{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5780680964217585,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.0185,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 0.8649,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 0.7784,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 0.7386,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7037,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001990530303030303,
      "loss": 0.7019,
      "step": 120
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001981060606060606,
      "loss": 0.7117,
      "step": 140
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019715909090909094,
      "loss": 0.672,
      "step": 160
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019621212121212123,
      "loss": 0.664,
      "step": 180
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019526515151515152,
      "loss": 0.6666,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001943181818181818,
      "loss": 0.6685,
      "step": 220
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019337121212121213,
      "loss": 0.6788,
      "step": 240
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019242424242424245,
      "loss": 0.6673,
      "step": 260
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019147727272727274,
      "loss": 0.6628,
      "step": 280
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019053030303030303,
      "loss": 0.6643,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018958333333333332,
      "loss": 0.6607,
      "step": 320
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018863636363636364,
      "loss": 0.6706,
      "step": 340
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018768939393939396,
      "loss": 0.6709,
      "step": 360
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018674242424242425,
      "loss": 0.6616,
      "step": 380
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018579545454545454,
      "loss": 0.6566,
      "step": 400
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018484848484848484,
      "loss": 0.6513,
      "step": 420
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00018390151515151518,
      "loss": 0.6797,
      "step": 440
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018295454545454547,
      "loss": 0.6599,
      "step": 460
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00018200757575757577,
      "loss": 0.6561,
      "step": 480
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00018106060606060606,
      "loss": 0.662,
      "step": 500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00018011363636363638,
      "loss": 0.6629,
      "step": 520
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001791666666666667,
      "loss": 0.6475,
      "step": 540
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017821969696969699,
      "loss": 0.6607,
      "step": 560
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017727272727272728,
      "loss": 0.6512,
      "step": 580
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00017632575757575757,
      "loss": 0.6484,
      "step": 600
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001753787878787879,
      "loss": 0.6403,
      "step": 620
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001744318181818182,
      "loss": 0.6537,
      "step": 640
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001734848484848485,
      "loss": 0.6516,
      "step": 660
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001725378787878788,
      "loss": 0.6577,
      "step": 680
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00017159090909090908,
      "loss": 0.6374,
      "step": 700
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001706439393939394,
      "loss": 0.6551,
      "step": 720
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00016969696969696972,
      "loss": 0.6388,
      "step": 740
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00016875,
      "loss": 0.64,
      "step": 760
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001678030303030303,
      "loss": 0.6579,
      "step": 780
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001668560606060606,
      "loss": 0.6525,
      "step": 800
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016590909090909094,
      "loss": 0.6261,
      "step": 820
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00016496212121212123,
      "loss": 0.6351,
      "step": 840
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00016401515151515152,
      "loss": 0.6537,
      "step": 860
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001630681818181818,
      "loss": 0.6448,
      "step": 880
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00016212121212121213,
      "loss": 0.638,
      "step": 900
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00016117424242424245,
      "loss": 0.6503,
      "step": 920
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00016022727272727274,
      "loss": 0.6378,
      "step": 940
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00015928030303030303,
      "loss": 0.643,
      "step": 960
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015833333333333332,
      "loss": 0.6235,
      "step": 980
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00015738636363636364,
      "loss": 0.647,
      "step": 1000
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015643939393939396,
      "loss": 0.6408,
      "step": 1020
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00015549242424242425,
      "loss": 0.6391,
      "step": 1040
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.6356,
      "step": 1060
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015359848484848484,
      "loss": 0.6317,
      "step": 1080
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00015265151515151515,
      "loss": 0.6413,
      "step": 1100
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015170454545454547,
      "loss": 0.6338,
      "step": 1120
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015075757575757576,
      "loss": 0.6422,
      "step": 1140
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014981060606060606,
      "loss": 0.6442,
      "step": 1160
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00014886363636363635,
      "loss": 0.6523,
      "step": 1180
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001479166666666667,
      "loss": 0.6349,
      "step": 1200
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00014696969696969698,
      "loss": 0.6389,
      "step": 1220
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014602272727272728,
      "loss": 0.6468,
      "step": 1240
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00014507575757575757,
      "loss": 0.6431,
      "step": 1260
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00014412878787878789,
      "loss": 0.6287,
      "step": 1280
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001431818181818182,
      "loss": 0.6438,
      "step": 1300
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001422348484848485,
      "loss": 0.6274,
      "step": 1320
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001412878787878788,
      "loss": 0.6286,
      "step": 1340
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00014034090909090908,
      "loss": 0.6401,
      "step": 1360
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001393939393939394,
      "loss": 0.6472,
      "step": 1380
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00013844696969696972,
      "loss": 0.6458,
      "step": 1400
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001375,
      "loss": 0.6117,
      "step": 1420
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001365530303030303,
      "loss": 0.6271,
      "step": 1440
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001356060606060606,
      "loss": 0.6287,
      "step": 1460
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00013465909090909094,
      "loss": 0.6336,
      "step": 1480
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013371212121212123,
      "loss": 0.6404,
      "step": 1500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00013276515151515152,
      "loss": 0.6312,
      "step": 1520
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001318181818181818,
      "loss": 0.6168,
      "step": 1540
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00013087121212121213,
      "loss": 0.6272,
      "step": 1560
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012992424242424245,
      "loss": 0.6477,
      "step": 1580
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012897727272727274,
      "loss": 0.6477,
      "step": 1600
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00012803030303030303,
      "loss": 0.6227,
      "step": 1620
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012708333333333332,
      "loss": 0.6224,
      "step": 1640
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00012613636363636364,
      "loss": 0.6315,
      "step": 1660
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012518939393939396,
      "loss": 0.631,
      "step": 1680
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00012424242424242425,
      "loss": 0.6285,
      "step": 1700
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012329545454545454,
      "loss": 0.6359,
      "step": 1720
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00012234848484848484,
      "loss": 0.6282,
      "step": 1740
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00012140151515151517,
      "loss": 0.6196,
      "step": 1760
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00012045454545454546,
      "loss": 0.6346,
      "step": 1780
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011950757575757576,
      "loss": 0.6323,
      "step": 1800
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00011856060606060606,
      "loss": 0.6108,
      "step": 1820
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011761363636363636,
      "loss": 0.6324,
      "step": 1840
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011666666666666668,
      "loss": 0.618,
      "step": 1860
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00011571969696969698,
      "loss": 0.6099,
      "step": 1880
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011477272727272728,
      "loss": 0.6251,
      "step": 1900
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00011382575757575758,
      "loss": 0.6209,
      "step": 1920
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001128787878787879,
      "loss": 0.6218,
      "step": 1940
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011193181818181819,
      "loss": 0.6299,
      "step": 1960
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001109848484848485,
      "loss": 0.6211,
      "step": 1980
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011003787878787879,
      "loss": 0.6072,
      "step": 2000
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.6264,
      "step": 2020
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00010814393939393941,
      "loss": 0.6248,
      "step": 2040
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001071969696969697,
      "loss": 0.6125,
      "step": 2060
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010625000000000001,
      "loss": 0.6294,
      "step": 2080
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001053030303030303,
      "loss": 0.6193,
      "step": 2100
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001043560606060606,
      "loss": 0.6293,
      "step": 2120
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010340909090909092,
      "loss": 0.629,
      "step": 2140
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010246212121212121,
      "loss": 0.6353,
      "step": 2160
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010151515151515152,
      "loss": 0.6268,
      "step": 2180
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010056818181818181,
      "loss": 0.6256,
      "step": 2200
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.962121212121213e-05,
      "loss": 0.6404,
      "step": 2220
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.867424242424242e-05,
      "loss": 0.6347,
      "step": 2240
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.772727272727274e-05,
      "loss": 0.6317,
      "step": 2260
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.678030303030303e-05,
      "loss": 0.6335,
      "step": 2280
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.583333333333334e-05,
      "loss": 0.6239,
      "step": 2300
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.488636363636364e-05,
      "loss": 0.6302,
      "step": 2320
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.393939393939395e-05,
      "loss": 0.6182,
      "step": 2340
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.299242424242425e-05,
      "loss": 0.6219,
      "step": 2360
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.204545454545454e-05,
      "loss": 0.6229,
      "step": 2380
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.109848484848486e-05,
      "loss": 0.6413,
      "step": 2400
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.015151515151515e-05,
      "loss": 0.6237,
      "step": 2420
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.920454545454546e-05,
      "loss": 0.6397,
      "step": 2440
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.825757575757576e-05,
      "loss": 0.6259,
      "step": 2460
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.731060606060605e-05,
      "loss": 0.634,
      "step": 2480
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.636363636363637e-05,
      "loss": 0.622,
      "step": 2500
    }
  ],
  "logging_steps": 20,
  "max_steps": 4324,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 3.972710256835707e+17,
  "trial_name": null,
  "trial_params": null
}