 5.209782886505127,
|
|
"epoch": 9.109016811003565,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 6.0643443419733286e-05,
|
|
"loss": 4.3961,
|
|
"mean_token_accuracy": 0.25782007724046707,
|
|
"num_tokens": 21081142.0,
|
|
"step": 8945
|
|
},
|
|
{
|
|
"entropy": 5.230261945724488,
|
|
"epoch": 9.114111054508406,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 6.0521858966647246e-05,
|
|
"loss": 4.3689,
|
|
"mean_token_accuracy": 0.26080660074949263,
|
|
"num_tokens": 21092881.0,
|
|
"step": 8950
|
|
},
|
|
{
|
|
"entropy": 5.18303656578064,
|
|
"epoch": 9.119205298013245,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 6.0400956335323626e-05,
|
|
"loss": 4.3296,
|
|
"mean_token_accuracy": 0.2618766874074936,
|
|
"num_tokens": 21104804.0,
|
|
"step": 8955
|
|
},
|
|
{
|
|
"entropy": 5.2236799716949465,
|
|
"epoch": 9.124299541518084,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 6.028073591010958e-05,
|
|
"loss": 4.3747,
|
|
"mean_token_accuracy": 0.260775925219059,
|
|
"num_tokens": 21116872.0,
|
|
"step": 8960
|
|
},
|
|
{
|
|
"entropy": 5.263193273544312,
|
|
"epoch": 9.129393785022923,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 6.0161198073183407e-05,
|
|
"loss": 4.4364,
|
|
"mean_token_accuracy": 0.25289948284626007,
|
|
"num_tokens": 21128383.0,
|
|
"step": 8965
|
|
},
|
|
{
|
|
"entropy": 5.2281030178070065,
|
|
"epoch": 9.134488028527764,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 6.004234320455355e-05,
|
|
"loss": 4.4277,
|
|
"mean_token_accuracy": 0.25229390412569047,
|
|
"num_tokens": 21140912.0,
|
|
"step": 8970
|
|
},
|
|
{
|
|
"entropy": 5.197032356262207,
|
|
"epoch": 9.139582272032603,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.992417168205725e-05,
|
|
"loss": 4.378,
|
|
"mean_token_accuracy": 0.2605747550725937,
|
|
"num_tokens": 21153686.0,
|
|
"step": 8975
|
|
},
|
|
{
|
|
"entropy": 5.1817127704620365,
|
|
"epoch": 9.144676515537443,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.9806683881359416e-05,
|
|
"loss": 4.3211,
|
|
"mean_token_accuracy": 0.27229608297348024,
|
|
"num_tokens": 21165195.0,
|
|
"step": 8980
|
|
},
|
|
{
|
|
"entropy": 5.193417263031006,
|
|
"epoch": 9.149770759042282,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.9689880175951557e-05,
|
|
"loss": 4.3231,
|
|
"mean_token_accuracy": 0.26349902600049974,
|
|
"num_tokens": 21176017.0,
|
|
"step": 8985
|
|
},
|
|
{
|
|
"entropy": 5.203211116790771,
|
|
"epoch": 9.154865002547123,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.957376093715024e-05,
|
|
"loss": 4.3694,
|
|
"mean_token_accuracy": 0.2583352342247963,
|
|
"num_tokens": 21187285.0,
|
|
"step": 8990
|
|
},
|
|
{
|
|
"entropy": 5.186219072341919,
|
|
"epoch": 9.159959246051962,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.94583265340962e-05,
|
|
"loss": 4.3776,
|
|
"mean_token_accuracy": 0.25924491584300996,
|
|
"num_tokens": 21198673.0,
|
|
"step": 8995
|
|
},
|
|
{
|
|
"entropy": 5.166260480880737,
|
|
"epoch": 9.1650534895568,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.934357733375319e-05,
|
|
"loss": 4.3345,
|
|
"mean_token_accuracy": 0.26937445998191833,
|
|
"num_tokens": 21209109.0,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 9.1650534895568,
|
|
"eval_entropy": 5.050019178272765,
|
|
"eval_loss": 5.592836856842041,
|
|
"eval_mean_token_accuracy": 0.18838672428219408,
|
|
"eval_num_tokens": 21209109.0,
|
|
"eval_runtime": 2.638,
|
|
"eval_samples_per_second": 1228.182,
|
|
"eval_steps_per_second": 153.523,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"entropy": 5.172401571273804,
|
|
"epoch": 9.17014773306164,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.9229513700906626e-05,
|
|
"loss": 4.377,
|
|
"mean_token_accuracy": 0.25453816950321195,
|
|
"num_tokens": 21220906.0,
|
|
"step": 9005
|
|
},
|
|
{
|
|
"entropy": 5.209870958328247,
|
|
"epoch": 9.175241976566479,
|
|
"grad_norm": 1.1640625,
|
|
"learning_rate": 5.911613599816253e-05,
|
|
"loss": 4.3865,
|
|
"mean_token_accuracy": 0.25051199197769164,
|
|
"num_tokens": 21232549.0,
|
|
"step": 9010
|
|
},
|
|
{
|
|
"entropy": 5.176898956298828,
|
|
"epoch": 9.18033622007132,
|
|
"grad_norm": 1.171875,
|
|
"learning_rate": 5.900344458594636e-05,
|
|
"loss": 4.3765,
|
|
"mean_token_accuracy": 0.26216463148593905,
|
|
"num_tokens": 21245034.0,
|
|
"step": 9015
|
|
},
|
|
{
|
|
"entropy": 5.315535545349121,
|
|
"epoch": 9.185430463576159,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.8891439822501894e-05,
|
|
"loss": 4.5042,
|
|
"mean_token_accuracy": 0.24447063058614732,
|
|
"num_tokens": 21257955.0,
|
|
"step": 9020
|
|
},
|
|
{
|
|
"entropy": 5.160243368148803,
|
|
"epoch": 9.190524707080998,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.878012206389009e-05,
|
|
"loss": 4.2922,
|
|
"mean_token_accuracy": 0.27345449179410936,
|
|
"num_tokens": 21269680.0,
|
|
"step": 9025
|
|
},
|
|
{
|
|
"entropy": 5.24161958694458,
|
|
"epoch": 9.195618950585837,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.866949166398786e-05,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.25508705973625184,
|
|
"num_tokens": 21282383.0,
|
|
"step": 9030
|
|
},
|
|
{
|
|
"entropy": 5.2488127708435055,
|
|
"epoch": 9.200713194090678,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.855954897448702e-05,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.24759764075279236,
|
|
"num_tokens": 21294981.0,
|
|
"step": 9035
|
|
},
|
|
{
|
|
"entropy": 5.163005685806274,
|
|
"epoch": 9.205807437595517,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.845029434489329e-05,
|
|
"loss": 4.3574,
|
|
"mean_token_accuracy": 0.2588090658187866,
|
|
"num_tokens": 21306972.0,
|
|
"step": 9040
|
|
},
|
|
{
|
|
"entropy": 5.224446105957031,
|
|
"epoch": 9.210901681100356,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.8341728122524916e-05,
|
|
"loss": 4.3135,
|
|
"mean_token_accuracy": 0.26506141275167466,
|
|
"num_tokens": 21317876.0,
|
|
"step": 9045
|
|
},
|
|
{
|
|
"entropy": 5.184188032150269,
|
|
"epoch": 9.215995924605195,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.8233850652511765e-05,
|
|
"loss": 4.3854,
|
|
"mean_token_accuracy": 0.26373375207185745,
|
|
"num_tokens": 21329411.0,
|
|
"step": 9050
|
|
},
|
|
{
|
|
"entropy": 5.219321393966675,
|
|
"epoch": 9.221090168110036,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.812666227779419e-05,
|
|
"loss": 4.3869,
|
|
"mean_token_accuracy": 0.2590327948331833,
|
|
"num_tokens": 21341971.0,
|
|
"step": 9055
|
|
},
|
|
{
|
|
"entropy": 5.215021324157715,
|
|
"epoch": 9.226184411614875,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.802016333912194e-05,
|
|
"loss": 4.4373,
|
|
"mean_token_accuracy": 0.2493841156363487,
|
|
"num_tokens": 21353086.0,
|
|
"step": 9060
|
|
},
|
|
{
|
|
"entropy": 5.250539779663086,
|
|
"epoch": 9.231278655119715,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.791435417505303e-05,
|
|
"loss": 4.4232,
|
|
"mean_token_accuracy": 0.2543834298849106,
|
|
"num_tokens": 21365281.0,
|
|
"step": 9065
|
|
},
|
|
{
|
|
"entropy": 5.247555494308472,
|
|
"epoch": 9.236372898624554,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.780923512195264e-05,
|
|
"loss": 4.3062,
|
|
"mean_token_accuracy": 0.26053662300109864,
|
|
"num_tokens": 21376646.0,
|
|
"step": 9070
|
|
},
|
|
{
|
|
"entropy": 5.265791606903076,
|
|
"epoch": 9.241467142129395,
|
|
"grad_norm": 1.4453125,
|
|
"learning_rate": 5.770480651399218e-05,
|
|
"loss": 4.4315,
|
|
"mean_token_accuracy": 0.25259600430727003,
|
|
"num_tokens": 21387577.0,
|
|
"step": 9075
|
|
},
|
|
{
|
|
"entropy": 5.145134592056275,
|
|
"epoch": 9.246561385634234,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.760106868314814e-05,
|
|
"loss": 4.3186,
|
|
"mean_token_accuracy": 0.27366075813770296,
|
|
"num_tokens": 21399210.0,
|
|
"step": 9080
|
|
},
|
|
{
|
|
"entropy": 5.248245763778686,
|
|
"epoch": 9.251655629139073,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.749802195920105e-05,
|
|
"loss": 4.3967,
|
|
"mean_token_accuracy": 0.2506695717573166,
|
|
"num_tokens": 21410606.0,
|
|
"step": 9085
|
|
},
|
|
{
|
|
"entropy": 5.206801223754883,
|
|
"epoch": 9.256749872643912,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.739566666973438e-05,
|
|
"loss": 4.3748,
|
|
"mean_token_accuracy": 0.26177004128694537,
|
|
"num_tokens": 21424968.0,
|
|
"step": 9090
|
|
},
|
|
{
|
|
"entropy": 5.178715372085572,
|
|
"epoch": 9.261844116148751,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.729400314013353e-05,
|
|
"loss": 4.378,
|
|
"mean_token_accuracy": 0.2621872201561928,
|
|
"num_tokens": 21436686.0,
|
|
"step": 9095
|
|
},
|
|
{
|
|
"entropy": 5.234049606323242,
|
|
"epoch": 9.266938359653592,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.719303169358492e-05,
|
|
"loss": 4.4227,
|
|
"mean_token_accuracy": 0.2553515166044235,
|
|
"num_tokens": 21450072.0,
|
|
"step": 9100
|
|
},
|
|
{
|
|
"entropy": 5.240210008621216,
|
|
"epoch": 9.272032603158431,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.709275265107477e-05,
|
|
"loss": 4.3928,
|
|
"mean_token_accuracy": 0.25804716944694517,
|
|
"num_tokens": 21461369.0,
|
|
"step": 9105
|
|
},
|
|
{
|
|
"entropy": 5.221291875839233,
|
|
"epoch": 9.27712684666327,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.699316633138809e-05,
|
|
"loss": 4.37,
|
|
"mean_token_accuracy": 0.2679221600294113,
|
|
"num_tokens": 21472633.0,
|
|
"step": 9110
|
|
},
|
|
{
|
|
"entropy": 5.16949429512024,
|
|
"epoch": 9.28222109016811,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.689427305110791e-05,
|
|
"loss": 4.3479,
|
|
"mean_token_accuracy": 0.261329311132431,
|
|
"num_tokens": 21484501.0,
|
|
"step": 9115
|
|
},
|
|
{
|
|
"entropy": 5.162904071807861,
|
|
"epoch": 9.28731533367295,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.679607312461398e-05,
|
|
"loss": 4.3058,
|
|
"mean_token_accuracy": 0.2688350021839142,
|
|
"num_tokens": 21495258.0,
|
|
"step": 9120
|
|
},
|
|
{
|
|
"entropy": 5.266991472244262,
|
|
"epoch": 9.29240957717779,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.66985668640819e-05,
|
|
"loss": 4.423,
|
|
"mean_token_accuracy": 0.2573879599571228,
|
|
"num_tokens": 21507475.0,
|
|
"step": 9125
|
|
},
|
|
{
|
|
"entropy": 5.260095262527466,
|
|
"epoch": 9.297503820682628,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.660175457948215e-05,
|
|
"loss": 4.4212,
|
|
"mean_token_accuracy": 0.2540705785155296,
|
|
"num_tokens": 21520401.0,
|
|
"step": 9130
|
|
},
|
|
{
|
|
"entropy": 5.221770143508911,
|
|
"epoch": 9.302598064187467,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 5.650563657857905e-05,
|
|
"loss": 4.4266,
|
|
"mean_token_accuracy": 0.25044783055782316,
|
|
"num_tokens": 21532343.0,
|
|
"step": 9135
|
|
},
|
|
{
|
|
"entropy": 5.22874002456665,
|
|
"epoch": 9.307692307692308,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.641021316692989e-05,
|
|
"loss": 4.4507,
|
|
"mean_token_accuracy": 0.24777987152338027,
|
|
"num_tokens": 21544763.0,
|
|
"step": 9140
|
|
},
|
|
{
|
|
"entropy": 5.183925437927246,
|
|
"epoch": 9.312786551197147,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.631548464788376e-05,
|
|
"loss": 4.2954,
|
|
"mean_token_accuracy": 0.2622640773653984,
|
|
"num_tokens": 21557004.0,
|
|
"step": 9145
|
|
},
|
|
{
|
|
"entropy": 5.237141180038452,
|
|
"epoch": 9.317880794701987,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.62214513225807e-05,
|
|
"loss": 4.344,
|
|
"mean_token_accuracy": 0.2607619032263756,
|
|
"num_tokens": 21567731.0,
|
|
"step": 9150
|
|
},
|
|
{
|
|
"entropy": 5.255859899520874,
|
|
"epoch": 9.322975038206826,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.6128113489950844e-05,
|
|
"loss": 4.3982,
|
|
"mean_token_accuracy": 0.24969375282526016,
|
|
"num_tokens": 21579536.0,
|
|
"step": 9155
|
|
},
|
|
{
|
|
"entropy": 5.241299486160278,
|
|
"epoch": 9.328069281711667,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.6035471446713314e-05,
|
|
"loss": 4.4325,
|
|
"mean_token_accuracy": 0.25174289643764497,
|
|
"num_tokens": 21592655.0,
|
|
"step": 9160
|
|
},
|
|
{
|
|
"entropy": 5.222051429748535,
|
|
"epoch": 9.333163525216506,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.594352548737531e-05,
|
|
"loss": 4.3496,
|
|
"mean_token_accuracy": 0.2628124549984932,
|
|
"num_tokens": 21603387.0,
|
|
"step": 9165
|
|
},
|
|
{
|
|
"entropy": 5.203886604309082,
|
|
"epoch": 9.338257768721345,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.585227590423123e-05,
|
|
"loss": 4.3396,
|
|
"mean_token_accuracy": 0.261469829082489,
|
|
"num_tokens": 21613033.0,
|
|
"step": 9170
|
|
},
|
|
{
|
|
"entropy": 5.2484846115112305,
|
|
"epoch": 9.343352012226184,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.576172298736168e-05,
|
|
"loss": 4.4152,
|
|
"mean_token_accuracy": 0.2509225904941559,
|
|
"num_tokens": 21624593.0,
|
|
"step": 9175
|
|
},
|
|
{
|
|
"entropy": 5.262305164337159,
|
|
"epoch": 9.348446255731023,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.56718670246326e-05,
|
|
"loss": 4.4446,
|
|
"mean_token_accuracy": 0.2552341252565384,
|
|
"num_tokens": 21637920.0,
|
|
"step": 9180
|
|
},
|
|
{
|
|
"entropy": 5.156659698486328,
|
|
"epoch": 9.353540499235864,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.5582708301694326e-05,
|
|
"loss": 4.4123,
|
|
"mean_token_accuracy": 0.2629585087299347,
|
|
"num_tokens": 21650214.0,
|
|
"step": 9185
|
|
},
|
|
{
|
|
"entropy": 5.165005111694336,
|
|
"epoch": 9.358634742740703,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.549424710198063e-05,
|
|
"loss": 4.3152,
|
|
"mean_token_accuracy": 0.2730478003621101,
|
|
"num_tokens": 21660152.0,
|
|
"step": 9190
|
|
},
|
|
{
|
|
"entropy": 5.221422481536865,
|
|
"epoch": 9.363728986245542,
|
|
"grad_norm": 1.453125,
|
|
"learning_rate": 5.540648370670794e-05,
|
|
"loss": 4.3629,
|
|
"mean_token_accuracy": 0.25685478299856185,
|
|
"num_tokens": 21671380.0,
|
|
"step": 9195
|
|
},
|
|
{
|
|
"entropy": 5.225584268569946,
|
|
"epoch": 9.368823229750381,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.531941839487437e-05,
|
|
"loss": 4.4071,
|
|
"mean_token_accuracy": 0.25384733378887175,
|
|
"num_tokens": 21683170.0,
|
|
"step": 9200
|
|
},
|
|
{
|
|
"entropy": 5.190740537643433,
|
|
"epoch": 9.373917473255222,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.523305144325879e-05,
|
|
"loss": 4.3593,
|
|
"mean_token_accuracy": 0.25756863951683046,
|
|
"num_tokens": 21694547.0,
|
|
"step": 9205
|
|
},
|
|
{
|
|
"entropy": 5.148402118682862,
|
|
"epoch": 9.379011716760061,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.514738312642003e-05,
|
|
"loss": 4.2941,
|
|
"mean_token_accuracy": 0.2745544001460075,
|
|
"num_tokens": 21705553.0,
|
|
"step": 9210
|
|
},
|
|
{
|
|
"entropy": 5.2757518768310545,
|
|
"epoch": 9.3841059602649,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.506241371669602e-05,
|
|
"loss": 4.4288,
|
|
"mean_token_accuracy": 0.2610105603933334,
|
|
"num_tokens": 21717517.0,
|
|
"step": 9215
|
|
},
|
|
{
|
|
"entropy": 5.26189546585083,
|
|
"epoch": 9.38920020376974,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.4978143484202785e-05,
|
|
"loss": 4.447,
|
|
"mean_token_accuracy": 0.2537351563572884,
|
|
"num_tokens": 21727665.0,
|
|
"step": 9220
|
|
},
|
|
{
|
|
"entropy": 5.240252590179443,
|
|
"epoch": 9.39429444727458,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.489457269683375e-05,
|
|
"loss": 4.4012,
|
|
"mean_token_accuracy": 0.25257612615823744,
|
|
"num_tokens": 21740553.0,
|
|
"step": 9225
|
|
},
|
|
{
|
|
"entropy": 5.17227611541748,
|
|
"epoch": 9.39938869077942,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.4811701620258766e-05,
|
|
"loss": 4.3409,
|
|
"mean_token_accuracy": 0.2633024722337723,
|
|
"num_tokens": 21752055.0,
|
|
"step": 9230
|
|
},
|
|
{
|
|
"entropy": 5.1690877914428714,
|
|
"epoch": 9.404482934284259,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.472953051792335e-05,
|
|
"loss": 4.3343,
|
|
"mean_token_accuracy": 0.2683193445205688,
|
|
"num_tokens": 21762515.0,
|
|
"step": 9235
|
|
},
|
|
{
|
|
"entropy": 5.291845273971558,
|
|
"epoch": 9.409577177789098,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.46480596510478e-05,
|
|
"loss": 4.463,
|
|
"mean_token_accuracy": 0.24559276551008224,
|
|
"num_tokens": 21772409.0,
|
|
"step": 9240
|
|
},
|
|
{
|
|
"entropy": 5.176699113845825,
|
|
"epoch": 9.414671421293939,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.4567289278626424e-05,
|
|
"loss": 4.3269,
|
|
"mean_token_accuracy": 0.26425777822732927,
|
|
"num_tokens": 21783784.0,
|
|
"step": 9245
|
|
},
|
|
{
|
|
"entropy": 5.203429317474365,
|
|
"epoch": 9.419765664798778,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.4487219657426615e-05,
|
|
"loss": 4.3696,
|
|
"mean_token_accuracy": 0.2587173327803612,
|
|
"num_tokens": 21794920.0,
|
|
"step": 9250
|
|
},
|
|
{
|
|
"entropy": 5.215222454071045,
|
|
"epoch": 9.424859908303617,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.4407851041988105e-05,
|
|
"loss": 4.4232,
|
|
"mean_token_accuracy": 0.25364246368408205,
|
|
"num_tokens": 21806960.0,
|
|
"step": 9255
|
|
},
|
|
{
|
|
"entropy": 5.21107439994812,
|
|
"epoch": 9.429954151808456,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.4329183684622174e-05,
|
|
"loss": 4.3712,
|
|
"mean_token_accuracy": 0.2604333236813545,
|
|
"num_tokens": 21819313.0,
|
|
"step": 9260
|
|
},
|
|
{
|
|
"entropy": 5.1939277172088625,
|
|
"epoch": 9.435048395313295,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.425121783541081e-05,
|
|
"loss": 4.3095,
|
|
"mean_token_accuracy": 0.26100440323352814,
|
|
"num_tokens": 21829602.0,
|
|
"step": 9265
|
|
},
|
|
{
|
|
"entropy": 5.188802576065063,
|
|
"epoch": 9.440142638818136,
|
|
"grad_norm": 1.2421875,
|
|
"learning_rate": 5.41739537422058e-05,
|
|
"loss": 4.3514,
|
|
"mean_token_accuracy": 0.26454823315143583,
|
|
"num_tokens": 21841972.0,
|
|
"step": 9270
|
|
},
|
|
{
|
|
"entropy": 5.208502388000488,
|
|
"epoch": 9.445236882322975,
|
|
"grad_norm": 1.1171875,
|
|
"learning_rate": 5.40973916506283e-05,
|
|
"loss": 4.3692,
|
|
"mean_token_accuracy": 0.26064190864562986,
|
|
"num_tokens": 21854291.0,
|
|
"step": 9275
|
|
},
|
|
{
|
|
"entropy": 5.190014791488648,
|
|
"epoch": 9.450331125827814,
|
|
"grad_norm": 1.2265625,
|
|
"learning_rate": 5.40215318040676e-05,
|
|
"loss": 4.4647,
|
|
"mean_token_accuracy": 0.2579666718840599,
|
|
"num_tokens": 21868249.0,
|
|
"step": 9280
|
|
},
|
|
{
|
|
"entropy": 5.177255916595459,
|
|
"epoch": 9.455425369332653,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.394637444368066e-05,
|
|
"loss": 4.3364,
|
|
"mean_token_accuracy": 0.2630578115582466,
|
|
"num_tokens": 21881026.0,
|
|
"step": 9285
|
|
},
|
|
{
|
|
"entropy": 5.1599548816680905,
|
|
"epoch": 9.460519612837494,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.387191980839124e-05,
|
|
"loss": 4.3406,
|
|
"mean_token_accuracy": 0.26544962376356124,
|
|
"num_tokens": 21893013.0,
|
|
"step": 9290
|
|
},
|
|
{
|
|
"entropy": 5.237991189956665,
|
|
"epoch": 9.465613856342333,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.379816813488919e-05,
|
|
"loss": 4.3977,
|
|
"mean_token_accuracy": 0.26135640144348143,
|
|
"num_tokens": 21904202.0,
|
|
"step": 9295
|
|
},
|
|
{
|
|
"entropy": 5.179881238937378,
|
|
"epoch": 9.470708099847172,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.372511965762958e-05,
|
|
"loss": 4.3312,
|
|
"mean_token_accuracy": 0.2597409650683403,
|
|
"num_tokens": 21914905.0,
|
|
"step": 9300
|
|
},
|
|
{
|
|
"entropy": 5.104130411148072,
|
|
"epoch": 9.475802343352012,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.3652774608832074e-05,
|
|
"loss": 4.2488,
|
|
"mean_token_accuracy": 0.2738989979028702,
|
|
"num_tokens": 21926080.0,
|
|
"step": 9305
|
|
},
|
|
{
|
|
"entropy": 5.246713876724243,
|
|
"epoch": 9.480896586856852,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.358113321848018e-05,
|
|
"loss": 4.4178,
|
|
"mean_token_accuracy": 0.25386123508214953,
|
|
"num_tokens": 21937873.0,
|
|
"step": 9310
|
|
},
|
|
{
|
|
"entropy": 5.212632274627685,
|
|
"epoch": 9.485990830361692,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.351019571432044e-05,
|
|
"loss": 4.4186,
|
|
"mean_token_accuracy": 0.2579557910561562,
|
|
"num_tokens": 21948777.0,
|
|
"step": 9315
|
|
},
|
|
{
|
|
"entropy": 5.246230697631836,
|
|
"epoch": 9.49108507386653,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.3439962321861745e-05,
|
|
"loss": 4.456,
|
|
"mean_token_accuracy": 0.25319080203771593,
|
|
"num_tokens": 21960825.0,
|
|
"step": 9320
|
|
},
|
|
{
|
|
"entropy": 5.24738187789917,
|
|
"epoch": 9.49617931737137,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.337043326437473e-05,
|
|
"loss": 4.4269,
|
|
"mean_token_accuracy": 0.2533916309475899,
|
|
"num_tokens": 21974805.0,
|
|
"step": 9325
|
|
},
|
|
{
|
|
"entropy": 5.20265679359436,
|
|
"epoch": 9.50127356087621,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 5.3301608762890795e-05,
|
|
"loss": 4.3383,
|
|
"mean_token_accuracy": 0.2677122414112091,
|
|
"num_tokens": 21985827.0,
|
|
"step": 9330
|
|
},
|
|
{
|
|
"entropy": 5.248458480834961,
|
|
"epoch": 9.50636780438105,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.3233489036201735e-05,
|
|
"loss": 4.4915,
|
|
"mean_token_accuracy": 0.24889273196458817,
|
|
"num_tokens": 21998958.0,
|
|
"step": 9335
|
|
},
|
|
{
|
|
"entropy": 5.2005856990814205,
|
|
"epoch": 9.511462047885889,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.3166074300858826e-05,
|
|
"loss": 4.3702,
|
|
"mean_token_accuracy": 0.2613302394747734,
|
|
"num_tokens": 22010425.0,
|
|
"step": 9340
|
|
},
|
|
{
|
|
"entropy": 5.202708148956299,
|
|
"epoch": 9.516556291390728,
|
|
"grad_norm": 1.2109375,
|
|
"learning_rate": 5.309936477117212e-05,
|
|
"loss": 4.3736,
|
|
"mean_token_accuracy": 0.2615066424012184,
|
|
"num_tokens": 22022588.0,
|
|
"step": 9345
|
|
},
|
|
{
|
|
"entropy": 5.272076749801636,
|
|
"epoch": 9.521650534895567,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 5.303336065920994e-05,
|
|
"loss": 4.4365,
|
|
"mean_token_accuracy": 0.2520070016384125,
|
|
"num_tokens": 22035019.0,
|
|
"step": 9350
|
|
},
|
|
{
|
|
"entropy": 5.272449111938476,
|
|
"epoch": 9.526744778400408,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.296806217479802e-05,
|
|
"loss": 4.4768,
|
|
"mean_token_accuracy": 0.25130927711725237,
|
|
"num_tokens": 22045895.0,
|
|
"step": 9355
|
|
},
|
|
{
|
|
"entropy": 5.185212230682373,
|
|
"epoch": 9.531839021905247,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.2903469525518954e-05,
|
|
"loss": 4.3926,
|
|
"mean_token_accuracy": 0.26192880868911744,
|
|
"num_tokens": 22057174.0,
|
|
"step": 9360
|
|
},
|
|
{
|
|
"entropy": 5.206588268280029,
|
|
"epoch": 9.536933265410086,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.2839582916711496e-05,
|
|
"loss": 4.3721,
|
|
"mean_token_accuracy": 0.2693273663520813,
|
|
"num_tokens": 22069177.0,
|
|
"step": 9365
|
|
},
|
|
{
|
|
"entropy": 5.168446350097656,
|
|
"epoch": 9.542027508914925,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.277640255146991e-05,
|
|
"loss": 4.3344,
|
|
"mean_token_accuracy": 0.26914759129285815,
|
|
"num_tokens": 22080554.0,
|
|
"step": 9370
|
|
},
|
|
{
|
|
"entropy": 5.255085420608521,
|
|
"epoch": 9.547121752419766,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.2713928630643324e-05,
|
|
"loss": 4.3901,
|
|
"mean_token_accuracy": 0.2570668816566467,
|
|
"num_tokens": 22092661.0,
|
|
"step": 9375
|
|
},
|
|
{
|
|
"entropy": 5.218854331970215,
|
|
"epoch": 9.552215995924605,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.2652161352835115e-05,
|
|
"loss": 4.3727,
|
|
"mean_token_accuracy": 0.2639762610197067,
|
|
"num_tokens": 22103726.0,
|
|
"step": 9380
|
|
},
|
|
{
|
|
"entropy": 5.20581636428833,
|
|
"epoch": 9.557310239429444,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.2591100914402226e-05,
|
|
"loss": 4.3917,
|
|
"mean_token_accuracy": 0.25331327617168425,
|
|
"num_tokens": 22115198.0,
|
|
"step": 9385
|
|
},
|
|
{
|
|
"entropy": 5.155240249633789,
|
|
"epoch": 9.562404482934284,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.253074750945455e-05,
|
|
"loss": 4.3069,
|
|
"mean_token_accuracy": 0.2648371607065201,
|
|
"num_tokens": 22125671.0,
|
|
"step": 9390
|
|
},
|
|
{
|
|
"entropy": 5.198412466049194,
|
|
"epoch": 9.567498726439124,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.247110132985441e-05,
|
|
"loss": 4.3506,
|
|
"mean_token_accuracy": 0.2638612076640129,
|
|
"num_tokens": 22137374.0,
|
|
"step": 9395
|
|
},
|
|
{
|
|
"entropy": 5.177314043045044,
|
|
"epoch": 9.572592969943964,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.2412162565215804e-05,
|
|
"loss": 4.3813,
|
|
"mean_token_accuracy": 0.2579807326197624,
|
|
"num_tokens": 22149737.0,
|
|
"step": 9400
|
|
},
|
|
{
|
|
"entropy": 5.099501085281372,
|
|
"epoch": 9.577687213448803,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.235393140290391e-05,
|
|
"loss": 4.2857,
|
|
"mean_token_accuracy": 0.27330702245235444,
|
|
"num_tokens": 22161451.0,
|
|
"step": 9405
|
|
},
|
|
{
|
|
"entropy": 5.224106121063232,
|
|
"epoch": 9.582781456953642,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.229640802803442e-05,
|
|
"loss": 4.3972,
|
|
"mean_token_accuracy": 0.2579248040914536,
|
|
"num_tokens": 22173306.0,
|
|
"step": 9410
|
|
},
|
|
{
|
|
"entropy": 5.178874778747558,
|
|
"epoch": 9.587875700458483,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.2239592623473026e-05,
|
|
"loss": 4.3474,
|
|
"mean_token_accuracy": 0.26133008301258087,
|
|
"num_tokens": 22185844.0,
|
|
"step": 9415
|
|
},
|
|
{
|
|
"entropy": 5.247241640090943,
|
|
"epoch": 9.592969943963322,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.218348536983479e-05,
|
|
"loss": 4.4182,
|
|
"mean_token_accuracy": 0.25152028650045394,
|
|
"num_tokens": 22197712.0,
|
|
"step": 9420
|
|
},
|
|
{
|
|
"entropy": 5.184352588653565,
|
|
"epoch": 9.598064187468161,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.21280864454835e-05,
|
|
"loss": 4.3458,
|
|
"mean_token_accuracy": 0.26515993475914,
|
|
"num_tokens": 22208902.0,
|
|
"step": 9425
|
|
},
|
|
{
|
|
"entropy": 5.1943412780761715,
|
|
"epoch": 9.603158430973,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.2073396026531285e-05,
|
|
"loss": 4.3308,
|
|
"mean_token_accuracy": 0.2651795923709869,
|
|
"num_tokens": 22220362.0,
|
|
"step": 9430
|
|
},
|
|
{
|
|
"entropy": 5.233055162429809,
|
|
"epoch": 9.60825267447784,
|
|
"grad_norm": 1.234375,
|
|
"learning_rate": 5.2019414286837926e-05,
|
|
"loss": 4.3921,
|
|
"mean_token_accuracy": 0.25241330862045286,
|
|
"num_tokens": 22232309.0,
|
|
"step": 9435
|
|
},
|
|
{
|
|
"entropy": 5.154585123062134,
|
|
"epoch": 9.61334691798268,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.196614139801025e-05,
|
|
"loss": 4.3803,
|
|
"mean_token_accuracy": 0.25827189832925795,
|
|
"num_tokens": 22243222.0,
|
|
"step": 9440
|
|
},
|
|
{
|
|
"entropy": 5.151184511184693,
|
|
"epoch": 9.61844116148752,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.19135775294017e-05,
|
|
"loss": 4.3026,
|
|
"mean_token_accuracy": 0.27746296375989915,
|
|
"num_tokens": 22254389.0,
|
|
"step": 9445
|
|
},
|
|
{
|
|
"entropy": 5.219047784805298,
|
|
"epoch": 9.623535404992358,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.186172284811184e-05,
|
|
"loss": 4.3868,
|
|
"mean_token_accuracy": 0.26126243472099303,
|
|
"num_tokens": 22266075.0,
|
|
"step": 9450
|
|
},
|
|
{
|
|
"entropy": 5.1818562030792235,
|
|
"epoch": 9.628629648497197,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.181057751898566e-05,
|
|
"loss": 4.3076,
|
|
"mean_token_accuracy": 0.26455207020044325,
|
|
"num_tokens": 22276807.0,
|
|
"step": 9455
|
|
},
|
|
{
|
|
"entropy": 5.190911293029785,
|
|
"epoch": 9.633723892002038,
|
|
"grad_norm": 1.140625,
|
|
"learning_rate": 5.176014170461312e-05,
|
|
"loss": 4.2971,
|
|
"mean_token_accuracy": 0.26321778893470765,
|
|
"num_tokens": 22289743.0,
|
|
"step": 9460
|
|
},
|
|
{
|
|
"entropy": 5.2445189476013185,
|
|
"epoch": 9.638818135506877,
|
|
"grad_norm": 1.25,
|
|
"learning_rate": 5.171041556532869e-05,
|
|
"loss": 4.4294,
|
|
"mean_token_accuracy": 0.24666493237018586,
|
|
"num_tokens": 22301707.0,
|
|
"step": 9465
|
|
},
|
|
{
|
|
"entropy": 5.232217073440552,
|
|
"epoch": 9.643912379011716,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.166139925921079e-05,
|
|
"loss": 4.4005,
|
|
"mean_token_accuracy": 0.25458727180957796,
|
|
"num_tokens": 22313026.0,
|
|
"step": 9470
|
|
},
|
|
{
|
|
"entropy": 5.116698837280273,
|
|
"epoch": 9.649006622516556,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.161309294208126e-05,
|
|
"loss": 4.3296,
|
|
"mean_token_accuracy": 0.2722329363226891,
|
|
"num_tokens": 22325499.0,
|
|
"step": 9475
|
|
},
|
|
{
|
|
"entropy": 5.2387299060821535,
|
|
"epoch": 9.654100866021396,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.1565496767504944e-05,
|
|
"loss": 4.3934,
|
|
"mean_token_accuracy": 0.2581327438354492,
|
|
"num_tokens": 22337058.0,
|
|
"step": 9480
|
|
},
|
|
{
|
|
"entropy": 5.22675518989563,
|
|
"epoch": 9.659195109526236,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.1518610886789136e-05,
|
|
"loss": 4.3824,
|
|
"mean_token_accuracy": 0.254459810256958,
|
|
"num_tokens": 22349265.0,
|
|
"step": 9485
|
|
},
|
|
{
|
|
"entropy": 5.2048999786376955,
|
|
"epoch": 9.664289353031075,
|
|
"grad_norm": 1.3828125,
|
|
"learning_rate": 5.1472435448983123e-05,
|
|
"loss": 4.3035,
|
|
"mean_token_accuracy": 0.2732574865221977,
|
|
"num_tokens": 22360064.0,
|
|
"step": 9490
|
|
},
|
|
{
|
|
"entropy": 5.247843313217163,
|
|
"epoch": 9.669383596535914,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.1426970600877724e-05,
|
|
"loss": 4.495,
|
|
"mean_token_accuracy": 0.2546615689992905,
|
|
"num_tokens": 22373344.0,
|
|
"step": 9495
|
|
},
|
|
{
|
|
"entropy": 5.180827665328979,
|
|
"epoch": 9.674477840040755,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.1382216487004766e-05,
|
|
"loss": 4.3238,
|
|
"mean_token_accuracy": 0.262418358027935,
|
|
"num_tokens": 22383656.0,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"entropy": 5.1517867088317875,
|
|
"epoch": 9.679572083545594,
|
|
"grad_norm": 1.203125,
|
|
"learning_rate": 5.1338173249636685e-05,
|
|
"loss": 4.2964,
|
|
"mean_token_accuracy": 0.26416260898113253,
|
|
"num_tokens": 22395203.0,
|
|
"step": 9505
|
|
},
|
|
{
|
|
"entropy": 5.106749057769775,
|
|
"epoch": 9.684666327050433,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.12948410287861e-05,
|
|
"loss": 4.2423,
|
|
"mean_token_accuracy": 0.2760588198900223,
|
|
"num_tokens": 22405567.0,
|
|
"step": 9510
|
|
},
|
|
{
|
|
"entropy": 5.261894989013672,
|
|
"epoch": 9.689760570555272,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.125221996220523e-05,
|
|
"loss": 4.4298,
|
|
"mean_token_accuracy": 0.250904743373394,
|
|
"num_tokens": 22416914.0,
|
|
"step": 9515
|
|
},
|
|
{
|
|
"entropy": 5.175843238830566,
|
|
"epoch": 9.694854814060111,
|
|
"grad_norm": 1.53125,
|
|
"learning_rate": 5.121031018538564e-05,
|
|
"loss": 4.3435,
|
|
"mean_token_accuracy": 0.26594756096601485,
|
|
"num_tokens": 22426893.0,
|
|
"step": 9520
|
|
},
|
|
{
|
|
"entropy": 5.231868934631348,
|
|
"epoch": 9.699949057564952,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.1169111831557684e-05,
|
|
"loss": 4.3682,
|
|
"mean_token_accuracy": 0.26301634311676025,
|
|
"num_tokens": 22439000.0,
|
|
"step": 9525
|
|
},
|
|
{
|
|
"entropy": 5.200386047363281,
|
|
"epoch": 9.705043301069791,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.1128625031690076e-05,
|
|
"loss": 4.3571,
|
|
"mean_token_accuracy": 0.26536749452352526,
|
|
"num_tokens": 22451295.0,
|
|
"step": 9530
|
|
},
|
|
{
|
|
"entropy": 5.196373128890992,
|
|
"epoch": 9.71013754457463,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.108884991448957e-05,
|
|
"loss": 4.3929,
|
|
"mean_token_accuracy": 0.25845430344343184,
|
|
"num_tokens": 22463498.0,
|
|
"step": 9535
|
|
},
|
|
{
|
|
"entropy": 5.214223909378052,
|
|
"epoch": 9.71523178807947,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.10497866064005e-05,
|
|
"loss": 4.3678,
|
|
"mean_token_accuracy": 0.2557774931192398,
|
|
"num_tokens": 22474757.0,
|
|
"step": 9540
|
|
},
|
|
{
|
|
"entropy": 5.195131254196167,
|
|
"epoch": 9.72032603158431,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.1011435231604314e-05,
|
|
"loss": 4.3651,
|
|
"mean_token_accuracy": 0.2651370778679848,
|
|
"num_tokens": 22486969.0,
|
|
"step": 9545
|
|
},
|
|
{
|
|
"entropy": 5.122254037857056,
|
|
"epoch": 9.72542027508915,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.0973795912019276e-05,
|
|
"loss": 4.2696,
|
|
"mean_token_accuracy": 0.27388901114463804,
|
|
"num_tokens": 22498370.0,
|
|
"step": 9550
|
|
},
|
|
{
|
|
"entropy": 5.188859367370606,
|
|
"epoch": 9.730514518593989,
|
|
"grad_norm": 1.40625,
|
|
"learning_rate": 5.0936868767300065e-05,
|
|
"loss": 4.3991,
|
|
"mean_token_accuracy": 0.25445412248373034,
|
|
"num_tokens": 22510635.0,
|
|
"step": 9555
|
|
},
|
|
{
|
|
"entropy": 5.1802318572998045,
|
|
"epoch": 9.735608762098828,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.090065391483731e-05,
|
|
"loss": 4.3108,
|
|
"mean_token_accuracy": 0.25604595243930817,
|
|
"num_tokens": 22521226.0,
|
|
"step": 9560
|
|
},
|
|
{
|
|
"entropy": 5.247699117660522,
|
|
"epoch": 9.740703005603669,
|
|
"grad_norm": 1.4140625,
|
|
"learning_rate": 5.086515146975731e-05,
|
|
"loss": 4.4323,
|
|
"mean_token_accuracy": 0.24907077997922897,
|
|
"num_tokens": 22533220.0,
|
|
"step": 9565
|
|
},
|
|
{
|
|
"entropy": 5.103401041030883,
|
|
"epoch": 9.745797249108508,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.0830361544921666e-05,
|
|
"loss": 4.3559,
|
|
"mean_token_accuracy": 0.2661367356777191,
|
|
"num_tokens": 22544475.0,
|
|
"step": 9570
|
|
},
|
|
{
|
|
"entropy": 5.214594125747681,
|
|
"epoch": 9.750891492613347,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.0796284250926866e-05,
|
|
"loss": 4.405,
|
|
"mean_token_accuracy": 0.2550816997885704,
|
|
"num_tokens": 22555133.0,
|
|
"step": 9575
|
|
},
|
|
{
|
|
"entropy": 5.141333055496216,
|
|
"epoch": 9.755985736118186,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.07629196961039e-05,
|
|
"loss": 4.3241,
|
|
"mean_token_accuracy": 0.2625136524438858,
|
|
"num_tokens": 22567102.0,
|
|
"step": 9580
|
|
},
|
|
{
|
|
"entropy": 5.174791049957276,
|
|
"epoch": 9.761079979623027,
|
|
"grad_norm": 1.375,
|
|
"learning_rate": 5.073026798651809e-05,
|
|
"loss": 4.3523,
|
|
"mean_token_accuracy": 0.26274550557136533,
|
|
"num_tokens": 22578592.0,
|
|
"step": 9585
|
|
},
|
|
{
|
|
"entropy": 5.263333892822265,
|
|
"epoch": 9.766174223127866,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.069832922596852e-05,
|
|
"loss": 4.5175,
|
|
"mean_token_accuracy": 0.24525001943111419,
|
|
"num_tokens": 22591286.0,
|
|
"step": 9590
|
|
},
|
|
{
|
|
"entropy": 5.15567307472229,
|
|
"epoch": 9.771268466632705,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.0667103515987883e-05,
|
|
"loss": 4.3925,
|
|
"mean_token_accuracy": 0.26378793716430665,
|
|
"num_tokens": 22603032.0,
|
|
"step": 9595
|
|
},
|
|
{
|
|
"entropy": 5.1526707172393795,
|
|
"epoch": 9.776362710137544,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.063659095584214e-05,
|
|
"loss": 4.3605,
|
|
"mean_token_accuracy": 0.2635680451989174,
|
|
"num_tokens": 22616071.0,
|
|
"step": 9600
|
|
},
|
|
{
|
|
"entropy": 5.228186368942261,
|
|
"epoch": 9.781456953642383,
|
|
"grad_norm": 1.5234375,
|
|
"learning_rate": 5.0606791642530056e-05,
|
|
"loss": 4.3647,
|
|
"mean_token_accuracy": 0.25947851985692977,
|
|
"num_tokens": 22627189.0,
|
|
"step": 9605
|
|
},
|
|
{
|
|
"entropy": 5.241382646560669,
|
|
"epoch": 9.786551197147224,
|
|
"grad_norm": 1.265625,
|
|
"learning_rate": 5.05777056707831e-05,
|
|
"loss": 4.3222,
|
|
"mean_token_accuracy": 0.2671191170811653,
|
|
"num_tokens": 22637691.0,
|
|
"step": 9610
|
|
},
|
|
{
|
|
"entropy": 5.266277885437011,
|
|
"epoch": 9.791645440652063,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.0549333133064984e-05,
|
|
"loss": 4.4437,
|
|
"mean_token_accuracy": 0.2551340594887733,
|
|
"num_tokens": 22650775.0,
|
|
"step": 9615
|
|
},
|
|
{
|
|
"entropy": 5.239672899246216,
|
|
"epoch": 9.796739684156902,
|
|
"grad_norm": 1.4296875,
|
|
"learning_rate": 5.052167411957143e-05,
|
|
"loss": 4.3904,
|
|
"mean_token_accuracy": 0.25861859768629075,
|
|
"num_tokens": 22661915.0,
|
|
"step": 9620
|
|
},
|
|
{
|
|
"entropy": 5.235914802551269,
|
|
"epoch": 9.801833927661741,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.0494728718229925e-05,
|
|
"loss": 4.3792,
|
|
"mean_token_accuracy": 0.2549362078309059,
|
|
"num_tokens": 22673875.0,
|
|
"step": 9625
|
|
},
|
|
{
|
|
"entropy": 5.183571434020996,
|
|
"epoch": 9.806928171166582,
|
|
"grad_norm": 1.390625,
|
|
"learning_rate": 5.046849701469934e-05,
|
|
"loss": 4.3643,
|
|
"mean_token_accuracy": 0.26266286373138426,
|
|
"num_tokens": 22685847.0,
|
|
"step": 9630
|
|
},
|
|
{
|
|
"entropy": 5.129880046844482,
|
|
"epoch": 9.812022414671421,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.044297909236976e-05,
|
|
"loss": 4.2803,
|
|
"mean_token_accuracy": 0.27514340430498124,
|
|
"num_tokens": 22697067.0,
|
|
"step": 9635
|
|
},
|
|
{
|
|
"entropy": 5.142257928848267,
|
|
"epoch": 9.81711665817626,
|
|
"grad_norm": 1.421875,
|
|
"learning_rate": 5.041817503236215e-05,
|
|
"loss": 4.3086,
|
|
"mean_token_accuracy": 0.26405641436576843,
|
|
"num_tokens": 22708496.0,
|
|
"step": 9640
|
|
},
|
|
{
|
|
"entropy": 5.253781270980835,
|
|
"epoch": 9.8222109016811,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.039408491352812e-05,
|
|
"loss": 4.409,
|
|
"mean_token_accuracy": 0.25355858355760574,
|
|
"num_tokens": 22721234.0,
|
|
"step": 9645
|
|
},
|
|
{
|
|
"entropy": 5.261454486846924,
|
|
"epoch": 9.82730514518594,
|
|
"grad_norm": 1.484375,
|
|
"learning_rate": 5.037070881244967e-05,
|
|
"loss": 4.4003,
|
|
"mean_token_accuracy": 0.2534809872508049,
|
|
"num_tokens": 22733341.0,
|
|
"step": 9650
|
|
},
|
|
{
|
|
"entropy": 5.178796768188477,
|
|
"epoch": 9.83239938869078,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.0348046803438986e-05,
|
|
"loss": 4.3477,
|
|
"mean_token_accuracy": 0.262468059360981,
|
|
"num_tokens": 22744772.0,
|
|
"step": 9655
|
|
},
|
|
{
|
|
"entropy": 5.140042924880982,
|
|
"epoch": 9.837493632195619,
|
|
"grad_norm": 1.28125,
|
|
"learning_rate": 5.0326098958538106e-05,
|
|
"loss": 4.2452,
|
|
"mean_token_accuracy": 0.2728316053748131,
|
|
"num_tokens": 22756704.0,
|
|
"step": 9660
|
|
},
|
|
{
|
|
"entropy": 5.199070596694947,
|
|
"epoch": 9.842587875700458,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.0304865347518866e-05,
|
|
"loss": 4.3701,
|
|
"mean_token_accuracy": 0.2572945773601532,
|
|
"num_tokens": 22768845.0,
|
|
"step": 9665
|
|
},
|
|
{
|
|
"entropy": 5.19055962562561,
|
|
"epoch": 9.847682119205299,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.028434603788241e-05,
|
|
"loss": 4.3684,
|
|
"mean_token_accuracy": 0.26124154329299926,
|
|
"num_tokens": 22781071.0,
|
|
"step": 9670
|
|
},
|
|
{
|
|
"entropy": 5.165404796600342,
|
|
"epoch": 9.852776362710138,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.0264541094859306e-05,
|
|
"loss": 4.3535,
|
|
"mean_token_accuracy": 0.2620279356837273,
|
|
"num_tokens": 22793715.0,
|
|
"step": 9675
|
|
},
|
|
{
|
|
"entropy": 5.23808798789978,
|
|
"epoch": 9.857870606214977,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.0245450581408994e-05,
|
|
"loss": 4.4007,
|
|
"mean_token_accuracy": 0.2576723739504814,
|
|
"num_tokens": 22805422.0,
|
|
"step": 9680
|
|
},
|
|
{
|
|
"entropy": 5.209451913833618,
|
|
"epoch": 9.862964849719816,
|
|
"grad_norm": 1.4375,
|
|
"learning_rate": 5.022707455821987e-05,
|
|
"loss": 4.363,
|
|
"mean_token_accuracy": 0.2634808212518692,
|
|
"num_tokens": 22816679.0,
|
|
"step": 9685
|
|
},
|
|
{
|
|
"entropy": 5.189386034011841,
|
|
"epoch": 9.868059093224655,
|
|
"grad_norm": 1.2890625,
|
|
"learning_rate": 5.020941308370896e-05,
|
|
"loss": 4.3611,
|
|
"mean_token_accuracy": 0.2662105232477188,
|
|
"num_tokens": 22829684.0,
|
|
"step": 9690
|
|
},
|
|
{
|
|
"entropy": 5.21067795753479,
|
|
"epoch": 9.873153336729496,
|
|
"grad_norm": 1.5,
|
|
"learning_rate": 5.0192466214021724e-05,
|
|
"loss": 4.3815,
|
|
"mean_token_accuracy": 0.2592469319701195,
|
|
"num_tokens": 22840946.0,
|
|
"step": 9695
|
|
},
|
|
{
|
|
"entropy": 5.2343462944030765,
|
|
"epoch": 9.878247580234335,
|
|
"grad_norm": 1.21875,
|
|
"learning_rate": 5.017623400303194e-05,
|
|
"loss": 4.402,
|
|
"mean_token_accuracy": 0.253300778567791,
|
|
"num_tokens": 22852759.0,
|
|
"step": 9700
|
|
},
|
|
{
|
|
"entropy": 5.247484731674194,
|
|
"epoch": 9.883341823739174,
|
|
"grad_norm": 1.3359375,
|
|
"learning_rate": 5.016071650234148e-05,
|
|
"loss": 4.3915,
|
|
"mean_token_accuracy": 0.25756223797798156,
|
|
"num_tokens": 22865134.0,
|
|
"step": 9705
|
|
},
|
|
{
|
|
"entropy": 5.248297214508057,
|
|
"epoch": 9.888436067244013,
|
|
"grad_norm": 1.3203125,
|
|
"learning_rate": 5.014591376128017e-05,
|
|
"loss": 4.4089,
|
|
"mean_token_accuracy": 0.2574723526835442,
|
|
"num_tokens": 22876906.0,
|
|
"step": 9710
|
|
},
|
|
{
|
|
"entropy": 5.245439100265503,
|
|
"epoch": 9.893530310748854,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.0131825826905617e-05,
|
|
"loss": 4.4079,
|
|
"mean_token_accuracy": 0.257714731991291,
|
|
"num_tokens": 22889625.0,
|
|
"step": 9715
|
|
},
|
|
{
|
|
"entropy": 5.162558460235596,
|
|
"epoch": 9.898624554253693,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.011845274400312e-05,
|
|
"loss": 4.3671,
|
|
"mean_token_accuracy": 0.2592877417802811,
|
|
"num_tokens": 22902024.0,
|
|
"step": 9720
|
|
},
|
|
{
|
|
"entropy": 5.170391082763672,
|
|
"epoch": 9.903718797758533,
|
|
"grad_norm": 1.2578125,
|
|
"learning_rate": 5.010579455508539e-05,
|
|
"loss": 4.402,
|
|
"mean_token_accuracy": 0.2586463674902916,
|
|
"num_tokens": 22915078.0,
|
|
"step": 9725
|
|
},
|
|
{
|
|
"entropy": 5.222092723846435,
|
|
"epoch": 9.908813041263372,
|
|
"grad_norm": 1.1953125,
|
|
"learning_rate": 5.0093851300392616e-05,
|
|
"loss": 4.4286,
|
|
"mean_token_accuracy": 0.25738802552223206,
|
|
"num_tokens": 22927768.0,
|
|
"step": 9730
|
|
},
|
|
{
|
|
"entropy": 5.246504068374634,
|
|
"epoch": 9.913907284768213,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.008262301789214e-05,
|
|
"loss": 4.461,
|
|
"mean_token_accuracy": 0.24662546515464784,
|
|
"num_tokens": 22940779.0,
|
|
"step": 9735
|
|
},
|
|
{
|
|
"entropy": 5.260292673110962,
|
|
"epoch": 9.919001528273052,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.007210974327844e-05,
|
|
"loss": 4.4857,
|
|
"mean_token_accuracy": 0.2504152551293373,
|
|
"num_tokens": 22953761.0,
|
|
"step": 9740
|
|
},
|
|
{
|
|
"entropy": 5.19365291595459,
|
|
"epoch": 9.92409577177789,
|
|
"grad_norm": 1.2734375,
|
|
"learning_rate": 5.006231150997305e-05,
|
|
"loss": 4.4028,
|
|
"mean_token_accuracy": 0.2610335901379585,
|
|
"num_tokens": 22966904.0,
|
|
"step": 9745
|
|
},
|
|
{
|
|
"entropy": 5.199558258056641,
|
|
"epoch": 9.92919001528273,
|
|
"grad_norm": 1.296875,
|
|
"learning_rate": 5.0053228349124315e-05,
|
|
"loss": 4.3444,
|
|
"mean_token_accuracy": 0.25964693278074263,
|
|
"num_tokens": 22977996.0,
|
|
"step": 9750
|
|
},
|
|
{
|
|
"entropy": 5.1969235897064205,
|
|
"epoch": 9.93428425878757,
|
|
"grad_norm": 1.4921875,
|
|
"learning_rate": 5.004486028960742e-05,
|
|
"loss": 4.3746,
|
|
"mean_token_accuracy": 0.2665391132235527,
|
|
"num_tokens": 22988709.0,
|
|
"step": 9755
|
|
},
|
|
{
|
|
"entropy": 5.151747608184815,
|
|
"epoch": 9.93937850229241,
|
|
"grad_norm": 1.3125,
|
|
"learning_rate": 5.00372073580243e-05,
|
|
"loss": 4.3132,
|
|
"mean_token_accuracy": 0.2646899178624153,
|
|
"num_tokens": 23000108.0,
|
|
"step": 9760
|
|
},
|
|
{
|
|
"entropy": 5.243110609054566,
|
|
"epoch": 9.944472745797249,
|
|
"grad_norm": 1.3515625,
|
|
"learning_rate": 5.003026957870346e-05,
|
|
"loss": 4.3577,
|
|
"mean_token_accuracy": 0.26162149012088776,
|
|
"num_tokens": 23011932.0,
|
|
"step": 9765
|
|
},
|
|
{
|
|
"entropy": 5.179471158981324,
|
|
"epoch": 9.949566989302088,
|
|
"grad_norm": 1.1875,
|
|
"learning_rate": 5.002404697369994e-05,
|
|
"loss": 4.3547,
|
|
"mean_token_accuracy": 0.25971881598234176,
|
|
"num_tokens": 23024422.0,
|
|
"step": 9770
|
|
},
|
|
{
|
|
"entropy": 5.238095426559449,
|
|
"epoch": 9.954661232806927,
|
|
"grad_norm": 1.34375,
|
|
"learning_rate": 5.001853956279529e-05,
|
|
"loss": 4.4247,
|
|
"mean_token_accuracy": 0.25481459200382234,
|
|
"num_tokens": 23036161.0,
|
|
"step": 9775
|
|
},
|
|
{
|
|
"entropy": 5.190629339218139,
|
|
"epoch": 9.959755476311768,
|
|
"grad_norm": 1.3671875,
|
|
"learning_rate": 5.001374736349748e-05,
|
|
"loss": 4.3721,
|
|
"mean_token_accuracy": 0.26199475675821304,
|
|
"num_tokens": 23048528.0,
|
|
"step": 9780
|
|
},
|
|
{
|
|
"entropy": 5.1933009147644045,
|
|
"epoch": 9.964849719816607,
|
|
"grad_norm": 1.3984375,
|
|
"learning_rate": 5.000967039104079e-05,
|
|
"loss": 4.3142,
|
|
"mean_token_accuracy": 0.26235527247190477,
|
|
"num_tokens": 23060265.0,
|
|
"step": 9785
|
|
},
|
|
{
|
|
"entropy": 5.228091382980347,
|
|
"epoch": 9.969943963321446,
|
|
"grad_norm": 1.328125,
|
|
"learning_rate": 5.0006308658385846e-05,
|
|
"loss": 4.4146,
|
|
"mean_token_accuracy": 0.2544662818312645,
|
|
"num_tokens": 23073450.0,
|
|
"step": 9790
|
|
},
|
|
{
|
|
"entropy": 5.2528692245483395,
|
|
"epoch": 9.975038206826286,
|
|
"grad_norm": 1.359375,
|
|
"learning_rate": 5.000366217621953e-05,
|
|
"loss": 4.4616,
|
|
"mean_token_accuracy": 0.249209164083004,
|
|
"num_tokens": 23085231.0,
|
|
"step": 9795
|
|
},
|
|
{
|
|
"entropy": 5.165295791625977,
|
|
"epoch": 9.980132450331126,
|
|
"grad_norm": 1.515625,
|
|
"learning_rate": 5.0001730952954974e-05,
|
|
"loss": 4.3368,
|
|
"mean_token_accuracy": 0.25955434143543243,
|
|
"num_tokens": 23096949.0,
|
|
"step": 9800
|
|
},
|
|
{
|
|
"entropy": 5.201594734191895,
|
|
"epoch": 9.985226693835966,
|
|
"grad_norm": 1.3046875,
|
|
"learning_rate": 5.000051499473146e-05,
|
|
"loss": 4.386,
|
|
"mean_token_accuracy": 0.260998909175396,
|
|
"num_tokens": 23108609.0,
|
|
"step": 9805
|
|
},
|
|
{
|
|
"entropy": 5.237290716171264,
|
|
"epoch": 9.990320937340805,
|
|
"grad_norm": 1.4609375,
|
|
"learning_rate": 5.000001430541451e-05,
|
|
"loss": 4.375,
|
|
"mean_token_accuracy": 0.2558904021978378,
|
|
"num_tokens": 23118745.0,
|
|
"step": 9810
|
|
}
|
|
],
|
|
"logging_steps": 5,
|
|
"max_steps": 9810,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 10,
|
|
"save_steps": 1000,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 3.6941797161216e+16,
|
|
"train_batch_size": 16,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|