{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06255082254331644,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.8341,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.9527,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.9158,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 1.8797,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 1.7949,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.7219,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 1.623,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00014,
      "loss": 1.5828,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 1.5208,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018,
      "loss": 1.4697,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.4292,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001999390827019096,
      "loss": 1.4127,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019975640502598244,
      "loss": 1.3752,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019945218953682734,
      "loss": 1.338,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.325,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.3627,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.3026,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.3302,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.3032,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3538,
      "step": 95
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.3524,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019271838545667876,
      "loss": 1.2811,
      "step": 105
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.2991,
      "step": 110
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001898794046299167,
      "loss": 1.314,
      "step": 115
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.2834,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.3266,
      "step": 125
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001848048096156426,
      "loss": 1.294,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018290375725550417,
      "loss": 1.3133,
      "step": 135
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3191,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.2459,
      "step": 145
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.3149,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00017431448254773944,
      "loss": 1.2173,
      "step": 155
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001719339800338651,
      "loss": 1.277,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016946583704589973,
      "loss": 1.2873,
      "step": 165
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.2535,
      "step": 170
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016427876096865394,
      "loss": 1.2991,
      "step": 175
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.2486,
      "step": 180
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.3577,
      "step": 185
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001559192903470747,
      "loss": 1.2981,
      "step": 190
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001529919264233205,
      "loss": 1.3271,
      "step": 195
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3087,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014694715627858908,
      "loss": 1.2858,
      "step": 205
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014383711467890774,
      "loss": 1.306,
      "step": 210
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00014067366430758004,
      "loss": 1.279,
      "step": 215
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013746065934159123,
      "loss": 1.3175,
      "step": 220
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013420201433256689,
      "loss": 1.2362,
      "step": 225
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2573,
      "step": 230
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001275637355816999,
      "loss": 1.2666,
      "step": 235
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012419218955996676,
      "loss": 1.2854,
      "step": 240
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00012079116908177593,
      "loss": 1.3342,
      "step": 245
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.2907,
      "step": 250
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011391731009600654,
      "loss": 1.2878,
      "step": 255
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.2695,
      "step": 260
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010697564737441252,
      "loss": 1.2497,
      "step": 265
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010348994967025012,
      "loss": 1.2663,
      "step": 270
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.2748,
      "step": 275
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.651005032974994e-05,
      "loss": 1.2526,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.302435262558747e-05,
      "loss": 1.3002,
      "step": 285
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.2367,
      "step": 290
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.608268990399349e-05,
      "loss": 1.2935,
      "step": 295
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.3007,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.920883091822408e-05,
      "loss": 1.3359,
      "step": 305
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.580781044003324e-05,
      "loss": 1.2743,
      "step": 310
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.243626441830009e-05,
      "loss": 1.2772,
      "step": 315
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.2885,
      "step": 320
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.579798566743314e-05,
      "loss": 1.2912,
      "step": 325
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.25393406584088e-05,
      "loss": 1.2306,
      "step": 330
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 1.3064,
      "step": 335
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.616288532109225e-05,
      "loss": 1.297,
      "step": 340
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.305284372141095e-05,
      "loss": 1.2715,
      "step": 345
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2466,
      "step": 350
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.700807357667952e-05,
      "loss": 1.2669,
      "step": 355
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 1.249,
      "step": 360
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.235,
      "step": 365
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.843385246743417e-05,
      "loss": 1.2891,
      "step": 370
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 1.2281,
      "step": 375
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.2338,
      "step": 380
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.053416295410026e-05,
      "loss": 1.2941,
      "step": 385
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 1.2671,
      "step": 390
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 1.3195,
      "step": 395
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.339555568810221e-05,
      "loss": 1.2021,
      "step": 400
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.119892463932781e-05,
      "loss": 1.2715,
      "step": 405
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.2557,
      "step": 410
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 1.3001,
      "step": 415
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 1.2931,
      "step": 420
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.2374,
      "step": 425
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 1.2925,
      "step": 430
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 1.2766,
      "step": 435
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.3244,
      "step": 440
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.281614543321269e-06,
      "loss": 1.3404,
      "step": 445
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.030737921409169e-06,
      "loss": 1.2886,
      "step": 450
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.3172,
      "step": 455
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.873830406168111e-06,
      "loss": 1.2714,
      "step": 460
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.970427372400353e-06,
      "loss": 1.2419,
      "step": 465
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.2816,
      "step": 470
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 1.252,
      "step": 475
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.731931258429638e-07,
      "loss": 1.2246,
      "step": 480
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.478104631726711e-07,
      "loss": 1.2728,
      "step": 485
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 1.2357,
      "step": 490
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.09172980904238e-08,
      "loss": 1.2624,
      "step": 495
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 1.2922,
      "step": 500
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.249782919883728,
      "eval_runtime": 1717.6564,
      "eval_samples_per_second": 16.48,
      "eval_steps_per_second": 1.03,
      "step": 500
    },
    {
      "epoch": 0.06,
      "step": 500,
      "total_flos": 1123799500062720.0,
      "train_loss": 1.3271520497798919,
      "train_runtime": 4460.9425,
      "train_samples_per_second": 3.587,
      "train_steps_per_second": 0.112
    }
  ],
  "logging_steps": 5,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1123799500062720.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}