eeve-10.8B_A / trainer_state.json
c10's picture
Model save
1cf5512 verified
raw
history blame contribute delete
No virus
68 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 387,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002583979328165375,
"grad_norm": 62.7838249206543,
"learning_rate": 2.564102564102564e-07,
"loss": 1.8986,
"step": 1
},
{
"epoch": 0.00516795865633075,
"grad_norm": 64.10289001464844,
"learning_rate": 5.128205128205128e-07,
"loss": 1.8868,
"step": 2
},
{
"epoch": 0.007751937984496124,
"grad_norm": 64.08220672607422,
"learning_rate": 7.692307692307694e-07,
"loss": 1.9136,
"step": 3
},
{
"epoch": 0.0103359173126615,
"grad_norm": 57.040557861328125,
"learning_rate": 1.0256410256410257e-06,
"loss": 1.7739,
"step": 4
},
{
"epoch": 0.012919896640826873,
"grad_norm": 49.75514602661133,
"learning_rate": 1.282051282051282e-06,
"loss": 1.5788,
"step": 5
},
{
"epoch": 0.015503875968992248,
"grad_norm": 55.35374450683594,
"learning_rate": 1.5384615384615387e-06,
"loss": 1.1322,
"step": 6
},
{
"epoch": 0.01808785529715762,
"grad_norm": 40.152645111083984,
"learning_rate": 1.794871794871795e-06,
"loss": 0.8061,
"step": 7
},
{
"epoch": 0.020671834625323,
"grad_norm": 38.397464752197266,
"learning_rate": 2.0512820512820513e-06,
"loss": 0.5469,
"step": 8
},
{
"epoch": 0.023255813953488372,
"grad_norm": 18.86681365966797,
"learning_rate": 2.307692307692308e-06,
"loss": 0.4388,
"step": 9
},
{
"epoch": 0.025839793281653745,
"grad_norm": 48.16230773925781,
"learning_rate": 2.564102564102564e-06,
"loss": 0.4077,
"step": 10
},
{
"epoch": 0.028423772609819122,
"grad_norm": 38.27500534057617,
"learning_rate": 2.8205128205128207e-06,
"loss": 0.374,
"step": 11
},
{
"epoch": 0.031007751937984496,
"grad_norm": 10.813103675842285,
"learning_rate": 3.0769230769230774e-06,
"loss": 0.3252,
"step": 12
},
{
"epoch": 0.03359173126614987,
"grad_norm": 32.890769958496094,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.3145,
"step": 13
},
{
"epoch": 0.03617571059431524,
"grad_norm": 20.16728973388672,
"learning_rate": 3.58974358974359e-06,
"loss": 0.3279,
"step": 14
},
{
"epoch": 0.03875968992248062,
"grad_norm": 37.158111572265625,
"learning_rate": 3.846153846153847e-06,
"loss": 0.3358,
"step": 15
},
{
"epoch": 0.041343669250646,
"grad_norm": 10.882681846618652,
"learning_rate": 4.102564102564103e-06,
"loss": 0.2804,
"step": 16
},
{
"epoch": 0.04392764857881137,
"grad_norm": 57.284584045410156,
"learning_rate": 4.358974358974359e-06,
"loss": 0.3743,
"step": 17
},
{
"epoch": 0.046511627906976744,
"grad_norm": 93.74513244628906,
"learning_rate": 4.615384615384616e-06,
"loss": 0.2806,
"step": 18
},
{
"epoch": 0.04909560723514212,
"grad_norm": 123.45682525634766,
"learning_rate": 4.871794871794872e-06,
"loss": 0.4188,
"step": 19
},
{
"epoch": 0.05167958656330749,
"grad_norm": 35.84373474121094,
"learning_rate": 5.128205128205128e-06,
"loss": 0.4117,
"step": 20
},
{
"epoch": 0.05426356589147287,
"grad_norm": 49.38902282714844,
"learning_rate": 5.384615384615385e-06,
"loss": 0.3442,
"step": 21
},
{
"epoch": 0.056847545219638244,
"grad_norm": 19.53158187866211,
"learning_rate": 5.641025641025641e-06,
"loss": 0.2894,
"step": 22
},
{
"epoch": 0.059431524547803614,
"grad_norm": 12.666043281555176,
"learning_rate": 5.897435897435898e-06,
"loss": 0.3197,
"step": 23
},
{
"epoch": 0.06201550387596899,
"grad_norm": 52.884456634521484,
"learning_rate": 6.153846153846155e-06,
"loss": 0.3199,
"step": 24
},
{
"epoch": 0.06459948320413436,
"grad_norm": 5.781566619873047,
"learning_rate": 6.410256410256412e-06,
"loss": 0.2521,
"step": 25
},
{
"epoch": 0.06718346253229975,
"grad_norm": 3.7365846633911133,
"learning_rate": 6.666666666666667e-06,
"loss": 0.2781,
"step": 26
},
{
"epoch": 0.06976744186046512,
"grad_norm": 4.0676984786987305,
"learning_rate": 6.923076923076923e-06,
"loss": 0.2917,
"step": 27
},
{
"epoch": 0.07235142118863049,
"grad_norm": 5.059348106384277,
"learning_rate": 7.17948717948718e-06,
"loss": 0.2666,
"step": 28
},
{
"epoch": 0.07493540051679587,
"grad_norm": 3.9822773933410645,
"learning_rate": 7.435897435897437e-06,
"loss": 0.2698,
"step": 29
},
{
"epoch": 0.07751937984496124,
"grad_norm": 3.6662659645080566,
"learning_rate": 7.692307692307694e-06,
"loss": 0.2721,
"step": 30
},
{
"epoch": 0.08010335917312661,
"grad_norm": 3.566708564758301,
"learning_rate": 7.948717948717949e-06,
"loss": 0.2911,
"step": 31
},
{
"epoch": 0.082687338501292,
"grad_norm": 3.4506027698516846,
"learning_rate": 8.205128205128205e-06,
"loss": 0.2726,
"step": 32
},
{
"epoch": 0.08527131782945736,
"grad_norm": 2.4874958992004395,
"learning_rate": 8.461538461538462e-06,
"loss": 0.2268,
"step": 33
},
{
"epoch": 0.08785529715762273,
"grad_norm": 4.3625593185424805,
"learning_rate": 8.717948717948719e-06,
"loss": 0.2766,
"step": 34
},
{
"epoch": 0.09043927648578812,
"grad_norm": 3.773474931716919,
"learning_rate": 8.974358974358976e-06,
"loss": 0.2716,
"step": 35
},
{
"epoch": 0.09302325581395349,
"grad_norm": 2.7108590602874756,
"learning_rate": 9.230769230769232e-06,
"loss": 0.2393,
"step": 36
},
{
"epoch": 0.09560723514211886,
"grad_norm": 2.9571542739868164,
"learning_rate": 9.487179487179487e-06,
"loss": 0.2368,
"step": 37
},
{
"epoch": 0.09819121447028424,
"grad_norm": 3.408618688583374,
"learning_rate": 9.743589743589744e-06,
"loss": 0.2746,
"step": 38
},
{
"epoch": 0.10077519379844961,
"grad_norm": 3.4680657386779785,
"learning_rate": 1e-05,
"loss": 0.309,
"step": 39
},
{
"epoch": 0.10335917312661498,
"grad_norm": 2.9482579231262207,
"learning_rate": 9.999796259054765e-06,
"loss": 0.2705,
"step": 40
},
{
"epoch": 0.10594315245478036,
"grad_norm": 2.75227427482605,
"learning_rate": 9.999185052823207e-06,
"loss": 0.2693,
"step": 41
},
{
"epoch": 0.10852713178294573,
"grad_norm": 3.2529563903808594,
"learning_rate": 9.998166431116421e-06,
"loss": 0.2803,
"step": 42
},
{
"epoch": 0.1111111111111111,
"grad_norm": 3.7899768352508545,
"learning_rate": 9.996740476948386e-06,
"loss": 0.2532,
"step": 43
},
{
"epoch": 0.11369509043927649,
"grad_norm": 3.1697609424591064,
"learning_rate": 9.994907306529203e-06,
"loss": 0.305,
"step": 44
},
{
"epoch": 0.11627906976744186,
"grad_norm": 11.274734497070312,
"learning_rate": 9.99266706925562e-06,
"loss": 0.2741,
"step": 45
},
{
"epoch": 0.11886304909560723,
"grad_norm": 2.9524729251861572,
"learning_rate": 9.990019947698864e-06,
"loss": 0.2557,
"step": 46
},
{
"epoch": 0.12144702842377261,
"grad_norm": 2.668808698654175,
"learning_rate": 9.986966157589751e-06,
"loss": 0.2625,
"step": 47
},
{
"epoch": 0.12403100775193798,
"grad_norm": 2.914754629135132,
"learning_rate": 9.983505947801115e-06,
"loss": 0.2967,
"step": 48
},
{
"epoch": 0.12661498708010335,
"grad_norm": 33.38725662231445,
"learning_rate": 9.979639600327522e-06,
"loss": 0.3238,
"step": 49
},
{
"epoch": 0.12919896640826872,
"grad_norm": 6.390991687774658,
"learning_rate": 9.975367430262289e-06,
"loss": 0.32,
"step": 50
},
{
"epoch": 0.13178294573643412,
"grad_norm": 3.03119158744812,
"learning_rate": 9.970689785771798e-06,
"loss": 0.2721,
"step": 51
},
{
"epoch": 0.1343669250645995,
"grad_norm": 2.6381173133850098,
"learning_rate": 9.965607048067138e-06,
"loss": 0.2948,
"step": 52
},
{
"epoch": 0.13695090439276486,
"grad_norm": 2.643310308456421,
"learning_rate": 9.960119631373023e-06,
"loss": 0.2734,
"step": 53
},
{
"epoch": 0.13953488372093023,
"grad_norm": 2.6558730602264404,
"learning_rate": 9.954227982894034e-06,
"loss": 0.24,
"step": 54
},
{
"epoch": 0.1421188630490956,
"grad_norm": 2.789214849472046,
"learning_rate": 9.947932582778188e-06,
"loss": 0.2775,
"step": 55
},
{
"epoch": 0.14470284237726097,
"grad_norm": 2.645108699798584,
"learning_rate": 9.941233944077789e-06,
"loss": 0.2572,
"step": 56
},
{
"epoch": 0.14728682170542637,
"grad_norm": 3.7391746044158936,
"learning_rate": 9.934132612707631e-06,
"loss": 0.2821,
"step": 57
},
{
"epoch": 0.14987080103359174,
"grad_norm": 2.756499767303467,
"learning_rate": 9.9266291674005e-06,
"loss": 0.3018,
"step": 58
},
{
"epoch": 0.1524547803617571,
"grad_norm": 2.3780715465545654,
"learning_rate": 9.918724219660013e-06,
"loss": 0.2512,
"step": 59
},
{
"epoch": 0.15503875968992248,
"grad_norm": 2.6783838272094727,
"learning_rate": 9.91041841371078e-06,
"loss": 0.2781,
"step": 60
},
{
"epoch": 0.15762273901808785,
"grad_norm": 2.859645366668701,
"learning_rate": 9.901712426445901e-06,
"loss": 0.2558,
"step": 61
},
{
"epoch": 0.16020671834625322,
"grad_norm": 2.2829370498657227,
"learning_rate": 9.892606967371808e-06,
"loss": 0.2794,
"step": 62
},
{
"epoch": 0.16279069767441862,
"grad_norm": 2.7090861797332764,
"learning_rate": 9.883102778550434e-06,
"loss": 0.2788,
"step": 63
},
{
"epoch": 0.165374677002584,
"grad_norm": 2.501798391342163,
"learning_rate": 9.873200634538746e-06,
"loss": 0.2796,
"step": 64
},
{
"epoch": 0.16795865633074936,
"grad_norm": 3.149674654006958,
"learning_rate": 9.862901342325617e-06,
"loss": 0.2729,
"step": 65
},
{
"epoch": 0.17054263565891473,
"grad_norm": 2.2722795009613037,
"learning_rate": 9.852205741266058e-06,
"loss": 0.2346,
"step": 66
},
{
"epoch": 0.1731266149870801,
"grad_norm": 2.7709732055664062,
"learning_rate": 9.841114703012817e-06,
"loss": 0.2748,
"step": 67
},
{
"epoch": 0.17571059431524547,
"grad_norm": 3.9952242374420166,
"learning_rate": 9.829629131445342e-06,
"loss": 0.2411,
"step": 68
},
{
"epoch": 0.17829457364341086,
"grad_norm": 2.783984661102295,
"learning_rate": 9.817749962596115e-06,
"loss": 0.2729,
"step": 69
},
{
"epoch": 0.18087855297157623,
"grad_norm": 12.138313293457031,
"learning_rate": 9.805478164574374e-06,
"loss": 0.2857,
"step": 70
},
{
"epoch": 0.1834625322997416,
"grad_norm": 2.2798404693603516,
"learning_rate": 9.792814737487207e-06,
"loss": 0.2451,
"step": 71
},
{
"epoch": 0.18604651162790697,
"grad_norm": 3.0709733963012695,
"learning_rate": 9.77976071335806e-06,
"loss": 0.2786,
"step": 72
},
{
"epoch": 0.18863049095607234,
"grad_norm": 4.135012626647949,
"learning_rate": 9.766317156042615e-06,
"loss": 0.277,
"step": 73
},
{
"epoch": 0.19121447028423771,
"grad_norm": 2.4989020824432373,
"learning_rate": 9.752485161142103e-06,
"loss": 0.2699,
"step": 74
},
{
"epoch": 0.1937984496124031,
"grad_norm": 2.8741238117218018,
"learning_rate": 9.738265855914014e-06,
"loss": 0.2795,
"step": 75
},
{
"epoch": 0.19638242894056848,
"grad_norm": 2.3612139225006104,
"learning_rate": 9.723660399180216e-06,
"loss": 0.2463,
"step": 76
},
{
"epoch": 0.19896640826873385,
"grad_norm": 2.699559450149536,
"learning_rate": 9.708669981232542e-06,
"loss": 0.2465,
"step": 77
},
{
"epoch": 0.20155038759689922,
"grad_norm": 39.061222076416016,
"learning_rate": 9.693295823735754e-06,
"loss": 0.3251,
"step": 78
},
{
"epoch": 0.2041343669250646,
"grad_norm": 2.360377311706543,
"learning_rate": 9.677539179628005e-06,
"loss": 0.2518,
"step": 79
},
{
"epoch": 0.20671834625322996,
"grad_norm": 2.389756679534912,
"learning_rate": 9.661401333018725e-06,
"loss": 0.2622,
"step": 80
},
{
"epoch": 0.20930232558139536,
"grad_norm": 2.4635751247406006,
"learning_rate": 9.644883599083959e-06,
"loss": 0.2455,
"step": 81
},
{
"epoch": 0.21188630490956073,
"grad_norm": 2.5251641273498535,
"learning_rate": 9.627987323959195e-06,
"loss": 0.2401,
"step": 82
},
{
"epoch": 0.2144702842377261,
"grad_norm": 2.14884090423584,
"learning_rate": 9.610713884629667e-06,
"loss": 0.2406,
"step": 83
},
{
"epoch": 0.21705426356589147,
"grad_norm": 2.0660107135772705,
"learning_rate": 9.59306468881811e-06,
"loss": 0.2491,
"step": 84
},
{
"epoch": 0.21963824289405684,
"grad_norm": 2.663794994354248,
"learning_rate": 9.575041174870062e-06,
"loss": 0.2831,
"step": 85
},
{
"epoch": 0.2222222222222222,
"grad_norm": 2.469634532928467,
"learning_rate": 9.556644811636628e-06,
"loss": 0.2507,
"step": 86
},
{
"epoch": 0.2248062015503876,
"grad_norm": 2.5127339363098145,
"learning_rate": 9.537877098354787e-06,
"loss": 0.2913,
"step": 87
},
{
"epoch": 0.22739018087855298,
"grad_norm": 2.2336297035217285,
"learning_rate": 9.51873956452519e-06,
"loss": 0.2717,
"step": 88
},
{
"epoch": 0.22997416020671835,
"grad_norm": 2.478989601135254,
"learning_rate": 9.499233769787534e-06,
"loss": 0.2641,
"step": 89
},
{
"epoch": 0.23255813953488372,
"grad_norm": 2.26320219039917,
"learning_rate": 9.479361303793441e-06,
"loss": 0.244,
"step": 90
},
{
"epoch": 0.2351421188630491,
"grad_norm": 2.4783589839935303,
"learning_rate": 9.459123786076911e-06,
"loss": 0.2624,
"step": 91
},
{
"epoch": 0.23772609819121446,
"grad_norm": 2.497413158416748,
"learning_rate": 9.438522865922344e-06,
"loss": 0.2582,
"step": 92
},
{
"epoch": 0.24031007751937986,
"grad_norm": 2.4520232677459717,
"learning_rate": 9.417560222230115e-06,
"loss": 0.2624,
"step": 93
},
{
"epoch": 0.24289405684754523,
"grad_norm": 2.1241888999938965,
"learning_rate": 9.396237563379761e-06,
"loss": 0.2234,
"step": 94
},
{
"epoch": 0.2454780361757106,
"grad_norm": 2.104245185852051,
"learning_rate": 9.374556627090749e-06,
"loss": 0.2348,
"step": 95
},
{
"epoch": 0.24806201550387597,
"grad_norm": 2.5402724742889404,
"learning_rate": 9.352519180280862e-06,
"loss": 0.2638,
"step": 96
},
{
"epoch": 0.25064599483204136,
"grad_norm": 2.360741376876831,
"learning_rate": 9.330127018922195e-06,
"loss": 0.2612,
"step": 97
},
{
"epoch": 0.2532299741602067,
"grad_norm": 3.073049545288086,
"learning_rate": 9.307381967894798e-06,
"loss": 0.2675,
"step": 98
},
{
"epoch": 0.2558139534883721,
"grad_norm": 2.8394110202789307,
"learning_rate": 9.284285880837947e-06,
"loss": 0.2323,
"step": 99
},
{
"epoch": 0.25839793281653745,
"grad_norm": 2.1594583988189697,
"learning_rate": 9.26084063999909e-06,
"loss": 0.2501,
"step": 100
},
{
"epoch": 0.26098191214470284,
"grad_norm": 2.01662278175354,
"learning_rate": 9.237048156080433e-06,
"loss": 0.2424,
"step": 101
},
{
"epoch": 0.26356589147286824,
"grad_norm": 1.9394747018814087,
"learning_rate": 9.212910368083246e-06,
"loss": 0.224,
"step": 102
},
{
"epoch": 0.2661498708010336,
"grad_norm": 2.2723138332366943,
"learning_rate": 9.188429243149824e-06,
"loss": 0.2295,
"step": 103
},
{
"epoch": 0.268733850129199,
"grad_norm": 2.6535990238189697,
"learning_rate": 9.163606776403182e-06,
"loss": 0.2661,
"step": 104
},
{
"epoch": 0.2713178294573643,
"grad_norm": 2.0946295261383057,
"learning_rate": 9.138444990784455e-06,
"loss": 0.2572,
"step": 105
},
{
"epoch": 0.2739018087855297,
"grad_norm": 1.9430915117263794,
"learning_rate": 9.112945936888034e-06,
"loss": 0.2388,
"step": 106
},
{
"epoch": 0.27648578811369506,
"grad_norm": 1.6468437910079956,
"learning_rate": 9.08711169279446e-06,
"loss": 0.2026,
"step": 107
},
{
"epoch": 0.27906976744186046,
"grad_norm": 1.9926129579544067,
"learning_rate": 9.060944363901057e-06,
"loss": 0.2297,
"step": 108
},
{
"epoch": 0.28165374677002586,
"grad_norm": 2.1874048709869385,
"learning_rate": 9.034446082750352e-06,
"loss": 0.2474,
"step": 109
},
{
"epoch": 0.2842377260981912,
"grad_norm": 1.8041729927062988,
"learning_rate": 9.007619008856287e-06,
"loss": 0.233,
"step": 110
},
{
"epoch": 0.2868217054263566,
"grad_norm": 4.950301170349121,
"learning_rate": 8.98046532852822e-06,
"loss": 0.2134,
"step": 111
},
{
"epoch": 0.28940568475452194,
"grad_norm": 2.078723430633545,
"learning_rate": 8.952987254692746e-06,
"loss": 0.2547,
"step": 112
},
{
"epoch": 0.29198966408268734,
"grad_norm": 2.2332022190093994,
"learning_rate": 8.925187026713363e-06,
"loss": 0.2343,
"step": 113
},
{
"epoch": 0.29457364341085274,
"grad_norm": 1.7842631340026855,
"learning_rate": 8.897066910207958e-06,
"loss": 0.235,
"step": 114
},
{
"epoch": 0.2971576227390181,
"grad_norm": 2.2905609607696533,
"learning_rate": 8.868629196864182e-06,
"loss": 0.2287,
"step": 115
},
{
"epoch": 0.2997416020671835,
"grad_norm": 2.1392345428466797,
"learning_rate": 8.83987620425267e-06,
"loss": 0.2607,
"step": 116
},
{
"epoch": 0.3023255813953488,
"grad_norm": 2.5281567573547363,
"learning_rate": 8.810810275638183e-06,
"loss": 0.2643,
"step": 117
},
{
"epoch": 0.3049095607235142,
"grad_norm": 2.3782424926757812,
"learning_rate": 8.781433779788627e-06,
"loss": 0.2215,
"step": 118
},
{
"epoch": 0.30749354005167956,
"grad_norm": 1.8404749631881714,
"learning_rate": 8.751749110782013e-06,
"loss": 0.2332,
"step": 119
},
{
"epoch": 0.31007751937984496,
"grad_norm": 2.1314375400543213,
"learning_rate": 8.721758687811353e-06,
"loss": 0.2445,
"step": 120
},
{
"epoch": 0.31266149870801035,
"grad_norm": 2.1510751247406006,
"learning_rate": 8.691464954987494e-06,
"loss": 0.2373,
"step": 121
},
{
"epoch": 0.3152454780361757,
"grad_norm": 2.0221781730651855,
"learning_rate": 8.660870381139944e-06,
"loss": 0.2311,
"step": 122
},
{
"epoch": 0.3178294573643411,
"grad_norm": 2.068140745162964,
"learning_rate": 8.629977459615655e-06,
"loss": 0.2271,
"step": 123
},
{
"epoch": 0.32041343669250644,
"grad_norm": 1.9292054176330566,
"learning_rate": 8.598788708075844e-06,
"loss": 0.2438,
"step": 124
},
{
"epoch": 0.32299741602067183,
"grad_norm": 1.9059464931488037,
"learning_rate": 8.567306668290801e-06,
"loss": 0.2437,
"step": 125
},
{
"epoch": 0.32558139534883723,
"grad_norm": 1.87433922290802,
"learning_rate": 8.535533905932739e-06,
"loss": 0.2348,
"step": 126
},
{
"epoch": 0.3281653746770026,
"grad_norm": 1.9836807250976562,
"learning_rate": 8.503473010366713e-06,
"loss": 0.239,
"step": 127
},
{
"epoch": 0.330749354005168,
"grad_norm": 1.831213355064392,
"learning_rate": 8.471126594439591e-06,
"loss": 0.2364,
"step": 128
},
{
"epoch": 0.3333333333333333,
"grad_norm": 1.7371547222137451,
"learning_rate": 8.438497294267117e-06,
"loss": 0.2135,
"step": 129
},
{
"epoch": 0.3359173126614987,
"grad_norm": 2.7316882610321045,
"learning_rate": 8.405587769019072e-06,
"loss": 0.2562,
"step": 130
},
{
"epoch": 0.3385012919896641,
"grad_norm": 2.244509696960449,
"learning_rate": 8.372400700702569e-06,
"loss": 0.2545,
"step": 131
},
{
"epoch": 0.34108527131782945,
"grad_norm": 1.8742812871932983,
"learning_rate": 8.338938793943478e-06,
"loss": 0.2288,
"step": 132
},
{
"epoch": 0.34366925064599485,
"grad_norm": 2.042801856994629,
"learning_rate": 8.305204775766003e-06,
"loss": 0.2363,
"step": 133
},
{
"epoch": 0.3462532299741602,
"grad_norm": 1.7261626720428467,
"learning_rate": 8.27120139537044e-06,
"loss": 0.237,
"step": 134
},
{
"epoch": 0.3488372093023256,
"grad_norm": 1.798540711402893,
"learning_rate": 8.23693142390914e-06,
"loss": 0.2275,
"step": 135
},
{
"epoch": 0.35142118863049093,
"grad_norm": 1.6685022115707397,
"learning_rate": 8.202397654260649e-06,
"loss": 0.2061,
"step": 136
},
{
"epoch": 0.35400516795865633,
"grad_norm": 2.218613386154175,
"learning_rate": 8.167602900802121e-06,
"loss": 0.2377,
"step": 137
},
{
"epoch": 0.35658914728682173,
"grad_norm": 2.245936632156372,
"learning_rate": 8.132549999179934e-06,
"loss": 0.2208,
"step": 138
},
{
"epoch": 0.35917312661498707,
"grad_norm": 2.624891757965088,
"learning_rate": 8.097241806078616e-06,
"loss": 0.2476,
"step": 139
},
{
"epoch": 0.36175710594315247,
"grad_norm": 2.2246923446655273,
"learning_rate": 8.06168119898802e-06,
"loss": 0.2399,
"step": 140
},
{
"epoch": 0.3643410852713178,
"grad_norm": 1.6137202978134155,
"learning_rate": 8.025871075968828e-06,
"loss": 0.2179,
"step": 141
},
{
"epoch": 0.3669250645994832,
"grad_norm": 2.3189852237701416,
"learning_rate": 7.989814355416362e-06,
"loss": 0.2258,
"step": 142
},
{
"epoch": 0.3695090439276486,
"grad_norm": 1.66120183467865,
"learning_rate": 7.953513975822755e-06,
"loss": 0.2179,
"step": 143
},
{
"epoch": 0.37209302325581395,
"grad_norm": 1.8575221300125122,
"learning_rate": 7.916972895537471e-06,
"loss": 0.2385,
"step": 144
},
{
"epoch": 0.37467700258397935,
"grad_norm": 1.6913485527038574,
"learning_rate": 7.8801940925262e-06,
"loss": 0.2315,
"step": 145
},
{
"epoch": 0.3772609819121447,
"grad_norm": 2.0804011821746826,
"learning_rate": 7.843180564128178e-06,
"loss": 0.2329,
"step": 146
},
{
"epoch": 0.3798449612403101,
"grad_norm": 1.9570668935775757,
"learning_rate": 7.805935326811913e-06,
"loss": 0.236,
"step": 147
},
{
"epoch": 0.38242894056847543,
"grad_norm": 2.2063801288604736,
"learning_rate": 7.768461415929344e-06,
"loss": 0.2221,
"step": 148
},
{
"epoch": 0.3850129198966408,
"grad_norm": 1.6152676343917847,
"learning_rate": 7.730761885468486e-06,
"loss": 0.2238,
"step": 149
},
{
"epoch": 0.3875968992248062,
"grad_norm": 1.9125603437423706,
"learning_rate": 7.692839807804522e-06,
"loss": 0.2287,
"step": 150
},
{
"epoch": 0.39018087855297157,
"grad_norm": 1.910693645477295,
"learning_rate": 7.654698273449435e-06,
"loss": 0.2225,
"step": 151
},
{
"epoch": 0.39276485788113696,
"grad_norm": 1.5631076097488403,
"learning_rate": 7.616340390800127e-06,
"loss": 0.2376,
"step": 152
},
{
"epoch": 0.3953488372093023,
"grad_norm": 1.5215353965759277,
"learning_rate": 7.57776928588511e-06,
"loss": 0.212,
"step": 153
},
{
"epoch": 0.3979328165374677,
"grad_norm": 1.9194774627685547,
"learning_rate": 7.538988102109728e-06,
"loss": 0.2247,
"step": 154
},
{
"epoch": 0.4005167958656331,
"grad_norm": 2.0770885944366455,
"learning_rate": 7.500000000000001e-06,
"loss": 0.2527,
"step": 155
},
{
"epoch": 0.40310077519379844,
"grad_norm": 1.776774525642395,
"learning_rate": 7.4608081569450365e-06,
"loss": 0.243,
"step": 156
},
{
"epoch": 0.40568475452196384,
"grad_norm": 1.8917075395584106,
"learning_rate": 7.421415766938098e-06,
"loss": 0.2319,
"step": 157
},
{
"epoch": 0.4082687338501292,
"grad_norm": 1.8015702962875366,
"learning_rate": 7.381826040316294e-06,
"loss": 0.2115,
"step": 158
},
{
"epoch": 0.4108527131782946,
"grad_norm": 2.221393346786499,
"learning_rate": 7.342042203498952e-06,
"loss": 0.2334,
"step": 159
},
{
"epoch": 0.4134366925064599,
"grad_norm": 1.9779021739959717,
"learning_rate": 7.302067498724681e-06,
"loss": 0.2206,
"step": 160
},
{
"epoch": 0.4160206718346253,
"grad_norm": 1.6825449466705322,
"learning_rate": 7.261905183787136e-06,
"loss": 0.2068,
"step": 161
},
{
"epoch": 0.4186046511627907,
"grad_norm": 1.9611059427261353,
"learning_rate": 7.221558531769519e-06,
"loss": 0.2454,
"step": 162
},
{
"epoch": 0.42118863049095606,
"grad_norm": 1.7121902704238892,
"learning_rate": 7.181030830777838e-06,
"loss": 0.2397,
"step": 163
},
{
"epoch": 0.42377260981912146,
"grad_norm": 2.4492485523223877,
"learning_rate": 7.140325383672938e-06,
"loss": 0.2288,
"step": 164
},
{
"epoch": 0.4263565891472868,
"grad_norm": 1.4285128116607666,
"learning_rate": 7.099445507801324e-06,
"loss": 0.1875,
"step": 165
},
{
"epoch": 0.4289405684754522,
"grad_norm": 1.9082492589950562,
"learning_rate": 7.058394534724819e-06,
"loss": 0.2208,
"step": 166
},
{
"epoch": 0.4315245478036176,
"grad_norm": 1.6619027853012085,
"learning_rate": 7.017175809949044e-06,
"loss": 0.2062,
"step": 167
},
{
"epoch": 0.43410852713178294,
"grad_norm": 1.8407310247421265,
"learning_rate": 6.975792692650778e-06,
"loss": 0.2406,
"step": 168
},
{
"epoch": 0.43669250645994834,
"grad_norm": 1.7827914953231812,
"learning_rate": 6.934248555404197e-06,
"loss": 0.2258,
"step": 169
},
{
"epoch": 0.4392764857881137,
"grad_norm": 1.6271895170211792,
"learning_rate": 6.892546783906016e-06,
"loss": 0.2222,
"step": 170
},
{
"epoch": 0.4418604651162791,
"grad_norm": 1.9836379289627075,
"learning_rate": 6.850690776699574e-06,
"loss": 0.2307,
"step": 171
},
{
"epoch": 0.4444444444444444,
"grad_norm": 1.6630229949951172,
"learning_rate": 6.808683944897856e-06,
"loss": 0.2057,
"step": 172
},
{
"epoch": 0.4470284237726098,
"grad_norm": 1.7780696153640747,
"learning_rate": 6.766529711905513e-06,
"loss": 0.2034,
"step": 173
},
{
"epoch": 0.4496124031007752,
"grad_norm": 1.984447717666626,
"learning_rate": 6.724231513139853e-06,
"loss": 0.2303,
"step": 174
},
{
"epoch": 0.45219638242894056,
"grad_norm": 2.17633056640625,
"learning_rate": 6.681792795750876e-06,
"loss": 0.2373,
"step": 175
},
{
"epoch": 0.45478036175710596,
"grad_norm": 1.460951566696167,
"learning_rate": 6.639217018340342e-06,
"loss": 0.2015,
"step": 176
},
{
"epoch": 0.4573643410852713,
"grad_norm": 1.790872573852539,
"learning_rate": 6.5965076506799e-06,
"loss": 0.2244,
"step": 177
},
{
"epoch": 0.4599483204134367,
"grad_norm": 1.4559892416000366,
"learning_rate": 6.553668173428329e-06,
"loss": 0.2045,
"step": 178
},
{
"epoch": 0.4625322997416021,
"grad_norm": 2.018108367919922,
"learning_rate": 6.510702077847864e-06,
"loss": 0.2079,
"step": 179
},
{
"epoch": 0.46511627906976744,
"grad_norm": 1.6619304418563843,
"learning_rate": 6.467612865519674e-06,
"loss": 0.2031,
"step": 180
},
{
"epoch": 0.46770025839793283,
"grad_norm": 1.7696534395217896,
"learning_rate": 6.424404048058501e-06,
"loss": 0.2104,
"step": 181
},
{
"epoch": 0.4702842377260982,
"grad_norm": 1.6792902946472168,
"learning_rate": 6.3810791468264654e-06,
"loss": 0.1949,
"step": 182
},
{
"epoch": 0.4728682170542636,
"grad_norm": 1.7121378183364868,
"learning_rate": 6.337641692646106e-06,
"loss": 0.2261,
"step": 183
},
{
"epoch": 0.4754521963824289,
"grad_norm": 1.758552074432373,
"learning_rate": 6.294095225512604e-06,
"loss": 0.2272,
"step": 184
},
{
"epoch": 0.4780361757105943,
"grad_norm": 1.5094135999679565,
"learning_rate": 6.250443294305315e-06,
"loss": 0.2059,
"step": 185
},
{
"epoch": 0.4806201550387597,
"grad_norm": 1.5085089206695557,
"learning_rate": 6.206689456498529e-06,
"loss": 0.2173,
"step": 186
},
{
"epoch": 0.48320413436692505,
"grad_norm": 1.4562510251998901,
"learning_rate": 6.162837277871553e-06,
"loss": 0.2185,
"step": 187
},
{
"epoch": 0.48578811369509045,
"grad_norm": 1.507325530052185,
"learning_rate": 6.118890332218117e-06,
"loss": 0.2139,
"step": 188
},
{
"epoch": 0.4883720930232558,
"grad_norm": 1.7156720161437988,
"learning_rate": 6.074852201055121e-06,
"loss": 0.2161,
"step": 189
},
{
"epoch": 0.4909560723514212,
"grad_norm": 1.659424901008606,
"learning_rate": 6.0307264733307515e-06,
"loss": 0.2083,
"step": 190
},
{
"epoch": 0.4935400516795866,
"grad_norm": 1.4655615091323853,
"learning_rate": 5.986516745132e-06,
"loss": 0.2129,
"step": 191
},
{
"epoch": 0.49612403100775193,
"grad_norm": 1.5427219867706299,
"learning_rate": 5.942226619391592e-06,
"loss": 0.2064,
"step": 192
},
{
"epoch": 0.49870801033591733,
"grad_norm": 1.3408644199371338,
"learning_rate": 5.8978597055943585e-06,
"loss": 0.1982,
"step": 193
},
{
"epoch": 0.5012919896640827,
"grad_norm": 1.9902156591415405,
"learning_rate": 5.853419619483083e-06,
"loss": 0.226,
"step": 194
},
{
"epoch": 0.5038759689922481,
"grad_norm": 1.3126060962677002,
"learning_rate": 5.808909982763825e-06,
"loss": 0.1991,
"step": 195
},
{
"epoch": 0.5064599483204134,
"grad_norm": 1.8132307529449463,
"learning_rate": 5.764334422810767e-06,
"loss": 0.2271,
"step": 196
},
{
"epoch": 0.5090439276485789,
"grad_norm": 1.8984651565551758,
"learning_rate": 5.719696572370596e-06,
"loss": 0.2363,
"step": 197
},
{
"epoch": 0.5116279069767442,
"grad_norm": 1.817488670349121,
"learning_rate": 5.675000069266451e-06,
"loss": 0.2281,
"step": 198
},
{
"epoch": 0.5142118863049095,
"grad_norm": 2.4053938388824463,
"learning_rate": 5.630248556101448e-06,
"loss": 0.2349,
"step": 199
},
{
"epoch": 0.5167958656330749,
"grad_norm": 1.4642032384872437,
"learning_rate": 5.585445679961823e-06,
"loss": 0.1984,
"step": 200
},
{
"epoch": 0.5193798449612403,
"grad_norm": 2.2405009269714355,
"learning_rate": 5.540595092119709e-06,
"loss": 0.2101,
"step": 201
},
{
"epoch": 0.5219638242894057,
"grad_norm": 1.7168304920196533,
"learning_rate": 5.495700447735572e-06,
"loss": 0.2272,
"step": 202
},
{
"epoch": 0.524547803617571,
"grad_norm": 1.5339411497116089,
"learning_rate": 5.450765405560328e-06,
"loss": 0.2225,
"step": 203
},
{
"epoch": 0.5271317829457365,
"grad_norm": 1.3848717212677002,
"learning_rate": 5.405793627637157e-06,
"loss": 0.1989,
"step": 204
},
{
"epoch": 0.5297157622739018,
"grad_norm": 1.5923454761505127,
"learning_rate": 5.360788779003082e-06,
"loss": 0.2101,
"step": 205
},
{
"epoch": 0.5322997416020672,
"grad_norm": 1.538506269454956,
"learning_rate": 5.3157545273902585e-06,
"loss": 0.2203,
"step": 206
},
{
"epoch": 0.5348837209302325,
"grad_norm": 1.3902374505996704,
"learning_rate": 5.270694542927089e-06,
"loss": 0.2042,
"step": 207
},
{
"epoch": 0.537467700258398,
"grad_norm": 2.0255801677703857,
"learning_rate": 5.225612497839099e-06,
"loss": 0.2059,
"step": 208
},
{
"epoch": 0.5400516795865633,
"grad_norm": 1.9409769773483276,
"learning_rate": 5.180512066149682e-06,
"loss": 0.2154,
"step": 209
},
{
"epoch": 0.5426356589147286,
"grad_norm": 1.5798600912094116,
"learning_rate": 5.1353969233806735e-06,
"loss": 0.2116,
"step": 210
},
{
"epoch": 0.5452196382428941,
"grad_norm": 1.9305166006088257,
"learning_rate": 5.090270746252803e-06,
"loss": 0.1892,
"step": 211
},
{
"epoch": 0.5478036175710594,
"grad_norm": 2.8123254776000977,
"learning_rate": 5.045137212386065e-06,
"loss": 0.2128,
"step": 212
},
{
"epoch": 0.5503875968992248,
"grad_norm": 1.9373772144317627,
"learning_rate": 5e-06,
"loss": 0.2199,
"step": 213
},
{
"epoch": 0.5529715762273901,
"grad_norm": 1.5903531312942505,
"learning_rate": 4.954862787613937e-06,
"loss": 0.2148,
"step": 214
},
{
"epoch": 0.5555555555555556,
"grad_norm": 1.604992389678955,
"learning_rate": 4.909729253747197e-06,
"loss": 0.2236,
"step": 215
},
{
"epoch": 0.5581395348837209,
"grad_norm": 2.290006399154663,
"learning_rate": 4.864603076619329e-06,
"loss": 0.2175,
"step": 216
},
{
"epoch": 0.5607235142118863,
"grad_norm": 1.6406919956207275,
"learning_rate": 4.819487933850319e-06,
"loss": 0.2272,
"step": 217
},
{
"epoch": 0.5633074935400517,
"grad_norm": 1.8373345136642456,
"learning_rate": 4.774387502160902e-06,
"loss": 0.2245,
"step": 218
},
{
"epoch": 0.5658914728682171,
"grad_norm": 1.6454440355300903,
"learning_rate": 4.729305457072913e-06,
"loss": 0.203,
"step": 219
},
{
"epoch": 0.5684754521963824,
"grad_norm": 1.6277472972869873,
"learning_rate": 4.684245472609743e-06,
"loss": 0.2325,
"step": 220
},
{
"epoch": 0.5710594315245479,
"grad_norm": 1.4459894895553589,
"learning_rate": 4.6392112209969205e-06,
"loss": 0.2095,
"step": 221
},
{
"epoch": 0.5736434108527132,
"grad_norm": 1.5780946016311646,
"learning_rate": 4.594206372362845e-06,
"loss": 0.2033,
"step": 222
},
{
"epoch": 0.5762273901808785,
"grad_norm": 1.4234222173690796,
"learning_rate": 4.549234594439674e-06,
"loss": 0.2014,
"step": 223
},
{
"epoch": 0.5788113695090439,
"grad_norm": 1.2753453254699707,
"learning_rate": 4.504299552264428e-06,
"loss": 0.1729,
"step": 224
},
{
"epoch": 0.5813953488372093,
"grad_norm": 1.4043508768081665,
"learning_rate": 4.459404907880293e-06,
"loss": 0.2015,
"step": 225
},
{
"epoch": 0.5839793281653747,
"grad_norm": 1.548924446105957,
"learning_rate": 4.414554320038179e-06,
"loss": 0.2153,
"step": 226
},
{
"epoch": 0.58656330749354,
"grad_norm": 1.4754077196121216,
"learning_rate": 4.369751443898554e-06,
"loss": 0.2023,
"step": 227
},
{
"epoch": 0.5891472868217055,
"grad_norm": 1.2993725538253784,
"learning_rate": 4.32499993073355e-06,
"loss": 0.1763,
"step": 228
},
{
"epoch": 0.5917312661498708,
"grad_norm": 1.3788522481918335,
"learning_rate": 4.280303427629404e-06,
"loss": 0.1941,
"step": 229
},
{
"epoch": 0.5943152454780362,
"grad_norm": 2.100757122039795,
"learning_rate": 4.2356655771892355e-06,
"loss": 0.227,
"step": 230
},
{
"epoch": 0.5968992248062015,
"grad_norm": 1.526432991027832,
"learning_rate": 4.191090017236177e-06,
"loss": 0.2028,
"step": 231
},
{
"epoch": 0.599483204134367,
"grad_norm": 1.5663360357284546,
"learning_rate": 4.146580380516918e-06,
"loss": 0.2094,
"step": 232
},
{
"epoch": 0.6020671834625323,
"grad_norm": 1.3962419033050537,
"learning_rate": 4.1021402944056415e-06,
"loss": 0.1891,
"step": 233
},
{
"epoch": 0.6046511627906976,
"grad_norm": 1.3490815162658691,
"learning_rate": 4.057773380608411e-06,
"loss": 0.1682,
"step": 234
},
{
"epoch": 0.6072351421188631,
"grad_norm": 1.5363324880599976,
"learning_rate": 4.013483254868001e-06,
"loss": 0.1997,
"step": 235
},
{
"epoch": 0.6098191214470284,
"grad_norm": 1.261446237564087,
"learning_rate": 3.969273526669249e-06,
"loss": 0.1766,
"step": 236
},
{
"epoch": 0.6124031007751938,
"grad_norm": 1.8413023948669434,
"learning_rate": 3.92514779894488e-06,
"loss": 0.2168,
"step": 237
},
{
"epoch": 0.6149870801033591,
"grad_norm": 1.784358263015747,
"learning_rate": 3.881109667781884e-06,
"loss": 0.194,
"step": 238
},
{
"epoch": 0.6175710594315246,
"grad_norm": 1.5789978504180908,
"learning_rate": 3.8371627221284495e-06,
"loss": 0.1961,
"step": 239
},
{
"epoch": 0.6201550387596899,
"grad_norm": 1.3455345630645752,
"learning_rate": 3.7933105435014727e-06,
"loss": 0.1929,
"step": 240
},
{
"epoch": 0.6227390180878553,
"grad_norm": 1.4323828220367432,
"learning_rate": 3.7495567056946856e-06,
"loss": 0.2066,
"step": 241
},
{
"epoch": 0.6253229974160207,
"grad_norm": 1.5241978168487549,
"learning_rate": 3.705904774487396e-06,
"loss": 0.2147,
"step": 242
},
{
"epoch": 0.627906976744186,
"grad_norm": 1.6744216680526733,
"learning_rate": 3.662358307353897e-06,
"loss": 0.2254,
"step": 243
},
{
"epoch": 0.6304909560723514,
"grad_norm": 2.2153306007385254,
"learning_rate": 3.6189208531735354e-06,
"loss": 0.1895,
"step": 244
},
{
"epoch": 0.6330749354005168,
"grad_norm": 1.4624733924865723,
"learning_rate": 3.5755959519415008e-06,
"loss": 0.1873,
"step": 245
},
{
"epoch": 0.6356589147286822,
"grad_norm": 1.6091656684875488,
"learning_rate": 3.532387134480327e-06,
"loss": 0.198,
"step": 246
},
{
"epoch": 0.6382428940568475,
"grad_norm": 1.208809733390808,
"learning_rate": 3.489297922152136e-06,
"loss": 0.1866,
"step": 247
},
{
"epoch": 0.6408268733850129,
"grad_norm": 1.3647226095199585,
"learning_rate": 3.446331826571672e-06,
"loss": 0.1981,
"step": 248
},
{
"epoch": 0.6434108527131783,
"grad_norm": 1.6208391189575195,
"learning_rate": 3.403492349320101e-06,
"loss": 0.2192,
"step": 249
},
{
"epoch": 0.6459948320413437,
"grad_norm": 1.5029717683792114,
"learning_rate": 3.360782981659659e-06,
"loss": 0.1784,
"step": 250
},
{
"epoch": 0.648578811369509,
"grad_norm": 1.6115533113479614,
"learning_rate": 3.3182072042491244e-06,
"loss": 0.2231,
"step": 251
},
{
"epoch": 0.6511627906976745,
"grad_norm": 1.621906042098999,
"learning_rate": 3.275768486860149e-06,
"loss": 0.1729,
"step": 252
},
{
"epoch": 0.6537467700258398,
"grad_norm": 1.356162190437317,
"learning_rate": 3.233470288094489e-06,
"loss": 0.1873,
"step": 253
},
{
"epoch": 0.6563307493540051,
"grad_norm": 1.4512073993682861,
"learning_rate": 3.191316055102146e-06,
"loss": 0.1955,
"step": 254
},
{
"epoch": 0.6589147286821705,
"grad_norm": 1.5930757522583008,
"learning_rate": 3.149309223300428e-06,
"loss": 0.1773,
"step": 255
},
{
"epoch": 0.661498708010336,
"grad_norm": 1.3301100730895996,
"learning_rate": 3.107453216093985e-06,
"loss": 0.1838,
"step": 256
},
{
"epoch": 0.6640826873385013,
"grad_norm": 1.2428103685379028,
"learning_rate": 3.0657514445958055e-06,
"loss": 0.1795,
"step": 257
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.2732970714569092,
"learning_rate": 3.0242073073492238e-06,
"loss": 0.1907,
"step": 258
},
{
"epoch": 0.6692506459948321,
"grad_norm": 1.7173457145690918,
"learning_rate": 2.982824190050958e-06,
"loss": 0.1962,
"step": 259
},
{
"epoch": 0.6718346253229974,
"grad_norm": 1.1723400354385376,
"learning_rate": 2.9416054652751834e-06,
"loss": 0.1553,
"step": 260
},
{
"epoch": 0.6744186046511628,
"grad_norm": 1.2737828493118286,
"learning_rate": 2.9005544921986774e-06,
"loss": 0.1809,
"step": 261
},
{
"epoch": 0.6770025839793282,
"grad_norm": 1.6005208492279053,
"learning_rate": 2.8596746163270646e-06,
"loss": 0.1876,
"step": 262
},
{
"epoch": 0.6795865633074936,
"grad_norm": 1.6597061157226562,
"learning_rate": 2.8189691692221627e-06,
"loss": 0.214,
"step": 263
},
{
"epoch": 0.6821705426356589,
"grad_norm": 1.4774705171585083,
"learning_rate": 2.778441468230483e-06,
"loss": 0.1851,
"step": 264
},
{
"epoch": 0.6847545219638242,
"grad_norm": 1.409745454788208,
"learning_rate": 2.738094816212866e-06,
"loss": 0.1734,
"step": 265
},
{
"epoch": 0.6873385012919897,
"grad_norm": 1.40264093875885,
"learning_rate": 2.6979325012753214e-06,
"loss": 0.175,
"step": 266
},
{
"epoch": 0.689922480620155,
"grad_norm": 1.2759225368499756,
"learning_rate": 2.65795779650105e-06,
"loss": 0.173,
"step": 267
},
{
"epoch": 0.6925064599483204,
"grad_norm": 1.3376514911651611,
"learning_rate": 2.6181739596837075e-06,
"loss": 0.1669,
"step": 268
},
{
"epoch": 0.6950904392764858,
"grad_norm": 1.813323974609375,
"learning_rate": 2.5785842330619038e-06,
"loss": 0.1915,
"step": 269
},
{
"epoch": 0.6976744186046512,
"grad_norm": 1.4839708805084229,
"learning_rate": 2.5391918430549635e-06,
"loss": 0.2038,
"step": 270
},
{
"epoch": 0.7002583979328165,
"grad_norm": 1.2945070266723633,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.1685,
"step": 271
},
{
"epoch": 0.7028423772609819,
"grad_norm": 1.5902131795883179,
"learning_rate": 2.4610118978902732e-06,
"loss": 0.1874,
"step": 272
},
{
"epoch": 0.7054263565891473,
"grad_norm": 1.3686803579330444,
"learning_rate": 2.422230714114891e-06,
"loss": 0.1701,
"step": 273
},
{
"epoch": 0.7080103359173127,
"grad_norm": 1.3523751497268677,
"learning_rate": 2.383659609199873e-06,
"loss": 0.1679,
"step": 274
},
{
"epoch": 0.710594315245478,
"grad_norm": 1.5173090696334839,
"learning_rate": 2.345301726550567e-06,
"loss": 0.203,
"step": 275
},
{
"epoch": 0.7131782945736435,
"grad_norm": 1.1696375608444214,
"learning_rate": 2.3071601921954797e-06,
"loss": 0.1645,
"step": 276
},
{
"epoch": 0.7157622739018088,
"grad_norm": 1.5028029680252075,
"learning_rate": 2.269238114531515e-06,
"loss": 0.1902,
"step": 277
},
{
"epoch": 0.7183462532299741,
"grad_norm": 1.4014875888824463,
"learning_rate": 2.2315385840706548e-06,
"loss": 0.1817,
"step": 278
},
{
"epoch": 0.7209302325581395,
"grad_norm": 1.1939343214035034,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.1574,
"step": 279
},
{
"epoch": 0.7235142118863049,
"grad_norm": 1.4427356719970703,
"learning_rate": 2.156819435871824e-06,
"loss": 0.1815,
"step": 280
},
{
"epoch": 0.7260981912144703,
"grad_norm": 1.421738624572754,
"learning_rate": 2.1198059074738027e-06,
"loss": 0.1996,
"step": 281
},
{
"epoch": 0.7286821705426356,
"grad_norm": 1.4071861505508423,
"learning_rate": 2.08302710446253e-06,
"loss": 0.1882,
"step": 282
},
{
"epoch": 0.7312661498708011,
"grad_norm": 1.2895996570587158,
"learning_rate": 2.0464860241772454e-06,
"loss": 0.1664,
"step": 283
},
{
"epoch": 0.7338501291989664,
"grad_norm": 1.6300632953643799,
"learning_rate": 2.010185644583641e-06,
"loss": 0.1849,
"step": 284
},
{
"epoch": 0.7364341085271318,
"grad_norm": 1.4193930625915527,
"learning_rate": 1.9741289240311757e-06,
"loss": 0.1903,
"step": 285
},
{
"epoch": 0.7390180878552972,
"grad_norm": 1.3659586906433105,
"learning_rate": 1.9383188010119818e-06,
"loss": 0.1891,
"step": 286
},
{
"epoch": 0.7416020671834626,
"grad_norm": 1.3775144815444946,
"learning_rate": 1.9027581939213852e-06,
"loss": 0.1934,
"step": 287
},
{
"epoch": 0.7441860465116279,
"grad_norm": 1.3561066389083862,
"learning_rate": 1.8674500008200675e-06,
"loss": 0.193,
"step": 288
},
{
"epoch": 0.7467700258397932,
"grad_norm": 1.3804134130477905,
"learning_rate": 1.8323970991978823e-06,
"loss": 0.1801,
"step": 289
},
{
"epoch": 0.7493540051679587,
"grad_norm": 1.3752516508102417,
"learning_rate": 1.797602345739352e-06,
"loss": 0.1784,
"step": 290
},
{
"epoch": 0.751937984496124,
"grad_norm": 1.4992294311523438,
"learning_rate": 1.7630685760908623e-06,
"loss": 0.1908,
"step": 291
},
{
"epoch": 0.7545219638242894,
"grad_norm": 1.555408000946045,
"learning_rate": 1.7287986046295597e-06,
"loss": 0.1756,
"step": 292
},
{
"epoch": 0.7571059431524548,
"grad_norm": 1.603082299232483,
"learning_rate": 1.6947952242339993e-06,
"loss": 0.157,
"step": 293
},
{
"epoch": 0.7596899224806202,
"grad_norm": 1.503893256187439,
"learning_rate": 1.6610612060565235e-06,
"loss": 0.1929,
"step": 294
},
{
"epoch": 0.7622739018087855,
"grad_norm": 1.3251415491104126,
"learning_rate": 1.627599299297431e-06,
"loss": 0.1776,
"step": 295
},
{
"epoch": 0.7648578811369509,
"grad_norm": 1.4177522659301758,
"learning_rate": 1.594412230980928e-06,
"loss": 0.1726,
"step": 296
},
{
"epoch": 0.7674418604651163,
"grad_norm": 1.4148153066635132,
"learning_rate": 1.561502705732883e-06,
"loss": 0.1823,
"step": 297
},
{
"epoch": 0.7700258397932817,
"grad_norm": 1.3199900388717651,
"learning_rate": 1.5288734055604087e-06,
"loss": 0.1809,
"step": 298
},
{
"epoch": 0.772609819121447,
"grad_norm": 1.4778473377227783,
"learning_rate": 1.4965269896332884e-06,
"loss": 0.1853,
"step": 299
},
{
"epoch": 0.7751937984496124,
"grad_norm": 1.3273617029190063,
"learning_rate": 1.4644660940672628e-06,
"loss": 0.1676,
"step": 300
},
{
"epoch": 0.7777777777777778,
"grad_norm": 1.4746593236923218,
"learning_rate": 1.4326933317092e-06,
"loss": 0.1803,
"step": 301
},
{
"epoch": 0.7803617571059431,
"grad_norm": 1.204885721206665,
"learning_rate": 1.4012112919241562e-06,
"loss": 0.1617,
"step": 302
},
{
"epoch": 0.7829457364341085,
"grad_norm": 1.4356775283813477,
"learning_rate": 1.370022540384347e-06,
"loss": 0.1723,
"step": 303
},
{
"epoch": 0.7855297157622739,
"grad_norm": 1.6779110431671143,
"learning_rate": 1.3391296188600594e-06,
"loss": 0.1768,
"step": 304
},
{
"epoch": 0.7881136950904393,
"grad_norm": 1.3418086767196655,
"learning_rate": 1.3085350450125073e-06,
"loss": 0.1807,
"step": 305
},
{
"epoch": 0.7906976744186046,
"grad_norm": 1.301296591758728,
"learning_rate": 1.2782413121886483e-06,
"loss": 0.1497,
"step": 306
},
{
"epoch": 0.7932816537467701,
"grad_norm": 1.1588480472564697,
"learning_rate": 1.2482508892179884e-06,
"loss": 0.1582,
"step": 307
},
{
"epoch": 0.7958656330749354,
"grad_norm": 1.2679500579833984,
"learning_rate": 1.2185662202113764e-06,
"loss": 0.1527,
"step": 308
},
{
"epoch": 0.7984496124031008,
"grad_norm": 1.13987398147583,
"learning_rate": 1.1891897243618184e-06,
"loss": 0.1582,
"step": 309
},
{
"epoch": 0.8010335917312662,
"grad_norm": 1.3159266710281372,
"learning_rate": 1.16012379574733e-06,
"loss": 0.1717,
"step": 310
},
{
"epoch": 0.8036175710594315,
"grad_norm": 1.5035459995269775,
"learning_rate": 1.1313708031358183e-06,
"loss": 0.1672,
"step": 311
},
{
"epoch": 0.8062015503875969,
"grad_norm": 1.5732388496398926,
"learning_rate": 1.102933089792042e-06,
"loss": 0.1763,
"step": 312
},
{
"epoch": 0.8087855297157622,
"grad_norm": 1.2379496097564697,
"learning_rate": 1.0748129732866391e-06,
"loss": 0.1521,
"step": 313
},
{
"epoch": 0.8113695090439277,
"grad_norm": 1.425968050956726,
"learning_rate": 1.047012745307255e-06,
"loss": 0.182,
"step": 314
},
{
"epoch": 0.813953488372093,
"grad_norm": 1.199998378753662,
"learning_rate": 1.0195346714717813e-06,
"loss": 0.1522,
"step": 315
},
{
"epoch": 0.8165374677002584,
"grad_norm": 1.3904505968093872,
"learning_rate": 9.92380991143712e-07,
"loss": 0.1705,
"step": 316
},
{
"epoch": 0.8191214470284238,
"grad_norm": 1.4871166944503784,
"learning_rate": 9.65553917249648e-07,
"loss": 0.1799,
"step": 317
},
{
"epoch": 0.8217054263565892,
"grad_norm": 1.431360125541687,
"learning_rate": 9.39055636098945e-07,
"loss": 0.1779,
"step": 318
},
{
"epoch": 0.8242894056847545,
"grad_norm": 1.1474868059158325,
"learning_rate": 9.128883072055411e-07,
"loss": 0.1473,
"step": 319
},
{
"epoch": 0.8268733850129198,
"grad_norm": 1.3604931831359863,
"learning_rate": 8.870540631119667e-07,
"loss": 0.1658,
"step": 320
},
{
"epoch": 0.8294573643410853,
"grad_norm": 1.319649338722229,
"learning_rate": 8.615550092155478e-07,
"loss": 0.1635,
"step": 321
},
{
"epoch": 0.8320413436692506,
"grad_norm": 1.6052929162979126,
"learning_rate": 8.363932235968198e-07,
"loss": 0.1862,
"step": 322
},
{
"epoch": 0.834625322997416,
"grad_norm": 1.2895382642745972,
"learning_rate": 8.115707568501768e-07,
"loss": 0.1603,
"step": 323
},
{
"epoch": 0.8372093023255814,
"grad_norm": 1.3937253952026367,
"learning_rate": 7.870896319167548e-07,
"loss": 0.1637,
"step": 324
},
{
"epoch": 0.8397932816537468,
"grad_norm": 1.549171805381775,
"learning_rate": 7.629518439195671e-07,
"loss": 0.1911,
"step": 325
},
{
"epoch": 0.8423772609819121,
"grad_norm": 1.5424485206604004,
"learning_rate": 7.391593600009123e-07,
"loss": 0.1835,
"step": 326
},
{
"epoch": 0.8449612403100775,
"grad_norm": 1.322595477104187,
"learning_rate": 7.157141191620548e-07,
"loss": 0.1589,
"step": 327
},
{
"epoch": 0.8475452196382429,
"grad_norm": 1.6589468717575073,
"learning_rate": 6.926180321052045e-07,
"loss": 0.1819,
"step": 328
},
{
"epoch": 0.8501291989664083,
"grad_norm": 1.3434414863586426,
"learning_rate": 6.698729810778065e-07,
"loss": 0.1683,
"step": 329
},
{
"epoch": 0.8527131782945736,
"grad_norm": 1.3851432800292969,
"learning_rate": 6.474808197191401e-07,
"loss": 0.1754,
"step": 330
},
{
"epoch": 0.8552971576227391,
"grad_norm": 1.1711254119873047,
"learning_rate": 6.254433729092518e-07,
"loss": 0.1552,
"step": 331
},
{
"epoch": 0.8578811369509044,
"grad_norm": 1.3657231330871582,
"learning_rate": 6.037624366202405e-07,
"loss": 0.1644,
"step": 332
},
{
"epoch": 0.8604651162790697,
"grad_norm": 1.3525211811065674,
"learning_rate": 5.824397777698859e-07,
"loss": 0.173,
"step": 333
},
{
"epoch": 0.8630490956072352,
"grad_norm": 1.3109862804412842,
"learning_rate": 5.614771340776559e-07,
"loss": 0.1692,
"step": 334
},
{
"epoch": 0.8656330749354005,
"grad_norm": 1.399511694908142,
"learning_rate": 5.408762139230889e-07,
"loss": 0.1602,
"step": 335
},
{
"epoch": 0.8682170542635659,
"grad_norm": 1.5356361865997314,
"learning_rate": 5.206386962065601e-07,
"loss": 0.181,
"step": 336
},
{
"epoch": 0.8708010335917312,
"grad_norm": 1.3737794160842896,
"learning_rate": 5.007662302124671e-07,
"loss": 0.1687,
"step": 337
},
{
"epoch": 0.8733850129198967,
"grad_norm": 1.4284069538116455,
"learning_rate": 4.812604354748107e-07,
"loss": 0.1673,
"step": 338
},
{
"epoch": 0.875968992248062,
"grad_norm": 1.4897751808166504,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.1727,
"step": 339
},
{
"epoch": 0.8785529715762274,
"grad_norm": 1.7438304424285889,
"learning_rate": 4.433551883633719e-07,
"loss": 0.1734,
"step": 340
},
{
"epoch": 0.8811369509043928,
"grad_norm": 1.7176605463027954,
"learning_rate": 4.2495882512993913e-07,
"loss": 0.1899,
"step": 341
},
{
"epoch": 0.8837209302325582,
"grad_norm": 1.2422411441802979,
"learning_rate": 4.069353111818913e-07,
"loss": 0.1701,
"step": 342
},
{
"epoch": 0.8863049095607235,
"grad_norm": 1.387807011604309,
"learning_rate": 3.8928611537033424e-07,
"loss": 0.1755,
"step": 343
},
{
"epoch": 0.8888888888888888,
"grad_norm": 1.3703078031539917,
"learning_rate": 3.7201267604080436e-07,
"loss": 0.1632,
"step": 344
},
{
"epoch": 0.8914728682170543,
"grad_norm": 1.3891550302505493,
"learning_rate": 3.5511640091604293e-07,
"loss": 0.1707,
"step": 345
},
{
"epoch": 0.8940568475452196,
"grad_norm": 1.5258495807647705,
"learning_rate": 3.385986669812769e-07,
"loss": 0.1719,
"step": 346
},
{
"epoch": 0.896640826873385,
"grad_norm": 1.3084255456924438,
"learning_rate": 3.224608203719953e-07,
"loss": 0.1639,
"step": 347
},
{
"epoch": 0.8992248062015504,
"grad_norm": 1.3888843059539795,
"learning_rate": 3.067041762642475e-07,
"loss": 0.1721,
"step": 348
},
{
"epoch": 0.9018087855297158,
"grad_norm": 1.3244494199752808,
"learning_rate": 2.9133001876746004e-07,
"loss": 0.1704,
"step": 349
},
{
"epoch": 0.9043927648578811,
"grad_norm": 1.3492217063903809,
"learning_rate": 2.763396008197833e-07,
"loss": 0.1789,
"step": 350
},
{
"epoch": 0.9069767441860465,
"grad_norm": 1.2785379886627197,
"learning_rate": 2.617341440859883e-07,
"loss": 0.1639,
"step": 351
},
{
"epoch": 0.9095607235142119,
"grad_norm": 1.225648045539856,
"learning_rate": 2.475148388578974e-07,
"loss": 0.1525,
"step": 352
},
{
"epoch": 0.9121447028423773,
"grad_norm": 1.4005565643310547,
"learning_rate": 2.3368284395738684e-07,
"loss": 0.1734,
"step": 353
},
{
"epoch": 0.9147286821705426,
"grad_norm": 1.3667218685150146,
"learning_rate": 2.2023928664194229e-07,
"loss": 0.1598,
"step": 354
},
{
"epoch": 0.917312661498708,
"grad_norm": 1.2286065816879272,
"learning_rate": 2.0718526251279346e-07,
"loss": 0.1533,
"step": 355
},
{
"epoch": 0.9198966408268734,
"grad_norm": 1.3071902990341187,
"learning_rate": 1.9452183542562785e-07,
"loss": 0.1612,
"step": 356
},
{
"epoch": 0.9224806201550387,
"grad_norm": 1.4558244943618774,
"learning_rate": 1.8225003740388546e-07,
"loss": 0.1624,
"step": 357
},
{
"epoch": 0.9250645994832042,
"grad_norm": 1.3047966957092285,
"learning_rate": 1.7037086855465902e-07,
"loss": 0.1555,
"step": 358
},
{
"epoch": 0.9276485788113695,
"grad_norm": 1.2621203660964966,
"learning_rate": 1.5888529698718347e-07,
"loss": 0.1514,
"step": 359
},
{
"epoch": 0.9302325581395349,
"grad_norm": 1.2364767789840698,
"learning_rate": 1.477942587339426e-07,
"loss": 0.1648,
"step": 360
},
{
"epoch": 0.9328165374677002,
"grad_norm": 1.6543505191802979,
"learning_rate": 1.3709865767438434e-07,
"loss": 0.1732,
"step": 361
},
{
"epoch": 0.9354005167958657,
"grad_norm": 1.1805888414382935,
"learning_rate": 1.2679936546125483e-07,
"loss": 0.1489,
"step": 362
},
{
"epoch": 0.937984496124031,
"grad_norm": 1.443524956703186,
"learning_rate": 1.1689722144956672e-07,
"loss": 0.1772,
"step": 363
},
{
"epoch": 0.9405684754521964,
"grad_norm": 1.4192824363708496,
"learning_rate": 1.0739303262819301e-07,
"loss": 0.1672,
"step": 364
},
{
"epoch": 0.9431524547803618,
"grad_norm": 1.573648452758789,
"learning_rate": 9.82875735540989e-08,
"loss": 0.1635,
"step": 365
},
{
"epoch": 0.9457364341085271,
"grad_norm": 1.3067245483398438,
"learning_rate": 8.95815862892202e-08,
"loss": 0.1664,
"step": 366
},
{
"epoch": 0.9483204134366925,
"grad_norm": 1.5704214572906494,
"learning_rate": 8.127578033998663e-08,
"loss": 0.1985,
"step": 367
},
{
"epoch": 0.9509043927648578,
"grad_norm": 1.3045734167099,
"learning_rate": 7.337083259949918e-08,
"loss": 0.1687,
"step": 368
},
{
"epoch": 0.9534883720930233,
"grad_norm": 1.2257012128829956,
"learning_rate": 6.58673872923693e-08,
"loss": 0.1668,
"step": 369
},
{
"epoch": 0.9560723514211886,
"grad_norm": 1.3284975290298462,
"learning_rate": 5.8766055922211965e-08,
"loss": 0.1604,
"step": 370
},
{
"epoch": 0.958656330749354,
"grad_norm": 1.494699478149414,
"learning_rate": 5.206741722181385e-08,
"loss": 0.1802,
"step": 371
},
{
"epoch": 0.9612403100775194,
"grad_norm": 1.6620988845825195,
"learning_rate": 4.577201710596613e-08,
"loss": 0.1794,
"step": 372
},
{
"epoch": 0.9638242894056848,
"grad_norm": 1.295282244682312,
"learning_rate": 3.98803686269783e-08,
"loss": 0.1607,
"step": 373
},
{
"epoch": 0.9664082687338501,
"grad_norm": 1.3023289442062378,
"learning_rate": 3.439295193286174e-08,
"loss": 0.1539,
"step": 374
},
{
"epoch": 0.9689922480620154,
"grad_norm": 1.3331167697906494,
"learning_rate": 2.9310214228202016e-08,
"loss": 0.1695,
"step": 375
},
{
"epoch": 0.9715762273901809,
"grad_norm": 1.3956187963485718,
"learning_rate": 2.463256973771311e-08,
"loss": 0.1647,
"step": 376
},
{
"epoch": 0.9741602067183462,
"grad_norm": 1.1754802465438843,
"learning_rate": 2.0360399672478826e-08,
"loss": 0.1489,
"step": 377
},
{
"epoch": 0.9767441860465116,
"grad_norm": 1.3734043836593628,
"learning_rate": 1.6494052198886557e-08,
"loss": 0.1675,
"step": 378
},
{
"epoch": 0.979328165374677,
"grad_norm": 1.3153494596481323,
"learning_rate": 1.3033842410251074e-08,
"loss": 0.1568,
"step": 379
},
{
"epoch": 0.9819121447028424,
"grad_norm": 1.3614672422409058,
"learning_rate": 9.980052301137854e-09,
"loss": 0.1564,
"step": 380
},
{
"epoch": 0.9844961240310077,
"grad_norm": 1.2049131393432617,
"learning_rate": 7.332930744380906e-09,
"loss": 0.1575,
"step": 381
},
{
"epoch": 0.9870801033591732,
"grad_norm": 1.2012826204299927,
"learning_rate": 5.092693470798438e-09,
"loss": 0.1483,
"step": 382
},
{
"epoch": 0.9896640826873385,
"grad_norm": 1.3296922445297241,
"learning_rate": 3.2595230516152543e-09,
"loss": 0.1578,
"step": 383
},
{
"epoch": 0.9922480620155039,
"grad_norm": 1.3670560121536255,
"learning_rate": 1.8335688835802169e-09,
"loss": 0.1673,
"step": 384
},
{
"epoch": 0.9948320413436692,
"grad_norm": 1.4654539823532104,
"learning_rate": 8.149471767937567e-10,
"loss": 0.1594,
"step": 385
},
{
"epoch": 0.9974160206718347,
"grad_norm": 1.3917102813720703,
"learning_rate": 2.0374094523600841e-10,
"loss": 0.1723,
"step": 386
},
{
"epoch": 1.0,
"grad_norm": 1.2807058095932007,
"learning_rate": 0.0,
"loss": 0.1694,
"step": 387
},
{
"epoch": 1.0,
"eval_loss": 0.3819105327129364,
"eval_runtime": 3.48,
"eval_samples_per_second": 66.091,
"eval_steps_per_second": 2.874,
"step": 387
},
{
"epoch": 1.0,
"step": 387,
"total_flos": 1.3654500629387674e+17,
"train_loss": 0.24298929205544542,
"train_runtime": 1239.3737,
"train_samples_per_second": 14.982,
"train_steps_per_second": 0.312
}
],
"logging_steps": 1,
"max_steps": 387,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 800,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3654500629387674e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}