caraxes / last-checkpoint /trainer_state.json
iamnguyen's picture
Training in progress, step 256, checkpoint
0c0ee93 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.01655073207492277,
"eval_steps": 500,
"global_step": 256,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.465129716766708e-05,
"grad_norm": 52.735591888427734,
"learning_rate": 6.451612903225807e-08,
"loss": 1.9276,
"step": 1
},
{
"epoch": 0.00012930259433533415,
"grad_norm": 54.205406188964844,
"learning_rate": 1.2903225806451614e-07,
"loss": 1.8498,
"step": 2
},
{
"epoch": 0.00019395389150300124,
"grad_norm": 55.422950744628906,
"learning_rate": 1.935483870967742e-07,
"loss": 2.0204,
"step": 3
},
{
"epoch": 0.0002586051886706683,
"grad_norm": 52.57908248901367,
"learning_rate": 2.580645161290323e-07,
"loss": 1.9851,
"step": 4
},
{
"epoch": 0.0003232564858383354,
"grad_norm": 53.102073669433594,
"learning_rate": 3.2258064516129035e-07,
"loss": 1.9575,
"step": 5
},
{
"epoch": 0.0003879077830060025,
"grad_norm": 39.96001052856445,
"learning_rate": 3.870967741935484e-07,
"loss": 1.9575,
"step": 6
},
{
"epoch": 0.00045255908017366957,
"grad_norm": 32.277435302734375,
"learning_rate": 4.5161290322580644e-07,
"loss": 1.8748,
"step": 7
},
{
"epoch": 0.0005172103773413366,
"grad_norm": 35.69306945800781,
"learning_rate": 5.161290322580646e-07,
"loss": 1.8319,
"step": 8
},
{
"epoch": 0.0005818616745090037,
"grad_norm": 32.267822265625,
"learning_rate": 5.806451612903227e-07,
"loss": 1.8492,
"step": 9
},
{
"epoch": 0.0006465129716766708,
"grad_norm": 15.390063285827637,
"learning_rate": 6.451612903225807e-07,
"loss": 1.8046,
"step": 10
},
{
"epoch": 0.0007111642688443379,
"grad_norm": 25.763904571533203,
"learning_rate": 7.096774193548388e-07,
"loss": 1.7649,
"step": 11
},
{
"epoch": 0.000775815566012005,
"grad_norm": 29.1771297454834,
"learning_rate": 7.741935483870968e-07,
"loss": 1.7684,
"step": 12
},
{
"epoch": 0.000840466863179672,
"grad_norm": 19.140987396240234,
"learning_rate": 8.38709677419355e-07,
"loss": 1.7782,
"step": 13
},
{
"epoch": 0.0009051181603473391,
"grad_norm": 13.840346336364746,
"learning_rate": 9.032258064516129e-07,
"loss": 1.8303,
"step": 14
},
{
"epoch": 0.0009697694575150061,
"grad_norm": 26.080778121948242,
"learning_rate": 9.67741935483871e-07,
"loss": 1.776,
"step": 15
},
{
"epoch": 0.0010344207546826732,
"grad_norm": 34.16382598876953,
"learning_rate": 1.0322580645161291e-06,
"loss": 1.6359,
"step": 16
},
{
"epoch": 0.0010990720518503404,
"grad_norm": 25.75543785095215,
"learning_rate": 1.0967741935483872e-06,
"loss": 1.6014,
"step": 17
},
{
"epoch": 0.0011637233490180074,
"grad_norm": 11.885198593139648,
"learning_rate": 1.1612903225806454e-06,
"loss": 1.6831,
"step": 18
},
{
"epoch": 0.0012283746461856746,
"grad_norm": 14.924345016479492,
"learning_rate": 1.2258064516129033e-06,
"loss": 1.7223,
"step": 19
},
{
"epoch": 0.0012930259433533416,
"grad_norm": 18.01887321472168,
"learning_rate": 1.2903225806451614e-06,
"loss": 1.6811,
"step": 20
},
{
"epoch": 0.0013576772405210086,
"grad_norm": 12.34964656829834,
"learning_rate": 1.3548387096774195e-06,
"loss": 1.6169,
"step": 21
},
{
"epoch": 0.0014223285376886757,
"grad_norm": 11.162965774536133,
"learning_rate": 1.4193548387096776e-06,
"loss": 1.6814,
"step": 22
},
{
"epoch": 0.0014869798348563427,
"grad_norm": 8.694445610046387,
"learning_rate": 1.4838709677419356e-06,
"loss": 1.5999,
"step": 23
},
{
"epoch": 0.00155163113202401,
"grad_norm": 9.510068893432617,
"learning_rate": 1.5483870967741937e-06,
"loss": 1.6327,
"step": 24
},
{
"epoch": 0.001616282429191677,
"grad_norm": 9.788911819458008,
"learning_rate": 1.6129032258064516e-06,
"loss": 1.6985,
"step": 25
},
{
"epoch": 0.001680933726359344,
"grad_norm": 8.04429817199707,
"learning_rate": 1.67741935483871e-06,
"loss": 1.6618,
"step": 26
},
{
"epoch": 0.001745585023527011,
"grad_norm": 7.545624256134033,
"learning_rate": 1.7419354838709678e-06,
"loss": 1.5472,
"step": 27
},
{
"epoch": 0.0018102363206946783,
"grad_norm": 7.069305419921875,
"learning_rate": 1.8064516129032258e-06,
"loss": 1.643,
"step": 28
},
{
"epoch": 0.0018748876178623453,
"grad_norm": 9.195314407348633,
"learning_rate": 1.870967741935484e-06,
"loss": 1.5956,
"step": 29
},
{
"epoch": 0.0019395389150300122,
"grad_norm": 6.884894371032715,
"learning_rate": 1.935483870967742e-06,
"loss": 1.5752,
"step": 30
},
{
"epoch": 0.0020041902121976794,
"grad_norm": 7.165380477905273,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.5812,
"step": 31
},
{
"epoch": 0.0020688415093653464,
"grad_norm": 6.563286781311035,
"learning_rate": 2.0645161290322582e-06,
"loss": 1.5938,
"step": 32
},
{
"epoch": 0.0021334928065330134,
"grad_norm": 5.998967170715332,
"learning_rate": 2.129032258064516e-06,
"loss": 1.5716,
"step": 33
},
{
"epoch": 0.002198144103700681,
"grad_norm": 6.407791614532471,
"learning_rate": 2.1935483870967745e-06,
"loss": 1.5848,
"step": 34
},
{
"epoch": 0.002262795400868348,
"grad_norm": 6.110191822052002,
"learning_rate": 2.2580645161290324e-06,
"loss": 1.643,
"step": 35
},
{
"epoch": 0.0023274466980360148,
"grad_norm": 6.058048248291016,
"learning_rate": 2.3225806451612907e-06,
"loss": 1.5242,
"step": 36
},
{
"epoch": 0.0023920979952036818,
"grad_norm": 7.348267078399658,
"learning_rate": 2.3870967741935486e-06,
"loss": 1.5112,
"step": 37
},
{
"epoch": 0.002456749292371349,
"grad_norm": 6.676770210266113,
"learning_rate": 2.4516129032258066e-06,
"loss": 1.5184,
"step": 38
},
{
"epoch": 0.002521400589539016,
"grad_norm": 9.655611038208008,
"learning_rate": 2.5161290322580645e-06,
"loss": 1.4867,
"step": 39
},
{
"epoch": 0.002586051886706683,
"grad_norm": 10.357527732849121,
"learning_rate": 2.580645161290323e-06,
"loss": 1.5255,
"step": 40
},
{
"epoch": 0.00265070318387435,
"grad_norm": 6.523240566253662,
"learning_rate": 2.645161290322581e-06,
"loss": 1.5326,
"step": 41
},
{
"epoch": 0.002715354481042017,
"grad_norm": 5.7459282875061035,
"learning_rate": 2.709677419354839e-06,
"loss": 1.5533,
"step": 42
},
{
"epoch": 0.0027800057782096845,
"grad_norm": 5.776258945465088,
"learning_rate": 2.774193548387097e-06,
"loss": 1.5261,
"step": 43
},
{
"epoch": 0.0028446570753773515,
"grad_norm": 7.176516056060791,
"learning_rate": 2.8387096774193553e-06,
"loss": 1.4434,
"step": 44
},
{
"epoch": 0.0029093083725450185,
"grad_norm": 6.083931922912598,
"learning_rate": 2.903225806451613e-06,
"loss": 1.5127,
"step": 45
},
{
"epoch": 0.0029739596697126855,
"grad_norm": 8.212278366088867,
"learning_rate": 2.967741935483871e-06,
"loss": 1.569,
"step": 46
},
{
"epoch": 0.003038610966880353,
"grad_norm": 6.138173580169678,
"learning_rate": 3.0322580645161295e-06,
"loss": 1.4985,
"step": 47
},
{
"epoch": 0.00310326226404802,
"grad_norm": 9.2051362991333,
"learning_rate": 3.0967741935483874e-06,
"loss": 1.4528,
"step": 48
},
{
"epoch": 0.003167913561215687,
"grad_norm": 9.6658353805542,
"learning_rate": 3.1612903225806453e-06,
"loss": 1.4432,
"step": 49
},
{
"epoch": 0.003232564858383354,
"grad_norm": 6.775389671325684,
"learning_rate": 3.225806451612903e-06,
"loss": 1.4649,
"step": 50
},
{
"epoch": 0.003297216155551021,
"grad_norm": 11.512835502624512,
"learning_rate": 3.2903225806451615e-06,
"loss": 1.4106,
"step": 51
},
{
"epoch": 0.003361867452718688,
"grad_norm": 5.44810676574707,
"learning_rate": 3.35483870967742e-06,
"loss": 1.4714,
"step": 52
},
{
"epoch": 0.003426518749886355,
"grad_norm": 6.4585185050964355,
"learning_rate": 3.4193548387096773e-06,
"loss": 1.5064,
"step": 53
},
{
"epoch": 0.003491170047054022,
"grad_norm": 8.523478507995605,
"learning_rate": 3.4838709677419357e-06,
"loss": 1.3392,
"step": 54
},
{
"epoch": 0.003555821344221689,
"grad_norm": 5.496897220611572,
"learning_rate": 3.548387096774194e-06,
"loss": 1.5616,
"step": 55
},
{
"epoch": 0.0036204726413893566,
"grad_norm": 8.096810340881348,
"learning_rate": 3.6129032258064515e-06,
"loss": 1.4941,
"step": 56
},
{
"epoch": 0.0036851239385570236,
"grad_norm": 6.6727705001831055,
"learning_rate": 3.67741935483871e-06,
"loss": 1.5466,
"step": 57
},
{
"epoch": 0.0037497752357246905,
"grad_norm": 7.022820949554443,
"learning_rate": 3.741935483870968e-06,
"loss": 1.4893,
"step": 58
},
{
"epoch": 0.0038144265328923575,
"grad_norm": 6.383000373840332,
"learning_rate": 3.8064516129032257e-06,
"loss": 1.4271,
"step": 59
},
{
"epoch": 0.0038790778300600245,
"grad_norm": 5.412594318389893,
"learning_rate": 3.870967741935484e-06,
"loss": 1.5204,
"step": 60
},
{
"epoch": 0.003943729127227692,
"grad_norm": 6.230757713317871,
"learning_rate": 3.935483870967742e-06,
"loss": 1.4508,
"step": 61
},
{
"epoch": 0.004008380424395359,
"grad_norm": 7.456300258636475,
"learning_rate": 4.000000000000001e-06,
"loss": 1.4439,
"step": 62
},
{
"epoch": 0.004073031721563026,
"grad_norm": 5.5062432289123535,
"learning_rate": 4.064516129032259e-06,
"loss": 1.4589,
"step": 63
},
{
"epoch": 0.004137683018730693,
"grad_norm": 6.719184398651123,
"learning_rate": 4.1290322580645165e-06,
"loss": 1.4779,
"step": 64
},
{
"epoch": 0.00420233431589836,
"grad_norm": 5.637788772583008,
"learning_rate": 4.193548387096774e-06,
"loss": 1.6323,
"step": 65
},
{
"epoch": 0.004266985613066027,
"grad_norm": 5.063558578491211,
"learning_rate": 4.258064516129032e-06,
"loss": 1.5131,
"step": 66
},
{
"epoch": 0.004331636910233695,
"grad_norm": 6.299156188964844,
"learning_rate": 4.32258064516129e-06,
"loss": 1.4999,
"step": 67
},
{
"epoch": 0.004396288207401362,
"grad_norm": 5.770033836364746,
"learning_rate": 4.387096774193549e-06,
"loss": 1.3813,
"step": 68
},
{
"epoch": 0.004460939504569029,
"grad_norm": 7.366373062133789,
"learning_rate": 4.451612903225807e-06,
"loss": 1.5073,
"step": 69
},
{
"epoch": 0.004525590801736696,
"grad_norm": 5.583267688751221,
"learning_rate": 4.516129032258065e-06,
"loss": 1.4769,
"step": 70
},
{
"epoch": 0.004590242098904363,
"grad_norm": 9.454716682434082,
"learning_rate": 4.580645161290323e-06,
"loss": 1.5203,
"step": 71
},
{
"epoch": 0.0046548933960720296,
"grad_norm": 6.360778331756592,
"learning_rate": 4.6451612903225815e-06,
"loss": 1.4848,
"step": 72
},
{
"epoch": 0.0047195446932396965,
"grad_norm": 4.729072093963623,
"learning_rate": 4.7096774193548385e-06,
"loss": 1.4475,
"step": 73
},
{
"epoch": 0.0047841959904073635,
"grad_norm": 6.975382328033447,
"learning_rate": 4.774193548387097e-06,
"loss": 1.5431,
"step": 74
},
{
"epoch": 0.0048488472875750305,
"grad_norm": 6.034017562866211,
"learning_rate": 4.838709677419355e-06,
"loss": 1.4028,
"step": 75
},
{
"epoch": 0.004913498584742698,
"grad_norm": 5.913821697235107,
"learning_rate": 4.903225806451613e-06,
"loss": 1.4364,
"step": 76
},
{
"epoch": 0.004978149881910365,
"grad_norm": 9.405481338500977,
"learning_rate": 4.967741935483871e-06,
"loss": 1.5207,
"step": 77
},
{
"epoch": 0.005042801179078032,
"grad_norm": 6.983378887176514,
"learning_rate": 5.032258064516129e-06,
"loss": 1.4487,
"step": 78
},
{
"epoch": 0.005107452476245699,
"grad_norm": 5.04365348815918,
"learning_rate": 5.096774193548387e-06,
"loss": 1.4282,
"step": 79
},
{
"epoch": 0.005172103773413366,
"grad_norm": 7.815653324127197,
"learning_rate": 5.161290322580646e-06,
"loss": 1.3231,
"step": 80
},
{
"epoch": 0.005236755070581033,
"grad_norm": 6.0287041664123535,
"learning_rate": 5.2258064516129035e-06,
"loss": 1.4106,
"step": 81
},
{
"epoch": 0.0053014063677487,
"grad_norm": 5.727312088012695,
"learning_rate": 5.290322580645162e-06,
"loss": 1.52,
"step": 82
},
{
"epoch": 0.005366057664916367,
"grad_norm": 4.75112771987915,
"learning_rate": 5.35483870967742e-06,
"loss": 1.434,
"step": 83
},
{
"epoch": 0.005430708962084034,
"grad_norm": 5.614027500152588,
"learning_rate": 5.419354838709678e-06,
"loss": 1.4501,
"step": 84
},
{
"epoch": 0.005495360259251702,
"grad_norm": 6.246868133544922,
"learning_rate": 5.483870967741935e-06,
"loss": 1.4065,
"step": 85
},
{
"epoch": 0.005560011556419369,
"grad_norm": 4.8930559158325195,
"learning_rate": 5.548387096774194e-06,
"loss": 1.4059,
"step": 86
},
{
"epoch": 0.005624662853587036,
"grad_norm": 9.081551551818848,
"learning_rate": 5.612903225806452e-06,
"loss": 1.4045,
"step": 87
},
{
"epoch": 0.005689314150754703,
"grad_norm": 6.593941688537598,
"learning_rate": 5.677419354838711e-06,
"loss": 1.4229,
"step": 88
},
{
"epoch": 0.00575396544792237,
"grad_norm": 4.863624095916748,
"learning_rate": 5.7419354838709685e-06,
"loss": 1.4073,
"step": 89
},
{
"epoch": 0.005818616745090037,
"grad_norm": 5.167389392852783,
"learning_rate": 5.806451612903226e-06,
"loss": 1.5046,
"step": 90
},
{
"epoch": 0.005883268042257704,
"grad_norm": 4.816722869873047,
"learning_rate": 5.8709677419354835e-06,
"loss": 1.4358,
"step": 91
},
{
"epoch": 0.005947919339425371,
"grad_norm": 5.505555629730225,
"learning_rate": 5.935483870967742e-06,
"loss": 1.5727,
"step": 92
},
{
"epoch": 0.006012570636593038,
"grad_norm": 5.764698505401611,
"learning_rate": 6e-06,
"loss": 1.4799,
"step": 93
},
{
"epoch": 0.006077221933760706,
"grad_norm": 5.312406063079834,
"learning_rate": 6.064516129032259e-06,
"loss": 1.5233,
"step": 94
},
{
"epoch": 0.006141873230928373,
"grad_norm": 6.0215253829956055,
"learning_rate": 6.129032258064517e-06,
"loss": 1.3764,
"step": 95
},
{
"epoch": 0.00620652452809604,
"grad_norm": 6.582176208496094,
"learning_rate": 6.193548387096775e-06,
"loss": 1.3687,
"step": 96
},
{
"epoch": 0.006271175825263707,
"grad_norm": 4.946031093597412,
"learning_rate": 6.2580645161290335e-06,
"loss": 1.4276,
"step": 97
},
{
"epoch": 0.006335827122431374,
"grad_norm": 5.586654186248779,
"learning_rate": 6.3225806451612906e-06,
"loss": 1.4366,
"step": 98
},
{
"epoch": 0.006400478419599041,
"grad_norm": 6.844956874847412,
"learning_rate": 6.3870967741935485e-06,
"loss": 1.3953,
"step": 99
},
{
"epoch": 0.006465129716766708,
"grad_norm": 5.709033012390137,
"learning_rate": 6.451612903225806e-06,
"loss": 1.441,
"step": 100
},
{
"epoch": 0.006529781013934375,
"grad_norm": 5.266170501708984,
"learning_rate": 6.516129032258065e-06,
"loss": 1.5336,
"step": 101
},
{
"epoch": 0.006594432311102042,
"grad_norm": 5.025949954986572,
"learning_rate": 6.580645161290323e-06,
"loss": 1.3602,
"step": 102
},
{
"epoch": 0.0066590836082697094,
"grad_norm": 6.4935126304626465,
"learning_rate": 6.645161290322582e-06,
"loss": 1.4612,
"step": 103
},
{
"epoch": 0.006723734905437376,
"grad_norm": 5.3272881507873535,
"learning_rate": 6.70967741935484e-06,
"loss": 1.4056,
"step": 104
},
{
"epoch": 0.006788386202605043,
"grad_norm": 5.2499213218688965,
"learning_rate": 6.774193548387097e-06,
"loss": 1.4908,
"step": 105
},
{
"epoch": 0.00685303749977271,
"grad_norm": 5.568053722381592,
"learning_rate": 6.838709677419355e-06,
"loss": 1.3711,
"step": 106
},
{
"epoch": 0.006917688796940377,
"grad_norm": 5.129876613616943,
"learning_rate": 6.9032258064516135e-06,
"loss": 1.3819,
"step": 107
},
{
"epoch": 0.006982340094108044,
"grad_norm": 6.102237224578857,
"learning_rate": 6.967741935483871e-06,
"loss": 1.4534,
"step": 108
},
{
"epoch": 0.007046991391275711,
"grad_norm": 6.690826892852783,
"learning_rate": 7.03225806451613e-06,
"loss": 1.3944,
"step": 109
},
{
"epoch": 0.007111642688443378,
"grad_norm": 4.548076629638672,
"learning_rate": 7.096774193548388e-06,
"loss": 1.5244,
"step": 110
},
{
"epoch": 0.007176293985611045,
"grad_norm": 4.901518821716309,
"learning_rate": 7.161290322580646e-06,
"loss": 1.4677,
"step": 111
},
{
"epoch": 0.007240945282778713,
"grad_norm": 5.2007155418396,
"learning_rate": 7.225806451612903e-06,
"loss": 1.4194,
"step": 112
},
{
"epoch": 0.00730559657994638,
"grad_norm": 5.50141716003418,
"learning_rate": 7.290322580645162e-06,
"loss": 1.4837,
"step": 113
},
{
"epoch": 0.007370247877114047,
"grad_norm": 5.740527153015137,
"learning_rate": 7.35483870967742e-06,
"loss": 1.5181,
"step": 114
},
{
"epoch": 0.007434899174281714,
"grad_norm": 6.510746002197266,
"learning_rate": 7.4193548387096784e-06,
"loss": 1.3614,
"step": 115
},
{
"epoch": 0.007499550471449381,
"grad_norm": 6.607003211975098,
"learning_rate": 7.483870967741936e-06,
"loss": 1.4396,
"step": 116
},
{
"epoch": 0.007564201768617048,
"grad_norm": 6.828821182250977,
"learning_rate": 7.548387096774194e-06,
"loss": 1.4888,
"step": 117
},
{
"epoch": 0.007628853065784715,
"grad_norm": 5.51243782043457,
"learning_rate": 7.612903225806451e-06,
"loss": 1.4666,
"step": 118
},
{
"epoch": 0.007693504362952382,
"grad_norm": 5.797337532043457,
"learning_rate": 7.67741935483871e-06,
"loss": 1.3761,
"step": 119
},
{
"epoch": 0.007758155660120049,
"grad_norm": 5.460038185119629,
"learning_rate": 7.741935483870968e-06,
"loss": 1.4361,
"step": 120
},
{
"epoch": 0.007822806957287716,
"grad_norm": 5.366038799285889,
"learning_rate": 7.806451612903227e-06,
"loss": 1.4087,
"step": 121
},
{
"epoch": 0.007887458254455384,
"grad_norm": 6.333535194396973,
"learning_rate": 7.870967741935484e-06,
"loss": 1.4527,
"step": 122
},
{
"epoch": 0.00795210955162305,
"grad_norm": 5.908946514129639,
"learning_rate": 7.935483870967743e-06,
"loss": 1.4128,
"step": 123
},
{
"epoch": 0.008016760848790718,
"grad_norm": 5.050029754638672,
"learning_rate": 8.000000000000001e-06,
"loss": 1.4311,
"step": 124
},
{
"epoch": 0.008081412145958386,
"grad_norm": 6.2919816970825195,
"learning_rate": 8.064516129032258e-06,
"loss": 1.3892,
"step": 125
},
{
"epoch": 0.008146063443126052,
"grad_norm": 5.789970874786377,
"learning_rate": 8.129032258064517e-06,
"loss": 1.4024,
"step": 126
},
{
"epoch": 0.00821071474029372,
"grad_norm": 5.259674549102783,
"learning_rate": 8.193548387096774e-06,
"loss": 1.3323,
"step": 127
},
{
"epoch": 0.008275366037461386,
"grad_norm": 5.545688152313232,
"learning_rate": 8.258064516129033e-06,
"loss": 1.332,
"step": 128
},
{
"epoch": 0.008340017334629054,
"grad_norm": 6.5449676513671875,
"learning_rate": 8.322580645161292e-06,
"loss": 1.3696,
"step": 129
},
{
"epoch": 0.00840466863179672,
"grad_norm": 4.6496806144714355,
"learning_rate": 8.387096774193549e-06,
"loss": 1.4208,
"step": 130
},
{
"epoch": 0.008469319928964388,
"grad_norm": 5.263716220855713,
"learning_rate": 8.451612903225808e-06,
"loss": 1.3825,
"step": 131
},
{
"epoch": 0.008533971226132054,
"grad_norm": 5.719542980194092,
"learning_rate": 8.516129032258065e-06,
"loss": 1.445,
"step": 132
},
{
"epoch": 0.008598622523299721,
"grad_norm": 4.548699855804443,
"learning_rate": 8.580645161290323e-06,
"loss": 1.3844,
"step": 133
},
{
"epoch": 0.00866327382046739,
"grad_norm": 4.696458339691162,
"learning_rate": 8.64516129032258e-06,
"loss": 1.3721,
"step": 134
},
{
"epoch": 0.008727925117635055,
"grad_norm": 5.142691612243652,
"learning_rate": 8.70967741935484e-06,
"loss": 1.3952,
"step": 135
},
{
"epoch": 0.008792576414802723,
"grad_norm": 4.870302677154541,
"learning_rate": 8.774193548387098e-06,
"loss": 1.462,
"step": 136
},
{
"epoch": 0.00885722771197039,
"grad_norm": 5.207381248474121,
"learning_rate": 8.838709677419357e-06,
"loss": 1.4555,
"step": 137
},
{
"epoch": 0.008921879009138057,
"grad_norm": 4.8738226890563965,
"learning_rate": 8.903225806451614e-06,
"loss": 1.3776,
"step": 138
},
{
"epoch": 0.008986530306305723,
"grad_norm": 5.064065456390381,
"learning_rate": 8.967741935483871e-06,
"loss": 1.4316,
"step": 139
},
{
"epoch": 0.009051181603473391,
"grad_norm": 5.246875286102295,
"learning_rate": 9.03225806451613e-06,
"loss": 1.5043,
"step": 140
},
{
"epoch": 0.009115832900641057,
"grad_norm": 5.119837284088135,
"learning_rate": 9.096774193548388e-06,
"loss": 1.4734,
"step": 141
},
{
"epoch": 0.009180484197808725,
"grad_norm": 6.316291332244873,
"learning_rate": 9.161290322580645e-06,
"loss": 1.4854,
"step": 142
},
{
"epoch": 0.009245135494976393,
"grad_norm": 4.688175201416016,
"learning_rate": 9.225806451612904e-06,
"loss": 1.4162,
"step": 143
},
{
"epoch": 0.009309786792144059,
"grad_norm": 5.010703086853027,
"learning_rate": 9.290322580645163e-06,
"loss": 1.3963,
"step": 144
},
{
"epoch": 0.009374438089311727,
"grad_norm": 4.959914207458496,
"learning_rate": 9.35483870967742e-06,
"loss": 1.3585,
"step": 145
},
{
"epoch": 0.009439089386479393,
"grad_norm": 4.275010585784912,
"learning_rate": 9.419354838709677e-06,
"loss": 1.4689,
"step": 146
},
{
"epoch": 0.009503740683647061,
"grad_norm": 4.852663040161133,
"learning_rate": 9.483870967741936e-06,
"loss": 1.4583,
"step": 147
},
{
"epoch": 0.009568391980814727,
"grad_norm": 4.935046195983887,
"learning_rate": 9.548387096774195e-06,
"loss": 1.4283,
"step": 148
},
{
"epoch": 0.009633043277982395,
"grad_norm": 4.662842273712158,
"learning_rate": 9.612903225806453e-06,
"loss": 1.4022,
"step": 149
},
{
"epoch": 0.009697694575150061,
"grad_norm": 6.32338285446167,
"learning_rate": 9.67741935483871e-06,
"loss": 1.4224,
"step": 150
},
{
"epoch": 0.009762345872317729,
"grad_norm": 4.785338401794434,
"learning_rate": 9.74193548387097e-06,
"loss": 1.4596,
"step": 151
},
{
"epoch": 0.009826997169485397,
"grad_norm": 4.482601642608643,
"learning_rate": 9.806451612903226e-06,
"loss": 1.4124,
"step": 152
},
{
"epoch": 0.009891648466653063,
"grad_norm": 4.771188259124756,
"learning_rate": 9.870967741935485e-06,
"loss": 1.4576,
"step": 153
},
{
"epoch": 0.00995629976382073,
"grad_norm": 4.497616291046143,
"learning_rate": 9.935483870967742e-06,
"loss": 1.4631,
"step": 154
},
{
"epoch": 0.010020951060988397,
"grad_norm": 4.109068870544434,
"learning_rate": 1e-05,
"loss": 1.403,
"step": 155
},
{
"epoch": 0.010085602358156065,
"grad_norm": 4.779379367828369,
"learning_rate": 9.999999894761194e-06,
"loss": 1.3295,
"step": 156
},
{
"epoch": 0.01015025365532373,
"grad_norm": 4.87537145614624,
"learning_rate": 9.999999579044782e-06,
"loss": 1.3468,
"step": 157
},
{
"epoch": 0.010214904952491399,
"grad_norm": 4.218890190124512,
"learning_rate": 9.999999052850775e-06,
"loss": 1.3863,
"step": 158
},
{
"epoch": 0.010279556249659065,
"grad_norm": 5.191406726837158,
"learning_rate": 9.999998316179195e-06,
"loss": 1.4638,
"step": 159
},
{
"epoch": 0.010344207546826733,
"grad_norm": 4.713414669036865,
"learning_rate": 9.999997369030074e-06,
"loss": 1.3629,
"step": 160
},
{
"epoch": 0.0104088588439944,
"grad_norm": 4.200235366821289,
"learning_rate": 9.999996211403454e-06,
"loss": 1.4429,
"step": 161
},
{
"epoch": 0.010473510141162067,
"grad_norm": 4.418542385101318,
"learning_rate": 9.999994843299381e-06,
"loss": 1.3971,
"step": 162
},
{
"epoch": 0.010538161438329734,
"grad_norm": 4.672099590301514,
"learning_rate": 9.999993264717911e-06,
"loss": 1.3352,
"step": 163
},
{
"epoch": 0.0106028127354974,
"grad_norm": 4.304332256317139,
"learning_rate": 9.999991475659115e-06,
"loss": 1.3116,
"step": 164
},
{
"epoch": 0.010667464032665068,
"grad_norm": 4.34376335144043,
"learning_rate": 9.999989476123067e-06,
"loss": 1.3822,
"step": 165
},
{
"epoch": 0.010732115329832734,
"grad_norm": 4.60739278793335,
"learning_rate": 9.999987266109848e-06,
"loss": 1.3655,
"step": 166
},
{
"epoch": 0.010796766627000402,
"grad_norm": 6.895850658416748,
"learning_rate": 9.999984845619553e-06,
"loss": 1.3699,
"step": 167
},
{
"epoch": 0.010861417924168068,
"grad_norm": 3.9377450942993164,
"learning_rate": 9.999982214652286e-06,
"loss": 1.4356,
"step": 168
},
{
"epoch": 0.010926069221335736,
"grad_norm": 4.687614440917969,
"learning_rate": 9.999979373208155e-06,
"loss": 1.3916,
"step": 169
},
{
"epoch": 0.010990720518503404,
"grad_norm": 4.686786651611328,
"learning_rate": 9.99997632128728e-06,
"loss": 1.3448,
"step": 170
},
{
"epoch": 0.01105537181567107,
"grad_norm": 4.827507495880127,
"learning_rate": 9.999973058889791e-06,
"loss": 1.3514,
"step": 171
},
{
"epoch": 0.011120023112838738,
"grad_norm": 4.3625617027282715,
"learning_rate": 9.999969586015824e-06,
"loss": 1.4232,
"step": 172
},
{
"epoch": 0.011184674410006404,
"grad_norm": 4.434966087341309,
"learning_rate": 9.999965902665524e-06,
"loss": 1.4217,
"step": 173
},
{
"epoch": 0.011249325707174072,
"grad_norm": 5.053067207336426,
"learning_rate": 9.99996200883905e-06,
"loss": 1.4709,
"step": 174
},
{
"epoch": 0.011313977004341738,
"grad_norm": 4.309473514556885,
"learning_rate": 9.999957904536562e-06,
"loss": 1.3668,
"step": 175
},
{
"epoch": 0.011378628301509406,
"grad_norm": 4.460648536682129,
"learning_rate": 9.999953589758235e-06,
"loss": 1.4512,
"step": 176
},
{
"epoch": 0.011443279598677072,
"grad_norm": 4.450823783874512,
"learning_rate": 9.99994906450425e-06,
"loss": 1.2986,
"step": 177
},
{
"epoch": 0.01150793089584474,
"grad_norm": 4.192991256713867,
"learning_rate": 9.999944328774796e-06,
"loss": 1.413,
"step": 178
},
{
"epoch": 0.011572582193012408,
"grad_norm": 4.157929420471191,
"learning_rate": 9.999939382570075e-06,
"loss": 1.4509,
"step": 179
},
{
"epoch": 0.011637233490180074,
"grad_norm": 3.6802518367767334,
"learning_rate": 9.999934225890294e-06,
"loss": 1.3918,
"step": 180
},
{
"epoch": 0.011701884787347742,
"grad_norm": 5.291732311248779,
"learning_rate": 9.999928858735668e-06,
"loss": 1.4045,
"step": 181
},
{
"epoch": 0.011766536084515408,
"grad_norm": 4.054734230041504,
"learning_rate": 9.999923281106427e-06,
"loss": 1.3101,
"step": 182
},
{
"epoch": 0.011831187381683076,
"grad_norm": 4.11862325668335,
"learning_rate": 9.999917493002803e-06,
"loss": 1.4398,
"step": 183
},
{
"epoch": 0.011895838678850742,
"grad_norm": 4.4882307052612305,
"learning_rate": 9.999911494425041e-06,
"loss": 1.3585,
"step": 184
},
{
"epoch": 0.01196048997601841,
"grad_norm": 4.65657377243042,
"learning_rate": 9.999905285373392e-06,
"loss": 1.3673,
"step": 185
},
{
"epoch": 0.012025141273186076,
"grad_norm": 3.629178047180176,
"learning_rate": 9.999898865848119e-06,
"loss": 1.4998,
"step": 186
},
{
"epoch": 0.012089792570353744,
"grad_norm": 4.499670028686523,
"learning_rate": 9.99989223584949e-06,
"loss": 1.4083,
"step": 187
},
{
"epoch": 0.012154443867521411,
"grad_norm": 4.342660427093506,
"learning_rate": 9.999885395377788e-06,
"loss": 1.3362,
"step": 188
},
{
"epoch": 0.012219095164689078,
"grad_norm": 4.276759147644043,
"learning_rate": 9.999878344433297e-06,
"loss": 1.3912,
"step": 189
},
{
"epoch": 0.012283746461856745,
"grad_norm": 3.7648189067840576,
"learning_rate": 9.999871083016316e-06,
"loss": 1.3583,
"step": 190
},
{
"epoch": 0.012348397759024412,
"grad_norm": 4.836668491363525,
"learning_rate": 9.999863611127149e-06,
"loss": 1.3465,
"step": 191
},
{
"epoch": 0.01241304905619208,
"grad_norm": 4.41436767578125,
"learning_rate": 9.999855928766113e-06,
"loss": 1.4314,
"step": 192
},
{
"epoch": 0.012477700353359746,
"grad_norm": 3.9474074840545654,
"learning_rate": 9.99984803593353e-06,
"loss": 1.4435,
"step": 193
},
{
"epoch": 0.012542351650527413,
"grad_norm": 4.373626232147217,
"learning_rate": 9.999839932629732e-06,
"loss": 1.3644,
"step": 194
},
{
"epoch": 0.01260700294769508,
"grad_norm": 4.185675621032715,
"learning_rate": 9.999831618855058e-06,
"loss": 1.3399,
"step": 195
},
{
"epoch": 0.012671654244862747,
"grad_norm": 4.8992109298706055,
"learning_rate": 9.999823094609862e-06,
"loss": 1.2623,
"step": 196
},
{
"epoch": 0.012736305542030415,
"grad_norm": 4.317060470581055,
"learning_rate": 9.999814359894501e-06,
"loss": 1.5297,
"step": 197
},
{
"epoch": 0.012800956839198081,
"grad_norm": 4.501911640167236,
"learning_rate": 9.999805414709344e-06,
"loss": 1.4305,
"step": 198
},
{
"epoch": 0.01286560813636575,
"grad_norm": 4.288606643676758,
"learning_rate": 9.999796259054765e-06,
"loss": 1.4358,
"step": 199
},
{
"epoch": 0.012930259433533415,
"grad_norm": 4.692774772644043,
"learning_rate": 9.99978689293115e-06,
"loss": 1.4448,
"step": 200
},
{
"epoch": 0.012994910730701083,
"grad_norm": 4.893410682678223,
"learning_rate": 9.999777316338897e-06,
"loss": 1.4313,
"step": 201
},
{
"epoch": 0.01305956202786875,
"grad_norm": 4.01968240737915,
"learning_rate": 9.999767529278403e-06,
"loss": 1.3831,
"step": 202
},
{
"epoch": 0.013124213325036417,
"grad_norm": 4.3122076988220215,
"learning_rate": 9.999757531750086e-06,
"loss": 1.3605,
"step": 203
},
{
"epoch": 0.013188864622204083,
"grad_norm": 3.9625604152679443,
"learning_rate": 9.999747323754363e-06,
"loss": 1.2944,
"step": 204
},
{
"epoch": 0.013253515919371751,
"grad_norm": 4.135870456695557,
"learning_rate": 9.999736905291664e-06,
"loss": 1.3465,
"step": 205
},
{
"epoch": 0.013318167216539419,
"grad_norm": 3.485560655593872,
"learning_rate": 9.999726276362429e-06,
"loss": 1.4901,
"step": 206
},
{
"epoch": 0.013382818513707085,
"grad_norm": 4.223531246185303,
"learning_rate": 9.999715436967104e-06,
"loss": 1.4342,
"step": 207
},
{
"epoch": 0.013447469810874753,
"grad_norm": 4.688872814178467,
"learning_rate": 9.999704387106147e-06,
"loss": 1.3735,
"step": 208
},
{
"epoch": 0.013512121108042419,
"grad_norm": 4.388930320739746,
"learning_rate": 9.999693126780022e-06,
"loss": 1.4288,
"step": 209
},
{
"epoch": 0.013576772405210087,
"grad_norm": 3.7054548263549805,
"learning_rate": 9.999681655989203e-06,
"loss": 1.3322,
"step": 210
},
{
"epoch": 0.013641423702377753,
"grad_norm": 4.013354778289795,
"learning_rate": 9.999669974734172e-06,
"loss": 1.4192,
"step": 211
},
{
"epoch": 0.01370607499954542,
"grad_norm": 4.022690773010254,
"learning_rate": 9.999658083015423e-06,
"loss": 1.3474,
"step": 212
},
{
"epoch": 0.013770726296713087,
"grad_norm": 3.8308322429656982,
"learning_rate": 9.999645980833454e-06,
"loss": 1.3902,
"step": 213
},
{
"epoch": 0.013835377593880755,
"grad_norm": 4.453736305236816,
"learning_rate": 9.999633668188778e-06,
"loss": 1.4876,
"step": 214
},
{
"epoch": 0.013900028891048423,
"grad_norm": 4.379161834716797,
"learning_rate": 9.99962114508191e-06,
"loss": 1.369,
"step": 215
},
{
"epoch": 0.013964680188216089,
"grad_norm": 4.23476505279541,
"learning_rate": 9.999608411513378e-06,
"loss": 1.371,
"step": 216
},
{
"epoch": 0.014029331485383757,
"grad_norm": 3.8091630935668945,
"learning_rate": 9.999595467483719e-06,
"loss": 1.3317,
"step": 217
},
{
"epoch": 0.014093982782551423,
"grad_norm": 4.4740118980407715,
"learning_rate": 9.999582312993476e-06,
"loss": 1.3864,
"step": 218
},
{
"epoch": 0.01415863407971909,
"grad_norm": 3.8283002376556396,
"learning_rate": 9.999568948043206e-06,
"loss": 1.3924,
"step": 219
},
{
"epoch": 0.014223285376886757,
"grad_norm": 3.9413399696350098,
"learning_rate": 9.99955537263347e-06,
"loss": 1.365,
"step": 220
},
{
"epoch": 0.014287936674054424,
"grad_norm": 3.7700750827789307,
"learning_rate": 9.999541586764836e-06,
"loss": 1.3265,
"step": 221
},
{
"epoch": 0.01435258797122209,
"grad_norm": 4.468739986419678,
"learning_rate": 9.999527590437889e-06,
"loss": 1.4056,
"step": 222
},
{
"epoch": 0.014417239268389758,
"grad_norm": 3.847881555557251,
"learning_rate": 9.999513383653216e-06,
"loss": 1.3369,
"step": 223
},
{
"epoch": 0.014481890565557426,
"grad_norm": 4.515076637268066,
"learning_rate": 9.999498966411415e-06,
"loss": 1.3715,
"step": 224
},
{
"epoch": 0.014546541862725092,
"grad_norm": 4.114704608917236,
"learning_rate": 9.999484338713096e-06,
"loss": 1.376,
"step": 225
},
{
"epoch": 0.01461119315989276,
"grad_norm": 4.159117221832275,
"learning_rate": 9.999469500558872e-06,
"loss": 1.3388,
"step": 226
},
{
"epoch": 0.014675844457060426,
"grad_norm": 4.336222171783447,
"learning_rate": 9.999454451949364e-06,
"loss": 1.3121,
"step": 227
},
{
"epoch": 0.014740495754228094,
"grad_norm": 3.4951186180114746,
"learning_rate": 9.999439192885212e-06,
"loss": 1.3861,
"step": 228
},
{
"epoch": 0.01480514705139576,
"grad_norm": 4.519493579864502,
"learning_rate": 9.999423723367056e-06,
"loss": 1.3151,
"step": 229
},
{
"epoch": 0.014869798348563428,
"grad_norm": 3.895230770111084,
"learning_rate": 9.999408043395546e-06,
"loss": 1.3877,
"step": 230
},
{
"epoch": 0.014934449645731094,
"grad_norm": 3.6650257110595703,
"learning_rate": 9.999392152971344e-06,
"loss": 1.3744,
"step": 231
},
{
"epoch": 0.014999100942898762,
"grad_norm": 4.416625022888184,
"learning_rate": 9.999376052095117e-06,
"loss": 1.2943,
"step": 232
},
{
"epoch": 0.01506375224006643,
"grad_norm": 4.903157711029053,
"learning_rate": 9.999359740767545e-06,
"loss": 1.3302,
"step": 233
},
{
"epoch": 0.015128403537234096,
"grad_norm": 4.176599502563477,
"learning_rate": 9.999343218989313e-06,
"loss": 1.3421,
"step": 234
},
{
"epoch": 0.015193054834401764,
"grad_norm": 4.2415876388549805,
"learning_rate": 9.999326486761114e-06,
"loss": 1.3693,
"step": 235
},
{
"epoch": 0.01525770613156943,
"grad_norm": 4.100305080413818,
"learning_rate": 9.999309544083657e-06,
"loss": 1.3251,
"step": 236
},
{
"epoch": 0.015322357428737098,
"grad_norm": 3.9971888065338135,
"learning_rate": 9.999292390957653e-06,
"loss": 1.4118,
"step": 237
},
{
"epoch": 0.015387008725904764,
"grad_norm": 4.218728065490723,
"learning_rate": 9.999275027383826e-06,
"loss": 1.371,
"step": 238
},
{
"epoch": 0.015451660023072432,
"grad_norm": 5.075481414794922,
"learning_rate": 9.999257453362903e-06,
"loss": 1.3753,
"step": 239
},
{
"epoch": 0.015516311320240098,
"grad_norm": 4.296051025390625,
"learning_rate": 9.999239668895627e-06,
"loss": 1.4116,
"step": 240
},
{
"epoch": 0.015580962617407766,
"grad_norm": 4.260445594787598,
"learning_rate": 9.999221673982747e-06,
"loss": 1.3179,
"step": 241
},
{
"epoch": 0.015645613914575432,
"grad_norm": 4.778342247009277,
"learning_rate": 9.999203468625017e-06,
"loss": 1.3185,
"step": 242
},
{
"epoch": 0.0157102652117431,
"grad_norm": 3.723858594894409,
"learning_rate": 9.999185052823207e-06,
"loss": 1.3,
"step": 243
},
{
"epoch": 0.015774916508910768,
"grad_norm": 3.748918294906616,
"learning_rate": 9.99916642657809e-06,
"loss": 1.455,
"step": 244
},
{
"epoch": 0.015839567806078435,
"grad_norm": 4.436662197113037,
"learning_rate": 9.999147589890452e-06,
"loss": 1.3895,
"step": 245
},
{
"epoch": 0.0159042191032461,
"grad_norm": 4.519418716430664,
"learning_rate": 9.999128542761085e-06,
"loss": 1.2948,
"step": 246
},
{
"epoch": 0.015968870400413768,
"grad_norm": 4.407564640045166,
"learning_rate": 9.99910928519079e-06,
"loss": 1.5275,
"step": 247
},
{
"epoch": 0.016033521697581436,
"grad_norm": 4.254813194274902,
"learning_rate": 9.999089817180378e-06,
"loss": 1.3428,
"step": 248
},
{
"epoch": 0.016098172994749103,
"grad_norm": 4.610138893127441,
"learning_rate": 9.999070138730668e-06,
"loss": 1.3733,
"step": 249
},
{
"epoch": 0.01616282429191677,
"grad_norm": 3.6939423084259033,
"learning_rate": 9.99905024984249e-06,
"loss": 1.3943,
"step": 250
},
{
"epoch": 0.016227475589084436,
"grad_norm": 3.755028247833252,
"learning_rate": 9.999030150516681e-06,
"loss": 1.4256,
"step": 251
},
{
"epoch": 0.016292126886252103,
"grad_norm": 4.2649149894714355,
"learning_rate": 9.999009840754085e-06,
"loss": 1.4257,
"step": 252
},
{
"epoch": 0.01635677818341977,
"grad_norm": 3.718479633331299,
"learning_rate": 9.998989320555562e-06,
"loss": 1.3312,
"step": 253
},
{
"epoch": 0.01642142948058744,
"grad_norm": 3.7253224849700928,
"learning_rate": 9.998968589921969e-06,
"loss": 1.37,
"step": 254
},
{
"epoch": 0.016486080777755104,
"grad_norm": 3.8125829696655273,
"learning_rate": 9.998947648854182e-06,
"loss": 1.3721,
"step": 255
},
{
"epoch": 0.01655073207492277,
"grad_norm": 4.105193138122559,
"learning_rate": 9.998926497353084e-06,
"loss": 1.3238,
"step": 256
}
],
"logging_steps": 1,
"max_steps": 15467,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.637374085936087e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}