{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3315579227696404,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 1.4126338958740234,
      "learning_rate": 0.0002,
      "loss": 2.411,
      "step": 10
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.0683205127716064,
      "learning_rate": 0.0002,
      "loss": 1.7825,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.250962734222412,
      "learning_rate": 0.0002,
      "loss": 1.6118,
      "step": 30
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.128470778465271,
      "learning_rate": 0.0002,
      "loss": 1.4993,
      "step": 40
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.0976437330245972,
      "learning_rate": 0.0002,
      "loss": 1.538,
      "step": 50
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.0831102132797241,
      "learning_rate": 0.0002,
      "loss": 1.4524,
      "step": 60
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.1627174615859985,
      "learning_rate": 0.0002,
      "loss": 1.4061,
      "step": 70
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.1374784708023071,
      "learning_rate": 0.0002,
      "loss": 1.4085,
      "step": 80
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.2638696432113647,
      "learning_rate": 0.0002,
      "loss": 1.3816,
      "step": 90
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.0406217575073242,
      "learning_rate": 0.0002,
      "loss": 1.3639,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.1120456457138062,
      "learning_rate": 0.0002,
      "loss": 1.3145,
      "step": 110
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.0537450313568115,
      "learning_rate": 0.0002,
      "loss": 1.3204,
      "step": 120
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.0962114334106445,
      "learning_rate": 0.0002,
      "loss": 1.3467,
      "step": 130
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.0847195386886597,
      "learning_rate": 0.0002,
      "loss": 1.3216,
      "step": 140
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.1323330402374268,
      "learning_rate": 0.0002,
      "loss": 1.3546,
      "step": 150
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.1049960851669312,
      "learning_rate": 0.0002,
      "loss": 1.3617,
      "step": 160
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.0923413038253784,
      "learning_rate": 0.0002,
      "loss": 1.3248,
      "step": 170
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.128686547279358,
      "learning_rate": 0.0002,
      "loss": 1.3002,
      "step": 180
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0518907308578491,
      "learning_rate": 0.0002,
      "loss": 1.3624,
      "step": 190
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.060835599899292,
      "learning_rate": 0.0002,
      "loss": 1.368,
      "step": 200
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.1328442096710205,
      "learning_rate": 0.0002,
      "loss": 1.2611,
      "step": 210
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.0428252220153809,
      "learning_rate": 0.0002,
      "loss": 1.2889,
      "step": 220
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.0666313171386719,
      "learning_rate": 0.0002,
      "loss": 1.2383,
      "step": 230
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0708130598068237,
      "learning_rate": 0.0002,
      "loss": 1.2666,
      "step": 240
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.0374865531921387,
      "learning_rate": 0.0002,
      "loss": 1.231,
      "step": 250
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.02108895778656,
      "learning_rate": 0.0002,
      "loss": 1.2519,
      "step": 260
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.9618756175041199,
      "learning_rate": 0.0002,
      "loss": 1.2115,
      "step": 270
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.0125309228897095,
      "learning_rate": 0.0002,
      "loss": 1.1766,
      "step": 280
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.031528115272522,
      "learning_rate": 0.0002,
      "loss": 1.2598,
      "step": 290
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1020361185073853,
      "learning_rate": 0.0002,
      "loss": 1.1946,
      "step": 300
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.0392624139785767,
      "learning_rate": 0.0002,
      "loss": 1.226,
      "step": 310
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.0464197397232056,
      "learning_rate": 0.0002,
      "loss": 1.2406,
      "step": 320
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.035586953163147,
      "learning_rate": 0.0002,
      "loss": 1.1949,
      "step": 330
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.053875207901001,
      "learning_rate": 0.0002,
      "loss": 1.2137,
      "step": 340
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.013602375984192,
      "learning_rate": 0.0002,
      "loss": 1.2162,
      "step": 350
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0841283798217773,
      "learning_rate": 0.0002,
      "loss": 1.1973,
      "step": 360
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.9872801303863525,
      "learning_rate": 0.0002,
      "loss": 1.2096,
      "step": 370
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.9933327436447144,
      "learning_rate": 0.0002,
      "loss": 1.2049,
      "step": 380
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.0115890502929688,
      "learning_rate": 0.0002,
      "loss": 1.231,
      "step": 390
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.0036671161651611,
      "learning_rate": 0.0002,
      "loss": 1.225,
      "step": 400
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.027393102645874,
      "learning_rate": 0.0002,
      "loss": 1.1855,
      "step": 410
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.0328060388565063,
      "learning_rate": 0.0002,
      "loss": 1.1978,
      "step": 420
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.9716214537620544,
      "learning_rate": 0.0002,
      "loss": 1.2326,
      "step": 430
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.9971627593040466,
      "learning_rate": 0.0002,
      "loss": 1.2019,
      "step": 440
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.002035140991211,
      "learning_rate": 0.0002,
      "loss": 1.1845,
      "step": 450
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.0371512174606323,
      "learning_rate": 0.0002,
      "loss": 1.1668,
      "step": 460
    },
    {
      "epoch": 0.63,
      "grad_norm": 1.0316438674926758,
      "learning_rate": 0.0002,
      "loss": 1.1967,
      "step": 470
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.0340334177017212,
      "learning_rate": 0.0002,
      "loss": 1.1564,
      "step": 480
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.0055785179138184,
      "learning_rate": 0.0002,
      "loss": 1.1749,
      "step": 490
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.9474852085113525,
      "learning_rate": 0.0002,
      "loss": 1.1847,
      "step": 500
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.979642927646637,
      "learning_rate": 0.0002,
      "loss": 1.213,
      "step": 510
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.0399181842803955,
      "learning_rate": 0.0002,
      "loss": 1.1641,
      "step": 520
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.9442302584648132,
      "learning_rate": 0.0002,
      "loss": 1.2084,
      "step": 530
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.038650393486023,
      "learning_rate": 0.0002,
      "loss": 1.1934,
      "step": 540
    },
    {
      "epoch": 0.73,
      "grad_norm": 1.0110139846801758,
      "learning_rate": 0.0002,
      "loss": 1.1741,
      "step": 550
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.0062506198883057,
      "learning_rate": 0.0002,
      "loss": 1.2044,
      "step": 560
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.0056486129760742,
      "learning_rate": 0.0002,
      "loss": 1.1683,
      "step": 570
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.9406468272209167,
      "learning_rate": 0.0002,
      "loss": 1.2082,
      "step": 580
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.9766492247581482,
      "learning_rate": 0.0002,
      "loss": 1.1402,
      "step": 590
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.011161208152771,
      "learning_rate": 0.0002,
      "loss": 1.1836,
      "step": 600
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.9706726670265198,
      "learning_rate": 0.0002,
      "loss": 1.1364,
      "step": 610
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.060975193977356,
      "learning_rate": 0.0002,
      "loss": 1.1492,
      "step": 620
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.0223751068115234,
      "learning_rate": 0.0002,
      "loss": 1.1389,
      "step": 630
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.132886290550232,
      "learning_rate": 0.0002,
      "loss": 1.195,
      "step": 640
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.9614752531051636,
      "learning_rate": 0.0002,
      "loss": 1.1469,
      "step": 650
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.0038574934005737,
      "learning_rate": 0.0002,
      "loss": 1.1901,
      "step": 660
    },
    {
      "epoch": 0.89,
      "grad_norm": 1.0092958211898804,
      "learning_rate": 0.0002,
      "loss": 1.1215,
      "step": 670
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.0625172853469849,
      "learning_rate": 0.0002,
      "loss": 1.1552,
      "step": 680
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.9498062133789062,
      "learning_rate": 0.0002,
      "loss": 1.1454,
      "step": 690
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.9746269583702087,
      "learning_rate": 0.0002,
      "loss": 1.1322,
      "step": 700
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.9876968860626221,
      "learning_rate": 0.0002,
      "loss": 1.1473,
      "step": 710
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9368664622306824,
      "learning_rate": 0.0002,
      "loss": 1.1036,
      "step": 720
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.9563239216804504,
      "learning_rate": 0.0002,
      "loss": 1.124,
      "step": 730
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.9494954347610474,
      "learning_rate": 0.0002,
      "loss": 1.0844,
      "step": 740
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9336316585540771,
      "learning_rate": 0.0002,
      "loss": 1.0938,
      "step": 750
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.9765089154243469,
      "learning_rate": 0.0002,
      "loss": 1.0245,
      "step": 760
    },
    {
      "epoch": 1.03,
      "grad_norm": 1.0190706253051758,
      "learning_rate": 0.0002,
      "loss": 1.0672,
      "step": 770
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.0273311138153076,
      "learning_rate": 0.0002,
      "loss": 1.0371,
      "step": 780
    },
    {
      "epoch": 1.05,
      "grad_norm": 1.0353707075119019,
      "learning_rate": 0.0002,
      "loss": 1.0212,
      "step": 790
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.9515432119369507,
      "learning_rate": 0.0002,
      "loss": 1.0721,
      "step": 800
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.0564075708389282,
      "learning_rate": 0.0002,
      "loss": 1.0495,
      "step": 810
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.004117727279663,
      "learning_rate": 0.0002,
      "loss": 1.032,
      "step": 820
    },
    {
      "epoch": 1.11,
      "grad_norm": 1.0284982919692993,
      "learning_rate": 0.0002,
      "loss": 1.0621,
      "step": 830
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.9780373573303223,
      "learning_rate": 0.0002,
      "loss": 1.0241,
      "step": 840
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.9741361141204834,
      "learning_rate": 0.0002,
      "loss": 1.0932,
      "step": 850
    },
    {
      "epoch": 1.15,
      "grad_norm": 1.0497852563858032,
      "learning_rate": 0.0002,
      "loss": 1.0665,
      "step": 860
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.0611335039138794,
      "learning_rate": 0.0002,
      "loss": 1.0485,
      "step": 870
    },
    {
      "epoch": 1.17,
      "grad_norm": 1.0571497678756714,
      "learning_rate": 0.0002,
      "loss": 1.0452,
      "step": 880
    },
    {
      "epoch": 1.19,
      "grad_norm": 1.038238525390625,
      "learning_rate": 0.0002,
      "loss": 1.0088,
      "step": 890
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.0717825889587402,
      "learning_rate": 0.0002,
      "loss": 1.0708,
      "step": 900
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.1264833211898804,
      "learning_rate": 0.0002,
      "loss": 1.0645,
      "step": 910
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.0441728830337524,
      "learning_rate": 0.0002,
      "loss": 1.0637,
      "step": 920
    },
    {
      "epoch": 1.24,
      "grad_norm": 1.0234287977218628,
      "learning_rate": 0.0002,
      "loss": 1.0639,
      "step": 930
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.043578028678894,
      "learning_rate": 0.0002,
      "loss": 1.0185,
      "step": 940
    },
    {
      "epoch": 1.26,
      "grad_norm": 1.0319379568099976,
      "learning_rate": 0.0002,
      "loss": 1.035,
      "step": 950
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.0528068542480469,
      "learning_rate": 0.0002,
      "loss": 1.0313,
      "step": 960
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.9674711227416992,
      "learning_rate": 0.0002,
      "loss": 1.051,
      "step": 970
    },
    {
      "epoch": 1.3,
      "grad_norm": 1.0464591979980469,
      "learning_rate": 0.0002,
      "loss": 1.0588,
      "step": 980
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.0295021533966064,
      "learning_rate": 0.0002,
      "loss": 1.0356,
      "step": 990
    },
    {
      "epoch": 1.33,
      "grad_norm": 1.0435758829116821,
      "learning_rate": 0.0002,
      "loss": 1.0621,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "total_flos": 9.789555867648e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}