{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.5459,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.4236,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2e-05,
      "loss": 3.3178,
      "step": 3
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.9503,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 0.6993,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9997864167879313e-05,
      "loss": 2.327,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.999145758387301e-05,
      "loss": 0.8785,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9980782984658682e-05,
      "loss": 0.6654,
      "step": 8
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.99658449300667e-05,
      "loss": 0.5044,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.994664980113243e-05,
      "loss": 0.4355,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.992320579737045e-05,
      "loss": 0.4326,
      "step": 11
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9895522933272028e-05,
      "loss": 0.3328,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.3407,
      "step": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9827489730473597e-05,
      "loss": 0.3706,
      "step": 14
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9787168453273546e-05,
      "loss": 0.3583,
      "step": 15
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9742666426322877e-05,
      "loss": 0.3605,
      "step": 16
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9694002659393306e-05,
      "loss": 0.3485,
      "step": 17
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9641197940012136e-05,
      "loss": 0.3165,
      "step": 18
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.958427482458253e-05,
      "loss": 0.3427,
      "step": 19
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9523257628748148e-05,
      "loss": 0.304,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9458172417006347e-05,
      "loss": 0.3207,
      "step": 21
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9389046991574298e-05,
      "loss": 0.3279,
      "step": 22
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.321,
      "step": 23
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9238795325112867e-05,
      "loss": 0.3537,
      "step": 24
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9157733266550577e-05,
      "loss": 0.3393,
      "step": 25
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9072759331815602e-05,
      "loss": 0.3461,
      "step": 26
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.898390981891979e-05,
      "loss": 0.2947,
      "step": 27
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8891222681391853e-05,
      "loss": 0.2954,
      "step": 28
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.879473751206489e-05,
      "loss": 0.379,
      "step": 29
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.869449552616367e-05,
      "loss": 0.3091,
      "step": 30
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8590539543698852e-05,
      "loss": 0.3874,
      "step": 31
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8482913971175737e-05,
      "loss": 0.2951,
      "step": 32
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.311,
      "step": 33
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.825683949996556e-05,
      "loss": 0.3077,
      "step": 34
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.813848717270195e-05,
      "loss": 0.291,
      "step": 35
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8016658356974885e-05,
      "loss": 0.2943,
      "step": 36
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.789140509396394e-05,
      "loss": 0.2756,
      "step": 37
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7762780887657576e-05,
      "loss": 0.3445,
      "step": 38
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7630840681998068e-05,
      "loss": 0.3063,
      "step": 39
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7495640837411265e-05,
      "loss": 0.3492,
      "step": 40
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.735723910673132e-05,
      "loss": 0.2996,
      "step": 41
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7215694610530624e-05,
      "loss": 0.3605,
      "step": 42
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.2549,
      "step": 43
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6923420490448298e-05,
      "loss": 0.3088,
      "step": 44
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 0.3427,
      "step": 45
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6619317822595666e-05,
      "loss": 0.3391,
      "step": 46
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.646299237860941e-05,
      "loss": 0.2995,
      "step": 47
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.6303906161279554e-05,
      "loss": 0.3122,
      "step": 48
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.6142127126896682e-05,
      "loss": 0.3089,
      "step": 49
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.597772438203241e-05,
      "loss": 0.278,
      "step": 50
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.5810768154019386e-05,
      "loss": 0.2876,
      "step": 51
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5641329760952514e-05,
      "loss": 0.3274,
      "step": 52
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.3166,
      "step": 53
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.529529702260709e-05,
      "loss": 0.2603,
      "step": 54
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.5118850490896012e-05,
      "loss": 0.2963,
      "step": 55
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4940217358125042e-05,
      "loss": 0.3985,
      "step": 56
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4759473930370738e-05,
      "loss": 0.325,
      "step": 57
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.4576697415156818e-05,
      "loss": 0.2987,
      "step": 58
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.4391965888473705e-05,
      "loss": 0.2841,
      "step": 59
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.4205358261427076e-05,
      "loss": 0.3268,
      "step": 60
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 0.2798,
      "step": 61
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3826834323650899e-05,
      "loss": 0.3086,
      "step": 62
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.3317,
      "step": 63
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.3441772303626387e-05,
      "loss": 0.312,
      "step": 64
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.3246994692046837e-05,
      "loss": 0.2899,
      "step": 65
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.305083007335549e-05,
      "loss": 0.3314,
      "step": 66
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.2853362242491054e-05,
      "loss": 0.284,
      "step": 67
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.2654675551080724e-05,
      "loss": 0.2699,
      "step": 68
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.2454854871407993e-05,
      "loss": 0.2718,
      "step": 69
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2253985560158064e-05,
      "loss": 0.3029,
      "step": 70
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.2052153421956343e-05,
      "loss": 0.3093,
      "step": 71
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1849444672715587e-05,
      "loss": 0.2993,
      "step": 72
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.3281,
      "step": 73
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.1441744040073469e-05,
      "loss": 0.2663,
      "step": 74
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.123692631269348e-05,
      "loss": 0.2842,
      "step": 75
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.103158021192357e-05,
      "loss": 0.3225,
      "step": 76
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 0.3047,
      "step": 77
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0619653946285948e-05,
      "loss": 0.28,
      "step": 78
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0413249742488132e-05,
      "loss": 0.2996,
      "step": 79
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.0206669012275546e-05,
      "loss": 0.2882,
      "step": 80
    },
    {
      "epoch": 0.52,
      "learning_rate": 1e-05,
      "loss": 0.3044,
      "step": 81
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.79333098772446e-06,
      "loss": 0.3004,
      "step": 82
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.2704,
      "step": 83
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.380346053714055e-06,
      "loss": 0.2532,
      "step": 84
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.174206545276678e-06,
      "loss": 0.2969,
      "step": 85
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.968419788076431e-06,
      "loss": 0.2648,
      "step": 86
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.763073687306523e-06,
      "loss": 0.2812,
      "step": 87
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.558255959926533e-06,
      "loss": 0.2527,
      "step": 88
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.35405409719266e-06,
      "loss": 0.2644,
      "step": 89
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.150555327284417e-06,
      "loss": 0.2754,
      "step": 90
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.947846578043658e-06,
      "loss": 0.2949,
      "step": 91
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.746014439841941e-06,
      "loss": 0.3079,
      "step": 92
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.3297,
      "step": 93
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.34532444891928e-06,
      "loss": 0.2351,
      "step": 94
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.14663775750895e-06,
      "loss": 0.2349,
      "step": 95
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.949169926644513e-06,
      "loss": 0.2642,
      "step": 96
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.7530053079531664e-06,
      "loss": 0.2736,
      "step": 97
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.558227696373617e-06,
      "loss": 0.2431,
      "step": 98
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.364920294361701e-06,
      "loss": 0.2582,
      "step": 99
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.173165676349103e-06,
      "loss": 0.2632,
      "step": 100
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.983045753470308e-06,
      "loss": 0.2498,
      "step": 101
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.794641738572925e-06,
      "loss": 0.2633,
      "step": 102
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.608034111526298e-06,
      "loss": 0.248,
      "step": 103
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.423302584843186e-06,
      "loss": 0.283,
      "step": 104
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.240526069629265e-06,
      "loss": 0.2657,
      "step": 105
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.059782641874962e-06,
      "loss": 0.2329,
      "step": 106
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.881149509103993e-06,
      "loss": 0.2495,
      "step": 107
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.704702977392914e-06,
      "loss": 0.2664,
      "step": 108
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.530518418775734e-06,
      "loss": 0.2699,
      "step": 109
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.35867023904749e-06,
      "loss": 0.2597,
      "step": 110
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.189231845980618e-06,
      "loss": 0.327,
      "step": 111
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0222756179675915e-06,
      "loss": 0.2283,
      "step": 112
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.857872873103322e-06,
      "loss": 0.2445,
      "step": 113
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.69609383872045e-06,
      "loss": 0.2579,
      "step": 114
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5370076213905904e-06,
      "loss": 0.2195,
      "step": 115
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.380682177404335e-06,
      "loss": 0.3006,
      "step": 116
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.2271842837425917e-06,
      "loss": 0.2459,
      "step": 117
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0765795095517026e-06,
      "loss": 0.2546,
      "step": 118
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.2376,
      "step": 119
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7843053894693805e-06,
      "loss": 0.2738,
      "step": 120
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.642760893268684e-06,
      "loss": 0.2436,
      "step": 121
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.504359162588741e-06,
      "loss": 0.221,
      "step": 122
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.369159318001937e-06,
      "loss": 0.2476,
      "step": 123
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.237219112342426e-06,
      "loss": 0.2052,
      "step": 124
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1085949060360654e-06,
      "loss": 0.2399,
      "step": 125
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.983341643025117e-06,
      "loss": 0.2403,
      "step": 126
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.861512827298051e-06,
      "loss": 0.2393,
      "step": 127
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.743160500034443e-06,
      "loss": 0.219,
      "step": 128
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6283352173747148e-06,
      "loss": 0.2503,
      "step": 129
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5170860288242638e-06,
      "loss": 0.2611,
      "step": 130
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.409460456301147e-06,
      "loss": 0.2408,
      "step": 131
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.305504473836331e-06,
      "loss": 0.2139,
      "step": 132
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.258,
      "step": 133
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1087773186081474e-06,
      "loss": 0.2513,
      "step": 134
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0160901810802114e-06,
      "loss": 0.2434,
      "step": 135
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.272406681844015e-07,
      "loss": 0.2794,
      "step": 136
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.42266733449425e-07,
      "loss": 0.2445,
      "step": 137
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.254,
      "step": 138
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.840891194872112e-07,
      "loss": 0.2105,
      "step": 139
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.109530084257043e-07,
      "loss": 0.2271,
      "step": 140
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.418275829936537e-07,
      "loss": 0.235,
      "step": 141
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.7674237125185597e-07,
      "loss": 0.239,
      "step": 142
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.1572517541747294e-07,
      "loss": 0.2158,
      "step": 143
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.588020599878639e-07,
      "loss": 0.2405,
      "step": 144
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.059973406066963e-07,
      "loss": 0.2453,
      "step": 145
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.573335736771254e-07,
      "loss": 0.2459,
      "step": 146
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1283154672645522e-07,
      "loss": 0.1961,
      "step": 147
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7251026952640583e-07,
      "loss": 0.2459,
      "step": 148
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3638696597277678e-07,
      "loss": 0.2326,
      "step": 149
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0447706672797264e-07,
      "loss": 0.2694,
      "step": 150
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.679420262954984e-08,
      "loss": 0.2555,
      "step": 151
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.3350198867574424e-08,
      "loss": 0.2413,
      "step": 152
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 0.26,
      "step": 153
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9217015341318478e-08,
      "loss": 0.2099,
      "step": 154
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.542416126989805e-09,
      "loss": 0.2156,
      "step": 155
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.1358321206899067e-09,
      "loss": 0.2168,
      "step": 156
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.2159,
      "step": 157
    },
    {
      "epoch": 1.0,
      "step": 157,
      "total_flos": 17139579125760.0,
      "train_loss": 0.377779698106134,
      "train_runtime": 411.9962,
      "train_samples_per_second": 48.544,
      "train_steps_per_second": 0.381
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 17139579125760.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}