fengyao1909's picture
Upload folder using huggingface_hub
bef8a57 verified
raw
history blame
87.7 kB
{
"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": 2.8401210755443786,
"learning_rate": 0.0,
"loss": 0.8251,
"step": 1
},
{
"epoch": 0.0036133694670280035,
"grad_norm": 2.884596771811998,
"learning_rate": 1.7857142857142857e-06,
"loss": 0.8284,
"step": 2
},
{
"epoch": 0.005420054200542005,
"grad_norm": 2.885426730353446,
"learning_rate": 3.5714285714285714e-06,
"loss": 0.8426,
"step": 3
},
{
"epoch": 0.007226738934056007,
"grad_norm": 2.651910724864975,
"learning_rate": 5.357142857142857e-06,
"loss": 0.8329,
"step": 4
},
{
"epoch": 0.009033423667570008,
"grad_norm": 2.138099539200911,
"learning_rate": 7.142857142857143e-06,
"loss": 0.8087,
"step": 5
},
{
"epoch": 0.01084010840108401,
"grad_norm": 1.5516804515831568,
"learning_rate": 8.92857142857143e-06,
"loss": 0.7878,
"step": 6
},
{
"epoch": 0.012646793134598013,
"grad_norm": 1.3537216088647457,
"learning_rate": 1.0714285714285714e-05,
"loss": 0.76,
"step": 7
},
{
"epoch": 0.014453477868112014,
"grad_norm": 2.2798033166818095,
"learning_rate": 1.25e-05,
"loss": 0.7502,
"step": 8
},
{
"epoch": 0.016260162601626018,
"grad_norm": 2.4280919600136315,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.7449,
"step": 9
},
{
"epoch": 0.018066847335140017,
"grad_norm": 1.931081683969551,
"learning_rate": 1.6071428571428572e-05,
"loss": 0.7271,
"step": 10
},
{
"epoch": 0.01987353206865402,
"grad_norm": 2.033957326273334,
"learning_rate": 1.785714285714286e-05,
"loss": 0.7224,
"step": 11
},
{
"epoch": 0.02168021680216802,
"grad_norm": 1.7440303482576578,
"learning_rate": 1.9642857142857145e-05,
"loss": 0.7373,
"step": 12
},
{
"epoch": 0.023486901535682024,
"grad_norm": 1.1423427090231095,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.7033,
"step": 13
},
{
"epoch": 0.025293586269196026,
"grad_norm": 0.9350758811837806,
"learning_rate": 2.3214285714285715e-05,
"loss": 0.6886,
"step": 14
},
{
"epoch": 0.02710027100271003,
"grad_norm": 0.9041529205527444,
"learning_rate": 2.5e-05,
"loss": 0.6858,
"step": 15
},
{
"epoch": 0.028906955736224028,
"grad_norm": 0.7774159470583337,
"learning_rate": 2.6785714285714288e-05,
"loss": 0.676,
"step": 16
},
{
"epoch": 0.03071364046973803,
"grad_norm": 0.6642849851627606,
"learning_rate": 2.857142857142857e-05,
"loss": 0.6816,
"step": 17
},
{
"epoch": 0.032520325203252036,
"grad_norm": 0.6696862181877565,
"learning_rate": 3.0357142857142857e-05,
"loss": 0.6727,
"step": 18
},
{
"epoch": 0.03432700993676603,
"grad_norm": 0.6199596133483118,
"learning_rate": 3.2142857142857144e-05,
"loss": 0.6678,
"step": 19
},
{
"epoch": 0.036133694670280034,
"grad_norm": 0.5724104094717255,
"learning_rate": 3.392857142857143e-05,
"loss": 0.6448,
"step": 20
},
{
"epoch": 0.037940379403794036,
"grad_norm": 0.5762214978597714,
"learning_rate": 3.571428571428572e-05,
"loss": 0.6506,
"step": 21
},
{
"epoch": 0.03974706413730804,
"grad_norm": 0.5444644294356963,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.6413,
"step": 22
},
{
"epoch": 0.04155374887082204,
"grad_norm": 0.4801008888914334,
"learning_rate": 3.928571428571429e-05,
"loss": 0.6425,
"step": 23
},
{
"epoch": 0.04336043360433604,
"grad_norm": 0.4780671650041637,
"learning_rate": 4.107142857142857e-05,
"loss": 0.6489,
"step": 24
},
{
"epoch": 0.045167118337850046,
"grad_norm": 0.5145358853730851,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.6306,
"step": 25
},
{
"epoch": 0.04697380307136405,
"grad_norm": 0.4229563893889767,
"learning_rate": 4.464285714285715e-05,
"loss": 0.6453,
"step": 26
},
{
"epoch": 0.04878048780487805,
"grad_norm": 0.4021332182222708,
"learning_rate": 4.642857142857143e-05,
"loss": 0.6251,
"step": 27
},
{
"epoch": 0.05058717253839205,
"grad_norm": 0.48615223659558016,
"learning_rate": 4.8214285714285716e-05,
"loss": 0.6272,
"step": 28
},
{
"epoch": 0.052393857271906055,
"grad_norm": 0.46304419453924084,
"learning_rate": 5e-05,
"loss": 0.6385,
"step": 29
},
{
"epoch": 0.05420054200542006,
"grad_norm": 0.4055914485047887,
"learning_rate": 4.999955240022902e-05,
"loss": 0.6406,
"step": 30
},
{
"epoch": 0.05600722673893405,
"grad_norm": 0.4320919468210144,
"learning_rate": 4.999820961694372e-05,
"loss": 0.6303,
"step": 31
},
{
"epoch": 0.057813911472448055,
"grad_norm": 0.4042983593828653,
"learning_rate": 4.999597169822646e-05,
"loss": 0.6186,
"step": 32
},
{
"epoch": 0.05962059620596206,
"grad_norm": 0.4310835292518631,
"learning_rate": 4.9992838724212585e-05,
"loss": 0.6287,
"step": 33
},
{
"epoch": 0.06142728093947606,
"grad_norm": 0.412271814827728,
"learning_rate": 4.9988810807087584e-05,
"loss": 0.6165,
"step": 34
},
{
"epoch": 0.06323396567299007,
"grad_norm": 0.40598837987994935,
"learning_rate": 4.998388809108303e-05,
"loss": 0.622,
"step": 35
},
{
"epoch": 0.06504065040650407,
"grad_norm": 0.4223908220324365,
"learning_rate": 4.997807075247146e-05,
"loss": 0.6189,
"step": 36
},
{
"epoch": 0.06684733514001806,
"grad_norm": 0.38197899028265064,
"learning_rate": 4.997135899956001e-05,
"loss": 0.623,
"step": 37
},
{
"epoch": 0.06865401987353206,
"grad_norm": 0.3885330150920031,
"learning_rate": 4.9963753072683025e-05,
"loss": 0.6164,
"step": 38
},
{
"epoch": 0.07046070460704607,
"grad_norm": 0.41115019726029983,
"learning_rate": 4.9955253244193375e-05,
"loss": 0.6182,
"step": 39
},
{
"epoch": 0.07226738934056007,
"grad_norm": 0.3495037257115665,
"learning_rate": 4.994585981845278e-05,
"loss": 0.6072,
"step": 40
},
{
"epoch": 0.07407407407407407,
"grad_norm": 0.3973831198418077,
"learning_rate": 4.9935573131820854e-05,
"loss": 0.6137,
"step": 41
},
{
"epoch": 0.07588075880758807,
"grad_norm": 0.3339390206679997,
"learning_rate": 4.9924393552643075e-05,
"loss": 0.6064,
"step": 42
},
{
"epoch": 0.07768744354110207,
"grad_norm": 0.3384678373992373,
"learning_rate": 4.991232148123761e-05,
"loss": 0.606,
"step": 43
},
{
"epoch": 0.07949412827461608,
"grad_norm": 0.3764492630812678,
"learning_rate": 4.989935734988098e-05,
"loss": 0.601,
"step": 44
},
{
"epoch": 0.08130081300813008,
"grad_norm": 0.35707353533847597,
"learning_rate": 4.988550162279255e-05,
"loss": 0.6097,
"step": 45
},
{
"epoch": 0.08310749774164408,
"grad_norm": 0.34040533355863656,
"learning_rate": 4.987075479611796e-05,
"loss": 0.6094,
"step": 46
},
{
"epoch": 0.08491418247515808,
"grad_norm": 0.34496537693497575,
"learning_rate": 4.985511739791129e-05,
"loss": 0.6129,
"step": 47
},
{
"epoch": 0.08672086720867209,
"grad_norm": 0.3655410266089117,
"learning_rate": 4.983858998811622e-05,
"loss": 0.5994,
"step": 48
},
{
"epoch": 0.08852755194218609,
"grad_norm": 0.32151319632227454,
"learning_rate": 4.9821173158545936e-05,
"loss": 0.607,
"step": 49
},
{
"epoch": 0.09033423667570009,
"grad_norm": 0.3573869377855791,
"learning_rate": 4.980286753286195e-05,
"loss": 0.6067,
"step": 50
},
{
"epoch": 0.0921409214092141,
"grad_norm": 0.3601371463623409,
"learning_rate": 4.978367376655177e-05,
"loss": 0.5965,
"step": 51
},
{
"epoch": 0.0939476061427281,
"grad_norm": 0.3288839599265164,
"learning_rate": 4.976359254690543e-05,
"loss": 0.6128,
"step": 52
},
{
"epoch": 0.0957542908762421,
"grad_norm": 0.3899144366212297,
"learning_rate": 4.974262459299087e-05,
"loss": 0.5992,
"step": 53
},
{
"epoch": 0.0975609756097561,
"grad_norm": 0.31373036051997816,
"learning_rate": 4.972077065562821e-05,
"loss": 0.5894,
"step": 54
},
{
"epoch": 0.0993676603432701,
"grad_norm": 0.3317064945312652,
"learning_rate": 4.969803151736284e-05,
"loss": 0.6046,
"step": 55
},
{
"epoch": 0.1011743450767841,
"grad_norm": 0.4008096818415782,
"learning_rate": 4.9674407992437394e-05,
"loss": 0.6091,
"step": 56
},
{
"epoch": 0.10298102981029811,
"grad_norm": 0.32205121061079506,
"learning_rate": 4.964990092676263e-05,
"loss": 0.5936,
"step": 57
},
{
"epoch": 0.10478771454381211,
"grad_norm": 0.3834592472356572,
"learning_rate": 4.962451119788709e-05,
"loss": 0.6035,
"step": 58
},
{
"epoch": 0.10659439927732611,
"grad_norm": 0.4364607834229955,
"learning_rate": 4.959823971496574e-05,
"loss": 0.5895,
"step": 59
},
{
"epoch": 0.10840108401084012,
"grad_norm": 0.39798614932188364,
"learning_rate": 4.957108741872736e-05,
"loss": 0.5903,
"step": 60
},
{
"epoch": 0.1102077687443541,
"grad_norm": 0.4078983073259993,
"learning_rate": 4.954305528144085e-05,
"loss": 0.594,
"step": 61
},
{
"epoch": 0.1120144534778681,
"grad_norm": 0.5064139886264023,
"learning_rate": 4.9514144306880506e-05,
"loss": 0.5989,
"step": 62
},
{
"epoch": 0.11382113821138211,
"grad_norm": 0.3049367414530056,
"learning_rate": 4.9484355530289944e-05,
"loss": 0.5982,
"step": 63
},
{
"epoch": 0.11562782294489611,
"grad_norm": 0.45932591541254997,
"learning_rate": 4.9453690018345144e-05,
"loss": 0.598,
"step": 64
},
{
"epoch": 0.11743450767841011,
"grad_norm": 0.34088884376991047,
"learning_rate": 4.9422148869116194e-05,
"loss": 0.5914,
"step": 65
},
{
"epoch": 0.11924119241192412,
"grad_norm": 0.4408196994719187,
"learning_rate": 4.938973321202799e-05,
"loss": 0.5943,
"step": 66
},
{
"epoch": 0.12104787714543812,
"grad_norm": 0.4034840944061305,
"learning_rate": 4.935644420781978e-05,
"loss": 0.5852,
"step": 67
},
{
"epoch": 0.12285456187895212,
"grad_norm": 0.3532258693927161,
"learning_rate": 4.932228304850363e-05,
"loss": 0.6003,
"step": 68
},
{
"epoch": 0.12466124661246612,
"grad_norm": 0.4041417285254443,
"learning_rate": 4.928725095732169e-05,
"loss": 0.6019,
"step": 69
},
{
"epoch": 0.12646793134598014,
"grad_norm": 0.338119605860217,
"learning_rate": 4.925134918870245e-05,
"loss": 0.6056,
"step": 70
},
{
"epoch": 0.12827461607949414,
"grad_norm": 0.2924641177682486,
"learning_rate": 4.9214579028215776e-05,
"loss": 0.5784,
"step": 71
},
{
"epoch": 0.13008130081300814,
"grad_norm": 0.37576892630911196,
"learning_rate": 4.917694179252692e-05,
"loss": 0.5966,
"step": 72
},
{
"epoch": 0.13188798554652212,
"grad_norm": 0.3066908816324021,
"learning_rate": 4.91384388293493e-05,
"loss": 0.5944,
"step": 73
},
{
"epoch": 0.13369467028003612,
"grad_norm": 0.3296017371410444,
"learning_rate": 4.909907151739633e-05,
"loss": 0.5863,
"step": 74
},
{
"epoch": 0.13550135501355012,
"grad_norm": 0.3510646842800697,
"learning_rate": 4.9058841266332e-05,
"loss": 0.5854,
"step": 75
},
{
"epoch": 0.13730803974706413,
"grad_norm": 0.33050013383675975,
"learning_rate": 4.90177495167204e-05,
"loss": 0.5816,
"step": 76
},
{
"epoch": 0.13911472448057813,
"grad_norm": 0.336545072709173,
"learning_rate": 4.897579773997415e-05,
"loss": 0.5768,
"step": 77
},
{
"epoch": 0.14092140921409213,
"grad_norm": 0.3401542906091868,
"learning_rate": 4.893298743830168e-05,
"loss": 0.5877,
"step": 78
},
{
"epoch": 0.14272809394760613,
"grad_norm": 0.30833272476392615,
"learning_rate": 4.888932014465352e-05,
"loss": 0.5949,
"step": 79
},
{
"epoch": 0.14453477868112014,
"grad_norm": 0.40829913126640544,
"learning_rate": 4.88447974226673e-05,
"loss": 0.6045,
"step": 80
},
{
"epoch": 0.14634146341463414,
"grad_norm": 0.3247095550760803,
"learning_rate": 4.879942086661184e-05,
"loss": 0.5901,
"step": 81
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.40484730371305205,
"learning_rate": 4.875319210133004e-05,
"loss": 0.5825,
"step": 82
},
{
"epoch": 0.14995483288166214,
"grad_norm": 0.37019522474324174,
"learning_rate": 4.870611278218066e-05,
"loss": 0.5918,
"step": 83
},
{
"epoch": 0.15176151761517614,
"grad_norm": 0.3654744041300334,
"learning_rate": 4.865818459497911e-05,
"loss": 0.5865,
"step": 84
},
{
"epoch": 0.15356820234869015,
"grad_norm": 0.3001653084612634,
"learning_rate": 4.860940925593703e-05,
"loss": 0.5889,
"step": 85
},
{
"epoch": 0.15537488708220415,
"grad_norm": 0.3463142769052332,
"learning_rate": 4.8559788511600876e-05,
"loss": 0.5881,
"step": 86
},
{
"epoch": 0.15718157181571815,
"grad_norm": 0.3221292284344934,
"learning_rate": 4.850932413878934e-05,
"loss": 0.5901,
"step": 87
},
{
"epoch": 0.15898825654923215,
"grad_norm": 0.33253415770699135,
"learning_rate": 4.8458017944529776e-05,
"loss": 0.5952,
"step": 88
},
{
"epoch": 0.16079494128274616,
"grad_norm": 0.37021022779245716,
"learning_rate": 4.8405871765993433e-05,
"loss": 0.5928,
"step": 89
},
{
"epoch": 0.16260162601626016,
"grad_norm": 0.3197338147243217,
"learning_rate": 4.8352887470429726e-05,
"loss": 0.5837,
"step": 90
},
{
"epoch": 0.16440831074977416,
"grad_norm": 0.35706780201968874,
"learning_rate": 4.8299066955099335e-05,
"loss": 0.5811,
"step": 91
},
{
"epoch": 0.16621499548328816,
"grad_norm": 0.3730971582648582,
"learning_rate": 4.8244412147206284e-05,
"loss": 0.586,
"step": 92
},
{
"epoch": 0.16802168021680217,
"grad_norm": 0.33467520904104064,
"learning_rate": 4.8188925003828945e-05,
"loss": 0.5919,
"step": 93
},
{
"epoch": 0.16982836495031617,
"grad_norm": 0.41181901183464464,
"learning_rate": 4.813260751184992e-05,
"loss": 0.5922,
"step": 94
},
{
"epoch": 0.17163504968383017,
"grad_norm": 0.31057237794043846,
"learning_rate": 4.807546168788494e-05,
"loss": 0.5835,
"step": 95
},
{
"epoch": 0.17344173441734417,
"grad_norm": 0.4045185112342142,
"learning_rate": 4.8017489578210604e-05,
"loss": 0.5839,
"step": 96
},
{
"epoch": 0.17524841915085818,
"grad_norm": 0.342091450071029,
"learning_rate": 4.7958693258691167e-05,
"loss": 0.5891,
"step": 97
},
{
"epoch": 0.17705510388437218,
"grad_norm": 0.32193383766669476,
"learning_rate": 4.7899074834704165e-05,
"loss": 0.5814,
"step": 98
},
{
"epoch": 0.17886178861788618,
"grad_norm": 0.33881983844597735,
"learning_rate": 4.783863644106502e-05,
"loss": 0.5951,
"step": 99
},
{
"epoch": 0.18066847335140018,
"grad_norm": 0.3141049036238513,
"learning_rate": 4.7777380241950645e-05,
"loss": 0.5672,
"step": 100
},
{
"epoch": 0.18247515808491419,
"grad_norm": 0.30258609960076854,
"learning_rate": 4.7715308430821864e-05,
"loss": 0.5831,
"step": 101
},
{
"epoch": 0.1842818428184282,
"grad_norm": 0.33013650150122287,
"learning_rate": 4.765242323034498e-05,
"loss": 0.6019,
"step": 102
},
{
"epoch": 0.1860885275519422,
"grad_norm": 0.31075076006352215,
"learning_rate": 4.758872689231208e-05,
"loss": 0.581,
"step": 103
},
{
"epoch": 0.1878952122854562,
"grad_norm": 0.3376659425636789,
"learning_rate": 4.752422169756048e-05,
"loss": 0.5775,
"step": 104
},
{
"epoch": 0.1897018970189702,
"grad_norm": 0.3373397970824128,
"learning_rate": 4.745890995589101e-05,
"loss": 0.5705,
"step": 105
},
{
"epoch": 0.1915085817524842,
"grad_norm": 0.3159036744458245,
"learning_rate": 4.7392794005985326e-05,
"loss": 0.574,
"step": 106
},
{
"epoch": 0.1933152664859982,
"grad_norm": 0.3157369760717556,
"learning_rate": 4.732587621532214e-05,
"loss": 0.58,
"step": 107
},
{
"epoch": 0.1951219512195122,
"grad_norm": 0.3151534184596026,
"learning_rate": 4.725815898009247e-05,
"loss": 0.5785,
"step": 108
},
{
"epoch": 0.1969286359530262,
"grad_norm": 0.3067792635656275,
"learning_rate": 4.718964472511386e-05,
"loss": 0.5864,
"step": 109
},
{
"epoch": 0.1987353206865402,
"grad_norm": 0.34885189836356073,
"learning_rate": 4.712033590374346e-05,
"loss": 0.5685,
"step": 110
},
{
"epoch": 0.2005420054200542,
"grad_norm": 0.2725346961548414,
"learning_rate": 4.705023499779031e-05,
"loss": 0.5876,
"step": 111
},
{
"epoch": 0.2023486901535682,
"grad_norm": 0.34146491162388654,
"learning_rate": 4.6979344517426345e-05,
"loss": 0.5814,
"step": 112
},
{
"epoch": 0.2041553748870822,
"grad_norm": 0.2979010304617956,
"learning_rate": 4.690766700109659e-05,
"loss": 0.5857,
"step": 113
},
{
"epoch": 0.20596205962059622,
"grad_norm": 0.3317475544222318,
"learning_rate": 4.6835205015428246e-05,
"loss": 0.5685,
"step": 114
},
{
"epoch": 0.20776874435411022,
"grad_norm": 0.3490432374306535,
"learning_rate": 4.676196115513876e-05,
"loss": 0.585,
"step": 115
},
{
"epoch": 0.20957542908762422,
"grad_norm": 0.2845519792036694,
"learning_rate": 4.668793804294294e-05,
"loss": 0.5779,
"step": 116
},
{
"epoch": 0.21138211382113822,
"grad_norm": 0.30626266068728963,
"learning_rate": 4.661313832945904e-05,
"loss": 0.5901,
"step": 117
},
{
"epoch": 0.21318879855465223,
"grad_norm": 0.3411792829442568,
"learning_rate": 4.653756469311381e-05,
"loss": 0.5766,
"step": 118
},
{
"epoch": 0.21499548328816623,
"grad_norm": 0.273095998341187,
"learning_rate": 4.6461219840046654e-05,
"loss": 0.5666,
"step": 119
},
{
"epoch": 0.21680216802168023,
"grad_norm": 0.3070242568215688,
"learning_rate": 4.638410650401267e-05,
"loss": 0.5861,
"step": 120
},
{
"epoch": 0.2186088527551942,
"grad_norm": 0.315496788680795,
"learning_rate": 4.6306227446284775e-05,
"loss": 0.5817,
"step": 121
},
{
"epoch": 0.2204155374887082,
"grad_norm": 0.285486208489652,
"learning_rate": 4.622758545555485e-05,
"loss": 0.5862,
"step": 122
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.3014286983026253,
"learning_rate": 4.614818334783384e-05,
"loss": 0.5756,
"step": 123
},
{
"epoch": 0.2240289069557362,
"grad_norm": 0.3286311142757772,
"learning_rate": 4.606802396635098e-05,
"loss": 0.5622,
"step": 124
},
{
"epoch": 0.22583559168925021,
"grad_norm": 0.3099894773692972,
"learning_rate": 4.598711018145193e-05,
"loss": 0.5702,
"step": 125
},
{
"epoch": 0.22764227642276422,
"grad_norm": 0.3402171436347276,
"learning_rate": 4.590544489049602e-05,
"loss": 0.5822,
"step": 126
},
{
"epoch": 0.22944896115627822,
"grad_norm": 0.2949342532195096,
"learning_rate": 4.5823031017752485e-05,
"loss": 0.5753,
"step": 127
},
{
"epoch": 0.23125564588979222,
"grad_norm": 0.33271367144515557,
"learning_rate": 4.5739871514295786e-05,
"loss": 0.5746,
"step": 128
},
{
"epoch": 0.23306233062330622,
"grad_norm": 0.2854287194746108,
"learning_rate": 4.5655969357899874e-05,
"loss": 0.5688,
"step": 129
},
{
"epoch": 0.23486901535682023,
"grad_norm": 0.2911634608087971,
"learning_rate": 4.5571327552931645e-05,
"loss": 0.5875,
"step": 130
},
{
"epoch": 0.23667570009033423,
"grad_norm": 0.3282856212432573,
"learning_rate": 4.54859491302433e-05,
"loss": 0.5828,
"step": 131
},
{
"epoch": 0.23848238482384823,
"grad_norm": 0.31230217501155305,
"learning_rate": 4.5399837147063825e-05,
"loss": 0.5622,
"step": 132
},
{
"epoch": 0.24028906955736223,
"grad_norm": 0.26497408669368616,
"learning_rate": 4.531299468688955e-05,
"loss": 0.576,
"step": 133
},
{
"epoch": 0.24209575429087624,
"grad_norm": 0.31735124152798094,
"learning_rate": 4.522542485937369e-05,
"loss": 0.5772,
"step": 134
},
{
"epoch": 0.24390243902439024,
"grad_norm": 0.3015639590739915,
"learning_rate": 4.5137130800215025e-05,
"loss": 0.5748,
"step": 135
},
{
"epoch": 0.24570912375790424,
"grad_norm": 0.27756271594362325,
"learning_rate": 4.50481156710456e-05,
"loss": 0.5782,
"step": 136
},
{
"epoch": 0.24751580849141824,
"grad_norm": 0.3311373615406198,
"learning_rate": 4.495838265931754e-05,
"loss": 0.5632,
"step": 137
},
{
"epoch": 0.24932249322493225,
"grad_norm": 0.26966897365996273,
"learning_rate": 4.486793497818889e-05,
"loss": 0.5778,
"step": 138
},
{
"epoch": 0.25112917795844625,
"grad_norm": 0.3458179405656153,
"learning_rate": 4.477677586640854e-05,
"loss": 0.5814,
"step": 139
},
{
"epoch": 0.2529358626919603,
"grad_norm": 0.2722125808652539,
"learning_rate": 4.4684908588200304e-05,
"loss": 0.5804,
"step": 140
},
{
"epoch": 0.25474254742547425,
"grad_norm": 0.29853453900528515,
"learning_rate": 4.4592336433146e-05,
"loss": 0.5622,
"step": 141
},
{
"epoch": 0.2565492321589883,
"grad_norm": 0.2616025861086357,
"learning_rate": 4.449906271606766e-05,
"loss": 0.5816,
"step": 142
},
{
"epoch": 0.25835591689250226,
"grad_norm": 0.28875897468487793,
"learning_rate": 4.440509077690883e-05,
"loss": 0.5751,
"step": 143
},
{
"epoch": 0.2601626016260163,
"grad_norm": 0.31089280557100357,
"learning_rate": 4.431042398061499e-05,
"loss": 0.5614,
"step": 144
},
{
"epoch": 0.26196928635953026,
"grad_norm": 0.24453740569318233,
"learning_rate": 4.421506571701305e-05,
"loss": 0.5739,
"step": 145
},
{
"epoch": 0.26377597109304424,
"grad_norm": 0.3298892559409927,
"learning_rate": 4.4119019400689967e-05,
"loss": 0.5789,
"step": 146
},
{
"epoch": 0.26558265582655827,
"grad_norm": 0.29175370949614915,
"learning_rate": 4.402228847087047e-05,
"loss": 0.5687,
"step": 147
},
{
"epoch": 0.26738934056007224,
"grad_norm": 0.30364879113096566,
"learning_rate": 4.3924876391293915e-05,
"loss": 0.57,
"step": 148
},
{
"epoch": 0.26919602529358627,
"grad_norm": 0.2924856865957413,
"learning_rate": 4.382678665009028e-05,
"loss": 0.5675,
"step": 149
},
{
"epoch": 0.27100271002710025,
"grad_norm": 0.2831086406138475,
"learning_rate": 4.372802275965521e-05,
"loss": 0.5777,
"step": 150
},
{
"epoch": 0.2728093947606143,
"grad_norm": 0.3017093604784243,
"learning_rate": 4.3628588256524285e-05,
"loss": 0.5589,
"step": 151
},
{
"epoch": 0.27461607949412825,
"grad_norm": 0.2765860953865558,
"learning_rate": 4.3528486701246376e-05,
"loss": 0.5669,
"step": 152
},
{
"epoch": 0.2764227642276423,
"grad_norm": 0.2904031273845622,
"learning_rate": 4.3427721678256125e-05,
"loss": 0.5671,
"step": 153
},
{
"epoch": 0.27822944896115626,
"grad_norm": 0.2540349949087337,
"learning_rate": 4.332629679574566e-05,
"loss": 0.5702,
"step": 154
},
{
"epoch": 0.2800361336946703,
"grad_norm": 0.3069633678570879,
"learning_rate": 4.3224215685535294e-05,
"loss": 0.5637,
"step": 155
},
{
"epoch": 0.28184281842818426,
"grad_norm": 0.2542441755605158,
"learning_rate": 4.312148200294355e-05,
"loss": 0.5627,
"step": 156
},
{
"epoch": 0.2836495031616983,
"grad_norm": 0.3018408188777611,
"learning_rate": 4.301809942665625e-05,
"loss": 0.5757,
"step": 157
},
{
"epoch": 0.28545618789521227,
"grad_norm": 0.28743959410933695,
"learning_rate": 4.2914071658594805e-05,
"loss": 0.5734,
"step": 158
},
{
"epoch": 0.2872628726287263,
"grad_norm": 0.2787808725595535,
"learning_rate": 4.2809402423783624e-05,
"loss": 0.5542,
"step": 159
},
{
"epoch": 0.28906955736224027,
"grad_norm": 0.29206183996226404,
"learning_rate": 4.2704095470216744e-05,
"loss": 0.5635,
"step": 160
},
{
"epoch": 0.2908762420957543,
"grad_norm": 0.28832091136901655,
"learning_rate": 4.2598154568723626e-05,
"loss": 0.5716,
"step": 161
},
{
"epoch": 0.2926829268292683,
"grad_norm": 0.26053870722630096,
"learning_rate": 4.249158351283414e-05,
"loss": 0.5568,
"step": 162
},
{
"epoch": 0.2944896115627823,
"grad_norm": 0.30602256840625275,
"learning_rate": 4.2384386118642694e-05,
"loss": 0.5661,
"step": 163
},
{
"epoch": 0.2962962962962963,
"grad_norm": 0.24580296790912456,
"learning_rate": 4.227656622467162e-05,
"loss": 0.5751,
"step": 164
},
{
"epoch": 0.2981029810298103,
"grad_norm": 0.29059059202913196,
"learning_rate": 4.2168127691733706e-05,
"loss": 0.5662,
"step": 165
},
{
"epoch": 0.2999096657633243,
"grad_norm": 0.29414515714153977,
"learning_rate": 4.205907440279395e-05,
"loss": 0.5724,
"step": 166
},
{
"epoch": 0.3017163504968383,
"grad_norm": 0.29414614437874254,
"learning_rate": 4.1949410262830525e-05,
"loss": 0.5717,
"step": 167
},
{
"epoch": 0.3035230352303523,
"grad_norm": 0.2971349224474148,
"learning_rate": 4.1839139198694946e-05,
"loss": 0.5697,
"step": 168
},
{
"epoch": 0.3053297199638663,
"grad_norm": 0.2793813743979144,
"learning_rate": 4.172826515897146e-05,
"loss": 0.5617,
"step": 169
},
{
"epoch": 0.3071364046973803,
"grad_norm": 0.3023179135068114,
"learning_rate": 4.161679211383565e-05,
"loss": 0.5751,
"step": 170
},
{
"epoch": 0.3089430894308943,
"grad_norm": 0.2477222878497878,
"learning_rate": 4.150472405491226e-05,
"loss": 0.5583,
"step": 171
},
{
"epoch": 0.3107497741644083,
"grad_norm": 0.2707854956368433,
"learning_rate": 4.139206499513231e-05,
"loss": 0.5658,
"step": 172
},
{
"epoch": 0.31255645889792233,
"grad_norm": 0.26805394435378294,
"learning_rate": 4.127881896858934e-05,
"loss": 0.5687,
"step": 173
},
{
"epoch": 0.3143631436314363,
"grad_norm": 0.24818328664431513,
"learning_rate": 4.116499003039499e-05,
"loss": 0.5597,
"step": 174
},
{
"epoch": 0.31616982836495033,
"grad_norm": 0.3076486841492656,
"learning_rate": 4.105058225653381e-05,
"loss": 0.5638,
"step": 175
},
{
"epoch": 0.3179765130984643,
"grad_norm": 0.24484381551700804,
"learning_rate": 4.093559974371725e-05,
"loss": 0.578,
"step": 176
},
{
"epoch": 0.31978319783197834,
"grad_norm": 0.25779831771912026,
"learning_rate": 4.082004660923703e-05,
"loss": 0.5536,
"step": 177
},
{
"epoch": 0.3215898825654923,
"grad_norm": 0.2431924544197558,
"learning_rate": 4.070392699081767e-05,
"loss": 0.5606,
"step": 178
},
{
"epoch": 0.32339656729900634,
"grad_norm": 0.24360453043613553,
"learning_rate": 4.058724504646834e-05,
"loss": 0.571,
"step": 179
},
{
"epoch": 0.3252032520325203,
"grad_norm": 0.28406098303419186,
"learning_rate": 4.047000495433397e-05,
"loss": 0.5781,
"step": 180
},
{
"epoch": 0.32700993676603435,
"grad_norm": 0.22058075555118684,
"learning_rate": 4.035221091254563e-05,
"loss": 0.5574,
"step": 181
},
{
"epoch": 0.3288166214995483,
"grad_norm": 0.3009339432220675,
"learning_rate": 4.023386713907021e-05,
"loss": 0.5677,
"step": 182
},
{
"epoch": 0.33062330623306235,
"grad_norm": 0.26774508776974565,
"learning_rate": 4.011497787155938e-05,
"loss": 0.577,
"step": 183
},
{
"epoch": 0.3324299909665763,
"grad_norm": 0.284303170530224,
"learning_rate": 3.9995547367197845e-05,
"loss": 0.5735,
"step": 184
},
{
"epoch": 0.33423667570009036,
"grad_norm": 0.2614285883935899,
"learning_rate": 3.987557990255093e-05,
"loss": 0.5695,
"step": 185
},
{
"epoch": 0.33604336043360433,
"grad_norm": 0.28256380914027235,
"learning_rate": 3.975507977341141e-05,
"loss": 0.5648,
"step": 186
},
{
"epoch": 0.33785004516711836,
"grad_norm": 0.28945389202706384,
"learning_rate": 3.963405129464569e-05,
"loss": 0.5618,
"step": 187
},
{
"epoch": 0.33965672990063234,
"grad_norm": 0.2654043705467122,
"learning_rate": 3.9512498800039335e-05,
"loss": 0.5622,
"step": 188
},
{
"epoch": 0.34146341463414637,
"grad_norm": 0.28212350075401693,
"learning_rate": 3.939042664214184e-05,
"loss": 0.5691,
"step": 189
},
{
"epoch": 0.34327009936766034,
"grad_norm": 0.2666801982334387,
"learning_rate": 3.92678391921108e-05,
"loss": 0.5582,
"step": 190
},
{
"epoch": 0.34507678410117437,
"grad_norm": 0.2658380267209616,
"learning_rate": 3.914474083955537e-05,
"loss": 0.5561,
"step": 191
},
{
"epoch": 0.34688346883468835,
"grad_norm": 0.2767810249999182,
"learning_rate": 3.902113599237911e-05,
"loss": 0.5637,
"step": 192
},
{
"epoch": 0.3486901535682023,
"grad_norm": 0.2686248952050933,
"learning_rate": 3.8897029076622116e-05,
"loss": 0.5648,
"step": 193
},
{
"epoch": 0.35049683830171635,
"grad_norm": 0.2671044597386809,
"learning_rate": 3.8772424536302564e-05,
"loss": 0.5668,
"step": 194
},
{
"epoch": 0.3523035230352303,
"grad_norm": 0.28240978604941985,
"learning_rate": 3.8647326833257545e-05,
"loss": 0.5503,
"step": 195
},
{
"epoch": 0.35411020776874436,
"grad_norm": 0.2545745653651051,
"learning_rate": 3.852174044698333e-05,
"loss": 0.564,
"step": 196
},
{
"epoch": 0.35591689250225833,
"grad_norm": 0.2788914079559153,
"learning_rate": 3.8395669874474915e-05,
"loss": 0.563,
"step": 197
},
{
"epoch": 0.35772357723577236,
"grad_norm": 0.27664913837367605,
"learning_rate": 3.826911963006507e-05,
"loss": 0.5397,
"step": 198
},
{
"epoch": 0.35953026196928634,
"grad_norm": 0.2854592929422416,
"learning_rate": 3.814209424526262e-05,
"loss": 0.5646,
"step": 199
},
{
"epoch": 0.36133694670280037,
"grad_norm": 0.31461524287063203,
"learning_rate": 3.801459826859022e-05,
"loss": 0.5521,
"step": 200
},
{
"epoch": 0.36314363143631434,
"grad_norm": 0.2571618033810251,
"learning_rate": 3.788663626542146e-05,
"loss": 0.547,
"step": 201
},
{
"epoch": 0.36495031616982837,
"grad_norm": 0.2698316727635178,
"learning_rate": 3.7758212817817405e-05,
"loss": 0.5735,
"step": 202
},
{
"epoch": 0.36675700090334235,
"grad_norm": 0.28386625197611576,
"learning_rate": 3.762933252436253e-05,
"loss": 0.5607,
"step": 203
},
{
"epoch": 0.3685636856368564,
"grad_norm": 0.23910352580001357,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.5729,
"step": 204
},
{
"epoch": 0.37037037037037035,
"grad_norm": 0.25373354611118293,
"learning_rate": 3.73702198758665e-05,
"loss": 0.5636,
"step": 205
},
{
"epoch": 0.3721770551038844,
"grad_norm": 0.26220155901200526,
"learning_rate": 3.7239996799126314e-05,
"loss": 0.5511,
"step": 206
},
{
"epoch": 0.37398373983739835,
"grad_norm": 0.2703230132182625,
"learning_rate": 3.7109335432805006e-05,
"loss": 0.559,
"step": 207
},
{
"epoch": 0.3757904245709124,
"grad_norm": 0.25300776840046674,
"learning_rate": 3.697824045562238e-05,
"loss": 0.5467,
"step": 208
},
{
"epoch": 0.37759710930442636,
"grad_norm": 0.31024727576581884,
"learning_rate": 3.6846716561824965e-05,
"loss": 0.5681,
"step": 209
},
{
"epoch": 0.3794037940379404,
"grad_norm": 0.2547242302465973,
"learning_rate": 3.6714768461017965e-05,
"loss": 0.5641,
"step": 210
},
{
"epoch": 0.38121047877145436,
"grad_norm": 0.2832537591345291,
"learning_rate": 3.6582400877996546e-05,
"loss": 0.5631,
"step": 211
},
{
"epoch": 0.3830171635049684,
"grad_norm": 0.23740735296590512,
"learning_rate": 3.6449618552576695e-05,
"loss": 0.5705,
"step": 212
},
{
"epoch": 0.38482384823848237,
"grad_norm": 0.25138099601672315,
"learning_rate": 3.6316426239425485e-05,
"loss": 0.5712,
"step": 213
},
{
"epoch": 0.3866305329719964,
"grad_norm": 0.2446936529822529,
"learning_rate": 3.6182828707890816e-05,
"loss": 0.5574,
"step": 214
},
{
"epoch": 0.3884372177055104,
"grad_norm": 0.28278554244015486,
"learning_rate": 3.604883074183068e-05,
"loss": 0.5848,
"step": 215
},
{
"epoch": 0.3902439024390244,
"grad_norm": 0.2868056773879424,
"learning_rate": 3.591443713944175e-05,
"loss": 0.5728,
"step": 216
},
{
"epoch": 0.3920505871725384,
"grad_norm": 0.23733474164783092,
"learning_rate": 3.577965271308771e-05,
"loss": 0.5734,
"step": 217
},
{
"epoch": 0.3938572719060524,
"grad_norm": 0.2418348363911958,
"learning_rate": 3.564448228912682e-05,
"loss": 0.5644,
"step": 218
},
{
"epoch": 0.3956639566395664,
"grad_norm": 0.24258866663076342,
"learning_rate": 3.550893070773914e-05,
"loss": 0.5597,
"step": 219
},
{
"epoch": 0.3974706413730804,
"grad_norm": 0.23248379507210618,
"learning_rate": 3.5373002822753216e-05,
"loss": 0.5619,
"step": 220
},
{
"epoch": 0.3992773261065944,
"grad_norm": 0.23221387790837575,
"learning_rate": 3.5236703501472266e-05,
"loss": 0.551,
"step": 221
},
{
"epoch": 0.4010840108401084,
"grad_norm": 0.27427489494087726,
"learning_rate": 3.510003762449988e-05,
"loss": 0.5685,
"step": 222
},
{
"epoch": 0.4028906955736224,
"grad_norm": 0.25685297943543806,
"learning_rate": 3.496301008556529e-05,
"loss": 0.5508,
"step": 223
},
{
"epoch": 0.4046973803071364,
"grad_norm": 0.23751224178133434,
"learning_rate": 3.4825625791348096e-05,
"loss": 0.5553,
"step": 224
},
{
"epoch": 0.4065040650406504,
"grad_norm": 0.2533622057517779,
"learning_rate": 3.4687889661302576e-05,
"loss": 0.5616,
"step": 225
},
{
"epoch": 0.4083107497741644,
"grad_norm": 0.25908397166669356,
"learning_rate": 3.454980662748156e-05,
"loss": 0.5659,
"step": 226
},
{
"epoch": 0.4101174345076784,
"grad_norm": 0.25053206427350594,
"learning_rate": 3.44113816343598e-05,
"loss": 0.5701,
"step": 227
},
{
"epoch": 0.41192411924119243,
"grad_norm": 0.2371124422311737,
"learning_rate": 3.427261963865691e-05,
"loss": 0.5567,
"step": 228
},
{
"epoch": 0.4137308039747064,
"grad_norm": 0.26537475430824775,
"learning_rate": 3.413352560915988e-05,
"loss": 0.5594,
"step": 229
},
{
"epoch": 0.41553748870822044,
"grad_norm": 0.24213575293916792,
"learning_rate": 3.399410452654518e-05,
"loss": 0.5612,
"step": 230
},
{
"epoch": 0.4173441734417344,
"grad_norm": 0.24275309716779916,
"learning_rate": 3.3854361383200374e-05,
"loss": 0.561,
"step": 231
},
{
"epoch": 0.41915085817524844,
"grad_norm": 0.23843095168601489,
"learning_rate": 3.3714301183045385e-05,
"loss": 0.5631,
"step": 232
},
{
"epoch": 0.4209575429087624,
"grad_norm": 0.21791224002383097,
"learning_rate": 3.357392894135329e-05,
"loss": 0.5457,
"step": 233
},
{
"epoch": 0.42276422764227645,
"grad_norm": 0.23785549929021552,
"learning_rate": 3.343324968457076e-05,
"loss": 0.5608,
"step": 234
},
{
"epoch": 0.4245709123757904,
"grad_norm": 0.22396755626120254,
"learning_rate": 3.329226845013802e-05,
"loss": 0.5558,
"step": 235
},
{
"epoch": 0.42637759710930445,
"grad_norm": 0.22217117995010718,
"learning_rate": 3.315099028630855e-05,
"loss": 0.5669,
"step": 236
},
{
"epoch": 0.4281842818428184,
"grad_norm": 0.2368068176727353,
"learning_rate": 3.3009420251968244e-05,
"loss": 0.5676,
"step": 237
},
{
"epoch": 0.42999096657633246,
"grad_norm": 0.2913166749962225,
"learning_rate": 3.28675634164543e-05,
"loss": 0.5757,
"step": 238
},
{
"epoch": 0.43179765130984643,
"grad_norm": 0.2326443530840128,
"learning_rate": 3.272542485937369e-05,
"loss": 0.5562,
"step": 239
},
{
"epoch": 0.43360433604336046,
"grad_norm": 0.21709853787458164,
"learning_rate": 3.258300967042125e-05,
"loss": 0.5566,
"step": 240
},
{
"epoch": 0.43541102077687444,
"grad_norm": 0.24943018423195573,
"learning_rate": 3.244032294919747e-05,
"loss": 0.5558,
"step": 241
},
{
"epoch": 0.4372177055103884,
"grad_norm": 0.2088255652107171,
"learning_rate": 3.229736980502584e-05,
"loss": 0.5561,
"step": 242
},
{
"epoch": 0.43902439024390244,
"grad_norm": 0.2753534476789369,
"learning_rate": 3.215415535676992e-05,
"loss": 0.561,
"step": 243
},
{
"epoch": 0.4408310749774164,
"grad_norm": 0.21949470480639668,
"learning_rate": 3.201068473265007e-05,
"loss": 0.5681,
"step": 244
},
{
"epoch": 0.44263775971093045,
"grad_norm": 0.26944393055258614,
"learning_rate": 3.186696307005976e-05,
"loss": 0.5591,
"step": 245
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.2191119214759813,
"learning_rate": 3.172299551538164e-05,
"loss": 0.566,
"step": 246
},
{
"epoch": 0.44625112917795845,
"grad_norm": 0.23598250909414767,
"learning_rate": 3.15787872238033e-05,
"loss": 0.5474,
"step": 247
},
{
"epoch": 0.4480578139114724,
"grad_norm": 0.2244716812824527,
"learning_rate": 3.143434335913256e-05,
"loss": 0.5665,
"step": 248
},
{
"epoch": 0.44986449864498645,
"grad_norm": 0.2605217389849008,
"learning_rate": 3.1289669093612714e-05,
"loss": 0.55,
"step": 249
},
{
"epoch": 0.45167118337850043,
"grad_norm": 0.23565788514397004,
"learning_rate": 3.1144769607737204e-05,
"loss": 0.5648,
"step": 250
},
{
"epoch": 0.45347786811201446,
"grad_norm": 0.2520253908292615,
"learning_rate": 3.099965009006415e-05,
"loss": 0.5515,
"step": 251
},
{
"epoch": 0.45528455284552843,
"grad_norm": 0.23382294482671243,
"learning_rate": 3.0854315737030596e-05,
"loss": 0.5343,
"step": 252
},
{
"epoch": 0.45709123757904246,
"grad_norm": 0.21156862362731088,
"learning_rate": 3.0708771752766394e-05,
"loss": 0.5566,
"step": 253
},
{
"epoch": 0.45889792231255644,
"grad_norm": 0.2858583262540506,
"learning_rate": 3.056302334890786e-05,
"loss": 0.5562,
"step": 254
},
{
"epoch": 0.46070460704607047,
"grad_norm": 0.21446015297714893,
"learning_rate": 3.0417075744411178e-05,
"loss": 0.5491,
"step": 255
},
{
"epoch": 0.46251129177958444,
"grad_norm": 0.27175171429400885,
"learning_rate": 3.0270934165365478e-05,
"loss": 0.549,
"step": 256
},
{
"epoch": 0.4643179765130985,
"grad_norm": 0.2332022756162156,
"learning_rate": 3.0124603844805767e-05,
"loss": 0.5615,
"step": 257
},
{
"epoch": 0.46612466124661245,
"grad_norm": 0.25726612906200885,
"learning_rate": 2.997809002252546e-05,
"loss": 0.5545,
"step": 258
},
{
"epoch": 0.4679313459801265,
"grad_norm": 0.26470532087807114,
"learning_rate": 2.9831397944888833e-05,
"loss": 0.5586,
"step": 259
},
{
"epoch": 0.46973803071364045,
"grad_norm": 0.244315447384743,
"learning_rate": 2.9684532864643122e-05,
"loss": 0.5719,
"step": 260
},
{
"epoch": 0.4715447154471545,
"grad_norm": 0.2579290960374767,
"learning_rate": 2.953750004073041e-05,
"loss": 0.5625,
"step": 261
},
{
"epoch": 0.47335140018066846,
"grad_norm": 0.2502355307959324,
"learning_rate": 2.9390304738099384e-05,
"loss": 0.5508,
"step": 262
},
{
"epoch": 0.4751580849141825,
"grad_norm": 0.22745648145569985,
"learning_rate": 2.9242952227516722e-05,
"loss": 0.5558,
"step": 263
},
{
"epoch": 0.47696476964769646,
"grad_norm": 0.2880551827736454,
"learning_rate": 2.9095447785378443e-05,
"loss": 0.5615,
"step": 264
},
{
"epoch": 0.4787714543812105,
"grad_norm": 0.21091165839321852,
"learning_rate": 2.89477966935209e-05,
"loss": 0.543,
"step": 265
},
{
"epoch": 0.48057813911472447,
"grad_norm": 0.3146456092706863,
"learning_rate": 2.8800004239031684e-05,
"loss": 0.5676,
"step": 266
},
{
"epoch": 0.4823848238482385,
"grad_norm": 0.2187643898145053,
"learning_rate": 2.8652075714060295e-05,
"loss": 0.552,
"step": 267
},
{
"epoch": 0.48419150858175247,
"grad_norm": 0.25789704379288414,
"learning_rate": 2.850401641562865e-05,
"loss": 0.5511,
"step": 268
},
{
"epoch": 0.4859981933152665,
"grad_norm": 0.23735131054824035,
"learning_rate": 2.8355831645441388e-05,
"loss": 0.5593,
"step": 269
},
{
"epoch": 0.4878048780487805,
"grad_norm": 0.22178545968987512,
"learning_rate": 2.8207526709696057e-05,
"loss": 0.54,
"step": 270
},
{
"epoch": 0.4896115627822945,
"grad_norm": 0.2444983259488006,
"learning_rate": 2.8059106918893068e-05,
"loss": 0.5618,
"step": 271
},
{
"epoch": 0.4914182475158085,
"grad_norm": 0.23074078288504987,
"learning_rate": 2.791057758764557e-05,
"loss": 0.5561,
"step": 272
},
{
"epoch": 0.4932249322493225,
"grad_norm": 0.2122648915326668,
"learning_rate": 2.7761944034489152e-05,
"loss": 0.564,
"step": 273
},
{
"epoch": 0.4950316169828365,
"grad_norm": 0.21492258086562654,
"learning_rate": 2.761321158169134e-05,
"loss": 0.5517,
"step": 274
},
{
"epoch": 0.4968383017163505,
"grad_norm": 0.27472351877781365,
"learning_rate": 2.746438555506109e-05,
"loss": 0.5462,
"step": 275
},
{
"epoch": 0.4986449864498645,
"grad_norm": 0.21428421421146693,
"learning_rate": 2.7315471283758037e-05,
"loss": 0.5378,
"step": 276
},
{
"epoch": 0.5004516711833785,
"grad_norm": 0.22502606248228424,
"learning_rate": 2.7166474100101673e-05,
"loss": 0.5497,
"step": 277
},
{
"epoch": 0.5022583559168925,
"grad_norm": 0.22837843189987042,
"learning_rate": 2.7017399339380434e-05,
"loss": 0.5371,
"step": 278
},
{
"epoch": 0.5040650406504065,
"grad_norm": 0.24309416552693688,
"learning_rate": 2.686825233966061e-05,
"loss": 0.5521,
"step": 279
},
{
"epoch": 0.5058717253839206,
"grad_norm": 0.21900766697042293,
"learning_rate": 2.6719038441595233e-05,
"loss": 0.5481,
"step": 280
},
{
"epoch": 0.5076784101174345,
"grad_norm": 0.22388193391843347,
"learning_rate": 2.656976298823284e-05,
"loss": 0.5491,
"step": 281
},
{
"epoch": 0.5094850948509485,
"grad_norm": 0.22518528793598785,
"learning_rate": 2.6420431324826117e-05,
"loss": 0.5437,
"step": 282
},
{
"epoch": 0.5112917795844625,
"grad_norm": 0.22899910230756002,
"learning_rate": 2.6271048798640547e-05,
"loss": 0.5585,
"step": 283
},
{
"epoch": 0.5130984643179766,
"grad_norm": 0.23580513860894517,
"learning_rate": 2.6121620758762877e-05,
"loss": 0.5466,
"step": 284
},
{
"epoch": 0.5149051490514905,
"grad_norm": 0.2424173649022125,
"learning_rate": 2.5972152555909625e-05,
"loss": 0.542,
"step": 285
},
{
"epoch": 0.5167118337850045,
"grad_norm": 0.21694029342367355,
"learning_rate": 2.5822649542235466e-05,
"loss": 0.5386,
"step": 286
},
{
"epoch": 0.5185185185185185,
"grad_norm": 0.25827875560858626,
"learning_rate": 2.5673117071141572e-05,
"loss": 0.5601,
"step": 287
},
{
"epoch": 0.5203252032520326,
"grad_norm": 0.23262800077998166,
"learning_rate": 2.5523560497083926e-05,
"loss": 0.5575,
"step": 288
},
{
"epoch": 0.5221318879855466,
"grad_norm": 0.2761966922116131,
"learning_rate": 2.5373985175381594e-05,
"loss": 0.5418,
"step": 289
},
{
"epoch": 0.5239385727190605,
"grad_norm": 0.26156166020108806,
"learning_rate": 2.5224396462024947e-05,
"loss": 0.5539,
"step": 290
},
{
"epoch": 0.5257452574525745,
"grad_norm": 0.21779581948691018,
"learning_rate": 2.507479971348391e-05,
"loss": 0.5581,
"step": 291
},
{
"epoch": 0.5275519421860885,
"grad_norm": 0.2377723759423303,
"learning_rate": 2.4925200286516097e-05,
"loss": 0.5621,
"step": 292
},
{
"epoch": 0.5293586269196026,
"grad_norm": 0.25645028358412414,
"learning_rate": 2.4775603537975052e-05,
"loss": 0.5545,
"step": 293
},
{
"epoch": 0.5311653116531165,
"grad_norm": 0.23027125665344333,
"learning_rate": 2.4626014824618415e-05,
"loss": 0.5466,
"step": 294
},
{
"epoch": 0.5329719963866305,
"grad_norm": 0.21506264402370667,
"learning_rate": 2.447643950291608e-05,
"loss": 0.5444,
"step": 295
},
{
"epoch": 0.5347786811201445,
"grad_norm": 0.23689584066775435,
"learning_rate": 2.4326882928858434e-05,
"loss": 0.5486,
"step": 296
},
{
"epoch": 0.5365853658536586,
"grad_norm": 0.24755488327450098,
"learning_rate": 2.417735045776453e-05,
"loss": 0.553,
"step": 297
},
{
"epoch": 0.5383920505871725,
"grad_norm": 0.23203698871403608,
"learning_rate": 2.402784744409038e-05,
"loss": 0.5484,
"step": 298
},
{
"epoch": 0.5401987353206865,
"grad_norm": 0.24571656282529886,
"learning_rate": 2.3878379241237136e-05,
"loss": 0.5632,
"step": 299
},
{
"epoch": 0.5420054200542005,
"grad_norm": 0.20706812965056257,
"learning_rate": 2.372895120135946e-05,
"loss": 0.5513,
"step": 300
},
{
"epoch": 0.5438121047877146,
"grad_norm": 0.2232064747129914,
"learning_rate": 2.3579568675173895e-05,
"loss": 0.5538,
"step": 301
},
{
"epoch": 0.5456187895212286,
"grad_norm": 0.22016741676196278,
"learning_rate": 2.3430237011767167e-05,
"loss": 0.5652,
"step": 302
},
{
"epoch": 0.5474254742547425,
"grad_norm": 0.2235020612958559,
"learning_rate": 2.3280961558404773e-05,
"loss": 0.5464,
"step": 303
},
{
"epoch": 0.5492321589882565,
"grad_norm": 0.22311333060737396,
"learning_rate": 2.3131747660339394e-05,
"loss": 0.5413,
"step": 304
},
{
"epoch": 0.5510388437217706,
"grad_norm": 0.22680586256234805,
"learning_rate": 2.2982600660619572e-05,
"loss": 0.5485,
"step": 305
},
{
"epoch": 0.5528455284552846,
"grad_norm": 0.21059821879953544,
"learning_rate": 2.2833525899898326e-05,
"loss": 0.5459,
"step": 306
},
{
"epoch": 0.5546522131887985,
"grad_norm": 0.20743952304888144,
"learning_rate": 2.268452871624197e-05,
"loss": 0.5626,
"step": 307
},
{
"epoch": 0.5564588979223125,
"grad_norm": 0.21066384195448498,
"learning_rate": 2.2535614444938912e-05,
"loss": 0.5422,
"step": 308
},
{
"epoch": 0.5582655826558266,
"grad_norm": 0.2161934609194102,
"learning_rate": 2.238678841830867e-05,
"loss": 0.552,
"step": 309
},
{
"epoch": 0.5600722673893406,
"grad_norm": 0.1908970151997147,
"learning_rate": 2.223805596551085e-05,
"loss": 0.5339,
"step": 310
},
{
"epoch": 0.5618789521228545,
"grad_norm": 0.2116878435572703,
"learning_rate": 2.2089422412354432e-05,
"loss": 0.553,
"step": 311
},
{
"epoch": 0.5636856368563685,
"grad_norm": 0.6821216144361701,
"learning_rate": 2.1940893081106945e-05,
"loss": 0.5522,
"step": 312
},
{
"epoch": 0.5654923215898826,
"grad_norm": 0.19933075280256027,
"learning_rate": 2.1792473290303946e-05,
"loss": 0.5527,
"step": 313
},
{
"epoch": 0.5672990063233966,
"grad_norm": 0.20221512416983153,
"learning_rate": 2.164416835455862e-05,
"loss": 0.5461,
"step": 314
},
{
"epoch": 0.5691056910569106,
"grad_norm": 0.2068054666438288,
"learning_rate": 2.1495983584371353e-05,
"loss": 0.5466,
"step": 315
},
{
"epoch": 0.5709123757904245,
"grad_norm": 0.2134121906837669,
"learning_rate": 2.1347924285939714e-05,
"loss": 0.5422,
"step": 316
},
{
"epoch": 0.5727190605239386,
"grad_norm": 0.20455764217338732,
"learning_rate": 2.119999576096832e-05,
"loss": 0.5382,
"step": 317
},
{
"epoch": 0.5745257452574526,
"grad_norm": 0.199331906522498,
"learning_rate": 2.1052203306479105e-05,
"loss": 0.5501,
"step": 318
},
{
"epoch": 0.5763324299909666,
"grad_norm": 0.2412560852605461,
"learning_rate": 2.090455221462156e-05,
"loss": 0.5603,
"step": 319
},
{
"epoch": 0.5781391147244805,
"grad_norm": 0.21519069134067864,
"learning_rate": 2.075704777248328e-05,
"loss": 0.5418,
"step": 320
},
{
"epoch": 0.5799457994579946,
"grad_norm": 0.228727628427062,
"learning_rate": 2.0609695261900622e-05,
"loss": 0.5394,
"step": 321
},
{
"epoch": 0.5817524841915086,
"grad_norm": 0.2176156146729185,
"learning_rate": 2.0462499959269593e-05,
"loss": 0.56,
"step": 322
},
{
"epoch": 0.5835591689250226,
"grad_norm": 0.21488586345042776,
"learning_rate": 2.031546713535688e-05,
"loss": 0.5466,
"step": 323
},
{
"epoch": 0.5853658536585366,
"grad_norm": 0.22926197483380642,
"learning_rate": 2.0168602055111173e-05,
"loss": 0.5274,
"step": 324
},
{
"epoch": 0.5871725383920506,
"grad_norm": 0.2229955712111904,
"learning_rate": 2.002190997747455e-05,
"loss": 0.5448,
"step": 325
},
{
"epoch": 0.5889792231255646,
"grad_norm": 0.21531963162859075,
"learning_rate": 1.9875396155194242e-05,
"loss": 0.5544,
"step": 326
},
{
"epoch": 0.5907859078590786,
"grad_norm": 0.20885719552228893,
"learning_rate": 1.972906583463453e-05,
"loss": 0.5404,
"step": 327
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.261458475205465,
"learning_rate": 1.9582924255588828e-05,
"loss": 0.5472,
"step": 328
},
{
"epoch": 0.5943992773261066,
"grad_norm": 0.2103996141488197,
"learning_rate": 1.9436976651092144e-05,
"loss": 0.5368,
"step": 329
},
{
"epoch": 0.5962059620596206,
"grad_norm": 0.21748833338313744,
"learning_rate": 1.9291228247233605e-05,
"loss": 0.5443,
"step": 330
},
{
"epoch": 0.5980126467931346,
"grad_norm": 0.2520334978409223,
"learning_rate": 1.9145684262969403e-05,
"loss": 0.5477,
"step": 331
},
{
"epoch": 0.5998193315266486,
"grad_norm": 0.1957961791185171,
"learning_rate": 1.9000349909935853e-05,
"loss": 0.5315,
"step": 332
},
{
"epoch": 0.6016260162601627,
"grad_norm": 0.20783779398827862,
"learning_rate": 1.885523039226281e-05,
"loss": 0.5521,
"step": 333
},
{
"epoch": 0.6034327009936766,
"grad_norm": 0.20898559191833543,
"learning_rate": 1.871033090638729e-05,
"loss": 0.5642,
"step": 334
},
{
"epoch": 0.6052393857271906,
"grad_norm": 0.1873586938961715,
"learning_rate": 1.8565656640867446e-05,
"loss": 0.5479,
"step": 335
},
{
"epoch": 0.6070460704607046,
"grad_norm": 0.2255988844983079,
"learning_rate": 1.8421212776196712e-05,
"loss": 0.5442,
"step": 336
},
{
"epoch": 0.6088527551942186,
"grad_norm": 0.2132867422782542,
"learning_rate": 1.827700448461836e-05,
"loss": 0.5455,
"step": 337
},
{
"epoch": 0.6106594399277326,
"grad_norm": 0.2013497795480394,
"learning_rate": 1.813303692994025e-05,
"loss": 0.5418,
"step": 338
},
{
"epoch": 0.6124661246612466,
"grad_norm": 0.19449789688874272,
"learning_rate": 1.7989315267349936e-05,
"loss": 0.5503,
"step": 339
},
{
"epoch": 0.6142728093947606,
"grad_norm": 0.20623159680652037,
"learning_rate": 1.7845844643230086e-05,
"loss": 0.5452,
"step": 340
},
{
"epoch": 0.6160794941282746,
"grad_norm": 0.20573869402653808,
"learning_rate": 1.7702630194974168e-05,
"loss": 0.5445,
"step": 341
},
{
"epoch": 0.6178861788617886,
"grad_norm": 0.1964685647724217,
"learning_rate": 1.7559677050802544e-05,
"loss": 0.5466,
"step": 342
},
{
"epoch": 0.6196928635953026,
"grad_norm": 0.20315885913212622,
"learning_rate": 1.7416990329578753e-05,
"loss": 0.5415,
"step": 343
},
{
"epoch": 0.6214995483288166,
"grad_norm": 0.18101549711166035,
"learning_rate": 1.7274575140626318e-05,
"loss": 0.5307,
"step": 344
},
{
"epoch": 0.6233062330623306,
"grad_norm": 0.1994104297590127,
"learning_rate": 1.71324365835457e-05,
"loss": 0.5444,
"step": 345
},
{
"epoch": 0.6251129177958447,
"grad_norm": 0.19723145686498575,
"learning_rate": 1.699057974803176e-05,
"loss": 0.5467,
"step": 346
},
{
"epoch": 0.6269196025293586,
"grad_norm": 0.1850077678736798,
"learning_rate": 1.6849009713691454e-05,
"loss": 0.5323,
"step": 347
},
{
"epoch": 0.6287262872628726,
"grad_norm": 0.276502296878791,
"learning_rate": 1.670773154986199e-05,
"loss": 0.5335,
"step": 348
},
{
"epoch": 0.6305329719963866,
"grad_norm": 0.19317461968464228,
"learning_rate": 1.6566750315429254e-05,
"loss": 0.5375,
"step": 349
},
{
"epoch": 0.6323396567299007,
"grad_norm": 0.19910869280957114,
"learning_rate": 1.6426071058646717e-05,
"loss": 0.549,
"step": 350
},
{
"epoch": 0.6341463414634146,
"grad_norm": 0.18690184695616166,
"learning_rate": 1.6285698816954624e-05,
"loss": 0.5381,
"step": 351
},
{
"epoch": 0.6359530261969286,
"grad_norm": 0.18174973617298104,
"learning_rate": 1.6145638616799635e-05,
"loss": 0.5521,
"step": 352
},
{
"epoch": 0.6377597109304426,
"grad_norm": 0.19064784919043637,
"learning_rate": 1.6005895473454834e-05,
"loss": 0.5525,
"step": 353
},
{
"epoch": 0.6395663956639567,
"grad_norm": 0.18767396978783557,
"learning_rate": 1.5866474390840125e-05,
"loss": 0.5474,
"step": 354
},
{
"epoch": 0.6413730803974707,
"grad_norm": 0.1954432958053184,
"learning_rate": 1.5727380361343103e-05,
"loss": 0.5362,
"step": 355
},
{
"epoch": 0.6431797651309846,
"grad_norm": 0.17705406426867062,
"learning_rate": 1.55886183656402e-05,
"loss": 0.5496,
"step": 356
},
{
"epoch": 0.6449864498644986,
"grad_norm": 0.20060277252597722,
"learning_rate": 1.545019337251844e-05,
"loss": 0.5514,
"step": 357
},
{
"epoch": 0.6467931345980127,
"grad_norm": 0.193669354774866,
"learning_rate": 1.5312110338697426e-05,
"loss": 0.5568,
"step": 358
},
{
"epoch": 0.6485998193315267,
"grad_norm": 0.18018469221264521,
"learning_rate": 1.5174374208651912e-05,
"loss": 0.5306,
"step": 359
},
{
"epoch": 0.6504065040650406,
"grad_norm": 0.1778288207244956,
"learning_rate": 1.503698991443471e-05,
"loss": 0.5392,
"step": 360
},
{
"epoch": 0.6522131887985546,
"grad_norm": 0.2115671504855792,
"learning_rate": 1.4899962375500121e-05,
"loss": 0.544,
"step": 361
},
{
"epoch": 0.6540198735320687,
"grad_norm": 0.18387092791329196,
"learning_rate": 1.4763296498527743e-05,
"loss": 0.5551,
"step": 362
},
{
"epoch": 0.6558265582655827,
"grad_norm": 0.20242860658284711,
"learning_rate": 1.4626997177246787e-05,
"loss": 0.5457,
"step": 363
},
{
"epoch": 0.6576332429990966,
"grad_norm": 0.19345607164662235,
"learning_rate": 1.4491069292260868e-05,
"loss": 0.5458,
"step": 364
},
{
"epoch": 0.6594399277326106,
"grad_norm": 0.186250552017406,
"learning_rate": 1.4355517710873184e-05,
"loss": 0.537,
"step": 365
},
{
"epoch": 0.6612466124661247,
"grad_norm": 0.19349404868910808,
"learning_rate": 1.4220347286912294e-05,
"loss": 0.558,
"step": 366
},
{
"epoch": 0.6630532971996387,
"grad_norm": 0.1805348865094129,
"learning_rate": 1.4085562860558255e-05,
"loss": 0.5395,
"step": 367
},
{
"epoch": 0.6648599819331527,
"grad_norm": 0.18495404781177935,
"learning_rate": 1.3951169258169338e-05,
"loss": 0.551,
"step": 368
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.18688251287931992,
"learning_rate": 1.3817171292109183e-05,
"loss": 0.5516,
"step": 369
},
{
"epoch": 0.6684733514001807,
"grad_norm": 0.1898547525063398,
"learning_rate": 1.3683573760574526e-05,
"loss": 0.5506,
"step": 370
},
{
"epoch": 0.6702800361336947,
"grad_norm": 0.18239213301354457,
"learning_rate": 1.3550381447423316e-05,
"loss": 0.5381,
"step": 371
},
{
"epoch": 0.6720867208672087,
"grad_norm": 0.17814691094904994,
"learning_rate": 1.3417599122003464e-05,
"loss": 0.5555,
"step": 372
},
{
"epoch": 0.6738934056007226,
"grad_norm": 0.21908295063893554,
"learning_rate": 1.3285231538982034e-05,
"loss": 0.5415,
"step": 373
},
{
"epoch": 0.6757000903342367,
"grad_norm": 0.17230078309311048,
"learning_rate": 1.3153283438175034e-05,
"loss": 0.5317,
"step": 374
},
{
"epoch": 0.6775067750677507,
"grad_norm": 0.18162525160837265,
"learning_rate": 1.3021759544377632e-05,
"loss": 0.5453,
"step": 375
},
{
"epoch": 0.6793134598012647,
"grad_norm": 0.17485786762275105,
"learning_rate": 1.2890664567194998e-05,
"loss": 0.5304,
"step": 376
},
{
"epoch": 0.6811201445347786,
"grad_norm": 0.16794425941753846,
"learning_rate": 1.2760003200873699e-05,
"loss": 0.5464,
"step": 377
},
{
"epoch": 0.6829268292682927,
"grad_norm": 0.18163641320102142,
"learning_rate": 1.2629780124133511e-05,
"loss": 0.5472,
"step": 378
},
{
"epoch": 0.6847335140018067,
"grad_norm": 0.18356921181202607,
"learning_rate": 1.2500000000000006e-05,
"loss": 0.5503,
"step": 379
},
{
"epoch": 0.6865401987353207,
"grad_norm": 0.189587834239473,
"learning_rate": 1.2370667475637473e-05,
"loss": 0.5316,
"step": 380
},
{
"epoch": 0.6883468834688347,
"grad_norm": 0.19057832221881246,
"learning_rate": 1.2241787182182595e-05,
"loss": 0.5473,
"step": 381
},
{
"epoch": 0.6901535682023487,
"grad_norm": 0.1874557710612082,
"learning_rate": 1.2113363734578548e-05,
"loss": 0.5347,
"step": 382
},
{
"epoch": 0.6919602529358627,
"grad_norm": 0.17256058169239688,
"learning_rate": 1.1985401731409792e-05,
"loss": 0.5537,
"step": 383
},
{
"epoch": 0.6937669376693767,
"grad_norm": 0.1871844566367914,
"learning_rate": 1.185790575473738e-05,
"loss": 0.5506,
"step": 384
},
{
"epoch": 0.6955736224028907,
"grad_norm": 0.1894245222651623,
"learning_rate": 1.1730880369934933e-05,
"loss": 0.5338,
"step": 385
},
{
"epoch": 0.6973803071364046,
"grad_norm": 0.18773033629918157,
"learning_rate": 1.1604330125525079e-05,
"loss": 0.5455,
"step": 386
},
{
"epoch": 0.6991869918699187,
"grad_norm": 0.19204257911058253,
"learning_rate": 1.1478259553016682e-05,
"loss": 0.5455,
"step": 387
},
{
"epoch": 0.7009936766034327,
"grad_norm": 0.17625044703357365,
"learning_rate": 1.135267316674246e-05,
"loss": 0.5442,
"step": 388
},
{
"epoch": 0.7028003613369467,
"grad_norm": 0.18034125469253723,
"learning_rate": 1.122757546369744e-05,
"loss": 0.5467,
"step": 389
},
{
"epoch": 0.7046070460704607,
"grad_norm": 0.19225536088509088,
"learning_rate": 1.1102970923377892e-05,
"loss": 0.5418,
"step": 390
},
{
"epoch": 0.7064137308039747,
"grad_norm": 0.19942810091065274,
"learning_rate": 1.0978864007620895e-05,
"loss": 0.5407,
"step": 391
},
{
"epoch": 0.7082204155374887,
"grad_norm": 0.21501138455823338,
"learning_rate": 1.0855259160444639e-05,
"loss": 0.5476,
"step": 392
},
{
"epoch": 0.7100271002710027,
"grad_norm": 0.2884668010582998,
"learning_rate": 1.0732160807889211e-05,
"loss": 0.5519,
"step": 393
},
{
"epoch": 0.7118337850045167,
"grad_norm": 0.17022174290624156,
"learning_rate": 1.0609573357858166e-05,
"loss": 0.5546,
"step": 394
},
{
"epoch": 0.7136404697380307,
"grad_norm": 0.1854412182788549,
"learning_rate": 1.0487501199960662e-05,
"loss": 0.5484,
"step": 395
},
{
"epoch": 0.7154471544715447,
"grad_norm": 0.17931062842447656,
"learning_rate": 1.0365948705354308e-05,
"loss": 0.5432,
"step": 396
},
{
"epoch": 0.7172538392050587,
"grad_norm": 0.18675467992935785,
"learning_rate": 1.0244920226588597e-05,
"loss": 0.5433,
"step": 397
},
{
"epoch": 0.7190605239385727,
"grad_norm": 0.1813756337924599,
"learning_rate": 1.0124420097449078e-05,
"loss": 0.5448,
"step": 398
},
{
"epoch": 0.7208672086720868,
"grad_norm": 0.1827888408060404,
"learning_rate": 1.0004452632802158e-05,
"loss": 0.5467,
"step": 399
},
{
"epoch": 0.7226738934056007,
"grad_norm": 0.193764370666216,
"learning_rate": 9.88502212844063e-06,
"loss": 0.5443,
"step": 400
},
{
"epoch": 0.7244805781391147,
"grad_norm": 0.16545671285046895,
"learning_rate": 9.7661328609298e-06,
"loss": 0.5457,
"step": 401
},
{
"epoch": 0.7262872628726287,
"grad_norm": 0.17759841178915517,
"learning_rate": 9.64778908745437e-06,
"loss": 0.5523,
"step": 402
},
{
"epoch": 0.7280939476061428,
"grad_norm": 0.16977669465620818,
"learning_rate": 9.52999504566604e-06,
"loss": 0.5339,
"step": 403
},
{
"epoch": 0.7299006323396567,
"grad_norm": 0.1697665049131124,
"learning_rate": 9.412754953531663e-06,
"loss": 0.54,
"step": 404
},
{
"epoch": 0.7317073170731707,
"grad_norm": 0.17079386129703159,
"learning_rate": 9.29607300918234e-06,
"loss": 0.5376,
"step": 405
},
{
"epoch": 0.7335140018066847,
"grad_norm": 0.19277525431650847,
"learning_rate": 9.179953390762977e-06,
"loss": 0.5438,
"step": 406
},
{
"epoch": 0.7353206865401988,
"grad_norm": 0.16461495695395428,
"learning_rate": 9.064400256282757e-06,
"loss": 0.5358,
"step": 407
},
{
"epoch": 0.7371273712737128,
"grad_norm": 0.18879440447103327,
"learning_rate": 8.9494177434662e-06,
"loss": 0.5297,
"step": 408
},
{
"epoch": 0.7389340560072267,
"grad_norm": 0.19522621872944385,
"learning_rate": 8.835009969605012e-06,
"loss": 0.5501,
"step": 409
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.17214238999653064,
"learning_rate": 8.72118103141066e-06,
"loss": 0.5498,
"step": 410
},
{
"epoch": 0.7425474254742548,
"grad_norm": 0.1749110612132328,
"learning_rate": 8.607935004867693e-06,
"loss": 0.5524,
"step": 411
},
{
"epoch": 0.7443541102077688,
"grad_norm": 0.17609386516997122,
"learning_rate": 8.495275945087744e-06,
"loss": 0.5258,
"step": 412
},
{
"epoch": 0.7461607949412827,
"grad_norm": 0.1797618429427097,
"learning_rate": 8.383207886164366e-06,
"loss": 0.5412,
"step": 413
},
{
"epoch": 0.7479674796747967,
"grad_norm": 0.17992769342301995,
"learning_rate": 8.271734841028553e-06,
"loss": 0.5299,
"step": 414
},
{
"epoch": 0.7497741644083108,
"grad_norm": 0.17963490369072127,
"learning_rate": 8.16086080130506e-06,
"loss": 0.5504,
"step": 415
},
{
"epoch": 0.7515808491418248,
"grad_norm": 0.1816082193046965,
"learning_rate": 8.050589737169485e-06,
"loss": 0.5374,
"step": 416
},
{
"epoch": 0.7533875338753387,
"grad_norm": 0.17209070843288865,
"learning_rate": 7.940925597206054e-06,
"loss": 0.5577,
"step": 417
},
{
"epoch": 0.7551942186088527,
"grad_norm": 0.1772584025417161,
"learning_rate": 7.831872308266305e-06,
"loss": 0.5395,
"step": 418
},
{
"epoch": 0.7570009033423668,
"grad_norm": 0.16311139160161808,
"learning_rate": 7.723433775328384e-06,
"loss": 0.5417,
"step": 419
},
{
"epoch": 0.7588075880758808,
"grad_norm": 0.17003456646796242,
"learning_rate": 7.615613881357314e-06,
"loss": 0.555,
"step": 420
},
{
"epoch": 0.7606142728093948,
"grad_norm": 0.16854440477398433,
"learning_rate": 7.508416487165862e-06,
"loss": 0.5375,
"step": 421
},
{
"epoch": 0.7624209575429087,
"grad_norm": 0.15674937980320675,
"learning_rate": 7.401845431276378e-06,
"loss": 0.5411,
"step": 422
},
{
"epoch": 0.7642276422764228,
"grad_norm": 0.16794250291803633,
"learning_rate": 7.2959045297832655e-06,
"loss": 0.5493,
"step": 423
},
{
"epoch": 0.7660343270099368,
"grad_norm": 0.17102277468152005,
"learning_rate": 7.190597576216385e-06,
"loss": 0.5529,
"step": 424
},
{
"epoch": 0.7678410117434508,
"grad_norm": 0.17340617098247255,
"learning_rate": 7.085928341405193e-06,
"loss": 0.5316,
"step": 425
},
{
"epoch": 0.7696476964769647,
"grad_norm": 0.20436247869710572,
"learning_rate": 6.98190057334375e-06,
"loss": 0.5515,
"step": 426
},
{
"epoch": 0.7714543812104788,
"grad_norm": 0.16090455324449274,
"learning_rate": 6.8785179970564575e-06,
"loss": 0.5235,
"step": 427
},
{
"epoch": 0.7732610659439928,
"grad_norm": 0.16491506792849778,
"learning_rate": 6.775784314464717e-06,
"loss": 0.544,
"step": 428
},
{
"epoch": 0.7750677506775068,
"grad_norm": 0.17703605814499973,
"learning_rate": 6.673703204254347e-06,
"loss": 0.5392,
"step": 429
},
{
"epoch": 0.7768744354110207,
"grad_norm": 0.16598578274238826,
"learning_rate": 6.572278321743871e-06,
"loss": 0.54,
"step": 430
},
{
"epoch": 0.7786811201445348,
"grad_norm": 0.18841603342599839,
"learning_rate": 6.471513298753634e-06,
"loss": 0.5489,
"step": 431
},
{
"epoch": 0.7804878048780488,
"grad_norm": 0.16749176773882715,
"learning_rate": 6.371411743475716e-06,
"loss": 0.5443,
"step": 432
},
{
"epoch": 0.7822944896115628,
"grad_norm": 0.16428065339926168,
"learning_rate": 6.271977240344795e-06,
"loss": 0.5517,
"step": 433
},
{
"epoch": 0.7841011743450768,
"grad_norm": 0.15595782253122276,
"learning_rate": 6.173213349909729e-06,
"loss": 0.5498,
"step": 434
},
{
"epoch": 0.7859078590785907,
"grad_norm": 0.1687428753872847,
"learning_rate": 6.075123608706093e-06,
"loss": 0.5283,
"step": 435
},
{
"epoch": 0.7877145438121048,
"grad_norm": 0.17401608915458225,
"learning_rate": 5.97771152912954e-06,
"loss": 0.5419,
"step": 436
},
{
"epoch": 0.7895212285456188,
"grad_norm": 0.165969115970308,
"learning_rate": 5.88098059931004e-06,
"loss": 0.5414,
"step": 437
},
{
"epoch": 0.7913279132791328,
"grad_norm": 0.18993772688540833,
"learning_rate": 5.784934282986956e-06,
"loss": 0.5326,
"step": 438
},
{
"epoch": 0.7931345980126467,
"grad_norm": 0.17267310640404834,
"learning_rate": 5.689576019385015e-06,
"loss": 0.5498,
"step": 439
},
{
"epoch": 0.7949412827461608,
"grad_norm": 0.1636848023371795,
"learning_rate": 5.59490922309118e-06,
"loss": 0.5408,
"step": 440
},
{
"epoch": 0.7967479674796748,
"grad_norm": 0.15808909958482328,
"learning_rate": 5.500937283932348e-06,
"loss": 0.5268,
"step": 441
},
{
"epoch": 0.7985546522131888,
"grad_norm": 0.16564988647802914,
"learning_rate": 5.4076635668540075e-06,
"loss": 0.5355,
"step": 442
},
{
"epoch": 0.8003613369467028,
"grad_norm": 0.17071401506597764,
"learning_rate": 5.3150914117996995e-06,
"loss": 0.543,
"step": 443
},
{
"epoch": 0.8021680216802168,
"grad_norm": 0.1628448162977609,
"learning_rate": 5.223224133591476e-06,
"loss": 0.5482,
"step": 444
},
{
"epoch": 0.8039747064137308,
"grad_norm": 0.17103430640341877,
"learning_rate": 5.132065021811122e-06,
"loss": 0.5366,
"step": 445
},
{
"epoch": 0.8057813911472448,
"grad_norm": 0.16682698787825212,
"learning_rate": 5.041617340682467e-06,
"loss": 0.5346,
"step": 446
},
{
"epoch": 0.8075880758807588,
"grad_norm": 0.15971926510706536,
"learning_rate": 4.951884328954401e-06,
"loss": 0.5393,
"step": 447
},
{
"epoch": 0.8093947606142728,
"grad_norm": 0.15478384009393892,
"learning_rate": 4.862869199784984e-06,
"loss": 0.5421,
"step": 448
},
{
"epoch": 0.8112014453477868,
"grad_norm": 0.15933300652649096,
"learning_rate": 4.7745751406263165e-06,
"loss": 0.536,
"step": 449
},
{
"epoch": 0.8130081300813008,
"grad_norm": 0.16285567779331575,
"learning_rate": 4.687005313110454e-06,
"loss": 0.547,
"step": 450
},
{
"epoch": 0.8148148148148148,
"grad_norm": 0.1745816724015838,
"learning_rate": 4.600162852936171e-06,
"loss": 0.5475,
"step": 451
},
{
"epoch": 0.8166214995483289,
"grad_norm": 0.15772843709224638,
"learning_rate": 4.514050869756703e-06,
"loss": 0.5452,
"step": 452
},
{
"epoch": 0.8184281842818428,
"grad_norm": 0.17376869601451123,
"learning_rate": 4.428672447068357e-06,
"loss": 0.5365,
"step": 453
},
{
"epoch": 0.8202348690153568,
"grad_norm": 0.17830063470449606,
"learning_rate": 4.344030642100133e-06,
"loss": 0.5216,
"step": 454
},
{
"epoch": 0.8220415537488708,
"grad_norm": 0.1624558883333754,
"learning_rate": 4.2601284857042266e-06,
"loss": 0.5441,
"step": 455
},
{
"epoch": 0.8238482384823849,
"grad_norm": 0.1524054782501282,
"learning_rate": 4.176968982247514e-06,
"loss": 0.5373,
"step": 456
},
{
"epoch": 0.8256549232158988,
"grad_norm": 0.16912982631464618,
"learning_rate": 4.094555109503983e-06,
"loss": 0.551,
"step": 457
},
{
"epoch": 0.8274616079494128,
"grad_norm": 0.15367849586984553,
"learning_rate": 4.012889818548069e-06,
"loss": 0.5427,
"step": 458
},
{
"epoch": 0.8292682926829268,
"grad_norm": 0.15386717642477954,
"learning_rate": 3.931976033649021e-06,
"loss": 0.5327,
"step": 459
},
{
"epoch": 0.8310749774164409,
"grad_norm": 0.16360562053015648,
"learning_rate": 3.851816652166165e-06,
"loss": 0.542,
"step": 460
},
{
"epoch": 0.8328816621499548,
"grad_norm": 0.16611831314230519,
"learning_rate": 3.772414544445163e-06,
"loss": 0.5308,
"step": 461
},
{
"epoch": 0.8346883468834688,
"grad_norm": 0.1719087225544376,
"learning_rate": 3.6937725537152274e-06,
"loss": 0.5389,
"step": 462
},
{
"epoch": 0.8364950316169828,
"grad_norm": 0.1530697651515559,
"learning_rate": 3.6158934959873353e-06,
"loss": 0.5421,
"step": 463
},
{
"epoch": 0.8383017163504969,
"grad_norm": 0.16949870584991475,
"learning_rate": 3.5387801599533475e-06,
"loss": 0.5446,
"step": 464
},
{
"epoch": 0.8401084010840109,
"grad_norm": 0.1814848827742537,
"learning_rate": 3.4624353068861943e-06,
"loss": 0.5547,
"step": 465
},
{
"epoch": 0.8419150858175248,
"grad_norm": 0.1617536304146353,
"learning_rate": 3.386861670540972e-06,
"loss": 0.5374,
"step": 466
},
{
"epoch": 0.8437217705510388,
"grad_norm": 0.15306707484519436,
"learning_rate": 3.312061957057061e-06,
"loss": 0.5348,
"step": 467
},
{
"epoch": 0.8455284552845529,
"grad_norm": 0.23382324587988676,
"learning_rate": 3.2380388448612437e-06,
"loss": 0.5448,
"step": 468
},
{
"epoch": 0.8473351400180669,
"grad_norm": 0.1662985426730699,
"learning_rate": 3.164794984571759e-06,
"loss": 0.5342,
"step": 469
},
{
"epoch": 0.8491418247515808,
"grad_norm": 0.1867364488340354,
"learning_rate": 3.092332998903416e-06,
"loss": 0.531,
"step": 470
},
{
"epoch": 0.8509485094850948,
"grad_norm": 0.16499419657563977,
"learning_rate": 3.020655482573659e-06,
"loss": 0.5593,
"step": 471
},
{
"epoch": 0.8527551942186089,
"grad_norm": 0.16082015565225696,
"learning_rate": 2.949765002209698e-06,
"loss": 0.5312,
"step": 472
},
{
"epoch": 0.8545618789521229,
"grad_norm": 0.15597231184905325,
"learning_rate": 2.8796640962565374e-06,
"loss": 0.549,
"step": 473
},
{
"epoch": 0.8563685636856369,
"grad_norm": 0.39671617649713814,
"learning_rate": 2.8103552748861476e-06,
"loss": 0.5451,
"step": 474
},
{
"epoch": 0.8581752484191508,
"grad_norm": 0.17753504313617807,
"learning_rate": 2.741841019907529e-06,
"loss": 0.5348,
"step": 475
},
{
"epoch": 0.8599819331526649,
"grad_norm": 0.1637289948609238,
"learning_rate": 2.6741237846778676e-06,
"loss": 0.5409,
"step": 476
},
{
"epoch": 0.8617886178861789,
"grad_norm": 0.1585219127905966,
"learning_rate": 2.6072059940146775e-06,
"loss": 0.5388,
"step": 477
},
{
"epoch": 0.8635953026196929,
"grad_norm": 0.168840088490212,
"learning_rate": 2.5410900441089903e-06,
"loss": 0.5485,
"step": 478
},
{
"epoch": 0.8654019873532068,
"grad_norm": 0.16390582789463012,
"learning_rate": 2.475778302439524e-06,
"loss": 0.5344,
"step": 479
},
{
"epoch": 0.8672086720867209,
"grad_norm": 0.1520203237608367,
"learning_rate": 2.411273107687925e-06,
"loss": 0.5335,
"step": 480
},
{
"epoch": 0.8690153568202349,
"grad_norm": 0.16016367056006486,
"learning_rate": 2.3475767696550327e-06,
"loss": 0.5441,
"step": 481
},
{
"epoch": 0.8708220415537489,
"grad_norm": 0.16365201764510548,
"learning_rate": 2.284691569178138e-06,
"loss": 0.5481,
"step": 482
},
{
"epoch": 0.8726287262872628,
"grad_norm": 0.1580464673317223,
"learning_rate": 2.222619758049366e-06,
"loss": 0.5333,
"step": 483
},
{
"epoch": 0.8744354110207768,
"grad_norm": 0.156148786762582,
"learning_rate": 2.1613635589349756e-06,
"loss": 0.5291,
"step": 484
},
{
"epoch": 0.8762420957542909,
"grad_norm": 0.1659657301447351,
"learning_rate": 2.1009251652958387e-06,
"loss": 0.5394,
"step": 485
},
{
"epoch": 0.8780487804878049,
"grad_norm": 0.15790108586836402,
"learning_rate": 2.041306741308832e-06,
"loss": 0.5455,
"step": 486
},
{
"epoch": 0.8798554652213189,
"grad_norm": 0.1478785936292581,
"learning_rate": 1.9825104217894018e-06,
"loss": 0.5332,
"step": 487
},
{
"epoch": 0.8816621499548328,
"grad_norm": 0.1462534164047016,
"learning_rate": 1.9245383121150677e-06,
"loss": 0.5327,
"step": 488
},
{
"epoch": 0.8834688346883469,
"grad_norm": 0.14605069151679811,
"learning_rate": 1.8673924881500826e-06,
"loss": 0.5416,
"step": 489
},
{
"epoch": 0.8852755194218609,
"grad_norm": 0.1589930446245649,
"learning_rate": 1.8110749961710584e-06,
"loss": 0.5392,
"step": 490
},
{
"epoch": 0.8870822041553749,
"grad_norm": 0.14986223598486392,
"learning_rate": 1.7555878527937164e-06,
"loss": 0.5301,
"step": 491
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.15447871937241114,
"learning_rate": 1.700933044900671e-06,
"loss": 0.5319,
"step": 492
},
{
"epoch": 0.8906955736224029,
"grad_norm": 0.15296232399715282,
"learning_rate": 1.6471125295702771e-06,
"loss": 0.5261,
"step": 493
},
{
"epoch": 0.8925022583559169,
"grad_norm": 0.14757354919345866,
"learning_rate": 1.59412823400657e-06,
"loss": 0.5435,
"step": 494
},
{
"epoch": 0.8943089430894309,
"grad_norm": 0.15297818755134698,
"learning_rate": 1.5419820554702314e-06,
"loss": 0.5401,
"step": 495
},
{
"epoch": 0.8961156278229448,
"grad_norm": 0.15271018404390577,
"learning_rate": 1.4906758612106636e-06,
"loss": 0.5519,
"step": 496
},
{
"epoch": 0.8979223125564589,
"grad_norm": 0.1625002948888311,
"learning_rate": 1.4402114883991318e-06,
"loss": 0.5395,
"step": 497
},
{
"epoch": 0.8997289972899729,
"grad_norm": 0.16940382579519814,
"learning_rate": 1.3905907440629752e-06,
"loss": 0.539,
"step": 498
},
{
"epoch": 0.9015356820234869,
"grad_norm": 0.16321190702331076,
"learning_rate": 1.3418154050208936e-06,
"loss": 0.5475,
"step": 499
},
{
"epoch": 0.9033423667570009,
"grad_norm": 0.24374183136883182,
"learning_rate": 1.2938872178193395e-06,
"loss": 0.5465,
"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
}