model-calm3 / trainer_state.json
Kendamarron's picture
Upload folder using huggingface_hub
41eec31 verified
Raw History Blame Contribute Delete
85.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 492,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0040650406504065045,
"grad_norm": 7.601864633791059,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.6619,
"step": 1
},
{
"epoch": 0.008130081300813009,
"grad_norm": 8.90950489095892,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.6939,
"step": 2
},
{
"epoch": 0.012195121951219513,
"grad_norm": 8.653661544119263,
"learning_rate": 6.000000000000001e-07,
"loss": 1.6815,
"step": 3
},
{
"epoch": 0.016260162601626018,
"grad_norm": 8.19389905975729,
"learning_rate": 8.000000000000001e-07,
"loss": 1.6773,
"step": 4
},
{
"epoch": 0.02032520325203252,
"grad_norm": 7.660785574860422,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.6592,
"step": 5
},
{
"epoch": 0.024390243902439025,
"grad_norm": 7.52084161369647,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.5694,
"step": 6
},
{
"epoch": 0.028455284552845527,
"grad_norm": 7.899024403331175,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.6924,
"step": 7
},
{
"epoch": 0.032520325203252036,
"grad_norm": 6.509312845370045,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.7214,
"step": 8
},
{
"epoch": 0.036585365853658534,
"grad_norm": 5.841824414556262,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.6014,
"step": 9
},
{
"epoch": 0.04065040650406504,
"grad_norm": 5.9478840184326796,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.5693,
"step": 10
},
{
"epoch": 0.044715447154471545,
"grad_norm": 4.622354276343799,
"learning_rate": 2.2e-06,
"loss": 1.5511,
"step": 11
},
{
"epoch": 0.04878048780487805,
"grad_norm": 5.333135757501214,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.5934,
"step": 12
},
{
"epoch": 0.052845528455284556,
"grad_norm": 4.933827488901234,
"learning_rate": 2.6e-06,
"loss": 1.5078,
"step": 13
},
{
"epoch": 0.056910569105691054,
"grad_norm": 4.384469679367266,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.4271,
"step": 14
},
{
"epoch": 0.06097560975609756,
"grad_norm": 5.201629229354225,
"learning_rate": 3e-06,
"loss": 1.4909,
"step": 15
},
{
"epoch": 0.06504065040650407,
"grad_norm": 5.370469326586405,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.2898,
"step": 16
},
{
"epoch": 0.06910569105691057,
"grad_norm": 4.594077436852246,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.6093,
"step": 17
},
{
"epoch": 0.07317073170731707,
"grad_norm": 4.562436798697651,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.533,
"step": 18
},
{
"epoch": 0.07723577235772358,
"grad_norm": 3.9560249475105427,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.5155,
"step": 19
},
{
"epoch": 0.08130081300813008,
"grad_norm": 4.107368289795713,
"learning_rate": 4.000000000000001e-06,
"loss": 1.5223,
"step": 20
},
{
"epoch": 0.08536585365853659,
"grad_norm": 4.217408440842752,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.4386,
"step": 21
},
{
"epoch": 0.08943089430894309,
"grad_norm": 4.3572778395491625,
"learning_rate": 4.4e-06,
"loss": 1.4819,
"step": 22
},
{
"epoch": 0.09349593495934959,
"grad_norm": 3.960914517136647,
"learning_rate": 4.600000000000001e-06,
"loss": 1.4183,
"step": 23
},
{
"epoch": 0.0975609756097561,
"grad_norm": 4.277795090912468,
"learning_rate": 4.800000000000001e-06,
"loss": 1.4352,
"step": 24
},
{
"epoch": 0.1016260162601626,
"grad_norm": 3.662410257559992,
"learning_rate": 5e-06,
"loss": 1.3187,
"step": 25
},
{
"epoch": 0.10569105691056911,
"grad_norm": 3.632520878287309,
"learning_rate": 5.2e-06,
"loss": 1.3634,
"step": 26
},
{
"epoch": 0.10975609756097561,
"grad_norm": 3.7695635315480516,
"learning_rate": 5.400000000000001e-06,
"loss": 1.3945,
"step": 27
},
{
"epoch": 0.11382113821138211,
"grad_norm": 4.618813786367727,
"learning_rate": 5.600000000000001e-06,
"loss": 1.4065,
"step": 28
},
{
"epoch": 0.11788617886178862,
"grad_norm": 4.360295729569898,
"learning_rate": 5.8e-06,
"loss": 1.4983,
"step": 29
},
{
"epoch": 0.12195121951219512,
"grad_norm": 3.4401062155218174,
"learning_rate": 6e-06,
"loss": 1.3678,
"step": 30
},
{
"epoch": 0.12601626016260162,
"grad_norm": 3.3378295453212403,
"learning_rate": 6.200000000000001e-06,
"loss": 1.422,
"step": 31
},
{
"epoch": 0.13008130081300814,
"grad_norm": 3.7133755764351424,
"learning_rate": 6.4000000000000006e-06,
"loss": 1.3796,
"step": 32
},
{
"epoch": 0.13414634146341464,
"grad_norm": 3.6484038120294344,
"learning_rate": 6.600000000000001e-06,
"loss": 1.3597,
"step": 33
},
{
"epoch": 0.13821138211382114,
"grad_norm": 3.9758580501492196,
"learning_rate": 6.800000000000001e-06,
"loss": 1.4014,
"step": 34
},
{
"epoch": 0.14227642276422764,
"grad_norm": 3.7673644641995727,
"learning_rate": 7e-06,
"loss": 1.3976,
"step": 35
},
{
"epoch": 0.14634146341463414,
"grad_norm": 3.4986919364189983,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.3708,
"step": 36
},
{
"epoch": 0.15040650406504066,
"grad_norm": 3.642524443198873,
"learning_rate": 7.4e-06,
"loss": 1.4249,
"step": 37
},
{
"epoch": 0.15447154471544716,
"grad_norm": 3.6896856780557825,
"learning_rate": 7.600000000000001e-06,
"loss": 1.4171,
"step": 38
},
{
"epoch": 0.15853658536585366,
"grad_norm": 3.5980645790229913,
"learning_rate": 7.800000000000002e-06,
"loss": 1.4014,
"step": 39
},
{
"epoch": 0.16260162601626016,
"grad_norm": 3.7186995729013836,
"learning_rate": 8.000000000000001e-06,
"loss": 1.3785,
"step": 40
},
{
"epoch": 0.16666666666666666,
"grad_norm": 3.5494019559541923,
"learning_rate": 8.2e-06,
"loss": 1.3188,
"step": 41
},
{
"epoch": 0.17073170731707318,
"grad_norm": 3.6394025889041965,
"learning_rate": 8.400000000000001e-06,
"loss": 1.3922,
"step": 42
},
{
"epoch": 0.17479674796747968,
"grad_norm": 3.4664594843390253,
"learning_rate": 8.6e-06,
"loss": 1.3229,
"step": 43
},
{
"epoch": 0.17886178861788618,
"grad_norm": 3.5077042343329436,
"learning_rate": 8.8e-06,
"loss": 1.2871,
"step": 44
},
{
"epoch": 0.18292682926829268,
"grad_norm": 3.7315881333644576,
"learning_rate": 9e-06,
"loss": 1.2928,
"step": 45
},
{
"epoch": 0.18699186991869918,
"grad_norm": 3.5393367592332163,
"learning_rate": 9.200000000000002e-06,
"loss": 1.2226,
"step": 46
},
{
"epoch": 0.1910569105691057,
"grad_norm": 3.218556473562904,
"learning_rate": 9.4e-06,
"loss": 1.2773,
"step": 47
},
{
"epoch": 0.1951219512195122,
"grad_norm": 2.977113069721881,
"learning_rate": 9.600000000000001e-06,
"loss": 1.1747,
"step": 48
},
{
"epoch": 0.1991869918699187,
"grad_norm": 3.8506682201925,
"learning_rate": 9.800000000000001e-06,
"loss": 1.3404,
"step": 49
},
{
"epoch": 0.2032520325203252,
"grad_norm": 3.2240933605706497,
"learning_rate": 1e-05,
"loss": 1.264,
"step": 50
},
{
"epoch": 0.2073170731707317,
"grad_norm": 3.333549619646554,
"learning_rate": 9.999873702897528e-06,
"loss": 1.2899,
"step": 51
},
{
"epoch": 0.21138211382113822,
"grad_norm": 4.403650985310743,
"learning_rate": 9.999494817970498e-06,
"loss": 1.3726,
"step": 52
},
{
"epoch": 0.21544715447154472,
"grad_norm": 3.8361682976277383,
"learning_rate": 9.998863364359734e-06,
"loss": 1.3113,
"step": 53
},
{
"epoch": 0.21951219512195122,
"grad_norm": 3.534046334234316,
"learning_rate": 9.997979373965542e-06,
"loss": 1.2444,
"step": 54
},
{
"epoch": 0.22357723577235772,
"grad_norm": 3.4704662905451182,
"learning_rate": 9.996842891446092e-06,
"loss": 1.2575,
"step": 55
},
{
"epoch": 0.22764227642276422,
"grad_norm": 3.3962483960282213,
"learning_rate": 9.995453974215164e-06,
"loss": 1.3113,
"step": 56
},
{
"epoch": 0.23170731707317074,
"grad_norm": 3.9086253718511066,
"learning_rate": 9.993812692439247e-06,
"loss": 1.3813,
"step": 57
},
{
"epoch": 0.23577235772357724,
"grad_norm": 3.843292149715078,
"learning_rate": 9.991919129033994e-06,
"loss": 1.353,
"step": 58
},
{
"epoch": 0.23983739837398374,
"grad_norm": 3.9260638911409473,
"learning_rate": 9.98977337966003e-06,
"loss": 1.3387,
"step": 59
},
{
"epoch": 0.24390243902439024,
"grad_norm": 3.795877124355826,
"learning_rate": 9.987375552718133e-06,
"loss": 1.3114,
"step": 60
},
{
"epoch": 0.24796747967479674,
"grad_norm": 3.5580148523465,
"learning_rate": 9.984725769343737e-06,
"loss": 1.2415,
"step": 61
},
{
"epoch": 0.25203252032520324,
"grad_norm": 3.9767665126163902,
"learning_rate": 9.981824163400827e-06,
"loss": 1.4033,
"step": 62
},
{
"epoch": 0.25609756097560976,
"grad_norm": 3.55177606133293,
"learning_rate": 9.978670881475173e-06,
"loss": 1.3146,
"step": 63
},
{
"epoch": 0.2601626016260163,
"grad_norm": 3.6363875922745357,
"learning_rate": 9.975266082866923e-06,
"loss": 1.2341,
"step": 64
},
{
"epoch": 0.26422764227642276,
"grad_norm": 3.737770535479784,
"learning_rate": 9.971609939582556e-06,
"loss": 1.2754,
"step": 65
},
{
"epoch": 0.2682926829268293,
"grad_norm": 3.037718171173777,
"learning_rate": 9.967702636326195e-06,
"loss": 1.3051,
"step": 66
},
{
"epoch": 0.27235772357723576,
"grad_norm": 3.2961244132241916,
"learning_rate": 9.96354437049027e-06,
"loss": 1.2848,
"step": 67
},
{
"epoch": 0.2764227642276423,
"grad_norm": 3.2454017036305434,
"learning_rate": 9.959135352145552e-06,
"loss": 1.3085,
"step": 68
},
{
"epoch": 0.2804878048780488,
"grad_norm": 3.5811119753587786,
"learning_rate": 9.954475804030539e-06,
"loss": 1.2777,
"step": 69
},
{
"epoch": 0.2845528455284553,
"grad_norm": 3.5163568542082952,
"learning_rate": 9.9495659615402e-06,
"loss": 1.3014,
"step": 70
},
{
"epoch": 0.2886178861788618,
"grad_norm": 3.7745745640357073,
"learning_rate": 9.944406072714086e-06,
"loss": 1.3298,
"step": 71
},
{
"epoch": 0.2926829268292683,
"grad_norm": 3.442814199481373,
"learning_rate": 9.938996398223802e-06,
"loss": 1.2849,
"step": 72
},
{
"epoch": 0.2967479674796748,
"grad_norm": 3.5095835123074837,
"learning_rate": 9.933337211359833e-06,
"loss": 1.2972,
"step": 73
},
{
"epoch": 0.3008130081300813,
"grad_norm": 3.380832113619762,
"learning_rate": 9.927428798017738e-06,
"loss": 1.2526,
"step": 74
},
{
"epoch": 0.3048780487804878,
"grad_norm": 3.549622447623024,
"learning_rate": 9.921271456683716e-06,
"loss": 1.3452,
"step": 75
},
{
"epoch": 0.3089430894308943,
"grad_norm": 3.4510120500688486,
"learning_rate": 9.91486549841951e-06,
"loss": 1.2526,
"step": 76
},
{
"epoch": 0.3130081300813008,
"grad_norm": 2.842150717683876,
"learning_rate": 9.908211246846708e-06,
"loss": 1.0849,
"step": 77
},
{
"epoch": 0.3170731707317073,
"grad_norm": 3.3573562351627873,
"learning_rate": 9.901309038130392e-06,
"loss": 1.3273,
"step": 78
},
{
"epoch": 0.32113821138211385,
"grad_norm": 3.170270363953111,
"learning_rate": 9.894159220962138e-06,
"loss": 1.1891,
"step": 79
},
{
"epoch": 0.3252032520325203,
"grad_norm": 3.160386778853492,
"learning_rate": 9.886762156542428e-06,
"loss": 1.2224,
"step": 80
},
{
"epoch": 0.32926829268292684,
"grad_norm": 4.360816086949134,
"learning_rate": 9.879118218562384e-06,
"loss": 1.2974,
"step": 81
},
{
"epoch": 0.3333333333333333,
"grad_norm": 3.548780694975849,
"learning_rate": 9.871227793184893e-06,
"loss": 1.2506,
"step": 82
},
{
"epoch": 0.33739837398373984,
"grad_norm": 3.5704089080384436,
"learning_rate": 9.863091279025095e-06,
"loss": 1.3203,
"step": 83
},
{
"epoch": 0.34146341463414637,
"grad_norm": 3.553759595140404,
"learning_rate": 9.854709087130261e-06,
"loss": 1.2636,
"step": 84
},
{
"epoch": 0.34552845528455284,
"grad_norm": 3.3202811856289087,
"learning_rate": 9.846081640959008e-06,
"loss": 1.2846,
"step": 85
},
{
"epoch": 0.34959349593495936,
"grad_norm": 3.6676665259046386,
"learning_rate": 9.837209376359918e-06,
"loss": 1.28,
"step": 86
},
{
"epoch": 0.35365853658536583,
"grad_norm": 3.5592429684221054,
"learning_rate": 9.828092741549513e-06,
"loss": 1.349,
"step": 87
},
{
"epoch": 0.35772357723577236,
"grad_norm": 3.415634726891849,
"learning_rate": 9.81873219708962e-06,
"loss": 1.3083,
"step": 88
},
{
"epoch": 0.3617886178861789,
"grad_norm": 4.020648891307815,
"learning_rate": 9.809128215864096e-06,
"loss": 1.375,
"step": 89
},
{
"epoch": 0.36585365853658536,
"grad_norm": 3.613669367094324,
"learning_rate": 9.79928128305494e-06,
"loss": 1.2763,
"step": 90
},
{
"epoch": 0.3699186991869919,
"grad_norm": 3.7024304415446605,
"learning_rate": 9.789191896117786e-06,
"loss": 1.3228,
"step": 91
},
{
"epoch": 0.37398373983739835,
"grad_norm": 3.3762140596742096,
"learning_rate": 9.778860564756769e-06,
"loss": 1.2107,
"step": 92
},
{
"epoch": 0.3780487804878049,
"grad_norm": 3.568415339282542,
"learning_rate": 9.768287810898773e-06,
"loss": 1.3002,
"step": 93
},
{
"epoch": 0.3821138211382114,
"grad_norm": 3.3507745036610443,
"learning_rate": 9.757474168667072e-06,
"loss": 1.272,
"step": 94
},
{
"epoch": 0.3861788617886179,
"grad_norm": 3.683831331611201,
"learning_rate": 9.746420184354334e-06,
"loss": 1.2288,
"step": 95
},
{
"epoch": 0.3902439024390244,
"grad_norm": 3.4564185979654702,
"learning_rate": 9.73512641639504e-06,
"loss": 1.2283,
"step": 96
},
{
"epoch": 0.3943089430894309,
"grad_norm": 3.486110029080406,
"learning_rate": 9.723593435337252e-06,
"loss": 1.2981,
"step": 97
},
{
"epoch": 0.3983739837398374,
"grad_norm": 3.4443364500039455,
"learning_rate": 9.711821823813812e-06,
"loss": 1.2062,
"step": 98
},
{
"epoch": 0.4024390243902439,
"grad_norm": 3.887062505086485,
"learning_rate": 9.699812176512887e-06,
"loss": 1.3186,
"step": 99
},
{
"epoch": 0.4065040650406504,
"grad_norm": 3.496296402696931,
"learning_rate": 9.68756510014794e-06,
"loss": 1.2149,
"step": 100
},
{
"epoch": 0.4105691056910569,
"grad_norm": 3.5683061924181265,
"learning_rate": 9.675081213427076e-06,
"loss": 1.2889,
"step": 101
},
{
"epoch": 0.4146341463414634,
"grad_norm": 3.422166716374822,
"learning_rate": 9.66236114702178e-06,
"loss": 1.2545,
"step": 102
},
{
"epoch": 0.4186991869918699,
"grad_norm": 3.5935070368338975,
"learning_rate": 9.649405543535067e-06,
"loss": 1.2812,
"step": 103
},
{
"epoch": 0.42276422764227645,
"grad_norm": 3.2791252508657887,
"learning_rate": 9.636215057469009e-06,
"loss": 1.2451,
"step": 104
},
{
"epoch": 0.4268292682926829,
"grad_norm": 3.751079391290334,
"learning_rate": 9.622790355191672e-06,
"loss": 1.2478,
"step": 105
},
{
"epoch": 0.43089430894308944,
"grad_norm": 3.837109939185116,
"learning_rate": 9.609132114903458e-06,
"loss": 1.3266,
"step": 106
},
{
"epoch": 0.4349593495934959,
"grad_norm": 3.284057289104673,
"learning_rate": 9.595241026602836e-06,
"loss": 1.3096,
"step": 107
},
{
"epoch": 0.43902439024390244,
"grad_norm": 3.353970714894927,
"learning_rate": 9.581117792051487e-06,
"loss": 1.3307,
"step": 108
},
{
"epoch": 0.44308943089430897,
"grad_norm": 3.4407863626104738,
"learning_rate": 9.56676312473885e-06,
"loss": 1.2742,
"step": 109
},
{
"epoch": 0.44715447154471544,
"grad_norm": 3.274727411422373,
"learning_rate": 9.552177749846083e-06,
"loss": 1.1484,
"step": 110
},
{
"epoch": 0.45121951219512196,
"grad_norm": 3.686780707426172,
"learning_rate": 9.537362404209419e-06,
"loss": 1.2624,
"step": 111
},
{
"epoch": 0.45528455284552843,
"grad_norm": 3.130585181158449,
"learning_rate": 9.522317836282949e-06,
"loss": 1.1935,
"step": 112
},
{
"epoch": 0.45934959349593496,
"grad_norm": 3.1546672900599075,
"learning_rate": 9.507044806100806e-06,
"loss": 1.3123,
"step": 113
},
{
"epoch": 0.4634146341463415,
"grad_norm": 3.1583283930267627,
"learning_rate": 9.491544085238778e-06,
"loss": 1.254,
"step": 114
},
{
"epoch": 0.46747967479674796,
"grad_norm": 3.8792518686316257,
"learning_rate": 9.475816456775313e-06,
"loss": 1.2213,
"step": 115
},
{
"epoch": 0.4715447154471545,
"grad_norm": 3.632580019405141,
"learning_rate": 9.459862715251973e-06,
"loss": 1.1208,
"step": 116
},
{
"epoch": 0.47560975609756095,
"grad_norm": 3.406515110364018,
"learning_rate": 9.44368366663329e-06,
"loss": 1.2806,
"step": 117
},
{
"epoch": 0.4796747967479675,
"grad_norm": 3.257262930401774,
"learning_rate": 9.427280128266049e-06,
"loss": 1.2638,
"step": 118
},
{
"epoch": 0.483739837398374,
"grad_norm": 3.384791751364498,
"learning_rate": 9.410652928837998e-06,
"loss": 1.2427,
"step": 119
},
{
"epoch": 0.4878048780487805,
"grad_norm": 3.4993557102778667,
"learning_rate": 9.393802908335978e-06,
"loss": 1.3081,
"step": 120
},
{
"epoch": 0.491869918699187,
"grad_norm": 3.5191969210120044,
"learning_rate": 9.376730918003495e-06,
"loss": 1.2625,
"step": 121
},
{
"epoch": 0.4959349593495935,
"grad_norm": 3.45753132618439,
"learning_rate": 9.359437820297716e-06,
"loss": 1.3023,
"step": 122
},
{
"epoch": 0.5,
"grad_norm": 3.2143713848767095,
"learning_rate": 9.341924488845892e-06,
"loss": 1.1889,
"step": 123
},
{
"epoch": 0.5040650406504065,
"grad_norm": 3.394160025526671,
"learning_rate": 9.324191808401235e-06,
"loss": 1.225,
"step": 124
},
{
"epoch": 0.508130081300813,
"grad_norm": 3.3553054022592272,
"learning_rate": 9.306240674798203e-06,
"loss": 1.2471,
"step": 125
},
{
"epoch": 0.5121951219512195,
"grad_norm": 3.5363040242500414,
"learning_rate": 9.288071994907262e-06,
"loss": 1.2121,
"step": 126
},
{
"epoch": 0.516260162601626,
"grad_norm": 3.5513644491592378,
"learning_rate": 9.269686686589063e-06,
"loss": 1.2605,
"step": 127
},
{
"epoch": 0.5203252032520326,
"grad_norm": 3.2096183499210684,
"learning_rate": 9.251085678648072e-06,
"loss": 1.2181,
"step": 128
},
{
"epoch": 0.524390243902439,
"grad_norm": 3.8349171328561047,
"learning_rate": 9.232269910785651e-06,
"loss": 1.2922,
"step": 129
},
{
"epoch": 0.5284552845528455,
"grad_norm": 3.3870433308761685,
"learning_rate": 9.213240333552589e-06,
"loss": 1.3359,
"step": 130
},
{
"epoch": 0.532520325203252,
"grad_norm": 3.119886674331583,
"learning_rate": 9.193997908301069e-06,
"loss": 1.2201,
"step": 131
},
{
"epoch": 0.5365853658536586,
"grad_norm": 3.4328684239264073,
"learning_rate": 9.174543607136111e-06,
"loss": 1.2733,
"step": 132
},
{
"epoch": 0.540650406504065,
"grad_norm": 3.5211778075079745,
"learning_rate": 9.154878412866465e-06,
"loss": 1.1865,
"step": 133
},
{
"epoch": 0.5447154471544715,
"grad_norm": 3.8457560436654905,
"learning_rate": 9.135003318954954e-06,
"loss": 1.2656,
"step": 134
},
{
"epoch": 0.5487804878048781,
"grad_norm": 2.860252954067704,
"learning_rate": 9.114919329468283e-06,
"loss": 1.0367,
"step": 135
},
{
"epoch": 0.5528455284552846,
"grad_norm": 3.1966625529009525,
"learning_rate": 9.094627459026326e-06,
"loss": 1.1913,
"step": 136
},
{
"epoch": 0.556910569105691,
"grad_norm": 3.3586333848047687,
"learning_rate": 9.074128732750859e-06,
"loss": 1.1965,
"step": 137
},
{
"epoch": 0.5609756097560976,
"grad_norm": 3.309006715689175,
"learning_rate": 9.053424186213776e-06,
"loss": 1.2739,
"step": 138
},
{
"epoch": 0.5650406504065041,
"grad_norm": 3.610998899181065,
"learning_rate": 9.032514865384767e-06,
"loss": 1.2361,
"step": 139
},
{
"epoch": 0.5691056910569106,
"grad_norm": 3.4092607492941123,
"learning_rate": 9.011401826578492e-06,
"loss": 1.2756,
"step": 140
},
{
"epoch": 0.573170731707317,
"grad_norm": 3.123803335281385,
"learning_rate": 8.990086136401199e-06,
"loss": 1.2046,
"step": 141
},
{
"epoch": 0.5772357723577236,
"grad_norm": 3.2180832415739746,
"learning_rate": 8.968568871696847e-06,
"loss": 1.2454,
"step": 142
},
{
"epoch": 0.5813008130081301,
"grad_norm": 3.392256479625929,
"learning_rate": 8.946851119492717e-06,
"loss": 1.2346,
"step": 143
},
{
"epoch": 0.5853658536585366,
"grad_norm": 3.5203027610167994,
"learning_rate": 8.924933976944474e-06,
"loss": 1.2098,
"step": 144
},
{
"epoch": 0.5894308943089431,
"grad_norm": 3.293995047135828,
"learning_rate": 8.902818551280758e-06,
"loss": 1.249,
"step": 145
},
{
"epoch": 0.5934959349593496,
"grad_norm": 2.8665049252390253,
"learning_rate": 8.880505959747245e-06,
"loss": 1.0725,
"step": 146
},
{
"epoch": 0.5975609756097561,
"grad_norm": 3.2594550044177524,
"learning_rate": 8.857997329550195e-06,
"loss": 1.2146,
"step": 147
},
{
"epoch": 0.6016260162601627,
"grad_norm": 3.445446281697995,
"learning_rate": 8.835293797799517e-06,
"loss": 1.3262,
"step": 148
},
{
"epoch": 0.6056910569105691,
"grad_norm": 3.9317510029226934,
"learning_rate": 8.812396511451324e-06,
"loss": 1.3188,
"step": 149
},
{
"epoch": 0.6097560975609756,
"grad_norm": 3.198084168395092,
"learning_rate": 8.789306627249985e-06,
"loss": 1.3008,
"step": 150
},
{
"epoch": 0.6138211382113821,
"grad_norm": 3.063778345515228,
"learning_rate": 8.766025311669685e-06,
"loss": 0.9978,
"step": 151
},
{
"epoch": 0.6178861788617886,
"grad_norm": 3.2905300689457637,
"learning_rate": 8.742553740855507e-06,
"loss": 1.2479,
"step": 152
},
{
"epoch": 0.6219512195121951,
"grad_norm": 3.395304079212877,
"learning_rate": 8.718893100564002e-06,
"loss": 1.2713,
"step": 153
},
{
"epoch": 0.6260162601626016,
"grad_norm": 3.522348630348412,
"learning_rate": 8.695044586103297e-06,
"loss": 1.2753,
"step": 154
},
{
"epoch": 0.6300813008130082,
"grad_norm": 3.2582864801451987,
"learning_rate": 8.6710094022727e-06,
"loss": 1.2243,
"step": 155
},
{
"epoch": 0.6341463414634146,
"grad_norm": 3.8766071391892125,
"learning_rate": 8.646788763301842e-06,
"loss": 1.2652,
"step": 156
},
{
"epoch": 0.6382113821138211,
"grad_norm": 2.9196919853077503,
"learning_rate": 8.62238389278933e-06,
"loss": 1.1576,
"step": 157
},
{
"epoch": 0.6422764227642277,
"grad_norm": 3.247641592653831,
"learning_rate": 8.59779602364094e-06,
"loss": 1.3151,
"step": 158
},
{
"epoch": 0.6463414634146342,
"grad_norm": 3.025628331987507,
"learning_rate": 8.573026398007323e-06,
"loss": 1.245,
"step": 159
},
{
"epoch": 0.6504065040650406,
"grad_norm": 3.1296381446742427,
"learning_rate": 8.548076267221258e-06,
"loss": 1.2281,
"step": 160
},
{
"epoch": 0.6544715447154471,
"grad_norm": 3.7321890066352874,
"learning_rate": 8.52294689173443e-06,
"loss": 1.2551,
"step": 161
},
{
"epoch": 0.6585365853658537,
"grad_norm": 3.0970454939543113,
"learning_rate": 8.497639541053769e-06,
"loss": 1.1847,
"step": 162
},
{
"epoch": 0.6626016260162602,
"grad_norm": 3.0874953153607043,
"learning_rate": 8.472155493677299e-06,
"loss": 1.2401,
"step": 163
},
{
"epoch": 0.6666666666666666,
"grad_norm": 3.5716326976346977,
"learning_rate": 8.446496037029555e-06,
"loss": 1.2741,
"step": 164
},
{
"epoch": 0.6707317073170732,
"grad_norm": 3.274519329536325,
"learning_rate": 8.420662467396548e-06,
"loss": 1.2243,
"step": 165
},
{
"epoch": 0.6747967479674797,
"grad_norm": 3.0273430953677285,
"learning_rate": 8.394656089860274e-06,
"loss": 1.2116,
"step": 166
},
{
"epoch": 0.6788617886178862,
"grad_norm": 3.7987378754555903,
"learning_rate": 8.368478218232787e-06,
"loss": 1.2516,
"step": 167
},
{
"epoch": 0.6829268292682927,
"grad_norm": 3.1571140529158686,
"learning_rate": 8.342130174989819e-06,
"loss": 1.2202,
"step": 168
},
{
"epoch": 0.6869918699186992,
"grad_norm": 3.4795978849026015,
"learning_rate": 8.315613291203977e-06,
"loss": 1.2015,
"step": 169
},
{
"epoch": 0.6910569105691057,
"grad_norm": 3.356846206738464,
"learning_rate": 8.288928906477497e-06,
"loss": 1.2784,
"step": 170
},
{
"epoch": 0.6951219512195121,
"grad_norm": 2.975674164772659,
"learning_rate": 8.262078368874566e-06,
"loss": 1.2806,
"step": 171
},
{
"epoch": 0.6991869918699187,
"grad_norm": 3.342698854245282,
"learning_rate": 8.235063034853228e-06,
"loss": 1.2434,
"step": 172
},
{
"epoch": 0.7032520325203252,
"grad_norm": 3.0021574646304265,
"learning_rate": 8.207884269196845e-06,
"loss": 1.2371,
"step": 173
},
{
"epoch": 0.7073170731707317,
"grad_norm": 3.371641208018489,
"learning_rate": 8.180543444945154e-06,
"loss": 1.2584,
"step": 174
},
{
"epoch": 0.7113821138211383,
"grad_norm": 3.4756530230066836,
"learning_rate": 8.153041943324912e-06,
"loss": 1.2621,
"step": 175
},
{
"epoch": 0.7154471544715447,
"grad_norm": 3.677440247481686,
"learning_rate": 8.125381153680103e-06,
"loss": 1.291,
"step": 176
},
{
"epoch": 0.7195121951219512,
"grad_norm": 3.724344603809136,
"learning_rate": 8.097562473401764e-06,
"loss": 1.1983,
"step": 177
},
{
"epoch": 0.7235772357723578,
"grad_norm": 3.881220605239073,
"learning_rate": 8.069587307857377e-06,
"loss": 1.3263,
"step": 178
},
{
"epoch": 0.7276422764227642,
"grad_norm": 3.2310425283801596,
"learning_rate": 8.041457070319884e-06,
"loss": 1.2153,
"step": 179
},
{
"epoch": 0.7317073170731707,
"grad_norm": 3.3870881335987857,
"learning_rate": 8.013173181896283e-06,
"loss": 1.3346,
"step": 180
},
{
"epoch": 0.7357723577235772,
"grad_norm": 3.1452509757261056,
"learning_rate": 7.984737071455834e-06,
"loss": 1.2516,
"step": 181
},
{
"epoch": 0.7398373983739838,
"grad_norm": 3.173497495557972,
"learning_rate": 7.95615017555788e-06,
"loss": 1.2476,
"step": 182
},
{
"epoch": 0.7439024390243902,
"grad_norm": 3.539096701539341,
"learning_rate": 7.927413938379268e-06,
"loss": 1.1907,
"step": 183
},
{
"epoch": 0.7479674796747967,
"grad_norm": 3.8034573367911424,
"learning_rate": 7.898529811641393e-06,
"loss": 1.2354,
"step": 184
},
{
"epoch": 0.7520325203252033,
"grad_norm": 3.6222299487232985,
"learning_rate": 7.869499254536865e-06,
"loss": 1.1107,
"step": 185
},
{
"epoch": 0.7560975609756098,
"grad_norm": 3.353460855074601,
"learning_rate": 7.84032373365578e-06,
"loss": 1.2157,
"step": 186
},
{
"epoch": 0.7601626016260162,
"grad_norm": 3.5757972164092418,
"learning_rate": 7.811004722911637e-06,
"loss": 1.2422,
"step": 187
},
{
"epoch": 0.7642276422764228,
"grad_norm": 3.200921333461777,
"learning_rate": 7.781543703466881e-06,
"loss": 1.3359,
"step": 188
},
{
"epoch": 0.7682926829268293,
"grad_norm": 3.37458572836464,
"learning_rate": 7.751942163658066e-06,
"loss": 1.2325,
"step": 189
},
{
"epoch": 0.7723577235772358,
"grad_norm": 3.336790278155762,
"learning_rate": 7.722201598920673e-06,
"loss": 1.289,
"step": 190
},
{
"epoch": 0.7764227642276422,
"grad_norm": 3.6578390679880677,
"learning_rate": 7.692323511713568e-06,
"loss": 1.2832,
"step": 191
},
{
"epoch": 0.7804878048780488,
"grad_norm": 3.7372849061035307,
"learning_rate": 7.662309411443084e-06,
"loss": 1.2682,
"step": 192
},
{
"epoch": 0.7845528455284553,
"grad_norm": 3.4787988556346177,
"learning_rate": 7.63216081438678e-06,
"loss": 1.2566,
"step": 193
},
{
"epoch": 0.7886178861788617,
"grad_norm": 3.2972501647590295,
"learning_rate": 7.601879243616838e-06,
"loss": 1.2405,
"step": 194
},
{
"epoch": 0.7926829268292683,
"grad_norm": 3.08018485547122,
"learning_rate": 7.571466228923115e-06,
"loss": 1.2073,
"step": 195
},
{
"epoch": 0.7967479674796748,
"grad_norm": 3.4711819604946346,
"learning_rate": 7.540923306735868e-06,
"loss": 1.2299,
"step": 196
},
{
"epoch": 0.8008130081300813,
"grad_norm": 2.965090576227292,
"learning_rate": 7.510252020048121e-06,
"loss": 1.219,
"step": 197
},
{
"epoch": 0.8048780487804879,
"grad_norm": 3.430612679713931,
"learning_rate": 7.479453918337733e-06,
"loss": 1.1801,
"step": 198
},
{
"epoch": 0.8089430894308943,
"grad_norm": 3.5256924218857364,
"learning_rate": 7.448530557489105e-06,
"loss": 1.2364,
"step": 199
},
{
"epoch": 0.8130081300813008,
"grad_norm": 3.3729004326724232,
"learning_rate": 7.417483499714589e-06,
"loss": 1.2172,
"step": 200
},
{
"epoch": 0.8170731707317073,
"grad_norm": 3.704140279583858,
"learning_rate": 7.386314313475557e-06,
"loss": 1.2462,
"step": 201
},
{
"epoch": 0.8211382113821138,
"grad_norm": 2.859256884612927,
"learning_rate": 7.355024573403174e-06,
"loss": 1.1915,
"step": 202
},
{
"epoch": 0.8252032520325203,
"grad_norm": 3.9308992936564455,
"learning_rate": 7.323615860218844e-06,
"loss": 1.2587,
"step": 203
},
{
"epoch": 0.8292682926829268,
"grad_norm": 3.4198261126400498,
"learning_rate": 7.292089760654352e-06,
"loss": 1.2962,
"step": 204
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.3412036255224433,
"learning_rate": 7.2604478673717095e-06,
"loss": 1.2395,
"step": 205
},
{
"epoch": 0.8373983739837398,
"grad_norm": 3.556537641445364,
"learning_rate": 7.2286917788826926e-06,
"loss": 1.2526,
"step": 206
},
{
"epoch": 0.8414634146341463,
"grad_norm": 3.18197682179574,
"learning_rate": 7.196823099468084e-06,
"loss": 1.2601,
"step": 207
},
{
"epoch": 0.8455284552845529,
"grad_norm": 3.395646140761288,
"learning_rate": 7.1648434390966356e-06,
"loss": 1.23,
"step": 208
},
{
"epoch": 0.8495934959349594,
"grad_norm": 3.3928578867441,
"learning_rate": 7.132754413343721e-06,
"loss": 1.2609,
"step": 209
},
{
"epoch": 0.8536585365853658,
"grad_norm": 3.1283882470236106,
"learning_rate": 7.100557643309732e-06,
"loss": 1.1809,
"step": 210
},
{
"epoch": 0.8577235772357723,
"grad_norm": 3.675071025819942,
"learning_rate": 7.0682547555381734e-06,
"loss": 1.2448,
"step": 211
},
{
"epoch": 0.8617886178861789,
"grad_norm": 3.0075418776078444,
"learning_rate": 7.035847381933494e-06,
"loss": 1.21,
"step": 212
},
{
"epoch": 0.8658536585365854,
"grad_norm": 3.457597870123879,
"learning_rate": 7.003337159678649e-06,
"loss": 1.2674,
"step": 213
},
{
"epoch": 0.8699186991869918,
"grad_norm": 3.394032369643457,
"learning_rate": 6.970725731152389e-06,
"loss": 1.2701,
"step": 214
},
{
"epoch": 0.8739837398373984,
"grad_norm": 3.348683954925548,
"learning_rate": 6.938014743846285e-06,
"loss": 1.2723,
"step": 215
},
{
"epoch": 0.8780487804878049,
"grad_norm": 3.380614445439332,
"learning_rate": 6.905205850281502e-06,
"loss": 1.3185,
"step": 216
},
{
"epoch": 0.8821138211382114,
"grad_norm": 2.82083389946448,
"learning_rate": 6.872300707925319e-06,
"loss": 1.0479,
"step": 217
},
{
"epoch": 0.8861788617886179,
"grad_norm": 3.2273081078802806,
"learning_rate": 6.8393009791073895e-06,
"loss": 1.2017,
"step": 218
},
{
"epoch": 0.8902439024390244,
"grad_norm": 2.9799477568840613,
"learning_rate": 6.806208330935766e-06,
"loss": 1.1383,
"step": 219
},
{
"epoch": 0.8943089430894309,
"grad_norm": 3.2837120753465037,
"learning_rate": 6.773024435212678e-06,
"loss": 1.2259,
"step": 220
},
{
"epoch": 0.8983739837398373,
"grad_norm": 3.6449591162008486,
"learning_rate": 6.739750968350081e-06,
"loss": 1.2948,
"step": 221
},
{
"epoch": 0.9024390243902439,
"grad_norm": 3.225238120108855,
"learning_rate": 6.706389611284953e-06,
"loss": 1.1855,
"step": 222
},
{
"epoch": 0.9065040650406504,
"grad_norm": 3.432916919843375,
"learning_rate": 6.6729420493943875e-06,
"loss": 1.247,
"step": 223
},
{
"epoch": 0.9105691056910569,
"grad_norm": 3.0718472155542353,
"learning_rate": 6.639409972410446e-06,
"loss": 1.1905,
"step": 224
},
{
"epoch": 0.9146341463414634,
"grad_norm": 3.3699226964349522,
"learning_rate": 6.605795074334793e-06,
"loss": 1.2424,
"step": 225
},
{
"epoch": 0.9186991869918699,
"grad_norm": 3.3821914270422027,
"learning_rate": 6.57209905335312e-06,
"loss": 1.2114,
"step": 226
},
{
"epoch": 0.9227642276422764,
"grad_norm": 3.025222008403353,
"learning_rate": 6.538323611749351e-06,
"loss": 1.1519,
"step": 227
},
{
"epoch": 0.926829268292683,
"grad_norm": 3.42250194898501,
"learning_rate": 6.504470455819651e-06,
"loss": 1.2768,
"step": 228
},
{
"epoch": 0.9308943089430894,
"grad_norm": 3.446861559528364,
"learning_rate": 6.470541295786222e-06,
"loss": 1.2202,
"step": 229
},
{
"epoch": 0.9349593495934959,
"grad_norm": 3.3472872172040646,
"learning_rate": 6.436537845710904e-06,
"loss": 1.2408,
"step": 230
},
{
"epoch": 0.9390243902439024,
"grad_norm": 3.435994418242901,
"learning_rate": 6.402461823408584e-06,
"loss": 1.193,
"step": 231
},
{
"epoch": 0.943089430894309,
"grad_norm": 3.9739734441369365,
"learning_rate": 6.368314950360416e-06,
"loss": 1.2113,
"step": 232
},
{
"epoch": 0.9471544715447154,
"grad_norm": 3.394258791013482,
"learning_rate": 6.334098951626847e-06,
"loss": 1.2076,
"step": 233
},
{
"epoch": 0.9512195121951219,
"grad_norm": 3.531729806577509,
"learning_rate": 6.299815555760478e-06,
"loss": 1.2218,
"step": 234
},
{
"epoch": 0.9552845528455285,
"grad_norm": 3.014602089114332,
"learning_rate": 6.265466494718731e-06,
"loss": 1.1879,
"step": 235
},
{
"epoch": 0.959349593495935,
"grad_norm": 3.33204325952638,
"learning_rate": 6.231053503776363e-06,
"loss": 1.2008,
"step": 236
},
{
"epoch": 0.9634146341463414,
"grad_norm": 3.344568538684679,
"learning_rate": 6.1965783214377895e-06,
"loss": 1.1897,
"step": 237
},
{
"epoch": 0.967479674796748,
"grad_norm": 3.4113570652803076,
"learning_rate": 6.1620426893492645e-06,
"loss": 1.2736,
"step": 238
},
{
"epoch": 0.9715447154471545,
"grad_norm": 3.4879360711731593,
"learning_rate": 6.127448352210894e-06,
"loss": 1.1798,
"step": 239
},
{
"epoch": 0.975609756097561,
"grad_norm": 3.7021368783212942,
"learning_rate": 6.092797057688496e-06,
"loss": 1.1927,
"step": 240
},
{
"epoch": 0.9796747967479674,
"grad_norm": 3.2380601035094934,
"learning_rate": 6.058090556325305e-06,
"loss": 1.1896,
"step": 241
},
{
"epoch": 0.983739837398374,
"grad_norm": 3.3467517032738994,
"learning_rate": 6.0233306014535505e-06,
"loss": 1.2357,
"step": 242
},
{
"epoch": 0.9878048780487805,
"grad_norm": 3.3216338993009034,
"learning_rate": 5.988518949105862e-06,
"loss": 1.1884,
"step": 243
},
{
"epoch": 0.991869918699187,
"grad_norm": 3.2077249913458985,
"learning_rate": 5.953657357926569e-06,
"loss": 1.2504,
"step": 244
},
{
"epoch": 0.9959349593495935,
"grad_norm": 3.326332160803518,
"learning_rate": 5.918747589082853e-06,
"loss": 1.2548,
"step": 245
},
{
"epoch": 1.0,
"grad_norm": 3.3151307527051257,
"learning_rate": 5.883791406175775e-06,
"loss": 1.1878,
"step": 246
},
{
"epoch": 1.0040650406504066,
"grad_norm": 4.323555049169963,
"learning_rate": 5.848790575151181e-06,
"loss": 0.9153,
"step": 247
},
{
"epoch": 1.008130081300813,
"grad_norm": 3.465939989112603,
"learning_rate": 5.813746864210489e-06,
"loss": 0.8676,
"step": 248
},
{
"epoch": 1.0121951219512195,
"grad_norm": 3.6801149888116336,
"learning_rate": 5.778662043721359e-06,
"loss": 0.926,
"step": 249
},
{
"epoch": 1.016260162601626,
"grad_norm": 3.0713182769499987,
"learning_rate": 5.743537886128258e-06,
"loss": 0.8602,
"step": 250
},
{
"epoch": 1.0203252032520325,
"grad_norm": 3.557190687922137,
"learning_rate": 5.708376165862921e-06,
"loss": 0.9028,
"step": 251
},
{
"epoch": 1.024390243902439,
"grad_norm": 3.3051978717310186,
"learning_rate": 5.673178659254698e-06,
"loss": 0.8645,
"step": 252
},
{
"epoch": 1.0284552845528456,
"grad_norm": 3.6105207649370628,
"learning_rate": 5.637947144440832e-06,
"loss": 0.857,
"step": 253
},
{
"epoch": 1.032520325203252,
"grad_norm": 3.4764241585248548,
"learning_rate": 5.6026834012766155e-06,
"loss": 0.8952,
"step": 254
},
{
"epoch": 1.0365853658536586,
"grad_norm": 3.6901515484750727,
"learning_rate": 5.567389211245486e-06,
"loss": 0.8852,
"step": 255
},
{
"epoch": 1.040650406504065,
"grad_norm": 2.797763471477429,
"learning_rate": 5.532066357369012e-06,
"loss": 0.8064,
"step": 256
},
{
"epoch": 1.0447154471544715,
"grad_norm": 6.8675497317344405,
"learning_rate": 5.496716624116836e-06,
"loss": 0.8803,
"step": 257
},
{
"epoch": 1.048780487804878,
"grad_norm": 3.874898167456331,
"learning_rate": 5.46134179731651e-06,
"loss": 0.7879,
"step": 258
},
{
"epoch": 1.0528455284552845,
"grad_norm": 3.3839912626060116,
"learning_rate": 5.425943664063284e-06,
"loss": 0.8645,
"step": 259
},
{
"epoch": 1.056910569105691,
"grad_norm": 3.3351665786851945,
"learning_rate": 5.390524012629824e-06,
"loss": 0.9009,
"step": 260
},
{
"epoch": 1.0609756097560976,
"grad_norm": 3.15122789490253,
"learning_rate": 5.3550846323758666e-06,
"loss": 0.8388,
"step": 261
},
{
"epoch": 1.065040650406504,
"grad_norm": 3.3003260837011807,
"learning_rate": 5.319627313657829e-06,
"loss": 0.8363,
"step": 262
},
{
"epoch": 1.0691056910569106,
"grad_norm": 2.936698289474364,
"learning_rate": 5.284153847738356e-06,
"loss": 0.8473,
"step": 263
},
{
"epoch": 1.0731707317073171,
"grad_norm": 3.572322782052897,
"learning_rate": 5.248666026695835e-06,
"loss": 0.8801,
"step": 264
},
{
"epoch": 1.0772357723577235,
"grad_norm": 3.129199412648207,
"learning_rate": 5.213165643333851e-06,
"loss": 0.8512,
"step": 265
},
{
"epoch": 1.08130081300813,
"grad_norm": 3.0887292783736577,
"learning_rate": 5.177654491090627e-06,
"loss": 0.8383,
"step": 266
},
{
"epoch": 1.0853658536585367,
"grad_norm": 3.381314067942086,
"learning_rate": 5.1421343639484165e-06,
"loss": 0.8487,
"step": 267
},
{
"epoch": 1.089430894308943,
"grad_norm": 3.6057501707631037,
"learning_rate": 5.1066070563428736e-06,
"loss": 0.8413,
"step": 268
},
{
"epoch": 1.0934959349593496,
"grad_norm": 2.9732383695526634,
"learning_rate": 5.071074363072403e-06,
"loss": 0.7804,
"step": 269
},
{
"epoch": 1.0975609756097562,
"grad_norm": 3.460563360283899,
"learning_rate": 5.035538079207488e-06,
"loss": 0.8791,
"step": 270
},
{
"epoch": 1.1016260162601625,
"grad_norm": 3.2682949069300333,
"learning_rate": 5e-06,
"loss": 0.8705,
"step": 271
},
{
"epoch": 1.1056910569105691,
"grad_norm": 3.308698310047778,
"learning_rate": 4.964461920792512e-06,
"loss": 0.8671,
"step": 272
},
{
"epoch": 1.1097560975609757,
"grad_norm": 3.1081622158579787,
"learning_rate": 4.928925636927597e-06,
"loss": 0.8352,
"step": 273
},
{
"epoch": 1.113821138211382,
"grad_norm": 3.5089544730564337,
"learning_rate": 4.893392943657127e-06,
"loss": 0.8125,
"step": 274
},
{
"epoch": 1.1178861788617886,
"grad_norm": 3.324066226795555,
"learning_rate": 4.857865636051586e-06,
"loss": 0.9,
"step": 275
},
{
"epoch": 1.1219512195121952,
"grad_norm": 2.9061490782523673,
"learning_rate": 4.822345508909376e-06,
"loss": 0.8462,
"step": 276
},
{
"epoch": 1.1260162601626016,
"grad_norm": 2.7881013420756418,
"learning_rate": 4.786834356666153e-06,
"loss": 0.8066,
"step": 277
},
{
"epoch": 1.1300813008130082,
"grad_norm": 3.141214336537279,
"learning_rate": 4.751333973304166e-06,
"loss": 0.8701,
"step": 278
},
{
"epoch": 1.1341463414634148,
"grad_norm": 2.888872540331265,
"learning_rate": 4.715846152261645e-06,
"loss": 0.8046,
"step": 279
},
{
"epoch": 1.1382113821138211,
"grad_norm": 3.353720993292887,
"learning_rate": 4.680372686342173e-06,
"loss": 0.8393,
"step": 280
},
{
"epoch": 1.1422764227642277,
"grad_norm": 3.4262846056368845,
"learning_rate": 4.644915367624134e-06,
"loss": 0.7747,
"step": 281
},
{
"epoch": 1.146341463414634,
"grad_norm": 3.2239577090327893,
"learning_rate": 4.609475987370177e-06,
"loss": 0.797,
"step": 282
},
{
"epoch": 1.1504065040650406,
"grad_norm": 3.223343944139248,
"learning_rate": 4.5740563359367164e-06,
"loss": 0.8407,
"step": 283
},
{
"epoch": 1.1544715447154472,
"grad_norm": 3.1818064609840198,
"learning_rate": 4.53865820268349e-06,
"loss": 0.8241,
"step": 284
},
{
"epoch": 1.1585365853658536,
"grad_norm": 3.1906411149160525,
"learning_rate": 4.503283375883165e-06,
"loss": 0.8057,
"step": 285
},
{
"epoch": 1.1626016260162602,
"grad_norm": 3.632793987489528,
"learning_rate": 4.467933642630989e-06,
"loss": 0.8379,
"step": 286
},
{
"epoch": 1.1666666666666667,
"grad_norm": 2.794213331335638,
"learning_rate": 4.432610788754517e-06,
"loss": 0.6732,
"step": 287
},
{
"epoch": 1.170731707317073,
"grad_norm": 3.436978769265818,
"learning_rate": 4.397316598723385e-06,
"loss": 0.8999,
"step": 288
},
{
"epoch": 1.1747967479674797,
"grad_norm": 3.5914755495139032,
"learning_rate": 4.362052855559171e-06,
"loss": 0.9225,
"step": 289
},
{
"epoch": 1.1788617886178863,
"grad_norm": 3.044495214801385,
"learning_rate": 4.326821340745304e-06,
"loss": 0.8492,
"step": 290
},
{
"epoch": 1.1829268292682926,
"grad_norm": 2.9176213210346478,
"learning_rate": 4.291623834137082e-06,
"loss": 0.6663,
"step": 291
},
{
"epoch": 1.1869918699186992,
"grad_norm": 3.263437323837356,
"learning_rate": 4.256462113871741e-06,
"loss": 0.8919,
"step": 292
},
{
"epoch": 1.1910569105691058,
"grad_norm": 3.420956911951543,
"learning_rate": 4.2213379562786406e-06,
"loss": 0.834,
"step": 293
},
{
"epoch": 1.1951219512195121,
"grad_norm": 2.967387533543618,
"learning_rate": 4.186253135789511e-06,
"loss": 0.8238,
"step": 294
},
{
"epoch": 1.1991869918699187,
"grad_norm": 3.2109782296405425,
"learning_rate": 4.15120942484882e-06,
"loss": 0.8617,
"step": 295
},
{
"epoch": 1.203252032520325,
"grad_norm": 3.483436429896311,
"learning_rate": 4.116208593824227e-06,
"loss": 0.9088,
"step": 296
},
{
"epoch": 1.2073170731707317,
"grad_norm": 3.103671650986791,
"learning_rate": 4.081252410917148e-06,
"loss": 0.8458,
"step": 297
},
{
"epoch": 1.2113821138211383,
"grad_norm": 3.4106408241432598,
"learning_rate": 4.046342642073433e-06,
"loss": 0.8274,
"step": 298
},
{
"epoch": 1.2154471544715446,
"grad_norm": 3.2949066557526288,
"learning_rate": 4.01148105089414e-06,
"loss": 0.8096,
"step": 299
},
{
"epoch": 1.2195121951219512,
"grad_norm": 3.3675251909490402,
"learning_rate": 3.976669398546451e-06,
"loss": 0.894,
"step": 300
},
{
"epoch": 1.2235772357723578,
"grad_norm": 3.0572162762552217,
"learning_rate": 3.941909443674696e-06,
"loss": 0.8826,
"step": 301
},
{
"epoch": 1.2276422764227641,
"grad_norm": 3.0686786710141747,
"learning_rate": 3.907202942311506e-06,
"loss": 0.8403,
"step": 302
},
{
"epoch": 1.2317073170731707,
"grad_norm": 3.3850347568207306,
"learning_rate": 3.872551647789108e-06,
"loss": 0.9008,
"step": 303
},
{
"epoch": 1.2357723577235773,
"grad_norm": 3.568496760837224,
"learning_rate": 3.837957310650738e-06,
"loss": 0.8299,
"step": 304
},
{
"epoch": 1.2398373983739837,
"grad_norm": 3.081234179900163,
"learning_rate": 3.803421678562213e-06,
"loss": 0.7561,
"step": 305
},
{
"epoch": 1.2439024390243902,
"grad_norm": 3.0395181179956294,
"learning_rate": 3.7689464962236367e-06,
"loss": 0.8344,
"step": 306
},
{
"epoch": 1.2479674796747968,
"grad_norm": 2.9387819795914165,
"learning_rate": 3.734533505281269e-06,
"loss": 0.8067,
"step": 307
},
{
"epoch": 1.2520325203252032,
"grad_norm": 3.362022257660303,
"learning_rate": 3.700184444239524e-06,
"loss": 0.8437,
"step": 308
},
{
"epoch": 1.2560975609756098,
"grad_norm": 3.0339266148997295,
"learning_rate": 3.6659010483731543e-06,
"loss": 0.814,
"step": 309
},
{
"epoch": 1.2601626016260163,
"grad_norm": 3.141762645727816,
"learning_rate": 3.6316850496395863e-06,
"loss": 0.8294,
"step": 310
},
{
"epoch": 1.2642276422764227,
"grad_norm": 3.4348088918026662,
"learning_rate": 3.597538176591417e-06,
"loss": 0.7657,
"step": 311
},
{
"epoch": 1.2682926829268293,
"grad_norm": 3.054857603912505,
"learning_rate": 3.563462154289098e-06,
"loss": 0.7799,
"step": 312
},
{
"epoch": 1.2723577235772359,
"grad_norm": 3.4737488253418425,
"learning_rate": 3.5294587042137796e-06,
"loss": 0.8867,
"step": 313
},
{
"epoch": 1.2764227642276422,
"grad_norm": 3.10636831049777,
"learning_rate": 3.49552954418035e-06,
"loss": 0.7944,
"step": 314
},
{
"epoch": 1.2804878048780488,
"grad_norm": 3.0056066846766196,
"learning_rate": 3.461676388250651e-06,
"loss": 0.806,
"step": 315
},
{
"epoch": 1.2845528455284554,
"grad_norm": 3.22935213051317,
"learning_rate": 3.4279009466468825e-06,
"loss": 0.803,
"step": 316
},
{
"epoch": 1.2886178861788617,
"grad_norm": 3.586063282737165,
"learning_rate": 3.3942049256652093e-06,
"loss": 0.889,
"step": 317
},
{
"epoch": 1.2926829268292683,
"grad_norm": 3.290341852319477,
"learning_rate": 3.3605900275895565e-06,
"loss": 0.8793,
"step": 318
},
{
"epoch": 1.296747967479675,
"grad_norm": 2.963322253867672,
"learning_rate": 3.3270579506056146e-06,
"loss": 0.8032,
"step": 319
},
{
"epoch": 1.3008130081300813,
"grad_norm": 3.2168072401660703,
"learning_rate": 3.2936103887150484e-06,
"loss": 0.8563,
"step": 320
},
{
"epoch": 1.3048780487804879,
"grad_norm": 3.1570333927956424,
"learning_rate": 3.2602490316499197e-06,
"loss": 0.8603,
"step": 321
},
{
"epoch": 1.3089430894308944,
"grad_norm": 3.2845649650072812,
"learning_rate": 3.226975564787322e-06,
"loss": 0.8787,
"step": 322
},
{
"epoch": 1.3130081300813008,
"grad_norm": 3.2182847820601146,
"learning_rate": 3.1937916690642356e-06,
"loss": 0.8411,
"step": 323
},
{
"epoch": 1.3170731707317074,
"grad_norm": 3.398939591260855,
"learning_rate": 3.1606990208926125e-06,
"loss": 0.855,
"step": 324
},
{
"epoch": 1.321138211382114,
"grad_norm": 2.706198394059073,
"learning_rate": 3.127699292074683e-06,
"loss": 0.7856,
"step": 325
},
{
"epoch": 1.3252032520325203,
"grad_norm": 3.263791744218598,
"learning_rate": 3.0947941497184985e-06,
"loss": 0.9305,
"step": 326
},
{
"epoch": 1.329268292682927,
"grad_norm": 3.638027473310664,
"learning_rate": 3.0619852561537165e-06,
"loss": 0.8801,
"step": 327
},
{
"epoch": 1.3333333333333333,
"grad_norm": 3.4194690003320964,
"learning_rate": 3.0292742688476125e-06,
"loss": 0.8694,
"step": 328
},
{
"epoch": 1.3373983739837398,
"grad_norm": 2.8625969545690473,
"learning_rate": 2.9966628403213528e-06,
"loss": 0.8601,
"step": 329
},
{
"epoch": 1.3414634146341464,
"grad_norm": 3.149728494159807,
"learning_rate": 2.964152618066508e-06,
"loss": 0.8055,
"step": 330
},
{
"epoch": 1.3455284552845528,
"grad_norm": 3.1471735889701895,
"learning_rate": 2.93174524446183e-06,
"loss": 0.8029,
"step": 331
},
{
"epoch": 1.3495934959349594,
"grad_norm": 3.737033991986332,
"learning_rate": 2.899442356690271e-06,
"loss": 0.8433,
"step": 332
},
{
"epoch": 1.3536585365853657,
"grad_norm": 3.038148294937328,
"learning_rate": 2.8672455866562797e-06,
"loss": 0.7904,
"step": 333
},
{
"epoch": 1.3577235772357723,
"grad_norm": 3.49987749409302,
"learning_rate": 2.835156560903365e-06,
"loss": 0.8513,
"step": 334
},
{
"epoch": 1.3617886178861789,
"grad_norm": 3.4423408822147623,
"learning_rate": 2.803176900531915e-06,
"loss": 0.8699,
"step": 335
},
{
"epoch": 1.3658536585365852,
"grad_norm": 3.0989763636949776,
"learning_rate": 2.771308221117309e-06,
"loss": 0.828,
"step": 336
},
{
"epoch": 1.3699186991869918,
"grad_norm": 3.570239925753034,
"learning_rate": 2.7395521326282913e-06,
"loss": 0.9138,
"step": 337
},
{
"epoch": 1.3739837398373984,
"grad_norm": 2.9867469290330146,
"learning_rate": 2.7079102393456503e-06,
"loss": 0.774,
"step": 338
},
{
"epoch": 1.3780487804878048,
"grad_norm": 3.2405869730657257,
"learning_rate": 2.6763841397811576e-06,
"loss": 0.7736,
"step": 339
},
{
"epoch": 1.3821138211382114,
"grad_norm": 3.3013068491566235,
"learning_rate": 2.6449754265968263e-06,
"loss": 0.8141,
"step": 340
},
{
"epoch": 1.386178861788618,
"grad_norm": 2.9459262525676406,
"learning_rate": 2.6136856865244443e-06,
"loss": 0.8195,
"step": 341
},
{
"epoch": 1.3902439024390243,
"grad_norm": 3.1841733357674364,
"learning_rate": 2.5825165002854124e-06,
"loss": 0.8344,
"step": 342
},
{
"epoch": 1.3943089430894309,
"grad_norm": 3.5810707392643293,
"learning_rate": 2.5514694425108968e-06,
"loss": 0.8499,
"step": 343
},
{
"epoch": 1.3983739837398375,
"grad_norm": 2.9742861052640874,
"learning_rate": 2.5205460816622684e-06,
"loss": 0.8667,
"step": 344
},
{
"epoch": 1.4024390243902438,
"grad_norm": 3.1444266229672575,
"learning_rate": 2.4897479799518797e-06,
"loss": 0.8924,
"step": 345
},
{
"epoch": 1.4065040650406504,
"grad_norm": 3.3362745541137597,
"learning_rate": 2.4590766932641353e-06,
"loss": 0.9045,
"step": 346
},
{
"epoch": 1.410569105691057,
"grad_norm": 3.3267334401886193,
"learning_rate": 2.4285337710768843e-06,
"loss": 0.8234,
"step": 347
},
{
"epoch": 1.4146341463414633,
"grad_norm": 3.1893552375875918,
"learning_rate": 2.3981207563831633e-06,
"loss": 0.8079,
"step": 348
},
{
"epoch": 1.41869918699187,
"grad_norm": 3.2683250472050847,
"learning_rate": 2.3678391856132203e-06,
"loss": 0.8218,
"step": 349
},
{
"epoch": 1.4227642276422765,
"grad_norm": 3.448624987848759,
"learning_rate": 2.3376905885569185e-06,
"loss": 0.8476,
"step": 350
},
{
"epoch": 1.4268292682926829,
"grad_norm": 3.670635888853914,
"learning_rate": 2.3076764882864333e-06,
"loss": 0.8716,
"step": 351
},
{
"epoch": 1.4308943089430894,
"grad_norm": 3.516539819419681,
"learning_rate": 2.2777984010793264e-06,
"loss": 0.8524,
"step": 352
},
{
"epoch": 1.434959349593496,
"grad_norm": 3.228259726275918,
"learning_rate": 2.2480578363419363e-06,
"loss": 0.7901,
"step": 353
},
{
"epoch": 1.4390243902439024,
"grad_norm": 3.553218992889345,
"learning_rate": 2.2184562965331203e-06,
"loss": 0.8905,
"step": 354
},
{
"epoch": 1.443089430894309,
"grad_norm": 3.6137062298684923,
"learning_rate": 2.1889952770883644e-06,
"loss": 0.7972,
"step": 355
},
{
"epoch": 1.4471544715447155,
"grad_norm": 3.3416767625599335,
"learning_rate": 2.159676266344222e-06,
"loss": 0.886,
"step": 356
},
{
"epoch": 1.451219512195122,
"grad_norm": 3.3906959649699715,
"learning_rate": 2.130500745463136e-06,
"loss": 0.8919,
"step": 357
},
{
"epoch": 1.4552845528455285,
"grad_norm": 3.6314079403765747,
"learning_rate": 2.1014701883586087e-06,
"loss": 0.8765,
"step": 358
},
{
"epoch": 1.459349593495935,
"grad_norm": 3.057301186038854,
"learning_rate": 2.072586061620735e-06,
"loss": 0.8237,
"step": 359
},
{
"epoch": 1.4634146341463414,
"grad_norm": 3.564428107436926,
"learning_rate": 2.043849824442124e-06,
"loss": 0.7742,
"step": 360
},
{
"epoch": 1.467479674796748,
"grad_norm": 3.178787951259167,
"learning_rate": 2.0152629285441668e-06,
"loss": 0.8365,
"step": 361
},
{
"epoch": 1.4715447154471546,
"grad_norm": 3.181406467166967,
"learning_rate": 1.9868268181037186e-06,
"loss": 0.8645,
"step": 362
},
{
"epoch": 1.475609756097561,
"grad_norm": 3.066096619760171,
"learning_rate": 1.958542929680117e-06,
"loss": 0.7604,
"step": 363
},
{
"epoch": 1.4796747967479675,
"grad_norm": 3.0788381680120604,
"learning_rate": 1.9304126921426235e-06,
"loss": 0.8887,
"step": 364
},
{
"epoch": 1.4837398373983741,
"grad_norm": 3.615003637576646,
"learning_rate": 1.9024375265982386e-06,
"loss": 0.8805,
"step": 365
},
{
"epoch": 1.4878048780487805,
"grad_norm": 2.8227276452116423,
"learning_rate": 1.8746188463198983e-06,
"loss": 0.758,
"step": 366
},
{
"epoch": 1.491869918699187,
"grad_norm": 3.3074090748960923,
"learning_rate": 1.8469580566750911e-06,
"loss": 0.8227,
"step": 367
},
{
"epoch": 1.4959349593495934,
"grad_norm": 2.971853438307015,
"learning_rate": 1.8194565550548477e-06,
"loss": 0.8551,
"step": 368
},
{
"epoch": 1.5,
"grad_norm": 3.5958157882917297,
"learning_rate": 1.7921157308031567e-06,
"loss": 0.7877,
"step": 369
},
{
"epoch": 1.5040650406504064,
"grad_norm": 3.099263275691927,
"learning_rate": 1.764936965146773e-06,
"loss": 0.9031,
"step": 370
},
{
"epoch": 1.5081300813008132,
"grad_norm": 3.7318628452131315,
"learning_rate": 1.7379216311254339e-06,
"loss": 0.8878,
"step": 371
},
{
"epoch": 1.5121951219512195,
"grad_norm": 3.414259418138962,
"learning_rate": 1.7110710935225055e-06,
"loss": 0.8567,
"step": 372
},
{
"epoch": 1.5162601626016259,
"grad_norm": 3.183690273924712,
"learning_rate": 1.6843867087960252e-06,
"loss": 0.8205,
"step": 373
},
{
"epoch": 1.5203252032520327,
"grad_norm": 3.208728871947272,
"learning_rate": 1.6578698250101828e-06,
"loss": 0.7876,
"step": 374
},
{
"epoch": 1.524390243902439,
"grad_norm": 3.049914247780551,
"learning_rate": 1.6315217817672142e-06,
"loss": 0.8012,
"step": 375
},
{
"epoch": 1.5284552845528454,
"grad_norm": 3.463789080277346,
"learning_rate": 1.6053439101397257e-06,
"loss": 0.8196,
"step": 376
},
{
"epoch": 1.532520325203252,
"grad_norm": 3.462794776018169,
"learning_rate": 1.5793375326034539e-06,
"loss": 0.8383,
"step": 377
},
{
"epoch": 1.5365853658536586,
"grad_norm": 3.1335857420520377,
"learning_rate": 1.5535039629704467e-06,
"loss": 0.8113,
"step": 378
},
{
"epoch": 1.540650406504065,
"grad_norm": 3.3079378565371274,
"learning_rate": 1.5278445063227038e-06,
"loss": 0.8283,
"step": 379
},
{
"epoch": 1.5447154471544715,
"grad_norm": 3.0120012731369843,
"learning_rate": 1.502360458946232e-06,
"loss": 0.8099,
"step": 380
},
{
"epoch": 1.548780487804878,
"grad_norm": 3.229793041226319,
"learning_rate": 1.4770531082655704e-06,
"loss": 0.8109,
"step": 381
},
{
"epoch": 1.5528455284552845,
"grad_norm": 3.511162269109416,
"learning_rate": 1.451923732778745e-06,
"loss": 0.8976,
"step": 382
},
{
"epoch": 1.556910569105691,
"grad_norm": 2.9067244803834713,
"learning_rate": 1.4269736019926778e-06,
"loss": 0.8148,
"step": 383
},
{
"epoch": 1.5609756097560976,
"grad_norm": 2.930774964453727,
"learning_rate": 1.4022039763590595e-06,
"loss": 0.7621,
"step": 384
},
{
"epoch": 1.565040650406504,
"grad_norm": 3.717522923760932,
"learning_rate": 1.3776161072106703e-06,
"loss": 0.8789,
"step": 385
},
{
"epoch": 1.5691056910569106,
"grad_norm": 3.094979402727913,
"learning_rate": 1.3532112366981598e-06,
"loss": 0.8271,
"step": 386
},
{
"epoch": 1.5731707317073171,
"grad_norm": 2.950304755367332,
"learning_rate": 1.3289905977273027e-06,
"loss": 0.7035,
"step": 387
},
{
"epoch": 1.5772357723577235,
"grad_norm": 3.236742910261528,
"learning_rate": 1.3049554138967052e-06,
"loss": 0.7916,
"step": 388
},
{
"epoch": 1.58130081300813,
"grad_norm": 3.5425830591951066,
"learning_rate": 1.2811068994359992e-06,
"loss": 0.8277,
"step": 389
},
{
"epoch": 1.5853658536585367,
"grad_norm": 3.3428841825375515,
"learning_rate": 1.257446259144494e-06,
"loss": 0.8651,
"step": 390
},
{
"epoch": 1.589430894308943,
"grad_norm": 3.2634832061442762,
"learning_rate": 1.233974688330315e-06,
"loss": 0.8235,
"step": 391
},
{
"epoch": 1.5934959349593496,
"grad_norm": 3.437454942801004,
"learning_rate": 1.210693372750017e-06,
"loss": 0.7957,
"step": 392
},
{
"epoch": 1.5975609756097562,
"grad_norm": 3.4099949882842244,
"learning_rate": 1.1876034885486764e-06,
"loss": 0.9101,
"step": 393
},
{
"epoch": 1.6016260162601625,
"grad_norm": 2.980999635502304,
"learning_rate": 1.1647062022004845e-06,
"loss": 0.7977,
"step": 394
},
{
"epoch": 1.6056910569105691,
"grad_norm": 3.3813769826015077,
"learning_rate": 1.1420026704498077e-06,
"loss": 0.8455,
"step": 395
},
{
"epoch": 1.6097560975609757,
"grad_norm": 3.031087545039113,
"learning_rate": 1.1194940402527566e-06,
"loss": 0.847,
"step": 396
},
{
"epoch": 1.613821138211382,
"grad_norm": 3.193358851750655,
"learning_rate": 1.0971814487192429e-06,
"loss": 0.8444,
"step": 397
},
{
"epoch": 1.6178861788617886,
"grad_norm": 3.311582664965811,
"learning_rate": 1.075066023055527e-06,
"loss": 0.8936,
"step": 398
},
{
"epoch": 1.6219512195121952,
"grad_norm": 3.31773166325498,
"learning_rate": 1.0531488805072848e-06,
"loss": 0.8469,
"step": 399
},
{
"epoch": 1.6260162601626016,
"grad_norm": 3.427286164377091,
"learning_rate": 1.0314311283031531e-06,
"loss": 0.8797,
"step": 400
},
{
"epoch": 1.6300813008130082,
"grad_norm": 3.4289554400406272,
"learning_rate": 1.0099138635988026e-06,
"loss": 0.7608,
"step": 401
},
{
"epoch": 1.6341463414634148,
"grad_norm": 3.1104366578535916,
"learning_rate": 9.885981734215094e-07,
"loss": 0.7867,
"step": 402
},
{
"epoch": 1.6382113821138211,
"grad_norm": 3.1085297250650936,
"learning_rate": 9.67485134615232e-07,
"loss": 0.859,
"step": 403
},
{
"epoch": 1.6422764227642277,
"grad_norm": 3.229541553690894,
"learning_rate": 9.465758137862264e-07,
"loss": 0.8225,
"step": 404
},
{
"epoch": 1.6463414634146343,
"grad_norm": 3.222195108635805,
"learning_rate": 9.258712672491416e-07,
"loss": 0.8448,
"step": 405
},
{
"epoch": 1.6504065040650406,
"grad_norm": 3.0614124706443473,
"learning_rate": 9.053725409736752e-07,
"loss": 0.8203,
"step": 406
},
{
"epoch": 1.654471544715447,
"grad_norm": 3.1258387440254856,
"learning_rate": 8.850806705317183e-07,
"loss": 0.7789,
"step": 407
},
{
"epoch": 1.6585365853658538,
"grad_norm": 3.626554828178778,
"learning_rate": 8.649966810450472e-07,
"loss": 0.8894,
"step": 408
},
{
"epoch": 1.6626016260162602,
"grad_norm": 3.5995551223443756,
"learning_rate": 8.451215871335355e-07,
"loss": 0.822,
"step": 409
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.3166639434548397,
"learning_rate": 8.254563928638892e-07,
"loss": 0.9231,
"step": 410
},
{
"epoch": 1.6707317073170733,
"grad_norm": 3.2249012002856867,
"learning_rate": 8.060020916989331e-07,
"loss": 0.851,
"step": 411
},
{
"epoch": 1.6747967479674797,
"grad_norm": 2.8257286859743123,
"learning_rate": 7.86759666447412e-07,
"loss": 0.7384,
"step": 412
},
{
"epoch": 1.678861788617886,
"grad_norm": 3.2981372141944196,
"learning_rate": 7.677300892143485e-07,
"loss": 0.8421,
"step": 413
},
{
"epoch": 1.6829268292682928,
"grad_norm": 3.6902124358425397,
"learning_rate": 7.489143213519301e-07,
"loss": 0.8662,
"step": 414
},
{
"epoch": 1.6869918699186992,
"grad_norm": 3.425137543714528,
"learning_rate": 7.303133134109391e-07,
"loss": 0.8289,
"step": 415
},
{
"epoch": 1.6910569105691056,
"grad_norm": 3.496178705820734,
"learning_rate": 7.119280050927407e-07,
"loss": 0.8694,
"step": 416
},
{
"epoch": 1.6951219512195121,
"grad_norm": 2.839539588149697,
"learning_rate": 6.937593252017983e-07,
"loss": 0.7891,
"step": 417
},
{
"epoch": 1.6991869918699187,
"grad_norm": 3.080879219721373,
"learning_rate": 6.758081915987669e-07,
"loss": 0.7891,
"step": 418
},
{
"epoch": 1.703252032520325,
"grad_norm": 3.0791115992790323,
"learning_rate": 6.580755111541076e-07,
"loss": 0.8322,
"step": 419
},
{
"epoch": 1.7073170731707317,
"grad_norm": 2.9278088133369686,
"learning_rate": 6.405621797022848e-07,
"loss": 0.8086,
"step": 420
},
{
"epoch": 1.7113821138211383,
"grad_norm": 3.1748945383560585,
"learning_rate": 6.232690819965065e-07,
"loss": 0.8606,
"step": 421
},
{
"epoch": 1.7154471544715446,
"grad_norm": 2.9963551222576577,
"learning_rate": 6.061970916640236e-07,
"loss": 0.7758,
"step": 422
},
{
"epoch": 1.7195121951219512,
"grad_norm": 3.3204508942195208,
"learning_rate": 5.893470711620036e-07,
"loss": 0.8062,
"step": 423
},
{
"epoch": 1.7235772357723578,
"grad_norm": 3.1047623326730034,
"learning_rate": 5.727198717339511e-07,
"loss": 0.8458,
"step": 424
},
{
"epoch": 1.7276422764227641,
"grad_norm": 2.883736699872172,
"learning_rate": 5.563163333667098e-07,
"loss": 0.8158,
"step": 425
},
{
"epoch": 1.7317073170731707,
"grad_norm": 3.464283249925107,
"learning_rate": 5.401372847480285e-07,
"loss": 0.8775,
"step": 426
},
{
"epoch": 1.7357723577235773,
"grad_norm": 3.2318522436014643,
"learning_rate": 5.241835432246888e-07,
"loss": 0.8637,
"step": 427
},
{
"epoch": 1.7398373983739837,
"grad_norm": 3.495372221002809,
"learning_rate": 5.084559147612244e-07,
"loss": 0.8639,
"step": 428
},
{
"epoch": 1.7439024390243902,
"grad_norm": 2.9749780792757994,
"learning_rate": 4.929551938991945e-07,
"loss": 0.7603,
"step": 429
},
{
"epoch": 1.7479674796747968,
"grad_norm": 3.197313436921309,
"learning_rate": 4.776821637170525e-07,
"loss": 0.8309,
"step": 430
},
{
"epoch": 1.7520325203252032,
"grad_norm": 3.145931357107065,
"learning_rate": 4.626375957905821e-07,
"loss": 0.8166,
"step": 431
},
{
"epoch": 1.7560975609756098,
"grad_norm": 3.0662306892293656,
"learning_rate": 4.4782225015391754e-07,
"loss": 0.7913,
"step": 432
},
{
"epoch": 1.7601626016260163,
"grad_norm": 2.9353362672641454,
"learning_rate": 4.3323687526115045e-07,
"loss": 0.8546,
"step": 433
},
{
"epoch": 1.7642276422764227,
"grad_norm": 3.041591136273237,
"learning_rate": 4.1888220794851386e-07,
"loss": 0.8,
"step": 434
},
{
"epoch": 1.7682926829268293,
"grad_norm": 3.4652351611448085,
"learning_rate": 4.0475897339716466e-07,
"loss": 0.8203,
"step": 435
},
{
"epoch": 1.7723577235772359,
"grad_norm": 3.2128533211337524,
"learning_rate": 3.908678850965425e-07,
"loss": 0.8773,
"step": 436
},
{
"epoch": 1.7764227642276422,
"grad_norm": 2.9700193205991017,
"learning_rate": 3.7720964480832847e-07,
"loss": 0.7585,
"step": 437
},
{
"epoch": 1.7804878048780488,
"grad_norm": 2.811315266132522,
"learning_rate": 3.6378494253099307e-07,
"loss": 0.7523,
"step": 438
},
{
"epoch": 1.7845528455284554,
"grad_norm": 2.9602663398362776,
"learning_rate": 3.505944564649344e-07,
"loss": 0.8212,
"step": 439
},
{
"epoch": 1.7886178861788617,
"grad_norm": 3.495997606088944,
"learning_rate": 3.3763885297822153e-07,
"loss": 0.8602,
"step": 440
},
{
"epoch": 1.7926829268292683,
"grad_norm": 3.2511151625293073,
"learning_rate": 3.2491878657292643e-07,
"loss": 0.7997,
"step": 441
},
{
"epoch": 1.796747967479675,
"grad_norm": 3.223561679857347,
"learning_rate": 3.1243489985206097e-07,
"loss": 0.7926,
"step": 442
},
{
"epoch": 1.8008130081300813,
"grad_norm": 2.978010628782192,
"learning_rate": 3.001878234871147e-07,
"loss": 0.8289,
"step": 443
},
{
"epoch": 1.8048780487804879,
"grad_norm": 3.6335500484232224,
"learning_rate": 2.8817817618618846e-07,
"loss": 0.9546,
"step": 444
},
{
"epoch": 1.8089430894308944,
"grad_norm": 3.0880272844399235,
"learning_rate": 2.7640656466274785e-07,
"loss": 0.8269,
"step": 445
},
{
"epoch": 1.8130081300813008,
"grad_norm": 3.0476265842662986,
"learning_rate": 2.648735836049615e-07,
"loss": 0.8278,
"step": 446
},
{
"epoch": 1.8170731707317072,
"grad_norm": 3.2273714580514925,
"learning_rate": 2.5357981564566647e-07,
"loss": 0.8837,
"step": 447
},
{
"epoch": 1.821138211382114,
"grad_norm": 3.4019435379320826,
"learning_rate": 2.4252583133292927e-07,
"loss": 0.8814,
"step": 448
},
{
"epoch": 1.8252032520325203,
"grad_norm": 3.228180312848657,
"learning_rate": 2.3171218910122695e-07,
"loss": 0.8636,
"step": 449
},
{
"epoch": 1.8292682926829267,
"grad_norm": 4.328141458441057,
"learning_rate": 2.2113943524323167e-07,
"loss": 0.7793,
"step": 450
},
{
"epoch": 1.8333333333333335,
"grad_norm": 3.279705756080727,
"learning_rate": 2.1080810388221406e-07,
"loss": 0.8198,
"step": 451
},
{
"epoch": 1.8373983739837398,
"grad_norm": 3.1756945998316173,
"learning_rate": 2.007187169450603e-07,
"loss": 0.7677,
"step": 452
},
{
"epoch": 1.8414634146341462,
"grad_norm": 2.854224611559776,
"learning_rate": 1.908717841359048e-07,
"loss": 0.8073,
"step": 453
},
{
"epoch": 1.845528455284553,
"grad_norm": 3.3891650093131185,
"learning_rate": 1.8126780291038037e-07,
"loss": 0.8719,
"step": 454
},
{
"epoch": 1.8495934959349594,
"grad_norm": 3.2156232562918166,
"learning_rate": 1.7190725845048827e-07,
"loss": 0.8315,
"step": 455
},
{
"epoch": 1.8536585365853657,
"grad_norm": 3.191126485348018,
"learning_rate": 1.6279062364008446e-07,
"loss": 0.8338,
"step": 456
},
{
"epoch": 1.8577235772357723,
"grad_norm": 3.2502496128696023,
"learning_rate": 1.5391835904099316e-07,
"loss": 0.878,
"step": 457
},
{
"epoch": 1.8617886178861789,
"grad_norm": 2.9383307925800177,
"learning_rate": 1.4529091286973994e-07,
"loss": 0.7495,
"step": 458
},
{
"epoch": 1.8658536585365852,
"grad_norm": 3.8927814894460075,
"learning_rate": 1.3690872097490481e-07,
"loss": 0.8998,
"step": 459
},
{
"epoch": 1.8699186991869918,
"grad_norm": 3.4023619692967397,
"learning_rate": 1.2877220681510927e-07,
"loss": 0.9376,
"step": 460
},
{
"epoch": 1.8739837398373984,
"grad_norm": 3.2188298190967286,
"learning_rate": 1.208817814376162e-07,
"loss": 0.8344,
"step": 461
},
{
"epoch": 1.8780487804878048,
"grad_norm": 3.2462630804047654,
"learning_rate": 1.1323784345757205e-07,
"loss": 0.8377,
"step": 462
},
{
"epoch": 1.8821138211382114,
"grad_norm": 3.392899106863404,
"learning_rate": 1.0584077903786238e-07,
"loss": 0.8516,
"step": 463
},
{
"epoch": 1.886178861788618,
"grad_norm": 3.182002261377221,
"learning_rate": 9.869096186961025e-08,
"loss": 0.8085,
"step": 464
},
{
"epoch": 1.8902439024390243,
"grad_norm": 3.1650002830415613,
"learning_rate": 9.178875315329183e-08,
"loss": 0.8175,
"step": 465
},
{
"epoch": 1.8943089430894309,
"grad_norm": 3.218966966848088,
"learning_rate": 8.513450158049109e-08,
"loss": 0.8363,
"step": 466
},
{
"epoch": 1.8983739837398375,
"grad_norm": 3.408262645552228,
"learning_rate": 7.872854331628599e-08,
"loss": 0.9397,
"step": 467
},
{
"epoch": 1.9024390243902438,
"grad_norm": 3.8342857272726696,
"learning_rate": 7.257120198226219e-08,
"loss": 0.8542,
"step": 468
},
{
"epoch": 1.9065040650406504,
"grad_norm": 3.1564453475681287,
"learning_rate": 6.666278864016884e-08,
"loss": 0.8513,
"step": 469
},
{
"epoch": 1.910569105691057,
"grad_norm": 3.2217807303958064,
"learning_rate": 6.100360177619946e-08,
"loss": 0.8503,
"step": 470
},
{
"epoch": 1.9146341463414633,
"grad_norm": 3.2114649161235356,
"learning_rate": 5.559392728591517e-08,
"loss": 0.9171,
"step": 471
},
{
"epoch": 1.91869918699187,
"grad_norm": 3.352405009441328,
"learning_rate": 5.0434038459801213e-08,
"loss": 0.8159,
"step": 472
},
{
"epoch": 1.9227642276422765,
"grad_norm": 3.1814982432174093,
"learning_rate": 4.5524195969461895e-08,
"loss": 0.8304,
"step": 473
},
{
"epoch": 1.9268292682926829,
"grad_norm": 3.158205461981237,
"learning_rate": 4.086464785444777e-08,
"loss": 0.7888,
"step": 474
},
{
"epoch": 1.9308943089430894,
"grad_norm": 2.8037462602147545,
"learning_rate": 3.645562950973014e-08,
"loss": 0.6949,
"step": 475
},
{
"epoch": 1.934959349593496,
"grad_norm": 2.980787245749961,
"learning_rate": 3.229736367380498e-08,
"loss": 0.7739,
"step": 476
},
{
"epoch": 1.9390243902439024,
"grad_norm": 3.128680334368289,
"learning_rate": 2.8390060417443632e-08,
"loss": 0.8677,
"step": 477
},
{
"epoch": 1.943089430894309,
"grad_norm": 3.7477720931810956,
"learning_rate": 2.4733917133077378e-08,
"loss": 0.9261,
"step": 478
},
{
"epoch": 1.9471544715447155,
"grad_norm": 3.689456926619419,
"learning_rate": 2.1329118524827662e-08,
"loss": 0.9032,
"step": 479
},
{
"epoch": 1.951219512195122,
"grad_norm": 3.5300716074533813,
"learning_rate": 1.8175836599173545e-08,
"loss": 0.8511,
"step": 480
},
{
"epoch": 1.9552845528455285,
"grad_norm": 3.1505817427132325,
"learning_rate": 1.5274230656263656e-08,
"loss": 0.7846,
"step": 481
},
{
"epoch": 1.959349593495935,
"grad_norm": 3.022385863744955,
"learning_rate": 1.2624447281867625e-08,
"loss": 0.7325,
"step": 482
},
{
"epoch": 1.9634146341463414,
"grad_norm": 3.3794689368212647,
"learning_rate": 1.0226620339969795e-08,
"loss": 0.8091,
"step": 483
},
{
"epoch": 1.967479674796748,
"grad_norm": 2.9275122073562,
"learning_rate": 8.080870966008513e-09,
"loss": 0.7285,
"step": 484
},
{
"epoch": 1.9715447154471546,
"grad_norm": 3.3140577653029806,
"learning_rate": 6.187307560754363e-09,
"loss": 0.8462,
"step": 485
},
{
"epoch": 1.975609756097561,
"grad_norm": 3.0026431051566926,
"learning_rate": 4.546025784837316e-09,
"loss": 0.7951,
"step": 486
},
{
"epoch": 1.9796747967479673,
"grad_norm": 3.4729051127349893,
"learning_rate": 3.1571085539089384e-09,
"loss": 0.8688,
"step": 487
},
{
"epoch": 1.9837398373983741,
"grad_norm": 2.662940908363704,
"learning_rate": 2.0206260344590724e-09,
"loss": 0.6993,
"step": 488
},
{
"epoch": 1.9878048780487805,
"grad_norm": 3.6478034020803274,
"learning_rate": 1.136635640267003e-09,
"loss": 0.8605,
"step": 489
},
{
"epoch": 1.9918699186991868,
"grad_norm": 3.5646048965813932,
"learning_rate": 5.051820295032262e-10,
"loss": 0.8902,
"step": 490
},
{
"epoch": 1.9959349593495936,
"grad_norm": 3.0096957163094813,
"learning_rate": 1.2629710247180626e-10,
"loss": 0.8419,
"step": 491
},
{
"epoch": 2.0,
"grad_norm": 3.5971711883525903,
"learning_rate": 0.0,
"loss": 0.898,
"step": 492
},
{
"epoch": 2.0,
"step": 492,
"total_flos": 10700496175104.0,
"train_loss": 1.062965918483773,
"train_runtime": 414.7958,
"train_samples_per_second": 37.937,
"train_steps_per_second": 1.186
}
],
"logging_steps": 1,
"max_steps": 492,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 10700496175104.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}