1JV38 / checkpoint-900 /trainer_state.json
gotzmann's picture
..
e976302
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.4012483281319661,
"eval_steps": 500,
"global_step": 900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00044583147570218456,
"grad_norm": 0.41694900393486023,
"learning_rate": 2.666666666666667e-07,
"loss": 1.9488,
"step": 1
},
{
"epoch": 0.0008916629514043691,
"grad_norm": 0.4325166940689087,
"learning_rate": 5.333333333333335e-07,
"loss": 1.9474,
"step": 2
},
{
"epoch": 0.0013374944271065537,
"grad_norm": 0.5329936146736145,
"learning_rate": 8.000000000000001e-07,
"loss": 1.9654,
"step": 3
},
{
"epoch": 0.0017833259028087382,
"grad_norm": 0.45425093173980713,
"learning_rate": 1.066666666666667e-06,
"loss": 2.0171,
"step": 4
},
{
"epoch": 0.002229157378510923,
"grad_norm": 0.42153477668762207,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.9727,
"step": 5
},
{
"epoch": 0.0026749888542131075,
"grad_norm": 0.42438578605651855,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.9308,
"step": 6
},
{
"epoch": 0.003120820329915292,
"grad_norm": 0.4049244225025177,
"learning_rate": 1.8666666666666669e-06,
"loss": 1.9581,
"step": 7
},
{
"epoch": 0.0035666518056174765,
"grad_norm": 0.40796998143196106,
"learning_rate": 2.133333333333334e-06,
"loss": 1.9542,
"step": 8
},
{
"epoch": 0.004012483281319661,
"grad_norm": 0.3876088261604309,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.9169,
"step": 9
},
{
"epoch": 0.004458314757021846,
"grad_norm": 0.41765469312667847,
"learning_rate": 2.666666666666667e-06,
"loss": 1.9551,
"step": 10
},
{
"epoch": 0.00490414623272403,
"grad_norm": 0.37440115213394165,
"learning_rate": 2.9333333333333338e-06,
"loss": 1.9341,
"step": 11
},
{
"epoch": 0.005349977708426215,
"grad_norm": 0.3740348815917969,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.9513,
"step": 12
},
{
"epoch": 0.0057958091841284,
"grad_norm": 0.34098368883132935,
"learning_rate": 3.4666666666666672e-06,
"loss": 1.9697,
"step": 13
},
{
"epoch": 0.006241640659830584,
"grad_norm": 0.3392350375652313,
"learning_rate": 3.7333333333333337e-06,
"loss": 1.8661,
"step": 14
},
{
"epoch": 0.006687472135532769,
"grad_norm": 0.30836546421051025,
"learning_rate": 4.000000000000001e-06,
"loss": 1.9398,
"step": 15
},
{
"epoch": 0.007133303611234953,
"grad_norm": 0.3208477199077606,
"learning_rate": 4.266666666666668e-06,
"loss": 1.9136,
"step": 16
},
{
"epoch": 0.007579135086937138,
"grad_norm": 0.31885215640068054,
"learning_rate": 4.533333333333334e-06,
"loss": 1.9242,
"step": 17
},
{
"epoch": 0.008024966562639322,
"grad_norm": 0.27593743801116943,
"learning_rate": 4.800000000000001e-06,
"loss": 1.8541,
"step": 18
},
{
"epoch": 0.008470798038341507,
"grad_norm": 0.2847069203853607,
"learning_rate": 5.0666666666666676e-06,
"loss": 1.9634,
"step": 19
},
{
"epoch": 0.008916629514043692,
"grad_norm": 0.274640828371048,
"learning_rate": 5.333333333333334e-06,
"loss": 1.8762,
"step": 20
},
{
"epoch": 0.009362460989745877,
"grad_norm": 0.2889622449874878,
"learning_rate": 5.600000000000001e-06,
"loss": 1.9744,
"step": 21
},
{
"epoch": 0.00980829246544806,
"grad_norm": 0.28000110387802124,
"learning_rate": 5.8666666666666675e-06,
"loss": 1.9691,
"step": 22
},
{
"epoch": 0.010254123941150245,
"grad_norm": 0.2684955894947052,
"learning_rate": 6.133333333333334e-06,
"loss": 1.9243,
"step": 23
},
{
"epoch": 0.01069995541685243,
"grad_norm": 0.2879243791103363,
"learning_rate": 6.4000000000000006e-06,
"loss": 2.062,
"step": 24
},
{
"epoch": 0.011145786892554615,
"grad_norm": 0.2579769492149353,
"learning_rate": 6.666666666666667e-06,
"loss": 1.9667,
"step": 25
},
{
"epoch": 0.0115916183682568,
"grad_norm": 0.2598419785499573,
"learning_rate": 6.9333333333333344e-06,
"loss": 1.9397,
"step": 26
},
{
"epoch": 0.012037449843958983,
"grad_norm": 0.2543875575065613,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.8795,
"step": 27
},
{
"epoch": 0.012483281319661168,
"grad_norm": 0.2683740258216858,
"learning_rate": 7.4666666666666675e-06,
"loss": 2.039,
"step": 28
},
{
"epoch": 0.012929112795363353,
"grad_norm": 0.22718575596809387,
"learning_rate": 7.733333333333334e-06,
"loss": 1.8735,
"step": 29
},
{
"epoch": 0.013374944271065538,
"grad_norm": 0.2308313548564911,
"learning_rate": 8.000000000000001e-06,
"loss": 1.9403,
"step": 30
},
{
"epoch": 0.013820775746767721,
"grad_norm": 0.22583268582820892,
"learning_rate": 8.266666666666667e-06,
"loss": 1.9798,
"step": 31
},
{
"epoch": 0.014266607222469906,
"grad_norm": 0.2153775542974472,
"learning_rate": 8.533333333333335e-06,
"loss": 1.8289,
"step": 32
},
{
"epoch": 0.014712438698172091,
"grad_norm": 0.21741226315498352,
"learning_rate": 8.8e-06,
"loss": 1.8725,
"step": 33
},
{
"epoch": 0.015158270173874276,
"grad_norm": 0.24217155575752258,
"learning_rate": 9.066666666666667e-06,
"loss": 2.0008,
"step": 34
},
{
"epoch": 0.01560410164957646,
"grad_norm": 0.21178147196769714,
"learning_rate": 9.333333333333334e-06,
"loss": 1.8646,
"step": 35
},
{
"epoch": 0.016049933125278644,
"grad_norm": 0.2568570077419281,
"learning_rate": 9.600000000000001e-06,
"loss": 1.8402,
"step": 36
},
{
"epoch": 0.01649576460098083,
"grad_norm": 0.21020956337451935,
"learning_rate": 9.866666666666668e-06,
"loss": 1.8991,
"step": 37
},
{
"epoch": 0.016941596076683014,
"grad_norm": 0.2205541729927063,
"learning_rate": 1.0133333333333335e-05,
"loss": 1.8296,
"step": 38
},
{
"epoch": 0.017387427552385197,
"grad_norm": 0.23295548558235168,
"learning_rate": 1.04e-05,
"loss": 1.8858,
"step": 39
},
{
"epoch": 0.017833259028087384,
"grad_norm": 0.20862042903900146,
"learning_rate": 1.0666666666666667e-05,
"loss": 1.8589,
"step": 40
},
{
"epoch": 0.018279090503789567,
"grad_norm": 0.20791663229465485,
"learning_rate": 1.0933333333333334e-05,
"loss": 1.9105,
"step": 41
},
{
"epoch": 0.018724921979491754,
"grad_norm": 0.23138144612312317,
"learning_rate": 1.1200000000000001e-05,
"loss": 1.9205,
"step": 42
},
{
"epoch": 0.019170753455193937,
"grad_norm": 0.2184125930070877,
"learning_rate": 1.1466666666666668e-05,
"loss": 1.9443,
"step": 43
},
{
"epoch": 0.01961658493089612,
"grad_norm": 0.19976778328418732,
"learning_rate": 1.1733333333333335e-05,
"loss": 1.7878,
"step": 44
},
{
"epoch": 0.020062416406598307,
"grad_norm": 0.19608213007450104,
"learning_rate": 1.2e-05,
"loss": 1.8668,
"step": 45
},
{
"epoch": 0.02050824788230049,
"grad_norm": 0.2110237330198288,
"learning_rate": 1.2266666666666667e-05,
"loss": 1.9117,
"step": 46
},
{
"epoch": 0.020954079358002677,
"grad_norm": 0.21283794939517975,
"learning_rate": 1.2533333333333336e-05,
"loss": 1.9009,
"step": 47
},
{
"epoch": 0.02139991083370486,
"grad_norm": 0.21566396951675415,
"learning_rate": 1.2800000000000001e-05,
"loss": 1.8339,
"step": 48
},
{
"epoch": 0.021845742309407043,
"grad_norm": 0.21194687485694885,
"learning_rate": 1.3066666666666668e-05,
"loss": 1.9119,
"step": 49
},
{
"epoch": 0.02229157378510923,
"grad_norm": 0.21619786322116852,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.9621,
"step": 50
},
{
"epoch": 0.022737405260811413,
"grad_norm": 0.21244817972183228,
"learning_rate": 1.3600000000000002e-05,
"loss": 1.8185,
"step": 51
},
{
"epoch": 0.0231832367365136,
"grad_norm": 0.20910470187664032,
"learning_rate": 1.3866666666666669e-05,
"loss": 1.8852,
"step": 52
},
{
"epoch": 0.023629068212215783,
"grad_norm": 0.2056826651096344,
"learning_rate": 1.4133333333333334e-05,
"loss": 1.7534,
"step": 53
},
{
"epoch": 0.024074899687917966,
"grad_norm": 0.20464245975017548,
"learning_rate": 1.4400000000000001e-05,
"loss": 1.8634,
"step": 54
},
{
"epoch": 0.024520731163620153,
"grad_norm": 0.21582286059856415,
"learning_rate": 1.4666666666666666e-05,
"loss": 1.8456,
"step": 55
},
{
"epoch": 0.024966562639322336,
"grad_norm": 0.21299712359905243,
"learning_rate": 1.4933333333333335e-05,
"loss": 1.8615,
"step": 56
},
{
"epoch": 0.02541239411502452,
"grad_norm": 0.22036010026931763,
"learning_rate": 1.5200000000000002e-05,
"loss": 1.9713,
"step": 57
},
{
"epoch": 0.025858225590726706,
"grad_norm": 0.2094155102968216,
"learning_rate": 1.546666666666667e-05,
"loss": 1.8669,
"step": 58
},
{
"epoch": 0.02630405706642889,
"grad_norm": 0.219874769449234,
"learning_rate": 1.5733333333333334e-05,
"loss": 1.9496,
"step": 59
},
{
"epoch": 0.026749888542131076,
"grad_norm": 0.2156878113746643,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.8569,
"step": 60
},
{
"epoch": 0.02719572001783326,
"grad_norm": 0.2157766968011856,
"learning_rate": 1.6266666666666668e-05,
"loss": 1.836,
"step": 61
},
{
"epoch": 0.027641551493535442,
"grad_norm": 0.2111901044845581,
"learning_rate": 1.6533333333333333e-05,
"loss": 1.8721,
"step": 62
},
{
"epoch": 0.02808738296923763,
"grad_norm": 0.2262468785047531,
"learning_rate": 1.6800000000000002e-05,
"loss": 1.9684,
"step": 63
},
{
"epoch": 0.028533214444939812,
"grad_norm": 0.21171987056732178,
"learning_rate": 1.706666666666667e-05,
"loss": 1.7913,
"step": 64
},
{
"epoch": 0.028979045920642,
"grad_norm": 0.2222784012556076,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.8713,
"step": 65
},
{
"epoch": 0.029424877396344182,
"grad_norm": 0.22467799484729767,
"learning_rate": 1.76e-05,
"loss": 1.8577,
"step": 66
},
{
"epoch": 0.029870708872046365,
"grad_norm": 0.22000645101070404,
"learning_rate": 1.7866666666666666e-05,
"loss": 1.7445,
"step": 67
},
{
"epoch": 0.03031654034774855,
"grad_norm": 0.21429285407066345,
"learning_rate": 1.8133333333333335e-05,
"loss": 1.7858,
"step": 68
},
{
"epoch": 0.030762371823450735,
"grad_norm": 0.2181319147348404,
"learning_rate": 1.8400000000000003e-05,
"loss": 1.8239,
"step": 69
},
{
"epoch": 0.03120820329915292,
"grad_norm": 0.23378431797027588,
"learning_rate": 1.866666666666667e-05,
"loss": 1.8719,
"step": 70
},
{
"epoch": 0.03165403477485511,
"grad_norm": 0.23543697595596313,
"learning_rate": 1.8933333333333334e-05,
"loss": 1.9101,
"step": 71
},
{
"epoch": 0.03209986625055729,
"grad_norm": 0.22190536558628082,
"learning_rate": 1.9200000000000003e-05,
"loss": 1.8254,
"step": 72
},
{
"epoch": 0.032545697726259475,
"grad_norm": 0.2234829217195511,
"learning_rate": 1.9466666666666668e-05,
"loss": 1.7942,
"step": 73
},
{
"epoch": 0.03299152920196166,
"grad_norm": 0.2278570681810379,
"learning_rate": 1.9733333333333336e-05,
"loss": 1.8664,
"step": 74
},
{
"epoch": 0.03343736067766384,
"grad_norm": 0.236073300242424,
"learning_rate": 2e-05,
"loss": 1.8614,
"step": 75
},
{
"epoch": 0.03388319215336603,
"grad_norm": 0.22639039158821106,
"learning_rate": 2.026666666666667e-05,
"loss": 1.8326,
"step": 76
},
{
"epoch": 0.034329023629068214,
"grad_norm": 0.23513582348823547,
"learning_rate": 2.0533333333333336e-05,
"loss": 1.8779,
"step": 77
},
{
"epoch": 0.034774855104770394,
"grad_norm": 0.24936141073703766,
"learning_rate": 2.08e-05,
"loss": 1.8061,
"step": 78
},
{
"epoch": 0.03522068658047258,
"grad_norm": 0.2312684804201126,
"learning_rate": 2.1066666666666666e-05,
"loss": 1.8214,
"step": 79
},
{
"epoch": 0.03566651805617477,
"grad_norm": 0.24221794307231903,
"learning_rate": 2.1333333333333335e-05,
"loss": 1.8691,
"step": 80
},
{
"epoch": 0.03611234953187695,
"grad_norm": 0.24977678060531616,
"learning_rate": 2.1600000000000003e-05,
"loss": 1.87,
"step": 81
},
{
"epoch": 0.036558181007579134,
"grad_norm": 0.24968618154525757,
"learning_rate": 2.186666666666667e-05,
"loss": 1.7725,
"step": 82
},
{
"epoch": 0.03700401248328132,
"grad_norm": 0.24534040689468384,
"learning_rate": 2.2133333333333337e-05,
"loss": 1.7268,
"step": 83
},
{
"epoch": 0.03744984395898351,
"grad_norm": 0.2817310392856598,
"learning_rate": 2.2400000000000002e-05,
"loss": 1.8211,
"step": 84
},
{
"epoch": 0.03789567543468569,
"grad_norm": 0.24851234257221222,
"learning_rate": 2.2666666666666668e-05,
"loss": 1.801,
"step": 85
},
{
"epoch": 0.038341506910387874,
"grad_norm": 0.2601252496242523,
"learning_rate": 2.2933333333333336e-05,
"loss": 1.8748,
"step": 86
},
{
"epoch": 0.03878733838609006,
"grad_norm": 0.25771164894104004,
"learning_rate": 2.32e-05,
"loss": 1.8054,
"step": 87
},
{
"epoch": 0.03923316986179224,
"grad_norm": 0.25612396001815796,
"learning_rate": 2.346666666666667e-05,
"loss": 1.8031,
"step": 88
},
{
"epoch": 0.03967900133749443,
"grad_norm": 0.30037111043930054,
"learning_rate": 2.373333333333334e-05,
"loss": 1.7969,
"step": 89
},
{
"epoch": 0.04012483281319661,
"grad_norm": 0.2585238218307495,
"learning_rate": 2.4e-05,
"loss": 1.8384,
"step": 90
},
{
"epoch": 0.04057066428889879,
"grad_norm": 0.26387372612953186,
"learning_rate": 2.426666666666667e-05,
"loss": 1.9031,
"step": 91
},
{
"epoch": 0.04101649576460098,
"grad_norm": 0.2529267370700836,
"learning_rate": 2.4533333333333334e-05,
"loss": 1.8204,
"step": 92
},
{
"epoch": 0.041462327240303166,
"grad_norm": 0.25664445757865906,
"learning_rate": 2.4800000000000003e-05,
"loss": 1.8447,
"step": 93
},
{
"epoch": 0.04190815871600535,
"grad_norm": 0.2572501301765442,
"learning_rate": 2.5066666666666672e-05,
"loss": 1.8514,
"step": 94
},
{
"epoch": 0.04235399019170753,
"grad_norm": 0.26171356439590454,
"learning_rate": 2.5333333333333334e-05,
"loss": 1.7994,
"step": 95
},
{
"epoch": 0.04279982166740972,
"grad_norm": 0.2504459619522095,
"learning_rate": 2.5600000000000002e-05,
"loss": 1.8271,
"step": 96
},
{
"epoch": 0.043245653143111906,
"grad_norm": 0.25057297945022583,
"learning_rate": 2.5866666666666667e-05,
"loss": 1.7822,
"step": 97
},
{
"epoch": 0.043691484618814086,
"grad_norm": 0.271733820438385,
"learning_rate": 2.6133333333333336e-05,
"loss": 1.8345,
"step": 98
},
{
"epoch": 0.04413731609451627,
"grad_norm": 0.2711006700992584,
"learning_rate": 2.6400000000000005e-05,
"loss": 1.8945,
"step": 99
},
{
"epoch": 0.04458314757021846,
"grad_norm": 0.29651570320129395,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.923,
"step": 100
},
{
"epoch": 0.04502897904592064,
"grad_norm": 0.28082215785980225,
"learning_rate": 2.6933333333333335e-05,
"loss": 1.8876,
"step": 101
},
{
"epoch": 0.045474810521622826,
"grad_norm": 0.26620352268218994,
"learning_rate": 2.7200000000000004e-05,
"loss": 1.8855,
"step": 102
},
{
"epoch": 0.04592064199732501,
"grad_norm": 0.2536965310573578,
"learning_rate": 2.746666666666667e-05,
"loss": 1.7922,
"step": 103
},
{
"epoch": 0.0463664734730272,
"grad_norm": 0.26968443393707275,
"learning_rate": 2.7733333333333338e-05,
"loss": 1.7784,
"step": 104
},
{
"epoch": 0.04681230494872938,
"grad_norm": 0.2990209460258484,
"learning_rate": 2.8e-05,
"loss": 1.8285,
"step": 105
},
{
"epoch": 0.047258136424431565,
"grad_norm": 0.294802188873291,
"learning_rate": 2.8266666666666668e-05,
"loss": 1.8964,
"step": 106
},
{
"epoch": 0.04770396790013375,
"grad_norm": 0.3011243939399719,
"learning_rate": 2.8533333333333337e-05,
"loss": 1.8652,
"step": 107
},
{
"epoch": 0.04814979937583593,
"grad_norm": 0.292427659034729,
"learning_rate": 2.8800000000000002e-05,
"loss": 1.7647,
"step": 108
},
{
"epoch": 0.04859563085153812,
"grad_norm": 0.2936179041862488,
"learning_rate": 2.906666666666667e-05,
"loss": 1.8371,
"step": 109
},
{
"epoch": 0.049041462327240305,
"grad_norm": 0.28111955523490906,
"learning_rate": 2.9333333333333333e-05,
"loss": 1.8064,
"step": 110
},
{
"epoch": 0.049487293802942485,
"grad_norm": 0.3002088963985443,
"learning_rate": 2.96e-05,
"loss": 1.8461,
"step": 111
},
{
"epoch": 0.04993312527864467,
"grad_norm": 0.2941628694534302,
"learning_rate": 2.986666666666667e-05,
"loss": 1.8619,
"step": 112
},
{
"epoch": 0.05037895675434686,
"grad_norm": 0.27041497826576233,
"learning_rate": 3.0133333333333335e-05,
"loss": 1.761,
"step": 113
},
{
"epoch": 0.05082478823004904,
"grad_norm": 0.3027989864349365,
"learning_rate": 3.0400000000000004e-05,
"loss": 1.8031,
"step": 114
},
{
"epoch": 0.051270619705751225,
"grad_norm": 0.2786939740180969,
"learning_rate": 3.066666666666667e-05,
"loss": 1.8061,
"step": 115
},
{
"epoch": 0.05171645118145341,
"grad_norm": 0.2974098324775696,
"learning_rate": 3.093333333333334e-05,
"loss": 1.9473,
"step": 116
},
{
"epoch": 0.0521622826571556,
"grad_norm": 0.32027050852775574,
"learning_rate": 3.1200000000000006e-05,
"loss": 1.7295,
"step": 117
},
{
"epoch": 0.05260811413285778,
"grad_norm": 0.27729111909866333,
"learning_rate": 3.146666666666667e-05,
"loss": 1.6948,
"step": 118
},
{
"epoch": 0.053053945608559964,
"grad_norm": 0.34655502438545227,
"learning_rate": 3.173333333333334e-05,
"loss": 1.8459,
"step": 119
},
{
"epoch": 0.05349977708426215,
"grad_norm": 0.29461273550987244,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.8,
"step": 120
},
{
"epoch": 0.05394560855996433,
"grad_norm": 0.3321416676044464,
"learning_rate": 3.226666666666667e-05,
"loss": 1.8233,
"step": 121
},
{
"epoch": 0.05439144003566652,
"grad_norm": 0.29211312532424927,
"learning_rate": 3.2533333333333336e-05,
"loss": 1.8488,
"step": 122
},
{
"epoch": 0.054837271511368704,
"grad_norm": 0.3023246228694916,
"learning_rate": 3.28e-05,
"loss": 1.8617,
"step": 123
},
{
"epoch": 0.055283102987070884,
"grad_norm": 0.3080272078514099,
"learning_rate": 3.3066666666666666e-05,
"loss": 1.8749,
"step": 124
},
{
"epoch": 0.05572893446277307,
"grad_norm": 0.29739588499069214,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.9163,
"step": 125
},
{
"epoch": 0.05617476593847526,
"grad_norm": 0.3099679946899414,
"learning_rate": 3.3600000000000004e-05,
"loss": 1.8256,
"step": 126
},
{
"epoch": 0.056620597414177444,
"grad_norm": 0.3503029942512512,
"learning_rate": 3.386666666666667e-05,
"loss": 1.9656,
"step": 127
},
{
"epoch": 0.057066428889879624,
"grad_norm": 0.35092490911483765,
"learning_rate": 3.413333333333334e-05,
"loss": 1.9083,
"step": 128
},
{
"epoch": 0.05751226036558181,
"grad_norm": 0.28823041915893555,
"learning_rate": 3.44e-05,
"loss": 1.837,
"step": 129
},
{
"epoch": 0.057958091841284,
"grad_norm": 0.3080367147922516,
"learning_rate": 3.466666666666667e-05,
"loss": 1.8351,
"step": 130
},
{
"epoch": 0.05840392331698618,
"grad_norm": 0.27589717507362366,
"learning_rate": 3.493333333333333e-05,
"loss": 1.8196,
"step": 131
},
{
"epoch": 0.058849754792688364,
"grad_norm": 0.310061514377594,
"learning_rate": 3.52e-05,
"loss": 1.8258,
"step": 132
},
{
"epoch": 0.05929558626839055,
"grad_norm": 0.30034536123275757,
"learning_rate": 3.546666666666667e-05,
"loss": 1.7869,
"step": 133
},
{
"epoch": 0.05974141774409273,
"grad_norm": 0.3570665419101715,
"learning_rate": 3.573333333333333e-05,
"loss": 1.8544,
"step": 134
},
{
"epoch": 0.06018724921979492,
"grad_norm": 0.3011762201786041,
"learning_rate": 3.6e-05,
"loss": 1.8537,
"step": 135
},
{
"epoch": 0.0606330806954971,
"grad_norm": 0.3773946762084961,
"learning_rate": 3.626666666666667e-05,
"loss": 1.8586,
"step": 136
},
{
"epoch": 0.06107891217119929,
"grad_norm": 0.27055782079696655,
"learning_rate": 3.653333333333334e-05,
"loss": 1.8264,
"step": 137
},
{
"epoch": 0.06152474364690147,
"grad_norm": 0.3715250492095947,
"learning_rate": 3.680000000000001e-05,
"loss": 1.8942,
"step": 138
},
{
"epoch": 0.061970575122603656,
"grad_norm": 0.29873985052108765,
"learning_rate": 3.706666666666667e-05,
"loss": 1.8412,
"step": 139
},
{
"epoch": 0.06241640659830584,
"grad_norm": 0.31906992197036743,
"learning_rate": 3.733333333333334e-05,
"loss": 1.7687,
"step": 140
},
{
"epoch": 0.06286223807400802,
"grad_norm": 0.2958746552467346,
"learning_rate": 3.76e-05,
"loss": 1.8127,
"step": 141
},
{
"epoch": 0.06330806954971022,
"grad_norm": 0.32697004079818726,
"learning_rate": 3.786666666666667e-05,
"loss": 1.8661,
"step": 142
},
{
"epoch": 0.0637539010254124,
"grad_norm": 0.2766285240650177,
"learning_rate": 3.8133333333333336e-05,
"loss": 1.7151,
"step": 143
},
{
"epoch": 0.06419973250111458,
"grad_norm": 0.31309226155281067,
"learning_rate": 3.8400000000000005e-05,
"loss": 1.8474,
"step": 144
},
{
"epoch": 0.06464556397681677,
"grad_norm": 0.2824843227863312,
"learning_rate": 3.866666666666667e-05,
"loss": 1.8155,
"step": 145
},
{
"epoch": 0.06509139545251895,
"grad_norm": 0.2713295817375183,
"learning_rate": 3.8933333333333336e-05,
"loss": 1.8877,
"step": 146
},
{
"epoch": 0.06553722692822113,
"grad_norm": 0.35191434621810913,
"learning_rate": 3.9200000000000004e-05,
"loss": 1.7751,
"step": 147
},
{
"epoch": 0.06598305840392332,
"grad_norm": 0.30430588126182556,
"learning_rate": 3.946666666666667e-05,
"loss": 1.8379,
"step": 148
},
{
"epoch": 0.0664288898796255,
"grad_norm": 0.34200629591941833,
"learning_rate": 3.9733333333333335e-05,
"loss": 1.7795,
"step": 149
},
{
"epoch": 0.06687472135532768,
"grad_norm": 0.28752633929252625,
"learning_rate": 4e-05,
"loss": 1.8612,
"step": 150
},
{
"epoch": 0.06732055283102988,
"grad_norm": 0.3259822726249695,
"learning_rate": 4.0266666666666665e-05,
"loss": 1.8534,
"step": 151
},
{
"epoch": 0.06776638430673206,
"grad_norm": 0.2901393175125122,
"learning_rate": 4.053333333333334e-05,
"loss": 1.8215,
"step": 152
},
{
"epoch": 0.06821221578243424,
"grad_norm": 0.30397653579711914,
"learning_rate": 4.08e-05,
"loss": 1.7901,
"step": 153
},
{
"epoch": 0.06865804725813643,
"grad_norm": 0.31820032000541687,
"learning_rate": 4.106666666666667e-05,
"loss": 1.7694,
"step": 154
},
{
"epoch": 0.06910387873383861,
"grad_norm": 0.31631478667259216,
"learning_rate": 4.133333333333334e-05,
"loss": 1.7254,
"step": 155
},
{
"epoch": 0.06954971020954079,
"grad_norm": 0.32512184977531433,
"learning_rate": 4.16e-05,
"loss": 1.7531,
"step": 156
},
{
"epoch": 0.06999554168524298,
"grad_norm": 0.2968920171260834,
"learning_rate": 4.186666666666667e-05,
"loss": 1.8147,
"step": 157
},
{
"epoch": 0.07044137316094516,
"grad_norm": 0.335467129945755,
"learning_rate": 4.213333333333333e-05,
"loss": 1.7788,
"step": 158
},
{
"epoch": 0.07088720463664734,
"grad_norm": 0.33457300066947937,
"learning_rate": 4.240000000000001e-05,
"loss": 1.874,
"step": 159
},
{
"epoch": 0.07133303611234953,
"grad_norm": 0.3013593554496765,
"learning_rate": 4.266666666666667e-05,
"loss": 1.8856,
"step": 160
},
{
"epoch": 0.07177886758805171,
"grad_norm": 0.273561030626297,
"learning_rate": 4.293333333333333e-05,
"loss": 1.7459,
"step": 161
},
{
"epoch": 0.0722246990637539,
"grad_norm": 0.283621221780777,
"learning_rate": 4.3200000000000007e-05,
"loss": 1.8431,
"step": 162
},
{
"epoch": 0.07267053053945609,
"grad_norm": 0.27030712366104126,
"learning_rate": 4.346666666666667e-05,
"loss": 1.7615,
"step": 163
},
{
"epoch": 0.07311636201515827,
"grad_norm": 0.27857705950737,
"learning_rate": 4.373333333333334e-05,
"loss": 1.8442,
"step": 164
},
{
"epoch": 0.07356219349086046,
"grad_norm": 0.2681543827056885,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.7566,
"step": 165
},
{
"epoch": 0.07400802496656264,
"grad_norm": 0.28761669993400574,
"learning_rate": 4.4266666666666674e-05,
"loss": 1.7749,
"step": 166
},
{
"epoch": 0.07445385644226482,
"grad_norm": 0.318764328956604,
"learning_rate": 4.4533333333333336e-05,
"loss": 1.8249,
"step": 167
},
{
"epoch": 0.07489968791796701,
"grad_norm": 0.2913915514945984,
"learning_rate": 4.4800000000000005e-05,
"loss": 1.8324,
"step": 168
},
{
"epoch": 0.0753455193936692,
"grad_norm": 0.2661246061325073,
"learning_rate": 4.506666666666667e-05,
"loss": 1.8126,
"step": 169
},
{
"epoch": 0.07579135086937137,
"grad_norm": 0.29662206768989563,
"learning_rate": 4.5333333333333335e-05,
"loss": 1.84,
"step": 170
},
{
"epoch": 0.07623718234507357,
"grad_norm": 0.3414687216281891,
"learning_rate": 4.56e-05,
"loss": 1.8259,
"step": 171
},
{
"epoch": 0.07668301382077575,
"grad_norm": 0.29384845495224,
"learning_rate": 4.586666666666667e-05,
"loss": 1.8341,
"step": 172
},
{
"epoch": 0.07712884529647793,
"grad_norm": 0.313362717628479,
"learning_rate": 4.6133333333333334e-05,
"loss": 1.8403,
"step": 173
},
{
"epoch": 0.07757467677218012,
"grad_norm": 0.27511510252952576,
"learning_rate": 4.64e-05,
"loss": 1.8502,
"step": 174
},
{
"epoch": 0.0780205082478823,
"grad_norm": 0.28761816024780273,
"learning_rate": 4.666666666666667e-05,
"loss": 1.8157,
"step": 175
},
{
"epoch": 0.07846633972358448,
"grad_norm": 0.30127012729644775,
"learning_rate": 4.693333333333334e-05,
"loss": 1.8559,
"step": 176
},
{
"epoch": 0.07891217119928667,
"grad_norm": 0.26424428820610046,
"learning_rate": 4.72e-05,
"loss": 1.81,
"step": 177
},
{
"epoch": 0.07935800267498885,
"grad_norm": 0.34712114930152893,
"learning_rate": 4.746666666666668e-05,
"loss": 1.8874,
"step": 178
},
{
"epoch": 0.07980383415069103,
"grad_norm": 0.34591299295425415,
"learning_rate": 4.773333333333334e-05,
"loss": 1.7735,
"step": 179
},
{
"epoch": 0.08024966562639323,
"grad_norm": 0.3041944205760956,
"learning_rate": 4.8e-05,
"loss": 1.8873,
"step": 180
},
{
"epoch": 0.0806954971020954,
"grad_norm": 0.3604406714439392,
"learning_rate": 4.826666666666668e-05,
"loss": 1.7453,
"step": 181
},
{
"epoch": 0.08114132857779759,
"grad_norm": 0.2718447744846344,
"learning_rate": 4.853333333333334e-05,
"loss": 1.7958,
"step": 182
},
{
"epoch": 0.08158716005349978,
"grad_norm": 0.42196327447891235,
"learning_rate": 4.88e-05,
"loss": 1.8315,
"step": 183
},
{
"epoch": 0.08203299152920196,
"grad_norm": 0.24650803208351135,
"learning_rate": 4.906666666666667e-05,
"loss": 1.7289,
"step": 184
},
{
"epoch": 0.08247882300490414,
"grad_norm": 0.35063791275024414,
"learning_rate": 4.933333333333334e-05,
"loss": 1.7582,
"step": 185
},
{
"epoch": 0.08292465448060633,
"grad_norm": 0.2629041373729706,
"learning_rate": 4.9600000000000006e-05,
"loss": 1.9033,
"step": 186
},
{
"epoch": 0.08337048595630851,
"grad_norm": 0.292608380317688,
"learning_rate": 4.986666666666667e-05,
"loss": 1.8062,
"step": 187
},
{
"epoch": 0.0838163174320107,
"grad_norm": 0.2840345501899719,
"learning_rate": 5.0133333333333343e-05,
"loss": 1.818,
"step": 188
},
{
"epoch": 0.08426214890771289,
"grad_norm": 0.3064083755016327,
"learning_rate": 5.0400000000000005e-05,
"loss": 1.7439,
"step": 189
},
{
"epoch": 0.08470798038341507,
"grad_norm": 0.2645147740840912,
"learning_rate": 5.066666666666667e-05,
"loss": 1.9059,
"step": 190
},
{
"epoch": 0.08515381185911726,
"grad_norm": 0.2822587192058563,
"learning_rate": 5.093333333333334e-05,
"loss": 1.8309,
"step": 191
},
{
"epoch": 0.08559964333481944,
"grad_norm": 0.2765088379383087,
"learning_rate": 5.1200000000000004e-05,
"loss": 1.8497,
"step": 192
},
{
"epoch": 0.08604547481052162,
"grad_norm": 0.27604249119758606,
"learning_rate": 5.1466666666666666e-05,
"loss": 1.6965,
"step": 193
},
{
"epoch": 0.08649130628622381,
"grad_norm": 0.24740959703922272,
"learning_rate": 5.1733333333333335e-05,
"loss": 1.7282,
"step": 194
},
{
"epoch": 0.08693713776192599,
"grad_norm": 0.28995606303215027,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.8073,
"step": 195
},
{
"epoch": 0.08738296923762817,
"grad_norm": 0.2612221837043762,
"learning_rate": 5.226666666666667e-05,
"loss": 1.8055,
"step": 196
},
{
"epoch": 0.08782880071333037,
"grad_norm": 0.2690058648586273,
"learning_rate": 5.2533333333333334e-05,
"loss": 1.8054,
"step": 197
},
{
"epoch": 0.08827463218903255,
"grad_norm": 0.28274258971214294,
"learning_rate": 5.280000000000001e-05,
"loss": 1.7532,
"step": 198
},
{
"epoch": 0.08872046366473473,
"grad_norm": 0.2919791340827942,
"learning_rate": 5.306666666666667e-05,
"loss": 1.8258,
"step": 199
},
{
"epoch": 0.08916629514043692,
"grad_norm": 0.25825726985931396,
"learning_rate": 5.333333333333333e-05,
"loss": 1.7981,
"step": 200
},
{
"epoch": 0.0896121266161391,
"grad_norm": 0.26243504881858826,
"learning_rate": 5.360000000000001e-05,
"loss": 1.8343,
"step": 201
},
{
"epoch": 0.09005795809184128,
"grad_norm": 0.2816524803638458,
"learning_rate": 5.386666666666667e-05,
"loss": 1.7426,
"step": 202
},
{
"epoch": 0.09050378956754347,
"grad_norm": 0.29419633746147156,
"learning_rate": 5.413333333333333e-05,
"loss": 1.7996,
"step": 203
},
{
"epoch": 0.09094962104324565,
"grad_norm": 0.28757423162460327,
"learning_rate": 5.440000000000001e-05,
"loss": 1.7916,
"step": 204
},
{
"epoch": 0.09139545251894783,
"grad_norm": 0.2410411238670349,
"learning_rate": 5.466666666666667e-05,
"loss": 1.743,
"step": 205
},
{
"epoch": 0.09184128399465002,
"grad_norm": 0.3360425531864166,
"learning_rate": 5.493333333333334e-05,
"loss": 1.77,
"step": 206
},
{
"epoch": 0.0922871154703522,
"grad_norm": 0.25519052147865295,
"learning_rate": 5.52e-05,
"loss": 1.8308,
"step": 207
},
{
"epoch": 0.0927329469460544,
"grad_norm": 0.3632420003414154,
"learning_rate": 5.5466666666666675e-05,
"loss": 1.8317,
"step": 208
},
{
"epoch": 0.09317877842175658,
"grad_norm": 0.24667537212371826,
"learning_rate": 5.573333333333334e-05,
"loss": 1.7549,
"step": 209
},
{
"epoch": 0.09362460989745876,
"grad_norm": 0.3362181782722473,
"learning_rate": 5.6e-05,
"loss": 1.7526,
"step": 210
},
{
"epoch": 0.09407044137316095,
"grad_norm": 0.25742268562316895,
"learning_rate": 5.6266666666666675e-05,
"loss": 1.817,
"step": 211
},
{
"epoch": 0.09451627284886313,
"grad_norm": 0.3430984318256378,
"learning_rate": 5.6533333333333336e-05,
"loss": 1.7939,
"step": 212
},
{
"epoch": 0.09496210432456531,
"grad_norm": 0.2712782919406891,
"learning_rate": 5.6800000000000005e-05,
"loss": 1.7742,
"step": 213
},
{
"epoch": 0.0954079358002675,
"grad_norm": 0.29844462871551514,
"learning_rate": 5.7066666666666674e-05,
"loss": 1.7925,
"step": 214
},
{
"epoch": 0.09585376727596968,
"grad_norm": 0.2859255075454712,
"learning_rate": 5.7333333333333336e-05,
"loss": 1.8115,
"step": 215
},
{
"epoch": 0.09629959875167186,
"grad_norm": 0.2815805971622467,
"learning_rate": 5.7600000000000004e-05,
"loss": 1.7645,
"step": 216
},
{
"epoch": 0.09674543022737406,
"grad_norm": 0.25476354360580444,
"learning_rate": 5.786666666666667e-05,
"loss": 1.7237,
"step": 217
},
{
"epoch": 0.09719126170307624,
"grad_norm": 0.25315555930137634,
"learning_rate": 5.813333333333334e-05,
"loss": 1.8144,
"step": 218
},
{
"epoch": 0.09763709317877842,
"grad_norm": 0.3066805899143219,
"learning_rate": 5.84e-05,
"loss": 1.7694,
"step": 219
},
{
"epoch": 0.09808292465448061,
"grad_norm": 0.2467024177312851,
"learning_rate": 5.8666666666666665e-05,
"loss": 1.7698,
"step": 220
},
{
"epoch": 0.09852875613018279,
"grad_norm": 0.3097245395183563,
"learning_rate": 5.893333333333334e-05,
"loss": 1.731,
"step": 221
},
{
"epoch": 0.09897458760588497,
"grad_norm": 0.24703380465507507,
"learning_rate": 5.92e-05,
"loss": 1.8203,
"step": 222
},
{
"epoch": 0.09942041908158716,
"grad_norm": 0.251916766166687,
"learning_rate": 5.946666666666667e-05,
"loss": 1.7469,
"step": 223
},
{
"epoch": 0.09986625055728934,
"grad_norm": 0.2684166133403778,
"learning_rate": 5.973333333333334e-05,
"loss": 1.8091,
"step": 224
},
{
"epoch": 0.10031208203299152,
"grad_norm": 0.2632969319820404,
"learning_rate": 6.000000000000001e-05,
"loss": 1.7271,
"step": 225
},
{
"epoch": 0.10075791350869372,
"grad_norm": 0.2678864002227783,
"learning_rate": 6.026666666666667e-05,
"loss": 1.7441,
"step": 226
},
{
"epoch": 0.1012037449843959,
"grad_norm": 0.2720136046409607,
"learning_rate": 6.053333333333334e-05,
"loss": 1.7874,
"step": 227
},
{
"epoch": 0.10164957646009808,
"grad_norm": 0.3209216892719269,
"learning_rate": 6.080000000000001e-05,
"loss": 1.7705,
"step": 228
},
{
"epoch": 0.10209540793580027,
"grad_norm": 0.3064902126789093,
"learning_rate": 6.106666666666667e-05,
"loss": 1.8002,
"step": 229
},
{
"epoch": 0.10254123941150245,
"grad_norm": 0.31737932562828064,
"learning_rate": 6.133333333333334e-05,
"loss": 1.7382,
"step": 230
},
{
"epoch": 0.10298707088720464,
"grad_norm": 0.3056716322898865,
"learning_rate": 6.16e-05,
"loss": 1.8704,
"step": 231
},
{
"epoch": 0.10343290236290682,
"grad_norm": 0.29310256242752075,
"learning_rate": 6.186666666666668e-05,
"loss": 1.8472,
"step": 232
},
{
"epoch": 0.103878733838609,
"grad_norm": 0.2623426914215088,
"learning_rate": 6.213333333333333e-05,
"loss": 1.8431,
"step": 233
},
{
"epoch": 0.1043245653143112,
"grad_norm": 0.35625219345092773,
"learning_rate": 6.240000000000001e-05,
"loss": 1.8601,
"step": 234
},
{
"epoch": 0.10477039679001338,
"grad_norm": 0.2834986746311188,
"learning_rate": 6.266666666666667e-05,
"loss": 1.8366,
"step": 235
},
{
"epoch": 0.10521622826571556,
"grad_norm": 0.2918021082878113,
"learning_rate": 6.293333333333334e-05,
"loss": 1.828,
"step": 236
},
{
"epoch": 0.10566205974141775,
"grad_norm": 0.23207345604896545,
"learning_rate": 6.32e-05,
"loss": 1.6808,
"step": 237
},
{
"epoch": 0.10610789121711993,
"grad_norm": 0.28747454285621643,
"learning_rate": 6.346666666666667e-05,
"loss": 1.8516,
"step": 238
},
{
"epoch": 0.10655372269282211,
"grad_norm": 0.2337469756603241,
"learning_rate": 6.373333333333334e-05,
"loss": 1.7969,
"step": 239
},
{
"epoch": 0.1069995541685243,
"grad_norm": 0.2963745892047882,
"learning_rate": 6.400000000000001e-05,
"loss": 1.7612,
"step": 240
},
{
"epoch": 0.10744538564422648,
"grad_norm": 0.2667463719844818,
"learning_rate": 6.426666666666668e-05,
"loss": 1.6857,
"step": 241
},
{
"epoch": 0.10789121711992866,
"grad_norm": 0.27753686904907227,
"learning_rate": 6.453333333333333e-05,
"loss": 1.8426,
"step": 242
},
{
"epoch": 0.10833704859563086,
"grad_norm": 0.23864240944385529,
"learning_rate": 6.48e-05,
"loss": 1.7344,
"step": 243
},
{
"epoch": 0.10878288007133304,
"grad_norm": 0.28611189126968384,
"learning_rate": 6.506666666666667e-05,
"loss": 1.8943,
"step": 244
},
{
"epoch": 0.10922871154703521,
"grad_norm": 0.26439395546913147,
"learning_rate": 6.533333333333334e-05,
"loss": 1.853,
"step": 245
},
{
"epoch": 0.10967454302273741,
"grad_norm": 0.24167154729366302,
"learning_rate": 6.56e-05,
"loss": 1.7802,
"step": 246
},
{
"epoch": 0.11012037449843959,
"grad_norm": 0.2444562166929245,
"learning_rate": 6.586666666666668e-05,
"loss": 1.7193,
"step": 247
},
{
"epoch": 0.11056620597414177,
"grad_norm": 0.298610657453537,
"learning_rate": 6.613333333333333e-05,
"loss": 1.784,
"step": 248
},
{
"epoch": 0.11101203744984396,
"grad_norm": 0.23441357910633087,
"learning_rate": 6.64e-05,
"loss": 1.7624,
"step": 249
},
{
"epoch": 0.11145786892554614,
"grad_norm": 0.2940090000629425,
"learning_rate": 6.666666666666667e-05,
"loss": 1.8419,
"step": 250
},
{
"epoch": 0.11190370040124833,
"grad_norm": 0.2812560200691223,
"learning_rate": 6.693333333333334e-05,
"loss": 1.8512,
"step": 251
},
{
"epoch": 0.11234953187695051,
"grad_norm": 0.24187949299812317,
"learning_rate": 6.720000000000001e-05,
"loss": 1.7801,
"step": 252
},
{
"epoch": 0.1127953633526527,
"grad_norm": 0.2625133693218231,
"learning_rate": 6.746666666666668e-05,
"loss": 1.8104,
"step": 253
},
{
"epoch": 0.11324119482835489,
"grad_norm": 0.22561997175216675,
"learning_rate": 6.773333333333334e-05,
"loss": 1.809,
"step": 254
},
{
"epoch": 0.11368702630405707,
"grad_norm": 0.2781251072883606,
"learning_rate": 6.8e-05,
"loss": 1.81,
"step": 255
},
{
"epoch": 0.11413285777975925,
"grad_norm": 0.28370434045791626,
"learning_rate": 6.826666666666668e-05,
"loss": 1.7855,
"step": 256
},
{
"epoch": 0.11457868925546144,
"grad_norm": 0.2266968935728073,
"learning_rate": 6.853333333333334e-05,
"loss": 1.7562,
"step": 257
},
{
"epoch": 0.11502452073116362,
"grad_norm": 0.2713560163974762,
"learning_rate": 6.88e-05,
"loss": 1.7536,
"step": 258
},
{
"epoch": 0.1154703522068658,
"grad_norm": 0.24759072065353394,
"learning_rate": 6.906666666666667e-05,
"loss": 1.8368,
"step": 259
},
{
"epoch": 0.115916183682568,
"grad_norm": 0.24621137976646423,
"learning_rate": 6.933333333333334e-05,
"loss": 1.6647,
"step": 260
},
{
"epoch": 0.11636201515827017,
"grad_norm": 0.24362999200820923,
"learning_rate": 6.960000000000001e-05,
"loss": 1.7761,
"step": 261
},
{
"epoch": 0.11680784663397235,
"grad_norm": 0.2415657788515091,
"learning_rate": 6.986666666666667e-05,
"loss": 1.8489,
"step": 262
},
{
"epoch": 0.11725367810967455,
"grad_norm": 0.22340714931488037,
"learning_rate": 7.013333333333335e-05,
"loss": 1.7276,
"step": 263
},
{
"epoch": 0.11769950958537673,
"grad_norm": 0.24080178141593933,
"learning_rate": 7.04e-05,
"loss": 1.7753,
"step": 264
},
{
"epoch": 0.1181453410610789,
"grad_norm": 0.22115445137023926,
"learning_rate": 7.066666666666667e-05,
"loss": 1.7597,
"step": 265
},
{
"epoch": 0.1185911725367811,
"grad_norm": 0.22792184352874756,
"learning_rate": 7.093333333333334e-05,
"loss": 1.7139,
"step": 266
},
{
"epoch": 0.11903700401248328,
"grad_norm": 0.2419521063566208,
"learning_rate": 7.120000000000001e-05,
"loss": 1.7849,
"step": 267
},
{
"epoch": 0.11948283548818546,
"grad_norm": 0.24347807466983795,
"learning_rate": 7.146666666666666e-05,
"loss": 1.7569,
"step": 268
},
{
"epoch": 0.11992866696388765,
"grad_norm": 0.24143561720848083,
"learning_rate": 7.173333333333333e-05,
"loss": 1.8188,
"step": 269
},
{
"epoch": 0.12037449843958983,
"grad_norm": 0.30590054392814636,
"learning_rate": 7.2e-05,
"loss": 1.8558,
"step": 270
},
{
"epoch": 0.12082032991529201,
"grad_norm": 0.2658385634422302,
"learning_rate": 7.226666666666667e-05,
"loss": 1.8763,
"step": 271
},
{
"epoch": 0.1212661613909942,
"grad_norm": 0.24798420071601868,
"learning_rate": 7.253333333333334e-05,
"loss": 1.8042,
"step": 272
},
{
"epoch": 0.12171199286669639,
"grad_norm": 0.28150761127471924,
"learning_rate": 7.280000000000001e-05,
"loss": 1.8033,
"step": 273
},
{
"epoch": 0.12215782434239858,
"grad_norm": 0.2389529049396515,
"learning_rate": 7.306666666666668e-05,
"loss": 1.8046,
"step": 274
},
{
"epoch": 0.12260365581810076,
"grad_norm": 0.24898123741149902,
"learning_rate": 7.333333333333333e-05,
"loss": 1.7515,
"step": 275
},
{
"epoch": 0.12304948729380294,
"grad_norm": 0.24504360556602478,
"learning_rate": 7.360000000000001e-05,
"loss": 1.7288,
"step": 276
},
{
"epoch": 0.12349531876950513,
"grad_norm": 0.3016360104084015,
"learning_rate": 7.386666666666667e-05,
"loss": 1.9285,
"step": 277
},
{
"epoch": 0.12394115024520731,
"grad_norm": 0.23023012280464172,
"learning_rate": 7.413333333333334e-05,
"loss": 1.7739,
"step": 278
},
{
"epoch": 0.12438698172090949,
"grad_norm": 0.26158833503723145,
"learning_rate": 7.44e-05,
"loss": 1.751,
"step": 279
},
{
"epoch": 0.12483281319661169,
"grad_norm": 0.2571043372154236,
"learning_rate": 7.466666666666667e-05,
"loss": 1.8096,
"step": 280
},
{
"epoch": 0.12527864467231387,
"grad_norm": 0.2688402831554413,
"learning_rate": 7.493333333333334e-05,
"loss": 1.9102,
"step": 281
},
{
"epoch": 0.12572447614801605,
"grad_norm": 0.23819898068904877,
"learning_rate": 7.52e-05,
"loss": 1.7089,
"step": 282
},
{
"epoch": 0.12617030762371823,
"grad_norm": 0.2830815315246582,
"learning_rate": 7.546666666666668e-05,
"loss": 1.7647,
"step": 283
},
{
"epoch": 0.12661613909942043,
"grad_norm": 0.23446160554885864,
"learning_rate": 7.573333333333334e-05,
"loss": 1.7359,
"step": 284
},
{
"epoch": 0.1270619705751226,
"grad_norm": 0.2588684856891632,
"learning_rate": 7.6e-05,
"loss": 1.7247,
"step": 285
},
{
"epoch": 0.1275078020508248,
"grad_norm": 0.2301066815853119,
"learning_rate": 7.626666666666667e-05,
"loss": 1.8099,
"step": 286
},
{
"epoch": 0.12795363352652697,
"grad_norm": 0.2484956830739975,
"learning_rate": 7.653333333333334e-05,
"loss": 1.7122,
"step": 287
},
{
"epoch": 0.12839946500222915,
"grad_norm": 0.22871418297290802,
"learning_rate": 7.680000000000001e-05,
"loss": 1.7922,
"step": 288
},
{
"epoch": 0.12884529647793133,
"grad_norm": 0.23120200634002686,
"learning_rate": 7.706666666666668e-05,
"loss": 1.7302,
"step": 289
},
{
"epoch": 0.12929112795363354,
"grad_norm": 0.24377760291099548,
"learning_rate": 7.733333333333333e-05,
"loss": 1.7644,
"step": 290
},
{
"epoch": 0.12973695942933572,
"grad_norm": 0.27873891592025757,
"learning_rate": 7.76e-05,
"loss": 1.7708,
"step": 291
},
{
"epoch": 0.1301827909050379,
"grad_norm": 0.23908622562885284,
"learning_rate": 7.786666666666667e-05,
"loss": 1.8235,
"step": 292
},
{
"epoch": 0.13062862238074008,
"grad_norm": 0.2732592821121216,
"learning_rate": 7.813333333333334e-05,
"loss": 1.7909,
"step": 293
},
{
"epoch": 0.13107445385644226,
"grad_norm": 0.2262636423110962,
"learning_rate": 7.840000000000001e-05,
"loss": 1.7058,
"step": 294
},
{
"epoch": 0.13152028533214444,
"grad_norm": 0.251850962638855,
"learning_rate": 7.866666666666666e-05,
"loss": 1.813,
"step": 295
},
{
"epoch": 0.13196611680784665,
"grad_norm": 0.2817717492580414,
"learning_rate": 7.893333333333335e-05,
"loss": 1.8096,
"step": 296
},
{
"epoch": 0.13241194828354882,
"grad_norm": 0.2282685786485672,
"learning_rate": 7.92e-05,
"loss": 1.6759,
"step": 297
},
{
"epoch": 0.132857779759251,
"grad_norm": 0.2728259265422821,
"learning_rate": 7.946666666666667e-05,
"loss": 1.7838,
"step": 298
},
{
"epoch": 0.13330361123495318,
"grad_norm": 0.27094462513923645,
"learning_rate": 7.973333333333334e-05,
"loss": 1.7412,
"step": 299
},
{
"epoch": 0.13374944271065536,
"grad_norm": 0.24353022873401642,
"learning_rate": 8e-05,
"loss": 1.7562,
"step": 300
},
{
"epoch": 0.13419527418635754,
"grad_norm": 0.26686304807662964,
"learning_rate": 7.999994771416534e-05,
"loss": 1.8088,
"step": 301
},
{
"epoch": 0.13464110566205975,
"grad_norm": 0.23156635463237762,
"learning_rate": 7.999979085679805e-05,
"loss": 1.6609,
"step": 302
},
{
"epoch": 0.13508693713776193,
"grad_norm": 0.21843333542346954,
"learning_rate": 7.99995294283082e-05,
"loss": 1.7144,
"step": 303
},
{
"epoch": 0.1355327686134641,
"grad_norm": 0.23980362713336945,
"learning_rate": 7.999916342937923e-05,
"loss": 1.7998,
"step": 304
},
{
"epoch": 0.1359786000891663,
"grad_norm": 0.23711195588111877,
"learning_rate": 7.999869286096798e-05,
"loss": 1.8144,
"step": 305
},
{
"epoch": 0.13642443156486847,
"grad_norm": 0.2704579830169678,
"learning_rate": 7.999811772430466e-05,
"loss": 1.7427,
"step": 306
},
{
"epoch": 0.13687026304057068,
"grad_norm": 0.23453868925571442,
"learning_rate": 7.999743802089283e-05,
"loss": 1.6939,
"step": 307
},
{
"epoch": 0.13731609451627286,
"grad_norm": 0.21298548579216003,
"learning_rate": 7.999665375250944e-05,
"loss": 1.7517,
"step": 308
},
{
"epoch": 0.13776192599197504,
"grad_norm": 0.28733065724372864,
"learning_rate": 7.99957649212048e-05,
"loss": 1.7647,
"step": 309
},
{
"epoch": 0.13820775746767722,
"grad_norm": 0.2919608950614929,
"learning_rate": 7.999477152930256e-05,
"loss": 1.7727,
"step": 310
},
{
"epoch": 0.1386535889433794,
"grad_norm": 0.28628838062286377,
"learning_rate": 7.999367357939974e-05,
"loss": 1.8061,
"step": 311
},
{
"epoch": 0.13909942041908158,
"grad_norm": 0.2606216371059418,
"learning_rate": 7.999247107436672e-05,
"loss": 1.7097,
"step": 312
},
{
"epoch": 0.13954525189478378,
"grad_norm": 0.22490161657333374,
"learning_rate": 7.999116401734718e-05,
"loss": 1.7861,
"step": 313
},
{
"epoch": 0.13999108337048596,
"grad_norm": 0.287057489156723,
"learning_rate": 7.998975241175815e-05,
"loss": 1.7041,
"step": 314
},
{
"epoch": 0.14043691484618814,
"grad_norm": 0.22429852187633514,
"learning_rate": 7.998823626129e-05,
"loss": 1.7224,
"step": 315
},
{
"epoch": 0.14088274632189032,
"grad_norm": 0.23749588429927826,
"learning_rate": 7.998661556990636e-05,
"loss": 1.7259,
"step": 316
},
{
"epoch": 0.1413285777975925,
"grad_norm": 0.2275572419166565,
"learning_rate": 7.99848903418442e-05,
"loss": 1.7777,
"step": 317
},
{
"epoch": 0.14177440927329468,
"grad_norm": 0.21902650594711304,
"learning_rate": 7.998306058161378e-05,
"loss": 1.7444,
"step": 318
},
{
"epoch": 0.1422202407489969,
"grad_norm": 0.2763417959213257,
"learning_rate": 7.998112629399861e-05,
"loss": 1.8482,
"step": 319
},
{
"epoch": 0.14266607222469907,
"grad_norm": 0.2526148557662964,
"learning_rate": 7.99790874840555e-05,
"loss": 1.8765,
"step": 320
},
{
"epoch": 0.14311190370040125,
"grad_norm": 0.22051188349723816,
"learning_rate": 7.997694415711448e-05,
"loss": 1.7598,
"step": 321
},
{
"epoch": 0.14355773517610343,
"grad_norm": 0.23414510488510132,
"learning_rate": 7.997469631877883e-05,
"loss": 1.701,
"step": 322
},
{
"epoch": 0.1440035666518056,
"grad_norm": 0.22807630896568298,
"learning_rate": 7.997234397492508e-05,
"loss": 1.8516,
"step": 323
},
{
"epoch": 0.1444493981275078,
"grad_norm": 0.2263704240322113,
"learning_rate": 7.996988713170292e-05,
"loss": 1.7997,
"step": 324
},
{
"epoch": 0.14489522960321,
"grad_norm": 0.24178504943847656,
"learning_rate": 7.996732579553526e-05,
"loss": 1.7961,
"step": 325
},
{
"epoch": 0.14534106107891218,
"grad_norm": 0.2487363964319229,
"learning_rate": 7.996465997311817e-05,
"loss": 1.7727,
"step": 326
},
{
"epoch": 0.14578689255461436,
"grad_norm": 0.23811641335487366,
"learning_rate": 7.996188967142091e-05,
"loss": 1.8489,
"step": 327
},
{
"epoch": 0.14623272403031654,
"grad_norm": 0.2284778505563736,
"learning_rate": 7.995901489768584e-05,
"loss": 1.7402,
"step": 328
},
{
"epoch": 0.14667855550601872,
"grad_norm": 0.24267128109931946,
"learning_rate": 7.995603565942846e-05,
"loss": 1.6906,
"step": 329
},
{
"epoch": 0.14712438698172092,
"grad_norm": 0.2633998394012451,
"learning_rate": 7.995295196443737e-05,
"loss": 1.8315,
"step": 330
},
{
"epoch": 0.1475702184574231,
"grad_norm": 0.23922331631183624,
"learning_rate": 7.994976382077425e-05,
"loss": 1.7517,
"step": 331
},
{
"epoch": 0.14801604993312528,
"grad_norm": 0.2259657233953476,
"learning_rate": 7.994647123677384e-05,
"loss": 1.7938,
"step": 332
},
{
"epoch": 0.14846188140882746,
"grad_norm": 0.2336091250181198,
"learning_rate": 7.99430742210439e-05,
"loss": 1.7878,
"step": 333
},
{
"epoch": 0.14890771288452964,
"grad_norm": 0.21656788885593414,
"learning_rate": 7.993957278246525e-05,
"loss": 1.7411,
"step": 334
},
{
"epoch": 0.14935354436023182,
"grad_norm": 0.22250677645206451,
"learning_rate": 7.993596693019165e-05,
"loss": 1.8132,
"step": 335
},
{
"epoch": 0.14979937583593403,
"grad_norm": 0.258594274520874,
"learning_rate": 7.993225667364984e-05,
"loss": 1.7314,
"step": 336
},
{
"epoch": 0.1502452073116362,
"grad_norm": 0.2388758510351181,
"learning_rate": 7.992844202253953e-05,
"loss": 1.7738,
"step": 337
},
{
"epoch": 0.1506910387873384,
"grad_norm": 0.26715052127838135,
"learning_rate": 7.992452298683333e-05,
"loss": 1.7666,
"step": 338
},
{
"epoch": 0.15113687026304057,
"grad_norm": 0.22846515476703644,
"learning_rate": 7.992049957677674e-05,
"loss": 1.7664,
"step": 339
},
{
"epoch": 0.15158270173874275,
"grad_norm": 0.23906578123569489,
"learning_rate": 7.991637180288813e-05,
"loss": 1.8869,
"step": 340
},
{
"epoch": 0.15202853321444493,
"grad_norm": 0.24840490520000458,
"learning_rate": 7.99121396759587e-05,
"loss": 1.707,
"step": 341
},
{
"epoch": 0.15247436469014714,
"grad_norm": 0.23409156501293182,
"learning_rate": 7.990780320705246e-05,
"loss": 1.8279,
"step": 342
},
{
"epoch": 0.15292019616584931,
"grad_norm": 0.23515836894512177,
"learning_rate": 7.990336240750621e-05,
"loss": 1.7601,
"step": 343
},
{
"epoch": 0.1533660276415515,
"grad_norm": 0.2411307990550995,
"learning_rate": 7.98988172889295e-05,
"loss": 1.8165,
"step": 344
},
{
"epoch": 0.15381185911725367,
"grad_norm": 0.2911078631877899,
"learning_rate": 7.98941678632046e-05,
"loss": 1.7544,
"step": 345
},
{
"epoch": 0.15425769059295585,
"grad_norm": 0.23404845595359802,
"learning_rate": 7.988941414248645e-05,
"loss": 1.8192,
"step": 346
},
{
"epoch": 0.15470352206865803,
"grad_norm": 0.274189829826355,
"learning_rate": 7.988455613920267e-05,
"loss": 1.8439,
"step": 347
},
{
"epoch": 0.15514935354436024,
"grad_norm": 0.21792374551296234,
"learning_rate": 7.98795938660535e-05,
"loss": 1.8227,
"step": 348
},
{
"epoch": 0.15559518502006242,
"grad_norm": 0.27858689427375793,
"learning_rate": 7.987452733601179e-05,
"loss": 1.77,
"step": 349
},
{
"epoch": 0.1560410164957646,
"grad_norm": 0.22310331463813782,
"learning_rate": 7.986935656232287e-05,
"loss": 1.763,
"step": 350
},
{
"epoch": 0.15648684797146678,
"grad_norm": 0.22564561665058136,
"learning_rate": 7.98640815585047e-05,
"loss": 1.7049,
"step": 351
},
{
"epoch": 0.15693267944716896,
"grad_norm": 0.2216060310602188,
"learning_rate": 7.985870233834767e-05,
"loss": 1.7523,
"step": 352
},
{
"epoch": 0.15737851092287117,
"grad_norm": 0.23628509044647217,
"learning_rate": 7.985321891591463e-05,
"loss": 1.7974,
"step": 353
},
{
"epoch": 0.15782434239857335,
"grad_norm": 0.21217618882656097,
"learning_rate": 7.984763130554084e-05,
"loss": 1.7335,
"step": 354
},
{
"epoch": 0.15827017387427553,
"grad_norm": 0.2183927595615387,
"learning_rate": 7.984193952183394e-05,
"loss": 1.822,
"step": 355
},
{
"epoch": 0.1587160053499777,
"grad_norm": 0.22199095785617828,
"learning_rate": 7.983614357967392e-05,
"loss": 1.7597,
"step": 356
},
{
"epoch": 0.1591618368256799,
"grad_norm": 0.20965681970119476,
"learning_rate": 7.983024349421307e-05,
"loss": 1.7823,
"step": 357
},
{
"epoch": 0.15960766830138207,
"grad_norm": 0.21876397728919983,
"learning_rate": 7.982423928087593e-05,
"loss": 1.8127,
"step": 358
},
{
"epoch": 0.16005349977708427,
"grad_norm": 0.21204975247383118,
"learning_rate": 7.981813095535926e-05,
"loss": 1.69,
"step": 359
},
{
"epoch": 0.16049933125278645,
"grad_norm": 0.2185240387916565,
"learning_rate": 7.981191853363201e-05,
"loss": 1.8001,
"step": 360
},
{
"epoch": 0.16094516272848863,
"grad_norm": 0.23309868574142456,
"learning_rate": 7.980560203193525e-05,
"loss": 1.7638,
"step": 361
},
{
"epoch": 0.1613909942041908,
"grad_norm": 0.21918439865112305,
"learning_rate": 7.979918146678218e-05,
"loss": 1.7739,
"step": 362
},
{
"epoch": 0.161836825679893,
"grad_norm": 0.2592524588108063,
"learning_rate": 7.979265685495801e-05,
"loss": 1.7639,
"step": 363
},
{
"epoch": 0.16228265715559517,
"grad_norm": 0.21176396310329437,
"learning_rate": 7.978602821351999e-05,
"loss": 1.7888,
"step": 364
},
{
"epoch": 0.16272848863129738,
"grad_norm": 0.22291821241378784,
"learning_rate": 7.977929555979732e-05,
"loss": 1.6619,
"step": 365
},
{
"epoch": 0.16317432010699956,
"grad_norm": 0.21604986488819122,
"learning_rate": 7.977245891139113e-05,
"loss": 1.7488,
"step": 366
},
{
"epoch": 0.16362015158270174,
"grad_norm": 0.22686690092086792,
"learning_rate": 7.976551828617439e-05,
"loss": 1.8615,
"step": 367
},
{
"epoch": 0.16406598305840392,
"grad_norm": 0.2151118963956833,
"learning_rate": 7.975847370229194e-05,
"loss": 1.79,
"step": 368
},
{
"epoch": 0.1645118145341061,
"grad_norm": 0.21530570089817047,
"learning_rate": 7.975132517816038e-05,
"loss": 1.7706,
"step": 369
},
{
"epoch": 0.16495764600980828,
"grad_norm": 0.21484266221523285,
"learning_rate": 7.974407273246801e-05,
"loss": 1.8433,
"step": 370
},
{
"epoch": 0.1654034774855105,
"grad_norm": 0.2247444987297058,
"learning_rate": 7.973671638417488e-05,
"loss": 1.8342,
"step": 371
},
{
"epoch": 0.16584930896121267,
"grad_norm": 0.21698202192783356,
"learning_rate": 7.97292561525126e-05,
"loss": 1.7795,
"step": 372
},
{
"epoch": 0.16629514043691485,
"grad_norm": 0.21239005029201508,
"learning_rate": 7.97216920569844e-05,
"loss": 1.7897,
"step": 373
},
{
"epoch": 0.16674097191261703,
"grad_norm": 0.2313557267189026,
"learning_rate": 7.971402411736502e-05,
"loss": 1.7493,
"step": 374
},
{
"epoch": 0.1671868033883192,
"grad_norm": 0.2117127925157547,
"learning_rate": 7.97062523537007e-05,
"loss": 1.7789,
"step": 375
},
{
"epoch": 0.1676326348640214,
"grad_norm": 0.21416178345680237,
"learning_rate": 7.969837678630912e-05,
"loss": 1.7463,
"step": 376
},
{
"epoch": 0.1680784663397236,
"grad_norm": 0.2061980962753296,
"learning_rate": 7.969039743577929e-05,
"loss": 1.6982,
"step": 377
},
{
"epoch": 0.16852429781542577,
"grad_norm": 0.21651746332645416,
"learning_rate": 7.968231432297157e-05,
"loss": 1.7723,
"step": 378
},
{
"epoch": 0.16897012929112795,
"grad_norm": 0.24461179971694946,
"learning_rate": 7.967412746901754e-05,
"loss": 1.8304,
"step": 379
},
{
"epoch": 0.16941596076683013,
"grad_norm": 0.2126745879650116,
"learning_rate": 7.966583689532007e-05,
"loss": 1.7447,
"step": 380
},
{
"epoch": 0.1698617922425323,
"grad_norm": 0.24304448068141937,
"learning_rate": 7.965744262355313e-05,
"loss": 1.7735,
"step": 381
},
{
"epoch": 0.17030762371823452,
"grad_norm": 0.22968406975269318,
"learning_rate": 7.964894467566177e-05,
"loss": 1.7358,
"step": 382
},
{
"epoch": 0.1707534551939367,
"grad_norm": 0.20871512591838837,
"learning_rate": 7.964034307386211e-05,
"loss": 1.7411,
"step": 383
},
{
"epoch": 0.17119928666963888,
"grad_norm": 0.21672800183296204,
"learning_rate": 7.963163784064128e-05,
"loss": 1.6548,
"step": 384
},
{
"epoch": 0.17164511814534106,
"grad_norm": 0.20464417338371277,
"learning_rate": 7.962282899875727e-05,
"loss": 1.7081,
"step": 385
},
{
"epoch": 0.17209094962104324,
"grad_norm": 0.2229240983724594,
"learning_rate": 7.961391657123896e-05,
"loss": 1.7655,
"step": 386
},
{
"epoch": 0.17253678109674542,
"grad_norm": 0.21150527894496918,
"learning_rate": 7.960490058138604e-05,
"loss": 1.7853,
"step": 387
},
{
"epoch": 0.17298261257244762,
"grad_norm": 0.21915920078754425,
"learning_rate": 7.959578105276896e-05,
"loss": 1.7652,
"step": 388
},
{
"epoch": 0.1734284440481498,
"grad_norm": 0.24295909702777863,
"learning_rate": 7.95865580092288e-05,
"loss": 1.8354,
"step": 389
},
{
"epoch": 0.17387427552385198,
"grad_norm": 0.20863685011863708,
"learning_rate": 7.957723147487728e-05,
"loss": 1.7122,
"step": 390
},
{
"epoch": 0.17432010699955416,
"grad_norm": 0.2294648438692093,
"learning_rate": 7.956780147409672e-05,
"loss": 1.7097,
"step": 391
},
{
"epoch": 0.17476593847525634,
"grad_norm": 0.21071994304656982,
"learning_rate": 7.955826803153986e-05,
"loss": 1.8451,
"step": 392
},
{
"epoch": 0.17521176995095855,
"grad_norm": 0.2508149743080139,
"learning_rate": 7.954863117212992e-05,
"loss": 1.8128,
"step": 393
},
{
"epoch": 0.17565760142666073,
"grad_norm": 0.21691708266735077,
"learning_rate": 7.953889092106045e-05,
"loss": 1.718,
"step": 394
},
{
"epoch": 0.1761034329023629,
"grad_norm": 0.2262207269668579,
"learning_rate": 7.952904730379531e-05,
"loss": 1.7128,
"step": 395
},
{
"epoch": 0.1765492643780651,
"grad_norm": 0.24705760180950165,
"learning_rate": 7.951910034606858e-05,
"loss": 1.7341,
"step": 396
},
{
"epoch": 0.17699509585376727,
"grad_norm": 0.2729456126689911,
"learning_rate": 7.950905007388453e-05,
"loss": 1.7499,
"step": 397
},
{
"epoch": 0.17744092732946945,
"grad_norm": 0.21897609531879425,
"learning_rate": 7.949889651351749e-05,
"loss": 1.765,
"step": 398
},
{
"epoch": 0.17788675880517166,
"grad_norm": 0.289559006690979,
"learning_rate": 7.948863969151182e-05,
"loss": 1.7466,
"step": 399
},
{
"epoch": 0.17833259028087384,
"grad_norm": 0.20668886601924896,
"learning_rate": 7.947827963468187e-05,
"loss": 1.817,
"step": 400
},
{
"epoch": 0.17877842175657602,
"grad_norm": 0.26898351311683655,
"learning_rate": 7.946781637011181e-05,
"loss": 1.8633,
"step": 401
},
{
"epoch": 0.1792242532322782,
"grad_norm": 0.21890974044799805,
"learning_rate": 7.945724992515573e-05,
"loss": 1.7948,
"step": 402
},
{
"epoch": 0.17967008470798038,
"grad_norm": 0.220897376537323,
"learning_rate": 7.944658032743733e-05,
"loss": 1.7348,
"step": 403
},
{
"epoch": 0.18011591618368256,
"grad_norm": 0.22162188589572906,
"learning_rate": 7.94358076048501e-05,
"loss": 1.7777,
"step": 404
},
{
"epoch": 0.18056174765938476,
"grad_norm": 0.23272553086280823,
"learning_rate": 7.942493178555705e-05,
"loss": 1.8239,
"step": 405
},
{
"epoch": 0.18100757913508694,
"grad_norm": 0.2248050570487976,
"learning_rate": 7.941395289799076e-05,
"loss": 1.7756,
"step": 406
},
{
"epoch": 0.18145341061078912,
"grad_norm": 0.22719000279903412,
"learning_rate": 7.940287097085324e-05,
"loss": 1.6338,
"step": 407
},
{
"epoch": 0.1818992420864913,
"grad_norm": 0.21583989262580872,
"learning_rate": 7.939168603311591e-05,
"loss": 1.7401,
"step": 408
},
{
"epoch": 0.18234507356219348,
"grad_norm": 0.21622613072395325,
"learning_rate": 7.93803981140194e-05,
"loss": 1.7647,
"step": 409
},
{
"epoch": 0.18279090503789566,
"grad_norm": 0.22838523983955383,
"learning_rate": 7.936900724307366e-05,
"loss": 1.8249,
"step": 410
},
{
"epoch": 0.18323673651359787,
"grad_norm": 0.2663255035877228,
"learning_rate": 7.935751345005776e-05,
"loss": 1.8474,
"step": 411
},
{
"epoch": 0.18368256798930005,
"grad_norm": 0.20833280682563782,
"learning_rate": 7.93459167650198e-05,
"loss": 1.7485,
"step": 412
},
{
"epoch": 0.18412839946500223,
"grad_norm": 0.2584652006626129,
"learning_rate": 7.933421721827692e-05,
"loss": 1.7936,
"step": 413
},
{
"epoch": 0.1845742309407044,
"grad_norm": 0.21740388870239258,
"learning_rate": 7.932241484041512e-05,
"loss": 1.7765,
"step": 414
},
{
"epoch": 0.1850200624164066,
"grad_norm": 0.2323867678642273,
"learning_rate": 7.931050966228931e-05,
"loss": 1.7967,
"step": 415
},
{
"epoch": 0.1854658938921088,
"grad_norm": 0.21234050393104553,
"learning_rate": 7.929850171502304e-05,
"loss": 1.7576,
"step": 416
},
{
"epoch": 0.18591172536781098,
"grad_norm": 0.24422520399093628,
"learning_rate": 7.928639103000864e-05,
"loss": 1.7178,
"step": 417
},
{
"epoch": 0.18635755684351316,
"grad_norm": 0.20524504780769348,
"learning_rate": 7.927417763890693e-05,
"loss": 1.6605,
"step": 418
},
{
"epoch": 0.18680338831921534,
"grad_norm": 0.2728728652000427,
"learning_rate": 7.926186157364732e-05,
"loss": 1.7642,
"step": 419
},
{
"epoch": 0.18724921979491752,
"grad_norm": 0.2353711575269699,
"learning_rate": 7.924944286642754e-05,
"loss": 1.6901,
"step": 420
},
{
"epoch": 0.1876950512706197,
"grad_norm": 0.22307051718235016,
"learning_rate": 7.923692154971378e-05,
"loss": 1.7768,
"step": 421
},
{
"epoch": 0.1881408827463219,
"grad_norm": 0.20437411963939667,
"learning_rate": 7.922429765624037e-05,
"loss": 1.6671,
"step": 422
},
{
"epoch": 0.18858671422202408,
"grad_norm": 0.22397580742835999,
"learning_rate": 7.921157121900985e-05,
"loss": 1.8473,
"step": 423
},
{
"epoch": 0.18903254569772626,
"grad_norm": 0.27350035309791565,
"learning_rate": 7.919874227129286e-05,
"loss": 1.7446,
"step": 424
},
{
"epoch": 0.18947837717342844,
"grad_norm": 0.21913419663906097,
"learning_rate": 7.918581084662801e-05,
"loss": 1.8032,
"step": 425
},
{
"epoch": 0.18992420864913062,
"grad_norm": 0.2502184808254242,
"learning_rate": 7.917277697882181e-05,
"loss": 1.6962,
"step": 426
},
{
"epoch": 0.1903700401248328,
"grad_norm": 0.20700030028820038,
"learning_rate": 7.915964070194859e-05,
"loss": 1.7662,
"step": 427
},
{
"epoch": 0.190815871600535,
"grad_norm": 0.24439390003681183,
"learning_rate": 7.91464020503504e-05,
"loss": 1.7713,
"step": 428
},
{
"epoch": 0.1912617030762372,
"grad_norm": 0.2158062756061554,
"learning_rate": 7.913306105863698e-05,
"loss": 1.7541,
"step": 429
},
{
"epoch": 0.19170753455193937,
"grad_norm": 0.20007923245429993,
"learning_rate": 7.911961776168551e-05,
"loss": 1.7032,
"step": 430
},
{
"epoch": 0.19215336602764155,
"grad_norm": 0.219706729054451,
"learning_rate": 7.910607219464075e-05,
"loss": 1.8321,
"step": 431
},
{
"epoch": 0.19259919750334373,
"grad_norm": 0.22007739543914795,
"learning_rate": 7.909242439291474e-05,
"loss": 1.7962,
"step": 432
},
{
"epoch": 0.1930450289790459,
"grad_norm": 0.20321106910705566,
"learning_rate": 7.90786743921868e-05,
"loss": 1.6555,
"step": 433
},
{
"epoch": 0.19349086045474811,
"grad_norm": 0.22101330757141113,
"learning_rate": 7.906482222840347e-05,
"loss": 1.816,
"step": 434
},
{
"epoch": 0.1939366919304503,
"grad_norm": 0.21452194452285767,
"learning_rate": 7.905086793777834e-05,
"loss": 1.7222,
"step": 435
},
{
"epoch": 0.19438252340615247,
"grad_norm": 0.20491483807563782,
"learning_rate": 7.903681155679198e-05,
"loss": 1.779,
"step": 436
},
{
"epoch": 0.19482835488185465,
"grad_norm": 0.2175835222005844,
"learning_rate": 7.902265312219188e-05,
"loss": 1.7517,
"step": 437
},
{
"epoch": 0.19527418635755683,
"grad_norm": 0.2133513242006302,
"learning_rate": 7.900839267099233e-05,
"loss": 1.7672,
"step": 438
},
{
"epoch": 0.19572001783325904,
"grad_norm": 0.21768039464950562,
"learning_rate": 7.899403024047429e-05,
"loss": 1.7668,
"step": 439
},
{
"epoch": 0.19616584930896122,
"grad_norm": 0.19812998175621033,
"learning_rate": 7.897956586818536e-05,
"loss": 1.6268,
"step": 440
},
{
"epoch": 0.1966116807846634,
"grad_norm": 0.20877686142921448,
"learning_rate": 7.896499959193963e-05,
"loss": 1.7064,
"step": 441
},
{
"epoch": 0.19705751226036558,
"grad_norm": 0.2183704674243927,
"learning_rate": 7.895033144981759e-05,
"loss": 1.7475,
"step": 442
},
{
"epoch": 0.19750334373606776,
"grad_norm": 0.20506885647773743,
"learning_rate": 7.893556148016602e-05,
"loss": 1.7189,
"step": 443
},
{
"epoch": 0.19794917521176994,
"grad_norm": 0.20721159875392914,
"learning_rate": 7.892068972159797e-05,
"loss": 1.7609,
"step": 444
},
{
"epoch": 0.19839500668747215,
"grad_norm": 0.21451415121555328,
"learning_rate": 7.890571621299252e-05,
"loss": 1.8069,
"step": 445
},
{
"epoch": 0.19884083816317433,
"grad_norm": 0.2216353714466095,
"learning_rate": 7.889064099349483e-05,
"loss": 1.8198,
"step": 446
},
{
"epoch": 0.1992866696388765,
"grad_norm": 0.2052127569913864,
"learning_rate": 7.887546410251588e-05,
"loss": 1.7137,
"step": 447
},
{
"epoch": 0.1997325011145787,
"grad_norm": 0.202201709151268,
"learning_rate": 7.88601855797325e-05,
"loss": 1.7105,
"step": 448
},
{
"epoch": 0.20017833259028087,
"grad_norm": 0.23586085438728333,
"learning_rate": 7.884480546508724e-05,
"loss": 1.7372,
"step": 449
},
{
"epoch": 0.20062416406598305,
"grad_norm": 0.21336017549037933,
"learning_rate": 7.882932379878816e-05,
"loss": 1.7355,
"step": 450
},
{
"epoch": 0.20106999554168525,
"grad_norm": 0.19796158373355865,
"learning_rate": 7.881374062130888e-05,
"loss": 1.5849,
"step": 451
},
{
"epoch": 0.20151582701738743,
"grad_norm": 0.21551991999149323,
"learning_rate": 7.879805597338836e-05,
"loss": 1.7133,
"step": 452
},
{
"epoch": 0.2019616584930896,
"grad_norm": 0.21652403473854065,
"learning_rate": 7.878226989603085e-05,
"loss": 1.712,
"step": 453
},
{
"epoch": 0.2024074899687918,
"grad_norm": 0.23366712033748627,
"learning_rate": 7.876638243050577e-05,
"loss": 1.8546,
"step": 454
},
{
"epoch": 0.20285332144449397,
"grad_norm": 0.2219308465719223,
"learning_rate": 7.875039361834758e-05,
"loss": 1.7547,
"step": 455
},
{
"epoch": 0.20329915292019615,
"grad_norm": 0.22077837586402893,
"learning_rate": 7.873430350135569e-05,
"loss": 1.6704,
"step": 456
},
{
"epoch": 0.20374498439589836,
"grad_norm": 0.21282720565795898,
"learning_rate": 7.871811212159439e-05,
"loss": 1.7612,
"step": 457
},
{
"epoch": 0.20419081587160054,
"grad_norm": 0.21781127154827118,
"learning_rate": 7.870181952139263e-05,
"loss": 1.7018,
"step": 458
},
{
"epoch": 0.20463664734730272,
"grad_norm": 0.2093805968761444,
"learning_rate": 7.868542574334404e-05,
"loss": 1.6885,
"step": 459
},
{
"epoch": 0.2050824788230049,
"grad_norm": 0.22918467223644257,
"learning_rate": 7.866893083030675e-05,
"loss": 1.7805,
"step": 460
},
{
"epoch": 0.20552831029870708,
"grad_norm": 0.21219949424266815,
"learning_rate": 7.865233482540328e-05,
"loss": 1.7359,
"step": 461
},
{
"epoch": 0.2059741417744093,
"grad_norm": 0.2140708565711975,
"learning_rate": 7.86356377720204e-05,
"loss": 1.7639,
"step": 462
},
{
"epoch": 0.20641997325011147,
"grad_norm": 0.23221629858016968,
"learning_rate": 7.861883971380908e-05,
"loss": 1.8052,
"step": 463
},
{
"epoch": 0.20686580472581365,
"grad_norm": 0.21740645170211792,
"learning_rate": 7.860194069468437e-05,
"loss": 1.824,
"step": 464
},
{
"epoch": 0.20731163620151583,
"grad_norm": 0.21377727389335632,
"learning_rate": 7.85849407588252e-05,
"loss": 1.7575,
"step": 465
},
{
"epoch": 0.207757467677218,
"grad_norm": 0.2288164347410202,
"learning_rate": 7.856783995067441e-05,
"loss": 1.7964,
"step": 466
},
{
"epoch": 0.20820329915292018,
"grad_norm": 0.21703492105007172,
"learning_rate": 7.855063831493846e-05,
"loss": 1.7686,
"step": 467
},
{
"epoch": 0.2086491306286224,
"grad_norm": 0.20621813833713531,
"learning_rate": 7.853333589658747e-05,
"loss": 1.6916,
"step": 468
},
{
"epoch": 0.20909496210432457,
"grad_norm": 0.20889562368392944,
"learning_rate": 7.851593274085499e-05,
"loss": 1.802,
"step": 469
},
{
"epoch": 0.20954079358002675,
"grad_norm": 0.20696090161800385,
"learning_rate": 7.849842889323796e-05,
"loss": 1.7314,
"step": 470
},
{
"epoch": 0.20998662505572893,
"grad_norm": 0.2312188297510147,
"learning_rate": 7.848082439949654e-05,
"loss": 1.8498,
"step": 471
},
{
"epoch": 0.2104324565314311,
"grad_norm": 0.20535381138324738,
"learning_rate": 7.8463119305654e-05,
"loss": 1.8197,
"step": 472
},
{
"epoch": 0.2108782880071333,
"grad_norm": 0.2188010960817337,
"learning_rate": 7.844531365799666e-05,
"loss": 1.7539,
"step": 473
},
{
"epoch": 0.2113241194828355,
"grad_norm": 0.20804068446159363,
"learning_rate": 7.842740750307362e-05,
"loss": 1.7942,
"step": 474
},
{
"epoch": 0.21176995095853768,
"grad_norm": 0.2164592146873474,
"learning_rate": 7.840940088769683e-05,
"loss": 1.7582,
"step": 475
},
{
"epoch": 0.21221578243423986,
"grad_norm": 0.2279512584209442,
"learning_rate": 7.839129385894082e-05,
"loss": 1.7594,
"step": 476
},
{
"epoch": 0.21266161390994204,
"grad_norm": 0.20543353259563446,
"learning_rate": 7.837308646414267e-05,
"loss": 1.7261,
"step": 477
},
{
"epoch": 0.21310744538564422,
"grad_norm": 0.2820877432823181,
"learning_rate": 7.835477875090179e-05,
"loss": 1.7853,
"step": 478
},
{
"epoch": 0.2135532768613464,
"grad_norm": 0.24093766510486603,
"learning_rate": 7.833637076707991e-05,
"loss": 1.8439,
"step": 479
},
{
"epoch": 0.2139991083370486,
"grad_norm": 0.217599555850029,
"learning_rate": 7.831786256080085e-05,
"loss": 1.7984,
"step": 480
},
{
"epoch": 0.21444493981275078,
"grad_norm": 0.23980188369750977,
"learning_rate": 7.829925418045048e-05,
"loss": 1.7762,
"step": 481
},
{
"epoch": 0.21489077128845296,
"grad_norm": 0.22318458557128906,
"learning_rate": 7.828054567467652e-05,
"loss": 1.7612,
"step": 482
},
{
"epoch": 0.21533660276415514,
"grad_norm": 0.21457462012767792,
"learning_rate": 7.826173709238846e-05,
"loss": 1.7034,
"step": 483
},
{
"epoch": 0.21578243423985732,
"grad_norm": 0.2079022228717804,
"learning_rate": 7.824282848275741e-05,
"loss": 1.8033,
"step": 484
},
{
"epoch": 0.21622826571555953,
"grad_norm": 0.20726555585861206,
"learning_rate": 7.822381989521605e-05,
"loss": 1.7805,
"step": 485
},
{
"epoch": 0.2166740971912617,
"grad_norm": 0.2167215645313263,
"learning_rate": 7.820471137945831e-05,
"loss": 1.8171,
"step": 486
},
{
"epoch": 0.2171199286669639,
"grad_norm": 0.21359805762767792,
"learning_rate": 7.818550298543944e-05,
"loss": 1.7444,
"step": 487
},
{
"epoch": 0.21756576014266607,
"grad_norm": 0.20531319081783295,
"learning_rate": 7.81661947633758e-05,
"loss": 1.7091,
"step": 488
},
{
"epoch": 0.21801159161836825,
"grad_norm": 0.20193392038345337,
"learning_rate": 7.814678676374471e-05,
"loss": 1.7053,
"step": 489
},
{
"epoch": 0.21845742309407043,
"grad_norm": 0.2035619169473648,
"learning_rate": 7.812727903728433e-05,
"loss": 1.696,
"step": 490
},
{
"epoch": 0.21890325456977264,
"grad_norm": 0.20180848240852356,
"learning_rate": 7.810767163499358e-05,
"loss": 1.7959,
"step": 491
},
{
"epoch": 0.21934908604547482,
"grad_norm": 0.21526241302490234,
"learning_rate": 7.80879646081319e-05,
"loss": 1.8276,
"step": 492
},
{
"epoch": 0.219794917521177,
"grad_norm": 0.20258860290050507,
"learning_rate": 7.806815800821922e-05,
"loss": 1.6339,
"step": 493
},
{
"epoch": 0.22024074899687918,
"grad_norm": 0.2058095633983612,
"learning_rate": 7.804825188703575e-05,
"loss": 1.7035,
"step": 494
},
{
"epoch": 0.22068658047258136,
"grad_norm": 0.1978922039270401,
"learning_rate": 7.802824629662192e-05,
"loss": 1.6683,
"step": 495
},
{
"epoch": 0.22113241194828354,
"grad_norm": 0.21317130327224731,
"learning_rate": 7.800814128927819e-05,
"loss": 1.8152,
"step": 496
},
{
"epoch": 0.22157824342398574,
"grad_norm": 0.1988740861415863,
"learning_rate": 7.798793691756488e-05,
"loss": 1.65,
"step": 497
},
{
"epoch": 0.22202407489968792,
"grad_norm": 0.20139382779598236,
"learning_rate": 7.796763323430215e-05,
"loss": 1.6872,
"step": 498
},
{
"epoch": 0.2224699063753901,
"grad_norm": 0.20387861132621765,
"learning_rate": 7.794723029256971e-05,
"loss": 1.7308,
"step": 499
},
{
"epoch": 0.22291573785109228,
"grad_norm": 0.204574853181839,
"learning_rate": 7.792672814570683e-05,
"loss": 1.7583,
"step": 500
},
{
"epoch": 0.22336156932679446,
"grad_norm": 0.2186586558818817,
"learning_rate": 7.790612684731211e-05,
"loss": 1.8411,
"step": 501
},
{
"epoch": 0.22380740080249667,
"grad_norm": 0.22103360295295715,
"learning_rate": 7.788542645124333e-05,
"loss": 1.8295,
"step": 502
},
{
"epoch": 0.22425323227819885,
"grad_norm": 0.2011125087738037,
"learning_rate": 7.786462701161738e-05,
"loss": 1.7213,
"step": 503
},
{
"epoch": 0.22469906375390103,
"grad_norm": 0.21138082444667816,
"learning_rate": 7.784372858281006e-05,
"loss": 1.7867,
"step": 504
},
{
"epoch": 0.2251448952296032,
"grad_norm": 0.20400221645832062,
"learning_rate": 7.782273121945594e-05,
"loss": 1.7661,
"step": 505
},
{
"epoch": 0.2255907267053054,
"grad_norm": 0.19883286952972412,
"learning_rate": 7.780163497644829e-05,
"loss": 1.7831,
"step": 506
},
{
"epoch": 0.22603655818100757,
"grad_norm": 0.20815902948379517,
"learning_rate": 7.778043990893882e-05,
"loss": 1.7682,
"step": 507
},
{
"epoch": 0.22648238965670978,
"grad_norm": 0.20501793920993805,
"learning_rate": 7.775914607233761e-05,
"loss": 1.7769,
"step": 508
},
{
"epoch": 0.22692822113241196,
"grad_norm": 0.2141670286655426,
"learning_rate": 7.773775352231299e-05,
"loss": 1.7864,
"step": 509
},
{
"epoch": 0.22737405260811414,
"grad_norm": 0.1976698487997055,
"learning_rate": 7.771626231479133e-05,
"loss": 1.7345,
"step": 510
},
{
"epoch": 0.22781988408381632,
"grad_norm": 0.2203235626220703,
"learning_rate": 7.769467250595688e-05,
"loss": 1.7741,
"step": 511
},
{
"epoch": 0.2282657155595185,
"grad_norm": 0.20633700489997864,
"learning_rate": 7.767298415225172e-05,
"loss": 1.6671,
"step": 512
},
{
"epoch": 0.22871154703522067,
"grad_norm": 0.21930013597011566,
"learning_rate": 7.765119731037554e-05,
"loss": 1.6226,
"step": 513
},
{
"epoch": 0.22915737851092288,
"grad_norm": 0.2221810221672058,
"learning_rate": 7.762931203728547e-05,
"loss": 1.7949,
"step": 514
},
{
"epoch": 0.22960320998662506,
"grad_norm": 0.2116052806377411,
"learning_rate": 7.760732839019604e-05,
"loss": 1.7742,
"step": 515
},
{
"epoch": 0.23004904146232724,
"grad_norm": 0.22342365980148315,
"learning_rate": 7.758524642657887e-05,
"loss": 1.8095,
"step": 516
},
{
"epoch": 0.23049487293802942,
"grad_norm": 0.19809666275978088,
"learning_rate": 7.756306620416272e-05,
"loss": 1.6623,
"step": 517
},
{
"epoch": 0.2309407044137316,
"grad_norm": 0.2312929928302765,
"learning_rate": 7.75407877809331e-05,
"loss": 1.7861,
"step": 518
},
{
"epoch": 0.23138653588943378,
"grad_norm": 0.21036399900913239,
"learning_rate": 7.751841121513235e-05,
"loss": 1.7913,
"step": 519
},
{
"epoch": 0.231832367365136,
"grad_norm": 0.21546313166618347,
"learning_rate": 7.749593656525931e-05,
"loss": 1.7115,
"step": 520
},
{
"epoch": 0.23227819884083817,
"grad_norm": 0.21037909388542175,
"learning_rate": 7.747336389006928e-05,
"loss": 1.7683,
"step": 521
},
{
"epoch": 0.23272403031654035,
"grad_norm": 0.2078377604484558,
"learning_rate": 7.745069324857383e-05,
"loss": 1.7656,
"step": 522
},
{
"epoch": 0.23316986179224253,
"grad_norm": 0.21215571463108063,
"learning_rate": 7.742792470004062e-05,
"loss": 1.7216,
"step": 523
},
{
"epoch": 0.2336156932679447,
"grad_norm": 0.19274559617042542,
"learning_rate": 7.740505830399329e-05,
"loss": 1.6717,
"step": 524
},
{
"epoch": 0.23406152474364691,
"grad_norm": 0.2016606479883194,
"learning_rate": 7.738209412021124e-05,
"loss": 1.7287,
"step": 525
},
{
"epoch": 0.2345073562193491,
"grad_norm": 0.20804037153720856,
"learning_rate": 7.735903220872958e-05,
"loss": 1.7927,
"step": 526
},
{
"epoch": 0.23495318769505127,
"grad_norm": 0.22181366384029388,
"learning_rate": 7.733587262983888e-05,
"loss": 1.835,
"step": 527
},
{
"epoch": 0.23539901917075345,
"grad_norm": 0.20415058732032776,
"learning_rate": 7.7312615444085e-05,
"loss": 1.7226,
"step": 528
},
{
"epoch": 0.23584485064645563,
"grad_norm": 0.21193745732307434,
"learning_rate": 7.728926071226902e-05,
"loss": 1.8005,
"step": 529
},
{
"epoch": 0.2362906821221578,
"grad_norm": 0.21242454648017883,
"learning_rate": 7.726580849544704e-05,
"loss": 1.7163,
"step": 530
},
{
"epoch": 0.23673651359786002,
"grad_norm": 0.20869044959545135,
"learning_rate": 7.724225885492998e-05,
"loss": 1.7958,
"step": 531
},
{
"epoch": 0.2371823450735622,
"grad_norm": 0.21901239454746246,
"learning_rate": 7.721861185228347e-05,
"loss": 1.7394,
"step": 532
},
{
"epoch": 0.23762817654926438,
"grad_norm": 0.20783841609954834,
"learning_rate": 7.719486754932768e-05,
"loss": 1.7592,
"step": 533
},
{
"epoch": 0.23807400802496656,
"grad_norm": 0.2176273763179779,
"learning_rate": 7.717102600813716e-05,
"loss": 1.7896,
"step": 534
},
{
"epoch": 0.23851983950066874,
"grad_norm": 0.2128293663263321,
"learning_rate": 7.714708729104062e-05,
"loss": 1.7401,
"step": 535
},
{
"epoch": 0.23896567097637092,
"grad_norm": 0.2054302990436554,
"learning_rate": 7.712305146062087e-05,
"loss": 1.7348,
"step": 536
},
{
"epoch": 0.23941150245207313,
"grad_norm": 0.2005021572113037,
"learning_rate": 7.709891857971458e-05,
"loss": 1.76,
"step": 537
},
{
"epoch": 0.2398573339277753,
"grad_norm": 0.2186511605978012,
"learning_rate": 7.707468871141215e-05,
"loss": 1.8412,
"step": 538
},
{
"epoch": 0.2403031654034775,
"grad_norm": 0.204304039478302,
"learning_rate": 7.705036191905752e-05,
"loss": 1.703,
"step": 539
},
{
"epoch": 0.24074899687917967,
"grad_norm": 0.2037625014781952,
"learning_rate": 7.702593826624801e-05,
"loss": 1.7164,
"step": 540
},
{
"epoch": 0.24119482835488185,
"grad_norm": 0.2177598923444748,
"learning_rate": 7.700141781683418e-05,
"loss": 1.738,
"step": 541
},
{
"epoch": 0.24164065983058403,
"grad_norm": 0.21556971967220306,
"learning_rate": 7.697680063491964e-05,
"loss": 1.6842,
"step": 542
},
{
"epoch": 0.24208649130628623,
"grad_norm": 0.2162875533103943,
"learning_rate": 7.695208678486088e-05,
"loss": 1.7615,
"step": 543
},
{
"epoch": 0.2425323227819884,
"grad_norm": 0.21224163472652435,
"learning_rate": 7.692727633126714e-05,
"loss": 1.7354,
"step": 544
},
{
"epoch": 0.2429781542576906,
"grad_norm": 0.2110309898853302,
"learning_rate": 7.690236933900014e-05,
"loss": 1.6944,
"step": 545
},
{
"epoch": 0.24342398573339277,
"grad_norm": 0.20104189217090607,
"learning_rate": 7.687736587317407e-05,
"loss": 1.7314,
"step": 546
},
{
"epoch": 0.24386981720909495,
"grad_norm": 0.21651782095432281,
"learning_rate": 7.685226599915524e-05,
"loss": 1.7696,
"step": 547
},
{
"epoch": 0.24431564868479716,
"grad_norm": 0.206302210688591,
"learning_rate": 7.682706978256208e-05,
"loss": 1.7771,
"step": 548
},
{
"epoch": 0.24476148016049934,
"grad_norm": 0.20536518096923828,
"learning_rate": 7.680177728926483e-05,
"loss": 1.7412,
"step": 549
},
{
"epoch": 0.24520731163620152,
"grad_norm": 0.2088993638753891,
"learning_rate": 7.677638858538544e-05,
"loss": 1.7634,
"step": 550
},
{
"epoch": 0.2456531431119037,
"grad_norm": 0.20735305547714233,
"learning_rate": 7.675090373729741e-05,
"loss": 1.7782,
"step": 551
},
{
"epoch": 0.24609897458760588,
"grad_norm": 0.2111474722623825,
"learning_rate": 7.672532281162556e-05,
"loss": 1.7773,
"step": 552
},
{
"epoch": 0.24654480606330806,
"grad_norm": 0.19856305420398712,
"learning_rate": 7.669964587524588e-05,
"loss": 1.6685,
"step": 553
},
{
"epoch": 0.24699063753901027,
"grad_norm": 0.20613139867782593,
"learning_rate": 7.66738729952854e-05,
"loss": 1.6916,
"step": 554
},
{
"epoch": 0.24743646901471245,
"grad_norm": 0.20895972847938538,
"learning_rate": 7.664800423912191e-05,
"loss": 1.7875,
"step": 555
},
{
"epoch": 0.24788230049041463,
"grad_norm": 0.20388461649417877,
"learning_rate": 7.662203967438391e-05,
"loss": 1.6645,
"step": 556
},
{
"epoch": 0.2483281319661168,
"grad_norm": 0.20363497734069824,
"learning_rate": 7.659597936895034e-05,
"loss": 1.755,
"step": 557
},
{
"epoch": 0.24877396344181898,
"grad_norm": 0.21989643573760986,
"learning_rate": 7.656982339095045e-05,
"loss": 1.8409,
"step": 558
},
{
"epoch": 0.24921979491752116,
"grad_norm": 0.19894006848335266,
"learning_rate": 7.654357180876358e-05,
"loss": 1.7576,
"step": 559
},
{
"epoch": 0.24966562639322337,
"grad_norm": 0.21573615074157715,
"learning_rate": 7.651722469101905e-05,
"loss": 1.7228,
"step": 560
},
{
"epoch": 0.2501114578689255,
"grad_norm": 0.24178695678710938,
"learning_rate": 7.649078210659587e-05,
"loss": 1.7428,
"step": 561
},
{
"epoch": 0.25055728934462773,
"grad_norm": 0.21728956699371338,
"learning_rate": 7.646424412462273e-05,
"loss": 1.8551,
"step": 562
},
{
"epoch": 0.25100312082032994,
"grad_norm": 0.21060433983802795,
"learning_rate": 7.643761081447758e-05,
"loss": 1.7606,
"step": 563
},
{
"epoch": 0.2514489522960321,
"grad_norm": 0.22947797179222107,
"learning_rate": 7.641088224578773e-05,
"loss": 1.7306,
"step": 564
},
{
"epoch": 0.2518947837717343,
"grad_norm": 0.21212172508239746,
"learning_rate": 7.638405848842945e-05,
"loss": 1.7445,
"step": 565
},
{
"epoch": 0.25234061524743645,
"grad_norm": 0.21673139929771423,
"learning_rate": 7.635713961252782e-05,
"loss": 1.7556,
"step": 566
},
{
"epoch": 0.25278644672313866,
"grad_norm": 0.22516381740570068,
"learning_rate": 7.633012568845668e-05,
"loss": 1.7493,
"step": 567
},
{
"epoch": 0.25323227819884087,
"grad_norm": 0.23668955266475677,
"learning_rate": 7.63030167868383e-05,
"loss": 1.7352,
"step": 568
},
{
"epoch": 0.253678109674543,
"grad_norm": 0.22791285812854767,
"learning_rate": 7.627581297854322e-05,
"loss": 1.7048,
"step": 569
},
{
"epoch": 0.2541239411502452,
"grad_norm": 0.24229630827903748,
"learning_rate": 7.624851433469017e-05,
"loss": 1.7953,
"step": 570
},
{
"epoch": 0.2545697726259474,
"grad_norm": 0.20149646699428558,
"learning_rate": 7.622112092664577e-05,
"loss": 1.7353,
"step": 571
},
{
"epoch": 0.2550156041016496,
"grad_norm": 0.21539618074893951,
"learning_rate": 7.619363282602436e-05,
"loss": 1.6643,
"step": 572
},
{
"epoch": 0.25546143557735174,
"grad_norm": 0.23108653724193573,
"learning_rate": 7.616605010468787e-05,
"loss": 1.77,
"step": 573
},
{
"epoch": 0.25590726705305394,
"grad_norm": 0.21947409212589264,
"learning_rate": 7.613837283474559e-05,
"loss": 1.7714,
"step": 574
},
{
"epoch": 0.25635309852875615,
"grad_norm": 0.2154000699520111,
"learning_rate": 7.611060108855393e-05,
"loss": 1.7469,
"step": 575
},
{
"epoch": 0.2567989300044583,
"grad_norm": 0.23046647012233734,
"learning_rate": 7.608273493871639e-05,
"loss": 1.7607,
"step": 576
},
{
"epoch": 0.2572447614801605,
"grad_norm": 0.23710086941719055,
"learning_rate": 7.605477445808318e-05,
"loss": 1.7796,
"step": 577
},
{
"epoch": 0.25769059295586266,
"grad_norm": 0.20885971188545227,
"learning_rate": 7.602671971975118e-05,
"loss": 1.816,
"step": 578
},
{
"epoch": 0.25813642443156487,
"grad_norm": 0.22010734677314758,
"learning_rate": 7.599857079706364e-05,
"loss": 1.7466,
"step": 579
},
{
"epoch": 0.2585822559072671,
"grad_norm": 0.21547986567020416,
"learning_rate": 7.597032776361007e-05,
"loss": 1.7816,
"step": 580
},
{
"epoch": 0.25902808738296923,
"grad_norm": 0.19855529069900513,
"learning_rate": 7.594199069322598e-05,
"loss": 1.7245,
"step": 581
},
{
"epoch": 0.25947391885867144,
"grad_norm": 0.19900168478488922,
"learning_rate": 7.591355965999276e-05,
"loss": 1.7174,
"step": 582
},
{
"epoch": 0.2599197503343736,
"grad_norm": 0.2193600833415985,
"learning_rate": 7.588503473823742e-05,
"loss": 1.7096,
"step": 583
},
{
"epoch": 0.2603655818100758,
"grad_norm": 0.21309758722782135,
"learning_rate": 7.585641600253242e-05,
"loss": 1.7349,
"step": 584
},
{
"epoch": 0.26081141328577795,
"grad_norm": 0.20293527841567993,
"learning_rate": 7.582770352769548e-05,
"loss": 1.7084,
"step": 585
},
{
"epoch": 0.26125724476148016,
"grad_norm": 0.20566365122795105,
"learning_rate": 7.57988973887894e-05,
"loss": 1.6904,
"step": 586
},
{
"epoch": 0.26170307623718236,
"grad_norm": 0.21862030029296875,
"learning_rate": 7.576999766112183e-05,
"loss": 1.7699,
"step": 587
},
{
"epoch": 0.2621489077128845,
"grad_norm": 0.22617413103580475,
"learning_rate": 7.574100442024507e-05,
"loss": 1.9066,
"step": 588
},
{
"epoch": 0.2625947391885867,
"grad_norm": 0.23065897822380066,
"learning_rate": 7.571191774195592e-05,
"loss": 1.7946,
"step": 589
},
{
"epoch": 0.2630405706642889,
"grad_norm": 0.21127870678901672,
"learning_rate": 7.568273770229546e-05,
"loss": 1.7289,
"step": 590
},
{
"epoch": 0.2634864021399911,
"grad_norm": 0.2256181687116623,
"learning_rate": 7.565346437754881e-05,
"loss": 1.7918,
"step": 591
},
{
"epoch": 0.2639322336156933,
"grad_norm": 0.2192109078168869,
"learning_rate": 7.562409784424499e-05,
"loss": 1.7303,
"step": 592
},
{
"epoch": 0.26437806509139544,
"grad_norm": 0.20271852612495422,
"learning_rate": 7.559463817915666e-05,
"loss": 1.7136,
"step": 593
},
{
"epoch": 0.26482389656709765,
"grad_norm": 0.2233620136976242,
"learning_rate": 7.556508545930001e-05,
"loss": 1.6845,
"step": 594
},
{
"epoch": 0.2652697280427998,
"grad_norm": 0.24921123683452606,
"learning_rate": 7.553543976193446e-05,
"loss": 1.7055,
"step": 595
},
{
"epoch": 0.265715559518502,
"grad_norm": 0.21758922934532166,
"learning_rate": 7.55057011645625e-05,
"loss": 1.6639,
"step": 596
},
{
"epoch": 0.2661613909942042,
"grad_norm": 0.22392435371875763,
"learning_rate": 7.547586974492951e-05,
"loss": 1.7267,
"step": 597
},
{
"epoch": 0.26660722246990637,
"grad_norm": 0.2134278565645218,
"learning_rate": 7.544594558102352e-05,
"loss": 1.7213,
"step": 598
},
{
"epoch": 0.2670530539456086,
"grad_norm": 0.21148909628391266,
"learning_rate": 7.541592875107504e-05,
"loss": 1.7874,
"step": 599
},
{
"epoch": 0.26749888542131073,
"grad_norm": 0.22129899263381958,
"learning_rate": 7.538581933355681e-05,
"loss": 1.714,
"step": 600
},
{
"epoch": 0.26794471689701294,
"grad_norm": 0.23374201357364655,
"learning_rate": 7.535561740718362e-05,
"loss": 1.7103,
"step": 601
},
{
"epoch": 0.2683905483727151,
"grad_norm": 0.21001872420310974,
"learning_rate": 7.532532305091211e-05,
"loss": 1.6265,
"step": 602
},
{
"epoch": 0.2688363798484173,
"grad_norm": 0.23460710048675537,
"learning_rate": 7.52949363439406e-05,
"loss": 1.7838,
"step": 603
},
{
"epoch": 0.2692822113241195,
"grad_norm": 0.23146916925907135,
"learning_rate": 7.526445736570879e-05,
"loss": 1.764,
"step": 604
},
{
"epoch": 0.26972804279982165,
"grad_norm": 0.19246350228786469,
"learning_rate": 7.52338861958976e-05,
"loss": 1.6467,
"step": 605
},
{
"epoch": 0.27017387427552386,
"grad_norm": 0.2351468801498413,
"learning_rate": 7.520322291442903e-05,
"loss": 1.6567,
"step": 606
},
{
"epoch": 0.270619705751226,
"grad_norm": 0.2138238102197647,
"learning_rate": 7.51724676014658e-05,
"loss": 1.6515,
"step": 607
},
{
"epoch": 0.2710655372269282,
"grad_norm": 0.23105895519256592,
"learning_rate": 7.51416203374113e-05,
"loss": 1.7563,
"step": 608
},
{
"epoch": 0.27151136870263043,
"grad_norm": 0.21428363025188446,
"learning_rate": 7.511068120290926e-05,
"loss": 1.7891,
"step": 609
},
{
"epoch": 0.2719572001783326,
"grad_norm": 0.21053239703178406,
"learning_rate": 7.507965027884361e-05,
"loss": 1.7177,
"step": 610
},
{
"epoch": 0.2724030316540348,
"grad_norm": 0.231001615524292,
"learning_rate": 7.504852764633823e-05,
"loss": 1.7051,
"step": 611
},
{
"epoch": 0.27284886312973694,
"grad_norm": 0.21583721041679382,
"learning_rate": 7.501731338675677e-05,
"loss": 1.7414,
"step": 612
},
{
"epoch": 0.27329469460543915,
"grad_norm": 0.21509505808353424,
"learning_rate": 7.498600758170241e-05,
"loss": 1.669,
"step": 613
},
{
"epoch": 0.27374052608114136,
"grad_norm": 0.22119706869125366,
"learning_rate": 7.495461031301765e-05,
"loss": 1.6687,
"step": 614
},
{
"epoch": 0.2741863575568435,
"grad_norm": 0.22133754193782806,
"learning_rate": 7.492312166278414e-05,
"loss": 1.8043,
"step": 615
},
{
"epoch": 0.2746321890325457,
"grad_norm": 0.2934802770614624,
"learning_rate": 7.489154171332236e-05,
"loss": 1.7561,
"step": 616
},
{
"epoch": 0.27507802050824787,
"grad_norm": 0.201655313372612,
"learning_rate": 7.485987054719153e-05,
"loss": 1.6652,
"step": 617
},
{
"epoch": 0.2755238519839501,
"grad_norm": 0.2276788353919983,
"learning_rate": 7.482810824718931e-05,
"loss": 1.7559,
"step": 618
},
{
"epoch": 0.2759696834596522,
"grad_norm": 0.22293934226036072,
"learning_rate": 7.479625489635162e-05,
"loss": 1.6903,
"step": 619
},
{
"epoch": 0.27641551493535443,
"grad_norm": 0.20375767350196838,
"learning_rate": 7.476431057795241e-05,
"loss": 1.7936,
"step": 620
},
{
"epoch": 0.27686134641105664,
"grad_norm": 0.22783713042736053,
"learning_rate": 7.473227537550346e-05,
"loss": 1.7063,
"step": 621
},
{
"epoch": 0.2773071778867588,
"grad_norm": 0.2079494595527649,
"learning_rate": 7.470014937275411e-05,
"loss": 1.7074,
"step": 622
},
{
"epoch": 0.277753009362461,
"grad_norm": 0.2122948169708252,
"learning_rate": 7.466793265369114e-05,
"loss": 1.7078,
"step": 623
},
{
"epoch": 0.27819884083816315,
"grad_norm": 0.2332155853509903,
"learning_rate": 7.463562530253842e-05,
"loss": 1.8,
"step": 624
},
{
"epoch": 0.27864467231386536,
"grad_norm": 0.2049056589603424,
"learning_rate": 7.46032274037568e-05,
"loss": 1.6335,
"step": 625
},
{
"epoch": 0.27909050378956757,
"grad_norm": 0.22888043522834778,
"learning_rate": 7.457073904204384e-05,
"loss": 1.6614,
"step": 626
},
{
"epoch": 0.2795363352652697,
"grad_norm": 0.2044975906610489,
"learning_rate": 7.45381603023336e-05,
"loss": 1.6818,
"step": 627
},
{
"epoch": 0.2799821667409719,
"grad_norm": 0.22751621901988983,
"learning_rate": 7.450549126979643e-05,
"loss": 1.8181,
"step": 628
},
{
"epoch": 0.2804279982166741,
"grad_norm": 0.20126068592071533,
"learning_rate": 7.447273202983866e-05,
"loss": 1.7101,
"step": 629
},
{
"epoch": 0.2808738296923763,
"grad_norm": 0.2142620086669922,
"learning_rate": 7.443988266810253e-05,
"loss": 1.7224,
"step": 630
},
{
"epoch": 0.28131966116807844,
"grad_norm": 0.20431213080883026,
"learning_rate": 7.440694327046587e-05,
"loss": 1.7421,
"step": 631
},
{
"epoch": 0.28176549264378065,
"grad_norm": 0.21456865966320038,
"learning_rate": 7.437391392304183e-05,
"loss": 1.8121,
"step": 632
},
{
"epoch": 0.28221132411948285,
"grad_norm": 0.21535775065422058,
"learning_rate": 7.43407947121788e-05,
"loss": 1.7968,
"step": 633
},
{
"epoch": 0.282657155595185,
"grad_norm": 0.20763567090034485,
"learning_rate": 7.430758572446007e-05,
"loss": 1.776,
"step": 634
},
{
"epoch": 0.2831029870708872,
"grad_norm": 0.2219155877828598,
"learning_rate": 7.427428704670357e-05,
"loss": 1.7112,
"step": 635
},
{
"epoch": 0.28354881854658937,
"grad_norm": 0.20080716907978058,
"learning_rate": 7.424089876596181e-05,
"loss": 1.7558,
"step": 636
},
{
"epoch": 0.2839946500222916,
"grad_norm": 0.2080196887254715,
"learning_rate": 7.420742096952147e-05,
"loss": 1.7308,
"step": 637
},
{
"epoch": 0.2844404814979938,
"grad_norm": 0.2138231247663498,
"learning_rate": 7.417385374490327e-05,
"loss": 1.7804,
"step": 638
},
{
"epoch": 0.28488631297369593,
"grad_norm": 0.20495419204235077,
"learning_rate": 7.414019717986174e-05,
"loss": 1.7727,
"step": 639
},
{
"epoch": 0.28533214444939814,
"grad_norm": 0.21069945394992828,
"learning_rate": 7.410645136238495e-05,
"loss": 1.7712,
"step": 640
},
{
"epoch": 0.2857779759251003,
"grad_norm": 0.19948187470436096,
"learning_rate": 7.407261638069433e-05,
"loss": 1.6869,
"step": 641
},
{
"epoch": 0.2862238074008025,
"grad_norm": 0.20422448217868805,
"learning_rate": 7.403869232324439e-05,
"loss": 1.7594,
"step": 642
},
{
"epoch": 0.2866696388765047,
"grad_norm": 0.1993008702993393,
"learning_rate": 7.40046792787225e-05,
"loss": 1.6994,
"step": 643
},
{
"epoch": 0.28711547035220686,
"grad_norm": 0.206438809633255,
"learning_rate": 7.397057733604868e-05,
"loss": 1.789,
"step": 644
},
{
"epoch": 0.28756130182790907,
"grad_norm": 0.22038403153419495,
"learning_rate": 7.393638658437537e-05,
"loss": 1.6763,
"step": 645
},
{
"epoch": 0.2880071333036112,
"grad_norm": 0.2054975926876068,
"learning_rate": 7.390210711308716e-05,
"loss": 1.7691,
"step": 646
},
{
"epoch": 0.2884529647793134,
"grad_norm": 0.20188304781913757,
"learning_rate": 7.38677390118006e-05,
"loss": 1.647,
"step": 647
},
{
"epoch": 0.2888987962550156,
"grad_norm": 0.20065569877624512,
"learning_rate": 7.38332823703639e-05,
"loss": 1.7561,
"step": 648
},
{
"epoch": 0.2893446277307178,
"grad_norm": 0.2073405534029007,
"learning_rate": 7.379873727885681e-05,
"loss": 1.7425,
"step": 649
},
{
"epoch": 0.28979045920642,
"grad_norm": 0.21183277666568756,
"learning_rate": 7.376410382759026e-05,
"loss": 1.7622,
"step": 650
},
{
"epoch": 0.29023629068212214,
"grad_norm": 0.21674148738384247,
"learning_rate": 7.372938210710622e-05,
"loss": 1.8301,
"step": 651
},
{
"epoch": 0.29068212215782435,
"grad_norm": 0.2239564210176468,
"learning_rate": 7.369457220817736e-05,
"loss": 1.7061,
"step": 652
},
{
"epoch": 0.2911279536335265,
"grad_norm": 0.2046596258878708,
"learning_rate": 7.365967422180692e-05,
"loss": 1.7185,
"step": 653
},
{
"epoch": 0.2915737851092287,
"grad_norm": 0.2077386975288391,
"learning_rate": 7.362468823922844e-05,
"loss": 1.6894,
"step": 654
},
{
"epoch": 0.2920196165849309,
"grad_norm": 0.22262682020664215,
"learning_rate": 7.358961435190546e-05,
"loss": 1.743,
"step": 655
},
{
"epoch": 0.29246544806063307,
"grad_norm": 0.22507880628108978,
"learning_rate": 7.355445265153136e-05,
"loss": 1.7843,
"step": 656
},
{
"epoch": 0.2929112795363353,
"grad_norm": 0.2175893634557724,
"learning_rate": 7.35192032300291e-05,
"loss": 1.7287,
"step": 657
},
{
"epoch": 0.29335711101203743,
"grad_norm": 0.2029731124639511,
"learning_rate": 7.348386617955094e-05,
"loss": 1.6842,
"step": 658
},
{
"epoch": 0.29380294248773964,
"grad_norm": 0.23122525215148926,
"learning_rate": 7.344844159247823e-05,
"loss": 1.8079,
"step": 659
},
{
"epoch": 0.29424877396344185,
"grad_norm": 0.2044292837381363,
"learning_rate": 7.341292956142117e-05,
"loss": 1.8154,
"step": 660
},
{
"epoch": 0.294694605439144,
"grad_norm": 0.20966410636901855,
"learning_rate": 7.337733017921859e-05,
"loss": 1.6904,
"step": 661
},
{
"epoch": 0.2951404369148462,
"grad_norm": 0.20876199007034302,
"learning_rate": 7.334164353893765e-05,
"loss": 1.7961,
"step": 662
},
{
"epoch": 0.29558626839054836,
"grad_norm": 0.2060309499502182,
"learning_rate": 7.330586973387364e-05,
"loss": 1.6499,
"step": 663
},
{
"epoch": 0.29603209986625056,
"grad_norm": 0.21161815524101257,
"learning_rate": 7.327000885754973e-05,
"loss": 1.7694,
"step": 664
},
{
"epoch": 0.2964779313419527,
"grad_norm": 0.22235240042209625,
"learning_rate": 7.32340610037167e-05,
"loss": 1.8006,
"step": 665
},
{
"epoch": 0.2969237628176549,
"grad_norm": 0.2124897986650467,
"learning_rate": 7.319802626635271e-05,
"loss": 1.8204,
"step": 666
},
{
"epoch": 0.29736959429335713,
"grad_norm": 0.24330593645572662,
"learning_rate": 7.316190473966312e-05,
"loss": 1.7003,
"step": 667
},
{
"epoch": 0.2978154257690593,
"grad_norm": 0.20732414722442627,
"learning_rate": 7.312569651808011e-05,
"loss": 1.5801,
"step": 668
},
{
"epoch": 0.2982612572447615,
"grad_norm": 0.22267280519008636,
"learning_rate": 7.308940169626255e-05,
"loss": 1.7417,
"step": 669
},
{
"epoch": 0.29870708872046364,
"grad_norm": 0.20995312929153442,
"learning_rate": 7.305302036909567e-05,
"loss": 1.7385,
"step": 670
},
{
"epoch": 0.29915292019616585,
"grad_norm": 0.21934688091278076,
"learning_rate": 7.30165526316909e-05,
"loss": 1.7042,
"step": 671
},
{
"epoch": 0.29959875167186806,
"grad_norm": 0.22048768401145935,
"learning_rate": 7.297999857938554e-05,
"loss": 1.7672,
"step": 672
},
{
"epoch": 0.3000445831475702,
"grad_norm": 0.20573429763317108,
"learning_rate": 7.294335830774252e-05,
"loss": 1.7556,
"step": 673
},
{
"epoch": 0.3004904146232724,
"grad_norm": 0.21020594239234924,
"learning_rate": 7.290663191255022e-05,
"loss": 1.727,
"step": 674
},
{
"epoch": 0.30093624609897457,
"grad_norm": 0.20675401389598846,
"learning_rate": 7.286981948982215e-05,
"loss": 1.6531,
"step": 675
},
{
"epoch": 0.3013820775746768,
"grad_norm": 0.20087653398513794,
"learning_rate": 7.283292113579672e-05,
"loss": 1.7088,
"step": 676
},
{
"epoch": 0.301827909050379,
"grad_norm": 0.21411505341529846,
"learning_rate": 7.279593694693698e-05,
"loss": 1.7798,
"step": 677
},
{
"epoch": 0.30227374052608114,
"grad_norm": 0.21519498527050018,
"learning_rate": 7.275886701993042e-05,
"loss": 1.722,
"step": 678
},
{
"epoch": 0.30271957200178334,
"grad_norm": 0.21711432933807373,
"learning_rate": 7.272171145168863e-05,
"loss": 1.8175,
"step": 679
},
{
"epoch": 0.3031654034774855,
"grad_norm": 0.20538119971752167,
"learning_rate": 7.268447033934708e-05,
"loss": 1.7196,
"step": 680
},
{
"epoch": 0.3036112349531877,
"grad_norm": 0.22172988951206207,
"learning_rate": 7.264714378026494e-05,
"loss": 1.7341,
"step": 681
},
{
"epoch": 0.30405706642888986,
"grad_norm": 0.20911812782287598,
"learning_rate": 7.26097318720247e-05,
"loss": 1.7628,
"step": 682
},
{
"epoch": 0.30450289790459206,
"grad_norm": 0.20472237467765808,
"learning_rate": 7.257223471243201e-05,
"loss": 1.8058,
"step": 683
},
{
"epoch": 0.30494872938029427,
"grad_norm": 0.2150549590587616,
"learning_rate": 7.253465239951539e-05,
"loss": 1.6952,
"step": 684
},
{
"epoch": 0.3053945608559964,
"grad_norm": 0.20892566442489624,
"learning_rate": 7.249698503152596e-05,
"loss": 1.757,
"step": 685
},
{
"epoch": 0.30584039233169863,
"grad_norm": 0.20996753871440887,
"learning_rate": 7.245923270693721e-05,
"loss": 1.7039,
"step": 686
},
{
"epoch": 0.3062862238074008,
"grad_norm": 0.20857934653759003,
"learning_rate": 7.242139552444473e-05,
"loss": 1.7152,
"step": 687
},
{
"epoch": 0.306732055283103,
"grad_norm": 0.20755071938037872,
"learning_rate": 7.238347358296596e-05,
"loss": 1.7138,
"step": 688
},
{
"epoch": 0.3071778867588052,
"grad_norm": 0.2029207944869995,
"learning_rate": 7.234546698163992e-05,
"loss": 1.7338,
"step": 689
},
{
"epoch": 0.30762371823450735,
"grad_norm": 0.20173445343971252,
"learning_rate": 7.230737581982694e-05,
"loss": 1.7759,
"step": 690
},
{
"epoch": 0.30806954971020956,
"grad_norm": 0.2252359688282013,
"learning_rate": 7.226920019710845e-05,
"loss": 1.7886,
"step": 691
},
{
"epoch": 0.3085153811859117,
"grad_norm": 0.2031915783882141,
"learning_rate": 7.223094021328664e-05,
"loss": 1.7351,
"step": 692
},
{
"epoch": 0.3089612126616139,
"grad_norm": 0.20862999558448792,
"learning_rate": 7.219259596838429e-05,
"loss": 1.6763,
"step": 693
},
{
"epoch": 0.30940704413731607,
"grad_norm": 0.21994739770889282,
"learning_rate": 7.215416756264442e-05,
"loss": 1.8017,
"step": 694
},
{
"epoch": 0.3098528756130183,
"grad_norm": 0.19967246055603027,
"learning_rate": 7.211565509653012e-05,
"loss": 1.696,
"step": 695
},
{
"epoch": 0.3102987070887205,
"grad_norm": 0.2177416831254959,
"learning_rate": 7.207705867072421e-05,
"loss": 1.7102,
"step": 696
},
{
"epoch": 0.31074453856442263,
"grad_norm": 0.22154054045677185,
"learning_rate": 7.203837838612897e-05,
"loss": 1.6522,
"step": 697
},
{
"epoch": 0.31119037004012484,
"grad_norm": 0.21412450075149536,
"learning_rate": 7.1999614343866e-05,
"loss": 1.8394,
"step": 698
},
{
"epoch": 0.311636201515827,
"grad_norm": 0.24822783470153809,
"learning_rate": 7.196076664527577e-05,
"loss": 1.7955,
"step": 699
},
{
"epoch": 0.3120820329915292,
"grad_norm": 0.21336504817008972,
"learning_rate": 7.192183539191753e-05,
"loss": 1.7144,
"step": 700
},
{
"epoch": 0.3125278644672314,
"grad_norm": 0.2380637526512146,
"learning_rate": 7.188282068556891e-05,
"loss": 1.6807,
"step": 701
},
{
"epoch": 0.31297369594293356,
"grad_norm": 0.19818735122680664,
"learning_rate": 7.184372262822575e-05,
"loss": 1.7561,
"step": 702
},
{
"epoch": 0.31341952741863577,
"grad_norm": 0.23580355942249298,
"learning_rate": 7.180454132210179e-05,
"loss": 1.7519,
"step": 703
},
{
"epoch": 0.3138653588943379,
"grad_norm": 0.2163688987493515,
"learning_rate": 7.176527686962835e-05,
"loss": 1.7003,
"step": 704
},
{
"epoch": 0.3143111903700401,
"grad_norm": 0.2241927832365036,
"learning_rate": 7.172592937345421e-05,
"loss": 1.6941,
"step": 705
},
{
"epoch": 0.31475702184574234,
"grad_norm": 0.22052347660064697,
"learning_rate": 7.168649893644517e-05,
"loss": 1.7133,
"step": 706
},
{
"epoch": 0.3152028533214445,
"grad_norm": 0.22314177453517914,
"learning_rate": 7.164698566168393e-05,
"loss": 1.7262,
"step": 707
},
{
"epoch": 0.3156486847971467,
"grad_norm": 0.2206079065799713,
"learning_rate": 7.16073896524697e-05,
"loss": 1.7779,
"step": 708
},
{
"epoch": 0.31609451627284885,
"grad_norm": 0.20930807292461395,
"learning_rate": 7.156771101231798e-05,
"loss": 1.7041,
"step": 709
},
{
"epoch": 0.31654034774855105,
"grad_norm": 0.21127712726593018,
"learning_rate": 7.152794984496034e-05,
"loss": 1.7807,
"step": 710
},
{
"epoch": 0.3169861792242532,
"grad_norm": 0.19875945150852203,
"learning_rate": 7.148810625434406e-05,
"loss": 1.7438,
"step": 711
},
{
"epoch": 0.3174320106999554,
"grad_norm": 0.20444701611995697,
"learning_rate": 7.14481803446319e-05,
"loss": 1.7587,
"step": 712
},
{
"epoch": 0.3178778421756576,
"grad_norm": 0.19894717633724213,
"learning_rate": 7.140817222020186e-05,
"loss": 1.7047,
"step": 713
},
{
"epoch": 0.3183236736513598,
"grad_norm": 0.20163820683956146,
"learning_rate": 7.136808198564683e-05,
"loss": 1.6941,
"step": 714
},
{
"epoch": 0.318769505127062,
"grad_norm": 0.20997068285942078,
"learning_rate": 7.132790974577438e-05,
"loss": 1.7468,
"step": 715
},
{
"epoch": 0.31921533660276413,
"grad_norm": 0.1935359686613083,
"learning_rate": 7.128765560560646e-05,
"loss": 1.7119,
"step": 716
},
{
"epoch": 0.31966116807846634,
"grad_norm": 0.20880842208862305,
"learning_rate": 7.124731967037916e-05,
"loss": 1.6706,
"step": 717
},
{
"epoch": 0.32010699955416855,
"grad_norm": 0.21494819223880768,
"learning_rate": 7.120690204554236e-05,
"loss": 1.774,
"step": 718
},
{
"epoch": 0.3205528310298707,
"grad_norm": 0.2001909464597702,
"learning_rate": 7.116640283675952e-05,
"loss": 1.6931,
"step": 719
},
{
"epoch": 0.3209986625055729,
"grad_norm": 0.20694108307361603,
"learning_rate": 7.112582214990739e-05,
"loss": 1.7273,
"step": 720
},
{
"epoch": 0.32144449398127506,
"grad_norm": 0.19691170752048492,
"learning_rate": 7.108516009107573e-05,
"loss": 1.6678,
"step": 721
},
{
"epoch": 0.32189032545697727,
"grad_norm": 0.21288730204105377,
"learning_rate": 7.104441676656704e-05,
"loss": 1.7421,
"step": 722
},
{
"epoch": 0.3223361569326795,
"grad_norm": 0.2045082151889801,
"learning_rate": 7.100359228289623e-05,
"loss": 1.7416,
"step": 723
},
{
"epoch": 0.3227819884083816,
"grad_norm": 0.23858684301376343,
"learning_rate": 7.096268674679042e-05,
"loss": 1.816,
"step": 724
},
{
"epoch": 0.32322781988408383,
"grad_norm": 0.20045718550682068,
"learning_rate": 7.092170026518863e-05,
"loss": 1.7845,
"step": 725
},
{
"epoch": 0.323673651359786,
"grad_norm": 0.22614650428295135,
"learning_rate": 7.088063294524144e-05,
"loss": 1.7489,
"step": 726
},
{
"epoch": 0.3241194828354882,
"grad_norm": 0.2049480676651001,
"learning_rate": 7.083948489431085e-05,
"loss": 1.6892,
"step": 727
},
{
"epoch": 0.32456531431119034,
"grad_norm": 0.20532821118831635,
"learning_rate": 7.079825621996984e-05,
"loss": 1.7088,
"step": 728
},
{
"epoch": 0.32501114578689255,
"grad_norm": 0.20658715069293976,
"learning_rate": 7.07569470300022e-05,
"loss": 1.6465,
"step": 729
},
{
"epoch": 0.32545697726259476,
"grad_norm": 0.21333490312099457,
"learning_rate": 7.07155574324022e-05,
"loss": 1.8009,
"step": 730
},
{
"epoch": 0.3259028087382969,
"grad_norm": 0.19863495230674744,
"learning_rate": 7.067408753537434e-05,
"loss": 1.6996,
"step": 731
},
{
"epoch": 0.3263486402139991,
"grad_norm": 0.19713807106018066,
"learning_rate": 7.063253744733301e-05,
"loss": 1.7072,
"step": 732
},
{
"epoch": 0.32679447168970127,
"grad_norm": 0.21338967978954315,
"learning_rate": 7.059090727690227e-05,
"loss": 1.739,
"step": 733
},
{
"epoch": 0.3272403031654035,
"grad_norm": 0.2086186707019806,
"learning_rate": 7.054919713291555e-05,
"loss": 1.7702,
"step": 734
},
{
"epoch": 0.3276861346411057,
"grad_norm": 0.20826803147792816,
"learning_rate": 7.050740712441528e-05,
"loss": 1.8603,
"step": 735
},
{
"epoch": 0.32813196611680784,
"grad_norm": 0.1978282779455185,
"learning_rate": 7.046553736065278e-05,
"loss": 1.6992,
"step": 736
},
{
"epoch": 0.32857779759251005,
"grad_norm": 0.21559976041316986,
"learning_rate": 7.042358795108783e-05,
"loss": 1.7706,
"step": 737
},
{
"epoch": 0.3290236290682122,
"grad_norm": 0.20173758268356323,
"learning_rate": 7.03815590053884e-05,
"loss": 1.7819,
"step": 738
},
{
"epoch": 0.3294694605439144,
"grad_norm": 0.20154009759426117,
"learning_rate": 7.033945063343041e-05,
"loss": 1.6949,
"step": 739
},
{
"epoch": 0.32991529201961656,
"grad_norm": 0.22486606240272522,
"learning_rate": 7.029726294529747e-05,
"loss": 1.7281,
"step": 740
},
{
"epoch": 0.33036112349531876,
"grad_norm": 0.2042747586965561,
"learning_rate": 7.025499605128046e-05,
"loss": 1.6134,
"step": 741
},
{
"epoch": 0.330806954971021,
"grad_norm": 0.23044522106647491,
"learning_rate": 7.021265006187739e-05,
"loss": 1.7322,
"step": 742
},
{
"epoch": 0.3312527864467231,
"grad_norm": 0.20150107145309448,
"learning_rate": 7.017022508779304e-05,
"loss": 1.6962,
"step": 743
},
{
"epoch": 0.33169861792242533,
"grad_norm": 0.23153840005397797,
"learning_rate": 7.012772123993865e-05,
"loss": 1.7392,
"step": 744
},
{
"epoch": 0.3321444493981275,
"grad_norm": 0.22877974808216095,
"learning_rate": 7.008513862943168e-05,
"loss": 1.7461,
"step": 745
},
{
"epoch": 0.3325902808738297,
"grad_norm": 0.22845101356506348,
"learning_rate": 7.004247736759552e-05,
"loss": 1.7318,
"step": 746
},
{
"epoch": 0.3330361123495319,
"grad_norm": 0.2245214730501175,
"learning_rate": 6.999973756595912e-05,
"loss": 1.7178,
"step": 747
},
{
"epoch": 0.33348194382523405,
"grad_norm": 0.21158166229724884,
"learning_rate": 6.995691933625683e-05,
"loss": 1.7885,
"step": 748
},
{
"epoch": 0.33392777530093626,
"grad_norm": 0.22586104273796082,
"learning_rate": 6.991402279042796e-05,
"loss": 1.8011,
"step": 749
},
{
"epoch": 0.3343736067766384,
"grad_norm": 0.2159549593925476,
"learning_rate": 6.987104804061659e-05,
"loss": 1.7776,
"step": 750
},
{
"epoch": 0.3348194382523406,
"grad_norm": 0.26645052433013916,
"learning_rate": 6.982799519917129e-05,
"loss": 1.7894,
"step": 751
},
{
"epoch": 0.3352652697280428,
"grad_norm": 0.22301529347896576,
"learning_rate": 6.978486437864473e-05,
"loss": 1.8246,
"step": 752
},
{
"epoch": 0.335711101203745,
"grad_norm": 0.2200409322977066,
"learning_rate": 6.974165569179343e-05,
"loss": 1.7634,
"step": 753
},
{
"epoch": 0.3361569326794472,
"grad_norm": 0.24905377626419067,
"learning_rate": 6.969836925157757e-05,
"loss": 1.7187,
"step": 754
},
{
"epoch": 0.33660276415514934,
"grad_norm": 0.20776088535785675,
"learning_rate": 6.965500517116045e-05,
"loss": 1.7115,
"step": 755
},
{
"epoch": 0.33704859563085154,
"grad_norm": 0.22392477095127106,
"learning_rate": 6.961156356390848e-05,
"loss": 1.8265,
"step": 756
},
{
"epoch": 0.3374944271065537,
"grad_norm": 0.23375096917152405,
"learning_rate": 6.956804454339069e-05,
"loss": 1.7948,
"step": 757
},
{
"epoch": 0.3379402585822559,
"grad_norm": 0.20256270468235016,
"learning_rate": 6.952444822337848e-05,
"loss": 1.69,
"step": 758
},
{
"epoch": 0.3383860900579581,
"grad_norm": 0.20559729635715485,
"learning_rate": 6.948077471784536e-05,
"loss": 1.6454,
"step": 759
},
{
"epoch": 0.33883192153366026,
"grad_norm": 0.23576031625270844,
"learning_rate": 6.94370241409666e-05,
"loss": 1.7647,
"step": 760
},
{
"epoch": 0.33927775300936247,
"grad_norm": 0.20360809564590454,
"learning_rate": 6.939319660711899e-05,
"loss": 1.6665,
"step": 761
},
{
"epoch": 0.3397235844850646,
"grad_norm": 0.21529042720794678,
"learning_rate": 6.934929223088049e-05,
"loss": 1.805,
"step": 762
},
{
"epoch": 0.34016941596076683,
"grad_norm": 0.22950305044651031,
"learning_rate": 6.930531112702993e-05,
"loss": 1.6865,
"step": 763
},
{
"epoch": 0.34061524743646904,
"grad_norm": 0.2098643183708191,
"learning_rate": 6.926125341054676e-05,
"loss": 1.7414,
"step": 764
},
{
"epoch": 0.3410610789121712,
"grad_norm": 0.2188938707113266,
"learning_rate": 6.921711919661071e-05,
"loss": 1.7158,
"step": 765
},
{
"epoch": 0.3415069103878734,
"grad_norm": 0.2061680257320404,
"learning_rate": 6.917290860060146e-05,
"loss": 1.6428,
"step": 766
},
{
"epoch": 0.34195274186357555,
"grad_norm": 0.2051788568496704,
"learning_rate": 6.912862173809844e-05,
"loss": 1.7216,
"step": 767
},
{
"epoch": 0.34239857333927776,
"grad_norm": 0.22325345873832703,
"learning_rate": 6.908425872488042e-05,
"loss": 1.7829,
"step": 768
},
{
"epoch": 0.34284440481497996,
"grad_norm": 0.2041957527399063,
"learning_rate": 6.903981967692524e-05,
"loss": 1.7991,
"step": 769
},
{
"epoch": 0.3432902362906821,
"grad_norm": 0.22522366046905518,
"learning_rate": 6.899530471040956e-05,
"loss": 1.6949,
"step": 770
},
{
"epoch": 0.3437360677663843,
"grad_norm": 0.21507549285888672,
"learning_rate": 6.895071394170847e-05,
"loss": 1.7102,
"step": 771
},
{
"epoch": 0.3441818992420865,
"grad_norm": 0.2359284907579422,
"learning_rate": 6.890604748739526e-05,
"loss": 1.7716,
"step": 772
},
{
"epoch": 0.3446277307177887,
"grad_norm": 0.2056940346956253,
"learning_rate": 6.886130546424106e-05,
"loss": 1.7614,
"step": 773
},
{
"epoch": 0.34507356219349083,
"grad_norm": 0.20665904879570007,
"learning_rate": 6.88164879892146e-05,
"loss": 1.7882,
"step": 774
},
{
"epoch": 0.34551939366919304,
"grad_norm": 0.21209891140460968,
"learning_rate": 6.87715951794818e-05,
"loss": 1.7265,
"step": 775
},
{
"epoch": 0.34596522514489525,
"grad_norm": 0.19885431230068207,
"learning_rate": 6.872662715240558e-05,
"loss": 1.6964,
"step": 776
},
{
"epoch": 0.3464110566205974,
"grad_norm": 0.2021333873271942,
"learning_rate": 6.868158402554546e-05,
"loss": 1.7327,
"step": 777
},
{
"epoch": 0.3468568880962996,
"grad_norm": 0.20405402779579163,
"learning_rate": 6.863646591665734e-05,
"loss": 1.733,
"step": 778
},
{
"epoch": 0.34730271957200176,
"grad_norm": 0.21486836671829224,
"learning_rate": 6.859127294369313e-05,
"loss": 1.8163,
"step": 779
},
{
"epoch": 0.34774855104770397,
"grad_norm": 0.2023477703332901,
"learning_rate": 6.85460052248004e-05,
"loss": 1.7342,
"step": 780
},
{
"epoch": 0.3481943825234062,
"grad_norm": 0.21515972912311554,
"learning_rate": 6.85006628783222e-05,
"loss": 1.7713,
"step": 781
},
{
"epoch": 0.34864021399910833,
"grad_norm": 0.20617273449897766,
"learning_rate": 6.845524602279668e-05,
"loss": 1.7489,
"step": 782
},
{
"epoch": 0.34908604547481054,
"grad_norm": 0.19855135679244995,
"learning_rate": 6.840975477695669e-05,
"loss": 1.7432,
"step": 783
},
{
"epoch": 0.3495318769505127,
"grad_norm": 0.21225327253341675,
"learning_rate": 6.836418925972967e-05,
"loss": 1.7179,
"step": 784
},
{
"epoch": 0.3499777084262149,
"grad_norm": 0.20852187275886536,
"learning_rate": 6.831854959023714e-05,
"loss": 1.6805,
"step": 785
},
{
"epoch": 0.3504235399019171,
"grad_norm": 0.2072257697582245,
"learning_rate": 6.827283588779451e-05,
"loss": 1.7291,
"step": 786
},
{
"epoch": 0.35086937137761925,
"grad_norm": 0.19819296896457672,
"learning_rate": 6.822704827191078e-05,
"loss": 1.6697,
"step": 787
},
{
"epoch": 0.35131520285332146,
"grad_norm": 0.22480206191539764,
"learning_rate": 6.81811868622881e-05,
"loss": 1.8037,
"step": 788
},
{
"epoch": 0.3517610343290236,
"grad_norm": 0.20416642725467682,
"learning_rate": 6.813525177882156e-05,
"loss": 1.7069,
"step": 789
},
{
"epoch": 0.3522068658047258,
"grad_norm": 0.2089570313692093,
"learning_rate": 6.808924314159889e-05,
"loss": 1.7296,
"step": 790
},
{
"epoch": 0.352652697280428,
"grad_norm": 0.2162252515554428,
"learning_rate": 6.804316107090009e-05,
"loss": 1.719,
"step": 791
},
{
"epoch": 0.3530985287561302,
"grad_norm": 0.21270179748535156,
"learning_rate": 6.799700568719714e-05,
"loss": 1.7671,
"step": 792
},
{
"epoch": 0.3535443602318324,
"grad_norm": 0.20561178028583527,
"learning_rate": 6.795077711115368e-05,
"loss": 1.6969,
"step": 793
},
{
"epoch": 0.35399019170753454,
"grad_norm": 0.19621388614177704,
"learning_rate": 6.790447546362467e-05,
"loss": 1.6404,
"step": 794
},
{
"epoch": 0.35443602318323675,
"grad_norm": 0.21053430438041687,
"learning_rate": 6.785810086565613e-05,
"loss": 1.7553,
"step": 795
},
{
"epoch": 0.3548818546589389,
"grad_norm": 0.20376941561698914,
"learning_rate": 6.781165343848482e-05,
"loss": 1.7597,
"step": 796
},
{
"epoch": 0.3553276861346411,
"grad_norm": 0.20846118032932281,
"learning_rate": 6.776513330353783e-05,
"loss": 1.7618,
"step": 797
},
{
"epoch": 0.3557735176103433,
"grad_norm": 0.21923816204071045,
"learning_rate": 6.771854058243239e-05,
"loss": 1.777,
"step": 798
},
{
"epoch": 0.35621934908604547,
"grad_norm": 0.2055412381887436,
"learning_rate": 6.767187539697544e-05,
"loss": 1.706,
"step": 799
},
{
"epoch": 0.3566651805617477,
"grad_norm": 0.21490585803985596,
"learning_rate": 6.762513786916341e-05,
"loss": 1.7621,
"step": 800
},
{
"epoch": 0.3571110120374498,
"grad_norm": 0.21446526050567627,
"learning_rate": 6.757832812118183e-05,
"loss": 1.6544,
"step": 801
},
{
"epoch": 0.35755684351315203,
"grad_norm": 0.20049992203712463,
"learning_rate": 6.753144627540503e-05,
"loss": 1.6754,
"step": 802
},
{
"epoch": 0.3580026749888542,
"grad_norm": 0.2026570439338684,
"learning_rate": 6.748449245439582e-05,
"loss": 1.6972,
"step": 803
},
{
"epoch": 0.3584485064645564,
"grad_norm": 0.2295822948217392,
"learning_rate": 6.743746678090521e-05,
"loss": 1.7813,
"step": 804
},
{
"epoch": 0.3588943379402586,
"grad_norm": 0.20751531422138214,
"learning_rate": 6.7390369377872e-05,
"loss": 1.6808,
"step": 805
},
{
"epoch": 0.35934016941596075,
"grad_norm": 0.2165253609418869,
"learning_rate": 6.734320036842259e-05,
"loss": 1.7764,
"step": 806
},
{
"epoch": 0.35978600089166296,
"grad_norm": 0.20914991199970245,
"learning_rate": 6.729595987587048e-05,
"loss": 1.7806,
"step": 807
},
{
"epoch": 0.3602318323673651,
"grad_norm": 0.21666984260082245,
"learning_rate": 6.724864802371613e-05,
"loss": 1.7888,
"step": 808
},
{
"epoch": 0.3606776638430673,
"grad_norm": 0.23241227865219116,
"learning_rate": 6.720126493564651e-05,
"loss": 1.8059,
"step": 809
},
{
"epoch": 0.3611234953187695,
"grad_norm": 0.20020677149295807,
"learning_rate": 6.715381073553484e-05,
"loss": 1.6864,
"step": 810
},
{
"epoch": 0.3615693267944717,
"grad_norm": 0.20438076555728912,
"learning_rate": 6.710628554744024e-05,
"loss": 1.6708,
"step": 811
},
{
"epoch": 0.3620151582701739,
"grad_norm": 0.21755672991275787,
"learning_rate": 6.705868949560743e-05,
"loss": 1.7963,
"step": 812
},
{
"epoch": 0.36246098974587604,
"grad_norm": 0.2186664640903473,
"learning_rate": 6.701102270446634e-05,
"loss": 1.7591,
"step": 813
},
{
"epoch": 0.36290682122157825,
"grad_norm": 0.2028367966413498,
"learning_rate": 6.696328529863193e-05,
"loss": 1.7197,
"step": 814
},
{
"epoch": 0.36335265269728045,
"grad_norm": 0.2205536663532257,
"learning_rate": 6.691547740290365e-05,
"loss": 1.6579,
"step": 815
},
{
"epoch": 0.3637984841729826,
"grad_norm": 0.19804279506206512,
"learning_rate": 6.68675991422653e-05,
"loss": 1.669,
"step": 816
},
{
"epoch": 0.3642443156486848,
"grad_norm": 0.21472683548927307,
"learning_rate": 6.681965064188463e-05,
"loss": 1.7421,
"step": 817
},
{
"epoch": 0.36469014712438697,
"grad_norm": 0.20572058856487274,
"learning_rate": 6.6771632027113e-05,
"loss": 1.6647,
"step": 818
},
{
"epoch": 0.3651359786000892,
"grad_norm": 0.21703673899173737,
"learning_rate": 6.672354342348508e-05,
"loss": 1.7923,
"step": 819
},
{
"epoch": 0.3655818100757913,
"grad_norm": 0.21246255934238434,
"learning_rate": 6.667538495671851e-05,
"loss": 1.6859,
"step": 820
},
{
"epoch": 0.36602764155149353,
"grad_norm": 0.19298550486564636,
"learning_rate": 6.662715675271358e-05,
"loss": 1.6656,
"step": 821
},
{
"epoch": 0.36647347302719574,
"grad_norm": 0.21339663863182068,
"learning_rate": 6.657885893755288e-05,
"loss": 1.7414,
"step": 822
},
{
"epoch": 0.3669193045028979,
"grad_norm": 0.21220877766609192,
"learning_rate": 6.653049163750098e-05,
"loss": 1.6884,
"step": 823
},
{
"epoch": 0.3673651359786001,
"grad_norm": 0.21043981611728668,
"learning_rate": 6.648205497900412e-05,
"loss": 1.7189,
"step": 824
},
{
"epoch": 0.36781096745430225,
"grad_norm": 0.2267450988292694,
"learning_rate": 6.643354908868985e-05,
"loss": 1.7781,
"step": 825
},
{
"epoch": 0.36825679893000446,
"grad_norm": 0.20768927037715912,
"learning_rate": 6.638497409336671e-05,
"loss": 1.6851,
"step": 826
},
{
"epoch": 0.36870263040570667,
"grad_norm": 0.20903393626213074,
"learning_rate": 6.633633012002392e-05,
"loss": 1.693,
"step": 827
},
{
"epoch": 0.3691484618814088,
"grad_norm": 0.21910394728183746,
"learning_rate": 6.628761729583104e-05,
"loss": 1.7055,
"step": 828
},
{
"epoch": 0.369594293357111,
"grad_norm": 0.19814462959766388,
"learning_rate": 6.623883574813758e-05,
"loss": 1.6605,
"step": 829
},
{
"epoch": 0.3700401248328132,
"grad_norm": 0.21070930361747742,
"learning_rate": 6.618998560447272e-05,
"loss": 1.6962,
"step": 830
},
{
"epoch": 0.3704859563085154,
"grad_norm": 0.20243875682353973,
"learning_rate": 6.614106699254502e-05,
"loss": 1.6691,
"step": 831
},
{
"epoch": 0.3709317877842176,
"grad_norm": 0.19810143113136292,
"learning_rate": 6.609208004024199e-05,
"loss": 1.6673,
"step": 832
},
{
"epoch": 0.37137761925991974,
"grad_norm": 0.2071191817522049,
"learning_rate": 6.604302487562981e-05,
"loss": 1.6635,
"step": 833
},
{
"epoch": 0.37182345073562195,
"grad_norm": 0.2069198191165924,
"learning_rate": 6.599390162695299e-05,
"loss": 1.8186,
"step": 834
},
{
"epoch": 0.3722692822113241,
"grad_norm": 0.20763137936592102,
"learning_rate": 6.594471042263404e-05,
"loss": 1.7275,
"step": 835
},
{
"epoch": 0.3727151136870263,
"grad_norm": 0.2052050232887268,
"learning_rate": 6.589545139127312e-05,
"loss": 1.6643,
"step": 836
},
{
"epoch": 0.37316094516272846,
"grad_norm": 0.21433968842029572,
"learning_rate": 6.58461246616477e-05,
"loss": 1.7497,
"step": 837
},
{
"epoch": 0.37360677663843067,
"grad_norm": 0.2157992571592331,
"learning_rate": 6.579673036271224e-05,
"loss": 1.7057,
"step": 838
},
{
"epoch": 0.3740526081141329,
"grad_norm": 0.20648705959320068,
"learning_rate": 6.574726862359785e-05,
"loss": 1.6205,
"step": 839
},
{
"epoch": 0.37449843958983503,
"grad_norm": 0.20061194896697998,
"learning_rate": 6.569773957361195e-05,
"loss": 1.6565,
"step": 840
},
{
"epoch": 0.37494427106553724,
"grad_norm": 0.21495498716831207,
"learning_rate": 6.564814334223793e-05,
"loss": 1.6354,
"step": 841
},
{
"epoch": 0.3753901025412394,
"grad_norm": 0.21777182817459106,
"learning_rate": 6.559848005913481e-05,
"loss": 1.7688,
"step": 842
},
{
"epoch": 0.3758359340169416,
"grad_norm": 0.22829119861125946,
"learning_rate": 6.554874985413689e-05,
"loss": 1.7521,
"step": 843
},
{
"epoch": 0.3762817654926438,
"grad_norm": 0.20866426825523376,
"learning_rate": 6.549895285725342e-05,
"loss": 1.6905,
"step": 844
},
{
"epoch": 0.37672759696834596,
"grad_norm": 0.22749756276607513,
"learning_rate": 6.544908919866831e-05,
"loss": 1.7736,
"step": 845
},
{
"epoch": 0.37717342844404816,
"grad_norm": 0.23048724234104156,
"learning_rate": 6.539915900873969e-05,
"loss": 1.7949,
"step": 846
},
{
"epoch": 0.3776192599197503,
"grad_norm": 0.21478885412216187,
"learning_rate": 6.534916241799965e-05,
"loss": 1.7441,
"step": 847
},
{
"epoch": 0.3780650913954525,
"grad_norm": 0.23727373778820038,
"learning_rate": 6.529909955715385e-05,
"loss": 1.7407,
"step": 848
},
{
"epoch": 0.3785109228711547,
"grad_norm": 0.21736378967761993,
"learning_rate": 6.524897055708123e-05,
"loss": 1.7306,
"step": 849
},
{
"epoch": 0.3789567543468569,
"grad_norm": 0.20656636357307434,
"learning_rate": 6.519877554883362e-05,
"loss": 1.7487,
"step": 850
},
{
"epoch": 0.3794025858225591,
"grad_norm": 0.21003365516662598,
"learning_rate": 6.51485146636354e-05,
"loss": 1.6466,
"step": 851
},
{
"epoch": 0.37984841729826124,
"grad_norm": 0.21377114951610565,
"learning_rate": 6.509818803288322e-05,
"loss": 1.7776,
"step": 852
},
{
"epoch": 0.38029424877396345,
"grad_norm": 0.2006235122680664,
"learning_rate": 6.504779578814552e-05,
"loss": 1.7191,
"step": 853
},
{
"epoch": 0.3807400802496656,
"grad_norm": 0.2083541452884674,
"learning_rate": 6.499733806116237e-05,
"loss": 1.7004,
"step": 854
},
{
"epoch": 0.3811859117253678,
"grad_norm": 0.20760244131088257,
"learning_rate": 6.494681498384497e-05,
"loss": 1.7231,
"step": 855
},
{
"epoch": 0.38163174320107,
"grad_norm": 0.21493734419345856,
"learning_rate": 6.48962266882754e-05,
"loss": 1.8476,
"step": 856
},
{
"epoch": 0.38207757467677217,
"grad_norm": 0.2154144048690796,
"learning_rate": 6.484557330670623e-05,
"loss": 1.7502,
"step": 857
},
{
"epoch": 0.3825234061524744,
"grad_norm": 0.21206477284431458,
"learning_rate": 6.479485497156015e-05,
"loss": 1.779,
"step": 858
},
{
"epoch": 0.38296923762817653,
"grad_norm": 0.20155435800552368,
"learning_rate": 6.474407181542969e-05,
"loss": 1.7466,
"step": 859
},
{
"epoch": 0.38341506910387874,
"grad_norm": 0.212468221783638,
"learning_rate": 6.469322397107685e-05,
"loss": 1.7478,
"step": 860
},
{
"epoch": 0.38386090057958094,
"grad_norm": 0.21040287613868713,
"learning_rate": 6.464231157143271e-05,
"loss": 1.7352,
"step": 861
},
{
"epoch": 0.3843067320552831,
"grad_norm": 0.2113109678030014,
"learning_rate": 6.459133474959715e-05,
"loss": 1.7363,
"step": 862
},
{
"epoch": 0.3847525635309853,
"grad_norm": 0.20767450332641602,
"learning_rate": 6.454029363883845e-05,
"loss": 1.7709,
"step": 863
},
{
"epoch": 0.38519839500668746,
"grad_norm": 0.20580929517745972,
"learning_rate": 6.448918837259297e-05,
"loss": 1.6631,
"step": 864
},
{
"epoch": 0.38564422648238966,
"grad_norm": 0.20532219111919403,
"learning_rate": 6.443801908446477e-05,
"loss": 1.6743,
"step": 865
},
{
"epoch": 0.3860900579580918,
"grad_norm": 0.20357473194599152,
"learning_rate": 6.43867859082253e-05,
"loss": 1.7709,
"step": 866
},
{
"epoch": 0.386535889433794,
"grad_norm": 0.20754805207252502,
"learning_rate": 6.433548897781303e-05,
"loss": 1.7029,
"step": 867
},
{
"epoch": 0.38698172090949623,
"grad_norm": 0.20898325741291046,
"learning_rate": 6.428412842733312e-05,
"loss": 1.7979,
"step": 868
},
{
"epoch": 0.3874275523851984,
"grad_norm": 0.2059037685394287,
"learning_rate": 6.423270439105702e-05,
"loss": 1.789,
"step": 869
},
{
"epoch": 0.3878733838609006,
"grad_norm": 0.2053404450416565,
"learning_rate": 6.418121700342214e-05,
"loss": 1.6802,
"step": 870
},
{
"epoch": 0.38831921533660274,
"grad_norm": 0.20702195167541504,
"learning_rate": 6.412966639903157e-05,
"loss": 1.7664,
"step": 871
},
{
"epoch": 0.38876504681230495,
"grad_norm": 0.20646905899047852,
"learning_rate": 6.407805271265361e-05,
"loss": 1.7266,
"step": 872
},
{
"epoch": 0.38921087828800716,
"grad_norm": 0.21376605331897736,
"learning_rate": 6.40263760792215e-05,
"loss": 1.6608,
"step": 873
},
{
"epoch": 0.3896567097637093,
"grad_norm": 0.20318657159805298,
"learning_rate": 6.397463663383302e-05,
"loss": 1.719,
"step": 874
},
{
"epoch": 0.3901025412394115,
"grad_norm": 0.20452015101909637,
"learning_rate": 6.392283451175019e-05,
"loss": 1.7949,
"step": 875
},
{
"epoch": 0.39054837271511367,
"grad_norm": 0.21763859689235687,
"learning_rate": 6.387096984839887e-05,
"loss": 1.6594,
"step": 876
},
{
"epoch": 0.3909942041908159,
"grad_norm": 0.21744206547737122,
"learning_rate": 6.38190427793684e-05,
"loss": 1.8175,
"step": 877
},
{
"epoch": 0.3914400356665181,
"grad_norm": 0.20281130075454712,
"learning_rate": 6.376705344041132e-05,
"loss": 1.7183,
"step": 878
},
{
"epoch": 0.39188586714222023,
"grad_norm": 0.21118947863578796,
"learning_rate": 6.371500196744291e-05,
"loss": 1.6888,
"step": 879
},
{
"epoch": 0.39233169861792244,
"grad_norm": 0.22375762462615967,
"learning_rate": 6.366288849654091e-05,
"loss": 1.7068,
"step": 880
},
{
"epoch": 0.3927775300936246,
"grad_norm": 0.23550164699554443,
"learning_rate": 6.361071316394512e-05,
"loss": 1.7814,
"step": 881
},
{
"epoch": 0.3932233615693268,
"grad_norm": 0.2262086272239685,
"learning_rate": 6.355847610605709e-05,
"loss": 1.6457,
"step": 882
},
{
"epoch": 0.39366919304502895,
"grad_norm": 0.21293623745441437,
"learning_rate": 6.350617745943975e-05,
"loss": 1.7592,
"step": 883
},
{
"epoch": 0.39411502452073116,
"grad_norm": 0.23403780162334442,
"learning_rate": 6.345381736081699e-05,
"loss": 1.7122,
"step": 884
},
{
"epoch": 0.39456085599643337,
"grad_norm": 0.22974692285060883,
"learning_rate": 6.34013959470734e-05,
"loss": 1.663,
"step": 885
},
{
"epoch": 0.3950066874721355,
"grad_norm": 0.20133690536022186,
"learning_rate": 6.334891335525385e-05,
"loss": 1.684,
"step": 886
},
{
"epoch": 0.39545251894783773,
"grad_norm": 0.22060684859752655,
"learning_rate": 6.329636972256314e-05,
"loss": 1.7129,
"step": 887
},
{
"epoch": 0.3958983504235399,
"grad_norm": 0.22694548964500427,
"learning_rate": 6.324376518636562e-05,
"loss": 1.7973,
"step": 888
},
{
"epoch": 0.3963441818992421,
"grad_norm": 0.20457105338573456,
"learning_rate": 6.319109988418497e-05,
"loss": 1.7433,
"step": 889
},
{
"epoch": 0.3967900133749443,
"grad_norm": 0.2157946079969406,
"learning_rate": 6.313837395370359e-05,
"loss": 1.7765,
"step": 890
},
{
"epoch": 0.39723584485064645,
"grad_norm": 0.20611245930194855,
"learning_rate": 6.308558753276248e-05,
"loss": 1.744,
"step": 891
},
{
"epoch": 0.39768167632634865,
"grad_norm": 0.20639915764331818,
"learning_rate": 6.303274075936073e-05,
"loss": 1.7489,
"step": 892
},
{
"epoch": 0.3981275078020508,
"grad_norm": 0.2307731956243515,
"learning_rate": 6.297983377165521e-05,
"loss": 1.7695,
"step": 893
},
{
"epoch": 0.398573339277753,
"grad_norm": 0.20785124599933624,
"learning_rate": 6.292686670796023e-05,
"loss": 1.7588,
"step": 894
},
{
"epoch": 0.3990191707534552,
"grad_norm": 0.20284093916416168,
"learning_rate": 6.287383970674716e-05,
"loss": 1.7078,
"step": 895
},
{
"epoch": 0.3994650022291574,
"grad_norm": 0.20751845836639404,
"learning_rate": 6.282075290664405e-05,
"loss": 1.7742,
"step": 896
},
{
"epoch": 0.3999108337048596,
"grad_norm": 0.21337181329727173,
"learning_rate": 6.276760644643528e-05,
"loss": 1.7026,
"step": 897
},
{
"epoch": 0.40035666518056173,
"grad_norm": 0.20509934425354004,
"learning_rate": 6.271440046506117e-05,
"loss": 1.7236,
"step": 898
},
{
"epoch": 0.40080249665626394,
"grad_norm": 0.20551203191280365,
"learning_rate": 6.266113510161772e-05,
"loss": 1.7098,
"step": 899
},
{
"epoch": 0.4012483281319661,
"grad_norm": 0.20775841176509857,
"learning_rate": 6.260781049535611e-05,
"loss": 1.7432,
"step": 900
}
],
"logging_steps": 1,
"max_steps": 2243,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 300,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.788311104356352e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}