{
  "best_metric": 0.2225116640329361,
  "best_model_checkpoint": "loras/RTE-lora-results/checkpoint-500",
  "epoch": 7.211538461538462,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 5e-06,
      "loss": 0.2524,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 0.2422,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.5e-05,
      "loss": 0.2129,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.2744,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.5e-05,
      "loss": 0.2803,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 3e-05,
      "loss": 0.2949,
      "step": 60
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.5e-05,
      "loss": 0.2074,
      "step": 70
    },
    {
      "epoch": 0.38,
      "learning_rate": 4e-05,
      "loss": 0.2353,
      "step": 80
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.5e-05,
      "loss": 0.2032,
      "step": 90
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 0.2756,
      "step": 100
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.974747474747475e-05,
      "loss": 0.2318,
      "step": 110
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.94949494949495e-05,
      "loss": 0.259,
      "step": 120
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.9242424242424245e-05,
      "loss": 0.2474,
      "step": 130
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.898989898989899e-05,
      "loss": 0.2098,
      "step": 140
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.8737373737373736e-05,
      "loss": 0.2425,
      "step": 150
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.848484848484849e-05,
      "loss": 0.1971,
      "step": 160
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.823232323232323e-05,
      "loss": 0.2563,
      "step": 170
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.797979797979798e-05,
      "loss": 0.2695,
      "step": 180
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.772727272727273e-05,
      "loss": 0.2235,
      "step": 190
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.7474747474747476e-05,
      "loss": 0.2412,
      "step": 200
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.2255,
      "step": 210
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.696969696969697e-05,
      "loss": 0.2465,
      "step": 220
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.671717171717172e-05,
      "loss": 0.1868,
      "step": 230
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.6464646464646464e-05,
      "loss": 0.2158,
      "step": 240
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.621212121212121e-05,
      "loss": 0.2469,
      "step": 250
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.595959595959596e-05,
      "loss": 0.2274,
      "step": 260
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.5707070707070706e-05,
      "loss": 0.2137,
      "step": 270
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.1944,
      "step": 280
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.5202020202020204e-05,
      "loss": 0.2389,
      "step": 290
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.494949494949495e-05,
      "loss": 0.2667,
      "step": 300
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.46969696969697e-05,
      "loss": 0.2591,
      "step": 310
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.2623,
      "step": 320
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.41919191919192e-05,
      "loss": 0.2651,
      "step": 330
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 0.2339,
      "step": 340
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.368686868686869e-05,
      "loss": 0.234,
      "step": 350
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.343434343434344e-05,
      "loss": 0.2506,
      "step": 360
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.318181818181819e-05,
      "loss": 0.2703,
      "step": 370
    },
    {
      "epoch": 1.83,
      "learning_rate": 4.292929292929293e-05,
      "loss": 0.2095,
      "step": 380
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.267676767676768e-05,
      "loss": 0.2501,
      "step": 390
    },
    {
      "epoch": 1.92,
      "learning_rate": 4.242424242424243e-05,
      "loss": 0.1951,
      "step": 400
    },
    {
      "epoch": 1.97,
      "learning_rate": 4.2171717171717175e-05,
      "loss": 0.2671,
      "step": 410
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.191919191919192e-05,
      "loss": 0.2179,
      "step": 420
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.2111,
      "step": 430
    },
    {
      "epoch": 2.12,
      "learning_rate": 4.141414141414142e-05,
      "loss": 0.2502,
      "step": 440
    },
    {
      "epoch": 2.16,
      "learning_rate": 4.116161616161616e-05,
      "loss": 0.1938,
      "step": 450
    },
    {
      "epoch": 2.21,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.2539,
      "step": 460
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.065656565656566e-05,
      "loss": 0.2325,
      "step": 470
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.0404040404040405e-05,
      "loss": 0.1858,
      "step": 480
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.015151515151515e-05,
      "loss": 0.2226,
      "step": 490
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.98989898989899e-05,
      "loss": 0.2351,
      "step": 500
    },
    {
      "epoch": 2.4,
      "eval_MCC": 0.5743913241540748,
      "eval_accuracy": 0.7833935018050542,
      "eval_f1-score": 0.7794791361410579,
      "eval_loss": 0.2225116640329361,
      "eval_runtime": 6.5816,
      "eval_samples_per_second": 42.087,
      "eval_steps_per_second": 1.823,
      "step": 500
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.964646464646465e-05,
      "loss": 0.2408,
      "step": 510
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.939393939393939e-05,
      "loss": 0.2224,
      "step": 520
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.9141414141414145e-05,
      "loss": 0.26,
      "step": 530
    },
    {
      "epoch": 2.6,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.2238,
      "step": 540
    },
    {
      "epoch": 2.64,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 0.2423,
      "step": 550
    },
    {
      "epoch": 2.69,
      "learning_rate": 3.838383838383838e-05,
      "loss": 0.2227,
      "step": 560
    },
    {
      "epoch": 2.74,
      "learning_rate": 3.8131313131313133e-05,
      "loss": 0.2635,
      "step": 570
    },
    {
      "epoch": 2.79,
      "learning_rate": 3.787878787878788e-05,
      "loss": 0.236,
      "step": 580
    },
    {
      "epoch": 2.84,
      "learning_rate": 3.7626262626262624e-05,
      "loss": 0.2339,
      "step": 590
    },
    {
      "epoch": 2.88,
      "learning_rate": 3.7373737373737376e-05,
      "loss": 0.2831,
      "step": 600
    },
    {
      "epoch": 2.93,
      "learning_rate": 3.712121212121212e-05,
      "loss": 0.1818,
      "step": 610
    },
    {
      "epoch": 2.98,
      "learning_rate": 3.686868686868687e-05,
      "loss": 0.2263,
      "step": 620
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.661616161616162e-05,
      "loss": 0.2271,
      "step": 630
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.2386,
      "step": 640
    },
    {
      "epoch": 3.12,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.2285,
      "step": 650
    },
    {
      "epoch": 3.17,
      "learning_rate": 3.5858585858585855e-05,
      "loss": 0.1966,
      "step": 660
    },
    {
      "epoch": 3.22,
      "learning_rate": 3.560606060606061e-05,
      "loss": 0.2553,
      "step": 670
    },
    {
      "epoch": 3.27,
      "learning_rate": 3.535353535353535e-05,
      "loss": 0.2091,
      "step": 680
    },
    {
      "epoch": 3.32,
      "learning_rate": 3.5101010101010104e-05,
      "loss": 0.2359,
      "step": 690
    },
    {
      "epoch": 3.37,
      "learning_rate": 3.484848484848485e-05,
      "loss": 0.2194,
      "step": 700
    },
    {
      "epoch": 3.41,
      "learning_rate": 3.45959595959596e-05,
      "loss": 0.212,
      "step": 710
    },
    {
      "epoch": 3.46,
      "learning_rate": 3.434343434343435e-05,
      "loss": 0.2334,
      "step": 720
    },
    {
      "epoch": 3.51,
      "learning_rate": 3.409090909090909e-05,
      "loss": 0.2359,
      "step": 730
    },
    {
      "epoch": 3.56,
      "learning_rate": 3.3838383838383844e-05,
      "loss": 0.1982,
      "step": 740
    },
    {
      "epoch": 3.61,
      "learning_rate": 3.358585858585859e-05,
      "loss": 0.2275,
      "step": 750
    },
    {
      "epoch": 3.65,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1935,
      "step": 760
    },
    {
      "epoch": 3.7,
      "learning_rate": 3.308080808080809e-05,
      "loss": 0.2083,
      "step": 770
    },
    {
      "epoch": 3.75,
      "learning_rate": 3.282828282828283e-05,
      "loss": 0.2164,
      "step": 780
    },
    {
      "epoch": 3.8,
      "learning_rate": 3.257575757575758e-05,
      "loss": 0.2011,
      "step": 790
    },
    {
      "epoch": 3.85,
      "learning_rate": 3.232323232323233e-05,
      "loss": 0.1781,
      "step": 800
    },
    {
      "epoch": 3.89,
      "learning_rate": 3.2070707070707075e-05,
      "loss": 0.2711,
      "step": 810
    },
    {
      "epoch": 3.94,
      "learning_rate": 3.181818181818182e-05,
      "loss": 0.2304,
      "step": 820
    },
    {
      "epoch": 3.99,
      "learning_rate": 3.1565656565656566e-05,
      "loss": 0.2696,
      "step": 830
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.131313131313132e-05,
      "loss": 0.1603,
      "step": 840
    },
    {
      "epoch": 4.09,
      "learning_rate": 3.106060606060606e-05,
      "loss": 0.2524,
      "step": 850
    },
    {
      "epoch": 4.13,
      "learning_rate": 3.080808080808081e-05,
      "loss": 0.2174,
      "step": 860
    },
    {
      "epoch": 4.18,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.2224,
      "step": 870
    },
    {
      "epoch": 4.23,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 0.2071,
      "step": 880
    },
    {
      "epoch": 4.28,
      "learning_rate": 3.005050505050505e-05,
      "loss": 0.2331,
      "step": 890
    },
    {
      "epoch": 4.33,
      "learning_rate": 2.9797979797979796e-05,
      "loss": 0.1696,
      "step": 900
    },
    {
      "epoch": 4.38,
      "learning_rate": 2.954545454545455e-05,
      "loss": 0.2193,
      "step": 910
    },
    {
      "epoch": 4.42,
      "learning_rate": 2.9292929292929294e-05,
      "loss": 0.2337,
      "step": 920
    },
    {
      "epoch": 4.47,
      "learning_rate": 2.904040404040404e-05,
      "loss": 0.2351,
      "step": 930
    },
    {
      "epoch": 4.52,
      "learning_rate": 2.878787878787879e-05,
      "loss": 0.1655,
      "step": 940
    },
    {
      "epoch": 4.57,
      "learning_rate": 2.8535353535353536e-05,
      "loss": 0.2151,
      "step": 950
    },
    {
      "epoch": 4.62,
      "learning_rate": 2.8282828282828282e-05,
      "loss": 0.2667,
      "step": 960
    },
    {
      "epoch": 4.66,
      "learning_rate": 2.803030303030303e-05,
      "loss": 0.2228,
      "step": 970
    },
    {
      "epoch": 4.71,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.2036,
      "step": 980
    },
    {
      "epoch": 4.76,
      "learning_rate": 2.7525252525252528e-05,
      "loss": 0.2031,
      "step": 990
    },
    {
      "epoch": 4.81,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.2193,
      "step": 1000
    },
    {
      "epoch": 4.81,
      "eval_MCC": 0.6229024526089935,
      "eval_accuracy": 0.8086642599277978,
      "eval_f1-score": 0.8061174971587979,
      "eval_loss": 0.21737736463546753,
      "eval_runtime": 4.873,
      "eval_samples_per_second": 56.844,
      "eval_steps_per_second": 2.463,
      "step": 1000
    },
    {
      "epoch": 4.86,
      "learning_rate": 2.7020202020202022e-05,
      "loss": 0.2319,
      "step": 1010
    },
    {
      "epoch": 4.9,
      "learning_rate": 2.676767676767677e-05,
      "loss": 0.2138,
      "step": 1020
    },
    {
      "epoch": 4.95,
      "learning_rate": 2.6515151515151516e-05,
      "loss": 0.2005,
      "step": 1030
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.6262626262626268e-05,
      "loss": 0.2562,
      "step": 1040
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.6010101010101013e-05,
      "loss": 0.1982,
      "step": 1050
    },
    {
      "epoch": 5.1,
      "learning_rate": 2.575757575757576e-05,
      "loss": 0.283,
      "step": 1060
    },
    {
      "epoch": 5.14,
      "learning_rate": 2.5505050505050504e-05,
      "loss": 0.1957,
      "step": 1070
    },
    {
      "epoch": 5.19,
      "learning_rate": 2.5252525252525256e-05,
      "loss": 0.2135,
      "step": 1080
    },
    {
      "epoch": 5.24,
      "learning_rate": 2.5e-05,
      "loss": 0.2646,
      "step": 1090
    },
    {
      "epoch": 5.29,
      "learning_rate": 2.474747474747475e-05,
      "loss": 0.1809,
      "step": 1100
    },
    {
      "epoch": 5.34,
      "learning_rate": 2.4494949494949495e-05,
      "loss": 0.2026,
      "step": 1110
    },
    {
      "epoch": 5.38,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 0.2504,
      "step": 1120
    },
    {
      "epoch": 5.43,
      "learning_rate": 2.398989898989899e-05,
      "loss": 0.2255,
      "step": 1130
    },
    {
      "epoch": 5.48,
      "learning_rate": 2.3737373737373738e-05,
      "loss": 0.2645,
      "step": 1140
    },
    {
      "epoch": 5.53,
      "learning_rate": 2.3484848484848487e-05,
      "loss": 0.2531,
      "step": 1150
    },
    {
      "epoch": 5.58,
      "learning_rate": 2.3232323232323232e-05,
      "loss": 0.2036,
      "step": 1160
    },
    {
      "epoch": 5.62,
      "learning_rate": 2.297979797979798e-05,
      "loss": 0.2628,
      "step": 1170
    },
    {
      "epoch": 5.67,
      "learning_rate": 2.272727272727273e-05,
      "loss": 0.195,
      "step": 1180
    },
    {
      "epoch": 5.72,
      "learning_rate": 2.2474747474747475e-05,
      "loss": 0.2283,
      "step": 1190
    },
    {
      "epoch": 5.77,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.2091,
      "step": 1200
    },
    {
      "epoch": 5.82,
      "learning_rate": 2.1969696969696972e-05,
      "loss": 0.2065,
      "step": 1210
    },
    {
      "epoch": 5.87,
      "learning_rate": 2.171717171717172e-05,
      "loss": 0.1773,
      "step": 1220
    },
    {
      "epoch": 5.91,
      "learning_rate": 2.1464646464646466e-05,
      "loss": 0.2471,
      "step": 1230
    },
    {
      "epoch": 5.96,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 0.215,
      "step": 1240
    },
    {
      "epoch": 6.01,
      "learning_rate": 2.095959595959596e-05,
      "loss": 0.1833,
      "step": 1250
    },
    {
      "epoch": 6.06,
      "learning_rate": 2.070707070707071e-05,
      "loss": 0.1981,
      "step": 1260
    },
    {
      "epoch": 6.11,
      "learning_rate": 2.0454545454545457e-05,
      "loss": 0.2149,
      "step": 1270
    },
    {
      "epoch": 6.15,
      "learning_rate": 2.0202020202020203e-05,
      "loss": 0.1759,
      "step": 1280
    },
    {
      "epoch": 6.2,
      "learning_rate": 1.994949494949495e-05,
      "loss": 0.2351,
      "step": 1290
    },
    {
      "epoch": 6.25,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 0.2085,
      "step": 1300
    },
    {
      "epoch": 6.3,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.2169,
      "step": 1310
    },
    {
      "epoch": 6.35,
      "learning_rate": 1.919191919191919e-05,
      "loss": 0.2034,
      "step": 1320
    },
    {
      "epoch": 6.39,
      "learning_rate": 1.893939393939394e-05,
      "loss": 0.2673,
      "step": 1330
    },
    {
      "epoch": 6.44,
      "learning_rate": 1.8686868686868688e-05,
      "loss": 0.1767,
      "step": 1340
    },
    {
      "epoch": 6.49,
      "learning_rate": 1.8434343434343433e-05,
      "loss": 0.2386,
      "step": 1350
    },
    {
      "epoch": 6.54,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.2157,
      "step": 1360
    },
    {
      "epoch": 6.59,
      "learning_rate": 1.7929292929292927e-05,
      "loss": 0.2151,
      "step": 1370
    },
    {
      "epoch": 6.63,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.2447,
      "step": 1380
    },
    {
      "epoch": 6.68,
      "learning_rate": 1.7424242424242425e-05,
      "loss": 0.2385,
      "step": 1390
    },
    {
      "epoch": 6.73,
      "learning_rate": 1.7171717171717173e-05,
      "loss": 0.1787,
      "step": 1400
    },
    {
      "epoch": 6.78,
      "learning_rate": 1.6919191919191922e-05,
      "loss": 0.1873,
      "step": 1410
    },
    {
      "epoch": 6.83,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.2398,
      "step": 1420
    },
    {
      "epoch": 6.88,
      "learning_rate": 1.6414141414141416e-05,
      "loss": 0.1952,
      "step": 1430
    },
    {
      "epoch": 6.92,
      "learning_rate": 1.6161616161616165e-05,
      "loss": 0.2513,
      "step": 1440
    },
    {
      "epoch": 6.97,
      "learning_rate": 1.590909090909091e-05,
      "loss": 0.1848,
      "step": 1450
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.565656565656566e-05,
      "loss": 0.2341,
      "step": 1460
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.5404040404040404e-05,
      "loss": 0.1803,
      "step": 1470
    },
    {
      "epoch": 7.12,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.2258,
      "step": 1480
    },
    {
      "epoch": 7.16,
      "learning_rate": 1.4898989898989898e-05,
      "loss": 0.2159,
      "step": 1490
    },
    {
      "epoch": 7.21,
      "learning_rate": 1.4646464646464647e-05,
      "loss": 0.2416,
      "step": 1500
    },
    {
      "epoch": 7.21,
      "eval_MCC": 0.6271860965381456,
      "eval_accuracy": 0.8122743682310469,
      "eval_f1-score": 0.8105339578920151,
      "eval_loss": 0.21340395510196686,
      "eval_runtime": 4.8244,
      "eval_samples_per_second": 57.416,
      "eval_steps_per_second": 2.487,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 2080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6172840372469760.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}