nisten's picture
Upload folder using huggingface_hub
ad1a955 verified
{
"best_metric": 0.5838193893432617,
"best_model_checkpoint": "./0.4b_finetuned_results/checkpoint-2500",
"epoch": 3.7425149700598803,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014970059880239521,
"grad_norm": 4.375,
"learning_rate": 6.666666666666667e-05,
"loss": 3.8882,
"step": 10
},
{
"epoch": 0.029940119760479042,
"grad_norm": 6.0625,
"learning_rate": 0.00013333333333333334,
"loss": 3.2257,
"step": 20
},
{
"epoch": 0.04491017964071856,
"grad_norm": 6.28125,
"learning_rate": 0.0002,
"loss": 2.92,
"step": 30
},
{
"epoch": 0.059880239520958084,
"grad_norm": 1.9765625,
"learning_rate": 0.00019999938668382333,
"loss": 2.3984,
"step": 40
},
{
"epoch": 0.0748502994011976,
"grad_norm": 1.484375,
"learning_rate": 0.00019999754674281632,
"loss": 2.1626,
"step": 50
},
{
"epoch": 0.08982035928143713,
"grad_norm": 3.375,
"learning_rate": 0.0001999944801995484,
"loss": 2.0388,
"step": 60
},
{
"epoch": 0.10479041916167664,
"grad_norm": 1.7890625,
"learning_rate": 0.0001999901870916347,
"loss": 2.0121,
"step": 70
},
{
"epoch": 0.11976047904191617,
"grad_norm": 1.609375,
"learning_rate": 0.00019998466747173592,
"loss": 1.8579,
"step": 80
},
{
"epoch": 0.1347305389221557,
"grad_norm": 0.81640625,
"learning_rate": 0.00019997792140755746,
"loss": 1.8254,
"step": 90
},
{
"epoch": 0.1497005988023952,
"grad_norm": 1.515625,
"learning_rate": 0.0001999699489818488,
"loss": 1.7037,
"step": 100
},
{
"epoch": 0.16467065868263472,
"grad_norm": 0.94140625,
"learning_rate": 0.00019996075029240219,
"loss": 1.6647,
"step": 110
},
{
"epoch": 0.17964071856287425,
"grad_norm": 0.61328125,
"learning_rate": 0.0001999503254520518,
"loss": 1.5988,
"step": 120
},
{
"epoch": 0.19461077844311378,
"grad_norm": 0.337890625,
"learning_rate": 0.00019993867458867207,
"loss": 1.6197,
"step": 130
},
{
"epoch": 0.20958083832335328,
"grad_norm": 0.47265625,
"learning_rate": 0.00019992579784517626,
"loss": 1.5954,
"step": 140
},
{
"epoch": 0.2245508982035928,
"grad_norm": 0.33203125,
"learning_rate": 0.00019991169537951468,
"loss": 1.5666,
"step": 150
},
{
"epoch": 0.23952095808383234,
"grad_norm": 0.52734375,
"learning_rate": 0.00019989636736467278,
"loss": 1.5227,
"step": 160
},
{
"epoch": 0.25449101796407186,
"grad_norm": 0.34375,
"learning_rate": 0.00019987981398866887,
"loss": 1.5048,
"step": 170
},
{
"epoch": 0.2694610778443114,
"grad_norm": 0.46875,
"learning_rate": 0.00019986203545455203,
"loss": 1.4755,
"step": 180
},
{
"epoch": 0.2844311377245509,
"grad_norm": 0.51953125,
"learning_rate": 0.0001998430319803996,
"loss": 1.4505,
"step": 190
},
{
"epoch": 0.2994011976047904,
"grad_norm": 0.38671875,
"learning_rate": 0.00019982280379931422,
"loss": 1.4295,
"step": 200
},
{
"epoch": 0.3143712574850299,
"grad_norm": 0.34765625,
"learning_rate": 0.00019980135115942136,
"loss": 1.4683,
"step": 210
},
{
"epoch": 0.32934131736526945,
"grad_norm": 0.306640625,
"learning_rate": 0.00019977867432386604,
"loss": 1.4427,
"step": 220
},
{
"epoch": 0.344311377245509,
"grad_norm": 0.357421875,
"learning_rate": 0.00019975477357080966,
"loss": 1.3852,
"step": 230
},
{
"epoch": 0.3592814371257485,
"grad_norm": 0.361328125,
"learning_rate": 0.00019972964919342663,
"loss": 1.427,
"step": 240
},
{
"epoch": 0.37425149700598803,
"grad_norm": 0.306640625,
"learning_rate": 0.00019970330149990062,
"loss": 1.3759,
"step": 250
},
{
"epoch": 0.38922155688622756,
"grad_norm": 0.3515625,
"learning_rate": 0.00019967573081342103,
"loss": 1.3559,
"step": 260
},
{
"epoch": 0.4041916167664671,
"grad_norm": 0.28515625,
"learning_rate": 0.00019964693747217874,
"loss": 1.3715,
"step": 270
},
{
"epoch": 0.41916167664670656,
"grad_norm": 0.30859375,
"learning_rate": 0.00019961692182936225,
"loss": 1.2932,
"step": 280
},
{
"epoch": 0.4341317365269461,
"grad_norm": 0.306640625,
"learning_rate": 0.00019958568425315314,
"loss": 1.3086,
"step": 290
},
{
"epoch": 0.4491017964071856,
"grad_norm": 0.291015625,
"learning_rate": 0.00019955322512672162,
"loss": 1.3091,
"step": 300
},
{
"epoch": 0.46407185628742514,
"grad_norm": 0.248046875,
"learning_rate": 0.00019951954484822182,
"loss": 1.3196,
"step": 310
},
{
"epoch": 0.47904191616766467,
"grad_norm": 0.267578125,
"learning_rate": 0.00019948464383078696,
"loss": 1.2944,
"step": 320
},
{
"epoch": 0.4940119760479042,
"grad_norm": 0.375,
"learning_rate": 0.00019944852250252418,
"loss": 1.3461,
"step": 330
},
{
"epoch": 0.5089820359281437,
"grad_norm": 0.275390625,
"learning_rate": 0.00019941118130650942,
"loss": 1.3221,
"step": 340
},
{
"epoch": 0.5239520958083832,
"grad_norm": 0.23828125,
"learning_rate": 0.00019937262070078183,
"loss": 1.3111,
"step": 350
},
{
"epoch": 0.5389221556886228,
"grad_norm": 0.2578125,
"learning_rate": 0.0001993328411583383,
"loss": 1.3128,
"step": 360
},
{
"epoch": 0.5538922155688623,
"grad_norm": 0.2578125,
"learning_rate": 0.00019929184316712758,
"loss": 1.2618,
"step": 370
},
{
"epoch": 0.5688622754491018,
"grad_norm": 0.29296875,
"learning_rate": 0.00019924962723004425,
"loss": 1.2893,
"step": 380
},
{
"epoch": 0.5838323353293413,
"grad_norm": 0.30859375,
"learning_rate": 0.0001992061938649227,
"loss": 1.2727,
"step": 390
},
{
"epoch": 0.5988023952095808,
"grad_norm": 0.3359375,
"learning_rate": 0.0001991615436045306,
"loss": 1.293,
"step": 400
},
{
"epoch": 0.6137724550898204,
"grad_norm": 0.314453125,
"learning_rate": 0.0001991156769965625,
"loss": 1.2692,
"step": 410
},
{
"epoch": 0.6287425149700598,
"grad_norm": 0.326171875,
"learning_rate": 0.00019906859460363307,
"loss": 1.2588,
"step": 420
},
{
"epoch": 0.6437125748502994,
"grad_norm": 0.26953125,
"learning_rate": 0.00019902029700327018,
"loss": 1.2576,
"step": 430
},
{
"epoch": 0.6586826347305389,
"grad_norm": 0.2890625,
"learning_rate": 0.0001989707847879078,
"loss": 1.2595,
"step": 440
},
{
"epoch": 0.6736526946107785,
"grad_norm": 0.337890625,
"learning_rate": 0.00019892005856487878,
"loss": 1.2331,
"step": 450
},
{
"epoch": 0.688622754491018,
"grad_norm": 0.28515625,
"learning_rate": 0.0001988681189564074,
"loss": 1.2161,
"step": 460
},
{
"epoch": 0.7035928143712575,
"grad_norm": 0.25390625,
"learning_rate": 0.0001988149665996017,
"loss": 1.2675,
"step": 470
},
{
"epoch": 0.718562874251497,
"grad_norm": 0.26953125,
"learning_rate": 0.00019876060214644566,
"loss": 1.269,
"step": 480
},
{
"epoch": 0.7335329341317365,
"grad_norm": 0.40625,
"learning_rate": 0.00019870502626379127,
"loss": 1.2342,
"step": 490
},
{
"epoch": 0.7485029940119761,
"grad_norm": 0.298828125,
"learning_rate": 0.00019864823963335033,
"loss": 1.2351,
"step": 500
},
{
"epoch": 0.7485029940119761,
"eval_loss": 1.1021808385849,
"eval_runtime": 109.4058,
"eval_samples_per_second": 9.14,
"eval_steps_per_second": 1.143,
"step": 500
},
{
"epoch": 0.7634730538922155,
"grad_norm": 0.3671875,
"learning_rate": 0.00019859024295168593,
"loss": 1.2235,
"step": 510
},
{
"epoch": 0.7784431137724551,
"grad_norm": 0.267578125,
"learning_rate": 0.0001985310369302042,
"loss": 1.2353,
"step": 520
},
{
"epoch": 0.7934131736526946,
"grad_norm": 0.24609375,
"learning_rate": 0.00019847062229514533,
"loss": 1.2445,
"step": 530
},
{
"epoch": 0.8083832335329342,
"grad_norm": 0.265625,
"learning_rate": 0.00019840899978757485,
"loss": 1.2687,
"step": 540
},
{
"epoch": 0.8233532934131736,
"grad_norm": 0.2138671875,
"learning_rate": 0.0001983461701633742,
"loss": 1.2026,
"step": 550
},
{
"epoch": 0.8383233532934131,
"grad_norm": 0.283203125,
"learning_rate": 0.00019828213419323208,
"loss": 1.2304,
"step": 560
},
{
"epoch": 0.8532934131736527,
"grad_norm": 0.26953125,
"learning_rate": 0.00019821689266263427,
"loss": 1.1961,
"step": 570
},
{
"epoch": 0.8682634730538922,
"grad_norm": 0.251953125,
"learning_rate": 0.00019815044637185456,
"loss": 1.158,
"step": 580
},
{
"epoch": 0.8832335329341318,
"grad_norm": 0.251953125,
"learning_rate": 0.00019808279613594464,
"loss": 1.1804,
"step": 590
},
{
"epoch": 0.8982035928143712,
"grad_norm": 0.25390625,
"learning_rate": 0.00019801394278472418,
"loss": 1.1705,
"step": 600
},
{
"epoch": 0.9131736526946108,
"grad_norm": 0.259765625,
"learning_rate": 0.0001979438871627707,
"loss": 1.1816,
"step": 610
},
{
"epoch": 0.9281437125748503,
"grad_norm": 0.3515625,
"learning_rate": 0.00019787263012940905,
"loss": 1.2516,
"step": 620
},
{
"epoch": 0.9431137724550899,
"grad_norm": 0.2734375,
"learning_rate": 0.00019780017255870114,
"loss": 1.2214,
"step": 630
},
{
"epoch": 0.9580838323353293,
"grad_norm": 0.27734375,
"learning_rate": 0.00019772651533943493,
"loss": 1.1855,
"step": 640
},
{
"epoch": 0.9730538922155688,
"grad_norm": 0.345703125,
"learning_rate": 0.0001976516593751137,
"loss": 1.1784,
"step": 650
},
{
"epoch": 0.9880239520958084,
"grad_norm": 0.32421875,
"learning_rate": 0.00019757560558394493,
"loss": 1.194,
"step": 660
},
{
"epoch": 1.0029940119760479,
"grad_norm": 0.283203125,
"learning_rate": 0.00019749835489882905,
"loss": 1.198,
"step": 670
},
{
"epoch": 1.0179640718562875,
"grad_norm": 0.255859375,
"learning_rate": 0.00019741990826734794,
"loss": 1.0274,
"step": 680
},
{
"epoch": 1.032934131736527,
"grad_norm": 0.30078125,
"learning_rate": 0.00019734026665175334,
"loss": 0.9878,
"step": 690
},
{
"epoch": 1.0479041916167664,
"grad_norm": 0.32421875,
"learning_rate": 0.0001972594310289551,
"loss": 1.0292,
"step": 700
},
{
"epoch": 1.062874251497006,
"grad_norm": 0.2890625,
"learning_rate": 0.00019717740239050914,
"loss": 1.0265,
"step": 710
},
{
"epoch": 1.0778443113772456,
"grad_norm": 0.314453125,
"learning_rate": 0.0001970941817426052,
"loss": 0.9696,
"step": 720
},
{
"epoch": 1.092814371257485,
"grad_norm": 0.4453125,
"learning_rate": 0.0001970097701060548,
"loss": 0.9735,
"step": 730
},
{
"epoch": 1.1077844311377245,
"grad_norm": 0.33984375,
"learning_rate": 0.00019692416851627826,
"loss": 1.0029,
"step": 740
},
{
"epoch": 1.122754491017964,
"grad_norm": 0.26171875,
"learning_rate": 0.00019683737802329244,
"loss": 1.0072,
"step": 750
},
{
"epoch": 1.1377245508982037,
"grad_norm": 0.271484375,
"learning_rate": 0.0001967493996916976,
"loss": 1.0173,
"step": 760
},
{
"epoch": 1.152694610778443,
"grad_norm": 0.267578125,
"learning_rate": 0.00019666023460066442,
"loss": 0.9945,
"step": 770
},
{
"epoch": 1.1676646706586826,
"grad_norm": 0.287109375,
"learning_rate": 0.00019656988384392075,
"loss": 0.9927,
"step": 780
},
{
"epoch": 1.1826347305389222,
"grad_norm": 0.283203125,
"learning_rate": 0.00019647834852973818,
"loss": 0.9995,
"step": 790
},
{
"epoch": 1.1976047904191618,
"grad_norm": 0.29296875,
"learning_rate": 0.00019638562978091853,
"loss": 0.9957,
"step": 800
},
{
"epoch": 1.2125748502994012,
"grad_norm": 0.2490234375,
"learning_rate": 0.00019629172873477995,
"loss": 0.9653,
"step": 810
},
{
"epoch": 1.2275449101796407,
"grad_norm": 0.2451171875,
"learning_rate": 0.00019619664654314302,
"loss": 0.9714,
"step": 820
},
{
"epoch": 1.2425149700598803,
"grad_norm": 0.302734375,
"learning_rate": 0.0001961003843723167,
"loss": 1.0226,
"step": 830
},
{
"epoch": 1.2574850299401197,
"grad_norm": 0.283203125,
"learning_rate": 0.00019600294340308398,
"loss": 1.0417,
"step": 840
},
{
"epoch": 1.2724550898203593,
"grad_norm": 0.287109375,
"learning_rate": 0.00019590432483068722,
"loss": 0.9593,
"step": 850
},
{
"epoch": 1.2874251497005988,
"grad_norm": 0.27734375,
"learning_rate": 0.00019580452986481378,
"loss": 1.0255,
"step": 860
},
{
"epoch": 1.3023952095808382,
"grad_norm": 0.341796875,
"learning_rate": 0.00019570355972958097,
"loss": 0.9971,
"step": 870
},
{
"epoch": 1.3173652694610778,
"grad_norm": 0.322265625,
"learning_rate": 0.00019560141566352115,
"loss": 0.9914,
"step": 880
},
{
"epoch": 1.3323353293413174,
"grad_norm": 0.2255859375,
"learning_rate": 0.0001954980989195665,
"loss": 0.9699,
"step": 890
},
{
"epoch": 1.347305389221557,
"grad_norm": 0.25390625,
"learning_rate": 0.0001953936107650336,
"loss": 0.9667,
"step": 900
},
{
"epoch": 1.3622754491017965,
"grad_norm": 0.28515625,
"learning_rate": 0.00019528795248160795,
"loss": 0.9813,
"step": 910
},
{
"epoch": 1.377245508982036,
"grad_norm": 0.23828125,
"learning_rate": 0.0001951811253653283,
"loss": 0.9861,
"step": 920
},
{
"epoch": 1.3922155688622755,
"grad_norm": 0.26953125,
"learning_rate": 0.00019507313072657055,
"loss": 0.9772,
"step": 930
},
{
"epoch": 1.407185628742515,
"grad_norm": 0.259765625,
"learning_rate": 0.00019496396989003193,
"loss": 1.0045,
"step": 940
},
{
"epoch": 1.4221556886227544,
"grad_norm": 0.302734375,
"learning_rate": 0.00019485364419471454,
"loss": 0.9919,
"step": 950
},
{
"epoch": 1.437125748502994,
"grad_norm": 0.279296875,
"learning_rate": 0.00019474215499390912,
"loss": 0.9796,
"step": 960
},
{
"epoch": 1.4520958083832336,
"grad_norm": 0.26171875,
"learning_rate": 0.00019462950365517817,
"loss": 0.9821,
"step": 970
},
{
"epoch": 1.467065868263473,
"grad_norm": 0.3203125,
"learning_rate": 0.00019451569156033954,
"loss": 1.0337,
"step": 980
},
{
"epoch": 1.4820359281437125,
"grad_norm": 0.310546875,
"learning_rate": 0.00019440072010544918,
"loss": 0.9987,
"step": 990
},
{
"epoch": 1.4970059880239521,
"grad_norm": 0.27734375,
"learning_rate": 0.00019428459070078416,
"loss": 1.004,
"step": 1000
},
{
"epoch": 1.4970059880239521,
"eval_loss": 0.9072233438491821,
"eval_runtime": 109.5318,
"eval_samples_per_second": 9.13,
"eval_steps_per_second": 1.141,
"step": 1000
},
{
"epoch": 1.5119760479041915,
"grad_norm": 0.2890625,
"learning_rate": 0.00019416730477082533,
"loss": 0.9444,
"step": 1010
},
{
"epoch": 1.5269461077844313,
"grad_norm": 0.296875,
"learning_rate": 0.00019404886375423984,
"loss": 0.9829,
"step": 1020
},
{
"epoch": 1.5419161676646707,
"grad_norm": 0.27734375,
"learning_rate": 0.00019392926910386353,
"loss": 0.9532,
"step": 1030
},
{
"epoch": 1.55688622754491,
"grad_norm": 0.265625,
"learning_rate": 0.00019380852228668304,
"loss": 0.9769,
"step": 1040
},
{
"epoch": 1.5718562874251498,
"grad_norm": 0.275390625,
"learning_rate": 0.00019368662478381799,
"loss": 0.9783,
"step": 1050
},
{
"epoch": 1.5868263473053892,
"grad_norm": 0.2890625,
"learning_rate": 0.00019356357809050247,
"loss": 0.9881,
"step": 1060
},
{
"epoch": 1.6017964071856288,
"grad_norm": 0.232421875,
"learning_rate": 0.00019343938371606712,
"loss": 0.9883,
"step": 1070
},
{
"epoch": 1.6167664670658684,
"grad_norm": 0.2734375,
"learning_rate": 0.00019331404318392027,
"loss": 0.9893,
"step": 1080
},
{
"epoch": 1.6317365269461077,
"grad_norm": 0.248046875,
"learning_rate": 0.00019318755803152945,
"loss": 0.9851,
"step": 1090
},
{
"epoch": 1.6467065868263473,
"grad_norm": 0.28515625,
"learning_rate": 0.00019305992981040246,
"loss": 0.9531,
"step": 1100
},
{
"epoch": 1.6616766467065869,
"grad_norm": 0.275390625,
"learning_rate": 0.00019293116008606837,
"loss": 0.9717,
"step": 1110
},
{
"epoch": 1.6766467065868262,
"grad_norm": 0.232421875,
"learning_rate": 0.00019280125043805824,
"loss": 0.9699,
"step": 1120
},
{
"epoch": 1.6916167664670658,
"grad_norm": 0.2294921875,
"learning_rate": 0.00019267020245988592,
"loss": 0.9407,
"step": 1130
},
{
"epoch": 1.7065868263473054,
"grad_norm": 0.251953125,
"learning_rate": 0.00019253801775902824,
"loss": 0.977,
"step": 1140
},
{
"epoch": 1.7215568862275448,
"grad_norm": 0.287109375,
"learning_rate": 0.0001924046979569055,
"loss": 0.9549,
"step": 1150
},
{
"epoch": 1.7365269461077846,
"grad_norm": 0.248046875,
"learning_rate": 0.00019227024468886157,
"loss": 0.9824,
"step": 1160
},
{
"epoch": 1.751497005988024,
"grad_norm": 0.259765625,
"learning_rate": 0.00019213465960414368,
"loss": 0.9936,
"step": 1170
},
{
"epoch": 1.7664670658682635,
"grad_norm": 0.29296875,
"learning_rate": 0.00019199794436588243,
"loss": 1.0042,
"step": 1180
},
{
"epoch": 1.781437125748503,
"grad_norm": 0.23828125,
"learning_rate": 0.0001918601006510711,
"loss": 0.9629,
"step": 1190
},
{
"epoch": 1.7964071856287425,
"grad_norm": 0.2890625,
"learning_rate": 0.00019172113015054532,
"loss": 0.9522,
"step": 1200
},
{
"epoch": 1.811377245508982,
"grad_norm": 0.26953125,
"learning_rate": 0.0001915810345689622,
"loss": 0.9806,
"step": 1210
},
{
"epoch": 1.8263473053892216,
"grad_norm": 0.263671875,
"learning_rate": 0.00019143981562477947,
"loss": 0.9736,
"step": 1220
},
{
"epoch": 1.841317365269461,
"grad_norm": 0.2578125,
"learning_rate": 0.00019129747505023436,
"loss": 0.9701,
"step": 1230
},
{
"epoch": 1.8562874251497006,
"grad_norm": 0.22265625,
"learning_rate": 0.00019115401459132247,
"loss": 0.9494,
"step": 1240
},
{
"epoch": 1.8712574850299402,
"grad_norm": 0.251953125,
"learning_rate": 0.00019100943600777615,
"loss": 0.9922,
"step": 1250
},
{
"epoch": 1.8862275449101795,
"grad_norm": 0.2490234375,
"learning_rate": 0.00019086374107304312,
"loss": 0.9711,
"step": 1260
},
{
"epoch": 1.9011976047904193,
"grad_norm": 0.25390625,
"learning_rate": 0.00019071693157426457,
"loss": 0.9664,
"step": 1270
},
{
"epoch": 1.9161676646706587,
"grad_norm": 0.26171875,
"learning_rate": 0.00019056900931225333,
"loss": 0.9591,
"step": 1280
},
{
"epoch": 1.931137724550898,
"grad_norm": 0.380859375,
"learning_rate": 0.00019041997610147167,
"loss": 0.9942,
"step": 1290
},
{
"epoch": 1.9461077844311379,
"grad_norm": 0.2294921875,
"learning_rate": 0.0001902698337700092,
"loss": 0.9391,
"step": 1300
},
{
"epoch": 1.9610778443113772,
"grad_norm": 0.298828125,
"learning_rate": 0.00019011858415956038,
"loss": 0.9993,
"step": 1310
},
{
"epoch": 1.9760479041916168,
"grad_norm": 0.29296875,
"learning_rate": 0.0001899662291254018,
"loss": 0.9571,
"step": 1320
},
{
"epoch": 1.9910179640718564,
"grad_norm": 0.283203125,
"learning_rate": 0.0001898127705363696,
"loss": 0.9835,
"step": 1330
},
{
"epoch": 2.0059880239520957,
"grad_norm": 0.27734375,
"learning_rate": 0.00018965821027483654,
"loss": 0.9305,
"step": 1340
},
{
"epoch": 2.020958083832335,
"grad_norm": 0.26171875,
"learning_rate": 0.00018950255023668876,
"loss": 0.8295,
"step": 1350
},
{
"epoch": 2.035928143712575,
"grad_norm": 0.240234375,
"learning_rate": 0.00018934579233130267,
"loss": 0.7653,
"step": 1360
},
{
"epoch": 2.0508982035928143,
"grad_norm": 0.29296875,
"learning_rate": 0.00018918793848152142,
"loss": 0.7581,
"step": 1370
},
{
"epoch": 2.065868263473054,
"grad_norm": 0.29296875,
"learning_rate": 0.00018902899062363143,
"loss": 0.7983,
"step": 1380
},
{
"epoch": 2.0808383233532934,
"grad_norm": 0.279296875,
"learning_rate": 0.0001888689507073385,
"loss": 0.8187,
"step": 1390
},
{
"epoch": 2.095808383233533,
"grad_norm": 0.29296875,
"learning_rate": 0.0001887078206957441,
"loss": 0.7879,
"step": 1400
},
{
"epoch": 2.1107784431137726,
"grad_norm": 0.2734375,
"learning_rate": 0.000188545602565321,
"loss": 0.8083,
"step": 1410
},
{
"epoch": 2.125748502994012,
"grad_norm": 0.263671875,
"learning_rate": 0.00018838229830588934,
"loss": 0.8057,
"step": 1420
},
{
"epoch": 2.1407185628742513,
"grad_norm": 0.244140625,
"learning_rate": 0.00018821790992059196,
"loss": 0.8194,
"step": 1430
},
{
"epoch": 2.155688622754491,
"grad_norm": 0.2451171875,
"learning_rate": 0.00018805243942587,
"loss": 0.7958,
"step": 1440
},
{
"epoch": 2.1706586826347305,
"grad_norm": 0.248046875,
"learning_rate": 0.00018788588885143808,
"loss": 0.8169,
"step": 1450
},
{
"epoch": 2.18562874251497,
"grad_norm": 0.265625,
"learning_rate": 0.00018771826024025946,
"loss": 0.7722,
"step": 1460
},
{
"epoch": 2.2005988023952097,
"grad_norm": 0.265625,
"learning_rate": 0.0001875495556485208,
"loss": 0.7934,
"step": 1470
},
{
"epoch": 2.215568862275449,
"grad_norm": 0.244140625,
"learning_rate": 0.00018737977714560738,
"loss": 0.7915,
"step": 1480
},
{
"epoch": 2.230538922155689,
"grad_norm": 0.310546875,
"learning_rate": 0.00018720892681407708,
"loss": 0.8021,
"step": 1490
},
{
"epoch": 2.245508982035928,
"grad_norm": 0.298828125,
"learning_rate": 0.00018703700674963547,
"loss": 0.7987,
"step": 1500
},
{
"epoch": 2.245508982035928,
"eval_loss": 0.7798940539360046,
"eval_runtime": 109.62,
"eval_samples_per_second": 9.122,
"eval_steps_per_second": 1.14,
"step": 1500
},
{
"epoch": 2.2604790419161676,
"grad_norm": 0.259765625,
"learning_rate": 0.00018686401906110964,
"loss": 0.7979,
"step": 1510
},
{
"epoch": 2.2754491017964074,
"grad_norm": 0.265625,
"learning_rate": 0.00018668996587042252,
"loss": 0.8255,
"step": 1520
},
{
"epoch": 2.2904191616766467,
"grad_norm": 0.2470703125,
"learning_rate": 0.00018651484931256685,
"loss": 0.8252,
"step": 1530
},
{
"epoch": 2.305389221556886,
"grad_norm": 0.25,
"learning_rate": 0.00018633867153557905,
"loss": 0.8455,
"step": 1540
},
{
"epoch": 2.320359281437126,
"grad_norm": 0.302734375,
"learning_rate": 0.00018616143470051263,
"loss": 0.8118,
"step": 1550
},
{
"epoch": 2.3353293413173652,
"grad_norm": 0.283203125,
"learning_rate": 0.00018598314098141206,
"loss": 0.8122,
"step": 1560
},
{
"epoch": 2.3502994011976046,
"grad_norm": 0.24609375,
"learning_rate": 0.00018580379256528576,
"loss": 0.7965,
"step": 1570
},
{
"epoch": 2.3652694610778444,
"grad_norm": 0.279296875,
"learning_rate": 0.00018562339165207936,
"loss": 0.8309,
"step": 1580
},
{
"epoch": 2.3802395209580838,
"grad_norm": 0.31640625,
"learning_rate": 0.00018544194045464886,
"loss": 0.8046,
"step": 1590
},
{
"epoch": 2.3952095808383236,
"grad_norm": 0.2734375,
"learning_rate": 0.0001852594411987334,
"loss": 0.8467,
"step": 1600
},
{
"epoch": 2.410179640718563,
"grad_norm": 0.275390625,
"learning_rate": 0.00018507589612292783,
"loss": 0.8566,
"step": 1610
},
{
"epoch": 2.4251497005988023,
"grad_norm": 0.30859375,
"learning_rate": 0.00018489130747865548,
"loss": 0.8297,
"step": 1620
},
{
"epoch": 2.440119760479042,
"grad_norm": 0.359375,
"learning_rate": 0.00018470567753014035,
"loss": 0.7823,
"step": 1630
},
{
"epoch": 2.4550898203592815,
"grad_norm": 0.29296875,
"learning_rate": 0.0001845190085543795,
"loss": 0.8558,
"step": 1640
},
{
"epoch": 2.470059880239521,
"grad_norm": 0.3046875,
"learning_rate": 0.0001843313028411149,
"loss": 0.8262,
"step": 1650
},
{
"epoch": 2.4850299401197606,
"grad_norm": 0.2578125,
"learning_rate": 0.00018414256269280564,
"loss": 0.7982,
"step": 1660
},
{
"epoch": 2.5,
"grad_norm": 0.314453125,
"learning_rate": 0.00018395279042459937,
"loss": 0.8182,
"step": 1670
},
{
"epoch": 2.5149700598802394,
"grad_norm": 0.328125,
"learning_rate": 0.00018376198836430417,
"loss": 0.8275,
"step": 1680
},
{
"epoch": 2.529940119760479,
"grad_norm": 0.271484375,
"learning_rate": 0.00018357015885235982,
"loss": 0.8102,
"step": 1690
},
{
"epoch": 2.5449101796407185,
"grad_norm": 0.3125,
"learning_rate": 0.0001833773042418092,
"loss": 0.8145,
"step": 1700
},
{
"epoch": 2.5598802395209583,
"grad_norm": 1.40625,
"learning_rate": 0.00018318342689826938,
"loss": 0.8279,
"step": 1710
},
{
"epoch": 2.5748502994011977,
"grad_norm": 0.275390625,
"learning_rate": 0.00018298852919990252,
"loss": 0.8354,
"step": 1720
},
{
"epoch": 2.589820359281437,
"grad_norm": 0.3125,
"learning_rate": 0.0001827926135373869,
"loss": 0.8106,
"step": 1730
},
{
"epoch": 2.6047904191616764,
"grad_norm": 0.267578125,
"learning_rate": 0.00018259568231388738,
"loss": 0.7983,
"step": 1740
},
{
"epoch": 2.6197604790419162,
"grad_norm": 0.251953125,
"learning_rate": 0.00018239773794502607,
"loss": 0.8183,
"step": 1750
},
{
"epoch": 2.6347305389221556,
"grad_norm": 0.294921875,
"learning_rate": 0.00018219878285885267,
"loss": 0.8462,
"step": 1760
},
{
"epoch": 2.6497005988023954,
"grad_norm": 0.283203125,
"learning_rate": 0.0001819988194958146,
"loss": 0.8227,
"step": 1770
},
{
"epoch": 2.6646706586826348,
"grad_norm": 0.2431640625,
"learning_rate": 0.0001817978503087272,
"loss": 0.8104,
"step": 1780
},
{
"epoch": 2.679640718562874,
"grad_norm": 0.271484375,
"learning_rate": 0.0001815958777627435,
"loss": 0.7972,
"step": 1790
},
{
"epoch": 2.694610778443114,
"grad_norm": 0.283203125,
"learning_rate": 0.00018139290433532416,
"loss": 0.8339,
"step": 1800
},
{
"epoch": 2.7095808383233533,
"grad_norm": 0.298828125,
"learning_rate": 0.00018118893251620682,
"loss": 0.8723,
"step": 1810
},
{
"epoch": 2.724550898203593,
"grad_norm": 0.3203125,
"learning_rate": 0.00018098396480737585,
"loss": 0.8544,
"step": 1820
},
{
"epoch": 2.7395209580838324,
"grad_norm": 0.265625,
"learning_rate": 0.0001807780037230315,
"loss": 0.8557,
"step": 1830
},
{
"epoch": 2.754491017964072,
"grad_norm": 0.279296875,
"learning_rate": 0.00018057105178955905,
"loss": 0.8283,
"step": 1840
},
{
"epoch": 2.769461077844311,
"grad_norm": 0.3828125,
"learning_rate": 0.00018036311154549784,
"loss": 0.7906,
"step": 1850
},
{
"epoch": 2.784431137724551,
"grad_norm": 0.2490234375,
"learning_rate": 0.0001801541855415102,
"loss": 0.8036,
"step": 1860
},
{
"epoch": 2.7994011976047903,
"grad_norm": 0.298828125,
"learning_rate": 0.00017994427634035015,
"loss": 0.7828,
"step": 1870
},
{
"epoch": 2.81437125748503,
"grad_norm": 0.306640625,
"learning_rate": 0.00017973338651683176,
"loss": 0.7915,
"step": 1880
},
{
"epoch": 2.8293413173652695,
"grad_norm": 0.228515625,
"learning_rate": 0.00017952151865779792,
"loss": 0.8141,
"step": 1890
},
{
"epoch": 2.844311377245509,
"grad_norm": 0.349609375,
"learning_rate": 0.00017930867536208826,
"loss": 0.8155,
"step": 1900
},
{
"epoch": 2.8592814371257482,
"grad_norm": 0.310546875,
"learning_rate": 0.00017909485924050758,
"loss": 0.8004,
"step": 1910
},
{
"epoch": 2.874251497005988,
"grad_norm": 0.2470703125,
"learning_rate": 0.00017888007291579357,
"loss": 0.803,
"step": 1920
},
{
"epoch": 2.8892215568862274,
"grad_norm": 0.275390625,
"learning_rate": 0.00017866431902258478,
"loss": 0.804,
"step": 1930
},
{
"epoch": 2.904191616766467,
"grad_norm": 0.310546875,
"learning_rate": 0.00017844760020738827,
"loss": 0.8154,
"step": 1940
},
{
"epoch": 2.9191616766467066,
"grad_norm": 0.251953125,
"learning_rate": 0.00017822991912854713,
"loss": 0.8257,
"step": 1950
},
{
"epoch": 2.934131736526946,
"grad_norm": 0.3125,
"learning_rate": 0.00017801127845620793,
"loss": 0.8386,
"step": 1960
},
{
"epoch": 2.9491017964071857,
"grad_norm": 0.275390625,
"learning_rate": 0.0001777916808722879,
"loss": 0.8003,
"step": 1970
},
{
"epoch": 2.964071856287425,
"grad_norm": 0.28515625,
"learning_rate": 0.000177571129070442,
"loss": 0.8055,
"step": 1980
},
{
"epoch": 2.979041916167665,
"grad_norm": 0.271484375,
"learning_rate": 0.00017734962575603,
"loss": 0.8233,
"step": 1990
},
{
"epoch": 2.9940119760479043,
"grad_norm": 0.255859375,
"learning_rate": 0.00017712717364608328,
"loss": 0.8106,
"step": 2000
},
{
"epoch": 2.9940119760479043,
"eval_loss": 0.6911507844924927,
"eval_runtime": 109.6711,
"eval_samples_per_second": 9.118,
"eval_steps_per_second": 1.14,
"step": 2000
},
{
"epoch": 3.0089820359281436,
"grad_norm": 0.37890625,
"learning_rate": 0.00017690377546927133,
"loss": 0.7276,
"step": 2010
},
{
"epoch": 3.0239520958083834,
"grad_norm": 0.27734375,
"learning_rate": 0.00017667943396586848,
"loss": 0.6882,
"step": 2020
},
{
"epoch": 3.038922155688623,
"grad_norm": 0.291015625,
"learning_rate": 0.0001764541518877202,
"loss": 0.6786,
"step": 2030
},
{
"epoch": 3.053892215568862,
"grad_norm": 0.31640625,
"learning_rate": 0.00017622793199820934,
"loss": 0.6352,
"step": 2040
},
{
"epoch": 3.068862275449102,
"grad_norm": 0.294921875,
"learning_rate": 0.00017600077707222224,
"loss": 0.6648,
"step": 2050
},
{
"epoch": 3.0838323353293413,
"grad_norm": 0.294921875,
"learning_rate": 0.00017577268989611472,
"loss": 0.6601,
"step": 2060
},
{
"epoch": 3.0988023952095807,
"grad_norm": 0.361328125,
"learning_rate": 0.00017554367326767792,
"loss": 0.6645,
"step": 2070
},
{
"epoch": 3.1137724550898205,
"grad_norm": 0.251953125,
"learning_rate": 0.00017531372999610384,
"loss": 0.6631,
"step": 2080
},
{
"epoch": 3.12874251497006,
"grad_norm": 0.30078125,
"learning_rate": 0.0001750828629019511,
"loss": 0.6451,
"step": 2090
},
{
"epoch": 3.143712574850299,
"grad_norm": 0.365234375,
"learning_rate": 0.00017485107481711012,
"loss": 0.6703,
"step": 2100
},
{
"epoch": 3.158682634730539,
"grad_norm": 0.341796875,
"learning_rate": 0.00017461836858476856,
"loss": 0.6598,
"step": 2110
},
{
"epoch": 3.1736526946107784,
"grad_norm": 0.287109375,
"learning_rate": 0.00017438474705937639,
"loss": 0.6689,
"step": 2120
},
{
"epoch": 3.1886227544910177,
"grad_norm": 0.3125,
"learning_rate": 0.0001741502131066107,
"loss": 0.6741,
"step": 2130
},
{
"epoch": 3.2035928143712575,
"grad_norm": 0.31640625,
"learning_rate": 0.000173914769603341,
"loss": 0.6691,
"step": 2140
},
{
"epoch": 3.218562874251497,
"grad_norm": 0.322265625,
"learning_rate": 0.00017367841943759338,
"loss": 0.6702,
"step": 2150
},
{
"epoch": 3.2335329341317367,
"grad_norm": 0.265625,
"learning_rate": 0.00017344116550851543,
"loss": 0.6451,
"step": 2160
},
{
"epoch": 3.248502994011976,
"grad_norm": 0.328125,
"learning_rate": 0.00017320301072634066,
"loss": 0.6507,
"step": 2170
},
{
"epoch": 3.2634730538922154,
"grad_norm": 0.32421875,
"learning_rate": 0.00017296395801235265,
"loss": 0.695,
"step": 2180
},
{
"epoch": 3.2784431137724552,
"grad_norm": 0.31640625,
"learning_rate": 0.00017272401029884933,
"loss": 0.6798,
"step": 2190
},
{
"epoch": 3.2934131736526946,
"grad_norm": 0.330078125,
"learning_rate": 0.000172483170529107,
"loss": 0.6526,
"step": 2200
},
{
"epoch": 3.308383233532934,
"grad_norm": 0.35546875,
"learning_rate": 0.00017224144165734417,
"loss": 0.6538,
"step": 2210
},
{
"epoch": 3.3233532934131738,
"grad_norm": 0.291015625,
"learning_rate": 0.00017199882664868538,
"loss": 0.6777,
"step": 2220
},
{
"epoch": 3.338323353293413,
"grad_norm": 0.28515625,
"learning_rate": 0.00017175532847912487,
"loss": 0.6762,
"step": 2230
},
{
"epoch": 3.3532934131736525,
"grad_norm": 0.3203125,
"learning_rate": 0.00017151095013548994,
"loss": 0.673,
"step": 2240
},
{
"epoch": 3.3682634730538923,
"grad_norm": 0.318359375,
"learning_rate": 0.00017126569461540443,
"loss": 0.6757,
"step": 2250
},
{
"epoch": 3.3832335329341316,
"grad_norm": 0.3046875,
"learning_rate": 0.00017101956492725185,
"loss": 0.6563,
"step": 2260
},
{
"epoch": 3.3982035928143715,
"grad_norm": 0.267578125,
"learning_rate": 0.00017077256409013866,
"loss": 0.6877,
"step": 2270
},
{
"epoch": 3.413173652694611,
"grad_norm": 0.328125,
"learning_rate": 0.000170524695133857,
"loss": 0.67,
"step": 2280
},
{
"epoch": 3.42814371257485,
"grad_norm": 0.326171875,
"learning_rate": 0.00017027596109884768,
"loss": 0.6808,
"step": 2290
},
{
"epoch": 3.44311377245509,
"grad_norm": 0.318359375,
"learning_rate": 0.00017002636503616282,
"loss": 0.6941,
"step": 2300
},
{
"epoch": 3.4580838323353293,
"grad_norm": 0.279296875,
"learning_rate": 0.00016977591000742854,
"loss": 0.6798,
"step": 2310
},
{
"epoch": 3.4730538922155687,
"grad_norm": 0.287109375,
"learning_rate": 0.0001695245990848072,
"loss": 0.6718,
"step": 2320
},
{
"epoch": 3.4880239520958085,
"grad_norm": 0.30859375,
"learning_rate": 0.00016927243535095997,
"loss": 0.6483,
"step": 2330
},
{
"epoch": 3.502994011976048,
"grad_norm": 0.333984375,
"learning_rate": 0.00016901942189900867,
"loss": 0.7177,
"step": 2340
},
{
"epoch": 3.5179640718562872,
"grad_norm": 0.34765625,
"learning_rate": 0.00016876556183249822,
"loss": 0.6833,
"step": 2350
},
{
"epoch": 3.532934131736527,
"grad_norm": 0.365234375,
"learning_rate": 0.00016851085826535838,
"loss": 0.6826,
"step": 2360
},
{
"epoch": 3.5479041916167664,
"grad_norm": 0.396484375,
"learning_rate": 0.00016825531432186543,
"loss": 0.6835,
"step": 2370
},
{
"epoch": 3.562874251497006,
"grad_norm": 0.359375,
"learning_rate": 0.00016799893313660408,
"loss": 0.6791,
"step": 2380
},
{
"epoch": 3.5778443113772456,
"grad_norm": 0.291015625,
"learning_rate": 0.0001677417178544289,
"loss": 0.6787,
"step": 2390
},
{
"epoch": 3.592814371257485,
"grad_norm": 0.296875,
"learning_rate": 0.00016748367163042576,
"loss": 0.6542,
"step": 2400
},
{
"epoch": 3.6077844311377243,
"grad_norm": 0.30078125,
"learning_rate": 0.00016722479762987317,
"loss": 0.6805,
"step": 2410
},
{
"epoch": 3.622754491017964,
"grad_norm": 0.314453125,
"learning_rate": 0.0001669650990282033,
"loss": 0.6859,
"step": 2420
},
{
"epoch": 3.6377245508982035,
"grad_norm": 0.32421875,
"learning_rate": 0.00016670457901096328,
"loss": 0.6633,
"step": 2430
},
{
"epoch": 3.6526946107784433,
"grad_norm": 0.32421875,
"learning_rate": 0.00016644324077377592,
"loss": 0.6958,
"step": 2440
},
{
"epoch": 3.6676646706586826,
"grad_norm": 0.3125,
"learning_rate": 0.00016618108752230052,
"loss": 0.6965,
"step": 2450
},
{
"epoch": 3.682634730538922,
"grad_norm": 0.3046875,
"learning_rate": 0.00016591812247219377,
"loss": 0.6851,
"step": 2460
},
{
"epoch": 3.697604790419162,
"grad_norm": 0.400390625,
"learning_rate": 0.00016565434884907002,
"loss": 0.6669,
"step": 2470
},
{
"epoch": 3.712574850299401,
"grad_norm": 0.306640625,
"learning_rate": 0.0001653897698884619,
"loss": 0.6672,
"step": 2480
},
{
"epoch": 3.727544910179641,
"grad_norm": 0.30078125,
"learning_rate": 0.00016512438883578044,
"loss": 0.7049,
"step": 2490
},
{
"epoch": 3.7425149700598803,
"grad_norm": 0.30859375,
"learning_rate": 0.0001648582089462756,
"loss": 0.6821,
"step": 2500
},
{
"epoch": 3.7425149700598803,
"eval_loss": 0.5838193893432617,
"eval_runtime": 109.8377,
"eval_samples_per_second": 9.104,
"eval_steps_per_second": 1.138,
"step": 2500
}
],
"logging_steps": 10,
"max_steps": 9000,
"num_input_tokens_seen": 0,
"num_train_epochs": 14,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.7382403865051136e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}