CodeIsAbstract's picture
Upload folder using huggingface_hub
c19bc03 verified
Raw
History Blame Contribute Delete
92.3 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 2787,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005382131324004306,
"grad_norm": 19.25,
"learning_rate": 5.7142857142857145e-06,
"loss": 7.5826,
"step": 5
},
{
"epoch": 0.010764262648008612,
"grad_norm": 24.125,
"learning_rate": 1.2857142857142857e-05,
"loss": 7.7389,
"step": 10
},
{
"epoch": 0.016146393972012917,
"grad_norm": 20.375,
"learning_rate": 2e-05,
"loss": 8.0474,
"step": 15
},
{
"epoch": 0.021528525296017224,
"grad_norm": 17.375,
"learning_rate": 2.714285714285714e-05,
"loss": 7.2989,
"step": 20
},
{
"epoch": 0.02691065662002153,
"grad_norm": 15.0625,
"learning_rate": 3.428571428571429e-05,
"loss": 7.8579,
"step": 25
},
{
"epoch": 0.03229278794402583,
"grad_norm": 12.875,
"learning_rate": 4.1428571428571437e-05,
"loss": 7.3271,
"step": 30
},
{
"epoch": 0.03767491926803014,
"grad_norm": 8.5,
"learning_rate": 4.8571428571428576e-05,
"loss": 7.0945,
"step": 35
},
{
"epoch": 0.04305705059203445,
"grad_norm": 7.46875,
"learning_rate": 5.571428571428572e-05,
"loss": 6.3577,
"step": 40
},
{
"epoch": 0.04843918191603875,
"grad_norm": 7.40625,
"learning_rate": 6.285714285714286e-05,
"loss": 6.2656,
"step": 45
},
{
"epoch": 0.05382131324004306,
"grad_norm": 3.53125,
"learning_rate": 7e-05,
"loss": 6.2146,
"step": 50
},
{
"epoch": 0.059203444564047365,
"grad_norm": 3.671875,
"learning_rate": 7.714285714285715e-05,
"loss": 5.7147,
"step": 55
},
{
"epoch": 0.06458557588805167,
"grad_norm": 2.6875,
"learning_rate": 8.428571428571429e-05,
"loss": 5.2684,
"step": 60
},
{
"epoch": 0.06996770721205597,
"grad_norm": 2.203125,
"learning_rate": 9.142857142857143e-05,
"loss": 4.914,
"step": 65
},
{
"epoch": 0.07534983853606028,
"grad_norm": 2.28125,
"learning_rate": 9.857142857142858e-05,
"loss": 5.5474,
"step": 70
},
{
"epoch": 0.08073196986006459,
"grad_norm": 3.03125,
"learning_rate": 0.00010571428571428572,
"loss": 4.0901,
"step": 75
},
{
"epoch": 0.0861141011840689,
"grad_norm": 2.40625,
"learning_rate": 0.00011285714285714286,
"loss": 4.1259,
"step": 80
},
{
"epoch": 0.09149623250807319,
"grad_norm": 2.328125,
"learning_rate": 0.00012,
"loss": 3.7235,
"step": 85
},
{
"epoch": 0.0968783638320775,
"grad_norm": 2.46875,
"learning_rate": 0.00012714285714285714,
"loss": 3.1657,
"step": 90
},
{
"epoch": 0.10226049515608181,
"grad_norm": 3.171875,
"learning_rate": 0.00013428571428571428,
"loss": 3.4388,
"step": 95
},
{
"epoch": 0.10764262648008611,
"grad_norm": 2.34375,
"learning_rate": 0.00014142857142857145,
"loss": 3.637,
"step": 100
},
{
"epoch": 0.11302475780409042,
"grad_norm": 1.9375,
"learning_rate": 0.00014857142857142857,
"loss": 2.8895,
"step": 105
},
{
"epoch": 0.11840688912809473,
"grad_norm": 2.40625,
"learning_rate": 0.00015571428571428572,
"loss": 3.011,
"step": 110
},
{
"epoch": 0.12378902045209902,
"grad_norm": 1.6796875,
"learning_rate": 0.00016285714285714287,
"loss": 2.5217,
"step": 115
},
{
"epoch": 0.12917115177610333,
"grad_norm": 1.609375,
"learning_rate": 0.00017,
"loss": 2.3684,
"step": 120
},
{
"epoch": 0.13455328310010764,
"grad_norm": 1.3203125,
"learning_rate": 0.00017714285714285713,
"loss": 2.6268,
"step": 125
},
{
"epoch": 0.13993541442411195,
"grad_norm": 1.6953125,
"learning_rate": 0.00018428571428571428,
"loss": 2.2101,
"step": 130
},
{
"epoch": 0.14531754574811626,
"grad_norm": 1.71875,
"learning_rate": 0.00019142857142857145,
"loss": 2.1823,
"step": 135
},
{
"epoch": 0.15069967707212056,
"grad_norm": 0.9375,
"learning_rate": 0.0001985714285714286,
"loss": 1.8939,
"step": 140
},
{
"epoch": 0.15608180839612487,
"grad_norm": 1.3125,
"learning_rate": 0.00019999887311127372,
"loss": 2.6186,
"step": 145
},
{
"epoch": 0.16146393972012918,
"grad_norm": 1.15625,
"learning_rate": 0.0001999942951693512,
"loss": 2.3448,
"step": 150
},
{
"epoch": 0.1668460710441335,
"grad_norm": 1.53125,
"learning_rate": 0.00019998619590477638,
"loss": 2.0453,
"step": 155
},
{
"epoch": 0.1722282023681378,
"grad_norm": 1.1328125,
"learning_rate": 0.00019997457560276666,
"loss": 1.9159,
"step": 160
},
{
"epoch": 0.17761033369214208,
"grad_norm": 1.3359375,
"learning_rate": 0.00019995943467253385,
"loss": 2.2564,
"step": 165
},
{
"epoch": 0.18299246501614638,
"grad_norm": 1.453125,
"learning_rate": 0.00019994077364726925,
"loss": 2.1459,
"step": 170
},
{
"epoch": 0.1883745963401507,
"grad_norm": 1.15625,
"learning_rate": 0.00019991859318412537,
"loss": 2.3652,
"step": 175
},
{
"epoch": 0.193756727664155,
"grad_norm": 1.703125,
"learning_rate": 0.00019989289406419238,
"loss": 2.0883,
"step": 180
},
{
"epoch": 0.1991388589881593,
"grad_norm": 1.046875,
"learning_rate": 0.00019986367719247082,
"loss": 2.0466,
"step": 185
},
{
"epoch": 0.20452099031216361,
"grad_norm": 1.9765625,
"learning_rate": 0.00019983094359783977,
"loss": 2.0306,
"step": 190
},
{
"epoch": 0.20990312163616792,
"grad_norm": 0.93359375,
"learning_rate": 0.00019979469443302046,
"loss": 1.73,
"step": 195
},
{
"epoch": 0.21528525296017223,
"grad_norm": 1.203125,
"learning_rate": 0.0001997549309745357,
"loss": 2.1835,
"step": 200
},
{
"epoch": 0.22066738428417654,
"grad_norm": 0.80859375,
"learning_rate": 0.00019971165462266512,
"loss": 1.8594,
"step": 205
},
{
"epoch": 0.22604951560818085,
"grad_norm": 0.98828125,
"learning_rate": 0.00019966486690139564,
"loss": 1.8338,
"step": 210
},
{
"epoch": 0.23143164693218515,
"grad_norm": 1.15625,
"learning_rate": 0.0001996145694583678,
"loss": 2.0899,
"step": 215
},
{
"epoch": 0.23681377825618946,
"grad_norm": 1.296875,
"learning_rate": 0.000199560764064818,
"loss": 2.0116,
"step": 220
},
{
"epoch": 0.24219590958019377,
"grad_norm": 1.4375,
"learning_rate": 0.00019950345261551583,
"loss": 1.9816,
"step": 225
},
{
"epoch": 0.24757804090419805,
"grad_norm": 0.89453125,
"learning_rate": 0.0001994426371286974,
"loss": 1.4429,
"step": 230
},
{
"epoch": 0.2529601722282024,
"grad_norm": 1.171875,
"learning_rate": 0.00019937831974599447,
"loss": 1.8191,
"step": 235
},
{
"epoch": 0.25834230355220666,
"grad_norm": 1.0625,
"learning_rate": 0.0001993105027323588,
"loss": 2.0092,
"step": 240
},
{
"epoch": 0.263724434876211,
"grad_norm": 0.95703125,
"learning_rate": 0.00019923918847598247,
"loss": 1.6442,
"step": 245
},
{
"epoch": 0.2691065662002153,
"grad_norm": 1.1953125,
"learning_rate": 0.00019916437948821382,
"loss": 2.29,
"step": 250
},
{
"epoch": 0.2744886975242196,
"grad_norm": 1.2734375,
"learning_rate": 0.00019908607840346903,
"loss": 1.7178,
"step": 255
},
{
"epoch": 0.2798708288482239,
"grad_norm": 0.91015625,
"learning_rate": 0.00019900428797913915,
"loss": 1.8539,
"step": 260
},
{
"epoch": 0.2852529601722282,
"grad_norm": 1.21875,
"learning_rate": 0.0001989190110954933,
"loss": 1.9345,
"step": 265
},
{
"epoch": 0.2906350914962325,
"grad_norm": 1.3515625,
"learning_rate": 0.000198830250755577,
"loss": 2.1381,
"step": 270
},
{
"epoch": 0.2960172228202368,
"grad_norm": 1.015625,
"learning_rate": 0.0001987380100851065,
"loss": 2.0466,
"step": 275
},
{
"epoch": 0.3013993541442411,
"grad_norm": 0.953125,
"learning_rate": 0.00019864229233235875,
"loss": 2.1104,
"step": 280
},
{
"epoch": 0.3067814854682454,
"grad_norm": 0.984375,
"learning_rate": 0.000198543100868057,
"loss": 2.0808,
"step": 285
},
{
"epoch": 0.31216361679224974,
"grad_norm": 1.390625,
"learning_rate": 0.00019844043918525195,
"loss": 1.9378,
"step": 290
},
{
"epoch": 0.317545748116254,
"grad_norm": 0.78515625,
"learning_rate": 0.00019833431089919898,
"loss": 1.565,
"step": 295
},
{
"epoch": 0.32292787944025836,
"grad_norm": 1.7109375,
"learning_rate": 0.00019822471974723064,
"loss": 1.8316,
"step": 300
},
{
"epoch": 0.32831001076426264,
"grad_norm": 1.0234375,
"learning_rate": 0.0001981116695886252,
"loss": 1.9357,
"step": 305
},
{
"epoch": 0.333692142088267,
"grad_norm": 0.99609375,
"learning_rate": 0.00019799516440447058,
"loss": 1.7745,
"step": 310
},
{
"epoch": 0.33907427341227125,
"grad_norm": 0.97265625,
"learning_rate": 0.00019787520829752427,
"loss": 1.8947,
"step": 315
},
{
"epoch": 0.3444564047362756,
"grad_norm": 0.8046875,
"learning_rate": 0.00019775180549206888,
"loss": 1.6128,
"step": 320
},
{
"epoch": 0.34983853606027987,
"grad_norm": 0.921875,
"learning_rate": 0.0001976249603337632,
"loss": 1.6003,
"step": 325
},
{
"epoch": 0.35522066738428415,
"grad_norm": 0.7421875,
"learning_rate": 0.00019749467728948943,
"loss": 1.7543,
"step": 330
},
{
"epoch": 0.3606027987082885,
"grad_norm": 1.46875,
"learning_rate": 0.0001973609609471956,
"loss": 1.8543,
"step": 335
},
{
"epoch": 0.36598493003229277,
"grad_norm": 0.953125,
"learning_rate": 0.00019722381601573413,
"loss": 1.7436,
"step": 340
},
{
"epoch": 0.3713670613562971,
"grad_norm": 0.9765625,
"learning_rate": 0.0001970832473246962,
"loss": 2.1039,
"step": 345
},
{
"epoch": 0.3767491926803014,
"grad_norm": 0.76171875,
"learning_rate": 0.0001969392598242413,
"loss": 1.9624,
"step": 350
},
{
"epoch": 0.3821313240043057,
"grad_norm": 0.6796875,
"learning_rate": 0.0001967918585849232,
"loss": 1.4343,
"step": 355
},
{
"epoch": 0.38751345532831,
"grad_norm": 1.2421875,
"learning_rate": 0.00019664104879751123,
"loss": 1.5505,
"step": 360
},
{
"epoch": 0.39289558665231433,
"grad_norm": 0.86328125,
"learning_rate": 0.00019648683577280757,
"loss": 1.6731,
"step": 365
},
{
"epoch": 0.3982777179763186,
"grad_norm": 0.90234375,
"learning_rate": 0.0001963292249414602,
"loss": 1.6294,
"step": 370
},
{
"epoch": 0.40365984930032295,
"grad_norm": 0.80859375,
"learning_rate": 0.0001961682218537717,
"loss": 1.7152,
"step": 375
},
{
"epoch": 0.40904198062432723,
"grad_norm": 1.2890625,
"learning_rate": 0.00019600383217950365,
"loss": 2.0493,
"step": 380
},
{
"epoch": 0.41442411194833156,
"grad_norm": 1.2890625,
"learning_rate": 0.00019583606170767718,
"loss": 1.809,
"step": 385
},
{
"epoch": 0.41980624327233584,
"grad_norm": 0.93359375,
"learning_rate": 0.00019566491634636897,
"loss": 2.0224,
"step": 390
},
{
"epoch": 0.4251883745963401,
"grad_norm": 1.1484375,
"learning_rate": 0.0001954904021225032,
"loss": 1.8455,
"step": 395
},
{
"epoch": 0.43057050592034446,
"grad_norm": 0.83984375,
"learning_rate": 0.0001953125251816394,
"loss": 1.5119,
"step": 400
},
{
"epoch": 0.43595263724434874,
"grad_norm": 0.95703125,
"learning_rate": 0.00019513129178775588,
"loss": 1.6183,
"step": 405
},
{
"epoch": 0.4413347685683531,
"grad_norm": 0.97265625,
"learning_rate": 0.0001949467083230293,
"loss": 1.5994,
"step": 410
},
{
"epoch": 0.44671689989235736,
"grad_norm": 0.92578125,
"learning_rate": 0.0001947587812876099,
"loss": 1.9839,
"step": 415
},
{
"epoch": 0.4520990312163617,
"grad_norm": 0.95703125,
"learning_rate": 0.00019456751729939238,
"loss": 1.7201,
"step": 420
},
{
"epoch": 0.45748116254036597,
"grad_norm": 0.74609375,
"learning_rate": 0.00019437292309378324,
"loss": 1.8024,
"step": 425
},
{
"epoch": 0.4628632938643703,
"grad_norm": 1.609375,
"learning_rate": 0.00019417500552346316,
"loss": 1.421,
"step": 430
},
{
"epoch": 0.4682454251883746,
"grad_norm": 0.98046875,
"learning_rate": 0.000193973771558146,
"loss": 1.5199,
"step": 435
},
{
"epoch": 0.4736275565123789,
"grad_norm": 0.97265625,
"learning_rate": 0.0001937692282843333,
"loss": 1.8052,
"step": 440
},
{
"epoch": 0.4790096878363832,
"grad_norm": 1.078125,
"learning_rate": 0.00019356138290506461,
"loss": 2.0869,
"step": 445
},
{
"epoch": 0.48439181916038754,
"grad_norm": 0.99609375,
"learning_rate": 0.00019335024273966383,
"loss": 1.5393,
"step": 450
},
{
"epoch": 0.4897739504843918,
"grad_norm": 1.171875,
"learning_rate": 0.00019313581522348164,
"loss": 1.6464,
"step": 455
},
{
"epoch": 0.4951560818083961,
"grad_norm": 0.83203125,
"learning_rate": 0.00019291810790763355,
"loss": 1.8133,
"step": 460
},
{
"epoch": 0.5005382131324004,
"grad_norm": 1.453125,
"learning_rate": 0.00019269712845873397,
"loss": 2.0506,
"step": 465
},
{
"epoch": 0.5059203444564048,
"grad_norm": 0.84375,
"learning_rate": 0.00019247288465862615,
"loss": 1.95,
"step": 470
},
{
"epoch": 0.511302475780409,
"grad_norm": 0.91015625,
"learning_rate": 0.0001922453844041084,
"loss": 1.565,
"step": 475
},
{
"epoch": 0.5166846071044133,
"grad_norm": 0.71875,
"learning_rate": 0.00019201463570665573,
"loss": 1.7664,
"step": 480
},
{
"epoch": 0.5220667384284177,
"grad_norm": 0.6015625,
"learning_rate": 0.0001917806466921378,
"loss": 1.6515,
"step": 485
},
{
"epoch": 0.527448869752422,
"grad_norm": 0.69140625,
"learning_rate": 0.00019154342560053297,
"loss": 1.654,
"step": 490
},
{
"epoch": 0.5328310010764262,
"grad_norm": 0.62109375,
"learning_rate": 0.0001913029807856378,
"loss": 1.5976,
"step": 495
},
{
"epoch": 0.5382131324004306,
"grad_norm": 1.0859375,
"learning_rate": 0.00019105932071477303,
"loss": 1.497,
"step": 500
},
{
"epoch": 0.5435952637244349,
"grad_norm": 0.87890625,
"learning_rate": 0.00019081245396848547,
"loss": 1.6065,
"step": 505
},
{
"epoch": 0.5489773950484392,
"grad_norm": 0.78125,
"learning_rate": 0.00019056238924024574,
"loss": 1.3089,
"step": 510
},
{
"epoch": 0.5543595263724435,
"grad_norm": 1.0546875,
"learning_rate": 0.00019030913533614208,
"loss": 1.8274,
"step": 515
},
{
"epoch": 0.5597416576964478,
"grad_norm": 1.1953125,
"learning_rate": 0.00019005270117457043,
"loss": 1.6165,
"step": 520
},
{
"epoch": 0.5651237890204521,
"grad_norm": 1.0625,
"learning_rate": 0.00018979309578592016,
"loss": 1.578,
"step": 525
},
{
"epoch": 0.5705059203444564,
"grad_norm": 1.7109375,
"learning_rate": 0.0001895303283122561,
"loss": 1.7197,
"step": 530
},
{
"epoch": 0.5758880516684607,
"grad_norm": 1.0390625,
"learning_rate": 0.00018926440800699678,
"loss": 1.7235,
"step": 535
},
{
"epoch": 0.581270182992465,
"grad_norm": 0.92578125,
"learning_rate": 0.0001889953442345884,
"loss": 1.536,
"step": 540
},
{
"epoch": 0.5866523143164694,
"grad_norm": 0.8125,
"learning_rate": 0.000188723146470175,
"loss": 1.8374,
"step": 545
},
{
"epoch": 0.5920344456404736,
"grad_norm": 0.96484375,
"learning_rate": 0.00018844782429926495,
"loss": 1.4953,
"step": 550
},
{
"epoch": 0.5974165769644779,
"grad_norm": 0.7734375,
"learning_rate": 0.0001881693874173934,
"loss": 1.3424,
"step": 555
},
{
"epoch": 0.6027987082884823,
"grad_norm": 0.7890625,
"learning_rate": 0.0001878878456297807,
"loss": 1.4368,
"step": 560
},
{
"epoch": 0.6081808396124866,
"grad_norm": 1.09375,
"learning_rate": 0.00018760320885098715,
"loss": 1.7983,
"step": 565
},
{
"epoch": 0.6135629709364908,
"grad_norm": 1.1015625,
"learning_rate": 0.00018731548710456398,
"loss": 1.8513,
"step": 570
},
{
"epoch": 0.6189451022604952,
"grad_norm": 2.125,
"learning_rate": 0.00018702469052270023,
"loss": 2.1254,
"step": 575
},
{
"epoch": 0.6243272335844995,
"grad_norm": 0.7421875,
"learning_rate": 0.00018673082934586607,
"loss": 1.6763,
"step": 580
},
{
"epoch": 0.6297093649085038,
"grad_norm": 1.140625,
"learning_rate": 0.00018643391392245197,
"loss": 1.6641,
"step": 585
},
{
"epoch": 0.635091496232508,
"grad_norm": 0.890625,
"learning_rate": 0.00018613395470840454,
"loss": 2.0576,
"step": 590
},
{
"epoch": 0.6404736275565124,
"grad_norm": 0.74609375,
"learning_rate": 0.0001858309622668581,
"loss": 1.643,
"step": 595
},
{
"epoch": 0.6458557588805167,
"grad_norm": 1.3671875,
"learning_rate": 0.00018552494726776283,
"loss": 1.8816,
"step": 600
},
{
"epoch": 0.6512378902045209,
"grad_norm": 0.8515625,
"learning_rate": 0.00018521592048750907,
"loss": 1.4728,
"step": 605
},
{
"epoch": 0.6566200215285253,
"grad_norm": 0.94921875,
"learning_rate": 0.00018490389280854754,
"loss": 1.6078,
"step": 610
},
{
"epoch": 0.6620021528525296,
"grad_norm": 0.96484375,
"learning_rate": 0.0001845888752190065,
"loss": 1.6509,
"step": 615
},
{
"epoch": 0.667384284176534,
"grad_norm": 0.73046875,
"learning_rate": 0.00018427087881230455,
"loss": 1.1777,
"step": 620
},
{
"epoch": 0.6727664155005382,
"grad_norm": 1.09375,
"learning_rate": 0.00018394991478676005,
"loss": 1.4283,
"step": 625
},
{
"epoch": 0.6781485468245425,
"grad_norm": 0.859375,
"learning_rate": 0.0001836259944451967,
"loss": 1.6932,
"step": 630
},
{
"epoch": 0.6835306781485468,
"grad_norm": 1.03125,
"learning_rate": 0.00018329912919454565,
"loss": 1.4168,
"step": 635
},
{
"epoch": 0.6889128094725512,
"grad_norm": 0.77734375,
"learning_rate": 0.00018296933054544367,
"loss": 1.7149,
"step": 640
},
{
"epoch": 0.6942949407965554,
"grad_norm": 0.921875,
"learning_rate": 0.00018263661011182783,
"loss": 1.5492,
"step": 645
},
{
"epoch": 0.6996770721205597,
"grad_norm": 0.8828125,
"learning_rate": 0.00018230097961052658,
"loss": 1.8432,
"step": 650
},
{
"epoch": 0.7050592034445641,
"grad_norm": 0.8359375,
"learning_rate": 0.00018196245086084703,
"loss": 1.5463,
"step": 655
},
{
"epoch": 0.7104413347685683,
"grad_norm": 1.03125,
"learning_rate": 0.00018162103578415884,
"loss": 1.6883,
"step": 660
},
{
"epoch": 0.7158234660925726,
"grad_norm": 0.8515625,
"learning_rate": 0.0001812767464034743,
"loss": 1.5512,
"step": 665
},
{
"epoch": 0.721205597416577,
"grad_norm": 0.91796875,
"learning_rate": 0.00018092959484302515,
"loss": 1.387,
"step": 670
},
{
"epoch": 0.7265877287405813,
"grad_norm": 0.7421875,
"learning_rate": 0.00018057959332783518,
"loss": 1.2412,
"step": 675
},
{
"epoch": 0.7319698600645855,
"grad_norm": 0.6875,
"learning_rate": 0.0001802267541832903,
"loss": 1.4303,
"step": 680
},
{
"epoch": 0.7373519913885899,
"grad_norm": 1.359375,
"learning_rate": 0.00017987108983470403,
"loss": 1.9346,
"step": 685
},
{
"epoch": 0.7427341227125942,
"grad_norm": 1.890625,
"learning_rate": 0.0001795126128068801,
"loss": 1.5194,
"step": 690
},
{
"epoch": 0.7481162540365985,
"grad_norm": 1.1796875,
"learning_rate": 0.00017915133572367155,
"loss": 1.9612,
"step": 695
},
{
"epoch": 0.7534983853606028,
"grad_norm": 1.15625,
"learning_rate": 0.00017878727130753592,
"loss": 1.8595,
"step": 700
},
{
"epoch": 0.7588805166846071,
"grad_norm": 1.1640625,
"learning_rate": 0.00017842043237908733,
"loss": 1.4777,
"step": 705
},
{
"epoch": 0.7642626480086114,
"grad_norm": 1.1171875,
"learning_rate": 0.00017805083185664508,
"loss": 1.6248,
"step": 710
},
{
"epoch": 0.7696447793326158,
"grad_norm": 0.82421875,
"learning_rate": 0.00017767848275577856,
"loss": 1.7387,
"step": 715
},
{
"epoch": 0.77502691065662,
"grad_norm": 0.83984375,
"learning_rate": 0.0001773033981888491,
"loss": 1.7641,
"step": 720
},
{
"epoch": 0.7804090419806243,
"grad_norm": 0.8359375,
"learning_rate": 0.000176925591364548,
"loss": 1.853,
"step": 725
},
{
"epoch": 0.7857911733046287,
"grad_norm": 1.046875,
"learning_rate": 0.00017654507558743153,
"loss": 1.3802,
"step": 730
},
{
"epoch": 0.7911733046286329,
"grad_norm": 0.87890625,
"learning_rate": 0.00017616186425745248,
"loss": 1.8941,
"step": 735
},
{
"epoch": 0.7965554359526372,
"grad_norm": 0.80078125,
"learning_rate": 0.00017577597086948797,
"loss": 1.6458,
"step": 740
},
{
"epoch": 0.8019375672766416,
"grad_norm": 1.0078125,
"learning_rate": 0.00017538740901286464,
"loss": 1.6792,
"step": 745
},
{
"epoch": 0.8073196986006459,
"grad_norm": 0.640625,
"learning_rate": 0.00017499619237087969,
"loss": 1.389,
"step": 750
},
{
"epoch": 0.8127018299246501,
"grad_norm": 1.015625,
"learning_rate": 0.00017460233472031935,
"loss": 2.0551,
"step": 755
},
{
"epoch": 0.8180839612486545,
"grad_norm": 1.0625,
"learning_rate": 0.0001742058499309735,
"loss": 1.6721,
"step": 760
},
{
"epoch": 0.8234660925726588,
"grad_norm": 0.83203125,
"learning_rate": 0.00017380675196514739,
"loss": 1.3685,
"step": 765
},
{
"epoch": 0.8288482238966631,
"grad_norm": 1.09375,
"learning_rate": 0.00017340505487716985,
"loss": 1.7255,
"step": 770
},
{
"epoch": 0.8342303552206674,
"grad_norm": 1.0546875,
"learning_rate": 0.00017300077281289845,
"loss": 1.5643,
"step": 775
},
{
"epoch": 0.8396124865446717,
"grad_norm": 0.8203125,
"learning_rate": 0.00017259392000922125,
"loss": 1.516,
"step": 780
},
{
"epoch": 0.844994617868676,
"grad_norm": 1.1328125,
"learning_rate": 0.0001721845107935556,
"loss": 1.6089,
"step": 785
},
{
"epoch": 0.8503767491926802,
"grad_norm": 0.67578125,
"learning_rate": 0.00017177255958334342,
"loss": 1.5203,
"step": 790
},
{
"epoch": 0.8557588805166846,
"grad_norm": 0.796875,
"learning_rate": 0.00017135808088554358,
"loss": 2.1079,
"step": 795
},
{
"epoch": 0.8611410118406889,
"grad_norm": 0.87890625,
"learning_rate": 0.000170941089296121,
"loss": 1.8979,
"step": 800
},
{
"epoch": 0.8665231431646933,
"grad_norm": 0.90625,
"learning_rate": 0.00017052159949953278,
"loss": 1.4225,
"step": 805
},
{
"epoch": 0.8719052744886975,
"grad_norm": 1.03125,
"learning_rate": 0.00017009962626821082,
"loss": 1.7616,
"step": 810
},
{
"epoch": 0.8772874058127018,
"grad_norm": 0.87890625,
"learning_rate": 0.0001696751844620419,
"loss": 1.8864,
"step": 815
},
{
"epoch": 0.8826695371367062,
"grad_norm": 1.234375,
"learning_rate": 0.00016924828902784407,
"loss": 1.6568,
"step": 820
},
{
"epoch": 0.8880516684607105,
"grad_norm": 0.8046875,
"learning_rate": 0.00016881895499884072,
"loss": 1.6826,
"step": 825
},
{
"epoch": 0.8934337997847147,
"grad_norm": 0.95703125,
"learning_rate": 0.00016838719749413063,
"loss": 1.3967,
"step": 830
},
{
"epoch": 0.898815931108719,
"grad_norm": 1.1953125,
"learning_rate": 0.00016795303171815616,
"loss": 1.7213,
"step": 835
},
{
"epoch": 0.9041980624327234,
"grad_norm": 0.8125,
"learning_rate": 0.00016751647296016725,
"loss": 1.6946,
"step": 840
},
{
"epoch": 0.9095801937567277,
"grad_norm": 0.71484375,
"learning_rate": 0.00016707753659368337,
"loss": 1.8869,
"step": 845
},
{
"epoch": 0.9149623250807319,
"grad_norm": 1.0,
"learning_rate": 0.0001666362380759521,
"loss": 1.5258,
"step": 850
},
{
"epoch": 0.9203444564047363,
"grad_norm": 1.28125,
"learning_rate": 0.0001661925929474046,
"loss": 1.8925,
"step": 855
},
{
"epoch": 0.9257265877287406,
"grad_norm": 0.84765625,
"learning_rate": 0.00016574661683110858,
"loss": 1.7461,
"step": 860
},
{
"epoch": 0.9311087190527448,
"grad_norm": 1.0546875,
"learning_rate": 0.00016529832543221796,
"loss": 1.6321,
"step": 865
},
{
"epoch": 0.9364908503767492,
"grad_norm": 0.83203125,
"learning_rate": 0.00016484773453741999,
"loss": 1.4394,
"step": 870
},
{
"epoch": 0.9418729817007535,
"grad_norm": 0.84375,
"learning_rate": 0.0001643948600143791,
"loss": 1.7612,
"step": 875
},
{
"epoch": 0.9472551130247578,
"grad_norm": 1.2890625,
"learning_rate": 0.00016393971781117827,
"loss": 1.5663,
"step": 880
},
{
"epoch": 0.9526372443487621,
"grad_norm": 0.9375,
"learning_rate": 0.00016348232395575738,
"loss": 1.6009,
"step": 885
},
{
"epoch": 0.9580193756727664,
"grad_norm": 0.796875,
"learning_rate": 0.0001630226945553487,
"loss": 1.5051,
"step": 890
},
{
"epoch": 0.9634015069967707,
"grad_norm": 0.58984375,
"learning_rate": 0.00016256084579590991,
"loss": 1.3798,
"step": 895
},
{
"epoch": 0.9687836383207751,
"grad_norm": 1.1328125,
"learning_rate": 0.00016209679394155378,
"loss": 1.542,
"step": 900
},
{
"epoch": 0.9741657696447793,
"grad_norm": 0.875,
"learning_rate": 0.0001616305553339756,
"loss": 1.7239,
"step": 905
},
{
"epoch": 0.9795479009687836,
"grad_norm": 1.0078125,
"learning_rate": 0.0001611621463918778,
"loss": 1.6649,
"step": 910
},
{
"epoch": 0.984930032292788,
"grad_norm": 0.91796875,
"learning_rate": 0.0001606915836103916,
"loss": 1.5315,
"step": 915
},
{
"epoch": 0.9903121636167922,
"grad_norm": 0.7734375,
"learning_rate": 0.00016021888356049607,
"loss": 1.6008,
"step": 920
},
{
"epoch": 0.9956942949407965,
"grad_norm": 0.875,
"learning_rate": 0.00015974406288843485,
"loss": 1.4304,
"step": 925
},
{
"epoch": 1.0010764262648009,
"grad_norm": 0.76953125,
"learning_rate": 0.0001592671383151297,
"loss": 1.2241,
"step": 930
},
{
"epoch": 1.0064585575888052,
"grad_norm": 0.6640625,
"learning_rate": 0.0001587881266355918,
"loss": 1.2942,
"step": 935
},
{
"epoch": 1.0118406889128095,
"grad_norm": 0.51953125,
"learning_rate": 0.00015830704471833028,
"loss": 1.4488,
"step": 940
},
{
"epoch": 1.0172228202368139,
"grad_norm": 1.03125,
"learning_rate": 0.00015782390950475804,
"loss": 1.3599,
"step": 945
},
{
"epoch": 1.022604951560818,
"grad_norm": 0.95703125,
"learning_rate": 0.0001573387380085955,
"loss": 1.4847,
"step": 950
},
{
"epoch": 1.0279870828848223,
"grad_norm": 0.69921875,
"learning_rate": 0.00015685154731527113,
"loss": 1.7192,
"step": 955
},
{
"epoch": 1.0333692142088267,
"grad_norm": 0.69140625,
"learning_rate": 0.0001563623545813199,
"loss": 1.3389,
"step": 960
},
{
"epoch": 1.038751345532831,
"grad_norm": 0.83984375,
"learning_rate": 0.0001558711770337792,
"loss": 1.625,
"step": 965
},
{
"epoch": 1.0441334768568353,
"grad_norm": 0.9453125,
"learning_rate": 0.00015537803196958195,
"loss": 1.5407,
"step": 970
},
{
"epoch": 1.0495156081808397,
"grad_norm": 0.6328125,
"learning_rate": 0.00015488293675494777,
"loss": 1.3429,
"step": 975
},
{
"epoch": 1.054897739504844,
"grad_norm": 0.953125,
"learning_rate": 0.00015438590882477118,
"loss": 1.016,
"step": 980
},
{
"epoch": 1.0602798708288481,
"grad_norm": 1.0,
"learning_rate": 0.00015388696568200788,
"loss": 1.428,
"step": 985
},
{
"epoch": 1.0656620021528525,
"grad_norm": 0.84765625,
"learning_rate": 0.00015338612489705807,
"loss": 1.2952,
"step": 990
},
{
"epoch": 1.0710441334768568,
"grad_norm": 0.73828125,
"learning_rate": 0.00015288340410714798,
"loss": 1.4856,
"step": 995
},
{
"epoch": 1.0764262648008611,
"grad_norm": 0.80078125,
"learning_rate": 0.00015237882101570854,
"loss": 1.7727,
"step": 1000
},
{
"epoch": 1.0818083961248655,
"grad_norm": 0.796875,
"learning_rate": 0.00015187239339175225,
"loss": 1.6775,
"step": 1005
},
{
"epoch": 1.0871905274488698,
"grad_norm": 0.91796875,
"learning_rate": 0.00015136413906924708,
"loss": 1.4311,
"step": 1010
},
{
"epoch": 1.0925726587728741,
"grad_norm": 1.2109375,
"learning_rate": 0.00015085407594648864,
"loss": 1.4255,
"step": 1015
},
{
"epoch": 1.0979547900968785,
"grad_norm": 0.84765625,
"learning_rate": 0.00015034222198547002,
"loss": 1.4475,
"step": 1020
},
{
"epoch": 1.1033369214208826,
"grad_norm": 0.61328125,
"learning_rate": 0.00014982859521124893,
"loss": 1.6184,
"step": 1025
},
{
"epoch": 1.108719052744887,
"grad_norm": 0.85546875,
"learning_rate": 0.00014931321371131323,
"loss": 1.403,
"step": 1030
},
{
"epoch": 1.1141011840688912,
"grad_norm": 0.61328125,
"learning_rate": 0.00014879609563494373,
"loss": 1.3015,
"step": 1035
},
{
"epoch": 1.1194833153928956,
"grad_norm": 0.7734375,
"learning_rate": 0.00014827725919257532,
"loss": 1.3636,
"step": 1040
},
{
"epoch": 1.1248654467169,
"grad_norm": 0.74609375,
"learning_rate": 0.0001477567226551555,
"loss": 1.318,
"step": 1045
},
{
"epoch": 1.1302475780409043,
"grad_norm": 0.578125,
"learning_rate": 0.00014723450435350101,
"loss": 1.4797,
"step": 1050
},
{
"epoch": 1.1356297093649086,
"grad_norm": 1.703125,
"learning_rate": 0.00014671062267765232,
"loss": 1.7593,
"step": 1055
},
{
"epoch": 1.141011840688913,
"grad_norm": 0.6328125,
"learning_rate": 0.000146185096076226,
"loss": 1.4441,
"step": 1060
},
{
"epoch": 1.146393972012917,
"grad_norm": 0.8828125,
"learning_rate": 0.00014565794305576512,
"loss": 1.3185,
"step": 1065
},
{
"epoch": 1.1517761033369214,
"grad_norm": 1.0859375,
"learning_rate": 0.0001451291821800874,
"loss": 1.335,
"step": 1070
},
{
"epoch": 1.1571582346609257,
"grad_norm": 0.92578125,
"learning_rate": 0.00014459883206963158,
"loss": 1.9123,
"step": 1075
},
{
"epoch": 1.16254036598493,
"grad_norm": 1.1640625,
"learning_rate": 0.00014406691140080174,
"loss": 1.5474,
"step": 1080
},
{
"epoch": 1.1679224973089344,
"grad_norm": 0.78125,
"learning_rate": 0.00014353343890530947,
"loss": 1.7054,
"step": 1085
},
{
"epoch": 1.1733046286329387,
"grad_norm": 1.1015625,
"learning_rate": 0.00014299843336951435,
"loss": 1.7048,
"step": 1090
},
{
"epoch": 1.178686759956943,
"grad_norm": 0.91015625,
"learning_rate": 0.0001424619136337623,
"loss": 1.4729,
"step": 1095
},
{
"epoch": 1.1840688912809472,
"grad_norm": 0.8046875,
"learning_rate": 0.00014192389859172215,
"loss": 1.5441,
"step": 1100
},
{
"epoch": 1.1894510226049515,
"grad_norm": 1.0234375,
"learning_rate": 0.0001413844071897203,
"loss": 1.3415,
"step": 1105
},
{
"epoch": 1.1948331539289558,
"grad_norm": 0.6796875,
"learning_rate": 0.00014084345842607353,
"loss": 1.6552,
"step": 1110
},
{
"epoch": 1.2002152852529602,
"grad_norm": 1.015625,
"learning_rate": 0.00014030107135041994,
"loss": 1.6165,
"step": 1115
},
{
"epoch": 1.2055974165769645,
"grad_norm": 0.9453125,
"learning_rate": 0.00013975726506304815,
"loss": 1.7135,
"step": 1120
},
{
"epoch": 1.2109795479009688,
"grad_norm": 0.9765625,
"learning_rate": 0.0001392120587142246,
"loss": 1.3601,
"step": 1125
},
{
"epoch": 1.2163616792249732,
"grad_norm": 0.86328125,
"learning_rate": 0.00013866547150351925,
"loss": 1.5728,
"step": 1130
},
{
"epoch": 1.2217438105489773,
"grad_norm": 1.0390625,
"learning_rate": 0.00013811752267912946,
"loss": 1.5137,
"step": 1135
},
{
"epoch": 1.2271259418729816,
"grad_norm": 0.7578125,
"learning_rate": 0.00013756823153720214,
"loss": 1.5428,
"step": 1140
},
{
"epoch": 1.232508073196986,
"grad_norm": 1.03125,
"learning_rate": 0.0001370176174211542,
"loss": 1.5014,
"step": 1145
},
{
"epoch": 1.2378902045209903,
"grad_norm": 1.0546875,
"learning_rate": 0.00013646569972099136,
"loss": 1.6073,
"step": 1150
},
{
"epoch": 1.2432723358449946,
"grad_norm": 0.79296875,
"learning_rate": 0.00013591249787262542,
"loss": 1.4086,
"step": 1155
},
{
"epoch": 1.248654467168999,
"grad_norm": 1.4921875,
"learning_rate": 0.0001353580313571898,
"loss": 1.633,
"step": 1160
},
{
"epoch": 1.2540365984930033,
"grad_norm": 0.68359375,
"learning_rate": 0.00013480231970035335,
"loss": 1.7106,
"step": 1165
},
{
"epoch": 1.2594187298170074,
"grad_norm": 0.74609375,
"learning_rate": 0.00013424538247163294,
"loss": 1.5289,
"step": 1170
},
{
"epoch": 1.264800861141012,
"grad_norm": 0.703125,
"learning_rate": 0.00013368723928370427,
"loss": 1.5076,
"step": 1175
},
{
"epoch": 1.270182992465016,
"grad_norm": 0.6875,
"learning_rate": 0.00013312790979171107,
"loss": 1.3272,
"step": 1180
},
{
"epoch": 1.2755651237890204,
"grad_norm": 0.7578125,
"learning_rate": 0.0001325674136925732,
"loss": 1.3299,
"step": 1185
},
{
"epoch": 1.2809472551130248,
"grad_norm": 1.0078125,
"learning_rate": 0.00013200577072429277,
"loss": 1.6876,
"step": 1190
},
{
"epoch": 1.286329386437029,
"grad_norm": 0.6328125,
"learning_rate": 0.00013144300066525913,
"loss": 1.26,
"step": 1195
},
{
"epoch": 1.2917115177610334,
"grad_norm": 0.8984375,
"learning_rate": 0.00013087912333355247,
"loss": 1.5801,
"step": 1200
},
{
"epoch": 1.2970936490850375,
"grad_norm": 0.6875,
"learning_rate": 0.00013031415858624578,
"loss": 1.5057,
"step": 1205
},
{
"epoch": 1.302475780409042,
"grad_norm": 0.5546875,
"learning_rate": 0.00012974812631870574,
"loss": 1.2602,
"step": 1210
},
{
"epoch": 1.3078579117330462,
"grad_norm": 0.8125,
"learning_rate": 0.0001291810464638919,
"loss": 1.2763,
"step": 1215
},
{
"epoch": 1.3132400430570506,
"grad_norm": 0.8203125,
"learning_rate": 0.0001286129389916549,
"loss": 1.6902,
"step": 1220
},
{
"epoch": 1.318622174381055,
"grad_norm": 0.8203125,
"learning_rate": 0.00012804382390803315,
"loss": 1.537,
"step": 1225
},
{
"epoch": 1.3240043057050592,
"grad_norm": 0.8671875,
"learning_rate": 0.0001274737212545484,
"loss": 1.7872,
"step": 1230
},
{
"epoch": 1.3293864370290636,
"grad_norm": 0.84375,
"learning_rate": 0.00012690265110749978,
"loss": 1.4077,
"step": 1235
},
{
"epoch": 1.334768568353068,
"grad_norm": 0.76171875,
"learning_rate": 0.00012633063357725703,
"loss": 1.4193,
"step": 1240
},
{
"epoch": 1.3401506996770722,
"grad_norm": 1.2578125,
"learning_rate": 0.00012575768880755217,
"loss": 1.9034,
"step": 1245
},
{
"epoch": 1.3455328310010763,
"grad_norm": 0.82421875,
"learning_rate": 0.00012518383697477018,
"loss": 1.5607,
"step": 1250
},
{
"epoch": 1.3509149623250807,
"grad_norm": 1.0234375,
"learning_rate": 0.00012460909828723854,
"loss": 1.4859,
"step": 1255
},
{
"epoch": 1.356297093649085,
"grad_norm": 0.734375,
"learning_rate": 0.00012403349298451544,
"loss": 1.2861,
"step": 1260
},
{
"epoch": 1.3616792249730894,
"grad_norm": 0.6953125,
"learning_rate": 0.00012345704133667716,
"loss": 1.336,
"step": 1265
},
{
"epoch": 1.3670613562970937,
"grad_norm": 0.80859375,
"learning_rate": 0.00012287976364360427,
"loss": 1.4538,
"step": 1270
},
{
"epoch": 1.372443487621098,
"grad_norm": 1.1640625,
"learning_rate": 0.00012230168023426665,
"loss": 1.8344,
"step": 1275
},
{
"epoch": 1.3778256189451024,
"grad_norm": 0.61328125,
"learning_rate": 0.00012172281146600768,
"loss": 1.1302,
"step": 1280
},
{
"epoch": 1.3832077502691065,
"grad_norm": 0.77734375,
"learning_rate": 0.00012114317772382736,
"loss": 1.8846,
"step": 1285
},
{
"epoch": 1.3885898815931108,
"grad_norm": 0.71484375,
"learning_rate": 0.00012056279941966445,
"loss": 1.4932,
"step": 1290
},
{
"epoch": 1.3939720129171151,
"grad_norm": 1.0234375,
"learning_rate": 0.00011998169699167754,
"loss": 1.5204,
"step": 1295
},
{
"epoch": 1.3993541442411195,
"grad_norm": 0.66796875,
"learning_rate": 0.00011939989090352553,
"loss": 1.6152,
"step": 1300
},
{
"epoch": 1.4047362755651238,
"grad_norm": 0.7421875,
"learning_rate": 0.00011881740164364683,
"loss": 1.3754,
"step": 1305
},
{
"epoch": 1.4101184068891282,
"grad_norm": 0.85546875,
"learning_rate": 0.00011823424972453789,
"loss": 1.5163,
"step": 1310
},
{
"epoch": 1.4155005382131325,
"grad_norm": 1.453125,
"learning_rate": 0.00011765045568203083,
"loss": 1.7636,
"step": 1315
},
{
"epoch": 1.4208826695371366,
"grad_norm": 0.84765625,
"learning_rate": 0.00011706604007457043,
"loss": 1.5983,
"step": 1320
},
{
"epoch": 1.426264800861141,
"grad_norm": 0.83203125,
"learning_rate": 0.00011648102348248984,
"loss": 1.5605,
"step": 1325
},
{
"epoch": 1.4316469321851453,
"grad_norm": 0.6953125,
"learning_rate": 0.00011589542650728615,
"loss": 1.3519,
"step": 1330
},
{
"epoch": 1.4370290635091496,
"grad_norm": 0.79296875,
"learning_rate": 0.00011530926977089475,
"loss": 1.4494,
"step": 1335
},
{
"epoch": 1.442411194833154,
"grad_norm": 0.796875,
"learning_rate": 0.00011472257391496312,
"loss": 1.4084,
"step": 1340
},
{
"epoch": 1.4477933261571583,
"grad_norm": 0.6484375,
"learning_rate": 0.00011413535960012404,
"loss": 1.6266,
"step": 1345
},
{
"epoch": 1.4531754574811626,
"grad_norm": 0.77734375,
"learning_rate": 0.00011354764750526786,
"loss": 1.4008,
"step": 1350
},
{
"epoch": 1.4585575888051667,
"grad_norm": 0.83203125,
"learning_rate": 0.00011295945832681441,
"loss": 1.2117,
"step": 1355
},
{
"epoch": 1.4639397201291713,
"grad_norm": 0.75,
"learning_rate": 0.00011237081277798409,
"loss": 1.5329,
"step": 1360
},
{
"epoch": 1.4693218514531754,
"grad_norm": 1.515625,
"learning_rate": 0.0001117817315880686,
"loss": 1.2452,
"step": 1365
},
{
"epoch": 1.4747039827771797,
"grad_norm": 1.359375,
"learning_rate": 0.0001111922355017007,
"loss": 1.7004,
"step": 1370
},
{
"epoch": 1.480086114101184,
"grad_norm": 0.7578125,
"learning_rate": 0.00011060234527812392,
"loss": 1.5766,
"step": 1375
},
{
"epoch": 1.4854682454251884,
"grad_norm": 0.9296875,
"learning_rate": 0.0001100120816904614,
"loss": 1.5775,
"step": 1380
},
{
"epoch": 1.4908503767491927,
"grad_norm": 0.85546875,
"learning_rate": 0.00010942146552498436,
"loss": 1.3943,
"step": 1385
},
{
"epoch": 1.4962325080731969,
"grad_norm": 0.86328125,
"learning_rate": 0.00010883051758038019,
"loss": 1.382,
"step": 1390
},
{
"epoch": 1.5016146393972014,
"grad_norm": 0.7421875,
"learning_rate": 0.00010823925866701987,
"loss": 1.4657,
"step": 1395
},
{
"epoch": 1.5069967707212055,
"grad_norm": 0.78125,
"learning_rate": 0.00010764770960622535,
"loss": 1.2955,
"step": 1400
},
{
"epoch": 1.5123789020452099,
"grad_norm": 1.1875,
"learning_rate": 0.00010705589122953601,
"loss": 1.4443,
"step": 1405
},
{
"epoch": 1.5177610333692142,
"grad_norm": 0.90234375,
"learning_rate": 0.00010646382437797544,
"loss": 1.5391,
"step": 1410
},
{
"epoch": 1.5231431646932185,
"grad_norm": 0.84765625,
"learning_rate": 0.00010587152990131722,
"loss": 1.3099,
"step": 1415
},
{
"epoch": 1.5285252960172229,
"grad_norm": 0.96484375,
"learning_rate": 0.0001052790286573508,
"loss": 1.616,
"step": 1420
},
{
"epoch": 1.533907427341227,
"grad_norm": 0.75,
"learning_rate": 0.00010468634151114707,
"loss": 1.5043,
"step": 1425
},
{
"epoch": 1.5392895586652315,
"grad_norm": 0.86328125,
"learning_rate": 0.0001040934893343234,
"loss": 1.498,
"step": 1430
},
{
"epoch": 1.5446716899892357,
"grad_norm": 1.125,
"learning_rate": 0.00010350049300430884,
"loss": 1.7188,
"step": 1435
},
{
"epoch": 1.55005382131324,
"grad_norm": 0.9296875,
"learning_rate": 0.00010290737340360878,
"loss": 1.7336,
"step": 1440
},
{
"epoch": 1.5554359526372443,
"grad_norm": 0.75,
"learning_rate": 0.00010231415141906968,
"loss": 1.5862,
"step": 1445
},
{
"epoch": 1.5608180839612487,
"grad_norm": 0.828125,
"learning_rate": 0.00010172084794114336,
"loss": 1.5656,
"step": 1450
},
{
"epoch": 1.566200215285253,
"grad_norm": 0.90234375,
"learning_rate": 0.00010112748386315157,
"loss": 1.6676,
"step": 1455
},
{
"epoch": 1.571582346609257,
"grad_norm": 0.66015625,
"learning_rate": 0.00010053408008054999,
"loss": 1.136,
"step": 1460
},
{
"epoch": 1.5769644779332617,
"grad_norm": 0.63671875,
"learning_rate": 9.994065749019263e-05,
"loss": 1.321,
"step": 1465
},
{
"epoch": 1.5823466092572658,
"grad_norm": 0.92578125,
"learning_rate": 9.934723698959571e-05,
"loss": 1.4646,
"step": 1470
},
{
"epoch": 1.5877287405812703,
"grad_norm": 0.80859375,
"learning_rate": 9.875383947620195e-05,
"loss": 1.4613,
"step": 1475
},
{
"epoch": 1.5931108719052745,
"grad_norm": 0.80078125,
"learning_rate": 9.816048584664445e-05,
"loss": 1.3651,
"step": 1480
},
{
"epoch": 1.5984930032292788,
"grad_norm": 0.75390625,
"learning_rate": 9.756719699601109e-05,
"loss": 1.4559,
"step": 1485
},
{
"epoch": 1.6038751345532831,
"grad_norm": 0.953125,
"learning_rate": 9.697399381710844e-05,
"loss": 1.6278,
"step": 1490
},
{
"epoch": 1.6092572658772875,
"grad_norm": 0.9140625,
"learning_rate": 9.638089719972609e-05,
"loss": 1.7128,
"step": 1495
},
{
"epoch": 1.6146393972012918,
"grad_norm": 0.78515625,
"learning_rate": 9.578792802990116e-05,
"loss": 1.5033,
"step": 1500
},
{
"epoch": 1.620021528525296,
"grad_norm": 0.80859375,
"learning_rate": 9.519510718918251e-05,
"loss": 1.5971,
"step": 1505
},
{
"epoch": 1.6254036598493005,
"grad_norm": 0.734375,
"learning_rate": 9.460245555389575e-05,
"loss": 1.982,
"step": 1510
},
{
"epoch": 1.6307857911733046,
"grad_norm": 0.65234375,
"learning_rate": 9.400999399440775e-05,
"loss": 1.7542,
"step": 1515
},
{
"epoch": 1.636167922497309,
"grad_norm": 0.73046875,
"learning_rate": 9.341774337439182e-05,
"loss": 1.7067,
"step": 1520
},
{
"epoch": 1.6415500538213132,
"grad_norm": 1.0390625,
"learning_rate": 9.282572455009304e-05,
"loss": 1.8912,
"step": 1525
},
{
"epoch": 1.6469321851453176,
"grad_norm": 1.15625,
"learning_rate": 9.223395836959371e-05,
"loss": 1.3994,
"step": 1530
},
{
"epoch": 1.652314316469322,
"grad_norm": 1.0703125,
"learning_rate": 9.164246567207927e-05,
"loss": 1.2383,
"step": 1535
},
{
"epoch": 1.657696447793326,
"grad_norm": 0.7265625,
"learning_rate": 9.105126728710432e-05,
"loss": 1.7729,
"step": 1540
},
{
"epoch": 1.6630785791173306,
"grad_norm": 0.8046875,
"learning_rate": 9.046038403385922e-05,
"loss": 1.2427,
"step": 1545
},
{
"epoch": 1.6684607104413347,
"grad_norm": 0.70703125,
"learning_rate": 8.986983672043684e-05,
"loss": 1.3331,
"step": 1550
},
{
"epoch": 1.673842841765339,
"grad_norm": 0.65625,
"learning_rate": 8.927964614309999e-05,
"loss": 1.4483,
"step": 1555
},
{
"epoch": 1.6792249730893434,
"grad_norm": 0.70703125,
"learning_rate": 8.868983308554875e-05,
"loss": 1.718,
"step": 1560
},
{
"epoch": 1.6846071044133477,
"grad_norm": 0.77734375,
"learning_rate": 8.810041831818889e-05,
"loss": 1.5577,
"step": 1565
},
{
"epoch": 1.689989235737352,
"grad_norm": 0.84375,
"learning_rate": 8.751142259740014e-05,
"loss": 1.4279,
"step": 1570
},
{
"epoch": 1.6953713670613562,
"grad_norm": 1.3984375,
"learning_rate": 8.692286666480568e-05,
"loss": 1.7283,
"step": 1575
},
{
"epoch": 1.7007534983853607,
"grad_norm": 0.93359375,
"learning_rate": 8.633477124654116e-05,
"loss": 1.596,
"step": 1580
},
{
"epoch": 1.7061356297093648,
"grad_norm": 0.71484375,
"learning_rate": 8.574715705252527e-05,
"loss": 1.8197,
"step": 1585
},
{
"epoch": 1.7115177610333692,
"grad_norm": 0.9140625,
"learning_rate": 8.516004477573022e-05,
"loss": 1.4374,
"step": 1590
},
{
"epoch": 1.7168998923573735,
"grad_norm": 0.80859375,
"learning_rate": 8.457345509145305e-05,
"loss": 1.5237,
"step": 1595
},
{
"epoch": 1.7222820236813778,
"grad_norm": 0.7109375,
"learning_rate": 8.398740865658773e-05,
"loss": 1.4578,
"step": 1600
},
{
"epoch": 1.7276641550053822,
"grad_norm": 0.78125,
"learning_rate": 8.340192610889741e-05,
"loss": 1.4532,
"step": 1605
},
{
"epoch": 1.7330462863293863,
"grad_norm": 0.80859375,
"learning_rate": 8.28170280662879e-05,
"loss": 1.5097,
"step": 1610
},
{
"epoch": 1.7384284176533908,
"grad_norm": 0.9140625,
"learning_rate": 8.223273512608146e-05,
"loss": 1.2694,
"step": 1615
},
{
"epoch": 1.743810548977395,
"grad_norm": 1.015625,
"learning_rate": 8.164906786429166e-05,
"loss": 1.5997,
"step": 1620
},
{
"epoch": 1.7491926803013995,
"grad_norm": 0.85546875,
"learning_rate": 8.106604683489853e-05,
"loss": 1.6204,
"step": 1625
},
{
"epoch": 1.7545748116254036,
"grad_norm": 1.2734375,
"learning_rate": 8.048369256912491e-05,
"loss": 1.5516,
"step": 1630
},
{
"epoch": 1.759956942949408,
"grad_norm": 0.62890625,
"learning_rate": 7.990202557471343e-05,
"loss": 1.1211,
"step": 1635
},
{
"epoch": 1.7653390742734123,
"grad_norm": 0.625,
"learning_rate": 7.932106633520427e-05,
"loss": 1.5284,
"step": 1640
},
{
"epoch": 1.7707212055974164,
"grad_norm": 0.7890625,
"learning_rate": 7.874083530921383e-05,
"loss": 1.7255,
"step": 1645
},
{
"epoch": 1.776103336921421,
"grad_norm": 0.78125,
"learning_rate": 7.816135292971438e-05,
"loss": 1.7802,
"step": 1650
},
{
"epoch": 1.781485468245425,
"grad_norm": 1.2890625,
"learning_rate": 7.758263960331438e-05,
"loss": 1.395,
"step": 1655
},
{
"epoch": 1.7868675995694296,
"grad_norm": 0.84375,
"learning_rate": 7.700471570953981e-05,
"loss": 1.4316,
"step": 1660
},
{
"epoch": 1.7922497308934338,
"grad_norm": 0.76171875,
"learning_rate": 7.642760160011681e-05,
"loss": 1.7198,
"step": 1665
},
{
"epoch": 1.797631862217438,
"grad_norm": 0.66015625,
"learning_rate": 7.58513175982546e-05,
"loss": 1.3174,
"step": 1670
},
{
"epoch": 1.8030139935414424,
"grad_norm": 0.81640625,
"learning_rate": 7.527588399792999e-05,
"loss": 1.3408,
"step": 1675
},
{
"epoch": 1.8083961248654468,
"grad_norm": 0.7890625,
"learning_rate": 7.470132106317275e-05,
"loss": 1.4783,
"step": 1680
},
{
"epoch": 1.813778256189451,
"grad_norm": 1.0625,
"learning_rate": 7.412764902735193e-05,
"loss": 1.0823,
"step": 1685
},
{
"epoch": 1.8191603875134552,
"grad_norm": 0.73046875,
"learning_rate": 7.355488809246336e-05,
"loss": 1.5913,
"step": 1690
},
{
"epoch": 1.8245425188374598,
"grad_norm": 0.6953125,
"learning_rate": 7.298305842841826e-05,
"loss": 1.5883,
"step": 1695
},
{
"epoch": 1.8299246501614639,
"grad_norm": 0.83984375,
"learning_rate": 7.24121801723329e-05,
"loss": 1.4392,
"step": 1700
},
{
"epoch": 1.8353067814854682,
"grad_norm": 0.74609375,
"learning_rate": 7.184227342781948e-05,
"loss": 1.6952,
"step": 1705
},
{
"epoch": 1.8406889128094726,
"grad_norm": 0.83203125,
"learning_rate": 7.127335826427828e-05,
"loss": 1.6377,
"step": 1710
},
{
"epoch": 1.846071044133477,
"grad_norm": 1.1171875,
"learning_rate": 7.070545471619072e-05,
"loss": 1.5065,
"step": 1715
},
{
"epoch": 1.8514531754574812,
"grad_norm": 0.66796875,
"learning_rate": 7.013858278241399e-05,
"loss": 1.3861,
"step": 1720
},
{
"epoch": 1.8568353067814853,
"grad_norm": 0.86328125,
"learning_rate": 6.957276242547672e-05,
"loss": 1.2102,
"step": 1725
},
{
"epoch": 1.86221743810549,
"grad_norm": 1.234375,
"learning_rate": 6.9008013570876e-05,
"loss": 1.5305,
"step": 1730
},
{
"epoch": 1.867599569429494,
"grad_norm": 0.7109375,
"learning_rate": 6.844435610637583e-05,
"loss": 1.2648,
"step": 1735
},
{
"epoch": 1.8729817007534983,
"grad_norm": 0.79296875,
"learning_rate": 6.78818098813065e-05,
"loss": 1.3824,
"step": 1740
},
{
"epoch": 1.8783638320775027,
"grad_norm": 0.7421875,
"learning_rate": 6.732039470586577e-05,
"loss": 1.7781,
"step": 1745
},
{
"epoch": 1.883745963401507,
"grad_norm": 0.7421875,
"learning_rate": 6.67601303504213e-05,
"loss": 1.2321,
"step": 1750
},
{
"epoch": 1.8891280947255114,
"grad_norm": 1.1015625,
"learning_rate": 6.620103654481429e-05,
"loss": 1.4159,
"step": 1755
},
{
"epoch": 1.8945102260495155,
"grad_norm": 0.96484375,
"learning_rate": 6.56431329776648e-05,
"loss": 1.4128,
"step": 1760
},
{
"epoch": 1.89989235737352,
"grad_norm": 0.9140625,
"learning_rate": 6.508643929567828e-05,
"loss": 1.4293,
"step": 1765
},
{
"epoch": 1.9052744886975241,
"grad_norm": 0.94140625,
"learning_rate": 6.453097510295387e-05,
"loss": 2.0126,
"step": 1770
},
{
"epoch": 1.9106566200215285,
"grad_norm": 0.73828125,
"learning_rate": 6.397675996029388e-05,
"loss": 1.3171,
"step": 1775
},
{
"epoch": 1.9160387513455328,
"grad_norm": 0.875,
"learning_rate": 6.342381338451513e-05,
"loss": 1.5463,
"step": 1780
},
{
"epoch": 1.9214208826695371,
"grad_norm": 0.85546875,
"learning_rate": 6.28721548477615e-05,
"loss": 1.4422,
"step": 1785
},
{
"epoch": 1.9268030139935415,
"grad_norm": 0.6796875,
"learning_rate": 6.232180377681822e-05,
"loss": 1.703,
"step": 1790
},
{
"epoch": 1.9321851453175456,
"grad_norm": 0.6953125,
"learning_rate": 6.177277955242786e-05,
"loss": 1.5379,
"step": 1795
},
{
"epoch": 1.9375672766415502,
"grad_norm": 1.40625,
"learning_rate": 6.122510150860785e-05,
"loss": 1.3108,
"step": 1800
},
{
"epoch": 1.9429494079655543,
"grad_norm": 0.97265625,
"learning_rate": 6.067878893196941e-05,
"loss": 1.4381,
"step": 1805
},
{
"epoch": 1.9483315392895588,
"grad_norm": 0.859375,
"learning_rate": 6.01338610610386e-05,
"loss": 1.5073,
"step": 1810
},
{
"epoch": 1.953713670613563,
"grad_norm": 0.94921875,
"learning_rate": 5.9590337085578726e-05,
"loss": 1.5662,
"step": 1815
},
{
"epoch": 1.9590958019375673,
"grad_norm": 0.91015625,
"learning_rate": 5.9048236145914524e-05,
"loss": 1.5529,
"step": 1820
},
{
"epoch": 1.9644779332615716,
"grad_norm": 1.859375,
"learning_rate": 5.8507577332258356e-05,
"loss": 1.4747,
"step": 1825
},
{
"epoch": 1.969860064585576,
"grad_norm": 0.8359375,
"learning_rate": 5.7968379684037565e-05,
"loss": 1.641,
"step": 1830
},
{
"epoch": 1.9752421959095803,
"grad_norm": 1.078125,
"learning_rate": 5.743066218922439e-05,
"loss": 1.6829,
"step": 1835
},
{
"epoch": 1.9806243272335844,
"grad_norm": 1.0,
"learning_rate": 5.689444378366696e-05,
"loss": 2.097,
"step": 1840
},
{
"epoch": 1.986006458557589,
"grad_norm": 0.7421875,
"learning_rate": 5.635974335042275e-05,
"loss": 1.2503,
"step": 1845
},
{
"epoch": 1.991388589881593,
"grad_norm": 0.99609375,
"learning_rate": 5.582657971909342e-05,
"loss": 1.3495,
"step": 1850
},
{
"epoch": 1.9967707212055974,
"grad_norm": 0.84765625,
"learning_rate": 5.529497166516184e-05,
"loss": 1.3844,
"step": 1855
},
{
"epoch": 2.0021528525296017,
"grad_norm": 0.6015625,
"learning_rate": 5.4764937909330746e-05,
"loss": 1.4768,
"step": 1860
},
{
"epoch": 2.007534983853606,
"grad_norm": 0.703125,
"learning_rate": 5.4236497116863726e-05,
"loss": 1.4405,
"step": 1865
},
{
"epoch": 2.0129171151776104,
"grad_norm": 0.9765625,
"learning_rate": 5.370966789692771e-05,
"loss": 1.5051,
"step": 1870
},
{
"epoch": 2.0182992465016145,
"grad_norm": 0.79296875,
"learning_rate": 5.318446880193779e-05,
"loss": 1.2863,
"step": 1875
},
{
"epoch": 2.023681377825619,
"grad_norm": 1.1328125,
"learning_rate": 5.26609183269037e-05,
"loss": 1.6646,
"step": 1880
},
{
"epoch": 2.029063509149623,
"grad_norm": 0.9375,
"learning_rate": 5.213903490877874e-05,
"loss": 1.5516,
"step": 1885
},
{
"epoch": 2.0344456404736277,
"grad_norm": 0.796875,
"learning_rate": 5.161883692581038e-05,
"loss": 1.5062,
"step": 1890
},
{
"epoch": 2.039827771797632,
"grad_norm": 0.94921875,
"learning_rate": 5.11003426968931e-05,
"loss": 1.2587,
"step": 1895
},
{
"epoch": 2.045209903121636,
"grad_norm": 1.015625,
"learning_rate": 5.0583570480923325e-05,
"loss": 1.2944,
"step": 1900
},
{
"epoch": 2.0505920344456405,
"grad_norm": 0.89453125,
"learning_rate": 5.0068538476156225e-05,
"loss": 1.3802,
"step": 1905
},
{
"epoch": 2.0559741657696446,
"grad_norm": 0.75,
"learning_rate": 4.9555264819565205e-05,
"loss": 1.4541,
"step": 1910
},
{
"epoch": 2.061356297093649,
"grad_norm": 0.5234375,
"learning_rate": 4.904376758620293e-05,
"loss": 1.4703,
"step": 1915
},
{
"epoch": 2.0667384284176533,
"grad_norm": 1.1171875,
"learning_rate": 4.853406478856498e-05,
"loss": 1.5858,
"step": 1920
},
{
"epoch": 2.072120559741658,
"grad_norm": 1.1875,
"learning_rate": 4.8026174375955336e-05,
"loss": 1.3889,
"step": 1925
},
{
"epoch": 2.077502691065662,
"grad_norm": 0.5703125,
"learning_rate": 4.75201142338545e-05,
"loss": 1.2628,
"step": 1930
},
{
"epoch": 2.082884822389666,
"grad_norm": 0.9140625,
"learning_rate": 4.701590218328955e-05,
"loss": 1.9168,
"step": 1935
},
{
"epoch": 2.0882669537136707,
"grad_norm": 0.9609375,
"learning_rate": 4.6513555980206643e-05,
"loss": 1.6785,
"step": 1940
},
{
"epoch": 2.0936490850376748,
"grad_norm": 0.70703125,
"learning_rate": 4.601309331484554e-05,
"loss": 1.6131,
"step": 1945
},
{
"epoch": 2.0990312163616793,
"grad_norm": 1.265625,
"learning_rate": 4.551453181111688e-05,
"loss": 1.6658,
"step": 1950
},
{
"epoch": 2.1044133476856834,
"grad_norm": 0.75,
"learning_rate": 4.501788902598143e-05,
"loss": 1.6256,
"step": 1955
},
{
"epoch": 2.109795479009688,
"grad_norm": 0.96875,
"learning_rate": 4.4523182448831834e-05,
"loss": 1.8338,
"step": 1960
},
{
"epoch": 2.115177610333692,
"grad_norm": 0.69140625,
"learning_rate": 4.4030429500876735e-05,
"loss": 1.5877,
"step": 1965
},
{
"epoch": 2.1205597416576962,
"grad_norm": 0.7734375,
"learning_rate": 4.353964753452716e-05,
"loss": 1.3338,
"step": 1970
},
{
"epoch": 2.125941872981701,
"grad_norm": 0.82421875,
"learning_rate": 4.305085383278567e-05,
"loss": 1.4618,
"step": 1975
},
{
"epoch": 2.131324004305705,
"grad_norm": 0.75,
"learning_rate": 4.256406560863758e-05,
"loss": 1.5282,
"step": 1980
},
{
"epoch": 2.1367061356297095,
"grad_norm": 0.78125,
"learning_rate": 4.2079300004444865e-05,
"loss": 1.4044,
"step": 1985
},
{
"epoch": 2.1420882669537136,
"grad_norm": 0.62890625,
"learning_rate": 4.1596574091342376e-05,
"loss": 1.4315,
"step": 1990
},
{
"epoch": 2.147470398277718,
"grad_norm": 0.98046875,
"learning_rate": 4.1115904868636856e-05,
"loss": 1.4956,
"step": 1995
},
{
"epoch": 2.1528525296017222,
"grad_norm": 0.73828125,
"learning_rate": 4.063730926320818e-05,
"loss": 1.4915,
"step": 2000
},
{
"epoch": 2.158234660925727,
"grad_norm": 0.77734375,
"learning_rate": 4.016080412891328e-05,
"loss": 1.3758,
"step": 2005
},
{
"epoch": 2.163616792249731,
"grad_norm": 0.67578125,
"learning_rate": 3.968640624599272e-05,
"loss": 1.4847,
"step": 2010
},
{
"epoch": 2.168998923573735,
"grad_norm": 1.0,
"learning_rate": 3.9214132320479614e-05,
"loss": 1.6858,
"step": 2015
},
{
"epoch": 2.1743810548977396,
"grad_norm": 0.6328125,
"learning_rate": 3.874399898361146e-05,
"loss": 1.3079,
"step": 2020
},
{
"epoch": 2.1797631862217437,
"grad_norm": 0.99609375,
"learning_rate": 3.827602279124447e-05,
"loss": 1.6033,
"step": 2025
},
{
"epoch": 2.1851453175457483,
"grad_norm": 0.80859375,
"learning_rate": 3.7810220223270466e-05,
"loss": 1.3613,
"step": 2030
},
{
"epoch": 2.1905274488697524,
"grad_norm": 0.77734375,
"learning_rate": 3.7346607683036525e-05,
"loss": 1.3334,
"step": 2035
},
{
"epoch": 2.195909580193757,
"grad_norm": 0.9609375,
"learning_rate": 3.688520149676748e-05,
"loss": 1.2178,
"step": 2040
},
{
"epoch": 2.201291711517761,
"grad_norm": 1.28125,
"learning_rate": 3.642601791299076e-05,
"loss": 1.4418,
"step": 2045
},
{
"epoch": 2.206673842841765,
"grad_norm": 0.65234375,
"learning_rate": 3.596907310196451e-05,
"loss": 1.2051,
"step": 2050
},
{
"epoch": 2.2120559741657697,
"grad_norm": 0.78125,
"learning_rate": 3.551438315510778e-05,
"loss": 1.6727,
"step": 2055
},
{
"epoch": 2.217438105489774,
"grad_norm": 0.75,
"learning_rate": 3.506196408443414e-05,
"loss": 1.6572,
"step": 2060
},
{
"epoch": 2.2228202368137784,
"grad_norm": 0.77734375,
"learning_rate": 3.4611831821987726e-05,
"loss": 1.2514,
"step": 2065
},
{
"epoch": 2.2282023681377825,
"grad_norm": 1.4375,
"learning_rate": 3.4164002219282145e-05,
"loss": 1.8706,
"step": 2070
},
{
"epoch": 2.233584499461787,
"grad_norm": 0.625,
"learning_rate": 3.371849104674234e-05,
"loss": 1.4124,
"step": 2075
},
{
"epoch": 2.238966630785791,
"grad_norm": 1.0703125,
"learning_rate": 3.327531399314914e-05,
"loss": 1.528,
"step": 2080
},
{
"epoch": 2.2443487621097953,
"grad_norm": 0.8984375,
"learning_rate": 3.283448666508687e-05,
"loss": 1.4631,
"step": 2085
},
{
"epoch": 2.2497308934338,
"grad_norm": 0.89453125,
"learning_rate": 3.239602458639364e-05,
"loss": 1.0781,
"step": 2090
},
{
"epoch": 2.255113024757804,
"grad_norm": 1.140625,
"learning_rate": 3.195994319761492e-05,
"loss": 1.6776,
"step": 2095
},
{
"epoch": 2.2604951560818085,
"grad_norm": 0.8125,
"learning_rate": 3.152625785545942e-05,
"loss": 1.3804,
"step": 2100
},
{
"epoch": 2.2658772874058126,
"grad_norm": 0.7421875,
"learning_rate": 3.1094983832258605e-05,
"loss": 1.6414,
"step": 2105
},
{
"epoch": 2.271259418729817,
"grad_norm": 0.7890625,
"learning_rate": 3.0666136315428794e-05,
"loss": 1.3944,
"step": 2110
},
{
"epoch": 2.2766415500538213,
"grad_norm": 0.96484375,
"learning_rate": 3.0239730406936295e-05,
"loss": 1.5675,
"step": 2115
},
{
"epoch": 2.282023681377826,
"grad_norm": 0.87890625,
"learning_rate": 2.9815781122765528e-05,
"loss": 1.2669,
"step": 2120
},
{
"epoch": 2.28740581270183,
"grad_norm": 1.546875,
"learning_rate": 2.939430339239041e-05,
"loss": 1.491,
"step": 2125
},
{
"epoch": 2.292787944025834,
"grad_norm": 0.68359375,
"learning_rate": 2.8975312058248504e-05,
"loss": 1.7579,
"step": 2130
},
{
"epoch": 2.2981700753498386,
"grad_norm": 0.64453125,
"learning_rate": 2.855882187521821e-05,
"loss": 1.3731,
"step": 2135
},
{
"epoch": 2.3035522066738428,
"grad_norm": 0.57421875,
"learning_rate": 2.8144847510099538e-05,
"loss": 1.465,
"step": 2140
},
{
"epoch": 2.3089343379978473,
"grad_norm": 0.859375,
"learning_rate": 2.7733403541097148e-05,
"loss": 1.5397,
"step": 2145
},
{
"epoch": 2.3143164693218514,
"grad_norm": 1.4140625,
"learning_rate": 2.7324504457307355e-05,
"loss": 1.5433,
"step": 2150
},
{
"epoch": 2.3196986006458555,
"grad_norm": 0.62890625,
"learning_rate": 2.69181646582076e-05,
"loss": 1.4736,
"step": 2155
},
{
"epoch": 2.32508073196986,
"grad_norm": 0.68359375,
"learning_rate": 2.6514398453149714e-05,
"loss": 1.482,
"step": 2160
},
{
"epoch": 2.330462863293864,
"grad_norm": 0.75390625,
"learning_rate": 2.6113220060855615e-05,
"loss": 1.1509,
"step": 2165
},
{
"epoch": 2.3358449946178688,
"grad_norm": 0.5625,
"learning_rate": 2.571464360891689e-05,
"loss": 1.4047,
"step": 2170
},
{
"epoch": 2.341227125941873,
"grad_norm": 0.8046875,
"learning_rate": 2.531868313329717e-05,
"loss": 1.4702,
"step": 2175
},
{
"epoch": 2.3466092572658774,
"grad_norm": 0.671875,
"learning_rate": 2.4925352577837778e-05,
"loss": 1.3064,
"step": 2180
},
{
"epoch": 2.3519913885898815,
"grad_norm": 0.63671875,
"learning_rate": 2.4534665793766964e-05,
"loss": 1.2348,
"step": 2185
},
{
"epoch": 2.357373519913886,
"grad_norm": 0.81640625,
"learning_rate": 2.4146636539211754e-05,
"loss": 1.6612,
"step": 2190
},
{
"epoch": 2.36275565123789,
"grad_norm": 0.6875,
"learning_rate": 2.3761278478713754e-05,
"loss": 1.3195,
"step": 2195
},
{
"epoch": 2.3681377825618943,
"grad_norm": 0.77734375,
"learning_rate": 2.337860518274776e-05,
"loss": 1.3896,
"step": 2200
},
{
"epoch": 2.373519913885899,
"grad_norm": 0.84765625,
"learning_rate": 2.2998630127244104e-05,
"loss": 1.7125,
"step": 2205
},
{
"epoch": 2.378902045209903,
"grad_norm": 0.640625,
"learning_rate": 2.2621366693113766e-05,
"loss": 1.3499,
"step": 2210
},
{
"epoch": 2.3842841765339076,
"grad_norm": 0.984375,
"learning_rate": 2.224682816577747e-05,
"loss": 1.2244,
"step": 2215
},
{
"epoch": 2.3896663078579117,
"grad_norm": 0.9765625,
"learning_rate": 2.187502773469762e-05,
"loss": 1.8846,
"step": 2220
},
{
"epoch": 2.395048439181916,
"grad_norm": 0.84765625,
"learning_rate": 2.1505978492913958e-05,
"loss": 1.4663,
"step": 2225
},
{
"epoch": 2.4004305705059203,
"grad_norm": 1.3203125,
"learning_rate": 2.1139693436582453e-05,
"loss": 1.7524,
"step": 2230
},
{
"epoch": 2.4058127018299245,
"grad_norm": 0.8671875,
"learning_rate": 2.0776185464517627e-05,
"loss": 1.5157,
"step": 2235
},
{
"epoch": 2.411194833153929,
"grad_norm": 0.7734375,
"learning_rate": 2.041546737773834e-05,
"loss": 1.1478,
"step": 2240
},
{
"epoch": 2.416576964477933,
"grad_norm": 0.80078125,
"learning_rate": 2.005755187901689e-05,
"loss": 1.5565,
"step": 2245
},
{
"epoch": 2.4219590958019377,
"grad_norm": 0.6328125,
"learning_rate": 1.9702451572431946e-05,
"loss": 1.1969,
"step": 2250
},
{
"epoch": 2.427341227125942,
"grad_norm": 0.609375,
"learning_rate": 1.935017896292436e-05,
"loss": 1.1778,
"step": 2255
},
{
"epoch": 2.4327233584499464,
"grad_norm": 0.84765625,
"learning_rate": 1.9000746455857078e-05,
"loss": 1.3546,
"step": 2260
},
{
"epoch": 2.4381054897739505,
"grad_norm": 0.921875,
"learning_rate": 1.8654166356578074e-05,
"loss": 1.173,
"step": 2265
},
{
"epoch": 2.4434876210979546,
"grad_norm": 0.59765625,
"learning_rate": 1.8310450869987195e-05,
"loss": 1.2932,
"step": 2270
},
{
"epoch": 2.448869752421959,
"grad_norm": 1.0078125,
"learning_rate": 1.7969612100106238e-05,
"loss": 1.3395,
"step": 2275
},
{
"epoch": 2.4542518837459633,
"grad_norm": 1.0234375,
"learning_rate": 1.763166204965275e-05,
"loss": 1.3869,
"step": 2280
},
{
"epoch": 2.459634015069968,
"grad_norm": 1.8203125,
"learning_rate": 1.729661261961737e-05,
"loss": 1.5892,
"step": 2285
},
{
"epoch": 2.465016146393972,
"grad_norm": 0.65625,
"learning_rate": 1.696447560884462e-05,
"loss": 1.1645,
"step": 2290
},
{
"epoch": 2.4703982777179765,
"grad_norm": 0.5859375,
"learning_rate": 1.6635262713617583e-05,
"loss": 1.5684,
"step": 2295
},
{
"epoch": 2.4757804090419806,
"grad_norm": 0.921875,
"learning_rate": 1.6308985527245892e-05,
"loss": 1.5329,
"step": 2300
},
{
"epoch": 2.481162540365985,
"grad_norm": 1.0625,
"learning_rate": 1.5985655539657517e-05,
"loss": 1.6929,
"step": 2305
},
{
"epoch": 2.4865446716899893,
"grad_norm": 1.109375,
"learning_rate": 1.5665284136994084e-05,
"loss": 1.7067,
"step": 2310
},
{
"epoch": 2.4919268030139934,
"grad_norm": 1.0546875,
"learning_rate": 1.5347882601209983e-05,
"loss": 1.4725,
"step": 2315
},
{
"epoch": 2.497308934337998,
"grad_norm": 0.61328125,
"learning_rate": 1.5033462109675056e-05,
"loss": 1.4677,
"step": 2320
},
{
"epoch": 2.502691065662002,
"grad_norm": 0.55078125,
"learning_rate": 1.4722033734780983e-05,
"loss": 1.2087,
"step": 2325
},
{
"epoch": 2.5080731969860066,
"grad_norm": 0.86328125,
"learning_rate": 1.4413608443551263e-05,
"loss": 1.1739,
"step": 2330
},
{
"epoch": 2.5134553283100107,
"grad_norm": 0.71875,
"learning_rate": 1.4108197097255193e-05,
"loss": 1.2955,
"step": 2335
},
{
"epoch": 2.518837459634015,
"grad_norm": 0.78515625,
"learning_rate": 1.3805810451025258e-05,
"loss": 1.2485,
"step": 2340
},
{
"epoch": 2.5242195909580194,
"grad_norm": 0.84765625,
"learning_rate": 1.3506459153478412e-05,
"loss": 1.4608,
"step": 2345
},
{
"epoch": 2.529601722282024,
"grad_norm": 0.796875,
"learning_rate": 1.3210153746341103e-05,
"loss": 1.2995,
"step": 2350
},
{
"epoch": 2.534983853606028,
"grad_norm": 0.609375,
"learning_rate": 1.2916904664078e-05,
"loss": 1.2907,
"step": 2355
},
{
"epoch": 2.540365984930032,
"grad_norm": 0.66015625,
"learning_rate": 1.262672223352459e-05,
"loss": 1.6971,
"step": 2360
},
{
"epoch": 2.5457481162540367,
"grad_norm": 0.8125,
"learning_rate": 1.2339616673523523e-05,
"loss": 1.4335,
"step": 2365
},
{
"epoch": 2.551130247578041,
"grad_norm": 0.71484375,
"learning_rate": 1.2055598094564713e-05,
"loss": 1.5192,
"step": 2370
},
{
"epoch": 2.5565123789020454,
"grad_norm": 0.79296875,
"learning_rate": 1.177467649842927e-05,
"loss": 1.8432,
"step": 2375
},
{
"epoch": 2.5618945102260495,
"grad_norm": 0.77734375,
"learning_rate": 1.1496861777837364e-05,
"loss": 1.6651,
"step": 2380
},
{
"epoch": 2.5672766415500536,
"grad_norm": 0.83203125,
"learning_rate": 1.122216371609982e-05,
"loss": 1.5468,
"step": 2385
},
{
"epoch": 2.572658772874058,
"grad_norm": 0.88671875,
"learning_rate": 1.0950591986773584e-05,
"loss": 1.6867,
"step": 2390
},
{
"epoch": 2.5780409041980623,
"grad_norm": 0.90234375,
"learning_rate": 1.068215615332101e-05,
"loss": 1.3598,
"step": 2395
},
{
"epoch": 2.583423035522067,
"grad_norm": 0.640625,
"learning_rate": 1.0416865668773223e-05,
"loss": 1.6012,
"step": 2400
},
{
"epoch": 2.588805166846071,
"grad_norm": 0.8359375,
"learning_rate": 1.0154729875397096e-05,
"loss": 1.5018,
"step": 2405
},
{
"epoch": 2.594187298170075,
"grad_norm": 0.85546875,
"learning_rate": 9.895758004366329e-06,
"loss": 1.517,
"step": 2410
},
{
"epoch": 2.5995694294940797,
"grad_norm": 0.625,
"learning_rate": 9.639959175436375e-06,
"loss": 1.4521,
"step": 2415
},
{
"epoch": 2.604951560818084,
"grad_norm": 0.78515625,
"learning_rate": 9.387342396623188e-06,
"loss": 1.3317,
"step": 2420
},
{
"epoch": 2.6103336921420883,
"grad_norm": 0.93359375,
"learning_rate": 9.13791656388614e-06,
"loss": 1.9211,
"step": 2425
},
{
"epoch": 2.6157158234660924,
"grad_norm": 0.7578125,
"learning_rate": 8.89169046081466e-06,
"loss": 1.5994,
"step": 2430
},
{
"epoch": 2.621097954790097,
"grad_norm": 0.6328125,
"learning_rate": 8.648672758318998e-06,
"loss": 1.4924,
"step": 2435
},
{
"epoch": 2.626480086114101,
"grad_norm": 0.76953125,
"learning_rate": 8.40887201432471e-06,
"loss": 1.3793,
"step": 2440
},
{
"epoch": 2.6318622174381057,
"grad_norm": 0.8203125,
"learning_rate": 8.172296673471502e-06,
"loss": 1.5989,
"step": 2445
},
{
"epoch": 2.63724434876211,
"grad_norm": 0.7890625,
"learning_rate": 7.938955066815712e-06,
"loss": 1.6884,
"step": 2450
},
{
"epoch": 2.642626480086114,
"grad_norm": 0.7265625,
"learning_rate": 7.708855411536975e-06,
"loss": 1.5167,
"step": 2455
},
{
"epoch": 2.6480086114101185,
"grad_norm": 1.1328125,
"learning_rate": 7.482005810648829e-06,
"loss": 1.489,
"step": 2460
},
{
"epoch": 2.6533907427341226,
"grad_norm": 0.78125,
"learning_rate": 7.258414252713386e-06,
"loss": 1.4912,
"step": 2465
},
{
"epoch": 2.658772874058127,
"grad_norm": 0.7578125,
"learning_rate": 7.038088611560034e-06,
"loss": 1.3837,
"step": 2470
},
{
"epoch": 2.6641550053821312,
"grad_norm": 0.73046875,
"learning_rate": 6.821036646008072e-06,
"loss": 1.4303,
"step": 2475
},
{
"epoch": 2.669537136706136,
"grad_norm": 0.91015625,
"learning_rate": 6.6072659995936255e-06,
"loss": 1.3774,
"step": 2480
},
{
"epoch": 2.67491926803014,
"grad_norm": 0.78125,
"learning_rate": 6.396784200300321e-06,
"loss": 1.3987,
"step": 2485
},
{
"epoch": 2.6803013993541445,
"grad_norm": 0.6953125,
"learning_rate": 6.189598660294305e-06,
"loss": 2.0529,
"step": 2490
},
{
"epoch": 2.6856835306781486,
"grad_norm": 0.64453125,
"learning_rate": 5.985716675663133e-06,
"loss": 1.3103,
"step": 2495
},
{
"epoch": 2.6910656620021527,
"grad_norm": 0.67578125,
"learning_rate": 5.785145426158944e-06,
"loss": 1.5402,
"step": 2500
},
{
"epoch": 2.6964477933261572,
"grad_norm": 0.474609375,
"learning_rate": 5.5878919749454914e-06,
"loss": 1.3674,
"step": 2505
},
{
"epoch": 2.7018299246501614,
"grad_norm": 0.76953125,
"learning_rate": 5.393963268349511e-06,
"loss": 1.1132,
"step": 2510
},
{
"epoch": 2.707212055974166,
"grad_norm": 0.97265625,
"learning_rate": 5.203366135616117e-06,
"loss": 1.7984,
"step": 2515
},
{
"epoch": 2.71259418729817,
"grad_norm": 0.96875,
"learning_rate": 5.016107288668148e-06,
"loss": 1.4965,
"step": 2520
},
{
"epoch": 2.717976318622174,
"grad_norm": 0.71484375,
"learning_rate": 4.832193321870082e-06,
"loss": 1.4131,
"step": 2525
},
{
"epoch": 2.7233584499461787,
"grad_norm": 1.21875,
"learning_rate": 4.651630711795507e-06,
"loss": 1.742,
"step": 2530
},
{
"epoch": 2.7287405812701833,
"grad_norm": 1.5703125,
"learning_rate": 4.474425816999306e-06,
"loss": 1.7317,
"step": 2535
},
{
"epoch": 2.7341227125941874,
"grad_norm": 0.7734375,
"learning_rate": 4.300584877793523e-06,
"loss": 1.4012,
"step": 2540
},
{
"epoch": 2.7395048439181915,
"grad_norm": 0.78515625,
"learning_rate": 4.13011401602782e-06,
"loss": 1.269,
"step": 2545
},
{
"epoch": 2.744886975242196,
"grad_norm": 0.69140625,
"learning_rate": 3.96301923487371e-06,
"loss": 1.4719,
"step": 2550
},
{
"epoch": 2.7502691065662,
"grad_norm": 0.98828125,
"learning_rate": 3.799306418613291e-06,
"loss": 1.424,
"step": 2555
},
{
"epoch": 2.7556512378902047,
"grad_norm": 1.0,
"learning_rate": 3.638981332431901e-06,
"loss": 1.5294,
"step": 2560
},
{
"epoch": 2.761033369214209,
"grad_norm": 0.94140625,
"learning_rate": 3.4820496222152333e-06,
"loss": 1.5446,
"step": 2565
},
{
"epoch": 2.766415500538213,
"grad_norm": 0.73046875,
"learning_rate": 3.328516814350402e-06,
"loss": 1.5216,
"step": 2570
},
{
"epoch": 2.7717976318622175,
"grad_norm": 0.9375,
"learning_rate": 3.178388315531411e-06,
"loss": 1.5401,
"step": 2575
},
{
"epoch": 2.7771797631862216,
"grad_norm": 0.703125,
"learning_rate": 3.031669412568694e-06,
"loss": 1.4231,
"step": 2580
},
{
"epoch": 2.782561894510226,
"grad_norm": 1.65625,
"learning_rate": 2.888365272202953e-06,
"loss": 1.2964,
"step": 2585
},
{
"epoch": 2.7879440258342303,
"grad_norm": 0.7109375,
"learning_rate": 2.7484809409232705e-06,
"loss": 1.2211,
"step": 2590
},
{
"epoch": 2.7933261571582344,
"grad_norm": 0.86328125,
"learning_rate": 2.612021344789284e-06,
"loss": 1.4812,
"step": 2595
},
{
"epoch": 2.798708288482239,
"grad_norm": 0.6953125,
"learning_rate": 2.4789912892578258e-06,
"loss": 1.7189,
"step": 2600
},
{
"epoch": 2.8040904198062435,
"grad_norm": 0.65625,
"learning_rate": 2.349395459013626e-06,
"loss": 1.3196,
"step": 2605
},
{
"epoch": 2.8094725511302476,
"grad_norm": 1.046875,
"learning_rate": 2.223238417804352e-06,
"loss": 1.4144,
"step": 2610
},
{
"epoch": 2.8148546824542517,
"grad_norm": 0.71875,
"learning_rate": 2.100524608279919e-06,
"loss": 1.3011,
"step": 2615
},
{
"epoch": 2.8202368137782563,
"grad_norm": 0.85546875,
"learning_rate": 1.9812583518360573e-06,
"loss": 1.4989,
"step": 2620
},
{
"epoch": 2.8256189451022604,
"grad_norm": 1.1953125,
"learning_rate": 1.865443848462045e-06,
"loss": 1.6008,
"step": 2625
},
{
"epoch": 2.831001076426265,
"grad_norm": 0.671875,
"learning_rate": 1.7530851765928947e-06,
"loss": 1.3724,
"step": 2630
},
{
"epoch": 2.836383207750269,
"grad_norm": 0.8359375,
"learning_rate": 1.6441862929657104e-06,
"loss": 1.4647,
"step": 2635
},
{
"epoch": 2.841765339074273,
"grad_norm": 0.85546875,
"learning_rate": 1.5387510324803122e-06,
"loss": 1.5235,
"step": 2640
},
{
"epoch": 2.8471474703982778,
"grad_norm": 0.6328125,
"learning_rate": 1.4367831080642435e-06,
"loss": 1.3849,
"step": 2645
},
{
"epoch": 2.852529601722282,
"grad_norm": 0.6796875,
"learning_rate": 1.338286110541942e-06,
"loss": 1.4417,
"step": 2650
},
{
"epoch": 2.8579117330462864,
"grad_norm": 1.140625,
"learning_rate": 1.2432635085084076e-06,
"loss": 1.2763,
"step": 2655
},
{
"epoch": 2.8632938643702905,
"grad_norm": 0.703125,
"learning_rate": 1.1517186482069232e-06,
"loss": 1.4491,
"step": 2660
},
{
"epoch": 2.868675995694295,
"grad_norm": 0.875,
"learning_rate": 1.0636547534113139e-06,
"loss": 1.6601,
"step": 2665
},
{
"epoch": 2.874058127018299,
"grad_norm": 0.65234375,
"learning_rate": 9.79074925312362e-07,
"loss": 1.2571,
"step": 2670
},
{
"epoch": 2.8794402583423038,
"grad_norm": 0.7734375,
"learning_rate": 8.979821424086488e-07,
"loss": 1.5522,
"step": 2675
},
{
"epoch": 2.884822389666308,
"grad_norm": 0.71875,
"learning_rate": 8.203792604016159e-07,
"loss": 1.5063,
"step": 2680
},
{
"epoch": 2.890204520990312,
"grad_norm": 0.80078125,
"learning_rate": 7.462690120950134e-07,
"loss": 1.4617,
"step": 2685
},
{
"epoch": 2.8955866523143166,
"grad_norm": 0.78515625,
"learning_rate": 6.756540072987094e-07,
"loss": 1.2957,
"step": 2690
},
{
"epoch": 2.9009687836383207,
"grad_norm": 1.3125,
"learning_rate": 6.085367327367197e-07,
"loss": 1.443,
"step": 2695
},
{
"epoch": 2.9063509149623252,
"grad_norm": 0.6875,
"learning_rate": 5.449195519596661e-07,
"loss": 1.4819,
"step": 2700
},
{
"epoch": 2.9117330462863293,
"grad_norm": 0.796875,
"learning_rate": 4.848047052615545e-07,
"loss": 1.6234,
"step": 2705
},
{
"epoch": 2.9171151776103335,
"grad_norm": 0.60546875,
"learning_rate": 4.2819430960087113e-07,
"loss": 1.5406,
"step": 2710
},
{
"epoch": 2.922497308934338,
"grad_norm": 0.66015625,
"learning_rate": 3.7509035852602015e-07,
"loss": 1.5775,
"step": 2715
},
{
"epoch": 2.9278794402583426,
"grad_norm": 0.77734375,
"learning_rate": 3.254947221051685e-07,
"loss": 1.5152,
"step": 2720
},
{
"epoch": 2.9332615715823467,
"grad_norm": 0.90625,
"learning_rate": 2.794091468602988e-07,
"loss": 1.57,
"step": 2725
},
{
"epoch": 2.938643702906351,
"grad_norm": 0.69140625,
"learning_rate": 2.368352557058362e-07,
"loss": 1.6458,
"step": 2730
},
{
"epoch": 2.9440258342303554,
"grad_norm": 0.78515625,
"learning_rate": 1.9777454789134953e-07,
"loss": 1.4748,
"step": 2735
},
{
"epoch": 2.9494079655543595,
"grad_norm": 1.421875,
"learning_rate": 1.6222839894887154e-07,
"loss": 1.6024,
"step": 2740
},
{
"epoch": 2.954790096878364,
"grad_norm": 0.6796875,
"learning_rate": 1.301980606444153e-07,
"loss": 1.0898,
"step": 2745
},
{
"epoch": 2.960172228202368,
"grad_norm": 0.71484375,
"learning_rate": 1.0168466093387619e-07,
"loss": 1.8948,
"step": 2750
},
{
"epoch": 2.9655543595263723,
"grad_norm": 0.7734375,
"learning_rate": 7.668920392335244e-08,
"loss": 1.5294,
"step": 2755
},
{
"epoch": 2.970936490850377,
"grad_norm": 0.55859375,
"learning_rate": 5.521256983374024e-08,
"loss": 1.0666,
"step": 2760
},
{
"epoch": 2.976318622174381,
"grad_norm": 0.6796875,
"learning_rate": 3.725551496978064e-08,
"loss": 1.6953,
"step": 2765
},
{
"epoch": 2.9817007534983855,
"grad_norm": 0.6796875,
"learning_rate": 2.281867169336982e-08,
"loss": 1.5101,
"step": 2770
},
{
"epoch": 2.9870828848223896,
"grad_norm": 0.79296875,
"learning_rate": 1.190254840135463e-08,
"loss": 1.4111,
"step": 2775
},
{
"epoch": 2.9924650161463937,
"grad_norm": 0.8359375,
"learning_rate": 4.507529507580266e-09,
"loss": 1.4808,
"step": 2780
},
{
"epoch": 2.9978471474703983,
"grad_norm": 0.7734375,
"learning_rate": 6.33875429389974e-10,
"loss": 1.6763,
"step": 2785
}
],
"logging_steps": 5,
"max_steps": 2787,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.04910971100201e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}