{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9166666666666666,
  "eval_steps": 30,
  "global_step": 990,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 1.4898,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.603,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 9e-07,
      "loss": 1.7131,
      "step": 30
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.6769884824752808,
      "eval_runtime": 42.9173,
      "eval_samples_per_second": 4.66,
      "eval_steps_per_second": 0.583,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.7649,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.5e-06,
      "loss": 1.9524,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.8e-06,
      "loss": 1.5466,
      "step": 60
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.6383670568466187,
      "eval_runtime": 43.1224,
      "eval_samples_per_second": 4.638,
      "eval_steps_per_second": 0.58,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1e-06,
      "loss": 1.5196,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.5654,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.7e-06,
      "loss": 1.6131,
      "step": 90
    },
    {
      "epoch": 0.08,
      "eval_loss": 1.572911262512207,
      "eval_runtime": 43.1916,
      "eval_samples_per_second": 4.631,
      "eval_steps_per_second": 0.579,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 3e-06,
      "loss": 1.6717,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.9990862405286437e-06,
      "loss": 1.403,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.9963460753897363e-06,
      "loss": 1.3671,
      "step": 120
    },
    {
      "epoch": 0.11,
      "eval_loss": 1.4739114046096802,
      "eval_runtime": 43.2692,
      "eval_samples_per_second": 4.622,
      "eval_steps_per_second": 0.578,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.99178284305241e-06,
      "loss": 1.4241,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.9854021031123555e-06,
      "loss": 1.4904,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.9772116295183124e-06,
      "loss": 1.5349,
      "step": 150
    },
    {
      "epoch": 0.14,
      "eval_loss": 1.3558812141418457,
      "eval_runtime": 43.2358,
      "eval_samples_per_second": 4.626,
      "eval_steps_per_second": 0.578,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.9672214011007086e-06,
      "loss": 1.1703,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.9554435894139947e-06,
      "loss": 1.2204,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.9418925439074784e-06,
      "loss": 1.2134,
      "step": 180
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.2288929224014282,
      "eval_runtime": 43.282,
      "eval_samples_per_second": 4.621,
      "eval_steps_per_second": 0.578,
      "step": 180
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.9265847744427307e-06,
      "loss": 1.2081,
      "step": 190
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.9095389311788626e-06,
      "loss": 1.2196,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.8907757818501814e-06,
      "loss": 1.083,
      "step": 210
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.079976201057434,
      "eval_runtime": 43.2803,
      "eval_samples_per_second": 4.621,
      "eval_steps_per_second": 0.578,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.8703181864639013e-06,
      "loss": 1.0504,
      "step": 220
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.8481910694487506e-06,
      "loss": 0.993,
      "step": 230
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.8244213892883906e-06,
      "loss": 0.9624,
      "step": 240
    },
    {
      "epoch": 0.22,
      "eval_loss": 0.938306450843811,
      "eval_runtime": 43.3163,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 240
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.7990381056766585e-06,
      "loss": 0.8176,
      "step": 250
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.772072144234639e-06,
      "loss": 0.8797,
      "step": 260
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.7435563588325624e-06,
      "loss": 0.8584,
      "step": 270
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8031389713287354,
      "eval_runtime": 43.324,
      "eval_samples_per_second": 4.616,
      "eval_steps_per_second": 0.577,
      "step": 270
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.713525491562421e-06,
      "loss": 0.7539,
      "step": 280
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.6820161304100827e-06,
      "loss": 0.6914,
      "step": 290
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.652425285390285e-06,
      "loss": 0.5904,
      "step": 300
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.711719810962677,
      "eval_runtime": 43.2643,
      "eval_samples_per_second": 4.623,
      "eval_steps_per_second": 0.578,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.6182139995242933e-06,
      "loss": 0.8539,
      "step": 310
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.5826403421475435e-06,
      "loss": 0.8114,
      "step": 320
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.545747654281847e-06,
      "loss": 0.6674,
      "step": 330
    },
    {
      "epoch": 0.31,
      "eval_loss": 0.6477487683296204,
      "eval_runtime": 43.294,
      "eval_samples_per_second": 4.62,
      "eval_steps_per_second": 0.577,
      "step": 330
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.5075808839844854e-06,
      "loss": 0.6056,
      "step": 340
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.468186531585926e-06,
      "loss": 0.5021,
      "step": 350
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.427612593036331e-06,
      "loss": 0.7264,
      "step": 360
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.593954861164093,
      "eval_runtime": 43.3205,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 360
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.385908501429888e-06,
      "loss": 0.6218,
      "step": 370
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.343125066778196e-06,
      "loss": 0.5625,
      "step": 380
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.299314414106095e-06,
      "loss": 0.5172,
      "step": 390
    },
    {
      "epoch": 0.36,
      "eval_loss": 0.5455488562583923,
      "eval_runtime": 43.2928,
      "eval_samples_per_second": 4.62,
      "eval_steps_per_second": 0.577,
      "step": 390
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.2545299199453527e-06,
      "loss": 0.4426,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.2088261473035813e-06,
      "loss": 0.6936,
      "step": 410
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.162258779187618e-06,
      "loss": 0.572,
      "step": 420
    },
    {
      "epoch": 0.39,
      "eval_loss": 0.5148348212242126,
      "eval_runtime": 43.32,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 420
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.1148845507623592e-06,
      "loss": 0.5241,
      "step": 430
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.0667611802277007e-06,
      "loss": 0.4678,
      "step": 440
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.017947298497802e-06,
      "loss": 0.4499,
      "step": 450
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.4825447201728821,
      "eval_runtime": 43.2939,
      "eval_samples_per_second": 4.62,
      "eval_steps_per_second": 0.577,
      "step": 450
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.968502377768349e-06,
      "loss": 0.5878,
      "step": 460
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.918486659058844e-06,
      "loss": 0.4392,
      "step": 470
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.867961078818204e-06,
      "loss": 0.4849,
      "step": 480
    },
    {
      "epoch": 0.44,
      "eval_loss": 0.45478785037994385,
      "eval_runtime": 43.3084,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 0.577,
      "step": 480
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8169871946830832e-06,
      "loss": 0.4713,
      "step": 490
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.7656271104793753e-06,
      "loss": 0.3371,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.7139434005582677e-06,
      "loss": 0.6713,
      "step": 510
    },
    {
      "epoch": 0.47,
      "eval_loss": 0.43661826848983765,
      "eval_runtime": 43.3338,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 0.577,
      "step": 510
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.6619990335590342e-06,
      "loss": 0.4761,
      "step": 520
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.6098572956914476e-06,
      "loss": 0.3853,
      "step": 530
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.55758171363128e-06,
      "loss": 0.3786,
      "step": 540
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.4211544692516327,
      "eval_runtime": 43.3208,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 540
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5052359771228356e-06,
      "loss": 0.3292,
      "step": 550
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.4528838613828075e-06,
      "loss": 0.5014,
      "step": 560
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.4005891494000002e-06,
      "loss": 0.4742,
      "step": 570
    },
    {
      "epoch": 0.53,
      "eval_loss": 0.4091000258922577,
      "eval_runtime": 43.3335,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 0.577,
      "step": 570
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.3484155542255805e-06,
      "loss": 0.4352,
      "step": 580
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.2964266413485436e-06,
      "loss": 0.375,
      "step": 590
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.2446857512509515e-06,
      "loss": 0.2914,
      "step": 600
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.40144798159599304,
      "eval_runtime": 43.3188,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 600
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.1932559222373146e-06,
      "loss": 0.437,
      "step": 610
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.142199813632129e-06,
      "loss": 0.435,
      "step": 620
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.0915796294391385e-06,
      "loss": 0.4561,
      "step": 630
    },
    {
      "epoch": 0.58,
      "eval_loss": 0.39555278420448303,
      "eval_runtime": 43.303,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 0.577,
      "step": 630
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.0414570425553416e-06,
      "loss": 0.4328,
      "step": 640
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.918931196320629e-07,
      "loss": 0.3112,
      "step": 650
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.429482466746482e-07,
      "loss": 0.464,
      "step": 660
    },
    {
      "epoch": 0.61,
      "eval_loss": 0.3911471962928772,
      "eval_runtime": 43.2973,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 0.577,
      "step": 660
    },
    {
      "epoch": 0.62,
      "learning_rate": 8.946820554714148e-07,
      "loss": 0.3314,
      "step": 670
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.471533509415089e-07,
      "loss": 0.3463,
      "step": 680
    },
    {
      "epoch": 0.64,
      "learning_rate": 8.004200394901634e-07,
      "loss": 0.3222,
      "step": 690
    },
    {
      "epoch": 0.64,
      "eval_loss": 0.3882828652858734,
      "eval_runtime": 43.2999,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 0.577,
      "step": 690
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.54539058458667e-07,
      "loss": 0.2882,
      "step": 700
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.095663067549837e-07,
      "loss": 0.4216,
      "step": 710
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.655565767495428e-07,
      "loss": 0.4166,
      "step": 720
    },
    {
      "epoch": 0.67,
      "eval_loss": 0.38488155603408813,
      "eval_runtime": 43.3338,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 0.577,
      "step": 720
    },
    {
      "epoch": 0.68,
      "learning_rate": 6.225634875191768e-07,
      "loss": 0.4709,
      "step": 730
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.806394195205356e-07,
      "loss": 0.4041,
      "step": 740
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.398354507725665e-07,
      "loss": 0.2599,
      "step": 750
    },
    {
      "epoch": 0.69,
      "eval_loss": 0.3818848431110382,
      "eval_runtime": 43.2854,
      "eval_samples_per_second": 4.62,
      "eval_steps_per_second": 0.578,
      "step": 750
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.002012946258214e-07,
      "loss": 0.4712,
      "step": 760
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.6178523919439e-07,
      "loss": 0.4283,
      "step": 770
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.246340885242759e-07,
      "loss": 0.3783,
      "step": 780
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.37969982624053955,
      "eval_runtime": 43.3044,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 0.577,
      "step": 780
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.88793105569875e-07,
      "loss": 0.4053,
      "step": 790
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.5430595704803714e-07,
      "loss": 0.2247,
      "step": 800
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.2121466023689703e-07,
      "loss": 0.4951,
      "step": 810
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.3787403106689453,
      "eval_runtime": 43.3483,
      "eval_samples_per_second": 4.614,
      "eval_steps_per_second": 0.577,
      "step": 810
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8955953178429745e-07,
      "loss": 0.4129,
      "step": 820
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.593791385881571e-07,
      "loss": 0.4215,
      "step": 830
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3071025080865416e-07,
      "loss": 0.3674,
      "step": 840
    },
    {
      "epoch": 0.78,
      "eval_loss": 0.3782441020011902,
      "eval_runtime": 43.3332,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 0.577,
      "step": 840
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.0358779706944303e-07,
      "loss": 0.238,
      "step": 850
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.7804482190251177e-07,
      "loss": 0.5652,
      "step": 860
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.5411244548850746e-07,
      "loss": 0.408,
      "step": 870
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.3777380883693695,
      "eval_runtime": 43.3364,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 0.577,
      "step": 870
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.3181982574159058e-07,
      "loss": 0.3653,
      "step": 880
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.111941227850079e-07,
      "loss": 0.326,
      "step": 890
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.226046586066611e-08,
      "loss": 0.256,
      "step": 900
    },
    {
      "epoch": 0.83,
      "eval_loss": 0.3771674633026123,
      "eval_runtime": 43.2958,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 0.577,
      "step": 900
    },
    {
      "epoch": 0.84,
      "learning_rate": 7.504192271302146e-08,
      "loss": 0.5621,
      "step": 910
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.9559471484585404e-08,
      "loss": 0.3322,
      "step": 920
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.583197515729171e-08,
      "loss": 0.3913,
      "step": 930
    },
    {
      "epoch": 0.86,
      "eval_loss": 0.3770001530647278,
      "eval_runtime": 43.3108,
      "eval_samples_per_second": 4.618,
      "eval_steps_per_second": 0.577,
      "step": 930
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.387615857085618e-08,
      "loss": 0.396,
      "step": 940
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.370658804613718e-08,
      "loss": 0.2624,
      "step": 950
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5335653638316516e-08,
      "loss": 0.5314,
      "step": 960
    },
    {
      "epoch": 0.89,
      "eval_loss": 0.3768998980522156,
      "eval_runtime": 43.3212,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 0.577,
      "step": 960
    },
    {
      "epoch": 0.9,
      "learning_rate": 8.77355404152691e-09,
      "loss": 0.3471,
      "step": 970
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.028284163312857e-09,
      "loss": 0.4668,
      "step": 980
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1056253840682762e-09,
      "loss": 0.4386,
      "step": 990
    },
    {
      "epoch": 0.92,
      "eval_loss": 0.37686625123023987,
      "eval_runtime": 43.494,
      "eval_samples_per_second": 4.598,
      "eval_steps_per_second": 0.575,
      "step": 990
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 30,
  "total_flos": 4.354481553518592e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}