halva13b384-lora / trainer_state.json
pritamqu's picture
Upload 6 files
9122f86 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 342,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.2727272727272728e-06,
"loss": 0.5451,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.5632,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 6.818181818181818e-06,
"loss": 0.5577,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 9.090909090909091e-06,
"loss": 0.5745,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.1363636363636365e-05,
"loss": 0.586,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 1.3636363636363637e-05,
"loss": 0.5623,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 1.590909090909091e-05,
"loss": 0.562,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.557,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 2.0454545454545457e-05,
"loss": 0.547,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 2.272727272727273e-05,
"loss": 0.5623,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 2.5e-05,
"loss": 0.5386,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 2.4999436984287818e-05,
"loss": 0.5861,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 2.4997747987869124e-05,
"loss": 0.559,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 2.499493316289298e-05,
"loss": 0.5426,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 2.4990992762925882e-05,
"loss": 0.5535,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 2.498592714292897e-05,
"loss": 0.5247,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 2.4979736759226035e-05,
"loss": 0.5005,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 2.4972422169462394e-05,
"loss": 0.5571,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 2.496398403255468e-05,
"loss": 0.5414,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 2.4954423108631487e-05,
"loss": 0.5326,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 2.4943740258964873e-05,
"loss": 0.5265,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 2.4931936445892793e-05,
"loss": 0.5212,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 2.49190127327324e-05,
"loss": 0.5385,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 2.490497028368427e-05,
"loss": 0.5077,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 2.4889810363727512e-05,
"loss": 0.4924,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 2.4873534338505826e-05,
"loss": 0.4808,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 2.4856143674204485e-05,
"loss": 0.5613,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 2.4837639937418248e-05,
"loss": 0.5357,
"step": 28
},
{
"epoch": 0.08,
"learning_rate": 2.4818024795010238e-05,
"loss": 0.4799,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 2.4797300013961797e-05,
"loss": 0.5087,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 2.4775467461213302e-05,
"loss": 0.4531,
"step": 31
},
{
"epoch": 0.09,
"learning_rate": 2.4752529103495995e-05,
"loss": 0.483,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 2.47284870071548e-05,
"loss": 0.5079,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 2.4703343337962194e-05,
"loss": 0.5084,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 2.4677100360923115e-05,
"loss": 0.4608,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 2.4649760440070905e-05,
"loss": 0.4466,
"step": 36
},
{
"epoch": 0.11,
"learning_rate": 2.4621326038254368e-05,
"loss": 0.4419,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 2.459179971691589e-05,
"loss": 0.4533,
"step": 38
},
{
"epoch": 0.11,
"learning_rate": 2.456118413586074e-05,
"loss": 0.4086,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 2.4529482053017422e-05,
"loss": 0.4582,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 2.449669632418925e-05,
"loss": 0.4315,
"step": 41
},
{
"epoch": 0.12,
"learning_rate": 2.446282990279711e-05,
"loss": 0.4644,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 2.442788583961336e-05,
"loss": 0.4648,
"step": 43
},
{
"epoch": 0.13,
"learning_rate": 2.439186728248708e-05,
"loss": 0.4385,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 2.4354777476060434e-05,
"loss": 0.4596,
"step": 45
},
{
"epoch": 0.13,
"learning_rate": 2.431661976147643e-05,
"loss": 0.4017,
"step": 46
},
{
"epoch": 0.14,
"learning_rate": 2.4277397576077916e-05,
"loss": 0.434,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 2.4237114453097968e-05,
"loss": 0.4484,
"step": 48
},
{
"epoch": 0.14,
"learning_rate": 2.4195774021341566e-05,
"loss": 0.455,
"step": 49
},
{
"epoch": 0.15,
"learning_rate": 2.4153380004858734e-05,
"loss": 0.4195,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 2.410993622260905e-05,
"loss": 0.4196,
"step": 51
},
{
"epoch": 0.15,
"learning_rate": 2.4065446588117636e-05,
"loss": 0.472,
"step": 52
},
{
"epoch": 0.15,
"learning_rate": 2.4019915109122615e-05,
"loss": 0.4439,
"step": 53
},
{
"epoch": 0.16,
"learning_rate": 2.3973345887214072e-05,
"loss": 0.4377,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 2.3925743117464592e-05,
"loss": 0.3872,
"step": 55
},
{
"epoch": 0.16,
"learning_rate": 2.3877111088051347e-05,
"loss": 0.359,
"step": 56
},
{
"epoch": 0.17,
"learning_rate": 2.3827454179869807e-05,
"loss": 0.4816,
"step": 57
},
{
"epoch": 0.17,
"learning_rate": 2.377677686613909e-05,
"loss": 0.3904,
"step": 58
},
{
"epoch": 0.17,
"learning_rate": 2.372508371199902e-05,
"loss": 0.4122,
"step": 59
},
{
"epoch": 0.18,
"learning_rate": 2.3672379374098877e-05,
"loss": 0.3988,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 2.361866860017791e-05,
"loss": 0.4375,
"step": 61
},
{
"epoch": 0.18,
"learning_rate": 2.356395622863767e-05,
"loss": 0.4183,
"step": 62
},
{
"epoch": 0.18,
"learning_rate": 2.350824718810612e-05,
"loss": 0.4307,
"step": 63
},
{
"epoch": 0.19,
"learning_rate": 2.345154649699368e-05,
"loss": 0.4254,
"step": 64
},
{
"epoch": 0.19,
"learning_rate": 2.3393859263041163e-05,
"loss": 0.3882,
"step": 65
},
{
"epoch": 0.19,
"learning_rate": 2.3335190682859608e-05,
"loss": 0.3946,
"step": 66
},
{
"epoch": 0.2,
"learning_rate": 2.3275546041462216e-05,
"loss": 0.3978,
"step": 67
},
{
"epoch": 0.2,
"learning_rate": 2.3214930711788226e-05,
"loss": 0.3984,
"step": 68
},
{
"epoch": 0.2,
"learning_rate": 2.3153350154218924e-05,
"loss": 0.422,
"step": 69
},
{
"epoch": 0.2,
"learning_rate": 2.3090809916085737e-05,
"loss": 0.4245,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 2.3027315631170548e-05,
"loss": 0.3964,
"step": 71
},
{
"epoch": 0.21,
"learning_rate": 2.2962873019198157e-05,
"loss": 0.3608,
"step": 72
},
{
"epoch": 0.21,
"learning_rate": 2.2897487885321062e-05,
"loss": 0.393,
"step": 73
},
{
"epoch": 0.22,
"learning_rate": 2.283116611959649e-05,
"loss": 0.3666,
"step": 74
},
{
"epoch": 0.22,
"learning_rate": 2.2763913696455835e-05,
"loss": 0.3785,
"step": 75
},
{
"epoch": 0.22,
"learning_rate": 2.269573667416644e-05,
"loss": 0.3637,
"step": 76
},
{
"epoch": 0.23,
"learning_rate": 2.2626641194285865e-05,
"loss": 0.3742,
"step": 77
},
{
"epoch": 0.23,
"learning_rate": 2.2556633481108636e-05,
"loss": 0.3584,
"step": 78
},
{
"epoch": 0.23,
"learning_rate": 2.2485719841105562e-05,
"loss": 0.3196,
"step": 79
},
{
"epoch": 0.23,
"learning_rate": 2.24139066623556e-05,
"loss": 0.3642,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 2.234120041397043e-05,
"loss": 0.328,
"step": 81
},
{
"epoch": 0.24,
"learning_rate": 2.2267607645511686e-05,
"loss": 0.335,
"step": 82
},
{
"epoch": 0.24,
"learning_rate": 2.2193134986400956e-05,
"loss": 0.3313,
"step": 83
},
{
"epoch": 0.25,
"learning_rate": 2.2117789145322597e-05,
"loss": 0.3223,
"step": 84
},
{
"epoch": 0.25,
"learning_rate": 2.204157690961939e-05,
"loss": 0.3653,
"step": 85
},
{
"epoch": 0.25,
"learning_rate": 2.1964505144681115e-05,
"loss": 0.2841,
"step": 86
},
{
"epoch": 0.25,
"learning_rate": 2.188658079332612e-05,
"loss": 0.3254,
"step": 87
},
{
"epoch": 0.26,
"learning_rate": 2.1807810875175866e-05,
"loss": 0.3567,
"step": 88
},
{
"epoch": 0.26,
"learning_rate": 2.1728202486022608e-05,
"loss": 0.3271,
"step": 89
},
{
"epoch": 0.26,
"learning_rate": 2.164776279719017e-05,
"loss": 0.3229,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 2.1566499054887947e-05,
"loss": 0.3727,
"step": 91
},
{
"epoch": 0.27,
"learning_rate": 2.1484418579558137e-05,
"loss": 0.358,
"step": 92
},
{
"epoch": 0.27,
"learning_rate": 2.14015287652163e-05,
"loss": 0.3337,
"step": 93
},
{
"epoch": 0.27,
"learning_rate": 2.131783707878529e-05,
"loss": 0.324,
"step": 94
},
{
"epoch": 0.28,
"learning_rate": 2.1233351059422632e-05,
"loss": 0.3281,
"step": 95
},
{
"epoch": 0.28,
"learning_rate": 2.114807831784133e-05,
"loss": 0.2809,
"step": 96
},
{
"epoch": 0.28,
"learning_rate": 2.1062026535624324e-05,
"loss": 0.2885,
"step": 97
},
{
"epoch": 0.29,
"learning_rate": 2.0975203464532482e-05,
"loss": 0.3549,
"step": 98
},
{
"epoch": 0.29,
"learning_rate": 2.088761692580632e-05,
"loss": 0.2672,
"step": 99
},
{
"epoch": 0.29,
"learning_rate": 2.0799274809461434e-05,
"loss": 0.3304,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 2.0710185073577747e-05,
"loss": 0.2967,
"step": 101
},
{
"epoch": 0.3,
"learning_rate": 2.0620355743582642e-05,
"loss": 0.302,
"step": 102
},
{
"epoch": 0.3,
"learning_rate": 2.052979491152799e-05,
"loss": 0.2947,
"step": 103
},
{
"epoch": 0.3,
"learning_rate": 2.0438510735361206e-05,
"loss": 0.3411,
"step": 104
},
{
"epoch": 0.31,
"learning_rate": 2.0346511438190356e-05,
"loss": 0.3386,
"step": 105
},
{
"epoch": 0.31,
"learning_rate": 2.0253805307543426e-05,
"loss": 0.3116,
"step": 106
},
{
"epoch": 0.31,
"learning_rate": 2.0160400694621706e-05,
"loss": 0.2887,
"step": 107
},
{
"epoch": 0.32,
"learning_rate": 2.0066306013547558e-05,
"loss": 0.3142,
"step": 108
},
{
"epoch": 0.32,
"learning_rate": 1.9971529740606398e-05,
"loss": 0.3886,
"step": 109
},
{
"epoch": 0.32,
"learning_rate": 1.9876080413483148e-05,
"loss": 0.2961,
"step": 110
},
{
"epoch": 0.32,
"learning_rate": 1.9779966630493156e-05,
"loss": 0.3061,
"step": 111
},
{
"epoch": 0.33,
"learning_rate": 1.968319704980762e-05,
"loss": 0.3286,
"step": 112
},
{
"epoch": 0.33,
"learning_rate": 1.958578038867364e-05,
"loss": 0.2825,
"step": 113
},
{
"epoch": 0.33,
"learning_rate": 1.948772542262895e-05,
"loss": 0.3029,
"step": 114
},
{
"epoch": 0.34,
"learning_rate": 1.9389040984711403e-05,
"loss": 0.2837,
"step": 115
},
{
"epoch": 0.34,
"learning_rate": 1.9289735964663247e-05,
"loss": 0.298,
"step": 116
},
{
"epoch": 0.34,
"learning_rate": 1.9189819308130334e-05,
"loss": 0.3005,
"step": 117
},
{
"epoch": 0.35,
"learning_rate": 1.908930001585628e-05,
"loss": 0.2827,
"step": 118
},
{
"epoch": 0.35,
"learning_rate": 1.898818714287163e-05,
"loss": 0.286,
"step": 119
},
{
"epoch": 0.35,
"learning_rate": 1.888648979767817e-05,
"loss": 0.331,
"step": 120
},
{
"epoch": 0.35,
"learning_rate": 1.878421714142842e-05,
"loss": 0.2751,
"step": 121
},
{
"epoch": 0.36,
"learning_rate": 1.8681378387100362e-05,
"loss": 0.2963,
"step": 122
},
{
"epoch": 0.36,
"learning_rate": 1.857798279866752e-05,
"loss": 0.2642,
"step": 123
},
{
"epoch": 0.36,
"learning_rate": 1.8474039690264435e-05,
"loss": 0.2529,
"step": 124
},
{
"epoch": 0.37,
"learning_rate": 1.8369558425347606e-05,
"loss": 0.2996,
"step": 125
},
{
"epoch": 0.37,
"learning_rate": 1.826454841585205e-05,
"loss": 0.3078,
"step": 126
},
{
"epoch": 0.37,
"learning_rate": 1.815901912134341e-05,
"loss": 0.2731,
"step": 127
},
{
"epoch": 0.37,
"learning_rate": 1.805298004816583e-05,
"loss": 0.3192,
"step": 128
},
{
"epoch": 0.38,
"learning_rate": 1.7946440748585595e-05,
"loss": 0.3108,
"step": 129
},
{
"epoch": 0.38,
"learning_rate": 1.7839410819930652e-05,
"loss": 0.3382,
"step": 130
},
{
"epoch": 0.38,
"learning_rate": 1.7731899903726037e-05,
"loss": 0.2913,
"step": 131
},
{
"epoch": 0.39,
"learning_rate": 1.7623917684825358e-05,
"loss": 0.2831,
"step": 132
},
{
"epoch": 0.39,
"learning_rate": 1.7515473890538363e-05,
"loss": 0.2698,
"step": 133
},
{
"epoch": 0.39,
"learning_rate": 1.7406578289754654e-05,
"loss": 0.3149,
"step": 134
},
{
"epoch": 0.39,
"learning_rate": 1.7297240692063713e-05,
"loss": 0.2767,
"step": 135
},
{
"epoch": 0.4,
"learning_rate": 1.718747094687121e-05,
"loss": 0.2866,
"step": 136
},
{
"epoch": 0.4,
"learning_rate": 1.7077278942511744e-05,
"loss": 0.3051,
"step": 137
},
{
"epoch": 0.4,
"learning_rate": 1.696667460535809e-05,
"loss": 0.3036,
"step": 138
},
{
"epoch": 0.41,
"learning_rate": 1.6855667898926988e-05,
"loss": 0.2989,
"step": 139
},
{
"epoch": 0.41,
"learning_rate": 1.674426882298162e-05,
"loss": 0.3045,
"step": 140
},
{
"epoch": 0.41,
"learning_rate": 1.6632487412630797e-05,
"loss": 0.3142,
"step": 141
},
{
"epoch": 0.42,
"learning_rate": 1.6520333737424985e-05,
"loss": 0.3167,
"step": 142
},
{
"epoch": 0.42,
"learning_rate": 1.6407817900449178e-05,
"loss": 0.2892,
"step": 143
},
{
"epoch": 0.42,
"learning_rate": 1.6294950037412848e-05,
"loss": 0.2691,
"step": 144
},
{
"epoch": 0.42,
"learning_rate": 1.618174031573683e-05,
"loss": 0.3152,
"step": 145
},
{
"epoch": 0.43,
"learning_rate": 1.6068198933637463e-05,
"loss": 0.3327,
"step": 146
},
{
"epoch": 0.43,
"learning_rate": 1.595433611920788e-05,
"loss": 0.3055,
"step": 147
},
{
"epoch": 0.43,
"learning_rate": 1.584016212949665e-05,
"loss": 0.312,
"step": 148
},
{
"epoch": 0.44,
"learning_rate": 1.5725687249583793e-05,
"loss": 0.2962,
"step": 149
},
{
"epoch": 0.44,
"learning_rate": 1.5610921791654283e-05,
"loss": 0.3211,
"step": 150
},
{
"epoch": 0.44,
"learning_rate": 1.549587609406908e-05,
"loss": 0.2786,
"step": 151
},
{
"epoch": 0.44,
"learning_rate": 1.538056052043383e-05,
"loss": 0.2957,
"step": 152
},
{
"epoch": 0.45,
"learning_rate": 1.5264985458665325e-05,
"loss": 0.3232,
"step": 153
},
{
"epoch": 0.45,
"learning_rate": 1.5149161320055665e-05,
"loss": 0.3149,
"step": 154
},
{
"epoch": 0.45,
"learning_rate": 1.5033098538334439e-05,
"loss": 0.2877,
"step": 155
},
{
"epoch": 0.46,
"learning_rate": 1.4916807568728793e-05,
"loss": 0.3071,
"step": 156
},
{
"epoch": 0.46,
"learning_rate": 1.4800298887021628e-05,
"loss": 0.3121,
"step": 157
},
{
"epoch": 0.46,
"learning_rate": 1.468358298860788e-05,
"loss": 0.2867,
"step": 158
},
{
"epoch": 0.46,
"learning_rate": 1.45666703875491e-05,
"loss": 0.2847,
"step": 159
},
{
"epoch": 0.47,
"learning_rate": 1.4449571615626303e-05,
"loss": 0.2768,
"step": 160
},
{
"epoch": 0.47,
"learning_rate": 1.433229722139125e-05,
"loss": 0.2823,
"step": 161
},
{
"epoch": 0.47,
"learning_rate": 1.4214857769216189e-05,
"loss": 0.2842,
"step": 162
},
{
"epoch": 0.48,
"learning_rate": 1.4097263838342206e-05,
"loss": 0.3397,
"step": 163
},
{
"epoch": 0.48,
"learning_rate": 1.3979526021926232e-05,
"loss": 0.3323,
"step": 164
},
{
"epoch": 0.48,
"learning_rate": 1.386165492608674e-05,
"loss": 0.2577,
"step": 165
},
{
"epoch": 0.49,
"learning_rate": 1.3743661168948377e-05,
"loss": 0.2982,
"step": 166
},
{
"epoch": 0.49,
"learning_rate": 1.3625555379685414e-05,
"loss": 0.3114,
"step": 167
},
{
"epoch": 0.49,
"learning_rate": 1.3507348197564262e-05,
"loss": 0.3086,
"step": 168
},
{
"epoch": 0.49,
"learning_rate": 1.3389050270985046e-05,
"loss": 0.3238,
"step": 169
},
{
"epoch": 0.5,
"learning_rate": 1.3270672256522395e-05,
"loss": 0.2996,
"step": 170
},
{
"epoch": 0.5,
"learning_rate": 1.3152224817965441e-05,
"loss": 0.2716,
"step": 171
},
{
"epoch": 0.5,
"learning_rate": 1.303371862535723e-05,
"loss": 0.3196,
"step": 172
},
{
"epoch": 0.51,
"learning_rate": 1.2915164354033505e-05,
"loss": 0.297,
"step": 173
},
{
"epoch": 0.51,
"learning_rate": 1.279657268366106e-05,
"loss": 0.3286,
"step": 174
},
{
"epoch": 0.51,
"learning_rate": 1.2677954297275707e-05,
"loss": 0.3165,
"step": 175
},
{
"epoch": 0.51,
"learning_rate": 1.2559319880319886e-05,
"loss": 0.2817,
"step": 176
},
{
"epoch": 0.52,
"learning_rate": 1.2440680119680116e-05,
"loss": 0.3136,
"step": 177
},
{
"epoch": 0.52,
"learning_rate": 1.2322045702724296e-05,
"loss": 0.297,
"step": 178
},
{
"epoch": 0.52,
"learning_rate": 1.2203427316338941e-05,
"loss": 0.2749,
"step": 179
},
{
"epoch": 0.53,
"learning_rate": 1.2084835645966501e-05,
"loss": 0.3587,
"step": 180
},
{
"epoch": 0.53,
"learning_rate": 1.1966281374642771e-05,
"loss": 0.2918,
"step": 181
},
{
"epoch": 0.53,
"learning_rate": 1.1847775182034557e-05,
"loss": 0.2823,
"step": 182
},
{
"epoch": 0.54,
"learning_rate": 1.1729327743477606e-05,
"loss": 0.3225,
"step": 183
},
{
"epoch": 0.54,
"learning_rate": 1.1610949729014959e-05,
"loss": 0.3224,
"step": 184
},
{
"epoch": 0.54,
"learning_rate": 1.1492651802435745e-05,
"loss": 0.2937,
"step": 185
},
{
"epoch": 0.54,
"learning_rate": 1.1374444620314583e-05,
"loss": 0.2667,
"step": 186
},
{
"epoch": 0.55,
"learning_rate": 1.1256338831051624e-05,
"loss": 0.2946,
"step": 187
},
{
"epoch": 0.55,
"learning_rate": 1.1138345073913263e-05,
"loss": 0.3551,
"step": 188
},
{
"epoch": 0.55,
"learning_rate": 1.1020473978073776e-05,
"loss": 0.2922,
"step": 189
},
{
"epoch": 0.56,
"learning_rate": 1.0902736161657795e-05,
"loss": 0.3132,
"step": 190
},
{
"epoch": 0.56,
"learning_rate": 1.0785142230783816e-05,
"loss": 0.3172,
"step": 191
},
{
"epoch": 0.56,
"learning_rate": 1.0667702778608753e-05,
"loss": 0.3007,
"step": 192
},
{
"epoch": 0.56,
"learning_rate": 1.05504283843737e-05,
"loss": 0.294,
"step": 193
},
{
"epoch": 0.57,
"learning_rate": 1.0433329612450906e-05,
"loss": 0.2616,
"step": 194
},
{
"epoch": 0.57,
"learning_rate": 1.0316417011392124e-05,
"loss": 0.3269,
"step": 195
},
{
"epoch": 0.57,
"learning_rate": 1.0199701112978377e-05,
"loss": 0.7307,
"step": 196
},
{
"epoch": 0.58,
"learning_rate": 1.008319243127121e-05,
"loss": 0.2375,
"step": 197
},
{
"epoch": 0.58,
"learning_rate": 9.966901461665564e-06,
"loss": 0.2837,
"step": 198
},
{
"epoch": 0.58,
"learning_rate": 9.850838679944334e-06,
"loss": 0.321,
"step": 199
},
{
"epoch": 0.58,
"learning_rate": 9.735014541334675e-06,
"loss": 0.2926,
"step": 200
},
{
"epoch": 0.59,
"learning_rate": 9.61943947956617e-06,
"loss": 0.3323,
"step": 201
},
{
"epoch": 0.59,
"learning_rate": 9.504123905930928e-06,
"loss": 0.3139,
"step": 202
},
{
"epoch": 0.59,
"learning_rate": 9.389078208345717e-06,
"loss": 0.3236,
"step": 203
},
{
"epoch": 0.6,
"learning_rate": 9.274312750416205e-06,
"loss": 0.3227,
"step": 204
},
{
"epoch": 0.6,
"learning_rate": 9.159837870503352e-06,
"loss": 0.3299,
"step": 205
},
{
"epoch": 0.6,
"learning_rate": 9.045663880792122e-06,
"loss": 0.2833,
"step": 206
},
{
"epoch": 0.61,
"learning_rate": 8.931801066362542e-06,
"loss": 0.2974,
"step": 207
},
{
"epoch": 0.61,
"learning_rate": 8.818259684263169e-06,
"loss": 0.3427,
"step": 208
},
{
"epoch": 0.61,
"learning_rate": 8.705049962587153e-06,
"loss": 0.3143,
"step": 209
},
{
"epoch": 0.61,
"learning_rate": 8.592182099550825e-06,
"loss": 0.3059,
"step": 210
},
{
"epoch": 0.62,
"learning_rate": 8.479666262575023e-06,
"loss": 0.3083,
"step": 211
},
{
"epoch": 0.62,
"learning_rate": 8.367512587369202e-06,
"loss": 0.3015,
"step": 212
},
{
"epoch": 0.62,
"learning_rate": 8.255731177018381e-06,
"loss": 0.2943,
"step": 213
},
{
"epoch": 0.63,
"learning_rate": 8.144332101073015e-06,
"loss": 0.2968,
"step": 214
},
{
"epoch": 0.63,
"learning_rate": 8.033325394641911e-06,
"loss": 0.3288,
"step": 215
},
{
"epoch": 0.63,
"learning_rate": 7.92272105748826e-06,
"loss": 0.3217,
"step": 216
},
{
"epoch": 0.63,
"learning_rate": 7.81252905312879e-06,
"loss": 0.2866,
"step": 217
},
{
"epoch": 0.64,
"learning_rate": 7.702759307936288e-06,
"loss": 0.2821,
"step": 218
},
{
"epoch": 0.64,
"learning_rate": 7.593421710245349e-06,
"loss": 0.3085,
"step": 219
},
{
"epoch": 0.64,
"learning_rate": 7.484526109461643e-06,
"loss": 0.2719,
"step": 220
},
{
"epoch": 0.65,
"learning_rate": 7.376082315174643e-06,
"loss": 0.2787,
"step": 221
},
{
"epoch": 0.65,
"learning_rate": 7.268100096273966e-06,
"loss": 0.2863,
"step": 222
},
{
"epoch": 0.65,
"learning_rate": 7.160589180069352e-06,
"loss": 0.3034,
"step": 223
},
{
"epoch": 0.65,
"learning_rate": 7.053559251414407e-06,
"loss": 0.3081,
"step": 224
},
{
"epoch": 0.66,
"learning_rate": 6.947019951834173e-06,
"loss": 0.282,
"step": 225
},
{
"epoch": 0.66,
"learning_rate": 6.840980878656592e-06,
"loss": 0.6257,
"step": 226
},
{
"epoch": 0.66,
"learning_rate": 6.735451584147952e-06,
"loss": 0.2789,
"step": 227
},
{
"epoch": 0.67,
"learning_rate": 6.630441574652396e-06,
"loss": 0.2921,
"step": 228
},
{
"epoch": 0.67,
"learning_rate": 6.5259603097355725e-06,
"loss": 0.3476,
"step": 229
},
{
"epoch": 0.67,
"learning_rate": 6.422017201332478e-06,
"loss": 0.337,
"step": 230
},
{
"epoch": 0.68,
"learning_rate": 6.318621612899641e-06,
"loss": 0.3057,
"step": 231
},
{
"epoch": 0.68,
"learning_rate": 6.215782858571586e-06,
"loss": 0.2956,
"step": 232
},
{
"epoch": 0.68,
"learning_rate": 6.113510202321836e-06,
"loss": 0.3095,
"step": 233
},
{
"epoch": 0.68,
"learning_rate": 6.011812857128371e-06,
"loss": 0.3404,
"step": 234
},
{
"epoch": 0.69,
"learning_rate": 5.910699984143718e-06,
"loss": 0.32,
"step": 235
},
{
"epoch": 0.69,
"learning_rate": 5.810180691869664e-06,
"loss": 0.2899,
"step": 236
},
{
"epoch": 0.69,
"learning_rate": 5.710264035336759e-06,
"loss": 0.2973,
"step": 237
},
{
"epoch": 0.7,
"learning_rate": 5.610959015288604e-06,
"loss": 0.3392,
"step": 238
},
{
"epoch": 0.7,
"learning_rate": 5.512274577371049e-06,
"loss": 0.3206,
"step": 239
},
{
"epoch": 0.7,
"learning_rate": 5.414219611326362e-06,
"loss": 0.2591,
"step": 240
},
{
"epoch": 0.7,
"learning_rate": 5.316802950192382e-06,
"loss": 0.331,
"step": 241
},
{
"epoch": 0.71,
"learning_rate": 5.220033369506845e-06,
"loss": 0.3198,
"step": 242
},
{
"epoch": 0.71,
"learning_rate": 5.1239195865168534e-06,
"loss": 0.3303,
"step": 243
},
{
"epoch": 0.71,
"learning_rate": 5.028470259393605e-06,
"loss": 0.3195,
"step": 244
},
{
"epoch": 0.72,
"learning_rate": 4.9336939864524425e-06,
"loss": 0.3184,
"step": 245
},
{
"epoch": 0.72,
"learning_rate": 4.839599305378294e-06,
"loss": 0.3269,
"step": 246
},
{
"epoch": 0.72,
"learning_rate": 4.746194692456579e-06,
"loss": 0.2523,
"step": 247
},
{
"epoch": 0.73,
"learning_rate": 4.6534885618096465e-06,
"loss": 0.3548,
"step": 248
},
{
"epoch": 0.73,
"learning_rate": 4.5614892646388e-06,
"loss": 0.2976,
"step": 249
},
{
"epoch": 0.73,
"learning_rate": 4.470205088472014e-06,
"loss": 0.3057,
"step": 250
},
{
"epoch": 0.73,
"learning_rate": 4.37964425641736e-06,
"loss": 0.3329,
"step": 251
},
{
"epoch": 0.74,
"learning_rate": 4.28981492642225e-06,
"loss": 0.3168,
"step": 252
},
{
"epoch": 0.74,
"learning_rate": 4.200725190538567e-06,
"loss": 0.3062,
"step": 253
},
{
"epoch": 0.74,
"learning_rate": 4.112383074193685e-06,
"loss": 0.2965,
"step": 254
},
{
"epoch": 0.75,
"learning_rate": 4.024796535467522e-06,
"loss": 0.2602,
"step": 255
},
{
"epoch": 0.75,
"learning_rate": 3.9379734643756774e-06,
"loss": 0.2906,
"step": 256
},
{
"epoch": 0.75,
"learning_rate": 3.85192168215867e-06,
"loss": 0.3076,
"step": 257
},
{
"epoch": 0.75,
"learning_rate": 3.766648940577369e-06,
"loss": 0.2998,
"step": 258
},
{
"epoch": 0.76,
"learning_rate": 3.6821629212147086e-06,
"loss": 0.3433,
"step": 259
},
{
"epoch": 0.76,
"learning_rate": 3.5984712347837083e-06,
"loss": 0.231,
"step": 260
},
{
"epoch": 0.76,
"learning_rate": 3.5155814204418672e-06,
"loss": 0.3227,
"step": 261
},
{
"epoch": 0.77,
"learning_rate": 3.4335009451120546e-06,
"loss": 0.2795,
"step": 262
},
{
"epoch": 0.77,
"learning_rate": 3.35223720280983e-06,
"loss": 0.286,
"step": 263
},
{
"epoch": 0.77,
"learning_rate": 3.2717975139773925e-06,
"loss": 0.2709,
"step": 264
},
{
"epoch": 0.77,
"learning_rate": 3.192189124824135e-06,
"loss": 0.3221,
"step": 265
},
{
"epoch": 0.78,
"learning_rate": 3.113419206673883e-06,
"loss": 0.3,
"step": 266
},
{
"epoch": 0.78,
"learning_rate": 3.0354948553188864e-06,
"loss": 0.3044,
"step": 267
},
{
"epoch": 0.78,
"learning_rate": 2.9584230903806147e-06,
"loss": 0.2697,
"step": 268
},
{
"epoch": 0.79,
"learning_rate": 2.8822108546774056e-06,
"loss": 0.2582,
"step": 269
},
{
"epoch": 0.79,
"learning_rate": 2.8068650135990444e-06,
"loss": 0.3168,
"step": 270
},
{
"epoch": 0.79,
"learning_rate": 2.7323923544883195e-06,
"loss": 0.2937,
"step": 271
},
{
"epoch": 0.8,
"learning_rate": 2.658799586029574e-06,
"loss": 0.3022,
"step": 272
},
{
"epoch": 0.8,
"learning_rate": 2.586093337644405e-06,
"loss": 0.2859,
"step": 273
},
{
"epoch": 0.8,
"learning_rate": 2.51428015889444e-06,
"loss": 0.2664,
"step": 274
},
{
"epoch": 0.8,
"learning_rate": 2.443366518891364e-06,
"loss": 0.3157,
"step": 275
},
{
"epoch": 0.81,
"learning_rate": 2.373358805714139e-06,
"loss": 0.282,
"step": 276
},
{
"epoch": 0.81,
"learning_rate": 2.304263325833565e-06,
"loss": 0.3231,
"step": 277
},
{
"epoch": 0.81,
"learning_rate": 2.2360863035441687e-06,
"loss": 0.332,
"step": 278
},
{
"epoch": 0.82,
"learning_rate": 2.168833880403509e-06,
"loss": 0.2946,
"step": 279
},
{
"epoch": 0.82,
"learning_rate": 2.102512114678941e-06,
"loss": 0.2883,
"step": 280
},
{
"epoch": 0.82,
"learning_rate": 2.037126980801844e-06,
"loss": 0.3,
"step": 281
},
{
"epoch": 0.82,
"learning_rate": 1.9726843688294543e-06,
"loss": 0.3085,
"step": 282
},
{
"epoch": 0.83,
"learning_rate": 1.909190083914264e-06,
"loss": 0.2834,
"step": 283
},
{
"epoch": 0.83,
"learning_rate": 1.84664984578108e-06,
"loss": 0.293,
"step": 284
},
{
"epoch": 0.83,
"learning_rate": 1.7850692882117756e-06,
"loss": 0.3056,
"step": 285
},
{
"epoch": 0.84,
"learning_rate": 1.7244539585377876e-06,
"loss": 0.2764,
"step": 286
},
{
"epoch": 0.84,
"learning_rate": 1.6648093171403923e-06,
"loss": 0.282,
"step": 287
},
{
"epoch": 0.84,
"learning_rate": 1.6061407369588416e-06,
"loss": 0.265,
"step": 288
},
{
"epoch": 0.85,
"learning_rate": 1.5484535030063196e-06,
"loss": 0.2962,
"step": 289
},
{
"epoch": 0.85,
"learning_rate": 1.491752811893883e-06,
"loss": 0.3393,
"step": 290
},
{
"epoch": 0.85,
"learning_rate": 1.4360437713623346e-06,
"loss": 0.3058,
"step": 291
},
{
"epoch": 0.85,
"learning_rate": 1.381331399822089e-06,
"loss": 0.2931,
"step": 292
},
{
"epoch": 0.86,
"learning_rate": 1.3276206259011242e-06,
"loss": 0.2935,
"step": 293
},
{
"epoch": 0.86,
"learning_rate": 1.2749162880009824e-06,
"loss": 0.3093,
"step": 294
},
{
"epoch": 0.86,
"learning_rate": 1.2232231338609136e-06,
"loss": 0.2724,
"step": 295
},
{
"epoch": 0.87,
"learning_rate": 1.1725458201301942e-06,
"loss": 0.315,
"step": 296
},
{
"epoch": 0.87,
"learning_rate": 1.1228889119486523e-06,
"loss": 0.2825,
"step": 297
},
{
"epoch": 0.87,
"learning_rate": 1.0742568825354086e-06,
"loss": 0.2676,
"step": 298
},
{
"epoch": 0.87,
"learning_rate": 1.0266541127859297e-06,
"loss": 0.2906,
"step": 299
},
{
"epoch": 0.88,
"learning_rate": 9.800848908773904e-07,
"loss": 0.2831,
"step": 300
},
{
"epoch": 0.88,
"learning_rate": 9.345534118823648e-07,
"loss": 0.2975,
"step": 301
},
{
"epoch": 0.88,
"learning_rate": 8.900637773909524e-07,
"loss": 0.3397,
"step": 302
},
{
"epoch": 0.89,
"learning_rate": 8.466199951412693e-07,
"loss": 0.3039,
"step": 303
},
{
"epoch": 0.89,
"learning_rate": 8.042259786584364e-07,
"loss": 0.3252,
"step": 304
},
{
"epoch": 0.89,
"learning_rate": 7.628855469020341e-07,
"loss": 0.3376,
"step": 305
},
{
"epoch": 0.89,
"learning_rate": 7.226024239220849e-07,
"loss": 0.2836,
"step": 306
},
{
"epoch": 0.9,
"learning_rate": 6.83380238523576e-07,
"loss": 0.3159,
"step": 307
},
{
"epoch": 0.9,
"learning_rate": 6.45222523939569e-07,
"loss": 0.3152,
"step": 308
},
{
"epoch": 0.9,
"learning_rate": 6.081327175129201e-07,
"loss": 0.3028,
"step": 309
},
{
"epoch": 0.91,
"learning_rate": 5.721141603866373e-07,
"loss": 0.2748,
"step": 310
},
{
"epoch": 0.91,
"learning_rate": 5.371700972028951e-07,
"loss": 0.2532,
"step": 311
},
{
"epoch": 0.91,
"learning_rate": 5.033036758107485e-07,
"loss": 0.3655,
"step": 312
},
{
"epoch": 0.92,
"learning_rate": 4.7051794698257936e-07,
"loss": 0.2931,
"step": 313
},
{
"epoch": 0.92,
"learning_rate": 4.3881586413925813e-07,
"loss": 0.2985,
"step": 314
},
{
"epoch": 0.92,
"learning_rate": 4.082002830841078e-07,
"loss": 0.2788,
"step": 315
},
{
"epoch": 0.92,
"learning_rate": 3.786739617456361e-07,
"loss": 0.3012,
"step": 316
},
{
"epoch": 0.93,
"learning_rate": 3.5023955992909697e-07,
"loss": 0.3143,
"step": 317
},
{
"epoch": 0.93,
"learning_rate": 3.2289963907688457e-07,
"loss": 0.3108,
"step": 318
},
{
"epoch": 0.93,
"learning_rate": 2.9665666203780586e-07,
"loss": 0.2578,
"step": 319
},
{
"epoch": 0.94,
"learning_rate": 2.7151299284520206e-07,
"loss": 0.3101,
"step": 320
},
{
"epoch": 0.94,
"learning_rate": 2.474708965040068e-07,
"loss": 0.3094,
"step": 321
},
{
"epoch": 0.94,
"learning_rate": 2.245325387866981e-07,
"loss": 0.2608,
"step": 322
},
{
"epoch": 0.94,
"learning_rate": 2.026999860382045e-07,
"loss": 0.3118,
"step": 323
},
{
"epoch": 0.95,
"learning_rate": 1.8197520498976357e-07,
"loss": 0.3102,
"step": 324
},
{
"epoch": 0.95,
"learning_rate": 1.6236006258175395e-07,
"loss": 0.2752,
"step": 325
},
{
"epoch": 0.95,
"learning_rate": 1.438563257955147e-07,
"loss": 0.3025,
"step": 326
},
{
"epoch": 0.96,
"learning_rate": 1.2646566149417255e-07,
"loss": 0.2947,
"step": 327
},
{
"epoch": 0.96,
"learning_rate": 1.1018963627248968e-07,
"loss": 0.2851,
"step": 328
},
{
"epoch": 0.96,
"learning_rate": 9.502971631573099e-08,
"loss": 0.3199,
"step": 329
},
{
"epoch": 0.96,
"learning_rate": 8.098726726760014e-08,
"loss": 0.2608,
"step": 330
},
{
"epoch": 0.97,
"learning_rate": 6.806355410720888e-08,
"loss": 0.3411,
"step": 331
},
{
"epoch": 0.97,
"learning_rate": 5.6259741035127875e-08,
"loss": 0.3067,
"step": 332
},
{
"epoch": 0.97,
"learning_rate": 4.5576891368513675e-08,
"loss": 0.2826,
"step": 333
},
{
"epoch": 0.98,
"learning_rate": 3.6015967445320044e-08,
"loss": 0.3149,
"step": 334
},
{
"epoch": 0.98,
"learning_rate": 2.7577830537608985e-08,
"loss": 0.3052,
"step": 335
},
{
"epoch": 0.98,
"learning_rate": 2.0263240773966963e-08,
"loss": 0.3009,
"step": 336
},
{
"epoch": 0.99,
"learning_rate": 1.4072857071027735e-08,
"loss": 0.287,
"step": 337
},
{
"epoch": 0.99,
"learning_rate": 9.007237074118435e-09,
"loss": 0.2913,
"step": 338
},
{
"epoch": 0.99,
"learning_rate": 5.0668371070219935e-09,
"loss": 0.287,
"step": 339
},
{
"epoch": 0.99,
"learning_rate": 2.2520121308752805e-09,
"loss": 0.2674,
"step": 340
},
{
"epoch": 1.0,
"learning_rate": 5.630157121863655e-10,
"loss": 0.3126,
"step": 341
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.268,
"step": 342
},
{
"epoch": 1.0,
"step": 342,
"total_flos": 0.0,
"train_loss": 0.3434351306648282,
"train_runtime": 6673.4034,
"train_samples_per_second": 3.278,
"train_steps_per_second": 0.051
}
],
"logging_steps": 1.0,
"max_steps": 342,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50000,
"total_flos": 0.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}