ramangpt_dft_model / trainer_state.json
knc6's picture
Upload folder using huggingface_hub
dfb140c verified
Raw History Blame Contribute Delete
138 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 2,
"global_step": 1270,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0031496062992125984,
"eval_loss": 0.3924538791179657,
"eval_runtime": 0.3893,
"eval_samples_per_second": 5.137,
"eval_steps_per_second": 2.569,
"step": 2
},
{
"epoch": 0.006299212598425197,
"eval_loss": 0.3304973244667053,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 4
},
{
"epoch": 0.009448818897637795,
"eval_loss": 0.31699004769325256,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 6
},
{
"epoch": 0.012598425196850394,
"eval_loss": 0.3123057186603546,
"eval_runtime": 0.3458,
"eval_samples_per_second": 5.784,
"eval_steps_per_second": 2.892,
"step": 8
},
{
"epoch": 0.015748031496062992,
"eval_loss": 0.3107089102268219,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 10
},
{
"epoch": 0.01889763779527559,
"eval_loss": 0.3101890981197357,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.773,
"eval_steps_per_second": 2.886,
"step": 12
},
{
"epoch": 0.02204724409448819,
"eval_loss": 0.30896076560020447,
"eval_runtime": 0.3461,
"eval_samples_per_second": 5.778,
"eval_steps_per_second": 2.889,
"step": 14
},
{
"epoch": 0.025196850393700787,
"eval_loss": 0.3102704584598541,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 16
},
{
"epoch": 0.028346456692913385,
"eval_loss": 0.3115064799785614,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 18
},
{
"epoch": 0.031496062992125984,
"eval_loss": 0.30983346700668335,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 20
},
{
"epoch": 0.03464566929133858,
"eval_loss": 0.3098318576812744,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 22
},
{
"epoch": 0.03779527559055118,
"eval_loss": 0.30872097611427307,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 24
},
{
"epoch": 0.04094488188976378,
"eval_loss": 0.3085379898548126,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 26
},
{
"epoch": 0.04409448818897638,
"eval_loss": 0.3072878420352936,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 28
},
{
"epoch": 0.047244094488188976,
"eval_loss": 0.30299630761146545,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 30
},
{
"epoch": 0.050393700787401574,
"eval_loss": 0.3007601797580719,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 32
},
{
"epoch": 0.05354330708661417,
"eval_loss": 0.2980590760707855,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 34
},
{
"epoch": 0.05669291338582677,
"eval_loss": 0.2967863082885742,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 36
},
{
"epoch": 0.05984251968503937,
"eval_loss": 0.2965218722820282,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 38
},
{
"epoch": 0.06299212598425197,
"eval_loss": 0.29822391271591187,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.866,
"step": 40
},
{
"epoch": 0.06614173228346457,
"eval_loss": 0.297976553440094,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 42
},
{
"epoch": 0.06929133858267716,
"eval_loss": 0.29542049765586853,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 44
},
{
"epoch": 0.07244094488188976,
"eval_loss": 0.2969954013824463,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.763,
"eval_steps_per_second": 2.881,
"step": 46
},
{
"epoch": 0.07559055118110236,
"eval_loss": 0.2955021560192108,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 48
},
{
"epoch": 0.07874015748031496,
"eval_loss": 0.29271337389945984,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.774,
"eval_steps_per_second": 2.887,
"step": 50
},
{
"epoch": 0.08188976377952756,
"eval_loss": 0.2890363335609436,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 52
},
{
"epoch": 0.08503937007874016,
"eval_loss": 0.28773531317710876,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 54
},
{
"epoch": 0.08818897637795275,
"eval_loss": 0.2882959842681885,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 56
},
{
"epoch": 0.09133858267716535,
"eval_loss": 0.2880721092224121,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 58
},
{
"epoch": 0.09448818897637795,
"eval_loss": 0.2880062460899353,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.769,
"eval_steps_per_second": 2.885,
"step": 60
},
{
"epoch": 0.09763779527559055,
"eval_loss": 0.28680866956710815,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 62
},
{
"epoch": 0.10078740157480315,
"eval_loss": 0.2864318788051605,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 64
},
{
"epoch": 0.10393700787401575,
"eval_loss": 0.286954402923584,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 66
},
{
"epoch": 0.10708661417322834,
"eval_loss": 0.2869313955307007,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 68
},
{
"epoch": 0.11023622047244094,
"eval_loss": 0.28629228472709656,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 70
},
{
"epoch": 0.11338582677165354,
"eval_loss": 0.28649017214775085,
"eval_runtime": 0.3456,
"eval_samples_per_second": 5.788,
"eval_steps_per_second": 2.894,
"step": 72
},
{
"epoch": 0.11653543307086614,
"eval_loss": 0.2855049669742584,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 74
},
{
"epoch": 0.11968503937007874,
"eval_loss": 0.2844473123550415,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 76
},
{
"epoch": 0.12283464566929134,
"eval_loss": 0.28396809101104736,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 78
},
{
"epoch": 0.12598425196850394,
"eval_loss": 0.2837795317173004,
"eval_runtime": 0.3503,
"eval_samples_per_second": 5.709,
"eval_steps_per_second": 2.854,
"step": 80
},
{
"epoch": 0.12913385826771653,
"eval_loss": 0.28213855624198914,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 82
},
{
"epoch": 0.13228346456692913,
"eval_loss": 0.2815304100513458,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 84
},
{
"epoch": 0.13543307086614173,
"eval_loss": 0.28142452239990234,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 86
},
{
"epoch": 0.13858267716535433,
"eval_loss": 0.28305861353874207,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 88
},
{
"epoch": 0.14173228346456693,
"eval_loss": 0.28504520654678345,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 90
},
{
"epoch": 0.14488188976377953,
"eval_loss": 0.28821712732315063,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 92
},
{
"epoch": 0.14803149606299212,
"eval_loss": 0.29037097096443176,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 94
},
{
"epoch": 0.15118110236220472,
"eval_loss": 0.2897632122039795,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.866,
"step": 96
},
{
"epoch": 0.15433070866141732,
"eval_loss": 0.28879278898239136,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 98
},
{
"epoch": 0.15748031496062992,
"grad_norm": 0.4121800363063812,
"learning_rate": 4.621152328334649e-05,
"loss": 0.3652,
"step": 100
},
{
"epoch": 0.15748031496062992,
"eval_loss": 0.2896532416343689,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.725,
"eval_steps_per_second": 2.862,
"step": 100
},
{
"epoch": 0.16062992125984252,
"eval_loss": 0.2889969050884247,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 102
},
{
"epoch": 0.16377952755905512,
"eval_loss": 0.2898699641227722,
"eval_runtime": 0.3513,
"eval_samples_per_second": 5.693,
"eval_steps_per_second": 2.846,
"step": 104
},
{
"epoch": 0.16692913385826771,
"eval_loss": 0.2902238070964813,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.864,
"step": 106
},
{
"epoch": 0.1700787401574803,
"eval_loss": 0.291797012090683,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 108
},
{
"epoch": 0.1732283464566929,
"eval_loss": 0.2921120524406433,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 110
},
{
"epoch": 0.1763779527559055,
"eval_loss": 0.2939179241657257,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 112
},
{
"epoch": 0.1795275590551181,
"eval_loss": 0.29445576667785645,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 114
},
{
"epoch": 0.1826771653543307,
"eval_loss": 0.2934577465057373,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 116
},
{
"epoch": 0.1858267716535433,
"eval_loss": 0.2888961732387543,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.865,
"step": 118
},
{
"epoch": 0.1889763779527559,
"eval_loss": 0.28480276465415955,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 120
},
{
"epoch": 0.1921259842519685,
"eval_loss": 0.28536275029182434,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.865,
"step": 122
},
{
"epoch": 0.1952755905511811,
"eval_loss": 0.28341853618621826,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.726,
"eval_steps_per_second": 2.863,
"step": 124
},
{
"epoch": 0.1984251968503937,
"eval_loss": 0.28424352407455444,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 126
},
{
"epoch": 0.2015748031496063,
"eval_loss": 0.2861064672470093,
"eval_runtime": 0.3502,
"eval_samples_per_second": 5.71,
"eval_steps_per_second": 2.855,
"step": 128
},
{
"epoch": 0.2047244094488189,
"eval_loss": 0.288029283285141,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 130
},
{
"epoch": 0.2078740157480315,
"eval_loss": 0.29044049978256226,
"eval_runtime": 0.35,
"eval_samples_per_second": 5.714,
"eval_steps_per_second": 2.857,
"step": 132
},
{
"epoch": 0.2110236220472441,
"eval_loss": 0.291236937046051,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.864,
"step": 134
},
{
"epoch": 0.2141732283464567,
"eval_loss": 0.29142552614212036,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 136
},
{
"epoch": 0.2173228346456693,
"eval_loss": 0.29070866107940674,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 138
},
{
"epoch": 0.2204724409448819,
"eval_loss": 0.2889135181903839,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 140
},
{
"epoch": 0.22362204724409449,
"eval_loss": 0.2894015908241272,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 142
},
{
"epoch": 0.22677165354330708,
"eval_loss": 0.28901204466819763,
"eval_runtime": 0.3505,
"eval_samples_per_second": 5.706,
"eval_steps_per_second": 2.853,
"step": 144
},
{
"epoch": 0.22992125984251968,
"eval_loss": 0.28979671001434326,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 146
},
{
"epoch": 0.23307086614173228,
"eval_loss": 0.2905084192752838,
"eval_runtime": 0.3508,
"eval_samples_per_second": 5.702,
"eval_steps_per_second": 2.851,
"step": 148
},
{
"epoch": 0.23622047244094488,
"eval_loss": 0.29154905676841736,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.724,
"eval_steps_per_second": 2.862,
"step": 150
},
{
"epoch": 0.23937007874015748,
"eval_loss": 0.29194581508636475,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.724,
"eval_steps_per_second": 2.862,
"step": 152
},
{
"epoch": 0.24251968503937008,
"eval_loss": 0.2939470410346985,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 154
},
{
"epoch": 0.24566929133858267,
"eval_loss": 0.2964265048503876,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.717,
"eval_steps_per_second": 2.858,
"step": 156
},
{
"epoch": 0.24881889763779527,
"eval_loss": 0.2976249158382416,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.726,
"eval_steps_per_second": 2.863,
"step": 158
},
{
"epoch": 0.25196850393700787,
"eval_loss": 0.2987654507160187,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.866,
"step": 160
},
{
"epoch": 0.2551181102362205,
"eval_loss": 0.2993534505367279,
"eval_runtime": 0.3499,
"eval_samples_per_second": 5.716,
"eval_steps_per_second": 2.858,
"step": 162
},
{
"epoch": 0.25826771653543307,
"eval_loss": 0.30035677552223206,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 164
},
{
"epoch": 0.2614173228346457,
"eval_loss": 0.30072832107543945,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.87,
"step": 166
},
{
"epoch": 0.26456692913385826,
"eval_loss": 0.3005051612854004,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 168
},
{
"epoch": 0.2677165354330709,
"eval_loss": 0.3008230924606323,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.723,
"eval_steps_per_second": 2.862,
"step": 170
},
{
"epoch": 0.27086614173228346,
"eval_loss": 0.29963645339012146,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 172
},
{
"epoch": 0.2740157480314961,
"eval_loss": 0.29796546697616577,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.723,
"eval_steps_per_second": 2.862,
"step": 174
},
{
"epoch": 0.27716535433070866,
"eval_loss": 0.29456067085266113,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 176
},
{
"epoch": 0.2803149606299213,
"eval_loss": 0.29196885228157043,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 178
},
{
"epoch": 0.28346456692913385,
"eval_loss": 0.29017481207847595,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 180
},
{
"epoch": 0.2866141732283465,
"eval_loss": 0.28901177644729614,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 182
},
{
"epoch": 0.28976377952755905,
"eval_loss": 0.28901025652885437,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.723,
"eval_steps_per_second": 2.862,
"step": 184
},
{
"epoch": 0.2929133858267717,
"eval_loss": 0.29002097249031067,
"eval_runtime": 0.352,
"eval_samples_per_second": 5.683,
"eval_steps_per_second": 2.841,
"step": 186
},
{
"epoch": 0.29606299212598425,
"eval_loss": 0.29118070006370544,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.725,
"eval_steps_per_second": 2.863,
"step": 188
},
{
"epoch": 0.2992125984251969,
"eval_loss": 0.2917858958244324,
"eval_runtime": 0.35,
"eval_samples_per_second": 5.714,
"eval_steps_per_second": 2.857,
"step": 190
},
{
"epoch": 0.30236220472440944,
"eval_loss": 0.2924749553203583,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.865,
"step": 192
},
{
"epoch": 0.30551181102362207,
"eval_loss": 0.2916746139526367,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 194
},
{
"epoch": 0.30866141732283464,
"eval_loss": 0.29395443201065063,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 196
},
{
"epoch": 0.31181102362204727,
"eval_loss": 0.293117880821228,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 198
},
{
"epoch": 0.31496062992125984,
"grad_norm": 0.3635024428367615,
"learning_rate": 4.226519337016575e-05,
"loss": 0.3458,
"step": 200
},
{
"epoch": 0.31496062992125984,
"eval_loss": 0.29124823212623596,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 200
},
{
"epoch": 0.31811023622047246,
"eval_loss": 0.2906414568424225,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.865,
"step": 202
},
{
"epoch": 0.32125984251968503,
"eval_loss": 0.29193347692489624,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 204
},
{
"epoch": 0.32440944881889766,
"eval_loss": 0.28856903314590454,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.718,
"eval_steps_per_second": 2.859,
"step": 206
},
{
"epoch": 0.32755905511811023,
"eval_loss": 0.2840542793273926,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 208
},
{
"epoch": 0.33070866141732286,
"eval_loss": 0.2835051417350769,
"eval_runtime": 0.3499,
"eval_samples_per_second": 5.716,
"eval_steps_per_second": 2.858,
"step": 210
},
{
"epoch": 0.33385826771653543,
"eval_loss": 0.2823528051376343,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 212
},
{
"epoch": 0.33700787401574805,
"eval_loss": 0.2810695469379425,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 214
},
{
"epoch": 0.3401574803149606,
"eval_loss": 0.2811725437641144,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.738,
"eval_steps_per_second": 2.869,
"step": 216
},
{
"epoch": 0.34330708661417325,
"eval_loss": 0.2779635787010193,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 218
},
{
"epoch": 0.3464566929133858,
"eval_loss": 0.2761663496494293,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 220
},
{
"epoch": 0.34960629921259845,
"eval_loss": 0.2759172022342682,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 222
},
{
"epoch": 0.352755905511811,
"eval_loss": 0.2744315266609192,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 224
},
{
"epoch": 0.35590551181102364,
"eval_loss": 0.2708997130393982,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.719,
"eval_steps_per_second": 2.86,
"step": 226
},
{
"epoch": 0.3590551181102362,
"eval_loss": 0.26690658926963806,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 228
},
{
"epoch": 0.36220472440944884,
"eval_loss": 0.26654624938964844,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 230
},
{
"epoch": 0.3653543307086614,
"eval_loss": 0.26766911149024963,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 232
},
{
"epoch": 0.36850393700787404,
"eval_loss": 0.26359066367149353,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 234
},
{
"epoch": 0.3716535433070866,
"eval_loss": 0.26057320833206177,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 236
},
{
"epoch": 0.37480314960629924,
"eval_loss": 0.26218682527542114,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.866,
"step": 238
},
{
"epoch": 0.3779527559055118,
"eval_loss": 0.2643265724182129,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 240
},
{
"epoch": 0.38110236220472443,
"eval_loss": 0.26531118154525757,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 242
},
{
"epoch": 0.384251968503937,
"eval_loss": 0.266572505235672,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 244
},
{
"epoch": 0.38740157480314963,
"eval_loss": 0.2653596103191376,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.721,
"eval_steps_per_second": 2.861,
"step": 246
},
{
"epoch": 0.3905511811023622,
"eval_loss": 0.26473838090896606,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 248
},
{
"epoch": 0.3937007874015748,
"eval_loss": 0.2625178396701813,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 250
},
{
"epoch": 0.3968503937007874,
"eval_loss": 0.2609028220176697,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 252
},
{
"epoch": 0.4,
"eval_loss": 0.261107861995697,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 254
},
{
"epoch": 0.4031496062992126,
"eval_loss": 0.26466724276542664,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 256
},
{
"epoch": 0.4062992125984252,
"eval_loss": 0.2641528248786926,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 258
},
{
"epoch": 0.4094488188976378,
"eval_loss": 0.2606296241283417,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 260
},
{
"epoch": 0.4125984251968504,
"eval_loss": 0.25797951221466064,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.724,
"eval_steps_per_second": 2.862,
"step": 262
},
{
"epoch": 0.415748031496063,
"eval_loss": 0.25691765546798706,
"eval_runtime": 0.3501,
"eval_samples_per_second": 5.712,
"eval_steps_per_second": 2.856,
"step": 264
},
{
"epoch": 0.4188976377952756,
"eval_loss": 0.25631454586982727,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 266
},
{
"epoch": 0.4220472440944882,
"eval_loss": 0.2571282982826233,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 268
},
{
"epoch": 0.4251968503937008,
"eval_loss": 0.257975697517395,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 270
},
{
"epoch": 0.4283464566929134,
"eval_loss": 0.2558448612689972,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 272
},
{
"epoch": 0.431496062992126,
"eval_loss": 0.2524794936180115,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 274
},
{
"epoch": 0.4346456692913386,
"eval_loss": 0.2509351670742035,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 276
},
{
"epoch": 0.4377952755905512,
"eval_loss": 0.2509020268917084,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 278
},
{
"epoch": 0.4409448818897638,
"eval_loss": 0.2512817084789276,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 280
},
{
"epoch": 0.4440944881889764,
"eval_loss": 0.25280559062957764,
"eval_runtime": 0.3502,
"eval_samples_per_second": 5.711,
"eval_steps_per_second": 2.856,
"step": 282
},
{
"epoch": 0.44724409448818897,
"eval_loss": 0.25375670194625854,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 284
},
{
"epoch": 0.4503937007874016,
"eval_loss": 0.2527334988117218,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 286
},
{
"epoch": 0.45354330708661417,
"eval_loss": 0.2527409791946411,
"eval_runtime": 0.3508,
"eval_samples_per_second": 5.701,
"eval_steps_per_second": 2.85,
"step": 288
},
{
"epoch": 0.4566929133858268,
"eval_loss": 0.2523551881313324,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 290
},
{
"epoch": 0.45984251968503936,
"eval_loss": 0.2525750994682312,
"eval_runtime": 0.3504,
"eval_samples_per_second": 5.708,
"eval_steps_per_second": 2.854,
"step": 292
},
{
"epoch": 0.462992125984252,
"eval_loss": 0.2522644102573395,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.865,
"step": 294
},
{
"epoch": 0.46614173228346456,
"eval_loss": 0.2501011788845062,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 296
},
{
"epoch": 0.4692913385826772,
"eval_loss": 0.25120070576667786,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.718,
"eval_steps_per_second": 2.859,
"step": 298
},
{
"epoch": 0.47244094488188976,
"grad_norm": 0.46345198154449463,
"learning_rate": 3.8318863456985004e-05,
"loss": 0.3088,
"step": 300
},
{
"epoch": 0.47244094488188976,
"eval_loss": 0.2512536346912384,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.725,
"eval_steps_per_second": 2.862,
"step": 300
},
{
"epoch": 0.4755905511811024,
"eval_loss": 0.25264617800712585,
"eval_runtime": 0.3503,
"eval_samples_per_second": 5.709,
"eval_steps_per_second": 2.854,
"step": 302
},
{
"epoch": 0.47874015748031495,
"eval_loss": 0.2543908357620239,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.726,
"eval_steps_per_second": 2.863,
"step": 304
},
{
"epoch": 0.4818897637795276,
"eval_loss": 0.2570995092391968,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.738,
"eval_steps_per_second": 2.869,
"step": 306
},
{
"epoch": 0.48503937007874015,
"eval_loss": 0.26003941893577576,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 308
},
{
"epoch": 0.4881889763779528,
"eval_loss": 0.2624886631965637,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.724,
"eval_steps_per_second": 2.862,
"step": 310
},
{
"epoch": 0.49133858267716535,
"eval_loss": 0.2620578408241272,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 312
},
{
"epoch": 0.494488188976378,
"eval_loss": 0.26084616780281067,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 314
},
{
"epoch": 0.49763779527559054,
"eval_loss": 0.25816601514816284,
"eval_runtime": 0.3503,
"eval_samples_per_second": 5.709,
"eval_steps_per_second": 2.855,
"step": 316
},
{
"epoch": 0.5007874015748032,
"eval_loss": 0.25735700130462646,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.722,
"eval_steps_per_second": 2.861,
"step": 318
},
{
"epoch": 0.5039370078740157,
"eval_loss": 0.2574799954891205,
"eval_runtime": 0.3495,
"eval_samples_per_second": 5.723,
"eval_steps_per_second": 2.861,
"step": 320
},
{
"epoch": 0.5070866141732283,
"eval_loss": 0.2572091519832611,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.718,
"eval_steps_per_second": 2.859,
"step": 322
},
{
"epoch": 0.510236220472441,
"eval_loss": 0.25527888536453247,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 324
},
{
"epoch": 0.5133858267716536,
"eval_loss": 0.253613144159317,
"eval_runtime": 0.351,
"eval_samples_per_second": 5.698,
"eval_steps_per_second": 2.849,
"step": 326
},
{
"epoch": 0.5165354330708661,
"eval_loss": 0.2540742754936218,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 328
},
{
"epoch": 0.5196850393700787,
"eval_loss": 0.25379279255867004,
"eval_runtime": 0.3522,
"eval_samples_per_second": 5.678,
"eval_steps_per_second": 2.839,
"step": 330
},
{
"epoch": 0.5228346456692914,
"eval_loss": 0.2537696659564972,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 332
},
{
"epoch": 0.525984251968504,
"eval_loss": 0.25334689021110535,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 334
},
{
"epoch": 0.5291338582677165,
"eval_loss": 0.25465843081474304,
"eval_runtime": 0.35,
"eval_samples_per_second": 5.714,
"eval_steps_per_second": 2.857,
"step": 336
},
{
"epoch": 0.5322834645669291,
"eval_loss": 0.25427162647247314,
"eval_runtime": 0.35,
"eval_samples_per_second": 5.715,
"eval_steps_per_second": 2.858,
"step": 338
},
{
"epoch": 0.5354330708661418,
"eval_loss": 0.2515546977519989,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 340
},
{
"epoch": 0.5385826771653544,
"eval_loss": 0.25021684169769287,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 342
},
{
"epoch": 0.5417322834645669,
"eval_loss": 0.24849390983581543,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.719,
"eval_steps_per_second": 2.859,
"step": 344
},
{
"epoch": 0.5448818897637795,
"eval_loss": 0.24830685555934906,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 346
},
{
"epoch": 0.5480314960629922,
"eval_loss": 0.24721373617649078,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 348
},
{
"epoch": 0.5511811023622047,
"eval_loss": 0.24681712687015533,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.869,
"step": 350
},
{
"epoch": 0.5543307086614173,
"eval_loss": 0.24766646325588226,
"eval_runtime": 0.3511,
"eval_samples_per_second": 5.697,
"eval_steps_per_second": 2.849,
"step": 352
},
{
"epoch": 0.5574803149606299,
"eval_loss": 0.24951478838920593,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.726,
"eval_steps_per_second": 2.863,
"step": 354
},
{
"epoch": 0.5606299212598426,
"eval_loss": 0.25090062618255615,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 356
},
{
"epoch": 0.5637795275590551,
"eval_loss": 0.2526218891143799,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 358
},
{
"epoch": 0.5669291338582677,
"eval_loss": 0.2541698217391968,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 360
},
{
"epoch": 0.5700787401574803,
"eval_loss": 0.25507837533950806,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.721,
"eval_steps_per_second": 2.86,
"step": 362
},
{
"epoch": 0.573228346456693,
"eval_loss": 0.25495150685310364,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 364
},
{
"epoch": 0.5763779527559055,
"eval_loss": 0.2539258897304535,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 366
},
{
"epoch": 0.5795275590551181,
"eval_loss": 0.25175759196281433,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 368
},
{
"epoch": 0.5826771653543307,
"eval_loss": 0.2497943490743637,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 370
},
{
"epoch": 0.5858267716535434,
"eval_loss": 0.24950113892555237,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.721,
"eval_steps_per_second": 2.86,
"step": 372
},
{
"epoch": 0.5889763779527559,
"eval_loss": 0.24870949983596802,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 374
},
{
"epoch": 0.5921259842519685,
"eval_loss": 0.2483173906803131,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.866,
"step": 376
},
{
"epoch": 0.5952755905511811,
"eval_loss": 0.24755032360553741,
"eval_runtime": 0.3493,
"eval_samples_per_second": 5.726,
"eval_steps_per_second": 2.863,
"step": 378
},
{
"epoch": 0.5984251968503937,
"eval_loss": 0.2489040344953537,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.721,
"eval_steps_per_second": 2.86,
"step": 380
},
{
"epoch": 0.6015748031496063,
"eval_loss": 0.2493334263563156,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 382
},
{
"epoch": 0.6047244094488189,
"eval_loss": 0.24853859841823578,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 384
},
{
"epoch": 0.6078740157480315,
"eval_loss": 0.2470569610595703,
"eval_runtime": 0.3501,
"eval_samples_per_second": 5.713,
"eval_steps_per_second": 2.857,
"step": 386
},
{
"epoch": 0.6110236220472441,
"eval_loss": 0.2444409430027008,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.738,
"eval_steps_per_second": 2.869,
"step": 388
},
{
"epoch": 0.6141732283464567,
"eval_loss": 0.2418692260980606,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 390
},
{
"epoch": 0.6173228346456693,
"eval_loss": 0.23993785679340363,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 392
},
{
"epoch": 0.6204724409448819,
"eval_loss": 0.23856890201568604,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 394
},
{
"epoch": 0.6236220472440945,
"eval_loss": 0.23821412026882172,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.866,
"step": 396
},
{
"epoch": 0.6267716535433071,
"eval_loss": 0.23897697031497955,
"eval_runtime": 0.3514,
"eval_samples_per_second": 5.691,
"eval_steps_per_second": 2.845,
"step": 398
},
{
"epoch": 0.6299212598425197,
"grad_norm": 0.5196242332458496,
"learning_rate": 3.4372533543804266e-05,
"loss": 0.2983,
"step": 400
},
{
"epoch": 0.6299212598425197,
"eval_loss": 0.23973239958286285,
"eval_runtime": 0.3504,
"eval_samples_per_second": 5.708,
"eval_steps_per_second": 2.854,
"step": 400
},
{
"epoch": 0.6330708661417322,
"eval_loss": 0.2410946935415268,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 402
},
{
"epoch": 0.6362204724409449,
"eval_loss": 0.24067173898220062,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 404
},
{
"epoch": 0.6393700787401575,
"eval_loss": 0.24163953959941864,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 406
},
{
"epoch": 0.6425196850393701,
"eval_loss": 0.2431313842535019,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 408
},
{
"epoch": 0.6456692913385826,
"eval_loss": 0.2444837987422943,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 410
},
{
"epoch": 0.6488188976377953,
"eval_loss": 0.24561473727226257,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 412
},
{
"epoch": 0.6519685039370079,
"eval_loss": 0.24582655727863312,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 414
},
{
"epoch": 0.6551181102362205,
"eval_loss": 0.24571368098258972,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 416
},
{
"epoch": 0.658267716535433,
"eval_loss": 0.24614694714546204,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.874,
"step": 418
},
{
"epoch": 0.6614173228346457,
"eval_loss": 0.24703222513198853,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 420
},
{
"epoch": 0.6645669291338583,
"eval_loss": 0.24814102053642273,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.773,
"eval_steps_per_second": 2.886,
"step": 422
},
{
"epoch": 0.6677165354330709,
"eval_loss": 0.250097393989563,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 424
},
{
"epoch": 0.6708661417322834,
"eval_loss": 0.2515372037887573,
"eval_runtime": 0.3531,
"eval_samples_per_second": 5.664,
"eval_steps_per_second": 2.832,
"step": 426
},
{
"epoch": 0.6740157480314961,
"eval_loss": 0.25102341175079346,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 428
},
{
"epoch": 0.6771653543307087,
"eval_loss": 0.2481279969215393,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 430
},
{
"epoch": 0.6803149606299213,
"eval_loss": 0.2458999902009964,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 432
},
{
"epoch": 0.6834645669291338,
"eval_loss": 0.24467678368091583,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 434
},
{
"epoch": 0.6866141732283465,
"eval_loss": 0.2433977723121643,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 436
},
{
"epoch": 0.6897637795275591,
"eval_loss": 0.2426670640707016,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 438
},
{
"epoch": 0.6929133858267716,
"eval_loss": 0.24378836154937744,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 440
},
{
"epoch": 0.6960629921259842,
"eval_loss": 0.24309661984443665,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 442
},
{
"epoch": 0.6992125984251969,
"eval_loss": 0.2418668121099472,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 444
},
{
"epoch": 0.7023622047244095,
"eval_loss": 0.24033157527446747,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.883,
"step": 446
},
{
"epoch": 0.705511811023622,
"eval_loss": 0.2397001087665558,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 448
},
{
"epoch": 0.7086614173228346,
"eval_loss": 0.2389679253101349,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 450
},
{
"epoch": 0.7118110236220473,
"eval_loss": 0.23955169320106506,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.876,
"step": 452
},
{
"epoch": 0.7149606299212599,
"eval_loss": 0.24064964056015015,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.876,
"step": 454
},
{
"epoch": 0.7181102362204724,
"eval_loss": 0.24189099669456482,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 456
},
{
"epoch": 0.721259842519685,
"eval_loss": 0.24446824193000793,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 458
},
{
"epoch": 0.7244094488188977,
"eval_loss": 0.24581347405910492,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 460
},
{
"epoch": 0.7275590551181103,
"eval_loss": 0.2461909055709839,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 462
},
{
"epoch": 0.7307086614173228,
"eval_loss": 0.24555188417434692,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 464
},
{
"epoch": 0.7338582677165354,
"eval_loss": 0.24435029923915863,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.884,
"step": 466
},
{
"epoch": 0.7370078740157481,
"eval_loss": 0.24303168058395386,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 468
},
{
"epoch": 0.7401574803149606,
"eval_loss": 0.2416306883096695,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 470
},
{
"epoch": 0.7433070866141732,
"eval_loss": 0.24084311723709106,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 472
},
{
"epoch": 0.7464566929133858,
"eval_loss": 0.24014924466609955,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 474
},
{
"epoch": 0.7496062992125985,
"eval_loss": 0.23961803317070007,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 476
},
{
"epoch": 0.752755905511811,
"eval_loss": 0.23997950553894043,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 478
},
{
"epoch": 0.7559055118110236,
"eval_loss": 0.2407733052968979,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 480
},
{
"epoch": 0.7590551181102362,
"eval_loss": 0.24159416556358337,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.87,
"step": 482
},
{
"epoch": 0.7622047244094489,
"eval_loss": 0.24023914337158203,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 484
},
{
"epoch": 0.7653543307086614,
"eval_loss": 0.23918534815311432,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 486
},
{
"epoch": 0.768503937007874,
"eval_loss": 0.23954296112060547,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.869,
"step": 488
},
{
"epoch": 0.7716535433070866,
"eval_loss": 0.24002641439437866,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.883,
"step": 490
},
{
"epoch": 0.7748031496062993,
"eval_loss": 0.24019937217235565,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 492
},
{
"epoch": 0.7779527559055118,
"eval_loss": 0.23941951990127563,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 494
},
{
"epoch": 0.7811023622047244,
"eval_loss": 0.23951633274555206,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.738,
"eval_steps_per_second": 2.869,
"step": 496
},
{
"epoch": 0.784251968503937,
"eval_loss": 0.23965123295783997,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 498
},
{
"epoch": 0.7874015748031497,
"grad_norm": 0.42014506459236145,
"learning_rate": 3.0426203630623522e-05,
"loss": 0.2983,
"step": 500
},
{
"epoch": 0.7874015748031497,
"eval_loss": 0.23971280455589294,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 500
},
{
"epoch": 0.7905511811023622,
"eval_loss": 0.23899975419044495,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 502
},
{
"epoch": 0.7937007874015748,
"eval_loss": 0.2383013367652893,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.883,
"step": 504
},
{
"epoch": 0.7968503937007874,
"eval_loss": 0.2383585423231125,
"eval_runtime": 0.3459,
"eval_samples_per_second": 5.781,
"eval_steps_per_second": 2.891,
"step": 506
},
{
"epoch": 0.8,
"eval_loss": 0.23841704428195953,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 508
},
{
"epoch": 0.8031496062992126,
"eval_loss": 0.23884700238704681,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 510
},
{
"epoch": 0.8062992125984252,
"eval_loss": 0.23903228342533112,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 512
},
{
"epoch": 0.8094488188976378,
"eval_loss": 0.2404712289571762,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 514
},
{
"epoch": 0.8125984251968504,
"eval_loss": 0.2417348325252533,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 516
},
{
"epoch": 0.815748031496063,
"eval_loss": 0.2421807497739792,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 518
},
{
"epoch": 0.8188976377952756,
"eval_loss": 0.2430046647787094,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 520
},
{
"epoch": 0.8220472440944881,
"eval_loss": 0.23838551342487335,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 522
},
{
"epoch": 0.8251968503937008,
"eval_loss": 0.23211409151554108,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 524
},
{
"epoch": 0.8283464566929134,
"eval_loss": 0.22673740983009338,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 526
},
{
"epoch": 0.831496062992126,
"eval_loss": 0.22330711781978607,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.763,
"eval_steps_per_second": 2.881,
"step": 528
},
{
"epoch": 0.8346456692913385,
"eval_loss": 0.22061069309711456,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.883,
"step": 530
},
{
"epoch": 0.8377952755905512,
"eval_loss": 0.21939681470394135,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 532
},
{
"epoch": 0.8409448818897638,
"eval_loss": 0.2190093696117401,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 534
},
{
"epoch": 0.8440944881889764,
"eval_loss": 0.21911847591400146,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 536
},
{
"epoch": 0.8472440944881889,
"eval_loss": 0.21935874223709106,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 538
},
{
"epoch": 0.8503937007874016,
"eval_loss": 0.21970351040363312,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 540
},
{
"epoch": 0.8535433070866142,
"eval_loss": 0.2186441719532013,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 542
},
{
"epoch": 0.8566929133858268,
"eval_loss": 0.21871551871299744,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.87,
"step": 544
},
{
"epoch": 0.8598425196850393,
"eval_loss": 0.2186393290758133,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 546
},
{
"epoch": 0.862992125984252,
"eval_loss": 0.21857605874538422,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 548
},
{
"epoch": 0.8661417322834646,
"eval_loss": 0.21860800683498383,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 550
},
{
"epoch": 0.8692913385826772,
"eval_loss": 0.21862417459487915,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 552
},
{
"epoch": 0.8724409448818897,
"eval_loss": 0.21853011846542358,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 554
},
{
"epoch": 0.8755905511811024,
"eval_loss": 0.21876664459705353,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.885,
"step": 556
},
{
"epoch": 0.878740157480315,
"eval_loss": 0.21962060034275055,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 558
},
{
"epoch": 0.8818897637795275,
"eval_loss": 0.22009848058223724,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 560
},
{
"epoch": 0.8850393700787401,
"eval_loss": 0.22019439935684204,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 562
},
{
"epoch": 0.8881889763779528,
"eval_loss": 0.22041678428649902,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 564
},
{
"epoch": 0.8913385826771654,
"eval_loss": 0.2202569991350174,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.881,
"step": 566
},
{
"epoch": 0.8944881889763779,
"eval_loss": 0.22122207283973694,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 568
},
{
"epoch": 0.8976377952755905,
"eval_loss": 0.2212667316198349,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 570
},
{
"epoch": 0.9007874015748032,
"eval_loss": 0.22105658054351807,
"eval_runtime": 0.3457,
"eval_samples_per_second": 5.786,
"eval_steps_per_second": 2.893,
"step": 572
},
{
"epoch": 0.9039370078740158,
"eval_loss": 0.2216799110174179,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 574
},
{
"epoch": 0.9070866141732283,
"eval_loss": 0.2226579189300537,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 576
},
{
"epoch": 0.9102362204724409,
"eval_loss": 0.2236708700656891,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 578
},
{
"epoch": 0.9133858267716536,
"eval_loss": 0.22398383915424347,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 580
},
{
"epoch": 0.9165354330708662,
"eval_loss": 0.22460885345935822,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 582
},
{
"epoch": 0.9196850393700787,
"eval_loss": 0.2247941941022873,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.775,
"eval_steps_per_second": 2.888,
"step": 584
},
{
"epoch": 0.9228346456692913,
"eval_loss": 0.22421392798423767,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 586
},
{
"epoch": 0.925984251968504,
"eval_loss": 0.22418507933616638,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 588
},
{
"epoch": 0.9291338582677166,
"eval_loss": 0.22449295222759247,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 590
},
{
"epoch": 0.9322834645669291,
"eval_loss": 0.22475506365299225,
"eval_runtime": 0.3456,
"eval_samples_per_second": 5.787,
"eval_steps_per_second": 2.894,
"step": 592
},
{
"epoch": 0.9354330708661417,
"eval_loss": 0.22587281465530396,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 594
},
{
"epoch": 0.9385826771653544,
"eval_loss": 0.22632764279842377,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 596
},
{
"epoch": 0.9417322834645669,
"eval_loss": 0.22690095007419586,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 598
},
{
"epoch": 0.9448818897637795,
"grad_norm": 0.5656266212463379,
"learning_rate": 2.6479873717442778e-05,
"loss": 0.2919,
"step": 600
},
{
"epoch": 0.9448818897637795,
"eval_loss": 0.22817616164684296,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 600
},
{
"epoch": 0.9480314960629921,
"eval_loss": 0.2281908094882965,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 602
},
{
"epoch": 0.9511811023622048,
"eval_loss": 0.2282770872116089,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 604
},
{
"epoch": 0.9543307086614173,
"eval_loss": 0.2281230390071869,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 606
},
{
"epoch": 0.9574803149606299,
"eval_loss": 0.2278699427843094,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 608
},
{
"epoch": 0.9606299212598425,
"eval_loss": 0.22721613943576813,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 610
},
{
"epoch": 0.9637795275590552,
"eval_loss": 0.22704194486141205,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 612
},
{
"epoch": 0.9669291338582677,
"eval_loss": 0.22705890238285065,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 614
},
{
"epoch": 0.9700787401574803,
"eval_loss": 0.22742748260498047,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.763,
"eval_steps_per_second": 2.882,
"step": 616
},
{
"epoch": 0.9732283464566929,
"eval_loss": 0.22810114920139313,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 618
},
{
"epoch": 0.9763779527559056,
"eval_loss": 0.22877345979213715,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 620
},
{
"epoch": 0.9795275590551181,
"eval_loss": 0.22847406566143036,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 622
},
{
"epoch": 0.9826771653543307,
"eval_loss": 0.22826185822486877,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 624
},
{
"epoch": 0.9858267716535433,
"eval_loss": 0.2278900295495987,
"eval_runtime": 0.3462,
"eval_samples_per_second": 5.777,
"eval_steps_per_second": 2.889,
"step": 626
},
{
"epoch": 0.988976377952756,
"eval_loss": 0.22757789492607117,
"eval_runtime": 0.3461,
"eval_samples_per_second": 5.779,
"eval_steps_per_second": 2.89,
"step": 628
},
{
"epoch": 0.9921259842519685,
"eval_loss": 0.22795431315898895,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 630
},
{
"epoch": 0.9952755905511811,
"eval_loss": 0.2281695455312729,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 632
},
{
"epoch": 0.9984251968503937,
"eval_loss": 0.22744913399219513,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 634
},
{
"epoch": 1.0015748031496063,
"eval_loss": 0.2271132916212082,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 636
},
{
"epoch": 1.0047244094488188,
"eval_loss": 0.22724951803684235,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 638
},
{
"epoch": 1.0078740157480315,
"eval_loss": 0.22710062563419342,
"eval_runtime": 0.3457,
"eval_samples_per_second": 5.785,
"eval_steps_per_second": 2.892,
"step": 640
},
{
"epoch": 1.0110236220472442,
"eval_loss": 0.22758325934410095,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 642
},
{
"epoch": 1.0141732283464566,
"eval_loss": 0.22726833820343018,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 644
},
{
"epoch": 1.0173228346456693,
"eval_loss": 0.22711965441703796,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 646
},
{
"epoch": 1.020472440944882,
"eval_loss": 0.22676637768745422,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 648
},
{
"epoch": 1.0236220472440944,
"eval_loss": 0.22597311437129974,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 650
},
{
"epoch": 1.0267716535433071,
"eval_loss": 0.22496254742145538,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 652
},
{
"epoch": 1.0299212598425196,
"eval_loss": 0.22419819235801697,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 654
},
{
"epoch": 1.0330708661417323,
"eval_loss": 0.22414547204971313,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 656
},
{
"epoch": 1.036220472440945,
"eval_loss": 0.22434547543525696,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 658
},
{
"epoch": 1.0393700787401574,
"eval_loss": 0.22517438232898712,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 660
},
{
"epoch": 1.04251968503937,
"eval_loss": 0.22600756585597992,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 662
},
{
"epoch": 1.0456692913385828,
"eval_loss": 0.2269682139158249,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 664
},
{
"epoch": 1.0488188976377952,
"eval_loss": 0.22615931928157806,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.881,
"step": 666
},
{
"epoch": 1.051968503937008,
"eval_loss": 0.22478696703910828,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 668
},
{
"epoch": 1.0551181102362204,
"eval_loss": 0.2241896241903305,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.774,
"eval_steps_per_second": 2.887,
"step": 670
},
{
"epoch": 1.058267716535433,
"eval_loss": 0.22383634746074677,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 672
},
{
"epoch": 1.0614173228346457,
"eval_loss": 0.2242012619972229,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 674
},
{
"epoch": 1.0645669291338582,
"eval_loss": 0.22520413994789124,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 676
},
{
"epoch": 1.0677165354330709,
"eval_loss": 0.22569924592971802,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.774,
"eval_steps_per_second": 2.887,
"step": 678
},
{
"epoch": 1.0708661417322836,
"eval_loss": 0.22563116252422333,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 680
},
{
"epoch": 1.074015748031496,
"eval_loss": 0.2253970205783844,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 682
},
{
"epoch": 1.0771653543307087,
"eval_loss": 0.22523759305477142,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 684
},
{
"epoch": 1.0803149606299212,
"eval_loss": 0.22503849864006042,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 686
},
{
"epoch": 1.0834645669291338,
"eval_loss": 0.22514674067497253,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 688
},
{
"epoch": 1.0866141732283465,
"eval_loss": 0.22560672461986542,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.883,
"step": 690
},
{
"epoch": 1.089763779527559,
"eval_loss": 0.2260504513978958,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 692
},
{
"epoch": 1.0929133858267717,
"eval_loss": 0.22611144185066223,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 694
},
{
"epoch": 1.0960629921259843,
"eval_loss": 0.2217782437801361,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 696
},
{
"epoch": 1.0992125984251968,
"eval_loss": 0.21539410948753357,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 698
},
{
"epoch": 1.1023622047244095,
"grad_norm": 0.5258780121803284,
"learning_rate": 2.2533543804262037e-05,
"loss": 0.2703,
"step": 700
},
{
"epoch": 1.1023622047244095,
"eval_loss": 0.21107958257198334,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.769,
"eval_steps_per_second": 2.884,
"step": 700
},
{
"epoch": 1.105511811023622,
"eval_loss": 0.20768335461616516,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 702
},
{
"epoch": 1.1086614173228346,
"eval_loss": 0.2053837776184082,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 704
},
{
"epoch": 1.1118110236220473,
"eval_loss": 0.20381729304790497,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 706
},
{
"epoch": 1.1149606299212598,
"eval_loss": 0.20234201848506927,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 708
},
{
"epoch": 1.1181102362204725,
"eval_loss": 0.2007295787334442,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 710
},
{
"epoch": 1.1212598425196851,
"eval_loss": 0.1999751776456833,
"eval_runtime": 0.3461,
"eval_samples_per_second": 5.779,
"eval_steps_per_second": 2.889,
"step": 712
},
{
"epoch": 1.1244094488188976,
"eval_loss": 0.20004306733608246,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 714
},
{
"epoch": 1.1275590551181103,
"eval_loss": 0.20042680203914642,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 716
},
{
"epoch": 1.130708661417323,
"eval_loss": 0.2011932134628296,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 718
},
{
"epoch": 1.1338582677165354,
"eval_loss": 0.20276018977165222,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 720
},
{
"epoch": 1.137007874015748,
"eval_loss": 0.20337159931659698,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.885,
"step": 722
},
{
"epoch": 1.1401574803149606,
"eval_loss": 0.20352710783481598,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 724
},
{
"epoch": 1.1433070866141732,
"eval_loss": 0.20363833010196686,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 726
},
{
"epoch": 1.146456692913386,
"eval_loss": 0.20363201200962067,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 728
},
{
"epoch": 1.1496062992125984,
"eval_loss": 0.2034953385591507,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.87,
"step": 730
},
{
"epoch": 1.152755905511811,
"eval_loss": 0.20352262258529663,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 732
},
{
"epoch": 1.1559055118110235,
"eval_loss": 0.20351071655750275,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 734
},
{
"epoch": 1.1590551181102362,
"eval_loss": 0.2037033587694168,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.886,
"step": 736
},
{
"epoch": 1.1622047244094489,
"eval_loss": 0.2041216641664505,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 738
},
{
"epoch": 1.1653543307086613,
"eval_loss": 0.20417848229408264,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.869,
"step": 740
},
{
"epoch": 1.168503937007874,
"eval_loss": 0.20413048565387726,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 742
},
{
"epoch": 1.1716535433070867,
"eval_loss": 0.20458516478538513,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 744
},
{
"epoch": 1.1748031496062992,
"eval_loss": 0.20432934165000916,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 746
},
{
"epoch": 1.1779527559055119,
"eval_loss": 0.20491603016853333,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 748
},
{
"epoch": 1.1811023622047245,
"eval_loss": 0.20502789318561554,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.775,
"eval_steps_per_second": 2.888,
"step": 750
},
{
"epoch": 1.184251968503937,
"eval_loss": 0.20499026775360107,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 752
},
{
"epoch": 1.1874015748031497,
"eval_loss": 0.2051118165254593,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 754
},
{
"epoch": 1.1905511811023621,
"eval_loss": 0.204225555062294,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.876,
"step": 756
},
{
"epoch": 1.1937007874015748,
"eval_loss": 0.20409975945949554,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.885,
"step": 758
},
{
"epoch": 1.1968503937007875,
"eval_loss": 0.20343449711799622,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 760
},
{
"epoch": 1.2,
"eval_loss": 0.20293109118938446,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 762
},
{
"epoch": 1.2031496062992126,
"eval_loss": 0.2029263973236084,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 764
},
{
"epoch": 1.206299212598425,
"eval_loss": 0.20265820622444153,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 766
},
{
"epoch": 1.2094488188976378,
"eval_loss": 0.20328301191329956,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.773,
"eval_steps_per_second": 2.886,
"step": 768
},
{
"epoch": 1.2125984251968505,
"eval_loss": 0.2034366875886917,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 770
},
{
"epoch": 1.215748031496063,
"eval_loss": 0.2036745399236679,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 772
},
{
"epoch": 1.2188976377952756,
"eval_loss": 0.204311341047287,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.884,
"step": 774
},
{
"epoch": 1.2220472440944883,
"eval_loss": 0.20514029264450073,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 776
},
{
"epoch": 1.2251968503937007,
"eval_loss": 0.20625926554203033,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.77,
"eval_steps_per_second": 2.885,
"step": 778
},
{
"epoch": 1.2283464566929134,
"eval_loss": 0.20752117037773132,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.883,
"step": 780
},
{
"epoch": 1.231496062992126,
"eval_loss": 0.20780110359191895,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 782
},
{
"epoch": 1.2346456692913386,
"eval_loss": 0.20721979439258575,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 784
},
{
"epoch": 1.2377952755905512,
"eval_loss": 0.20642000436782837,
"eval_runtime": 0.3541,
"eval_samples_per_second": 5.647,
"eval_steps_per_second": 2.824,
"step": 786
},
{
"epoch": 1.2409448818897637,
"eval_loss": 0.20629778504371643,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 788
},
{
"epoch": 1.2440944881889764,
"eval_loss": 0.205973818898201,
"eval_runtime": 0.3534,
"eval_samples_per_second": 5.66,
"eval_steps_per_second": 2.83,
"step": 790
},
{
"epoch": 1.247244094488189,
"eval_loss": 0.20671075582504272,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 792
},
{
"epoch": 1.2503937007874015,
"eval_loss": 0.2069523185491562,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 794
},
{
"epoch": 1.2535433070866142,
"eval_loss": 0.20688612759113312,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.864,
"step": 796
},
{
"epoch": 1.2566929133858267,
"eval_loss": 0.20710517466068268,
"eval_runtime": 0.3499,
"eval_samples_per_second": 5.715,
"eval_steps_per_second": 2.858,
"step": 798
},
{
"epoch": 1.2598425196850394,
"grad_norm": 0.5626622438430786,
"learning_rate": 1.8587213891081296e-05,
"loss": 0.2685,
"step": 800
},
{
"epoch": 1.2598425196850394,
"eval_loss": 0.20730409026145935,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 800
},
{
"epoch": 1.262992125984252,
"eval_loss": 0.20660564303398132,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.751,
"eval_steps_per_second": 2.875,
"step": 802
},
{
"epoch": 1.2661417322834645,
"eval_loss": 0.20662806928157806,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 804
},
{
"epoch": 1.2692913385826772,
"eval_loss": 0.20607197284698486,
"eval_runtime": 0.3502,
"eval_samples_per_second": 5.712,
"eval_steps_per_second": 2.856,
"step": 806
},
{
"epoch": 1.2724409448818896,
"eval_loss": 0.2064536064863205,
"eval_runtime": 0.3499,
"eval_samples_per_second": 5.717,
"eval_steps_per_second": 2.858,
"step": 808
},
{
"epoch": 1.2755905511811023,
"eval_loss": 0.20620197057724,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 810
},
{
"epoch": 1.278740157480315,
"eval_loss": 0.20696645975112915,
"eval_runtime": 0.3502,
"eval_samples_per_second": 5.711,
"eval_steps_per_second": 2.855,
"step": 812
},
{
"epoch": 1.2818897637795277,
"eval_loss": 0.2076433151960373,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.875,
"step": 814
},
{
"epoch": 1.2850393700787401,
"eval_loss": 0.20663098990917206,
"eval_runtime": 0.3526,
"eval_samples_per_second": 5.672,
"eval_steps_per_second": 2.836,
"step": 816
},
{
"epoch": 1.2881889763779528,
"eval_loss": 0.20660889148712158,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.724,
"eval_steps_per_second": 2.862,
"step": 818
},
{
"epoch": 1.2913385826771653,
"eval_loss": 0.2062617987394333,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.865,
"step": 820
},
{
"epoch": 1.294488188976378,
"eval_loss": 0.20592600107192993,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 822
},
{
"epoch": 1.2976377952755906,
"eval_loss": 0.20610259473323822,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 824
},
{
"epoch": 1.300787401574803,
"eval_loss": 0.20624753832817078,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 826
},
{
"epoch": 1.3039370078740158,
"eval_loss": 0.2069290578365326,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.874,
"step": 828
},
{
"epoch": 1.3070866141732282,
"eval_loss": 0.20712094008922577,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 830
},
{
"epoch": 1.310236220472441,
"eval_loss": 0.20737168192863464,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 832
},
{
"epoch": 1.3133858267716536,
"eval_loss": 0.2067430317401886,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 834
},
{
"epoch": 1.316535433070866,
"eval_loss": 0.20565177500247955,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 836
},
{
"epoch": 1.3196850393700787,
"eval_loss": 0.20468740165233612,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 838
},
{
"epoch": 1.3228346456692912,
"eval_loss": 0.20325765013694763,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 840
},
{
"epoch": 1.325984251968504,
"eval_loss": 0.20253823697566986,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 842
},
{
"epoch": 1.3291338582677166,
"eval_loss": 0.20254985988140106,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 844
},
{
"epoch": 1.3322834645669293,
"eval_loss": 0.2022475153207779,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 846
},
{
"epoch": 1.3354330708661417,
"eval_loss": 0.2029331922531128,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.866,
"step": 848
},
{
"epoch": 1.3385826771653544,
"eval_loss": 0.20355044305324554,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 850
},
{
"epoch": 1.3417322834645669,
"eval_loss": 0.20381534099578857,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.864,
"step": 852
},
{
"epoch": 1.3448818897637795,
"eval_loss": 0.20437617599964142,
"eval_runtime": 0.3499,
"eval_samples_per_second": 5.717,
"eval_steps_per_second": 2.858,
"step": 854
},
{
"epoch": 1.3480314960629922,
"eval_loss": 0.20404097437858582,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 856
},
{
"epoch": 1.3511811023622047,
"eval_loss": 0.20378455519676208,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 858
},
{
"epoch": 1.3543307086614174,
"eval_loss": 0.20325225591659546,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 860
},
{
"epoch": 1.3574803149606298,
"eval_loss": 0.20305326581001282,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 862
},
{
"epoch": 1.3606299212598425,
"eval_loss": 0.2026721090078354,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 864
},
{
"epoch": 1.3637795275590552,
"eval_loss": 0.20210377871990204,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 866
},
{
"epoch": 1.3669291338582676,
"eval_loss": 0.2014118731021881,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 868
},
{
"epoch": 1.3700787401574803,
"eval_loss": 0.20117370784282684,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 870
},
{
"epoch": 1.3732283464566928,
"eval_loss": 0.20069845020771027,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 872
},
{
"epoch": 1.3763779527559055,
"eval_loss": 0.20121270418167114,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.72,
"eval_steps_per_second": 2.86,
"step": 874
},
{
"epoch": 1.3795275590551181,
"eval_loss": 0.20093250274658203,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 876
},
{
"epoch": 1.3826771653543308,
"eval_loss": 0.2023553103208542,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 878
},
{
"epoch": 1.3858267716535433,
"eval_loss": 0.20359212160110474,
"eval_runtime": 0.3496,
"eval_samples_per_second": 5.721,
"eval_steps_per_second": 2.861,
"step": 880
},
{
"epoch": 1.388976377952756,
"eval_loss": 0.2043958157300949,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.73,
"eval_steps_per_second": 2.865,
"step": 882
},
{
"epoch": 1.3921259842519684,
"eval_loss": 0.20474563539028168,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 884
},
{
"epoch": 1.395275590551181,
"eval_loss": 0.20475420355796814,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 886
},
{
"epoch": 1.3984251968503938,
"eval_loss": 0.20483875274658203,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.874,
"step": 888
},
{
"epoch": 1.4015748031496063,
"eval_loss": 0.20389942824840546,
"eval_runtime": 0.3509,
"eval_samples_per_second": 5.7,
"eval_steps_per_second": 2.85,
"step": 890
},
{
"epoch": 1.404724409448819,
"eval_loss": 0.20294560492038727,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 892
},
{
"epoch": 1.4078740157480314,
"eval_loss": 0.2022228091955185,
"eval_runtime": 0.3512,
"eval_samples_per_second": 5.695,
"eval_steps_per_second": 2.847,
"step": 894
},
{
"epoch": 1.411023622047244,
"eval_loss": 0.20171600580215454,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.718,
"eval_steps_per_second": 2.859,
"step": 896
},
{
"epoch": 1.4141732283464568,
"eval_loss": 0.2025589644908905,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.732,
"eval_steps_per_second": 2.866,
"step": 898
},
{
"epoch": 1.4173228346456692,
"grad_norm": 0.6045472621917725,
"learning_rate": 1.4640883977900552e-05,
"loss": 0.2629,
"step": 900
},
{
"epoch": 1.4173228346456692,
"eval_loss": 0.2025490701198578,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 900
},
{
"epoch": 1.420472440944882,
"eval_loss": 0.20404885709285736,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 902
},
{
"epoch": 1.4236220472440944,
"eval_loss": 0.20501871407032013,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.881,
"step": 904
},
{
"epoch": 1.426771653543307,
"eval_loss": 0.20589396357536316,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 906
},
{
"epoch": 1.4299212598425197,
"eval_loss": 0.20673611760139465,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.866,
"step": 908
},
{
"epoch": 1.4330708661417324,
"eval_loss": 0.20699208974838257,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 910
},
{
"epoch": 1.4362204724409449,
"eval_loss": 0.20726977288722992,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 912
},
{
"epoch": 1.4393700787401575,
"eval_loss": 0.20725278556346893,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 914
},
{
"epoch": 1.44251968503937,
"eval_loss": 0.2062389999628067,
"eval_runtime": 0.3494,
"eval_samples_per_second": 5.725,
"eval_steps_per_second": 2.862,
"step": 916
},
{
"epoch": 1.4456692913385827,
"eval_loss": 0.20649917423725128,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 918
},
{
"epoch": 1.4488188976377954,
"eval_loss": 0.20573976635932922,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 920
},
{
"epoch": 1.4519685039370078,
"eval_loss": 0.20533862709999084,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 922
},
{
"epoch": 1.4551181102362205,
"eval_loss": 0.20516476035118103,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.87,
"step": 924
},
{
"epoch": 1.458267716535433,
"eval_loss": 0.20424659550189972,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 926
},
{
"epoch": 1.4614173228346456,
"eval_loss": 0.2035505771636963,
"eval_runtime": 0.3501,
"eval_samples_per_second": 5.713,
"eval_steps_per_second": 2.856,
"step": 928
},
{
"epoch": 1.4645669291338583,
"eval_loss": 0.20261389017105103,
"eval_runtime": 0.349,
"eval_samples_per_second": 5.731,
"eval_steps_per_second": 2.865,
"step": 930
},
{
"epoch": 1.4677165354330708,
"eval_loss": 0.20240332186222076,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 932
},
{
"epoch": 1.4708661417322835,
"eval_loss": 0.20212148129940033,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.749,
"eval_steps_per_second": 2.874,
"step": 934
},
{
"epoch": 1.474015748031496,
"eval_loss": 0.2025633007287979,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 936
},
{
"epoch": 1.4771653543307086,
"eval_loss": 0.2020474374294281,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 938
},
{
"epoch": 1.4803149606299213,
"eval_loss": 0.20244111120700836,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 940
},
{
"epoch": 1.483464566929134,
"eval_loss": 0.20223170518875122,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.886,
"step": 942
},
{
"epoch": 1.4866141732283464,
"eval_loss": 0.2019665390253067,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 944
},
{
"epoch": 1.4897637795275591,
"eval_loss": 0.20202280580997467,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 946
},
{
"epoch": 1.4929133858267716,
"eval_loss": 0.20245084166526794,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 948
},
{
"epoch": 1.4960629921259843,
"eval_loss": 0.2024083286523819,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 950
},
{
"epoch": 1.499212598425197,
"eval_loss": 0.20221827924251556,
"eval_runtime": 0.3466,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.885,
"step": 952
},
{
"epoch": 1.5023622047244094,
"eval_loss": 0.202116459608078,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 954
},
{
"epoch": 1.505511811023622,
"eval_loss": 0.20200569927692413,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 956
},
{
"epoch": 1.5086614173228345,
"eval_loss": 0.20204730331897736,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 958
},
{
"epoch": 1.5118110236220472,
"eval_loss": 0.20194220542907715,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 960
},
{
"epoch": 1.51496062992126,
"eval_loss": 0.2016419768333435,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 962
},
{
"epoch": 1.5181102362204726,
"eval_loss": 0.20146290957927704,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 964
},
{
"epoch": 1.521259842519685,
"eval_loss": 0.20127460360527039,
"eval_runtime": 0.3505,
"eval_samples_per_second": 5.706,
"eval_steps_per_second": 2.853,
"step": 966
},
{
"epoch": 1.5244094488188975,
"eval_loss": 0.20131409168243408,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 968
},
{
"epoch": 1.5275590551181102,
"eval_loss": 0.2020762860774994,
"eval_runtime": 0.3461,
"eval_samples_per_second": 5.778,
"eval_steps_per_second": 2.889,
"step": 970
},
{
"epoch": 1.5307086614173229,
"eval_loss": 0.2022102028131485,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 972
},
{
"epoch": 1.5338582677165356,
"eval_loss": 0.20295965671539307,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 974
},
{
"epoch": 1.537007874015748,
"eval_loss": 0.20335547626018524,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 976
},
{
"epoch": 1.5401574803149605,
"eval_loss": 0.20378966629505157,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 978
},
{
"epoch": 1.5433070866141732,
"eval_loss": 0.20386317372322083,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 980
},
{
"epoch": 1.5464566929133858,
"eval_loss": 0.20390541851520538,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 982
},
{
"epoch": 1.5496062992125985,
"eval_loss": 0.20381659269332886,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.727,
"eval_steps_per_second": 2.863,
"step": 984
},
{
"epoch": 1.552755905511811,
"eval_loss": 0.2037232518196106,
"eval_runtime": 0.3462,
"eval_samples_per_second": 5.777,
"eval_steps_per_second": 2.889,
"step": 986
},
{
"epoch": 1.5559055118110237,
"eval_loss": 0.20313450694084167,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 988
},
{
"epoch": 1.5590551181102361,
"eval_loss": 0.2031145840883255,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 990
},
{
"epoch": 1.5622047244094488,
"eval_loss": 0.20269346237182617,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 992
},
{
"epoch": 1.5653543307086615,
"eval_loss": 0.20311002433300018,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 994
},
{
"epoch": 1.5685039370078742,
"eval_loss": 0.20359496772289276,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.874,
"step": 996
},
{
"epoch": 1.5716535433070866,
"eval_loss": 0.2038438469171524,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 998
},
{
"epoch": 1.574803149606299,
"grad_norm": 0.6836279630661011,
"learning_rate": 1.069455406471981e-05,
"loss": 0.2679,
"step": 1000
},
{
"epoch": 1.574803149606299,
"eval_loss": 0.2036600261926651,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 1000
},
{
"epoch": 1.5779527559055118,
"eval_loss": 0.20389078557491302,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.886,
"step": 1002
},
{
"epoch": 1.5811023622047244,
"eval_loss": 0.20348089933395386,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.879,
"step": 1004
},
{
"epoch": 1.5842519685039371,
"eval_loss": 0.20383606851100922,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.763,
"eval_steps_per_second": 2.882,
"step": 1006
},
{
"epoch": 1.5874015748031496,
"eval_loss": 0.2036617249250412,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 1008
},
{
"epoch": 1.590551181102362,
"eval_loss": 0.20271004736423492,
"eval_runtime": 0.3459,
"eval_samples_per_second": 5.782,
"eval_steps_per_second": 2.891,
"step": 1010
},
{
"epoch": 1.5937007874015747,
"eval_loss": 0.20310062170028687,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 1012
},
{
"epoch": 1.5968503937007874,
"eval_loss": 0.20280981063842773,
"eval_runtime": 0.3486,
"eval_samples_per_second": 5.737,
"eval_steps_per_second": 2.868,
"step": 1014
},
{
"epoch": 1.6,
"eval_loss": 0.2024936079978943,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.738,
"eval_steps_per_second": 2.869,
"step": 1016
},
{
"epoch": 1.6031496062992125,
"eval_loss": 0.20220336318016052,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 1018
},
{
"epoch": 1.6062992125984252,
"eval_loss": 0.20181672275066376,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 1020
},
{
"epoch": 1.6094488188976377,
"eval_loss": 0.20159752666950226,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 1022
},
{
"epoch": 1.6125984251968504,
"eval_loss": 0.20041340589523315,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 1024
},
{
"epoch": 1.615748031496063,
"eval_loss": 0.1999630331993103,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 1026
},
{
"epoch": 1.6188976377952757,
"eval_loss": 0.19997118413448334,
"eval_runtime": 0.3497,
"eval_samples_per_second": 5.719,
"eval_steps_per_second": 2.859,
"step": 1028
},
{
"epoch": 1.6220472440944882,
"eval_loss": 0.1989332139492035,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 1030
},
{
"epoch": 1.6251968503937007,
"eval_loss": 0.1988600790500641,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.752,
"eval_steps_per_second": 2.876,
"step": 1032
},
{
"epoch": 1.6283464566929133,
"eval_loss": 0.19887009263038635,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 1034
},
{
"epoch": 1.631496062992126,
"eval_loss": 0.19852973520755768,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 1036
},
{
"epoch": 1.6346456692913387,
"eval_loss": 0.19859279692173004,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.763,
"eval_steps_per_second": 2.882,
"step": 1038
},
{
"epoch": 1.6377952755905512,
"eval_loss": 0.19779442250728607,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1040
},
{
"epoch": 1.6409448818897636,
"eval_loss": 0.1982453316450119,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 1042
},
{
"epoch": 1.6440944881889763,
"eval_loss": 0.19805452227592468,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 1044
},
{
"epoch": 1.647244094488189,
"eval_loss": 0.1983424574136734,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 1046
},
{
"epoch": 1.6503937007874017,
"eval_loss": 0.198614239692688,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 1048
},
{
"epoch": 1.6535433070866141,
"eval_loss": 0.19888301193714142,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.878,
"step": 1050
},
{
"epoch": 1.6566929133858268,
"eval_loss": 0.19872523844242096,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.736,
"eval_steps_per_second": 2.868,
"step": 1052
},
{
"epoch": 1.6598425196850393,
"eval_loss": 0.19910645484924316,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 1054
},
{
"epoch": 1.662992125984252,
"eval_loss": 0.19936327636241913,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 1056
},
{
"epoch": 1.6661417322834646,
"eval_loss": 0.19959034025669098,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 1058
},
{
"epoch": 1.6692913385826773,
"eval_loss": 0.19941551983356476,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.871,
"step": 1060
},
{
"epoch": 1.6724409448818898,
"eval_loss": 0.19928954541683197,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.756,
"eval_steps_per_second": 2.878,
"step": 1062
},
{
"epoch": 1.6755905511811022,
"eval_loss": 0.1993902176618576,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 1064
},
{
"epoch": 1.678740157480315,
"eval_loss": 0.1991710215806961,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.773,
"eval_steps_per_second": 2.886,
"step": 1066
},
{
"epoch": 1.6818897637795276,
"eval_loss": 0.1996215432882309,
"eval_runtime": 0.3489,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 1068
},
{
"epoch": 1.6850393700787403,
"eval_loss": 0.19980910420417786,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 1070
},
{
"epoch": 1.6881889763779527,
"eval_loss": 0.19976070523262024,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 1072
},
{
"epoch": 1.6913385826771652,
"eval_loss": 0.19977939128875732,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.771,
"eval_steps_per_second": 2.886,
"step": 1074
},
{
"epoch": 1.6944881889763779,
"eval_loss": 0.1988721787929535,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 1076
},
{
"epoch": 1.6976377952755906,
"eval_loss": 0.19855494797229767,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 1078
},
{
"epoch": 1.7007874015748032,
"eval_loss": 0.19845424592494965,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 1080
},
{
"epoch": 1.7039370078740157,
"eval_loss": 0.19786331057548523,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 1082
},
{
"epoch": 1.7070866141732284,
"eval_loss": 0.1978122889995575,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 1084
},
{
"epoch": 1.7102362204724408,
"eval_loss": 0.198022723197937,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 1086
},
{
"epoch": 1.7133858267716535,
"eval_loss": 0.19740678369998932,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1088
},
{
"epoch": 1.7165354330708662,
"eval_loss": 0.19713999330997467,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 1090
},
{
"epoch": 1.7196850393700789,
"eval_loss": 0.19737838208675385,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.741,
"eval_steps_per_second": 2.871,
"step": 1092
},
{
"epoch": 1.7228346456692913,
"eval_loss": 0.19747193157672882,
"eval_runtime": 0.3465,
"eval_samples_per_second": 5.772,
"eval_steps_per_second": 2.886,
"step": 1094
},
{
"epoch": 1.7259842519685038,
"eval_loss": 0.19672293961048126,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.769,
"eval_steps_per_second": 2.884,
"step": 1096
},
{
"epoch": 1.7291338582677165,
"eval_loss": 0.19675834476947784,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1098
},
{
"epoch": 1.7322834645669292,
"grad_norm": 0.6988422274589539,
"learning_rate": 6.748224151539069e-06,
"loss": 0.2665,
"step": 1100
},
{
"epoch": 1.7322834645669292,
"eval_loss": 0.196418896317482,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 1100
},
{
"epoch": 1.7354330708661418,
"eval_loss": 0.19637499749660492,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 1102
},
{
"epoch": 1.7385826771653543,
"eval_loss": 0.19661858677864075,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.717,
"eval_steps_per_second": 2.859,
"step": 1104
},
{
"epoch": 1.7417322834645668,
"eval_loss": 0.1960836946964264,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 1106
},
{
"epoch": 1.7448818897637794,
"eval_loss": 0.19602809846401215,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 1108
},
{
"epoch": 1.7480314960629921,
"eval_loss": 0.1960209757089615,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.759,
"eval_steps_per_second": 2.88,
"step": 1110
},
{
"epoch": 1.7511811023622048,
"eval_loss": 0.19583533704280853,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 1112
},
{
"epoch": 1.7543307086614173,
"eval_loss": 0.1960146129131317,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 1114
},
{
"epoch": 1.75748031496063,
"eval_loss": 0.19574031233787537,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 1116
},
{
"epoch": 1.7606299212598424,
"eval_loss": 0.19601492583751678,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 1118
},
{
"epoch": 1.763779527559055,
"eval_loss": 0.19606409966945648,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 1120
},
{
"epoch": 1.7669291338582678,
"eval_loss": 0.19606640934944153,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 1122
},
{
"epoch": 1.7700787401574805,
"eval_loss": 0.19612987339496613,
"eval_runtime": 0.3457,
"eval_samples_per_second": 5.786,
"eval_steps_per_second": 2.893,
"step": 1124
},
{
"epoch": 1.773228346456693,
"eval_loss": 0.19647565484046936,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.883,
"step": 1126
},
{
"epoch": 1.7763779527559054,
"eval_loss": 0.1972719132900238,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 1128
},
{
"epoch": 1.779527559055118,
"eval_loss": 0.19727349281311035,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.883,
"step": 1130
},
{
"epoch": 1.7826771653543307,
"eval_loss": 0.1972896158695221,
"eval_runtime": 0.3479,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 1132
},
{
"epoch": 1.7858267716535434,
"eval_loss": 0.19728370010852814,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1134
},
{
"epoch": 1.7889763779527559,
"eval_loss": 0.19749872386455536,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.769,
"eval_steps_per_second": 2.884,
"step": 1136
},
{
"epoch": 1.7921259842519683,
"eval_loss": 0.19797682762145996,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.734,
"eval_steps_per_second": 2.867,
"step": 1138
},
{
"epoch": 1.795275590551181,
"eval_loss": 0.19825181365013123,
"eval_runtime": 0.3487,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.868,
"step": 1140
},
{
"epoch": 1.7984251968503937,
"eval_loss": 0.1979563981294632,
"eval_runtime": 0.3467,
"eval_samples_per_second": 5.769,
"eval_steps_per_second": 2.884,
"step": 1142
},
{
"epoch": 1.8015748031496064,
"eval_loss": 0.19838236272335052,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 1144
},
{
"epoch": 1.8047244094488188,
"eval_loss": 0.19785432517528534,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1146
},
{
"epoch": 1.8078740157480315,
"eval_loss": 0.19788405299186707,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 1148
},
{
"epoch": 1.811023622047244,
"eval_loss": 0.19788511097431183,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.746,
"eval_steps_per_second": 2.873,
"step": 1150
},
{
"epoch": 1.8141732283464567,
"eval_loss": 0.19811120629310608,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.766,
"eval_steps_per_second": 2.883,
"step": 1152
},
{
"epoch": 1.8173228346456693,
"eval_loss": 0.19806963205337524,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 1154
},
{
"epoch": 1.820472440944882,
"eval_loss": 0.19791574776172638,
"eval_runtime": 0.3463,
"eval_samples_per_second": 5.776,
"eval_steps_per_second": 2.888,
"step": 1156
},
{
"epoch": 1.8236220472440945,
"eval_loss": 0.19810570776462555,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 1158
},
{
"epoch": 1.826771653543307,
"eval_loss": 0.19815976917743683,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 1160
},
{
"epoch": 1.8299212598425196,
"eval_loss": 0.19824393093585968,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 1162
},
{
"epoch": 1.8330708661417323,
"eval_loss": 0.19828525185585022,
"eval_runtime": 0.3475,
"eval_samples_per_second": 5.755,
"eval_steps_per_second": 2.877,
"step": 1164
},
{
"epoch": 1.836220472440945,
"eval_loss": 0.19825799763202667,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 1166
},
{
"epoch": 1.8393700787401575,
"eval_loss": 0.1982419192790985,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 1168
},
{
"epoch": 1.84251968503937,
"eval_loss": 0.19862309098243713,
"eval_runtime": 0.3478,
"eval_samples_per_second": 5.75,
"eval_steps_per_second": 2.875,
"step": 1170
},
{
"epoch": 1.8456692913385826,
"eval_loss": 0.19841212034225464,
"eval_runtime": 0.3456,
"eval_samples_per_second": 5.787,
"eval_steps_per_second": 2.893,
"step": 1172
},
{
"epoch": 1.8488188976377953,
"eval_loss": 0.19861873984336853,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1174
},
{
"epoch": 1.851968503937008,
"eval_loss": 0.19822253286838531,
"eval_runtime": 0.347,
"eval_samples_per_second": 5.764,
"eval_steps_per_second": 2.882,
"step": 1176
},
{
"epoch": 1.8551181102362204,
"eval_loss": 0.19842112064361572,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.747,
"eval_steps_per_second": 2.873,
"step": 1178
},
{
"epoch": 1.858267716535433,
"eval_loss": 0.1980394423007965,
"eval_runtime": 0.3498,
"eval_samples_per_second": 5.717,
"eval_steps_per_second": 2.859,
"step": 1180
},
{
"epoch": 1.8614173228346456,
"eval_loss": 0.1985034942626953,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 1182
},
{
"epoch": 1.8645669291338582,
"eval_loss": 0.197963148355484,
"eval_runtime": 0.3464,
"eval_samples_per_second": 5.773,
"eval_steps_per_second": 2.887,
"step": 1184
},
{
"epoch": 1.867716535433071,
"eval_loss": 0.19788368046283722,
"eval_runtime": 0.3495,
"eval_samples_per_second": 5.722,
"eval_steps_per_second": 2.861,
"step": 1186
},
{
"epoch": 1.8708661417322836,
"eval_loss": 0.19827842712402344,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.768,
"eval_steps_per_second": 2.884,
"step": 1188
},
{
"epoch": 1.874015748031496,
"eval_loss": 0.19781190156936646,
"eval_runtime": 0.3471,
"eval_samples_per_second": 5.762,
"eval_steps_per_second": 2.881,
"step": 1190
},
{
"epoch": 1.8771653543307085,
"eval_loss": 0.19800271093845367,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1192
},
{
"epoch": 1.8803149606299212,
"eval_loss": 0.19764357805252075,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 1194
},
{
"epoch": 1.8834645669291339,
"eval_loss": 0.19796139001846313,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.76,
"eval_steps_per_second": 2.88,
"step": 1196
},
{
"epoch": 1.8866141732283466,
"eval_loss": 0.197557270526886,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.743,
"eval_steps_per_second": 2.872,
"step": 1198
},
{
"epoch": 1.889763779527559,
"grad_norm": 0.5601646900177002,
"learning_rate": 2.801894238358327e-06,
"loss": 0.2613,
"step": 1200
},
{
"epoch": 1.889763779527559,
"eval_loss": 0.1976018249988556,
"eval_runtime": 0.3461,
"eval_samples_per_second": 5.779,
"eval_steps_per_second": 2.89,
"step": 1200
},
{
"epoch": 1.8929133858267715,
"eval_loss": 0.19802145659923553,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.735,
"eval_steps_per_second": 2.867,
"step": 1202
},
{
"epoch": 1.8960629921259842,
"eval_loss": 0.1972925364971161,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 1204
},
{
"epoch": 1.8992125984251969,
"eval_loss": 0.19728003442287445,
"eval_runtime": 0.3484,
"eval_samples_per_second": 5.74,
"eval_steps_per_second": 2.87,
"step": 1206
},
{
"epoch": 1.9023622047244095,
"eval_loss": 0.19743125140666962,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 1208
},
{
"epoch": 1.905511811023622,
"eval_loss": 0.19774848222732544,
"eval_runtime": 0.3472,
"eval_samples_per_second": 5.761,
"eval_steps_per_second": 2.88,
"step": 1210
},
{
"epoch": 1.9086614173228347,
"eval_loss": 0.19761374592781067,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1212
},
{
"epoch": 1.9118110236220471,
"eval_loss": 0.19731517136096954,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.883,
"step": 1214
},
{
"epoch": 1.9149606299212598,
"eval_loss": 0.19791986048221588,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 1216
},
{
"epoch": 1.9181102362204725,
"eval_loss": 0.19727776944637299,
"eval_runtime": 0.3485,
"eval_samples_per_second": 5.739,
"eval_steps_per_second": 2.87,
"step": 1218
},
{
"epoch": 1.9212598425196852,
"eval_loss": 0.19739235937595367,
"eval_runtime": 0.3492,
"eval_samples_per_second": 5.728,
"eval_steps_per_second": 2.864,
"step": 1220
},
{
"epoch": 1.9244094488188976,
"eval_loss": 0.19753655791282654,
"eval_runtime": 0.3491,
"eval_samples_per_second": 5.729,
"eval_steps_per_second": 2.864,
"step": 1222
},
{
"epoch": 1.92755905511811,
"eval_loss": 0.19751207530498505,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.879,
"step": 1224
},
{
"epoch": 1.9307086614173228,
"eval_loss": 0.1976042091846466,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1226
},
{
"epoch": 1.9338582677165355,
"eval_loss": 0.19759471714496613,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1228
},
{
"epoch": 1.9370078740157481,
"eval_loss": 0.19739989936351776,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 1230
},
{
"epoch": 1.9401574803149606,
"eval_loss": 0.1975041925907135,
"eval_runtime": 0.3488,
"eval_samples_per_second": 5.733,
"eval_steps_per_second": 2.867,
"step": 1232
},
{
"epoch": 1.943307086614173,
"eval_loss": 0.19724518060684204,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1234
},
{
"epoch": 1.9464566929133857,
"eval_loss": 0.19755536317825317,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 1236
},
{
"epoch": 1.9496062992125984,
"eval_loss": 0.19762204587459564,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.884,
"step": 1238
},
{
"epoch": 1.952755905511811,
"eval_loss": 0.19748742878437042,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 1240
},
{
"epoch": 1.9559055118110236,
"eval_loss": 0.19786527752876282,
"eval_runtime": 0.3477,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.876,
"step": 1242
},
{
"epoch": 1.9590551181102362,
"eval_loss": 0.19752757251262665,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 1244
},
{
"epoch": 1.9622047244094487,
"eval_loss": 0.19746313989162445,
"eval_runtime": 0.3469,
"eval_samples_per_second": 5.765,
"eval_steps_per_second": 2.882,
"step": 1246
},
{
"epoch": 1.9653543307086614,
"eval_loss": 0.19745899736881256,
"eval_runtime": 0.3468,
"eval_samples_per_second": 5.767,
"eval_steps_per_second": 2.884,
"step": 1248
},
{
"epoch": 1.968503937007874,
"eval_loss": 0.1974746137857437,
"eval_runtime": 0.3457,
"eval_samples_per_second": 5.785,
"eval_steps_per_second": 2.893,
"step": 1250
},
{
"epoch": 1.9716535433070868,
"eval_loss": 0.1976330280303955,
"eval_runtime": 0.3483,
"eval_samples_per_second": 5.742,
"eval_steps_per_second": 2.871,
"step": 1252
},
{
"epoch": 1.9748031496062992,
"eval_loss": 0.19755062460899353,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.754,
"eval_steps_per_second": 2.877,
"step": 1254
},
{
"epoch": 1.9779527559055117,
"eval_loss": 0.19772788882255554,
"eval_runtime": 0.3476,
"eval_samples_per_second": 5.753,
"eval_steps_per_second": 2.877,
"step": 1256
},
{
"epoch": 1.9811023622047244,
"eval_loss": 0.1972995549440384,
"eval_runtime": 0.3473,
"eval_samples_per_second": 5.758,
"eval_steps_per_second": 2.879,
"step": 1258
},
{
"epoch": 1.984251968503937,
"eval_loss": 0.19754815101623535,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 1260
},
{
"epoch": 1.9874015748031497,
"eval_loss": 0.1977696567773819,
"eval_runtime": 0.3454,
"eval_samples_per_second": 5.79,
"eval_steps_per_second": 2.895,
"step": 1262
},
{
"epoch": 1.9905511811023622,
"eval_loss": 0.19758668541908264,
"eval_runtime": 0.348,
"eval_samples_per_second": 5.748,
"eval_steps_per_second": 2.874,
"step": 1264
},
{
"epoch": 1.9937007874015746,
"eval_loss": 0.19804508984088898,
"eval_runtime": 0.3482,
"eval_samples_per_second": 5.744,
"eval_steps_per_second": 2.872,
"step": 1266
},
{
"epoch": 1.9968503937007873,
"eval_loss": 0.19809667766094208,
"eval_runtime": 0.3481,
"eval_samples_per_second": 5.745,
"eval_steps_per_second": 2.872,
"step": 1268
},
{
"epoch": 2.0,
"eval_loss": 0.19763582944869995,
"eval_runtime": 0.3474,
"eval_samples_per_second": 5.757,
"eval_steps_per_second": 2.878,
"step": 1270
}
],
"logging_steps": 100,
"max_steps": 1270,
"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": true
},
"attributes": {}
}
},
"total_flos": 8.929744633253069e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}