fengyao1909's picture
Upload folder using huggingface_hub
43a4566 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9033423667570009,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0018066847335140017,
"grad_norm": 2.659763906029275,
"learning_rate": 0.0,
"loss": 0.8251,
"step": 1
},
{
"epoch": 0.0036133694670280035,
"grad_norm": 2.7266428017973614,
"learning_rate": 1.7857142857142857e-06,
"loss": 0.8284,
"step": 2
},
{
"epoch": 0.005420054200542005,
"grad_norm": 2.7147205179950005,
"learning_rate": 3.5714285714285714e-06,
"loss": 0.8426,
"step": 3
},
{
"epoch": 0.007226738934056007,
"grad_norm": 2.5096942670348255,
"learning_rate": 5.357142857142857e-06,
"loss": 0.8346,
"step": 4
},
{
"epoch": 0.009033423667570008,
"grad_norm": 2.0059621964295196,
"learning_rate": 7.142857142857143e-06,
"loss": 0.8134,
"step": 5
},
{
"epoch": 0.01084010840108401,
"grad_norm": 1.2379695468926446,
"learning_rate": 8.92857142857143e-06,
"loss": 0.802,
"step": 6
},
{
"epoch": 0.012646793134598013,
"grad_norm": 1.1936887174522226,
"learning_rate": 1.0714285714285714e-05,
"loss": 0.7754,
"step": 7
},
{
"epoch": 0.014453477868112014,
"grad_norm": 2.3075172440200484,
"learning_rate": 1.25e-05,
"loss": 0.764,
"step": 8
},
{
"epoch": 0.016260162601626018,
"grad_norm": 2.4636205809715874,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.7576,
"step": 9
},
{
"epoch": 0.018066847335140017,
"grad_norm": 1.897979454666384,
"learning_rate": 1.6071428571428572e-05,
"loss": 0.7395,
"step": 10
},
{
"epoch": 0.01987353206865402,
"grad_norm": 1.7407222002880698,
"learning_rate": 1.785714285714286e-05,
"loss": 0.7285,
"step": 11
},
{
"epoch": 0.02168021680216802,
"grad_norm": 1.4289048493464356,
"learning_rate": 1.9642857142857145e-05,
"loss": 0.7431,
"step": 12
},
{
"epoch": 0.023486901535682024,
"grad_norm": 0.9141711050880629,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.7143,
"step": 13
},
{
"epoch": 0.025293586269196026,
"grad_norm": 0.8189622168882543,
"learning_rate": 2.3214285714285715e-05,
"loss": 0.7025,
"step": 14
},
{
"epoch": 0.02710027100271003,
"grad_norm": 0.7942265250326208,
"learning_rate": 2.5e-05,
"loss": 0.701,
"step": 15
},
{
"epoch": 0.028906955736224028,
"grad_norm": 0.7964221572939095,
"learning_rate": 2.6785714285714288e-05,
"loss": 0.694,
"step": 16
},
{
"epoch": 0.03071364046973803,
"grad_norm": 0.6662827476207438,
"learning_rate": 2.857142857142857e-05,
"loss": 0.7,
"step": 17
},
{
"epoch": 0.032520325203252036,
"grad_norm": 0.603606779398402,
"learning_rate": 3.0357142857142857e-05,
"loss": 0.6906,
"step": 18
},
{
"epoch": 0.03432700993676603,
"grad_norm": 0.5451456208361647,
"learning_rate": 3.2142857142857144e-05,
"loss": 0.6848,
"step": 19
},
{
"epoch": 0.036133694670280034,
"grad_norm": 0.5369469177848265,
"learning_rate": 3.392857142857143e-05,
"loss": 0.6607,
"step": 20
},
{
"epoch": 0.037940379403794036,
"grad_norm": 0.5274254086413857,
"learning_rate": 3.571428571428572e-05,
"loss": 0.6682,
"step": 21
},
{
"epoch": 0.03974706413730804,
"grad_norm": 0.5105354397496891,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.6586,
"step": 22
},
{
"epoch": 0.04155374887082204,
"grad_norm": 0.5369119533926304,
"learning_rate": 3.928571428571429e-05,
"loss": 0.661,
"step": 23
},
{
"epoch": 0.04336043360433604,
"grad_norm": 0.44274977503226,
"learning_rate": 4.107142857142857e-05,
"loss": 0.6664,
"step": 24
},
{
"epoch": 0.045167118337850046,
"grad_norm": 0.49423444990953536,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.6475,
"step": 25
},
{
"epoch": 0.04697380307136405,
"grad_norm": 0.42707881201756015,
"learning_rate": 4.464285714285715e-05,
"loss": 0.6632,
"step": 26
},
{
"epoch": 0.04878048780487805,
"grad_norm": 0.4197857224791722,
"learning_rate": 4.642857142857143e-05,
"loss": 0.6425,
"step": 27
},
{
"epoch": 0.05058717253839205,
"grad_norm": 0.38295470338642557,
"learning_rate": 4.8214285714285716e-05,
"loss": 0.6445,
"step": 28
},
{
"epoch": 0.052393857271906055,
"grad_norm": 0.40107126641720603,
"learning_rate": 5e-05,
"loss": 0.6549,
"step": 29
},
{
"epoch": 0.05420054200542006,
"grad_norm": 0.42495328665802157,
"learning_rate": 4.999955240022902e-05,
"loss": 0.6558,
"step": 30
},
{
"epoch": 0.05600722673893405,
"grad_norm": 0.4299967908685598,
"learning_rate": 4.999820961694372e-05,
"loss": 0.6457,
"step": 31
},
{
"epoch": 0.057813911472448055,
"grad_norm": 0.40985241889616997,
"learning_rate": 4.999597169822646e-05,
"loss": 0.6328,
"step": 32
},
{
"epoch": 0.05962059620596206,
"grad_norm": 0.3495200281239175,
"learning_rate": 4.9992838724212585e-05,
"loss": 0.6425,
"step": 33
},
{
"epoch": 0.06142728093947606,
"grad_norm": 0.38685883550102856,
"learning_rate": 4.9988810807087584e-05,
"loss": 0.6303,
"step": 34
},
{
"epoch": 0.06323396567299007,
"grad_norm": 0.33761952616373997,
"learning_rate": 4.998388809108303e-05,
"loss": 0.6361,
"step": 35
},
{
"epoch": 0.06504065040650407,
"grad_norm": 0.31993568814030454,
"learning_rate": 4.997807075247146e-05,
"loss": 0.6306,
"step": 36
},
{
"epoch": 0.06684733514001806,
"grad_norm": 0.300005248119346,
"learning_rate": 4.997135899956001e-05,
"loss": 0.6357,
"step": 37
},
{
"epoch": 0.06865401987353206,
"grad_norm": 0.34324199464545374,
"learning_rate": 4.9963753072683025e-05,
"loss": 0.6281,
"step": 38
},
{
"epoch": 0.07046070460704607,
"grad_norm": 0.3666988804506875,
"learning_rate": 4.9955253244193375e-05,
"loss": 0.6302,
"step": 39
},
{
"epoch": 0.07226738934056007,
"grad_norm": 0.3597397205758853,
"learning_rate": 4.994585981845278e-05,
"loss": 0.6182,
"step": 40
},
{
"epoch": 0.07407407407407407,
"grad_norm": 0.316655085321042,
"learning_rate": 4.9935573131820854e-05,
"loss": 0.6244,
"step": 41
},
{
"epoch": 0.07588075880758807,
"grad_norm": 0.32307238811600836,
"learning_rate": 4.9924393552643075e-05,
"loss": 0.617,
"step": 42
},
{
"epoch": 0.07768744354110207,
"grad_norm": 0.39160753680835997,
"learning_rate": 4.991232148123761e-05,
"loss": 0.6166,
"step": 43
},
{
"epoch": 0.07949412827461608,
"grad_norm": 0.29263938628410097,
"learning_rate": 4.989935734988098e-05,
"loss": 0.6117,
"step": 44
},
{
"epoch": 0.08130081300813008,
"grad_norm": 0.370842709761933,
"learning_rate": 4.988550162279255e-05,
"loss": 0.6193,
"step": 45
},
{
"epoch": 0.08310749774164408,
"grad_norm": 0.2911757694552668,
"learning_rate": 4.987075479611796e-05,
"loss": 0.6194,
"step": 46
},
{
"epoch": 0.08491418247515808,
"grad_norm": 0.3443307858819186,
"learning_rate": 4.985511739791129e-05,
"loss": 0.623,
"step": 47
},
{
"epoch": 0.08672086720867209,
"grad_norm": 0.31661112055855317,
"learning_rate": 4.983858998811622e-05,
"loss": 0.6094,
"step": 48
},
{
"epoch": 0.08852755194218609,
"grad_norm": 0.291516245034795,
"learning_rate": 4.9821173158545936e-05,
"loss": 0.6166,
"step": 49
},
{
"epoch": 0.09033423667570009,
"grad_norm": 0.30916980990061194,
"learning_rate": 4.980286753286195e-05,
"loss": 0.6154,
"step": 50
},
{
"epoch": 0.0921409214092141,
"grad_norm": 0.31742143743914125,
"learning_rate": 4.978367376655177e-05,
"loss": 0.6048,
"step": 51
},
{
"epoch": 0.0939476061427281,
"grad_norm": 0.25067727990568833,
"learning_rate": 4.976359254690543e-05,
"loss": 0.6217,
"step": 52
},
{
"epoch": 0.0957542908762421,
"grad_norm": 0.3441688790068107,
"learning_rate": 4.974262459299087e-05,
"loss": 0.6078,
"step": 53
},
{
"epoch": 0.0975609756097561,
"grad_norm": 0.28868980984789416,
"learning_rate": 4.972077065562821e-05,
"loss": 0.5976,
"step": 54
},
{
"epoch": 0.0993676603432701,
"grad_norm": 0.2836396863769562,
"learning_rate": 4.969803151736284e-05,
"loss": 0.6127,
"step": 55
},
{
"epoch": 0.1011743450767841,
"grad_norm": 0.30525962922898175,
"learning_rate": 4.9674407992437394e-05,
"loss": 0.6179,
"step": 56
},
{
"epoch": 0.10298102981029811,
"grad_norm": 0.2740631243855526,
"learning_rate": 4.964990092676263e-05,
"loss": 0.6024,
"step": 57
},
{
"epoch": 0.10478771454381211,
"grad_norm": 0.28308780985953025,
"learning_rate": 4.962451119788709e-05,
"loss": 0.6112,
"step": 58
},
{
"epoch": 0.10659439927732611,
"grad_norm": 0.2664377744504458,
"learning_rate": 4.959823971496574e-05,
"loss": 0.5967,
"step": 59
},
{
"epoch": 0.10840108401084012,
"grad_norm": 0.30863190015284836,
"learning_rate": 4.957108741872736e-05,
"loss": 0.5985,
"step": 60
},
{
"epoch": 0.1102077687443541,
"grad_norm": 0.2574405419751485,
"learning_rate": 4.954305528144085e-05,
"loss": 0.6025,
"step": 61
},
{
"epoch": 0.1120144534778681,
"grad_norm": 0.3605529638987124,
"learning_rate": 4.9514144306880506e-05,
"loss": 0.6066,
"step": 62
},
{
"epoch": 0.11382113821138211,
"grad_norm": 0.2643789885619675,
"learning_rate": 4.9484355530289944e-05,
"loss": 0.6071,
"step": 63
},
{
"epoch": 0.11562782294489611,
"grad_norm": 0.3195215128274048,
"learning_rate": 4.9453690018345144e-05,
"loss": 0.6055,
"step": 64
},
{
"epoch": 0.11743450767841011,
"grad_norm": 0.2590151502039366,
"learning_rate": 4.9422148869116194e-05,
"loss": 0.599,
"step": 65
},
{
"epoch": 0.11924119241192412,
"grad_norm": 0.31585136789422946,
"learning_rate": 4.938973321202799e-05,
"loss": 0.6022,
"step": 66
},
{
"epoch": 0.12104787714543812,
"grad_norm": 0.27316566589630514,
"learning_rate": 4.935644420781978e-05,
"loss": 0.5923,
"step": 67
},
{
"epoch": 0.12285456187895212,
"grad_norm": 0.3298587202496022,
"learning_rate": 4.932228304850363e-05,
"loss": 0.6079,
"step": 68
},
{
"epoch": 0.12466124661246612,
"grad_norm": 0.25714722630334,
"learning_rate": 4.928725095732169e-05,
"loss": 0.6096,
"step": 69
},
{
"epoch": 0.12646793134598014,
"grad_norm": 0.28260143846613023,
"learning_rate": 4.925134918870245e-05,
"loss": 0.6136,
"step": 70
},
{
"epoch": 0.12827461607949414,
"grad_norm": 0.2601107451419396,
"learning_rate": 4.9214579028215776e-05,
"loss": 0.5869,
"step": 71
},
{
"epoch": 0.13008130081300814,
"grad_norm": 0.30285335919958933,
"learning_rate": 4.917694179252692e-05,
"loss": 0.6045,
"step": 72
},
{
"epoch": 0.13188798554652212,
"grad_norm": 0.30864848291210845,
"learning_rate": 4.91384388293493e-05,
"loss": 0.6029,
"step": 73
},
{
"epoch": 0.13369467028003612,
"grad_norm": 0.2924165488418205,
"learning_rate": 4.909907151739633e-05,
"loss": 0.5947,
"step": 74
},
{
"epoch": 0.13550135501355012,
"grad_norm": 0.34108537126359484,
"learning_rate": 4.9058841266332e-05,
"loss": 0.5938,
"step": 75
},
{
"epoch": 0.13730803974706413,
"grad_norm": 0.31948510370131694,
"learning_rate": 4.90177495167204e-05,
"loss": 0.5895,
"step": 76
},
{
"epoch": 0.13911472448057813,
"grad_norm": 0.29301446332928244,
"learning_rate": 4.897579773997415e-05,
"loss": 0.5844,
"step": 77
},
{
"epoch": 0.14092140921409213,
"grad_norm": 0.31090724165639755,
"learning_rate": 4.893298743830168e-05,
"loss": 0.5956,
"step": 78
},
{
"epoch": 0.14272809394760613,
"grad_norm": 0.3171519603739174,
"learning_rate": 4.888932014465352e-05,
"loss": 0.6033,
"step": 79
},
{
"epoch": 0.14453477868112014,
"grad_norm": 0.3071070352071102,
"learning_rate": 4.88447974226673e-05,
"loss": 0.6125,
"step": 80
},
{
"epoch": 0.14634146341463414,
"grad_norm": 0.30253742499494274,
"learning_rate": 4.879942086661184e-05,
"loss": 0.5978,
"step": 81
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.3458384807175159,
"learning_rate": 4.875319210133004e-05,
"loss": 0.5911,
"step": 82
},
{
"epoch": 0.14995483288166214,
"grad_norm": 0.32629542976585363,
"learning_rate": 4.870611278218066e-05,
"loss": 0.6009,
"step": 83
},
{
"epoch": 0.15176151761517614,
"grad_norm": 0.3536238666751845,
"learning_rate": 4.865818459497911e-05,
"loss": 0.5943,
"step": 84
},
{
"epoch": 0.15356820234869015,
"grad_norm": 0.3367725985955079,
"learning_rate": 4.860940925593703e-05,
"loss": 0.5972,
"step": 85
},
{
"epoch": 0.15537488708220415,
"grad_norm": 0.4086748125141385,
"learning_rate": 4.8559788511600876e-05,
"loss": 0.597,
"step": 86
},
{
"epoch": 0.15718157181571815,
"grad_norm": 0.3644321887236506,
"learning_rate": 4.850932413878934e-05,
"loss": 0.5983,
"step": 87
},
{
"epoch": 0.15898825654923215,
"grad_norm": 0.42141719022476887,
"learning_rate": 4.8458017944529776e-05,
"loss": 0.6033,
"step": 88
},
{
"epoch": 0.16079494128274616,
"grad_norm": 0.38030614533998675,
"learning_rate": 4.8405871765993433e-05,
"loss": 0.6009,
"step": 89
},
{
"epoch": 0.16260162601626016,
"grad_norm": 0.3717294455305848,
"learning_rate": 4.8352887470429726e-05,
"loss": 0.5916,
"step": 90
},
{
"epoch": 0.16440831074977416,
"grad_norm": 0.3998846446125284,
"learning_rate": 4.8299066955099335e-05,
"loss": 0.5901,
"step": 91
},
{
"epoch": 0.16621499548328816,
"grad_norm": 0.4153650664913498,
"learning_rate": 4.8244412147206284e-05,
"loss": 0.5936,
"step": 92
},
{
"epoch": 0.16802168021680217,
"grad_norm": 0.3728021419776183,
"learning_rate": 4.8188925003828945e-05,
"loss": 0.6013,
"step": 93
},
{
"epoch": 0.16982836495031617,
"grad_norm": 0.4461860697930481,
"learning_rate": 4.813260751184992e-05,
"loss": 0.6009,
"step": 94
},
{
"epoch": 0.17163504968383017,
"grad_norm": 0.3168492009675633,
"learning_rate": 4.807546168788494e-05,
"loss": 0.5916,
"step": 95
},
{
"epoch": 0.17344173441734417,
"grad_norm": 0.43250962326831294,
"learning_rate": 4.8017489578210604e-05,
"loss": 0.5913,
"step": 96
},
{
"epoch": 0.17524841915085818,
"grad_norm": 0.2986865177455382,
"learning_rate": 4.7958693258691167e-05,
"loss": 0.5967,
"step": 97
},
{
"epoch": 0.17705510388437218,
"grad_norm": 0.3165232390515456,
"learning_rate": 4.7899074834704165e-05,
"loss": 0.5897,
"step": 98
},
{
"epoch": 0.17886178861788618,
"grad_norm": 0.32233792495600755,
"learning_rate": 4.783863644106502e-05,
"loss": 0.603,
"step": 99
},
{
"epoch": 0.18066847335140018,
"grad_norm": 0.27370066126981313,
"learning_rate": 4.7777380241950645e-05,
"loss": 0.5756,
"step": 100
},
{
"epoch": 0.18247515808491419,
"grad_norm": 0.3100603719164377,
"learning_rate": 4.7715308430821864e-05,
"loss": 0.5916,
"step": 101
},
{
"epoch": 0.1842818428184282,
"grad_norm": 0.3030298684281094,
"learning_rate": 4.765242323034498e-05,
"loss": 0.6101,
"step": 102
},
{
"epoch": 0.1860885275519422,
"grad_norm": 0.26623940548370334,
"learning_rate": 4.758872689231208e-05,
"loss": 0.5891,
"step": 103
},
{
"epoch": 0.1878952122854562,
"grad_norm": 0.3700367884498594,
"learning_rate": 4.752422169756048e-05,
"loss": 0.5866,
"step": 104
},
{
"epoch": 0.1897018970189702,
"grad_norm": 0.2828934652788091,
"learning_rate": 4.745890995589101e-05,
"loss": 0.5791,
"step": 105
},
{
"epoch": 0.1915085817524842,
"grad_norm": 0.37820570421849015,
"learning_rate": 4.7392794005985326e-05,
"loss": 0.5819,
"step": 106
},
{
"epoch": 0.1933152664859982,
"grad_norm": 0.30098730623292375,
"learning_rate": 4.732587621532214e-05,
"loss": 0.588,
"step": 107
},
{
"epoch": 0.1951219512195122,
"grad_norm": 0.3062261615745855,
"learning_rate": 4.725815898009247e-05,
"loss": 0.5862,
"step": 108
},
{
"epoch": 0.1969286359530262,
"grad_norm": 0.2977746789789922,
"learning_rate": 4.718964472511386e-05,
"loss": 0.5946,
"step": 109
},
{
"epoch": 0.1987353206865402,
"grad_norm": 0.2694364940159872,
"learning_rate": 4.712033590374346e-05,
"loss": 0.5761,
"step": 110
},
{
"epoch": 0.2005420054200542,
"grad_norm": 0.2834050892358286,
"learning_rate": 4.705023499779031e-05,
"loss": 0.5962,
"step": 111
},
{
"epoch": 0.2023486901535682,
"grad_norm": 0.2327359496248105,
"learning_rate": 4.6979344517426345e-05,
"loss": 0.5888,
"step": 112
},
{
"epoch": 0.2041553748870822,
"grad_norm": 0.31015496412234067,
"learning_rate": 4.690766700109659e-05,
"loss": 0.5934,
"step": 113
},
{
"epoch": 0.20596205962059622,
"grad_norm": 0.29046891341791853,
"learning_rate": 4.6835205015428246e-05,
"loss": 0.5767,
"step": 114
},
{
"epoch": 0.20776874435411022,
"grad_norm": 0.2845948992161244,
"learning_rate": 4.676196115513876e-05,
"loss": 0.5927,
"step": 115
},
{
"epoch": 0.20957542908762422,
"grad_norm": 0.2890620474334217,
"learning_rate": 4.668793804294294e-05,
"loss": 0.5859,
"step": 116
},
{
"epoch": 0.21138211382113822,
"grad_norm": 0.2944283918661472,
"learning_rate": 4.661313832945904e-05,
"loss": 0.5972,
"step": 117
},
{
"epoch": 0.21318879855465223,
"grad_norm": 0.35404405354459595,
"learning_rate": 4.653756469311381e-05,
"loss": 0.5848,
"step": 118
},
{
"epoch": 0.21499548328816623,
"grad_norm": 0.2281862529105396,
"learning_rate": 4.6461219840046654e-05,
"loss": 0.5745,
"step": 119
},
{
"epoch": 0.21680216802168023,
"grad_norm": 0.3306722482810818,
"learning_rate": 4.638410650401267e-05,
"loss": 0.5942,
"step": 120
},
{
"epoch": 0.2186088527551942,
"grad_norm": 0.29724649762107985,
"learning_rate": 4.6306227446284775e-05,
"loss": 0.5902,
"step": 121
},
{
"epoch": 0.2204155374887082,
"grad_norm": 0.25102605738006223,
"learning_rate": 4.622758545555485e-05,
"loss": 0.5935,
"step": 122
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.2833060561678344,
"learning_rate": 4.614818334783384e-05,
"loss": 0.5841,
"step": 123
},
{
"epoch": 0.2240289069557362,
"grad_norm": 0.27147467369154965,
"learning_rate": 4.606802396635098e-05,
"loss": 0.5708,
"step": 124
},
{
"epoch": 0.22583559168925021,
"grad_norm": 0.2848712761372514,
"learning_rate": 4.598711018145193e-05,
"loss": 0.5788,
"step": 125
},
{
"epoch": 0.22764227642276422,
"grad_norm": 0.2850209437886442,
"learning_rate": 4.590544489049602e-05,
"loss": 0.5904,
"step": 126
},
{
"epoch": 0.22944896115627822,
"grad_norm": 0.2812160194693432,
"learning_rate": 4.5823031017752485e-05,
"loss": 0.583,
"step": 127
},
{
"epoch": 0.23125564588979222,
"grad_norm": 0.28876317504585947,
"learning_rate": 4.5739871514295786e-05,
"loss": 0.583,
"step": 128
},
{
"epoch": 0.23306233062330622,
"grad_norm": 0.3071141762492437,
"learning_rate": 4.5655969357899874e-05,
"loss": 0.5772,
"step": 129
},
{
"epoch": 0.23486901535682023,
"grad_norm": 0.27490370808898895,
"learning_rate": 4.5571327552931645e-05,
"loss": 0.5955,
"step": 130
},
{
"epoch": 0.23667570009033423,
"grad_norm": 0.3110832282292401,
"learning_rate": 4.54859491302433e-05,
"loss": 0.5901,
"step": 131
},
{
"epoch": 0.23848238482384823,
"grad_norm": 0.2830517328765567,
"learning_rate": 4.5399837147063825e-05,
"loss": 0.5703,
"step": 132
},
{
"epoch": 0.24028906955736223,
"grad_norm": 0.23750468668782748,
"learning_rate": 4.531299468688955e-05,
"loss": 0.584,
"step": 133
},
{
"epoch": 0.24209575429087624,
"grad_norm": 0.3172354070469124,
"learning_rate": 4.522542485937369e-05,
"loss": 0.5853,
"step": 134
},
{
"epoch": 0.24390243902439024,
"grad_norm": 0.24756082828427745,
"learning_rate": 4.5137130800215025e-05,
"loss": 0.582,
"step": 135
},
{
"epoch": 0.24570912375790424,
"grad_norm": 0.29496151744433274,
"learning_rate": 4.50481156710456e-05,
"loss": 0.5855,
"step": 136
},
{
"epoch": 0.24751580849141824,
"grad_norm": 0.25898913707962645,
"learning_rate": 4.495838265931754e-05,
"loss": 0.5688,
"step": 137
},
{
"epoch": 0.24932249322493225,
"grad_norm": 0.3181464955042996,
"learning_rate": 4.486793497818889e-05,
"loss": 0.587,
"step": 138
},
{
"epoch": 0.25112917795844625,
"grad_norm": 0.29538242598686,
"learning_rate": 4.477677586640854e-05,
"loss": 0.5895,
"step": 139
},
{
"epoch": 0.2529358626919603,
"grad_norm": 0.2709856016491997,
"learning_rate": 4.4684908588200304e-05,
"loss": 0.5893,
"step": 140
},
{
"epoch": 0.25474254742547425,
"grad_norm": 0.2887366675203521,
"learning_rate": 4.4592336433146e-05,
"loss": 0.57,
"step": 141
},
{
"epoch": 0.2565492321589883,
"grad_norm": 0.2913907611912848,
"learning_rate": 4.449906271606766e-05,
"loss": 0.5901,
"step": 142
},
{
"epoch": 0.25835591689250226,
"grad_norm": 0.27556372878865987,
"learning_rate": 4.440509077690883e-05,
"loss": 0.5824,
"step": 143
},
{
"epoch": 0.2601626016260163,
"grad_norm": 0.2598126133725035,
"learning_rate": 4.431042398061499e-05,
"loss": 0.5696,
"step": 144
},
{
"epoch": 0.26196928635953026,
"grad_norm": 0.28440523852409555,
"learning_rate": 4.421506571701305e-05,
"loss": 0.5831,
"step": 145
},
{
"epoch": 0.26377597109304424,
"grad_norm": 0.28436436735518483,
"learning_rate": 4.4119019400689967e-05,
"loss": 0.5873,
"step": 146
},
{
"epoch": 0.26558265582655827,
"grad_norm": 0.28868061516524324,
"learning_rate": 4.402228847087047e-05,
"loss": 0.5774,
"step": 147
},
{
"epoch": 0.26738934056007224,
"grad_norm": 0.25530829920398135,
"learning_rate": 4.3924876391293915e-05,
"loss": 0.5784,
"step": 148
},
{
"epoch": 0.26919602529358627,
"grad_norm": 0.33084801058363894,
"learning_rate": 4.382678665009028e-05,
"loss": 0.5757,
"step": 149
},
{
"epoch": 0.27100271002710025,
"grad_norm": 0.26199181259016135,
"learning_rate": 4.372802275965521e-05,
"loss": 0.5856,
"step": 150
},
{
"epoch": 0.2728093947606143,
"grad_norm": 0.3001136862580597,
"learning_rate": 4.3628588256524285e-05,
"loss": 0.5672,
"step": 151
},
{
"epoch": 0.27461607949412825,
"grad_norm": 0.266660527503516,
"learning_rate": 4.3528486701246376e-05,
"loss": 0.5748,
"step": 152
},
{
"epoch": 0.2764227642276423,
"grad_norm": 0.24022467041582257,
"learning_rate": 4.3427721678256125e-05,
"loss": 0.575,
"step": 153
},
{
"epoch": 0.27822944896115626,
"grad_norm": 0.2758404776476118,
"learning_rate": 4.332629679574566e-05,
"loss": 0.5782,
"step": 154
},
{
"epoch": 0.2800361336946703,
"grad_norm": 0.22788731561805234,
"learning_rate": 4.3224215685535294e-05,
"loss": 0.5706,
"step": 155
},
{
"epoch": 0.28184281842818426,
"grad_norm": 0.25848604043973594,
"learning_rate": 4.312148200294355e-05,
"loss": 0.5713,
"step": 156
},
{
"epoch": 0.2836495031616983,
"grad_norm": 0.24936343108285672,
"learning_rate": 4.301809942665625e-05,
"loss": 0.5844,
"step": 157
},
{
"epoch": 0.28545618789521227,
"grad_norm": 0.2439022938306737,
"learning_rate": 4.2914071658594805e-05,
"loss": 0.5818,
"step": 158
},
{
"epoch": 0.2872628726287263,
"grad_norm": 0.2374269574090051,
"learning_rate": 4.2809402423783624e-05,
"loss": 0.5625,
"step": 159
},
{
"epoch": 0.28906955736224027,
"grad_norm": 0.24464499623427044,
"learning_rate": 4.2704095470216744e-05,
"loss": 0.5709,
"step": 160
},
{
"epoch": 0.2908762420957543,
"grad_norm": 0.24610212553116018,
"learning_rate": 4.2598154568723626e-05,
"loss": 0.5793,
"step": 161
},
{
"epoch": 0.2926829268292683,
"grad_norm": 0.2497534454789805,
"learning_rate": 4.249158351283414e-05,
"loss": 0.5651,
"step": 162
},
{
"epoch": 0.2944896115627823,
"grad_norm": 0.275228370383275,
"learning_rate": 4.2384386118642694e-05,
"loss": 0.5736,
"step": 163
},
{
"epoch": 0.2962962962962963,
"grad_norm": 0.26327233816330226,
"learning_rate": 4.227656622467162e-05,
"loss": 0.5836,
"step": 164
},
{
"epoch": 0.2981029810298103,
"grad_norm": 0.3045451405569592,
"learning_rate": 4.2168127691733706e-05,
"loss": 0.5739,
"step": 165
},
{
"epoch": 0.2999096657633243,
"grad_norm": 0.271238682019655,
"learning_rate": 4.205907440279395e-05,
"loss": 0.5809,
"step": 166
},
{
"epoch": 0.3017163504968383,
"grad_norm": 0.2811649912331929,
"learning_rate": 4.1949410262830525e-05,
"loss": 0.5798,
"step": 167
},
{
"epoch": 0.3035230352303523,
"grad_norm": 0.2191966544712532,
"learning_rate": 4.1839139198694946e-05,
"loss": 0.577,
"step": 168
},
{
"epoch": 0.3053297199638663,
"grad_norm": 0.26327524128109403,
"learning_rate": 4.172826515897146e-05,
"loss": 0.5702,
"step": 169
},
{
"epoch": 0.3071364046973803,
"grad_norm": 0.28266999279822,
"learning_rate": 4.161679211383565e-05,
"loss": 0.5833,
"step": 170
},
{
"epoch": 0.3089430894308943,
"grad_norm": 0.20433772275451065,
"learning_rate": 4.150472405491226e-05,
"loss": 0.5668,
"step": 171
},
{
"epoch": 0.3107497741644083,
"grad_norm": 0.3090701500447041,
"learning_rate": 4.139206499513231e-05,
"loss": 0.5738,
"step": 172
},
{
"epoch": 0.31255645889792233,
"grad_norm": 0.25861634331617656,
"learning_rate": 4.127881896858934e-05,
"loss": 0.5768,
"step": 173
},
{
"epoch": 0.3143631436314363,
"grad_norm": 0.2614421199415642,
"learning_rate": 4.116499003039499e-05,
"loss": 0.5686,
"step": 174
},
{
"epoch": 0.31616982836495033,
"grad_norm": 0.2724020553641339,
"learning_rate": 4.105058225653381e-05,
"loss": 0.5725,
"step": 175
},
{
"epoch": 0.3179765130984643,
"grad_norm": 0.22605445682362849,
"learning_rate": 4.093559974371725e-05,
"loss": 0.587,
"step": 176
},
{
"epoch": 0.31978319783197834,
"grad_norm": 0.21706832759188852,
"learning_rate": 4.082004660923703e-05,
"loss": 0.5616,
"step": 177
},
{
"epoch": 0.3215898825654923,
"grad_norm": 0.2481846505984343,
"learning_rate": 4.070392699081767e-05,
"loss": 0.5689,
"step": 178
},
{
"epoch": 0.32339656729900634,
"grad_norm": 0.24149669580110839,
"learning_rate": 4.058724504646834e-05,
"loss": 0.579,
"step": 179
},
{
"epoch": 0.3252032520325203,
"grad_norm": 0.23133462477946873,
"learning_rate": 4.047000495433397e-05,
"loss": 0.5866,
"step": 180
},
{
"epoch": 0.32700993676603435,
"grad_norm": 0.23600639611267185,
"learning_rate": 4.035221091254563e-05,
"loss": 0.566,
"step": 181
},
{
"epoch": 0.3288166214995483,
"grad_norm": 0.23797075690770303,
"learning_rate": 4.023386713907021e-05,
"loss": 0.5757,
"step": 182
},
{
"epoch": 0.33062330623306235,
"grad_norm": 0.2688028365794137,
"learning_rate": 4.011497787155938e-05,
"loss": 0.5858,
"step": 183
},
{
"epoch": 0.3324299909665763,
"grad_norm": 0.23800271670295056,
"learning_rate": 3.9995547367197845e-05,
"loss": 0.5821,
"step": 184
},
{
"epoch": 0.33423667570009036,
"grad_norm": 0.23996238172464596,
"learning_rate": 3.987557990255093e-05,
"loss": 0.578,
"step": 185
},
{
"epoch": 0.33604336043360433,
"grad_norm": 0.24643815239319994,
"learning_rate": 3.975507977341141e-05,
"loss": 0.5736,
"step": 186
},
{
"epoch": 0.33785004516711836,
"grad_norm": 0.24543621085998607,
"learning_rate": 3.963405129464569e-05,
"loss": 0.5708,
"step": 187
},
{
"epoch": 0.33965672990063234,
"grad_norm": 0.23743854464115116,
"learning_rate": 3.9512498800039335e-05,
"loss": 0.5709,
"step": 188
},
{
"epoch": 0.34146341463414637,
"grad_norm": 0.22533834632970712,
"learning_rate": 3.939042664214184e-05,
"loss": 0.578,
"step": 189
},
{
"epoch": 0.34327009936766034,
"grad_norm": 0.23906196177167377,
"learning_rate": 3.92678391921108e-05,
"loss": 0.5669,
"step": 190
},
{
"epoch": 0.34507678410117437,
"grad_norm": 0.234939946303407,
"learning_rate": 3.914474083955537e-05,
"loss": 0.5652,
"step": 191
},
{
"epoch": 0.34688346883468835,
"grad_norm": 0.2853536523500563,
"learning_rate": 3.902113599237911e-05,
"loss": 0.5724,
"step": 192
},
{
"epoch": 0.3486901535682023,
"grad_norm": 0.24065658900008963,
"learning_rate": 3.8897029076622116e-05,
"loss": 0.5737,
"step": 193
},
{
"epoch": 0.35049683830171635,
"grad_norm": 0.31527042154191526,
"learning_rate": 3.8772424536302564e-05,
"loss": 0.5753,
"step": 194
},
{
"epoch": 0.3523035230352303,
"grad_norm": 0.22054076252898716,
"learning_rate": 3.8647326833257545e-05,
"loss": 0.5583,
"step": 195
},
{
"epoch": 0.35411020776874436,
"grad_norm": 0.26633816149722417,
"learning_rate": 3.852174044698333e-05,
"loss": 0.5727,
"step": 196
},
{
"epoch": 0.35591689250225833,
"grad_norm": 0.25081592836844635,
"learning_rate": 3.8395669874474915e-05,
"loss": 0.5715,
"step": 197
},
{
"epoch": 0.35772357723577236,
"grad_norm": 0.2328216628078993,
"learning_rate": 3.826911963006507e-05,
"loss": 0.5479,
"step": 198
},
{
"epoch": 0.35953026196928634,
"grad_norm": 0.24562199794690823,
"learning_rate": 3.814209424526262e-05,
"loss": 0.5726,
"step": 199
},
{
"epoch": 0.36133694670280037,
"grad_norm": 0.29166626692895414,
"learning_rate": 3.801459826859022e-05,
"loss": 0.5611,
"step": 200
},
{
"epoch": 0.36314363143631434,
"grad_norm": 0.20936399329425792,
"learning_rate": 3.788663626542146e-05,
"loss": 0.5557,
"step": 201
},
{
"epoch": 0.36495031616982837,
"grad_norm": 0.26110170412679534,
"learning_rate": 3.7758212817817405e-05,
"loss": 0.5819,
"step": 202
},
{
"epoch": 0.36675700090334235,
"grad_norm": 0.2339662934290823,
"learning_rate": 3.762933252436253e-05,
"loss": 0.5692,
"step": 203
},
{
"epoch": 0.3685636856368564,
"grad_norm": 0.22495118765164016,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.5814,
"step": 204
},
{
"epoch": 0.37037037037037035,
"grad_norm": 0.23422516539657245,
"learning_rate": 3.73702198758665e-05,
"loss": 0.5722,
"step": 205
},
{
"epoch": 0.3721770551038844,
"grad_norm": 0.27457309451205547,
"learning_rate": 3.7239996799126314e-05,
"loss": 0.5595,
"step": 206
},
{
"epoch": 0.37398373983739835,
"grad_norm": 0.2065013157371132,
"learning_rate": 3.7109335432805006e-05,
"loss": 0.5674,
"step": 207
},
{
"epoch": 0.3757904245709124,
"grad_norm": 0.23041323605084132,
"learning_rate": 3.697824045562238e-05,
"loss": 0.5548,
"step": 208
},
{
"epoch": 0.37759710930442636,
"grad_norm": 0.2475043281474649,
"learning_rate": 3.6846716561824965e-05,
"loss": 0.5762,
"step": 209
},
{
"epoch": 0.3794037940379404,
"grad_norm": 0.22901018890711286,
"learning_rate": 3.6714768461017965e-05,
"loss": 0.5723,
"step": 210
},
{
"epoch": 0.38121047877145436,
"grad_norm": 0.22762832427941673,
"learning_rate": 3.6582400877996546e-05,
"loss": 0.5719,
"step": 211
},
{
"epoch": 0.3830171635049684,
"grad_norm": 0.21104506162866918,
"learning_rate": 3.6449618552576695e-05,
"loss": 0.5791,
"step": 212
},
{
"epoch": 0.38482384823848237,
"grad_norm": 0.22739150877525485,
"learning_rate": 3.6316426239425485e-05,
"loss": 0.5801,
"step": 213
},
{
"epoch": 0.3866305329719964,
"grad_norm": 0.22117803030552532,
"learning_rate": 3.6182828707890816e-05,
"loss": 0.5661,
"step": 214
},
{
"epoch": 0.3884372177055104,
"grad_norm": 0.2548691690473502,
"learning_rate": 3.604883074183068e-05,
"loss": 0.5935,
"step": 215
},
{
"epoch": 0.3902439024390244,
"grad_norm": 0.25069360622483716,
"learning_rate": 3.591443713944175e-05,
"loss": 0.5816,
"step": 216
},
{
"epoch": 0.3920505871725384,
"grad_norm": 0.21652716131806354,
"learning_rate": 3.577965271308771e-05,
"loss": 0.5818,
"step": 217
},
{
"epoch": 0.3938572719060524,
"grad_norm": 0.23187893836858786,
"learning_rate": 3.564448228912682e-05,
"loss": 0.5736,
"step": 218
},
{
"epoch": 0.3956639566395664,
"grad_norm": 0.23894374121488227,
"learning_rate": 3.550893070773914e-05,
"loss": 0.5683,
"step": 219
},
{
"epoch": 0.3974706413730804,
"grad_norm": 0.22426881166756849,
"learning_rate": 3.5373002822753216e-05,
"loss": 0.5702,
"step": 220
},
{
"epoch": 0.3992773261065944,
"grad_norm": 0.27082823768134284,
"learning_rate": 3.5236703501472266e-05,
"loss": 0.5595,
"step": 221
},
{
"epoch": 0.4010840108401084,
"grad_norm": 0.21217455734009724,
"learning_rate": 3.510003762449988e-05,
"loss": 0.5766,
"step": 222
},
{
"epoch": 0.4028906955736224,
"grad_norm": 0.2677576523036602,
"learning_rate": 3.496301008556529e-05,
"loss": 0.5589,
"step": 223
},
{
"epoch": 0.4046973803071364,
"grad_norm": 0.21007181644575368,
"learning_rate": 3.4825625791348096e-05,
"loss": 0.5642,
"step": 224
},
{
"epoch": 0.4065040650406504,
"grad_norm": 0.22612255630942563,
"learning_rate": 3.4687889661302576e-05,
"loss": 0.5693,
"step": 225
},
{
"epoch": 0.4083107497741644,
"grad_norm": 0.23999860680155646,
"learning_rate": 3.454980662748156e-05,
"loss": 0.5749,
"step": 226
},
{
"epoch": 0.4101174345076784,
"grad_norm": 0.2302756433264495,
"learning_rate": 3.44113816343598e-05,
"loss": 0.5793,
"step": 227
},
{
"epoch": 0.41192411924119243,
"grad_norm": 0.20519507944237925,
"learning_rate": 3.427261963865691e-05,
"loss": 0.5651,
"step": 228
},
{
"epoch": 0.4137308039747064,
"grad_norm": 0.21459693765627566,
"learning_rate": 3.413352560915988e-05,
"loss": 0.5679,
"step": 229
},
{
"epoch": 0.41553748870822044,
"grad_norm": 0.23921531610620533,
"learning_rate": 3.399410452654518e-05,
"loss": 0.5703,
"step": 230
},
{
"epoch": 0.4173441734417344,
"grad_norm": 0.20606457819819476,
"learning_rate": 3.3854361383200374e-05,
"loss": 0.5694,
"step": 231
},
{
"epoch": 0.41915085817524844,
"grad_norm": 0.20662212946020303,
"learning_rate": 3.3714301183045385e-05,
"loss": 0.572,
"step": 232
},
{
"epoch": 0.4209575429087624,
"grad_norm": 0.1917701637446543,
"learning_rate": 3.357392894135329e-05,
"loss": 0.5543,
"step": 233
},
{
"epoch": 0.42276422764227645,
"grad_norm": 0.2135935066590776,
"learning_rate": 3.343324968457076e-05,
"loss": 0.5694,
"step": 234
},
{
"epoch": 0.4245709123757904,
"grad_norm": 0.1997169832150021,
"learning_rate": 3.329226845013802e-05,
"loss": 0.565,
"step": 235
},
{
"epoch": 0.42637759710930445,
"grad_norm": 0.19119714928358325,
"learning_rate": 3.315099028630855e-05,
"loss": 0.576,
"step": 236
},
{
"epoch": 0.4281842818428184,
"grad_norm": 0.2167132206452593,
"learning_rate": 3.3009420251968244e-05,
"loss": 0.5762,
"step": 237
},
{
"epoch": 0.42999096657633246,
"grad_norm": 0.19361236720932806,
"learning_rate": 3.28675634164543e-05,
"loss": 0.5845,
"step": 238
},
{
"epoch": 0.43179765130984643,
"grad_norm": 0.20924017673648937,
"learning_rate": 3.272542485937369e-05,
"loss": 0.5649,
"step": 239
},
{
"epoch": 0.43360433604336046,
"grad_norm": 0.2024433124622794,
"learning_rate": 3.258300967042125e-05,
"loss": 0.5652,
"step": 240
},
{
"epoch": 0.43541102077687444,
"grad_norm": 0.197067118300435,
"learning_rate": 3.244032294919747e-05,
"loss": 0.5651,
"step": 241
},
{
"epoch": 0.4372177055103884,
"grad_norm": 0.18799553415935533,
"learning_rate": 3.229736980502584e-05,
"loss": 0.565,
"step": 242
},
{
"epoch": 0.43902439024390244,
"grad_norm": 0.20284508241402985,
"learning_rate": 3.215415535676992e-05,
"loss": 0.5694,
"step": 243
},
{
"epoch": 0.4408310749774164,
"grad_norm": 0.21012755724767168,
"learning_rate": 3.201068473265007e-05,
"loss": 0.5762,
"step": 244
},
{
"epoch": 0.44263775971093045,
"grad_norm": 0.23306650237217288,
"learning_rate": 3.186696307005976e-05,
"loss": 0.5679,
"step": 245
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.1827107011346752,
"learning_rate": 3.172299551538164e-05,
"loss": 0.5748,
"step": 246
},
{
"epoch": 0.44625112917795845,
"grad_norm": 0.2018448324475504,
"learning_rate": 3.15787872238033e-05,
"loss": 0.5566,
"step": 247
},
{
"epoch": 0.4480578139114724,
"grad_norm": 0.20873081637782312,
"learning_rate": 3.143434335913256e-05,
"loss": 0.5759,
"step": 248
},
{
"epoch": 0.44986449864498645,
"grad_norm": 0.21261898709611712,
"learning_rate": 3.1289669093612714e-05,
"loss": 0.5587,
"step": 249
},
{
"epoch": 0.45167118337850043,
"grad_norm": 0.21974879665378558,
"learning_rate": 3.1144769607737204e-05,
"loss": 0.5739,
"step": 250
},
{
"epoch": 0.45347786811201446,
"grad_norm": 0.18655406067278144,
"learning_rate": 3.099965009006415e-05,
"loss": 0.5602,
"step": 251
},
{
"epoch": 0.45528455284552843,
"grad_norm": 0.22629066901905626,
"learning_rate": 3.0854315737030596e-05,
"loss": 0.5428,
"step": 252
},
{
"epoch": 0.45709123757904246,
"grad_norm": 0.212471969946471,
"learning_rate": 3.0708771752766394e-05,
"loss": 0.5652,
"step": 253
},
{
"epoch": 0.45889792231255644,
"grad_norm": 0.24001608411694236,
"learning_rate": 3.056302334890786e-05,
"loss": 0.5648,
"step": 254
},
{
"epoch": 0.46070460704607047,
"grad_norm": 0.2148730003032322,
"learning_rate": 3.0417075744411178e-05,
"loss": 0.558,
"step": 255
},
{
"epoch": 0.46251129177958444,
"grad_norm": 0.22096935396084522,
"learning_rate": 3.0270934165365478e-05,
"loss": 0.5581,
"step": 256
},
{
"epoch": 0.4643179765130985,
"grad_norm": 0.21319228060557044,
"learning_rate": 3.0124603844805767e-05,
"loss": 0.5679,
"step": 257
},
{
"epoch": 0.46612466124661245,
"grad_norm": 0.22871931500058323,
"learning_rate": 2.997809002252546e-05,
"loss": 0.5631,
"step": 258
},
{
"epoch": 0.4679313459801265,
"grad_norm": 0.24428128779820235,
"learning_rate": 2.9831397944888833e-05,
"loss": 0.5673,
"step": 259
},
{
"epoch": 0.46973803071364045,
"grad_norm": 0.2265251803183641,
"learning_rate": 2.9684532864643122e-05,
"loss": 0.5806,
"step": 260
},
{
"epoch": 0.4715447154471545,
"grad_norm": 0.25052457618622453,
"learning_rate": 2.953750004073041e-05,
"loss": 0.5716,
"step": 261
},
{
"epoch": 0.47335140018066846,
"grad_norm": 0.2434373403199595,
"learning_rate": 2.9390304738099384e-05,
"loss": 0.5595,
"step": 262
},
{
"epoch": 0.4751580849141825,
"grad_norm": 0.20693141288254044,
"learning_rate": 2.9242952227516722e-05,
"loss": 0.5646,
"step": 263
},
{
"epoch": 0.47696476964769646,
"grad_norm": 0.2845443399908318,
"learning_rate": 2.9095447785378443e-05,
"loss": 0.5705,
"step": 264
},
{
"epoch": 0.4787714543812105,
"grad_norm": 0.19633709266116783,
"learning_rate": 2.89477966935209e-05,
"loss": 0.5516,
"step": 265
},
{
"epoch": 0.48057813911472447,
"grad_norm": 0.2985894654791596,
"learning_rate": 2.8800004239031684e-05,
"loss": 0.5766,
"step": 266
},
{
"epoch": 0.4823848238482385,
"grad_norm": 0.21068414183530343,
"learning_rate": 2.8652075714060295e-05,
"loss": 0.5604,
"step": 267
},
{
"epoch": 0.48419150858175247,
"grad_norm": 0.20641957678197634,
"learning_rate": 2.850401641562865e-05,
"loss": 0.5605,
"step": 268
},
{
"epoch": 0.4859981933152665,
"grad_norm": 0.2133053378034037,
"learning_rate": 2.8355831645441388e-05,
"loss": 0.5676,
"step": 269
},
{
"epoch": 0.4878048780487805,
"grad_norm": 0.1950245280759678,
"learning_rate": 2.8207526709696057e-05,
"loss": 0.5492,
"step": 270
},
{
"epoch": 0.4896115627822945,
"grad_norm": 0.18459613756055562,
"learning_rate": 2.8059106918893068e-05,
"loss": 0.5713,
"step": 271
},
{
"epoch": 0.4914182475158085,
"grad_norm": 0.20229720696059447,
"learning_rate": 2.791057758764557e-05,
"loss": 0.5653,
"step": 272
},
{
"epoch": 0.4932249322493225,
"grad_norm": 0.187115330075385,
"learning_rate": 2.7761944034489152e-05,
"loss": 0.5732,
"step": 273
},
{
"epoch": 0.4950316169828365,
"grad_norm": 0.19182011961116366,
"learning_rate": 2.761321158169134e-05,
"loss": 0.5609,
"step": 274
},
{
"epoch": 0.4968383017163505,
"grad_norm": 0.19961864168095195,
"learning_rate": 2.746438555506109e-05,
"loss": 0.5556,
"step": 275
},
{
"epoch": 0.4986449864498645,
"grad_norm": 0.17496821151909164,
"learning_rate": 2.7315471283758037e-05,
"loss": 0.5468,
"step": 276
},
{
"epoch": 0.5004516711833785,
"grad_norm": 0.17680628153347436,
"learning_rate": 2.7166474100101673e-05,
"loss": 0.5588,
"step": 277
},
{
"epoch": 0.5022583559168925,
"grad_norm": 0.20453728045467803,
"learning_rate": 2.7017399339380434e-05,
"loss": 0.5456,
"step": 278
},
{
"epoch": 0.5040650406504065,
"grad_norm": 0.1846772558220526,
"learning_rate": 2.686825233966061e-05,
"loss": 0.5605,
"step": 279
},
{
"epoch": 0.5058717253839206,
"grad_norm": 0.20728271186281336,
"learning_rate": 2.6719038441595233e-05,
"loss": 0.557,
"step": 280
},
{
"epoch": 0.5076784101174345,
"grad_norm": 0.19373879025332832,
"learning_rate": 2.656976298823284e-05,
"loss": 0.5577,
"step": 281
},
{
"epoch": 0.5094850948509485,
"grad_norm": 0.20242463285271575,
"learning_rate": 2.6420431324826117e-05,
"loss": 0.5529,
"step": 282
},
{
"epoch": 0.5112917795844625,
"grad_norm": 0.20671969932614678,
"learning_rate": 2.6271048798640547e-05,
"loss": 0.5675,
"step": 283
},
{
"epoch": 0.5130984643179766,
"grad_norm": 0.19523574253864587,
"learning_rate": 2.6121620758762877e-05,
"loss": 0.5558,
"step": 284
},
{
"epoch": 0.5149051490514905,
"grad_norm": 0.20809922506439904,
"learning_rate": 2.5972152555909625e-05,
"loss": 0.5508,
"step": 285
},
{
"epoch": 0.5167118337850045,
"grad_norm": 0.1987147573974009,
"learning_rate": 2.5822649542235466e-05,
"loss": 0.5477,
"step": 286
},
{
"epoch": 0.5185185185185185,
"grad_norm": 0.2044500647486356,
"learning_rate": 2.5673117071141572e-05,
"loss": 0.5695,
"step": 287
},
{
"epoch": 0.5203252032520326,
"grad_norm": 0.21743587787329935,
"learning_rate": 2.5523560497083926e-05,
"loss": 0.5668,
"step": 288
},
{
"epoch": 0.5221318879855466,
"grad_norm": 0.1524748342682823,
"learning_rate": 2.5373985175381594e-05,
"loss": 0.5511,
"step": 289
},
{
"epoch": 0.5239385727190605,
"grad_norm": 0.2306744007223048,
"learning_rate": 2.5224396462024947e-05,
"loss": 0.5629,
"step": 290
},
{
"epoch": 0.5257452574525745,
"grad_norm": 0.17775338298730703,
"learning_rate": 2.507479971348391e-05,
"loss": 0.5672,
"step": 291
},
{
"epoch": 0.5275519421860885,
"grad_norm": 0.20455792960737906,
"learning_rate": 2.4925200286516097e-05,
"loss": 0.5714,
"step": 292
},
{
"epoch": 0.5293586269196026,
"grad_norm": 0.19687677338346635,
"learning_rate": 2.4775603537975052e-05,
"loss": 0.5637,
"step": 293
},
{
"epoch": 0.5311653116531165,
"grad_norm": 0.1902782106166477,
"learning_rate": 2.4626014824618415e-05,
"loss": 0.5558,
"step": 294
},
{
"epoch": 0.5329719963866305,
"grad_norm": 0.19191842486692093,
"learning_rate": 2.447643950291608e-05,
"loss": 0.5531,
"step": 295
},
{
"epoch": 0.5347786811201445,
"grad_norm": 0.20477944497711367,
"learning_rate": 2.4326882928858434e-05,
"loss": 0.5576,
"step": 296
},
{
"epoch": 0.5365853658536586,
"grad_norm": 0.20355138027383593,
"learning_rate": 2.417735045776453e-05,
"loss": 0.5624,
"step": 297
},
{
"epoch": 0.5383920505871725,
"grad_norm": 0.20522482421330335,
"learning_rate": 2.402784744409038e-05,
"loss": 0.5572,
"step": 298
},
{
"epoch": 0.5401987353206865,
"grad_norm": 0.21612401652412894,
"learning_rate": 2.3878379241237136e-05,
"loss": 0.5726,
"step": 299
},
{
"epoch": 0.5420054200542005,
"grad_norm": 0.18718439748913515,
"learning_rate": 2.372895120135946e-05,
"loss": 0.5606,
"step": 300
},
{
"epoch": 0.5438121047877146,
"grad_norm": 0.20655510228807006,
"learning_rate": 2.3579568675173895e-05,
"loss": 0.563,
"step": 301
},
{
"epoch": 0.5456187895212286,
"grad_norm": 0.19986616554055486,
"learning_rate": 2.3430237011767167e-05,
"loss": 0.5742,
"step": 302
},
{
"epoch": 0.5474254742547425,
"grad_norm": 0.1708815737536436,
"learning_rate": 2.3280961558404773e-05,
"loss": 0.5552,
"step": 303
},
{
"epoch": 0.5492321589882565,
"grad_norm": 0.21485382031988715,
"learning_rate": 2.3131747660339394e-05,
"loss": 0.5504,
"step": 304
},
{
"epoch": 0.5510388437217706,
"grad_norm": 0.20605159502714507,
"learning_rate": 2.2982600660619572e-05,
"loss": 0.5569,
"step": 305
},
{
"epoch": 0.5528455284552846,
"grad_norm": 0.1641704272806159,
"learning_rate": 2.2833525899898326e-05,
"loss": 0.555,
"step": 306
},
{
"epoch": 0.5546522131887985,
"grad_norm": 0.21479657500132696,
"learning_rate": 2.268452871624197e-05,
"loss": 0.5723,
"step": 307
},
{
"epoch": 0.5564588979223125,
"grad_norm": 0.20996833106032847,
"learning_rate": 2.2535614444938912e-05,
"loss": 0.5512,
"step": 308
},
{
"epoch": 0.5582655826558266,
"grad_norm": 0.2029214726494778,
"learning_rate": 2.238678841830867e-05,
"loss": 0.5611,
"step": 309
},
{
"epoch": 0.5600722673893406,
"grad_norm": 0.17555009156826745,
"learning_rate": 2.223805596551085e-05,
"loss": 0.5429,
"step": 310
},
{
"epoch": 0.5618789521228545,
"grad_norm": 0.1999338963231407,
"learning_rate": 2.2089422412354432e-05,
"loss": 0.5626,
"step": 311
},
{
"epoch": 0.5636856368563685,
"grad_norm": 0.16777175092227642,
"learning_rate": 2.1940893081106945e-05,
"loss": 0.5618,
"step": 312
},
{
"epoch": 0.5654923215898826,
"grad_norm": 0.18839270792057577,
"learning_rate": 2.1792473290303946e-05,
"loss": 0.5622,
"step": 313
},
{
"epoch": 0.5672990063233966,
"grad_norm": 0.171252210254393,
"learning_rate": 2.164416835455862e-05,
"loss": 0.5548,
"step": 314
},
{
"epoch": 0.5691056910569106,
"grad_norm": 0.16167758551027236,
"learning_rate": 2.1495983584371353e-05,
"loss": 0.5554,
"step": 315
},
{
"epoch": 0.5709123757904245,
"grad_norm": 0.16983556095769603,
"learning_rate": 2.1347924285939714e-05,
"loss": 0.5509,
"step": 316
},
{
"epoch": 0.5727190605239386,
"grad_norm": 0.16081098293816312,
"learning_rate": 2.119999576096832e-05,
"loss": 0.5466,
"step": 317
},
{
"epoch": 0.5745257452574526,
"grad_norm": 0.1735900274427839,
"learning_rate": 2.1052203306479105e-05,
"loss": 0.5591,
"step": 318
},
{
"epoch": 0.5763324299909666,
"grad_norm": 0.20818262518741384,
"learning_rate": 2.090455221462156e-05,
"loss": 0.5685,
"step": 319
},
{
"epoch": 0.5781391147244805,
"grad_norm": 0.18585485739434782,
"learning_rate": 2.075704777248328e-05,
"loss": 0.5508,
"step": 320
},
{
"epoch": 0.5799457994579946,
"grad_norm": 0.17765189017593874,
"learning_rate": 2.0609695261900622e-05,
"loss": 0.5482,
"step": 321
},
{
"epoch": 0.5817524841915086,
"grad_norm": 0.1888140177134527,
"learning_rate": 2.0462499959269593e-05,
"loss": 0.5692,
"step": 322
},
{
"epoch": 0.5835591689250226,
"grad_norm": 0.1887535885868274,
"learning_rate": 2.031546713535688e-05,
"loss": 0.5552,
"step": 323
},
{
"epoch": 0.5853658536585366,
"grad_norm": 0.1708632281478148,
"learning_rate": 2.0168602055111173e-05,
"loss": 0.5362,
"step": 324
},
{
"epoch": 0.5871725383920506,
"grad_norm": 0.18004810755806852,
"learning_rate": 2.002190997747455e-05,
"loss": 0.553,
"step": 325
},
{
"epoch": 0.5889792231255646,
"grad_norm": 0.20548541788819144,
"learning_rate": 1.9875396155194242e-05,
"loss": 0.5632,
"step": 326
},
{
"epoch": 0.5907859078590786,
"grad_norm": 0.177852655772985,
"learning_rate": 1.972906583463453e-05,
"loss": 0.549,
"step": 327
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.2075462975074931,
"learning_rate": 1.9582924255588828e-05,
"loss": 0.5564,
"step": 328
},
{
"epoch": 0.5943992773261066,
"grad_norm": 0.18365236875660207,
"learning_rate": 1.9436976651092144e-05,
"loss": 0.5455,
"step": 329
},
{
"epoch": 0.5962059620596206,
"grad_norm": 0.18343466313569637,
"learning_rate": 1.9291228247233605e-05,
"loss": 0.5541,
"step": 330
},
{
"epoch": 0.5980126467931346,
"grad_norm": 0.21592712312915163,
"learning_rate": 1.9145684262969403e-05,
"loss": 0.5571,
"step": 331
},
{
"epoch": 0.5998193315266486,
"grad_norm": 0.1932700627769742,
"learning_rate": 1.9000349909935853e-05,
"loss": 0.5406,
"step": 332
},
{
"epoch": 0.6016260162601627,
"grad_norm": 0.16339930231591715,
"learning_rate": 1.885523039226281e-05,
"loss": 0.5611,
"step": 333
},
{
"epoch": 0.6034327009936766,
"grad_norm": 0.21730546749076898,
"learning_rate": 1.871033090638729e-05,
"loss": 0.5735,
"step": 334
},
{
"epoch": 0.6052393857271906,
"grad_norm": 0.17833202494703654,
"learning_rate": 1.8565656640867446e-05,
"loss": 0.5569,
"step": 335
},
{
"epoch": 0.6070460704607046,
"grad_norm": 0.22046249018405806,
"learning_rate": 1.8421212776196712e-05,
"loss": 0.5532,
"step": 336
},
{
"epoch": 0.6088527551942186,
"grad_norm": 0.19273802746665908,
"learning_rate": 1.827700448461836e-05,
"loss": 0.5553,
"step": 337
},
{
"epoch": 0.6106594399277326,
"grad_norm": 0.1717722139746852,
"learning_rate": 1.813303692994025e-05,
"loss": 0.5512,
"step": 338
},
{
"epoch": 0.6124661246612466,
"grad_norm": 0.19224160494805076,
"learning_rate": 1.7989315267349936e-05,
"loss": 0.5598,
"step": 339
},
{
"epoch": 0.6142728093947606,
"grad_norm": 0.19905838448911242,
"learning_rate": 1.7845844643230086e-05,
"loss": 0.5551,
"step": 340
},
{
"epoch": 0.6160794941282746,
"grad_norm": 0.15209072200928186,
"learning_rate": 1.7702630194974168e-05,
"loss": 0.5534,
"step": 341
},
{
"epoch": 0.6178861788617886,
"grad_norm": 0.19687154617168753,
"learning_rate": 1.7559677050802544e-05,
"loss": 0.5564,
"step": 342
},
{
"epoch": 0.6196928635953026,
"grad_norm": 0.19188924874973992,
"learning_rate": 1.7416990329578753e-05,
"loss": 0.5506,
"step": 343
},
{
"epoch": 0.6214995483288166,
"grad_norm": 0.14236315643590053,
"learning_rate": 1.7274575140626318e-05,
"loss": 0.5401,
"step": 344
},
{
"epoch": 0.6233062330623306,
"grad_norm": 0.20387469447466464,
"learning_rate": 1.71324365835457e-05,
"loss": 0.5542,
"step": 345
},
{
"epoch": 0.6251129177958447,
"grad_norm": 0.18992643721472474,
"learning_rate": 1.699057974803176e-05,
"loss": 0.5562,
"step": 346
},
{
"epoch": 0.6269196025293586,
"grad_norm": 0.1586577289853951,
"learning_rate": 1.6849009713691454e-05,
"loss": 0.542,
"step": 347
},
{
"epoch": 0.6287262872628726,
"grad_norm": 0.1548055569604781,
"learning_rate": 1.670773154986199e-05,
"loss": 0.5433,
"step": 348
},
{
"epoch": 0.6305329719963866,
"grad_norm": 0.18952772876915885,
"learning_rate": 1.6566750315429254e-05,
"loss": 0.5465,
"step": 349
},
{
"epoch": 0.6323396567299007,
"grad_norm": 0.17661144150936864,
"learning_rate": 1.6426071058646717e-05,
"loss": 0.5582,
"step": 350
},
{
"epoch": 0.6341463414634146,
"grad_norm": 0.1634210251821867,
"learning_rate": 1.6285698816954624e-05,
"loss": 0.5475,
"step": 351
},
{
"epoch": 0.6359530261969286,
"grad_norm": 0.16869752523852172,
"learning_rate": 1.6145638616799635e-05,
"loss": 0.5616,
"step": 352
},
{
"epoch": 0.6377597109304426,
"grad_norm": 0.16358016754832452,
"learning_rate": 1.6005895473454834e-05,
"loss": 0.5619,
"step": 353
},
{
"epoch": 0.6395663956639567,
"grad_norm": 0.1658741695923892,
"learning_rate": 1.5866474390840125e-05,
"loss": 0.5568,
"step": 354
},
{
"epoch": 0.6413730803974707,
"grad_norm": 0.16273812799461698,
"learning_rate": 1.5727380361343103e-05,
"loss": 0.5458,
"step": 355
},
{
"epoch": 0.6431797651309846,
"grad_norm": 0.15002769317168096,
"learning_rate": 1.55886183656402e-05,
"loss": 0.559,
"step": 356
},
{
"epoch": 0.6449864498644986,
"grad_norm": 0.16465546963678185,
"learning_rate": 1.545019337251844e-05,
"loss": 0.5611,
"step": 357
},
{
"epoch": 0.6467931345980127,
"grad_norm": 0.17913262704620259,
"learning_rate": 1.5312110338697426e-05,
"loss": 0.5666,
"step": 358
},
{
"epoch": 0.6485998193315267,
"grad_norm": 0.16396538642770328,
"learning_rate": 1.5174374208651912e-05,
"loss": 0.5396,
"step": 359
},
{
"epoch": 0.6504065040650406,
"grad_norm": 0.15380691000643246,
"learning_rate": 1.503698991443471e-05,
"loss": 0.5486,
"step": 360
},
{
"epoch": 0.6522131887985546,
"grad_norm": 0.1995320119007658,
"learning_rate": 1.4899962375500121e-05,
"loss": 0.5531,
"step": 361
},
{
"epoch": 0.6540198735320687,
"grad_norm": 0.161774707466089,
"learning_rate": 1.4763296498527743e-05,
"loss": 0.565,
"step": 362
},
{
"epoch": 0.6558265582655827,
"grad_norm": 0.1906331361355129,
"learning_rate": 1.4626997177246787e-05,
"loss": 0.5551,
"step": 363
},
{
"epoch": 0.6576332429990966,
"grad_norm": 0.1886665619129233,
"learning_rate": 1.4491069292260868e-05,
"loss": 0.5549,
"step": 364
},
{
"epoch": 0.6594399277326106,
"grad_norm": 0.17119682961707747,
"learning_rate": 1.4355517710873184e-05,
"loss": 0.5468,
"step": 365
},
{
"epoch": 0.6612466124661247,
"grad_norm": 0.18291533226322426,
"learning_rate": 1.4220347286912294e-05,
"loss": 0.5679,
"step": 366
},
{
"epoch": 0.6630532971996387,
"grad_norm": 0.1641189400153277,
"learning_rate": 1.4085562860558255e-05,
"loss": 0.549,
"step": 367
},
{
"epoch": 0.6648599819331527,
"grad_norm": 0.18230958758020346,
"learning_rate": 1.3951169258169338e-05,
"loss": 0.5607,
"step": 368
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.20111949543104507,
"learning_rate": 1.3817171292109183e-05,
"loss": 0.5618,
"step": 369
},
{
"epoch": 0.6684733514001807,
"grad_norm": 0.15758105531782077,
"learning_rate": 1.3683573760574526e-05,
"loss": 0.56,
"step": 370
},
{
"epoch": 0.6702800361336947,
"grad_norm": 0.16982875332850716,
"learning_rate": 1.3550381447423316e-05,
"loss": 0.5482,
"step": 371
},
{
"epoch": 0.6720867208672087,
"grad_norm": 0.17933157068180672,
"learning_rate": 1.3417599122003464e-05,
"loss": 0.5657,
"step": 372
},
{
"epoch": 0.6738934056007226,
"grad_norm": 0.18459440763752274,
"learning_rate": 1.3285231538982034e-05,
"loss": 0.5513,
"step": 373
},
{
"epoch": 0.6757000903342367,
"grad_norm": 0.16083685494739997,
"learning_rate": 1.3153283438175034e-05,
"loss": 0.5407,
"step": 374
},
{
"epoch": 0.6775067750677507,
"grad_norm": 0.15405258024233726,
"learning_rate": 1.3021759544377632e-05,
"loss": 0.5547,
"step": 375
},
{
"epoch": 0.6793134598012647,
"grad_norm": 0.16654047654120907,
"learning_rate": 1.2890664567194998e-05,
"loss": 0.5397,
"step": 376
},
{
"epoch": 0.6811201445347786,
"grad_norm": 0.14230106037907364,
"learning_rate": 1.2760003200873699e-05,
"loss": 0.5561,
"step": 377
},
{
"epoch": 0.6829268292682927,
"grad_norm": 0.15132539994045122,
"learning_rate": 1.2629780124133511e-05,
"loss": 0.5564,
"step": 378
},
{
"epoch": 0.6847335140018067,
"grad_norm": 0.15729562655387452,
"learning_rate": 1.2500000000000006e-05,
"loss": 0.5596,
"step": 379
},
{
"epoch": 0.6865401987353207,
"grad_norm": 0.15385535572955647,
"learning_rate": 1.2370667475637473e-05,
"loss": 0.5408,
"step": 380
},
{
"epoch": 0.6883468834688347,
"grad_norm": 0.1674564887807595,
"learning_rate": 1.2241787182182595e-05,
"loss": 0.5567,
"step": 381
},
{
"epoch": 0.6901535682023487,
"grad_norm": 0.16639339098640638,
"learning_rate": 1.2113363734578548e-05,
"loss": 0.5444,
"step": 382
},
{
"epoch": 0.6919602529358627,
"grad_norm": 0.1527514867231356,
"learning_rate": 1.1985401731409792e-05,
"loss": 0.5635,
"step": 383
},
{
"epoch": 0.6937669376693767,
"grad_norm": 0.16009854332609694,
"learning_rate": 1.185790575473738e-05,
"loss": 0.5609,
"step": 384
},
{
"epoch": 0.6955736224028907,
"grad_norm": 0.16766734469024944,
"learning_rate": 1.1730880369934933e-05,
"loss": 0.5436,
"step": 385
},
{
"epoch": 0.6973803071364046,
"grad_norm": 0.17885151327628188,
"learning_rate": 1.1604330125525079e-05,
"loss": 0.5553,
"step": 386
},
{
"epoch": 0.6991869918699187,
"grad_norm": 0.16462273760617374,
"learning_rate": 1.1478259553016682e-05,
"loss": 0.5552,
"step": 387
},
{
"epoch": 0.7009936766034327,
"grad_norm": 0.14238942232592058,
"learning_rate": 1.135267316674246e-05,
"loss": 0.5539,
"step": 388
},
{
"epoch": 0.7028003613369467,
"grad_norm": 0.15563141315692475,
"learning_rate": 1.122757546369744e-05,
"loss": 0.5565,
"step": 389
},
{
"epoch": 0.7046070460704607,
"grad_norm": 0.19104860399328163,
"learning_rate": 1.1102970923377892e-05,
"loss": 0.5517,
"step": 390
},
{
"epoch": 0.7064137308039747,
"grad_norm": 0.1675034589851422,
"learning_rate": 1.0978864007620895e-05,
"loss": 0.5508,
"step": 391
},
{
"epoch": 0.7082204155374887,
"grad_norm": 0.14316976954035696,
"learning_rate": 1.0855259160444639e-05,
"loss": 0.5569,
"step": 392
},
{
"epoch": 0.7100271002710027,
"grad_norm": 0.164822094386159,
"learning_rate": 1.0732160807889211e-05,
"loss": 0.5618,
"step": 393
},
{
"epoch": 0.7118337850045167,
"grad_norm": 0.1434819308104398,
"learning_rate": 1.0609573357858166e-05,
"loss": 0.5646,
"step": 394
},
{
"epoch": 0.7136404697380307,
"grad_norm": 0.15319132949187717,
"learning_rate": 1.0487501199960662e-05,
"loss": 0.5585,
"step": 395
},
{
"epoch": 0.7154471544715447,
"grad_norm": 0.14568825018363862,
"learning_rate": 1.0365948705354308e-05,
"loss": 0.5528,
"step": 396
},
{
"epoch": 0.7172538392050587,
"grad_norm": 0.13871097048038203,
"learning_rate": 1.0244920226588597e-05,
"loss": 0.5532,
"step": 397
},
{
"epoch": 0.7190605239385727,
"grad_norm": 0.14567794989191493,
"learning_rate": 1.0124420097449078e-05,
"loss": 0.5546,
"step": 398
},
{
"epoch": 0.7208672086720868,
"grad_norm": 0.14644885971929225,
"learning_rate": 1.0004452632802158e-05,
"loss": 0.5568,
"step": 399
},
{
"epoch": 0.7226738934056007,
"grad_norm": 0.14818158885551921,
"learning_rate": 9.88502212844063e-06,
"loss": 0.554,
"step": 400
},
{
"epoch": 0.7244805781391147,
"grad_norm": 0.14106148009378217,
"learning_rate": 9.7661328609298e-06,
"loss": 0.5553,
"step": 401
},
{
"epoch": 0.7262872628726287,
"grad_norm": 0.13667122105921192,
"learning_rate": 9.64778908745437e-06,
"loss": 0.5618,
"step": 402
},
{
"epoch": 0.7280939476061428,
"grad_norm": 0.1608469894131315,
"learning_rate": 9.52999504566604e-06,
"loss": 0.544,
"step": 403
},
{
"epoch": 0.7299006323396567,
"grad_norm": 0.15835331464294836,
"learning_rate": 9.412754953531663e-06,
"loss": 0.5498,
"step": 404
},
{
"epoch": 0.7317073170731707,
"grad_norm": 0.14610347758395736,
"learning_rate": 9.29607300918234e-06,
"loss": 0.5476,
"step": 405
},
{
"epoch": 0.7335140018066847,
"grad_norm": 0.15690849940347346,
"learning_rate": 9.179953390762977e-06,
"loss": 0.5538,
"step": 406
},
{
"epoch": 0.7353206865401988,
"grad_norm": 0.14885600275960284,
"learning_rate": 9.064400256282757e-06,
"loss": 0.5457,
"step": 407
},
{
"epoch": 0.7371273712737128,
"grad_norm": 0.16033956078405742,
"learning_rate": 8.9494177434662e-06,
"loss": 0.5395,
"step": 408
},
{
"epoch": 0.7389340560072267,
"grad_norm": 0.16975416753648587,
"learning_rate": 8.835009969605012e-06,
"loss": 0.5599,
"step": 409
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.14200975204371785,
"learning_rate": 8.72118103141066e-06,
"loss": 0.5597,
"step": 410
},
{
"epoch": 0.7425474254742548,
"grad_norm": 0.13590744017127132,
"learning_rate": 8.607935004867693e-06,
"loss": 0.562,
"step": 411
},
{
"epoch": 0.7443541102077688,
"grad_norm": 0.14704548150234487,
"learning_rate": 8.495275945087744e-06,
"loss": 0.5354,
"step": 412
},
{
"epoch": 0.7461607949412827,
"grad_norm": 0.1700265389519706,
"learning_rate": 8.383207886164366e-06,
"loss": 0.5509,
"step": 413
},
{
"epoch": 0.7479674796747967,
"grad_norm": 0.14029261574177768,
"learning_rate": 8.271734841028553e-06,
"loss": 0.5392,
"step": 414
},
{
"epoch": 0.7497741644083108,
"grad_norm": 0.14570171543098534,
"learning_rate": 8.16086080130506e-06,
"loss": 0.5603,
"step": 415
},
{
"epoch": 0.7515808491418248,
"grad_norm": 0.14459493509758678,
"learning_rate": 8.050589737169485e-06,
"loss": 0.5465,
"step": 416
},
{
"epoch": 0.7533875338753387,
"grad_norm": 0.14997051611036516,
"learning_rate": 7.940925597206054e-06,
"loss": 0.5677,
"step": 417
},
{
"epoch": 0.7551942186088527,
"grad_norm": 0.14893256736938013,
"learning_rate": 7.831872308266305e-06,
"loss": 0.5497,
"step": 418
},
{
"epoch": 0.7570009033423668,
"grad_norm": 0.12975833335896694,
"learning_rate": 7.723433775328384e-06,
"loss": 0.5516,
"step": 419
},
{
"epoch": 0.7588075880758808,
"grad_norm": 0.14300873943959558,
"learning_rate": 7.615613881357314e-06,
"loss": 0.565,
"step": 420
},
{
"epoch": 0.7606142728093948,
"grad_norm": 0.14079069334135458,
"learning_rate": 7.508416487165862e-06,
"loss": 0.5471,
"step": 421
},
{
"epoch": 0.7624209575429087,
"grad_norm": 0.1337273362255202,
"learning_rate": 7.401845431276378e-06,
"loss": 0.5507,
"step": 422
},
{
"epoch": 0.7642276422764228,
"grad_norm": 0.14360087992057755,
"learning_rate": 7.2959045297832655e-06,
"loss": 0.5594,
"step": 423
},
{
"epoch": 0.7660343270099368,
"grad_norm": 0.12921027019794465,
"learning_rate": 7.190597576216385e-06,
"loss": 0.5627,
"step": 424
},
{
"epoch": 0.7678410117434508,
"grad_norm": 0.1432604502796488,
"learning_rate": 7.085928341405193e-06,
"loss": 0.5412,
"step": 425
},
{
"epoch": 0.7696476964769647,
"grad_norm": 0.14064931255060933,
"learning_rate": 6.98190057334375e-06,
"loss": 0.5619,
"step": 426
},
{
"epoch": 0.7714543812104788,
"grad_norm": 0.13174198316950445,
"learning_rate": 6.8785179970564575e-06,
"loss": 0.5335,
"step": 427
},
{
"epoch": 0.7732610659439928,
"grad_norm": 0.13461721816405586,
"learning_rate": 6.775784314464717e-06,
"loss": 0.5541,
"step": 428
},
{
"epoch": 0.7750677506775068,
"grad_norm": 0.13918266216688774,
"learning_rate": 6.673703204254347e-06,
"loss": 0.5493,
"step": 429
},
{
"epoch": 0.7768744354110207,
"grad_norm": 0.1334982528230231,
"learning_rate": 6.572278321743871e-06,
"loss": 0.5498,
"step": 430
},
{
"epoch": 0.7786811201445348,
"grad_norm": 0.1446375191357851,
"learning_rate": 6.471513298753634e-06,
"loss": 0.5587,
"step": 431
},
{
"epoch": 0.7804878048780488,
"grad_norm": 0.1349572254064227,
"learning_rate": 6.371411743475716e-06,
"loss": 0.5543,
"step": 432
},
{
"epoch": 0.7822944896115628,
"grad_norm": 0.12916444725593595,
"learning_rate": 6.271977240344795e-06,
"loss": 0.5615,
"step": 433
},
{
"epoch": 0.7841011743450768,
"grad_norm": 0.13066976774818734,
"learning_rate": 6.173213349909729e-06,
"loss": 0.5598,
"step": 434
},
{
"epoch": 0.7859078590785907,
"grad_norm": 0.1405046563021993,
"learning_rate": 6.075123608706093e-06,
"loss": 0.5382,
"step": 435
},
{
"epoch": 0.7877145438121048,
"grad_norm": 0.14506911798470398,
"learning_rate": 5.97771152912954e-06,
"loss": 0.5523,
"step": 436
},
{
"epoch": 0.7895212285456188,
"grad_norm": 0.1304335472931119,
"learning_rate": 5.88098059931004e-06,
"loss": 0.5512,
"step": 437
},
{
"epoch": 0.7913279132791328,
"grad_norm": 0.1473977265159944,
"learning_rate": 5.784934282986956e-06,
"loss": 0.5424,
"step": 438
},
{
"epoch": 0.7931345980126467,
"grad_norm": 0.1411547897464082,
"learning_rate": 5.689576019385015e-06,
"loss": 0.5597,
"step": 439
},
{
"epoch": 0.7949412827461608,
"grad_norm": 0.13612601725097978,
"learning_rate": 5.59490922309118e-06,
"loss": 0.5505,
"step": 440
},
{
"epoch": 0.7967479674796748,
"grad_norm": 0.1322794213045051,
"learning_rate": 5.500937283932348e-06,
"loss": 0.5367,
"step": 441
},
{
"epoch": 0.7985546522131888,
"grad_norm": 0.12458267675211761,
"learning_rate": 5.4076635668540075e-06,
"loss": 0.5454,
"step": 442
},
{
"epoch": 0.8003613369467028,
"grad_norm": 0.15372071644276483,
"learning_rate": 5.3150914117996995e-06,
"loss": 0.5525,
"step": 443
},
{
"epoch": 0.8021680216802168,
"grad_norm": 0.13481571078325,
"learning_rate": 5.223224133591476e-06,
"loss": 0.5584,
"step": 444
},
{
"epoch": 0.8039747064137308,
"grad_norm": 0.1392239579880989,
"learning_rate": 5.132065021811122e-06,
"loss": 0.5464,
"step": 445
},
{
"epoch": 0.8057813911472448,
"grad_norm": 0.1440455592009233,
"learning_rate": 5.041617340682467e-06,
"loss": 0.5446,
"step": 446
},
{
"epoch": 0.8075880758807588,
"grad_norm": 0.13169239899061416,
"learning_rate": 4.951884328954401e-06,
"loss": 0.5489,
"step": 447
},
{
"epoch": 0.8093947606142728,
"grad_norm": 0.12835341463302258,
"learning_rate": 4.862869199784984e-06,
"loss": 0.5518,
"step": 448
},
{
"epoch": 0.8112014453477868,
"grad_norm": 0.13049293976698467,
"learning_rate": 4.7745751406263165e-06,
"loss": 0.5462,
"step": 449
},
{
"epoch": 0.8130081300813008,
"grad_norm": 0.13490608982833951,
"learning_rate": 4.687005313110454e-06,
"loss": 0.5573,
"step": 450
},
{
"epoch": 0.8148148148148148,
"grad_norm": 0.15409616538853282,
"learning_rate": 4.600162852936171e-06,
"loss": 0.5576,
"step": 451
},
{
"epoch": 0.8166214995483289,
"grad_norm": 0.1319073701280829,
"learning_rate": 4.514050869756703e-06,
"loss": 0.555,
"step": 452
},
{
"epoch": 0.8184281842818428,
"grad_norm": 0.14043052825133548,
"learning_rate": 4.428672447068357e-06,
"loss": 0.5469,
"step": 453
},
{
"epoch": 0.8202348690153568,
"grad_norm": 0.14320434022652317,
"learning_rate": 4.344030642100133e-06,
"loss": 0.5319,
"step": 454
},
{
"epoch": 0.8220415537488708,
"grad_norm": 0.12352233143884875,
"learning_rate": 4.2601284857042266e-06,
"loss": 0.5544,
"step": 455
},
{
"epoch": 0.8238482384823849,
"grad_norm": 0.12791641119273095,
"learning_rate": 4.176968982247514e-06,
"loss": 0.5472,
"step": 456
},
{
"epoch": 0.8256549232158988,
"grad_norm": 0.12756429713792805,
"learning_rate": 4.094555109503983e-06,
"loss": 0.5613,
"step": 457
},
{
"epoch": 0.8274616079494128,
"grad_norm": 0.126174994814594,
"learning_rate": 4.012889818548069e-06,
"loss": 0.553,
"step": 458
},
{
"epoch": 0.8292682926829268,
"grad_norm": 0.12380047427350403,
"learning_rate": 3.931976033649021e-06,
"loss": 0.5428,
"step": 459
},
{
"epoch": 0.8310749774164409,
"grad_norm": 0.14813524967986672,
"learning_rate": 3.851816652166165e-06,
"loss": 0.5521,
"step": 460
},
{
"epoch": 0.8328816621499548,
"grad_norm": 0.14157434762161733,
"learning_rate": 3.772414544445163e-06,
"loss": 0.5403,
"step": 461
},
{
"epoch": 0.8346883468834688,
"grad_norm": 0.1244834124319828,
"learning_rate": 3.6937725537152274e-06,
"loss": 0.5481,
"step": 462
},
{
"epoch": 0.8364950316169828,
"grad_norm": 0.12292461490782491,
"learning_rate": 3.6158934959873353e-06,
"loss": 0.5522,
"step": 463
},
{
"epoch": 0.8383017163504969,
"grad_norm": 0.1391924289910159,
"learning_rate": 3.5387801599533475e-06,
"loss": 0.5549,
"step": 464
},
{
"epoch": 0.8401084010840109,
"grad_norm": 0.16494278794967426,
"learning_rate": 3.4624353068861943e-06,
"loss": 0.565,
"step": 465
},
{
"epoch": 0.8419150858175248,
"grad_norm": 0.12253790382162442,
"learning_rate": 3.386861670540972e-06,
"loss": 0.5474,
"step": 466
},
{
"epoch": 0.8437217705510388,
"grad_norm": 0.12412506838379729,
"learning_rate": 3.312061957057061e-06,
"loss": 0.5449,
"step": 467
},
{
"epoch": 0.8455284552845529,
"grad_norm": 0.12608545254096767,
"learning_rate": 3.2380388448612437e-06,
"loss": 0.555,
"step": 468
},
{
"epoch": 0.8473351400180669,
"grad_norm": 0.13765660845308572,
"learning_rate": 3.164794984571759e-06,
"loss": 0.5439,
"step": 469
},
{
"epoch": 0.8491418247515808,
"grad_norm": 0.13303272946891692,
"learning_rate": 3.092332998903416e-06,
"loss": 0.5406,
"step": 470
},
{
"epoch": 0.8509485094850948,
"grad_norm": 0.13398725526516422,
"learning_rate": 3.020655482573659e-06,
"loss": 0.5695,
"step": 471
},
{
"epoch": 0.8527551942186089,
"grad_norm": 0.1257892586168214,
"learning_rate": 2.949765002209698e-06,
"loss": 0.5408,
"step": 472
},
{
"epoch": 0.8545618789521229,
"grad_norm": 0.13307872139497165,
"learning_rate": 2.8796640962565374e-06,
"loss": 0.5595,
"step": 473
},
{
"epoch": 0.8563685636856369,
"grad_norm": 0.12654937381055872,
"learning_rate": 2.8103552748861476e-06,
"loss": 0.5548,
"step": 474
},
{
"epoch": 0.8581752484191508,
"grad_norm": 0.15588973804220943,
"learning_rate": 2.741841019907529e-06,
"loss": 0.5449,
"step": 475
},
{
"epoch": 0.8599819331526649,
"grad_norm": 0.13606575707534016,
"learning_rate": 2.6741237846778676e-06,
"loss": 0.5512,
"step": 476
},
{
"epoch": 0.8617886178861789,
"grad_norm": 0.12582862963422667,
"learning_rate": 2.6072059940146775e-06,
"loss": 0.5484,
"step": 477
},
{
"epoch": 0.8635953026196929,
"grad_norm": 0.13448395028531923,
"learning_rate": 2.5410900441089903e-06,
"loss": 0.5588,
"step": 478
},
{
"epoch": 0.8654019873532068,
"grad_norm": 0.131896758506052,
"learning_rate": 2.475778302439524e-06,
"loss": 0.5449,
"step": 479
},
{
"epoch": 0.8672086720867209,
"grad_norm": 0.12317136603552087,
"learning_rate": 2.411273107687925e-06,
"loss": 0.5433,
"step": 480
},
{
"epoch": 0.8690153568202349,
"grad_norm": 0.12519659554367746,
"learning_rate": 2.3475767696550327e-06,
"loss": 0.5542,
"step": 481
},
{
"epoch": 0.8708220415537489,
"grad_norm": 0.12477743275169467,
"learning_rate": 2.284691569178138e-06,
"loss": 0.558,
"step": 482
},
{
"epoch": 0.8726287262872628,
"grad_norm": 0.13108905882126104,
"learning_rate": 2.222619758049366e-06,
"loss": 0.5425,
"step": 483
},
{
"epoch": 0.8744354110207768,
"grad_norm": 0.12783021427026073,
"learning_rate": 2.1613635589349756e-06,
"loss": 0.5389,
"step": 484
},
{
"epoch": 0.8762420957542909,
"grad_norm": 0.13442586381092825,
"learning_rate": 2.1009251652958387e-06,
"loss": 0.5495,
"step": 485
},
{
"epoch": 0.8780487804878049,
"grad_norm": 0.12218328740529147,
"learning_rate": 2.041306741308832e-06,
"loss": 0.5552,
"step": 486
},
{
"epoch": 0.8798554652213189,
"grad_norm": 0.11666083021995531,
"learning_rate": 1.9825104217894018e-06,
"loss": 0.5434,
"step": 487
},
{
"epoch": 0.8816621499548328,
"grad_norm": 0.11891817302152466,
"learning_rate": 1.9245383121150677e-06,
"loss": 0.5426,
"step": 488
},
{
"epoch": 0.8834688346883469,
"grad_norm": 0.1140234156588416,
"learning_rate": 1.8673924881500826e-06,
"loss": 0.5517,
"step": 489
},
{
"epoch": 0.8852755194218609,
"grad_norm": 0.12842139305951047,
"learning_rate": 1.8110749961710584e-06,
"loss": 0.5491,
"step": 490
},
{
"epoch": 0.8870822041553749,
"grad_norm": 0.11838976619432588,
"learning_rate": 1.7555878527937164e-06,
"loss": 0.5401,
"step": 491
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.12082210289598717,
"learning_rate": 1.700933044900671e-06,
"loss": 0.5417,
"step": 492
},
{
"epoch": 0.8906955736224029,
"grad_norm": 0.11570866034278628,
"learning_rate": 1.6471125295702771e-06,
"loss": 0.5361,
"step": 493
},
{
"epoch": 0.8925022583559169,
"grad_norm": 0.11343676015432415,
"learning_rate": 1.59412823400657e-06,
"loss": 0.5534,
"step": 494
},
{
"epoch": 0.8943089430894309,
"grad_norm": 0.12481665562887206,
"learning_rate": 1.5419820554702314e-06,
"loss": 0.5502,
"step": 495
},
{
"epoch": 0.8961156278229448,
"grad_norm": 0.12943261253764746,
"learning_rate": 1.4906758612106636e-06,
"loss": 0.5622,
"step": 496
},
{
"epoch": 0.8979223125564589,
"grad_norm": 0.13084171253702748,
"learning_rate": 1.4402114883991318e-06,
"loss": 0.5497,
"step": 497
},
{
"epoch": 0.8997289972899729,
"grad_norm": 0.12224161211709644,
"learning_rate": 1.3905907440629752e-06,
"loss": 0.549,
"step": 498
},
{
"epoch": 0.9015356820234869,
"grad_norm": 0.13065140590758795,
"learning_rate": 1.3418154050208936e-06,
"loss": 0.558,
"step": 499
},
{
"epoch": 0.9033423667570009,
"grad_norm": 0.11848757713223414,
"learning_rate": 1.2938872178193395e-06,
"loss": 0.557,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 553,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 579500543967232.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}