jerseyjerry's picture
Uploading model files
af26ccc verified
raw
history blame
91.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.00100150225338,
"eval_steps": 50,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00200300450676014,
"grad_norm": 1.1490445137023926,
"learning_rate": 6.666666666666667e-07,
"loss": 1.2042,
"step": 2
},
{
"epoch": 0.00400600901352028,
"grad_norm": 1.0771784782409668,
"learning_rate": 1.3333333333333334e-06,
"loss": 1.307,
"step": 4
},
{
"epoch": 0.006009013520280421,
"grad_norm": 1.569467306137085,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.3554,
"step": 6
},
{
"epoch": 0.00801201802704056,
"grad_norm": 1.3319200277328491,
"learning_rate": 2.666666666666667e-06,
"loss": 1.293,
"step": 8
},
{
"epoch": 0.010015022533800702,
"grad_norm": 1.0480939149856567,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.2224,
"step": 10
},
{
"epoch": 0.012018027040560842,
"grad_norm": 1.1433207988739014,
"learning_rate": 4.000000000000001e-06,
"loss": 1.2897,
"step": 12
},
{
"epoch": 0.014021031547320982,
"grad_norm": 1.073263168334961,
"learning_rate": 4.666666666666667e-06,
"loss": 1.2234,
"step": 14
},
{
"epoch": 0.01602403605408112,
"grad_norm": 1.4199696779251099,
"learning_rate": 5.333333333333334e-06,
"loss": 1.2185,
"step": 16
},
{
"epoch": 0.018027040560841263,
"grad_norm": 1.0688554048538208,
"learning_rate": 6e-06,
"loss": 1.1962,
"step": 18
},
{
"epoch": 0.020030045067601403,
"grad_norm": 0.7635518312454224,
"learning_rate": 6.666666666666667e-06,
"loss": 1.2015,
"step": 20
},
{
"epoch": 0.022033049574361543,
"grad_norm": 0.898193895816803,
"learning_rate": 7.333333333333334e-06,
"loss": 1.2538,
"step": 22
},
{
"epoch": 0.024036054081121683,
"grad_norm": 0.5049487948417664,
"learning_rate": 8.000000000000001e-06,
"loss": 1.1567,
"step": 24
},
{
"epoch": 0.026039058587881823,
"grad_norm": 0.5218433141708374,
"learning_rate": 8.666666666666668e-06,
"loss": 1.1553,
"step": 26
},
{
"epoch": 0.028042063094641963,
"grad_norm": 0.6712301969528198,
"learning_rate": 9.333333333333334e-06,
"loss": 1.2026,
"step": 28
},
{
"epoch": 0.030045067601402103,
"grad_norm": 0.5391427278518677,
"learning_rate": 1e-05,
"loss": 1.2703,
"step": 30
},
{
"epoch": 0.03204807210816224,
"grad_norm": 0.462812602519989,
"learning_rate": 1.0666666666666667e-05,
"loss": 1.1924,
"step": 32
},
{
"epoch": 0.03405107661492238,
"grad_norm": 0.6354833245277405,
"learning_rate": 1.1333333333333334e-05,
"loss": 1.1828,
"step": 34
},
{
"epoch": 0.03605408112168253,
"grad_norm": 0.41658806800842285,
"learning_rate": 1.2e-05,
"loss": 1.0911,
"step": 36
},
{
"epoch": 0.03805708562844266,
"grad_norm": 0.40210819244384766,
"learning_rate": 1.2666666666666668e-05,
"loss": 1.1088,
"step": 38
},
{
"epoch": 0.04006009013520281,
"grad_norm": 0.4195331931114197,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.1107,
"step": 40
},
{
"epoch": 0.04206309464196294,
"grad_norm": 0.4773981273174286,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.0895,
"step": 42
},
{
"epoch": 0.04406609914872309,
"grad_norm": 0.44729089736938477,
"learning_rate": 1.4666666666666668e-05,
"loss": 1.1064,
"step": 44
},
{
"epoch": 0.04606910365548322,
"grad_norm": 0.4262336492538452,
"learning_rate": 1.5333333333333334e-05,
"loss": 1.1339,
"step": 46
},
{
"epoch": 0.04807210816224337,
"grad_norm": 0.48148858547210693,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.0981,
"step": 48
},
{
"epoch": 0.0500751126690035,
"grad_norm": 0.39283275604248047,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.093,
"step": 50
},
{
"epoch": 0.0500751126690035,
"eval_loss": 1.2894173860549927,
"eval_runtime": 3.763,
"eval_samples_per_second": 15.413,
"eval_steps_per_second": 7.707,
"step": 50
},
{
"epoch": 0.05207811717576365,
"grad_norm": 0.37658512592315674,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.139,
"step": 52
},
{
"epoch": 0.05408112168252378,
"grad_norm": 0.5392587184906006,
"learning_rate": 1.8e-05,
"loss": 1.125,
"step": 54
},
{
"epoch": 0.05608412618928393,
"grad_norm": 0.4281522333621979,
"learning_rate": 1.866666666666667e-05,
"loss": 1.142,
"step": 56
},
{
"epoch": 0.05808713069604406,
"grad_norm": 0.3900790512561798,
"learning_rate": 1.9333333333333333e-05,
"loss": 1.0687,
"step": 58
},
{
"epoch": 0.06009013520280421,
"grad_norm": 0.43412598967552185,
"learning_rate": 2e-05,
"loss": 1.0266,
"step": 60
},
{
"epoch": 0.06209313970956434,
"grad_norm": 0.35002750158309937,
"learning_rate": 2.0666666666666666e-05,
"loss": 1.0595,
"step": 62
},
{
"epoch": 0.06409614421632448,
"grad_norm": 0.4777143597602844,
"learning_rate": 2.1333333333333335e-05,
"loss": 1.1136,
"step": 64
},
{
"epoch": 0.06609914872308463,
"grad_norm": 0.49310263991355896,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.0185,
"step": 66
},
{
"epoch": 0.06810215322984477,
"grad_norm": 0.449856698513031,
"learning_rate": 2.2666666666666668e-05,
"loss": 1.1279,
"step": 68
},
{
"epoch": 0.0701051577366049,
"grad_norm": 0.38826239109039307,
"learning_rate": 2.3333333333333336e-05,
"loss": 1.0885,
"step": 70
},
{
"epoch": 0.07210816224336505,
"grad_norm": 0.4807354509830475,
"learning_rate": 2.4e-05,
"loss": 1.0903,
"step": 72
},
{
"epoch": 0.07411116675012519,
"grad_norm": 0.4949500262737274,
"learning_rate": 2.466666666666667e-05,
"loss": 1.127,
"step": 74
},
{
"epoch": 0.07611417125688533,
"grad_norm": 0.3626649081707001,
"learning_rate": 2.5333333333333337e-05,
"loss": 1.0255,
"step": 76
},
{
"epoch": 0.07811717576364546,
"grad_norm": 0.5750380754470825,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.1275,
"step": 78
},
{
"epoch": 0.08012018027040561,
"grad_norm": 0.39814862608909607,
"learning_rate": 2.6666666666666667e-05,
"loss": 1.0341,
"step": 80
},
{
"epoch": 0.08212318477716575,
"grad_norm": 0.4639066457748413,
"learning_rate": 2.733333333333333e-05,
"loss": 1.0229,
"step": 82
},
{
"epoch": 0.08412618928392589,
"grad_norm": 0.4696304500102997,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.9657,
"step": 84
},
{
"epoch": 0.08612919379068602,
"grad_norm": 0.4721640646457672,
"learning_rate": 2.8666666666666668e-05,
"loss": 1.0449,
"step": 86
},
{
"epoch": 0.08813219829744617,
"grad_norm": 0.538497805595398,
"learning_rate": 2.9333333333333336e-05,
"loss": 1.0298,
"step": 88
},
{
"epoch": 0.09013520280420631,
"grad_norm": 0.4559970498085022,
"learning_rate": 3e-05,
"loss": 1.1037,
"step": 90
},
{
"epoch": 0.09213820731096645,
"grad_norm": 0.5490939617156982,
"learning_rate": 3.066666666666667e-05,
"loss": 1.0027,
"step": 92
},
{
"epoch": 0.09414121181772658,
"grad_norm": 0.45646870136260986,
"learning_rate": 3.1333333333333334e-05,
"loss": 0.9897,
"step": 94
},
{
"epoch": 0.09614421632448673,
"grad_norm": 0.43321868777275085,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.0761,
"step": 96
},
{
"epoch": 0.09814722083124687,
"grad_norm": 0.5118622183799744,
"learning_rate": 3.266666666666667e-05,
"loss": 1.02,
"step": 98
},
{
"epoch": 0.100150225338007,
"grad_norm": 0.496593177318573,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.0625,
"step": 100
},
{
"epoch": 0.100150225338007,
"eval_loss": 1.240967035293579,
"eval_runtime": 3.786,
"eval_samples_per_second": 15.32,
"eval_steps_per_second": 7.66,
"step": 100
},
{
"epoch": 0.10215322984476716,
"grad_norm": 0.4841687083244324,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.0166,
"step": 102
},
{
"epoch": 0.1041562343515273,
"grad_norm": 0.5562867522239685,
"learning_rate": 3.466666666666667e-05,
"loss": 1.0716,
"step": 104
},
{
"epoch": 0.10615923885828743,
"grad_norm": 0.5093795657157898,
"learning_rate": 3.5333333333333336e-05,
"loss": 1.0912,
"step": 106
},
{
"epoch": 0.10816224336504757,
"grad_norm": 0.4446066915988922,
"learning_rate": 3.6e-05,
"loss": 1.0152,
"step": 108
},
{
"epoch": 0.11016524787180772,
"grad_norm": 0.518335223197937,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.0098,
"step": 110
},
{
"epoch": 0.11216825237856785,
"grad_norm": 0.47020334005355835,
"learning_rate": 3.733333333333334e-05,
"loss": 1.0347,
"step": 112
},
{
"epoch": 0.11417125688532799,
"grad_norm": 0.5809981226921082,
"learning_rate": 3.8e-05,
"loss": 1.0242,
"step": 114
},
{
"epoch": 0.11617426139208813,
"grad_norm": 0.49666646122932434,
"learning_rate": 3.866666666666667e-05,
"loss": 1.053,
"step": 116
},
{
"epoch": 0.11817726589884828,
"grad_norm": 0.47094520926475525,
"learning_rate": 3.933333333333333e-05,
"loss": 1.0258,
"step": 118
},
{
"epoch": 0.12018027040560841,
"grad_norm": 0.5577300786972046,
"learning_rate": 4e-05,
"loss": 1.0197,
"step": 120
},
{
"epoch": 0.12218327491236855,
"grad_norm": 0.5453508496284485,
"learning_rate": 4.066666666666667e-05,
"loss": 0.9842,
"step": 122
},
{
"epoch": 0.12418627941912869,
"grad_norm": 0.5353218913078308,
"learning_rate": 4.133333333333333e-05,
"loss": 1.1579,
"step": 124
},
{
"epoch": 0.12618928392588882,
"grad_norm": 0.617546021938324,
"learning_rate": 4.2e-05,
"loss": 1.0052,
"step": 126
},
{
"epoch": 0.12819228843264896,
"grad_norm": 0.48849716782569885,
"learning_rate": 4.266666666666667e-05,
"loss": 1.0416,
"step": 128
},
{
"epoch": 0.13019529293940912,
"grad_norm": 0.5549625754356384,
"learning_rate": 4.3333333333333334e-05,
"loss": 1.0562,
"step": 130
},
{
"epoch": 0.13219829744616926,
"grad_norm": 0.6010375618934631,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.046,
"step": 132
},
{
"epoch": 0.1342013019529294,
"grad_norm": 0.481374591588974,
"learning_rate": 4.466666666666667e-05,
"loss": 1.0136,
"step": 134
},
{
"epoch": 0.13620430645968953,
"grad_norm": 0.4886944591999054,
"learning_rate": 4.5333333333333335e-05,
"loss": 0.9658,
"step": 136
},
{
"epoch": 0.13820731096644967,
"grad_norm": 0.6117609739303589,
"learning_rate": 4.600000000000001e-05,
"loss": 1.0545,
"step": 138
},
{
"epoch": 0.1402103154732098,
"grad_norm": 0.5340180397033691,
"learning_rate": 4.666666666666667e-05,
"loss": 0.9826,
"step": 140
},
{
"epoch": 0.14221331997996994,
"grad_norm": 0.5061513781547546,
"learning_rate": 4.7333333333333336e-05,
"loss": 0.9832,
"step": 142
},
{
"epoch": 0.1442163244867301,
"grad_norm": 0.5090388059616089,
"learning_rate": 4.8e-05,
"loss": 0.9733,
"step": 144
},
{
"epoch": 0.14621932899349024,
"grad_norm": 0.5136658549308777,
"learning_rate": 4.866666666666667e-05,
"loss": 0.9673,
"step": 146
},
{
"epoch": 0.14822233350025038,
"grad_norm": 0.5653979778289795,
"learning_rate": 4.933333333333334e-05,
"loss": 0.9908,
"step": 148
},
{
"epoch": 0.15022533800701052,
"grad_norm": 0.5377776026725769,
"learning_rate": 5e-05,
"loss": 0.9428,
"step": 150
},
{
"epoch": 0.15022533800701052,
"eval_loss": 1.2466219663619995,
"eval_runtime": 3.7908,
"eval_samples_per_second": 15.3,
"eval_steps_per_second": 7.65,
"step": 150
},
{
"epoch": 0.15222834251377065,
"grad_norm": 0.5484976768493652,
"learning_rate": 4.9999728022003156e-05,
"loss": 0.9523,
"step": 152
},
{
"epoch": 0.1542313470205308,
"grad_norm": 0.4431094229221344,
"learning_rate": 4.999891209393037e-05,
"loss": 0.9937,
"step": 154
},
{
"epoch": 0.15623435152729093,
"grad_norm": 0.6066553592681885,
"learning_rate": 4.999755223353482e-05,
"loss": 1.0431,
"step": 156
},
{
"epoch": 0.15823735603405106,
"grad_norm": 0.6024964451789856,
"learning_rate": 4.9995648470404664e-05,
"loss": 0.9671,
"step": 158
},
{
"epoch": 0.16024036054081123,
"grad_norm": 0.486589640378952,
"learning_rate": 4.9993200845962434e-05,
"loss": 0.949,
"step": 160
},
{
"epoch": 0.16224336504757136,
"grad_norm": 0.505987823009491,
"learning_rate": 4.9990209413464136e-05,
"loss": 1.0444,
"step": 162
},
{
"epoch": 0.1642463695543315,
"grad_norm": 0.46255800127983093,
"learning_rate": 4.998667423799807e-05,
"loss": 0.971,
"step": 164
},
{
"epoch": 0.16624937406109164,
"grad_norm": 0.5792336463928223,
"learning_rate": 4.9982595396483435e-05,
"loss": 0.9869,
"step": 166
},
{
"epoch": 0.16825237856785177,
"grad_norm": 0.48192256689071655,
"learning_rate": 4.997797297766864e-05,
"loss": 1.0234,
"step": 168
},
{
"epoch": 0.1702553830746119,
"grad_norm": 0.5370559692382812,
"learning_rate": 4.997280708212939e-05,
"loss": 0.9721,
"step": 170
},
{
"epoch": 0.17225838758137205,
"grad_norm": 0.4554755985736847,
"learning_rate": 4.996709782226646e-05,
"loss": 0.9292,
"step": 172
},
{
"epoch": 0.1742613920881322,
"grad_norm": 0.4883841872215271,
"learning_rate": 4.9960845322303315e-05,
"loss": 0.9815,
"step": 174
},
{
"epoch": 0.17626439659489235,
"grad_norm": 0.5221249461174011,
"learning_rate": 4.995404971828333e-05,
"loss": 1.0216,
"step": 176
},
{
"epoch": 0.17826740110165248,
"grad_norm": 0.5130178332328796,
"learning_rate": 4.994671115806691e-05,
"loss": 0.9855,
"step": 178
},
{
"epoch": 0.18027040560841262,
"grad_norm": 0.46121644973754883,
"learning_rate": 4.993882980132819e-05,
"loss": 0.9196,
"step": 180
},
{
"epoch": 0.18227341011517276,
"grad_norm": 0.49680426716804504,
"learning_rate": 4.9930405819551627e-05,
"loss": 1.0151,
"step": 182
},
{
"epoch": 0.1842764146219329,
"grad_norm": 0.48591047525405884,
"learning_rate": 4.992143939602823e-05,
"loss": 0.9901,
"step": 184
},
{
"epoch": 0.18627941912869303,
"grad_norm": 0.47092878818511963,
"learning_rate": 4.9911930725851583e-05,
"loss": 0.9632,
"step": 186
},
{
"epoch": 0.18828242363545317,
"grad_norm": 0.40838295221328735,
"learning_rate": 4.990188001591363e-05,
"loss": 0.9469,
"step": 188
},
{
"epoch": 0.19028542814221333,
"grad_norm": 0.4728156626224518,
"learning_rate": 4.9891287484900124e-05,
"loss": 0.9667,
"step": 190
},
{
"epoch": 0.19228843264897347,
"grad_norm": 0.534322202205658,
"learning_rate": 4.988015336328589e-05,
"loss": 0.9982,
"step": 192
},
{
"epoch": 0.1942914371557336,
"grad_norm": 0.43927860260009766,
"learning_rate": 4.986847789332981e-05,
"loss": 0.9898,
"step": 194
},
{
"epoch": 0.19629444166249374,
"grad_norm": 0.40531125664711,
"learning_rate": 4.985626132906957e-05,
"loss": 0.9442,
"step": 196
},
{
"epoch": 0.19829744616925388,
"grad_norm": 0.5949648022651672,
"learning_rate": 4.9843503936316095e-05,
"loss": 1.0381,
"step": 198
},
{
"epoch": 0.200300450676014,
"grad_norm": 0.43230050802230835,
"learning_rate": 4.983020599264781e-05,
"loss": 1.0166,
"step": 200
},
{
"epoch": 0.200300450676014,
"eval_loss": 1.2184284925460815,
"eval_runtime": 3.8028,
"eval_samples_per_second": 15.252,
"eval_steps_per_second": 7.626,
"step": 200
},
{
"epoch": 0.20230345518277415,
"grad_norm": 0.4429769814014435,
"learning_rate": 4.9816367787404534e-05,
"loss": 0.9594,
"step": 202
},
{
"epoch": 0.20430645968953431,
"grad_norm": 0.5523216724395752,
"learning_rate": 4.980198962168128e-05,
"loss": 1.0446,
"step": 204
},
{
"epoch": 0.20630946419629445,
"grad_norm": 0.4551699459552765,
"learning_rate": 4.978707180832161e-05,
"loss": 0.9913,
"step": 206
},
{
"epoch": 0.2083124687030546,
"grad_norm": 0.41649895906448364,
"learning_rate": 4.977161467191089e-05,
"loss": 0.9163,
"step": 208
},
{
"epoch": 0.21031547320981472,
"grad_norm": 0.4184020459651947,
"learning_rate": 4.97556185487692e-05,
"loss": 0.9463,
"step": 210
},
{
"epoch": 0.21231847771657486,
"grad_norm": 0.6365268230438232,
"learning_rate": 4.9739083786944016e-05,
"loss": 0.9992,
"step": 212
},
{
"epoch": 0.214321482223335,
"grad_norm": 0.5223124027252197,
"learning_rate": 4.9722010746202664e-05,
"loss": 0.923,
"step": 214
},
{
"epoch": 0.21632448673009513,
"grad_norm": 0.42879560589790344,
"learning_rate": 4.970439979802445e-05,
"loss": 0.9788,
"step": 216
},
{
"epoch": 0.21832749123685527,
"grad_norm": 0.4171353578567505,
"learning_rate": 4.96862513255926e-05,
"loss": 1.0101,
"step": 218
},
{
"epoch": 0.22033049574361543,
"grad_norm": 0.42286214232444763,
"learning_rate": 4.966756572378593e-05,
"loss": 0.981,
"step": 220
},
{
"epoch": 0.22233350025037557,
"grad_norm": 0.6001223921775818,
"learning_rate": 4.964834339917025e-05,
"loss": 1.0276,
"step": 222
},
{
"epoch": 0.2243365047571357,
"grad_norm": 0.6153950095176697,
"learning_rate": 4.9628584769989504e-05,
"loss": 1.0437,
"step": 224
},
{
"epoch": 0.22633950926389584,
"grad_norm": 0.419117271900177,
"learning_rate": 4.9608290266156695e-05,
"loss": 1.0168,
"step": 226
},
{
"epoch": 0.22834251377065598,
"grad_norm": 0.40286022424697876,
"learning_rate": 4.958746032924448e-05,
"loss": 0.988,
"step": 228
},
{
"epoch": 0.23034551827741612,
"grad_norm": 0.5287054181098938,
"learning_rate": 4.9566095412475636e-05,
"loss": 1.019,
"step": 230
},
{
"epoch": 0.23234852278417625,
"grad_norm": 0.43865758180618286,
"learning_rate": 4.9544195980713136e-05,
"loss": 0.9563,
"step": 232
},
{
"epoch": 0.23435152729093642,
"grad_norm": 0.5529116988182068,
"learning_rate": 4.952176251045008e-05,
"loss": 0.9288,
"step": 234
},
{
"epoch": 0.23635453179769655,
"grad_norm": 0.5552803874015808,
"learning_rate": 4.9498795489799276e-05,
"loss": 0.8924,
"step": 236
},
{
"epoch": 0.2383575363044567,
"grad_norm": 0.722111165523529,
"learning_rate": 4.947529541848268e-05,
"loss": 0.9598,
"step": 238
},
{
"epoch": 0.24036054081121683,
"grad_norm": 0.4804269075393677,
"learning_rate": 4.9451262807820466e-05,
"loss": 0.9757,
"step": 240
},
{
"epoch": 0.24236354531797696,
"grad_norm": 0.5181965231895447,
"learning_rate": 4.942669818071994e-05,
"loss": 1.0138,
"step": 242
},
{
"epoch": 0.2443665498247371,
"grad_norm": 0.43212518095970154,
"learning_rate": 4.9401602071664155e-05,
"loss": 0.9027,
"step": 244
},
{
"epoch": 0.24636955433149724,
"grad_norm": 0.5169520974159241,
"learning_rate": 4.937597502670027e-05,
"loss": 0.9668,
"step": 246
},
{
"epoch": 0.24837255883825737,
"grad_norm": 0.4116087555885315,
"learning_rate": 4.934981760342766e-05,
"loss": 0.9634,
"step": 248
},
{
"epoch": 0.25037556334501754,
"grad_norm": 0.5354374647140503,
"learning_rate": 4.932313037098582e-05,
"loss": 0.9993,
"step": 250
},
{
"epoch": 0.25037556334501754,
"eval_loss": 1.207343339920044,
"eval_runtime": 3.8101,
"eval_samples_per_second": 15.223,
"eval_steps_per_second": 7.611,
"step": 250
},
{
"epoch": 0.25237856785177765,
"grad_norm": 0.5648212432861328,
"learning_rate": 4.929591391004196e-05,
"loss": 1.0219,
"step": 252
},
{
"epoch": 0.2543815723585378,
"grad_norm": 0.6550512909889221,
"learning_rate": 4.926816881277834e-05,
"loss": 0.9505,
"step": 254
},
{
"epoch": 0.2563845768652979,
"grad_norm": 0.4034920334815979,
"learning_rate": 4.923989568287946e-05,
"loss": 0.929,
"step": 256
},
{
"epoch": 0.2583875813720581,
"grad_norm": 0.475777804851532,
"learning_rate": 4.921109513551885e-05,
"loss": 0.9811,
"step": 258
},
{
"epoch": 0.26039058587881825,
"grad_norm": 0.47418224811553955,
"learning_rate": 4.9181767797345724e-05,
"loss": 1.0354,
"step": 260
},
{
"epoch": 0.26239359038557836,
"grad_norm": 0.5102671384811401,
"learning_rate": 4.9151914306471345e-05,
"loss": 1.0212,
"step": 262
},
{
"epoch": 0.2643965948923385,
"grad_norm": 0.4163782298564911,
"learning_rate": 4.912153531245511e-05,
"loss": 0.9191,
"step": 264
},
{
"epoch": 0.26639959939909863,
"grad_norm": 0.5019692182540894,
"learning_rate": 4.909063147629046e-05,
"loss": 0.9337,
"step": 266
},
{
"epoch": 0.2684026039058588,
"grad_norm": 0.5193113088607788,
"learning_rate": 4.905920347039048e-05,
"loss": 0.9746,
"step": 268
},
{
"epoch": 0.2704056084126189,
"grad_norm": 0.4991247355937958,
"learning_rate": 4.9027251978573244e-05,
"loss": 0.9568,
"step": 270
},
{
"epoch": 0.27240861291937907,
"grad_norm": 0.3833785951137543,
"learning_rate": 4.8994777696046984e-05,
"loss": 0.9621,
"step": 272
},
{
"epoch": 0.27441161742613923,
"grad_norm": 0.5187920331954956,
"learning_rate": 4.8961781329394915e-05,
"loss": 0.9393,
"step": 274
},
{
"epoch": 0.27641462193289934,
"grad_norm": 0.6128193736076355,
"learning_rate": 4.89282635965599e-05,
"loss": 0.9734,
"step": 276
},
{
"epoch": 0.2784176264396595,
"grad_norm": 0.47504886984825134,
"learning_rate": 4.8894225226828795e-05,
"loss": 0.9592,
"step": 278
},
{
"epoch": 0.2804206309464196,
"grad_norm": 0.44938042759895325,
"learning_rate": 4.885966696081663e-05,
"loss": 0.9999,
"step": 280
},
{
"epoch": 0.2824236354531798,
"grad_norm": 0.48498111963272095,
"learning_rate": 4.8824589550450415e-05,
"loss": 0.9597,
"step": 282
},
{
"epoch": 0.2844266399599399,
"grad_norm": 0.582253098487854,
"learning_rate": 4.8788993758952875e-05,
"loss": 0.9322,
"step": 284
},
{
"epoch": 0.28642964446670005,
"grad_norm": 0.5211949944496155,
"learning_rate": 4.875288036082577e-05,
"loss": 0.9913,
"step": 286
},
{
"epoch": 0.2884326489734602,
"grad_norm": 0.5122332572937012,
"learning_rate": 4.8716250141833075e-05,
"loss": 0.92,
"step": 288
},
{
"epoch": 0.2904356534802203,
"grad_norm": 0.509671151638031,
"learning_rate": 4.867910389898387e-05,
"loss": 0.9686,
"step": 290
},
{
"epoch": 0.2924386579869805,
"grad_norm": 0.42992913722991943,
"learning_rate": 4.864144244051503e-05,
"loss": 0.8937,
"step": 292
},
{
"epoch": 0.2944416624937406,
"grad_norm": 0.558230996131897,
"learning_rate": 4.860326658587358e-05,
"loss": 1.005,
"step": 294
},
{
"epoch": 0.29644466700050076,
"grad_norm": 0.3904726505279541,
"learning_rate": 4.856457716569891e-05,
"loss": 0.9927,
"step": 296
},
{
"epoch": 0.29844767150726087,
"grad_norm": 0.377273827791214,
"learning_rate": 4.852537502180473e-05,
"loss": 0.9042,
"step": 298
},
{
"epoch": 0.30045067601402103,
"grad_norm": 0.4523603320121765,
"learning_rate": 4.848566100716066e-05,
"loss": 0.978,
"step": 300
},
{
"epoch": 0.30045067601402103,
"eval_loss": 1.191455602645874,
"eval_runtime": 3.8019,
"eval_samples_per_second": 15.256,
"eval_steps_per_second": 7.628,
"step": 300
},
{
"epoch": 0.3024536805207812,
"grad_norm": 0.39940956234931946,
"learning_rate": 4.8445435985873775e-05,
"loss": 1.0145,
"step": 302
},
{
"epoch": 0.3044566850275413,
"grad_norm": 0.42715466022491455,
"learning_rate": 4.84047008331697e-05,
"loss": 0.9933,
"step": 304
},
{
"epoch": 0.30645968953430147,
"grad_norm": 0.5550795793533325,
"learning_rate": 4.8363456435373686e-05,
"loss": 0.8994,
"step": 306
},
{
"epoch": 0.3084626940410616,
"grad_norm": 0.50642329454422,
"learning_rate": 4.832170368989121e-05,
"loss": 0.9708,
"step": 308
},
{
"epoch": 0.31046569854782174,
"grad_norm": 0.4395250976085663,
"learning_rate": 4.827944350518852e-05,
"loss": 1.055,
"step": 310
},
{
"epoch": 0.31246870305458185,
"grad_norm": 0.40183037519454956,
"learning_rate": 4.8236676800772845e-05,
"loss": 0.9564,
"step": 312
},
{
"epoch": 0.314471707561342,
"grad_norm": 0.4325483441352844,
"learning_rate": 4.8193404507172405e-05,
"loss": 0.9437,
"step": 314
},
{
"epoch": 0.3164747120681021,
"grad_norm": 0.5079526305198669,
"learning_rate": 4.814962756591612e-05,
"loss": 0.9426,
"step": 316
},
{
"epoch": 0.3184777165748623,
"grad_norm": 0.6221234202384949,
"learning_rate": 4.8105346929513195e-05,
"loss": 0.9674,
"step": 318
},
{
"epoch": 0.32048072108162245,
"grad_norm": 0.5088761448860168,
"learning_rate": 4.8060563561432313e-05,
"loss": 0.953,
"step": 320
},
{
"epoch": 0.32248372558838256,
"grad_norm": 0.4460401237010956,
"learning_rate": 4.801527843608075e-05,
"loss": 0.935,
"step": 322
},
{
"epoch": 0.32448673009514273,
"grad_norm": 0.39005428552627563,
"learning_rate": 4.796949253878311e-05,
"loss": 0.9204,
"step": 324
},
{
"epoch": 0.32648973460190284,
"grad_norm": 0.4077945351600647,
"learning_rate": 4.792320686575993e-05,
"loss": 1.0509,
"step": 326
},
{
"epoch": 0.328492739108663,
"grad_norm": 0.4249040186405182,
"learning_rate": 4.787642242410597e-05,
"loss": 0.9549,
"step": 328
},
{
"epoch": 0.3304957436154231,
"grad_norm": 0.4203990697860718,
"learning_rate": 4.7829140231768335e-05,
"loss": 0.9996,
"step": 330
},
{
"epoch": 0.3324987481221833,
"grad_norm": 0.4657137095928192,
"learning_rate": 4.778136131752431e-05,
"loss": 1.0336,
"step": 332
},
{
"epoch": 0.33450175262894344,
"grad_norm": 0.4463610053062439,
"learning_rate": 4.773308672095895e-05,
"loss": 0.936,
"step": 334
},
{
"epoch": 0.33650475713570355,
"grad_norm": 0.46322551369667053,
"learning_rate": 4.768431749244251e-05,
"loss": 0.8727,
"step": 336
},
{
"epoch": 0.3385077616424637,
"grad_norm": 0.4579392671585083,
"learning_rate": 4.7635054693107553e-05,
"loss": 0.9551,
"step": 338
},
{
"epoch": 0.3405107661492238,
"grad_norm": 0.40763622522354126,
"learning_rate": 4.758529939482588e-05,
"loss": 0.8965,
"step": 340
},
{
"epoch": 0.342513770655984,
"grad_norm": 0.5640069246292114,
"learning_rate": 4.75350526801852e-05,
"loss": 1.019,
"step": 342
},
{
"epoch": 0.3445167751627441,
"grad_norm": 0.378750741481781,
"learning_rate": 4.748431564246557e-05,
"loss": 0.974,
"step": 344
},
{
"epoch": 0.34651977966950426,
"grad_norm": 0.5434790849685669,
"learning_rate": 4.7433089385615634e-05,
"loss": 0.9863,
"step": 346
},
{
"epoch": 0.3485227841762644,
"grad_norm": 0.5737304091453552,
"learning_rate": 4.7381375024228556e-05,
"loss": 0.9044,
"step": 348
},
{
"epoch": 0.35052578868302453,
"grad_norm": 0.5187863707542419,
"learning_rate": 4.7329173683517825e-05,
"loss": 0.8692,
"step": 350
},
{
"epoch": 0.35052578868302453,
"eval_loss": 1.1893218755722046,
"eval_runtime": 3.7963,
"eval_samples_per_second": 15.278,
"eval_steps_per_second": 7.639,
"step": 350
},
{
"epoch": 0.3525287931897847,
"grad_norm": 0.417603462934494,
"learning_rate": 4.727648649929271e-05,
"loss": 0.9013,
"step": 352
},
{
"epoch": 0.3545317976965448,
"grad_norm": 0.5028386116027832,
"learning_rate": 4.7223314617933605e-05,
"loss": 0.9508,
"step": 354
},
{
"epoch": 0.35653480220330497,
"grad_norm": 0.3822748064994812,
"learning_rate": 4.7169659196367056e-05,
"loss": 0.9452,
"step": 356
},
{
"epoch": 0.3585378067100651,
"grad_norm": 0.44049903750419617,
"learning_rate": 4.711552140204059e-05,
"loss": 0.9455,
"step": 358
},
{
"epoch": 0.36054081121682524,
"grad_norm": 0.45998480916023254,
"learning_rate": 4.7060902412897304e-05,
"loss": 0.9731,
"step": 360
},
{
"epoch": 0.3625438157235854,
"grad_norm": 0.5747750401496887,
"learning_rate": 4.700580341735026e-05,
"loss": 0.9197,
"step": 362
},
{
"epoch": 0.3645468202303455,
"grad_norm": 0.39996007084846497,
"learning_rate": 4.695022561425663e-05,
"loss": 0.9464,
"step": 364
},
{
"epoch": 0.3665498247371057,
"grad_norm": 0.4300011396408081,
"learning_rate": 4.689417021289157e-05,
"loss": 0.8947,
"step": 366
},
{
"epoch": 0.3685528292438658,
"grad_norm": 0.38185784220695496,
"learning_rate": 4.6837638432921925e-05,
"loss": 0.9521,
"step": 368
},
{
"epoch": 0.37055583375062595,
"grad_norm": 0.48808950185775757,
"learning_rate": 4.6780631504379736e-05,
"loss": 0.9326,
"step": 370
},
{
"epoch": 0.37255883825738606,
"grad_norm": 0.40927746891975403,
"learning_rate": 4.672315066763542e-05,
"loss": 0.9949,
"step": 372
},
{
"epoch": 0.3745618427641462,
"grad_norm": 0.473628968000412,
"learning_rate": 4.666519717337079e-05,
"loss": 0.9808,
"step": 374
},
{
"epoch": 0.37656484727090633,
"grad_norm": 0.45377451181411743,
"learning_rate": 4.6606772282551894e-05,
"loss": 0.9978,
"step": 376
},
{
"epoch": 0.3785678517776665,
"grad_norm": 0.5329418182373047,
"learning_rate": 4.65478772664015e-05,
"loss": 0.9531,
"step": 378
},
{
"epoch": 0.38057085628442666,
"grad_norm": 0.4209918677806854,
"learning_rate": 4.648851340637147e-05,
"loss": 0.914,
"step": 380
},
{
"epoch": 0.38257386079118677,
"grad_norm": 0.40193280577659607,
"learning_rate": 4.642868199411493e-05,
"loss": 0.8853,
"step": 382
},
{
"epoch": 0.38457686529794693,
"grad_norm": 0.39280131459236145,
"learning_rate": 4.6368384331458085e-05,
"loss": 0.8992,
"step": 384
},
{
"epoch": 0.38657986980470704,
"grad_norm": 0.44302472472190857,
"learning_rate": 4.6307621730371934e-05,
"loss": 0.9454,
"step": 386
},
{
"epoch": 0.3885828743114672,
"grad_norm": 0.4578077793121338,
"learning_rate": 4.6246395512943716e-05,
"loss": 0.957,
"step": 388
},
{
"epoch": 0.3905858788182273,
"grad_norm": 0.4635055959224701,
"learning_rate": 4.618470701134815e-05,
"loss": 0.9978,
"step": 390
},
{
"epoch": 0.3925888833249875,
"grad_norm": 0.49186405539512634,
"learning_rate": 4.612255756781845e-05,
"loss": 0.9792,
"step": 392
},
{
"epoch": 0.39459188783174765,
"grad_norm": 0.42530110478401184,
"learning_rate": 4.605994853461709e-05,
"loss": 1.0054,
"step": 394
},
{
"epoch": 0.39659489233850775,
"grad_norm": 0.4250572919845581,
"learning_rate": 4.5996881274006446e-05,
"loss": 0.8744,
"step": 396
},
{
"epoch": 0.3985978968452679,
"grad_norm": 0.4212440550327301,
"learning_rate": 4.593335715821909e-05,
"loss": 0.9451,
"step": 398
},
{
"epoch": 0.400600901352028,
"grad_norm": 0.35784921050071716,
"learning_rate": 4.586937756942796e-05,
"loss": 0.9179,
"step": 400
},
{
"epoch": 0.400600901352028,
"eval_loss": 1.1884177923202515,
"eval_runtime": 3.8058,
"eval_samples_per_second": 15.24,
"eval_steps_per_second": 7.62,
"step": 400
},
{
"epoch": 0.4026039058587882,
"grad_norm": 0.4087256193161011,
"learning_rate": 4.580494389971628e-05,
"loss": 0.8817,
"step": 402
},
{
"epoch": 0.4046069103655483,
"grad_norm": 0.40662136673927307,
"learning_rate": 4.5740057551047294e-05,
"loss": 0.9219,
"step": 404
},
{
"epoch": 0.40660991487230846,
"grad_norm": 0.4162129759788513,
"learning_rate": 4.5674719935233726e-05,
"loss": 0.8831,
"step": 406
},
{
"epoch": 0.40861291937906863,
"grad_norm": 0.40978914499282837,
"learning_rate": 4.56089324739071e-05,
"loss": 0.9601,
"step": 408
},
{
"epoch": 0.41061592388582874,
"grad_norm": 0.42754805088043213,
"learning_rate": 4.554269659848675e-05,
"loss": 0.9463,
"step": 410
},
{
"epoch": 0.4126189283925889,
"grad_norm": 0.48228365182876587,
"learning_rate": 4.547601375014875e-05,
"loss": 0.9418,
"step": 412
},
{
"epoch": 0.414621932899349,
"grad_norm": 0.4946666657924652,
"learning_rate": 4.5408885379794494e-05,
"loss": 0.9011,
"step": 414
},
{
"epoch": 0.4166249374061092,
"grad_norm": 0.4881949722766876,
"learning_rate": 4.5341312948019155e-05,
"loss": 0.9794,
"step": 416
},
{
"epoch": 0.4186279419128693,
"grad_norm": 0.39862060546875,
"learning_rate": 4.527329792507991e-05,
"loss": 0.9116,
"step": 418
},
{
"epoch": 0.42063094641962945,
"grad_norm": 0.3882657587528229,
"learning_rate": 4.520484179086394e-05,
"loss": 0.9337,
"step": 420
},
{
"epoch": 0.42263395092638956,
"grad_norm": 0.3756396770477295,
"learning_rate": 4.51359460348562e-05,
"loss": 0.9272,
"step": 422
},
{
"epoch": 0.4246369554331497,
"grad_norm": 0.451297402381897,
"learning_rate": 4.50666121561071e-05,
"loss": 0.9306,
"step": 424
},
{
"epoch": 0.4266399599399099,
"grad_norm": 0.41500887274742126,
"learning_rate": 4.499684166319978e-05,
"loss": 0.9472,
"step": 426
},
{
"epoch": 0.42864296444667,
"grad_norm": 0.4838218688964844,
"learning_rate": 4.492663607421736e-05,
"loss": 0.8738,
"step": 428
},
{
"epoch": 0.43064596895343016,
"grad_norm": 0.3867829442024231,
"learning_rate": 4.4855996916709865e-05,
"loss": 1.0112,
"step": 430
},
{
"epoch": 0.43264897346019027,
"grad_norm": 0.40715524554252625,
"learning_rate": 4.478492572766102e-05,
"loss": 0.9571,
"step": 432
},
{
"epoch": 0.43465197796695043,
"grad_norm": 0.5042704343795776,
"learning_rate": 4.47134240534548e-05,
"loss": 0.9304,
"step": 434
},
{
"epoch": 0.43665498247371054,
"grad_norm": 0.4030342400074005,
"learning_rate": 4.464149344984178e-05,
"loss": 0.9479,
"step": 436
},
{
"epoch": 0.4386579869804707,
"grad_norm": 0.3429213762283325,
"learning_rate": 4.456913548190527e-05,
"loss": 0.9511,
"step": 438
},
{
"epoch": 0.44066099148723087,
"grad_norm": 0.4278419315814972,
"learning_rate": 4.44963517240273e-05,
"loss": 1.1125,
"step": 440
},
{
"epoch": 0.442663995993991,
"grad_norm": 0.4170474708080292,
"learning_rate": 4.44231437598543e-05,
"loss": 0.9498,
"step": 442
},
{
"epoch": 0.44466700050075114,
"grad_norm": 0.39053234457969666,
"learning_rate": 4.4349513182262715e-05,
"loss": 0.9796,
"step": 444
},
{
"epoch": 0.44667000500751125,
"grad_norm": 0.5083168148994446,
"learning_rate": 4.4275461593324306e-05,
"loss": 0.9236,
"step": 446
},
{
"epoch": 0.4486730095142714,
"grad_norm": 0.3927271068096161,
"learning_rate": 4.420099060427131e-05,
"loss": 1.011,
"step": 448
},
{
"epoch": 0.4506760140210315,
"grad_norm": 0.4185622036457062,
"learning_rate": 4.4126101835461346e-05,
"loss": 0.9671,
"step": 450
},
{
"epoch": 0.4506760140210315,
"eval_loss": 1.1852179765701294,
"eval_runtime": 3.8121,
"eval_samples_per_second": 15.215,
"eval_steps_per_second": 7.607,
"step": 450
},
{
"epoch": 0.4526790185277917,
"grad_norm": 0.5305806398391724,
"learning_rate": 4.405079691634221e-05,
"loss": 0.9388,
"step": 452
},
{
"epoch": 0.45468202303455185,
"grad_norm": 0.4585268497467041,
"learning_rate": 4.3975077485416377e-05,
"loss": 0.8841,
"step": 454
},
{
"epoch": 0.45668502754131196,
"grad_norm": 0.39412179589271545,
"learning_rate": 4.3898945190205386e-05,
"loss": 0.9371,
"step": 456
},
{
"epoch": 0.4586880320480721,
"grad_norm": 0.5423275828361511,
"learning_rate": 4.382240168721396e-05,
"loss": 0.9923,
"step": 458
},
{
"epoch": 0.46069103655483223,
"grad_norm": 0.3563918471336365,
"learning_rate": 4.3745448641894e-05,
"loss": 0.9546,
"step": 460
},
{
"epoch": 0.4626940410615924,
"grad_norm": 0.7710307836532593,
"learning_rate": 4.3668087728608316e-05,
"loss": 0.9195,
"step": 462
},
{
"epoch": 0.4646970455683525,
"grad_norm": 0.4273247718811035,
"learning_rate": 4.359032063059419e-05,
"loss": 0.9674,
"step": 464
},
{
"epoch": 0.46670005007511267,
"grad_norm": 0.41480231285095215,
"learning_rate": 4.3512149039926796e-05,
"loss": 0.8851,
"step": 466
},
{
"epoch": 0.46870305458187284,
"grad_norm": 0.559946596622467,
"learning_rate": 4.343357465748235e-05,
"loss": 0.8949,
"step": 468
},
{
"epoch": 0.47070605908863294,
"grad_norm": 0.5360729098320007,
"learning_rate": 4.33545991929011e-05,
"loss": 0.9014,
"step": 470
},
{
"epoch": 0.4727090635953931,
"grad_norm": 0.5606299042701721,
"learning_rate": 4.327522436455013e-05,
"loss": 0.9091,
"step": 472
},
{
"epoch": 0.4747120681021532,
"grad_norm": 0.49291422963142395,
"learning_rate": 4.3195451899485994e-05,
"loss": 0.9076,
"step": 474
},
{
"epoch": 0.4767150726089134,
"grad_norm": 0.3711169958114624,
"learning_rate": 4.3115283533417105e-05,
"loss": 0.9644,
"step": 476
},
{
"epoch": 0.4787180771156735,
"grad_norm": 0.4362380802631378,
"learning_rate": 4.3034721010666e-05,
"loss": 0.9263,
"step": 478
},
{
"epoch": 0.48072108162243365,
"grad_norm": 0.5104102492332458,
"learning_rate": 4.295376608413137e-05,
"loss": 0.96,
"step": 480
},
{
"epoch": 0.48272408612919376,
"grad_norm": 0.4157417416572571,
"learning_rate": 4.287242051524989e-05,
"loss": 0.9594,
"step": 482
},
{
"epoch": 0.4847270906359539,
"grad_norm": 0.36849111318588257,
"learning_rate": 4.2790686073957976e-05,
"loss": 0.8976,
"step": 484
},
{
"epoch": 0.4867300951427141,
"grad_norm": 0.6290056109428406,
"learning_rate": 4.270856453865318e-05,
"loss": 0.9248,
"step": 486
},
{
"epoch": 0.4887330996494742,
"grad_norm": 0.4833918511867523,
"learning_rate": 4.262605769615557e-05,
"loss": 1.0118,
"step": 488
},
{
"epoch": 0.49073610415623437,
"grad_norm": 0.6724058985710144,
"learning_rate": 4.25431673416688e-05,
"loss": 0.8823,
"step": 490
},
{
"epoch": 0.4927391086629945,
"grad_norm": 0.45951318740844727,
"learning_rate": 4.245989527874107e-05,
"loss": 0.9822,
"step": 492
},
{
"epoch": 0.49474211316975464,
"grad_norm": 0.4734819829463959,
"learning_rate": 4.237624331922589e-05,
"loss": 0.9181,
"step": 494
},
{
"epoch": 0.49674511767651475,
"grad_norm": 0.9102823138237,
"learning_rate": 4.229221328324265e-05,
"loss": 0.8974,
"step": 496
},
{
"epoch": 0.4987481221832749,
"grad_norm": 0.35548609495162964,
"learning_rate": 4.2207806999137035e-05,
"loss": 0.9309,
"step": 498
},
{
"epoch": 0.5007511266900351,
"grad_norm": 0.46587055921554565,
"learning_rate": 4.21230263034412e-05,
"loss": 0.9114,
"step": 500
},
{
"epoch": 0.5007511266900351,
"eval_loss": 1.174551248550415,
"eval_runtime": 3.8166,
"eval_samples_per_second": 15.197,
"eval_steps_per_second": 7.598,
"step": 500
},
{
"epoch": 0.5027541311967952,
"grad_norm": 0.3687826097011566,
"learning_rate": 4.2037873040833845e-05,
"loss": 0.9322,
"step": 502
},
{
"epoch": 0.5047571357035553,
"grad_norm": 0.5049874782562256,
"learning_rate": 4.1952349064100074e-05,
"loss": 0.9975,
"step": 504
},
{
"epoch": 0.5067601402103155,
"grad_norm": 0.4126236140727997,
"learning_rate": 4.1866456234091076e-05,
"loss": 0.929,
"step": 506
},
{
"epoch": 0.5087631447170756,
"grad_norm": 0.44455772638320923,
"learning_rate": 4.178019641968364e-05,
"loss": 0.9345,
"step": 508
},
{
"epoch": 0.5107661492238358,
"grad_norm": 0.4278281033039093,
"learning_rate": 4.1693571497739495e-05,
"loss": 0.8941,
"step": 510
},
{
"epoch": 0.5127691537305958,
"grad_norm": 0.3606776297092438,
"learning_rate": 4.160658335306446e-05,
"loss": 0.9442,
"step": 512
},
{
"epoch": 0.514772158237356,
"grad_norm": 0.5303627848625183,
"learning_rate": 4.1519233878367424e-05,
"loss": 0.8712,
"step": 514
},
{
"epoch": 0.5167751627441162,
"grad_norm": 0.3978877067565918,
"learning_rate": 4.143152497421922e-05,
"loss": 0.8558,
"step": 516
},
{
"epoch": 0.5187781672508763,
"grad_norm": 0.68426513671875,
"learning_rate": 4.134345854901121e-05,
"loss": 0.9229,
"step": 518
},
{
"epoch": 0.5207811717576365,
"grad_norm": 0.5070856809616089,
"learning_rate": 4.125503651891377e-05,
"loss": 0.8383,
"step": 520
},
{
"epoch": 0.5227841762643965,
"grad_norm": 0.5237690806388855,
"learning_rate": 4.1166260807834644e-05,
"loss": 0.8836,
"step": 522
},
{
"epoch": 0.5247871807711567,
"grad_norm": 0.38217777013778687,
"learning_rate": 4.107713334737704e-05,
"loss": 0.953,
"step": 524
},
{
"epoch": 0.5267901852779169,
"grad_norm": 0.4001261591911316,
"learning_rate": 4.098765607679761e-05,
"loss": 0.9681,
"step": 526
},
{
"epoch": 0.528793189784677,
"grad_norm": 0.4185451567173004,
"learning_rate": 4.0897830942964255e-05,
"loss": 0.9023,
"step": 528
},
{
"epoch": 0.5307961942914372,
"grad_norm": 0.4268343150615692,
"learning_rate": 4.080765990031377e-05,
"loss": 0.9154,
"step": 530
},
{
"epoch": 0.5327991987981973,
"grad_norm": 0.46939241886138916,
"learning_rate": 4.071714491080932e-05,
"loss": 0.9013,
"step": 532
},
{
"epoch": 0.5348022033049574,
"grad_norm": 0.3804875910282135,
"learning_rate": 4.0626287943897764e-05,
"loss": 0.9091,
"step": 534
},
{
"epoch": 0.5368052078117176,
"grad_norm": 0.5679438710212708,
"learning_rate": 4.053509097646674e-05,
"loss": 0.9361,
"step": 536
},
{
"epoch": 0.5388082123184778,
"grad_norm": 0.47385266423225403,
"learning_rate": 4.044355599280175e-05,
"loss": 0.9549,
"step": 538
},
{
"epoch": 0.5408112168252378,
"grad_norm": 0.48675286769866943,
"learning_rate": 4.035168498454292e-05,
"loss": 0.8835,
"step": 540
},
{
"epoch": 0.542814221331998,
"grad_norm": 0.46679016947746277,
"learning_rate": 4.025947995064166e-05,
"loss": 0.9377,
"step": 542
},
{
"epoch": 0.5448172258387581,
"grad_norm": 0.4926673471927643,
"learning_rate": 4.0166942897317205e-05,
"loss": 0.9036,
"step": 544
},
{
"epoch": 0.5468202303455183,
"grad_norm": 0.38182321190834045,
"learning_rate": 4.007407583801295e-05,
"loss": 0.9616,
"step": 546
},
{
"epoch": 0.5488232348522785,
"grad_norm": 0.45545268058776855,
"learning_rate": 3.9980880793352635e-05,
"loss": 0.9747,
"step": 548
},
{
"epoch": 0.5508262393590385,
"grad_norm": 0.47782036662101746,
"learning_rate": 3.988735979109638e-05,
"loss": 0.8995,
"step": 550
},
{
"epoch": 0.5508262393590385,
"eval_loss": 1.1662517786026,
"eval_runtime": 3.8013,
"eval_samples_per_second": 15.258,
"eval_steps_per_second": 7.629,
"step": 550
},
{
"epoch": 0.5528292438657987,
"grad_norm": 0.5856130123138428,
"learning_rate": 3.979351486609658e-05,
"loss": 0.8887,
"step": 552
},
{
"epoch": 0.5548322483725588,
"grad_norm": 0.3920418620109558,
"learning_rate": 3.969934806025361e-05,
"loss": 0.8773,
"step": 554
},
{
"epoch": 0.556835252879319,
"grad_norm": 0.43775448203086853,
"learning_rate": 3.960486142247142e-05,
"loss": 0.8969,
"step": 556
},
{
"epoch": 0.5588382573860792,
"grad_norm": 0.42693212628364563,
"learning_rate": 3.951005700861291e-05,
"loss": 0.9114,
"step": 558
},
{
"epoch": 0.5608412618928392,
"grad_norm": 0.45931047201156616,
"learning_rate": 3.9414936881455254e-05,
"loss": 0.9111,
"step": 560
},
{
"epoch": 0.5628442663995994,
"grad_norm": 0.5036295652389526,
"learning_rate": 3.931950311064498e-05,
"loss": 0.9606,
"step": 562
},
{
"epoch": 0.5648472709063596,
"grad_norm": 0.5762202143669128,
"learning_rate": 3.9223757772652956e-05,
"loss": 0.8566,
"step": 564
},
{
"epoch": 0.5668502754131197,
"grad_norm": 0.40658578276634216,
"learning_rate": 3.91277029507292e-05,
"loss": 0.9485,
"step": 566
},
{
"epoch": 0.5688532799198798,
"grad_norm": 0.3851291835308075,
"learning_rate": 3.903134073485756e-05,
"loss": 0.8902,
"step": 568
},
{
"epoch": 0.5708562844266399,
"grad_norm": 0.3543303906917572,
"learning_rate": 3.8934673221710215e-05,
"loss": 0.9411,
"step": 570
},
{
"epoch": 0.5728592889334001,
"grad_norm": 0.3977811336517334,
"learning_rate": 3.883770251460212e-05,
"loss": 0.9258,
"step": 572
},
{
"epoch": 0.5748622934401603,
"grad_norm": 0.4081217050552368,
"learning_rate": 3.8740430723445156e-05,
"loss": 0.9201,
"step": 574
},
{
"epoch": 0.5768652979469204,
"grad_norm": 0.4058239459991455,
"learning_rate": 3.864285996470226e-05,
"loss": 0.9428,
"step": 576
},
{
"epoch": 0.5788683024536805,
"grad_norm": 0.40673911571502686,
"learning_rate": 3.854499236134141e-05,
"loss": 0.985,
"step": 578
},
{
"epoch": 0.5808713069604406,
"grad_norm": 0.4199845790863037,
"learning_rate": 3.844683004278939e-05,
"loss": 0.9476,
"step": 580
},
{
"epoch": 0.5828743114672008,
"grad_norm": 0.4016932547092438,
"learning_rate": 3.834837514488544e-05,
"loss": 0.9464,
"step": 582
},
{
"epoch": 0.584877315973961,
"grad_norm": 0.41921266913414,
"learning_rate": 3.8249629809834845e-05,
"loss": 0.9651,
"step": 584
},
{
"epoch": 0.586880320480721,
"grad_norm": 0.4465863108634949,
"learning_rate": 3.8150596186162286e-05,
"loss": 0.8847,
"step": 586
},
{
"epoch": 0.5888833249874812,
"grad_norm": 0.4515509009361267,
"learning_rate": 3.805127642866507e-05,
"loss": 0.951,
"step": 588
},
{
"epoch": 0.5908863294942414,
"grad_norm": 0.44146063923835754,
"learning_rate": 3.795167269836631e-05,
"loss": 0.8924,
"step": 590
},
{
"epoch": 0.5928893340010015,
"grad_norm": 0.538754940032959,
"learning_rate": 3.785178716246786e-05,
"loss": 0.9536,
"step": 592
},
{
"epoch": 0.5948923385077617,
"grad_norm": 0.3271295130252838,
"learning_rate": 3.775162199430312e-05,
"loss": 0.8724,
"step": 594
},
{
"epoch": 0.5968953430145217,
"grad_norm": 0.4394945800304413,
"learning_rate": 3.765117937328986e-05,
"loss": 0.9133,
"step": 596
},
{
"epoch": 0.5988983475212819,
"grad_norm": 0.40261757373809814,
"learning_rate": 3.75504614848827e-05,
"loss": 0.9253,
"step": 598
},
{
"epoch": 0.6009013520280421,
"grad_norm": 0.4515800178050995,
"learning_rate": 3.744947052052562e-05,
"loss": 0.918,
"step": 600
},
{
"epoch": 0.6009013520280421,
"eval_loss": 1.1564297676086426,
"eval_runtime": 3.8109,
"eval_samples_per_second": 15.219,
"eval_steps_per_second": 7.61,
"step": 600
},
{
"epoch": 0.6029043565348022,
"grad_norm": 0.4420590400695801,
"learning_rate": 3.734820867760421e-05,
"loss": 0.8758,
"step": 602
},
{
"epoch": 0.6049073610415624,
"grad_norm": 0.41104549169540405,
"learning_rate": 3.724667815939794e-05,
"loss": 1.0595,
"step": 604
},
{
"epoch": 0.6069103655483225,
"grad_norm": 0.4642109274864197,
"learning_rate": 3.7144881175032174e-05,
"loss": 0.9576,
"step": 606
},
{
"epoch": 0.6089133700550826,
"grad_norm": 0.4654678404331207,
"learning_rate": 3.704281993943008e-05,
"loss": 0.9196,
"step": 608
},
{
"epoch": 0.6109163745618428,
"grad_norm": 0.44470739364624023,
"learning_rate": 3.694049667326451e-05,
"loss": 0.9326,
"step": 610
},
{
"epoch": 0.6129193790686029,
"grad_norm": 0.4389815330505371,
"learning_rate": 3.683791360290961e-05,
"loss": 0.9633,
"step": 612
},
{
"epoch": 0.614922383575363,
"grad_norm": 0.366268515586853,
"learning_rate": 3.673507296039243e-05,
"loss": 0.9876,
"step": 614
},
{
"epoch": 0.6169253880821232,
"grad_norm": 0.40563082695007324,
"learning_rate": 3.663197698334432e-05,
"loss": 0.8903,
"step": 616
},
{
"epoch": 0.6189283925888833,
"grad_norm": 0.35876786708831787,
"learning_rate": 3.6528627914952266e-05,
"loss": 0.9025,
"step": 618
},
{
"epoch": 0.6209313970956435,
"grad_norm": 0.44777098298072815,
"learning_rate": 3.6425028003910074e-05,
"loss": 0.9048,
"step": 620
},
{
"epoch": 0.6229344016024037,
"grad_norm": 0.40352246165275574,
"learning_rate": 3.6321179504369444e-05,
"loss": 0.9176,
"step": 622
},
{
"epoch": 0.6249374061091637,
"grad_norm": 0.4628620445728302,
"learning_rate": 3.6217084675890935e-05,
"loss": 0.9208,
"step": 624
},
{
"epoch": 0.6269404106159239,
"grad_norm": 0.45699334144592285,
"learning_rate": 3.611274578339477e-05,
"loss": 0.9284,
"step": 626
},
{
"epoch": 0.628943415122684,
"grad_norm": 0.45050838589668274,
"learning_rate": 3.60081650971116e-05,
"loss": 0.9417,
"step": 628
},
{
"epoch": 0.6309464196294442,
"grad_norm": 0.4145865738391876,
"learning_rate": 3.590334489253306e-05,
"loss": 0.9526,
"step": 630
},
{
"epoch": 0.6329494241362043,
"grad_norm": 0.4078468084335327,
"learning_rate": 3.5798287450362306e-05,
"loss": 0.8913,
"step": 632
},
{
"epoch": 0.6349524286429644,
"grad_norm": 0.49246945977211,
"learning_rate": 3.569299505646433e-05,
"loss": 0.862,
"step": 634
},
{
"epoch": 0.6369554331497246,
"grad_norm": 0.4269583523273468,
"learning_rate": 3.55874700018163e-05,
"loss": 0.9608,
"step": 636
},
{
"epoch": 0.6389584376564847,
"grad_norm": 0.4796135723590851,
"learning_rate": 3.548171458245765e-05,
"loss": 0.9123,
"step": 638
},
{
"epoch": 0.6409614421632449,
"grad_norm": 0.41421452164649963,
"learning_rate": 3.5375731099440135e-05,
"loss": 0.9702,
"step": 640
},
{
"epoch": 0.642964446670005,
"grad_norm": 0.4892091751098633,
"learning_rate": 3.526952185877781e-05,
"loss": 0.877,
"step": 642
},
{
"epoch": 0.6449674511767651,
"grad_norm": 0.39520540833473206,
"learning_rate": 3.516308917139678e-05,
"loss": 0.9643,
"step": 644
},
{
"epoch": 0.6469704556835253,
"grad_norm": 0.5455682873725891,
"learning_rate": 3.505643535308499e-05,
"loss": 0.9473,
"step": 646
},
{
"epoch": 0.6489734601902855,
"grad_norm": 0.40943270921707153,
"learning_rate": 3.494956272444177e-05,
"loss": 0.9506,
"step": 648
},
{
"epoch": 0.6509764646970456,
"grad_norm": 0.3957885503768921,
"learning_rate": 3.484247361082741e-05,
"loss": 0.8854,
"step": 650
},
{
"epoch": 0.6509764646970456,
"eval_loss": 1.1660796403884888,
"eval_runtime": 3.827,
"eval_samples_per_second": 15.155,
"eval_steps_per_second": 7.578,
"step": 650
},
{
"epoch": 0.6529794692038057,
"grad_norm": 0.4576199948787689,
"learning_rate": 3.473517034231251e-05,
"loss": 0.8848,
"step": 652
},
{
"epoch": 0.6549824737105658,
"grad_norm": 0.45555633306503296,
"learning_rate": 3.4627655253627323e-05,
"loss": 0.954,
"step": 654
},
{
"epoch": 0.656985478217326,
"grad_norm": 0.45799553394317627,
"learning_rate": 3.451993068411092e-05,
"loss": 0.9766,
"step": 656
},
{
"epoch": 0.6589884827240862,
"grad_norm": 0.44451501965522766,
"learning_rate": 3.441199897766031e-05,
"loss": 0.9934,
"step": 658
},
{
"epoch": 0.6609914872308462,
"grad_norm": 0.43687155842781067,
"learning_rate": 3.430386248267943e-05,
"loss": 0.8342,
"step": 660
},
{
"epoch": 0.6629944917376064,
"grad_norm": 0.385002076625824,
"learning_rate": 3.419552355202807e-05,
"loss": 0.9195,
"step": 662
},
{
"epoch": 0.6649974962443665,
"grad_norm": 0.4921188950538635,
"learning_rate": 3.408698454297067e-05,
"loss": 0.894,
"step": 664
},
{
"epoch": 0.6670005007511267,
"grad_norm": 0.45717331767082214,
"learning_rate": 3.397824781712499e-05,
"loss": 0.9223,
"step": 666
},
{
"epoch": 0.6690035052578869,
"grad_norm": 0.6077693700790405,
"learning_rate": 3.386931574041079e-05,
"loss": 0.8307,
"step": 668
},
{
"epoch": 0.6710065097646469,
"grad_norm": 0.5416433215141296,
"learning_rate": 3.376019068299832e-05,
"loss": 0.9084,
"step": 670
},
{
"epoch": 0.6730095142714071,
"grad_norm": 0.48100745677948,
"learning_rate": 3.365087501925673e-05,
"loss": 0.8687,
"step": 672
},
{
"epoch": 0.6750125187781673,
"grad_norm": 0.4744812846183777,
"learning_rate": 3.354137112770244e-05,
"loss": 0.9819,
"step": 674
},
{
"epoch": 0.6770155232849274,
"grad_norm": 0.5188727378845215,
"learning_rate": 3.343168139094738e-05,
"loss": 0.8702,
"step": 676
},
{
"epoch": 0.6790185277916875,
"grad_norm": 0.42871081829071045,
"learning_rate": 3.332180819564714e-05,
"loss": 0.9244,
"step": 678
},
{
"epoch": 0.6810215322984476,
"grad_norm": 0.3858610689640045,
"learning_rate": 3.321175393244904e-05,
"loss": 0.8371,
"step": 680
},
{
"epoch": 0.6830245368052078,
"grad_norm": 0.459778368473053,
"learning_rate": 3.310152099594013e-05,
"loss": 0.9146,
"step": 682
},
{
"epoch": 0.685027541311968,
"grad_norm": 0.36012330651283264,
"learning_rate": 3.299111178459507e-05,
"loss": 0.9806,
"step": 684
},
{
"epoch": 0.6870305458187281,
"grad_norm": 0.4208768606185913,
"learning_rate": 3.288052870072395e-05,
"loss": 0.8729,
"step": 686
},
{
"epoch": 0.6890335503254882,
"grad_norm": 0.4012265205383301,
"learning_rate": 3.2769774150420015e-05,
"loss": 0.8586,
"step": 688
},
{
"epoch": 0.6910365548322484,
"grad_norm": 0.442624032497406,
"learning_rate": 3.2658850543507334e-05,
"loss": 0.931,
"step": 690
},
{
"epoch": 0.6930395593390085,
"grad_norm": 0.3907168209552765,
"learning_rate": 3.2547760293488335e-05,
"loss": 0.9246,
"step": 692
},
{
"epoch": 0.6950425638457687,
"grad_norm": 0.4578626751899719,
"learning_rate": 3.2436505817491305e-05,
"loss": 0.9339,
"step": 694
},
{
"epoch": 0.6970455683525288,
"grad_norm": 0.49979129433631897,
"learning_rate": 3.2325089536217815e-05,
"loss": 0.9637,
"step": 696
},
{
"epoch": 0.6990485728592889,
"grad_norm": 0.41651976108551025,
"learning_rate": 3.2213513873890026e-05,
"loss": 0.9365,
"step": 698
},
{
"epoch": 0.7010515773660491,
"grad_norm": 0.4993303120136261,
"learning_rate": 3.210178125819795e-05,
"loss": 0.8978,
"step": 700
},
{
"epoch": 0.7010515773660491,
"eval_loss": 1.1489382982254028,
"eval_runtime": 3.8105,
"eval_samples_per_second": 15.221,
"eval_steps_per_second": 7.611,
"step": 700
},
{
"epoch": 0.7030545818728092,
"grad_norm": 0.5267933011054993,
"learning_rate": 3.1989894120246614e-05,
"loss": 0.8641,
"step": 702
},
{
"epoch": 0.7050575863795694,
"grad_norm": 0.5193835496902466,
"learning_rate": 3.1877854894503204e-05,
"loss": 0.9497,
"step": 704
},
{
"epoch": 0.7070605908863294,
"grad_norm": 0.43787896633148193,
"learning_rate": 3.1765666018744046e-05,
"loss": 0.8907,
"step": 706
},
{
"epoch": 0.7090635953930896,
"grad_norm": 0.418584406375885,
"learning_rate": 3.1653329934001584e-05,
"loss": 0.9517,
"step": 708
},
{
"epoch": 0.7110665998998498,
"grad_norm": 0.6064937114715576,
"learning_rate": 3.154084908451131e-05,
"loss": 0.8603,
"step": 710
},
{
"epoch": 0.7130696044066099,
"grad_norm": 0.37019243836402893,
"learning_rate": 3.142822591765851e-05,
"loss": 0.8974,
"step": 712
},
{
"epoch": 0.7150726089133701,
"grad_norm": 0.38166865706443787,
"learning_rate": 3.1315462883925025e-05,
"loss": 0.9558,
"step": 714
},
{
"epoch": 0.7170756134201302,
"grad_norm": 0.45281273126602173,
"learning_rate": 3.1202562436836e-05,
"loss": 0.9325,
"step": 716
},
{
"epoch": 0.7190786179268903,
"grad_norm": 0.4501991868019104,
"learning_rate": 3.1089527032906425e-05,
"loss": 0.9862,
"step": 718
},
{
"epoch": 0.7210816224336505,
"grad_norm": 0.43729260563850403,
"learning_rate": 3.097635913158772e-05,
"loss": 0.9339,
"step": 720
},
{
"epoch": 0.7230846269404106,
"grad_norm": 0.5757997632026672,
"learning_rate": 3.08630611952142e-05,
"loss": 0.8904,
"step": 722
},
{
"epoch": 0.7250876314471708,
"grad_norm": 0.4715934991836548,
"learning_rate": 3.0749635688949545e-05,
"loss": 0.8899,
"step": 724
},
{
"epoch": 0.7270906359539309,
"grad_norm": 0.5050368905067444,
"learning_rate": 3.063608508073311e-05,
"loss": 0.9324,
"step": 726
},
{
"epoch": 0.729093640460691,
"grad_norm": 0.6013456583023071,
"learning_rate": 3.052241184122625e-05,
"loss": 0.9626,
"step": 728
},
{
"epoch": 0.7310966449674512,
"grad_norm": 0.45164185762405396,
"learning_rate": 3.0408618443758557e-05,
"loss": 0.8899,
"step": 730
},
{
"epoch": 0.7330996494742114,
"grad_norm": 0.4240935444831848,
"learning_rate": 3.0294707364274067e-05,
"loss": 0.9151,
"step": 732
},
{
"epoch": 0.7351026539809714,
"grad_norm": 0.548370361328125,
"learning_rate": 3.018068108127735e-05,
"loss": 0.8976,
"step": 734
},
{
"epoch": 0.7371056584877316,
"grad_norm": 0.4141191840171814,
"learning_rate": 3.0066542075779602e-05,
"loss": 0.9035,
"step": 736
},
{
"epoch": 0.7391086629944917,
"grad_norm": 0.4236369729042053,
"learning_rate": 2.9952292831244676e-05,
"loss": 0.8906,
"step": 738
},
{
"epoch": 0.7411116675012519,
"grad_norm": 0.3607020974159241,
"learning_rate": 2.9837935833535037e-05,
"loss": 0.9423,
"step": 740
},
{
"epoch": 0.7431146720080121,
"grad_norm": 0.4230390191078186,
"learning_rate": 2.9723473570857642e-05,
"loss": 0.9092,
"step": 742
},
{
"epoch": 0.7451176765147721,
"grad_norm": 0.3703189492225647,
"learning_rate": 2.960890853370985e-05,
"loss": 0.8663,
"step": 744
},
{
"epoch": 0.7471206810215323,
"grad_norm": 0.49546095728874207,
"learning_rate": 2.9494243214825208e-05,
"loss": 0.8875,
"step": 746
},
{
"epoch": 0.7491236855282924,
"grad_norm": 0.44254347681999207,
"learning_rate": 2.9379480109119213e-05,
"loss": 0.923,
"step": 748
},
{
"epoch": 0.7511266900350526,
"grad_norm": 0.4102881848812103,
"learning_rate": 2.9264621713635028e-05,
"loss": 0.9357,
"step": 750
},
{
"epoch": 0.7511266900350526,
"eval_loss": 1.1563700437545776,
"eval_runtime": 3.8041,
"eval_samples_per_second": 15.247,
"eval_steps_per_second": 7.623,
"step": 750
},
{
"epoch": 0.7531296945418127,
"grad_norm": 0.42651745676994324,
"learning_rate": 2.914967052748917e-05,
"loss": 0.9277,
"step": 752
},
{
"epoch": 0.7551326990485728,
"grad_norm": 0.37917560338974,
"learning_rate": 2.9034629051817096e-05,
"loss": 0.9717,
"step": 754
},
{
"epoch": 0.757135703555333,
"grad_norm": 0.4591340720653534,
"learning_rate": 2.891949978971883e-05,
"loss": 0.9336,
"step": 756
},
{
"epoch": 0.7591387080620932,
"grad_norm": 0.5880463719367981,
"learning_rate": 2.8804285246204438e-05,
"loss": 0.9098,
"step": 758
},
{
"epoch": 0.7611417125688533,
"grad_norm": 0.39928752183914185,
"learning_rate": 2.8688987928139588e-05,
"loss": 0.8258,
"step": 760
},
{
"epoch": 0.7631447170756134,
"grad_norm": 0.5559530258178711,
"learning_rate": 2.8573610344190975e-05,
"loss": 0.8728,
"step": 762
},
{
"epoch": 0.7651477215823735,
"grad_norm": 0.49999016523361206,
"learning_rate": 2.8458155004771724e-05,
"loss": 1.0135,
"step": 764
},
{
"epoch": 0.7671507260891337,
"grad_norm": 0.35017403960227966,
"learning_rate": 2.8342624421986797e-05,
"loss": 0.8929,
"step": 766
},
{
"epoch": 0.7691537305958939,
"grad_norm": 0.48860040307044983,
"learning_rate": 2.822702110957831e-05,
"loss": 0.8784,
"step": 768
},
{
"epoch": 0.771156735102654,
"grad_norm": 0.4092211425304413,
"learning_rate": 2.811134758287085e-05,
"loss": 0.8643,
"step": 770
},
{
"epoch": 0.7731597396094141,
"grad_norm": 0.517197847366333,
"learning_rate": 2.799560635871675e-05,
"loss": 0.9033,
"step": 772
},
{
"epoch": 0.7751627441161743,
"grad_norm": 0.40133723616600037,
"learning_rate": 2.78797999554413e-05,
"loss": 0.9308,
"step": 774
},
{
"epoch": 0.7771657486229344,
"grad_norm": 0.4061048626899719,
"learning_rate": 2.7763930892787992e-05,
"loss": 0.9076,
"step": 776
},
{
"epoch": 0.7791687531296946,
"grad_norm": 0.5977723002433777,
"learning_rate": 2.7648001691863673e-05,
"loss": 0.8699,
"step": 778
},
{
"epoch": 0.7811717576364546,
"grad_norm": 0.3865041136741638,
"learning_rate": 2.753201487508369e-05,
"loss": 0.9565,
"step": 780
},
{
"epoch": 0.7831747621432148,
"grad_norm": 0.49114081263542175,
"learning_rate": 2.7415972966117014e-05,
"loss": 0.8533,
"step": 782
},
{
"epoch": 0.785177766649975,
"grad_norm": 0.3852551281452179,
"learning_rate": 2.7299878489831316e-05,
"loss": 0.8556,
"step": 784
},
{
"epoch": 0.7871807711567351,
"grad_norm": 0.4888080060482025,
"learning_rate": 2.718373397223804e-05,
"loss": 0.8734,
"step": 786
},
{
"epoch": 0.7891837756634953,
"grad_norm": 0.4077546298503876,
"learning_rate": 2.706754194043746e-05,
"loss": 0.9392,
"step": 788
},
{
"epoch": 0.7911867801702553,
"grad_norm": 0.408587247133255,
"learning_rate": 2.6951304922563642e-05,
"loss": 0.8565,
"step": 790
},
{
"epoch": 0.7931897846770155,
"grad_norm": 0.45802196860313416,
"learning_rate": 2.6835025447729495e-05,
"loss": 0.9535,
"step": 792
},
{
"epoch": 0.7951927891837757,
"grad_norm": 0.4353581964969635,
"learning_rate": 2.6718706045971726e-05,
"loss": 0.8428,
"step": 794
},
{
"epoch": 0.7971957936905358,
"grad_norm": 0.4018676280975342,
"learning_rate": 2.6602349248195746e-05,
"loss": 0.8754,
"step": 796
},
{
"epoch": 0.7991987981972959,
"grad_norm": 0.4653930068016052,
"learning_rate": 2.6485957586120663e-05,
"loss": 0.7725,
"step": 798
},
{
"epoch": 0.801201802704056,
"grad_norm": 0.5806179642677307,
"learning_rate": 2.6369533592224172e-05,
"loss": 0.8955,
"step": 800
},
{
"epoch": 0.801201802704056,
"eval_loss": 1.1470181941986084,
"eval_runtime": 3.7967,
"eval_samples_per_second": 15.277,
"eval_steps_per_second": 7.638,
"step": 800
},
{
"epoch": 0.8032048072108162,
"grad_norm": 0.4590522348880768,
"learning_rate": 2.6253079799687435e-05,
"loss": 0.9738,
"step": 802
},
{
"epoch": 0.8052078117175764,
"grad_norm": 0.5188782811164856,
"learning_rate": 2.613659874233999e-05,
"loss": 0.9573,
"step": 804
},
{
"epoch": 0.8072108162243365,
"grad_norm": 0.4585997760295868,
"learning_rate": 2.6020092954604614e-05,
"loss": 0.948,
"step": 806
},
{
"epoch": 0.8092138207310966,
"grad_norm": 0.39974266290664673,
"learning_rate": 2.5903564971442167e-05,
"loss": 1.0123,
"step": 808
},
{
"epoch": 0.8112168252378568,
"grad_norm": 0.4484356641769409,
"learning_rate": 2.5787017328296447e-05,
"loss": 0.8262,
"step": 810
},
{
"epoch": 0.8132198297446169,
"grad_norm": 0.4441506862640381,
"learning_rate": 2.5670452561039004e-05,
"loss": 0.8683,
"step": 812
},
{
"epoch": 0.8152228342513771,
"grad_norm": 0.6077110171318054,
"learning_rate": 2.555387320591401e-05,
"loss": 0.8657,
"step": 814
},
{
"epoch": 0.8172258387581373,
"grad_norm": 0.3740634322166443,
"learning_rate": 2.5437281799483004e-05,
"loss": 0.9215,
"step": 816
},
{
"epoch": 0.8192288432648973,
"grad_norm": 0.516426682472229,
"learning_rate": 2.5320680878569768e-05,
"loss": 0.8907,
"step": 818
},
{
"epoch": 0.8212318477716575,
"grad_norm": 0.42550894618034363,
"learning_rate": 2.5204072980205092e-05,
"loss": 0.9188,
"step": 820
},
{
"epoch": 0.8232348522784176,
"grad_norm": 0.5615983605384827,
"learning_rate": 2.508746064157159e-05,
"loss": 1.0489,
"step": 822
},
{
"epoch": 0.8252378567851778,
"grad_norm": 0.4470774233341217,
"learning_rate": 2.4970846399948487e-05,
"loss": 0.8668,
"step": 824
},
{
"epoch": 0.8272408612919379,
"grad_norm": 0.440336138010025,
"learning_rate": 2.4854232792656394e-05,
"loss": 0.8658,
"step": 826
},
{
"epoch": 0.829243865798698,
"grad_norm": 0.41719090938568115,
"learning_rate": 2.473762235700214e-05,
"loss": 0.9103,
"step": 828
},
{
"epoch": 0.8312468703054582,
"grad_norm": 0.4663768410682678,
"learning_rate": 2.462101763022356e-05,
"loss": 0.8621,
"step": 830
},
{
"epoch": 0.8332498748122183,
"grad_norm": 0.4149011969566345,
"learning_rate": 2.4504421149434233e-05,
"loss": 0.82,
"step": 832
},
{
"epoch": 0.8352528793189785,
"grad_norm": 0.4140399992465973,
"learning_rate": 2.4387835451568355e-05,
"loss": 0.9775,
"step": 834
},
{
"epoch": 0.8372558838257386,
"grad_norm": 0.44181761145591736,
"learning_rate": 2.427126307332549e-05,
"loss": 0.8591,
"step": 836
},
{
"epoch": 0.8392588883324987,
"grad_norm": 0.4710381031036377,
"learning_rate": 2.4154706551115384e-05,
"loss": 0.8738,
"step": 838
},
{
"epoch": 0.8412618928392589,
"grad_norm": 0.5030112266540527,
"learning_rate": 2.4038168421002794e-05,
"loss": 0.9506,
"step": 840
},
{
"epoch": 0.8432648973460191,
"grad_norm": 0.5199030041694641,
"learning_rate": 2.3921651218652293e-05,
"loss": 0.8508,
"step": 842
},
{
"epoch": 0.8452679018527791,
"grad_norm": 0.5105124115943909,
"learning_rate": 2.380515747927312e-05,
"loss": 0.8432,
"step": 844
},
{
"epoch": 0.8472709063595393,
"grad_norm": 0.49101004004478455,
"learning_rate": 2.3688689737563967e-05,
"loss": 0.9014,
"step": 846
},
{
"epoch": 0.8492739108662994,
"grad_norm": 0.4043116569519043,
"learning_rate": 2.3572250527657895e-05,
"loss": 0.9011,
"step": 848
},
{
"epoch": 0.8512769153730596,
"grad_norm": 0.4326643645763397,
"learning_rate": 2.345584238306713e-05,
"loss": 0.8597,
"step": 850
},
{
"epoch": 0.8512769153730596,
"eval_loss": 1.1495444774627686,
"eval_runtime": 3.7962,
"eval_samples_per_second": 15.279,
"eval_steps_per_second": 7.639,
"step": 850
},
{
"epoch": 0.8532799198798198,
"grad_norm": 0.5106630325317383,
"learning_rate": 2.3339467836628017e-05,
"loss": 0.9167,
"step": 852
},
{
"epoch": 0.8552829243865798,
"grad_norm": 0.42315831780433655,
"learning_rate": 2.322312942044581e-05,
"loss": 0.9248,
"step": 854
},
{
"epoch": 0.85728592889334,
"grad_norm": 0.4706262946128845,
"learning_rate": 2.3106829665839677e-05,
"loss": 0.8772,
"step": 856
},
{
"epoch": 0.8592889334001002,
"grad_norm": 0.7145017385482788,
"learning_rate": 2.2990571103287567e-05,
"loss": 0.9167,
"step": 858
},
{
"epoch": 0.8612919379068603,
"grad_norm": 0.47455379366874695,
"learning_rate": 2.2874356262371134e-05,
"loss": 0.9008,
"step": 860
},
{
"epoch": 0.8632949424136205,
"grad_norm": 0.41509053111076355,
"learning_rate": 2.2758187671720772e-05,
"loss": 0.8976,
"step": 862
},
{
"epoch": 0.8652979469203805,
"grad_norm": 0.5434259176254272,
"learning_rate": 2.2642067858960514e-05,
"loss": 0.8593,
"step": 864
},
{
"epoch": 0.8673009514271407,
"grad_norm": 0.43615275621414185,
"learning_rate": 2.2525999350653095e-05,
"loss": 0.9305,
"step": 866
},
{
"epoch": 0.8693039559339009,
"grad_norm": 0.5843902230262756,
"learning_rate": 2.2409984672244934e-05,
"loss": 0.8521,
"step": 868
},
{
"epoch": 0.871306960440661,
"grad_norm": 0.35046350955963135,
"learning_rate": 2.2294026348011223e-05,
"loss": 0.8392,
"step": 870
},
{
"epoch": 0.8733099649474211,
"grad_norm": 0.4275960624217987,
"learning_rate": 2.2178126901000996e-05,
"loss": 0.8883,
"step": 872
},
{
"epoch": 0.8753129694541812,
"grad_norm": 1.0779649019241333,
"learning_rate": 2.2062288852982182e-05,
"loss": 0.9226,
"step": 874
},
{
"epoch": 0.8773159739609414,
"grad_norm": 0.43578073382377625,
"learning_rate": 2.1946514724386828e-05,
"loss": 0.877,
"step": 876
},
{
"epoch": 0.8793189784677016,
"grad_norm": 0.5768626928329468,
"learning_rate": 2.1830807034256154e-05,
"loss": 0.8844,
"step": 878
},
{
"epoch": 0.8813219829744617,
"grad_norm": 0.4431218206882477,
"learning_rate": 2.1715168300185848e-05,
"loss": 0.9106,
"step": 880
},
{
"epoch": 0.8833249874812218,
"grad_norm": 0.44507092237472534,
"learning_rate": 2.1599601038271186e-05,
"loss": 0.9349,
"step": 882
},
{
"epoch": 0.885327991987982,
"grad_norm": 0.42408713698387146,
"learning_rate": 2.148410776305237e-05,
"loss": 0.8704,
"step": 884
},
{
"epoch": 0.8873309964947421,
"grad_norm": 0.45474737882614136,
"learning_rate": 2.136869098745978e-05,
"loss": 0.8854,
"step": 886
},
{
"epoch": 0.8893340010015023,
"grad_norm": 0.42297935485839844,
"learning_rate": 2.125335322275928e-05,
"loss": 0.8438,
"step": 888
},
{
"epoch": 0.8913370055082624,
"grad_norm": 0.5911722779273987,
"learning_rate": 2.1138096978497617e-05,
"loss": 0.8021,
"step": 890
},
{
"epoch": 0.8933400100150225,
"grad_norm": 0.5190030336380005,
"learning_rate": 2.1022924762447767e-05,
"loss": 0.8814,
"step": 892
},
{
"epoch": 0.8953430145217827,
"grad_norm": 0.4616602957248688,
"learning_rate": 2.0907839080554443e-05,
"loss": 0.9051,
"step": 894
},
{
"epoch": 0.8973460190285428,
"grad_norm": 0.6448442935943604,
"learning_rate": 2.079284243687948e-05,
"loss": 0.8667,
"step": 896
},
{
"epoch": 0.899349023535303,
"grad_norm": 0.46473053097724915,
"learning_rate": 2.067793733354743e-05,
"loss": 0.8543,
"step": 898
},
{
"epoch": 0.901352028042063,
"grad_norm": 0.47952961921691895,
"learning_rate": 2.0563126270691097e-05,
"loss": 0.869,
"step": 900
},
{
"epoch": 0.901352028042063,
"eval_loss": 1.1418862342834473,
"eval_runtime": 3.8348,
"eval_samples_per_second": 15.125,
"eval_steps_per_second": 7.562,
"step": 900
},
{
"epoch": 0.9033550325488232,
"grad_norm": 0.4736415147781372,
"learning_rate": 2.044841174639708e-05,
"loss": 0.8937,
"step": 902
},
{
"epoch": 0.9053580370555834,
"grad_norm": 0.48480942845344543,
"learning_rate": 2.0333796256651533e-05,
"loss": 0.9146,
"step": 904
},
{
"epoch": 0.9073610415623435,
"grad_norm": 0.519432544708252,
"learning_rate": 2.0219282295285737e-05,
"loss": 0.8845,
"step": 906
},
{
"epoch": 0.9093640460691037,
"grad_norm": 0.47801777720451355,
"learning_rate": 2.0104872353921927e-05,
"loss": 0.8701,
"step": 908
},
{
"epoch": 0.9113670505758638,
"grad_norm": 0.5259170532226562,
"learning_rate": 1.999056892191904e-05,
"loss": 0.9299,
"step": 910
},
{
"epoch": 0.9133700550826239,
"grad_norm": 0.503354549407959,
"learning_rate": 1.9876374486318543e-05,
"loss": 0.8895,
"step": 912
},
{
"epoch": 0.9153730595893841,
"grad_norm": 0.5313873887062073,
"learning_rate": 1.9762291531790355e-05,
"loss": 0.8254,
"step": 914
},
{
"epoch": 0.9173760640961443,
"grad_norm": 0.5693700313568115,
"learning_rate": 1.9648322540578744e-05,
"loss": 0.8246,
"step": 916
},
{
"epoch": 0.9193790686029043,
"grad_norm": 0.5147340893745422,
"learning_rate": 1.9534469992448358e-05,
"loss": 0.8987,
"step": 918
},
{
"epoch": 0.9213820731096645,
"grad_norm": 0.718410849571228,
"learning_rate": 1.9420736364630215e-05,
"loss": 0.8385,
"step": 920
},
{
"epoch": 0.9233850776164246,
"grad_norm": 0.49588289856910706,
"learning_rate": 1.9307124131767877e-05,
"loss": 0.8652,
"step": 922
},
{
"epoch": 0.9253880821231848,
"grad_norm": 0.6265762448310852,
"learning_rate": 1.9193635765863523e-05,
"loss": 0.8964,
"step": 924
},
{
"epoch": 0.927391086629945,
"grad_norm": 0.4153289496898651,
"learning_rate": 1.9080273736224236e-05,
"loss": 0.9286,
"step": 926
},
{
"epoch": 0.929394091136705,
"grad_norm": 0.6794211864471436,
"learning_rate": 1.8967040509408253e-05,
"loss": 0.9141,
"step": 928
},
{
"epoch": 0.9313970956434652,
"grad_norm": 0.595132052898407,
"learning_rate": 1.885393854917124e-05,
"loss": 0.8353,
"step": 930
},
{
"epoch": 0.9334001001502253,
"grad_norm": 0.4146586060523987,
"learning_rate": 1.8740970316412793e-05,
"loss": 0.898,
"step": 932
},
{
"epoch": 0.9354031046569855,
"grad_norm": 0.5133841633796692,
"learning_rate": 1.8628138269122773e-05,
"loss": 0.8648,
"step": 934
},
{
"epoch": 0.9374061091637457,
"grad_norm": 0.4042494595050812,
"learning_rate": 1.8515444862327946e-05,
"loss": 0.9285,
"step": 936
},
{
"epoch": 0.9394091136705057,
"grad_norm": 0.4541870057582855,
"learning_rate": 1.8402892548038453e-05,
"loss": 0.905,
"step": 938
},
{
"epoch": 0.9414121181772659,
"grad_norm": 0.4241974949836731,
"learning_rate": 1.829048377519455e-05,
"loss": 0.9802,
"step": 940
},
{
"epoch": 0.943415122684026,
"grad_norm": 0.5843325257301331,
"learning_rate": 1.8178220989613254e-05,
"loss": 0.8694,
"step": 942
},
{
"epoch": 0.9454181271907862,
"grad_norm": 0.3579271137714386,
"learning_rate": 1.806610663393517e-05,
"loss": 0.9004,
"step": 944
},
{
"epoch": 0.9474211316975463,
"grad_norm": 0.409402459859848,
"learning_rate": 1.795414314757134e-05,
"loss": 0.9436,
"step": 946
},
{
"epoch": 0.9494241362043064,
"grad_norm": 0.40799620747566223,
"learning_rate": 1.784233296665012e-05,
"loss": 0.8883,
"step": 948
},
{
"epoch": 0.9514271407110666,
"grad_norm": 0.45501673221588135,
"learning_rate": 1.773067852396426e-05,
"loss": 0.9641,
"step": 950
},
{
"epoch": 0.9514271407110666,
"eval_loss": 1.1456818580627441,
"eval_runtime": 3.8046,
"eval_samples_per_second": 15.245,
"eval_steps_per_second": 7.622,
"step": 950
},
{
"epoch": 0.9534301452178268,
"grad_norm": 0.4748212695121765,
"learning_rate": 1.761918224891787e-05,
"loss": 0.8753,
"step": 952
},
{
"epoch": 0.9554331497245869,
"grad_norm": 0.6242424249649048,
"learning_rate": 1.7507846567473644e-05,
"loss": 0.8713,
"step": 954
},
{
"epoch": 0.957436154231347,
"grad_norm": 0.42941513657569885,
"learning_rate": 1.7396673902100035e-05,
"loss": 0.9128,
"step": 956
},
{
"epoch": 0.9594391587381071,
"grad_norm": 0.44053131341934204,
"learning_rate": 1.728566667171854e-05,
"loss": 0.8996,
"step": 958
},
{
"epoch": 0.9614421632448673,
"grad_norm": 0.6191515922546387,
"learning_rate": 1.71748272916511e-05,
"loss": 0.8114,
"step": 960
},
{
"epoch": 0.9634451677516275,
"grad_norm": 0.40307995676994324,
"learning_rate": 1.7064158173567514e-05,
"loss": 0.8587,
"step": 962
},
{
"epoch": 0.9654481722583875,
"grad_norm": 0.3541308641433716,
"learning_rate": 1.695366172543299e-05,
"loss": 0.9487,
"step": 964
},
{
"epoch": 0.9674511767651477,
"grad_norm": 0.4575124979019165,
"learning_rate": 1.6843340351455726e-05,
"loss": 0.9219,
"step": 966
},
{
"epoch": 0.9694541812719079,
"grad_norm": 0.4024929702281952,
"learning_rate": 1.6733196452034653e-05,
"loss": 0.9609,
"step": 968
},
{
"epoch": 0.971457185778668,
"grad_norm": 0.4288537800312042,
"learning_rate": 1.662323242370711e-05,
"loss": 0.9131,
"step": 970
},
{
"epoch": 0.9734601902854282,
"grad_norm": 0.3629342317581177,
"learning_rate": 1.6513450659096804e-05,
"loss": 0.8327,
"step": 972
},
{
"epoch": 0.9754631947921882,
"grad_norm": 0.40302079916000366,
"learning_rate": 1.64038535468617e-05,
"loss": 0.9035,
"step": 974
},
{
"epoch": 0.9774661992989484,
"grad_norm": 0.44683897495269775,
"learning_rate": 1.629444347164202e-05,
"loss": 0.9142,
"step": 976
},
{
"epoch": 0.9794692038057086,
"grad_norm": 0.6119024157524109,
"learning_rate": 1.6185222814008433e-05,
"loss": 0.8105,
"step": 978
},
{
"epoch": 0.9814722083124687,
"grad_norm": 0.39314714074134827,
"learning_rate": 1.6076193950410172e-05,
"loss": 0.8817,
"step": 980
},
{
"epoch": 0.9834752128192289,
"grad_norm": 0.465087354183197,
"learning_rate": 1.5967359253123403e-05,
"loss": 0.8979,
"step": 982
},
{
"epoch": 0.985478217325989,
"grad_norm": 0.5371639728546143,
"learning_rate": 1.5858721090199565e-05,
"loss": 0.9335,
"step": 984
},
{
"epoch": 0.9874812218327491,
"grad_norm": 0.5564991235733032,
"learning_rate": 1.5750281825413836e-05,
"loss": 0.9051,
"step": 986
},
{
"epoch": 0.9894842263395093,
"grad_norm": 0.40404555201530457,
"learning_rate": 1.5642043818213757e-05,
"loss": 0.9676,
"step": 988
},
{
"epoch": 0.9914872308462694,
"grad_norm": 0.4462992548942566,
"learning_rate": 1.5534009423667827e-05,
"loss": 0.8869,
"step": 990
},
{
"epoch": 0.9934902353530295,
"grad_norm": 0.4584622085094452,
"learning_rate": 1.5426180992414318e-05,
"loss": 0.9093,
"step": 992
},
{
"epoch": 0.9954932398597897,
"grad_norm": 0.48583951592445374,
"learning_rate": 1.5318560870610065e-05,
"loss": 0.8587,
"step": 994
},
{
"epoch": 0.9974962443665498,
"grad_norm": 0.5246539115905762,
"learning_rate": 1.5211151399879506e-05,
"loss": 0.8145,
"step": 996
},
{
"epoch": 0.99949924887331,
"grad_norm": 0.5616730451583862,
"learning_rate": 1.510395491726363e-05,
"loss": 0.9115,
"step": 998
},
{
"epoch": 1.00100150225338,
"grad_norm": 0.398170530796051,
"learning_rate": 1.4996973755169219e-05,
"loss": 0.674,
"step": 1000
},
{
"epoch": 1.00100150225338,
"eval_loss": 1.1421712636947632,
"eval_runtime": 3.813,
"eval_samples_per_second": 15.211,
"eval_steps_per_second": 7.606,
"step": 1000
}
],
"logging_steps": 2,
"max_steps": 1497,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 9.382713588973568e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}