{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 2.691509962081909,
      "learning_rate": 0.00015998457923856519,
      "loss": 1.4456,
      "step": 1
    },
    {
      "epoch": 0.025,
      "grad_norm": 24.26286506652832,
      "learning_rate": 0.00015993832289925785,
      "loss": 4.3349,
      "step": 2
    },
    {
      "epoch": 0.0375,
      "grad_norm": 13.163036346435547,
      "learning_rate": 0.0001598612488147773,
      "loss": 2.6695,
      "step": 3
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.818785667419434,
      "learning_rate": 0.00015975338669865026,
      "loss": 2.3799,
      "step": 4
    },
    {
      "epoch": 0.0625,
      "grad_norm": 6.200242519378662,
      "learning_rate": 0.00015961477813377576,
      "loss": 2.0935,
      "step": 5
    },
    {
      "epoch": 0.075,
      "grad_norm": 2.0556814670562744,
      "learning_rate": 0.00015944547655639412,
      "loss": 1.8465,
      "step": 6
    },
    {
      "epoch": 0.0875,
      "grad_norm": 2.5195746421813965,
      "learning_rate": 0.00015924554723548617,
      "loss": 1.7321,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.300451278686523,
      "learning_rate": 0.00015901506724761103,
      "loss": 1.7284,
      "step": 8
    },
    {
      "epoch": 0.1125,
      "grad_norm": 1.5021892786026,
      "learning_rate": 0.00015875412544719134,
      "loss": 1.5971,
      "step": 9
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.5246820449829102,
      "learning_rate": 0.00015846282243225845,
      "loss": 1.562,
      "step": 10
    },
    {
      "epoch": 0.1375,
      "grad_norm": 2.0095787048339844,
      "learning_rate": 0.0001581412705056698,
      "loss": 1.578,
      "step": 11
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.9773982763290405,
      "learning_rate": 0.00015778959363181415,
      "loss": 1.4977,
      "step": 12
    },
    {
      "epoch": 0.1625,
      "grad_norm": 1.1493251323699951,
      "learning_rate": 0.0001574079273888208,
      "loss": 1.5075,
      "step": 13
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.8909309506416321,
      "learning_rate": 0.00015699641891629178,
      "loss": 1.4158,
      "step": 14
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.9415439963340759,
      "learning_rate": 0.00015655522685857672,
      "loss": 1.4219,
      "step": 15
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.1703603267669678,
      "learning_rate": 0.0001560845213036123,
      "loss": 1.4006,
      "step": 16
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.7575011849403381,
      "learning_rate": 0.00015558448371735025,
      "loss": 1.3675,
      "step": 17
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.6772542595863342,
      "learning_rate": 0.00015505530687379875,
      "loss": 1.3369,
      "step": 18
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.5587411522865295,
      "learning_rate": 0.00015449719478070428,
      "loss": 1.3632,
      "step": 19
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5920618772506714,
      "learning_rate": 0.00015391036260090294,
      "loss": 1.3511,
      "step": 20
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.4218953847885132,
      "learning_rate": 0.0001532950365693709,
      "loss": 1.3641,
      "step": 21
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.4676741361618042,
      "learning_rate": 0.00015265145390600652,
      "loss": 1.3441,
      "step": 22
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.38095250725746155,
      "learning_rate": 0.00015197986272417774,
      "loss": 1.3418,
      "step": 23
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.42308753728866577,
      "learning_rate": 0.00015128052193506944,
      "loss": 1.3646,
      "step": 24
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.4307089149951935,
      "learning_rate": 0.0001505537011478684,
      "loss": 1.2992,
      "step": 25
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.33103814721107483,
      "learning_rate": 0.0001497996805658238,
      "loss": 1.3435,
      "step": 26
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.3511773645877838,
      "learning_rate": 0.00014901875087822337,
      "loss": 1.3,
      "step": 27
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.2914850115776062,
      "learning_rate": 0.0001482112131483274,
      "loss": 1.3103,
      "step": 28
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.37050625681877136,
      "learning_rate": 0.00014737737869730292,
      "loss": 1.2731,
      "step": 29
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.3476356565952301,
      "learning_rate": 0.00014651756898420365,
      "loss": 1.3211,
      "step": 30
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.27799472212791443,
      "learning_rate": 0.0001456321154820411,
      "loss": 1.2657,
      "step": 31
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.318327397108078,
      "learning_rate": 0.00014472135954999581,
      "loss": 1.3068,
      "step": 32
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.30465707182884216,
      "learning_rate": 0.00014378565230181657,
      "loss": 1.2839,
      "step": 33
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.2618834376335144,
      "learning_rate": 0.0001428253544704596,
      "loss": 1.2868,
      "step": 34
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.2864656150341034,
      "learning_rate": 0.00014184083626901897,
      "loss": 1.2815,
      "step": 35
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.2776831388473511,
      "learning_rate": 0.0001408324772480025,
      "loss": 1.2895,
      "step": 36
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.31238630414009094,
      "learning_rate": 0.00013980066614900776,
      "loss": 1.2718,
      "step": 37
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.23365426063537598,
      "learning_rate": 0.00013874580075485485,
      "loss": 1.2596,
      "step": 38
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.23924365639686584,
      "learning_rate": 0.00013766828773623352,
      "loss": 1.2809,
      "step": 39
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.24298632144927979,
      "learning_rate": 0.00013656854249492382,
      "loss": 1.2248,
      "step": 40
    },
    {
      "epoch": 0.5125,
      "grad_norm": 0.25117772817611694,
      "learning_rate": 0.0001354469890036509,
      "loss": 1.2653,
      "step": 41
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.25377020239830017,
      "learning_rate": 0.00013430405964263536,
      "loss": 1.2687,
      "step": 42
    },
    {
      "epoch": 0.5375,
      "grad_norm": 0.24669994413852692,
      "learning_rate": 0.00013314019503290255,
      "loss": 1.269,
      "step": 43
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.22006134688854218,
      "learning_rate": 0.00013195584386641469,
      "loss": 1.2559,
      "step": 44
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.2517986595630646,
      "learning_rate": 0.00013075146273309164,
      "loss": 1.2477,
      "step": 45
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.21466796100139618,
      "learning_rate": 0.00012952751594478675,
      "loss": 1.2358,
      "step": 46
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.2188994437456131,
      "learning_rate": 0.0001282844753562857,
      "loss": 1.2444,
      "step": 47
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.4198501110076904,
      "learning_rate": 0.00012702282018339786,
      "loss": 1.2535,
      "step": 48
    },
    {
      "epoch": 0.6125,
      "grad_norm": 0.3393913209438324,
      "learning_rate": 0.00012574303681820898,
      "loss": 1.2361,
      "step": 49
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.32384437322616577,
      "learning_rate": 0.0001244456186415682,
      "loss": 1.2283,
      "step": 50
    },
    {
      "epoch": 0.6375,
      "grad_norm": 0.3469082713127136,
      "learning_rate": 0.00012313106583288004,
      "loss": 1.2401,
      "step": 51
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.42606261372566223,
      "learning_rate": 0.00012179988517727591,
      "loss": 1.2399,
      "step": 52
    },
    {
      "epoch": 0.6625,
      "grad_norm": 0.4077642261981964,
      "learning_rate": 0.00012045258987023879,
      "loss": 1.2441,
      "step": 53
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.3077225089073181,
      "learning_rate": 0.00011908969931975641,
      "loss": 1.253,
      "step": 54
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.9925752878189087,
      "learning_rate": 0.00011771173894607985,
      "loss": 1.2586,
      "step": 55
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.9072725772857666,
      "learning_rate": 0.00011631923997916375,
      "loss": 1.2643,
      "step": 56
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.5788567662239075,
      "learning_rate": 0.00011491273925386736,
      "loss": 1.2657,
      "step": 57
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.9417564868927002,
      "learning_rate": 0.00011349277900299426,
      "loss": 1.2526,
      "step": 58
    },
    {
      "epoch": 0.7375,
      "grad_norm": 0.9247767329216003,
      "learning_rate": 0.00011205990664825127,
      "loss": 1.2402,
      "step": 59
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.5092797875404358,
      "learning_rate": 0.00011061467458920719,
      "loss": 1.2264,
      "step": 60
    },
    {
      "epoch": 0.7625,
      "grad_norm": 0.8128093481063843,
      "learning_rate": 0.00010915763999033201,
      "loss": 1.22,
      "step": 61
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.4954143166542053,
      "learning_rate": 0.00010768936456619945,
      "loss": 1.203,
      "step": 62
    },
    {
      "epoch": 0.7875,
      "grad_norm": 0.7117099761962891,
      "learning_rate": 0.0001062104143649355,
      "loss": 1.2295,
      "step": 63
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5060359835624695,
      "learning_rate": 0.0001047213595499958,
      "loss": 1.1936,
      "step": 64
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.5212268829345703,
      "learning_rate": 0.000103222774180357,
      "loss": 1.1927,
      "step": 65
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.47975900769233704,
      "learning_rate": 0.00010171523598920594,
      "loss": 1.2116,
      "step": 66
    },
    {
      "epoch": 0.8375,
      "grad_norm": 0.3655720055103302,
      "learning_rate": 0.00010019932616121264,
      "loss": 1.2002,
      "step": 67
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.38993576169013977,
      "learning_rate": 9.867562910847246e-05,
      "loss": 1.2225,
      "step": 68
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.33190780878067017,
      "learning_rate": 9.714473224520406e-05,
      "loss": 1.1982,
      "step": 69
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.3178853988647461,
      "learning_rate": 9.560722576129029e-05,
      "loss": 1.2015,
      "step": 70
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.28483396768569946,
      "learning_rate": 9.406370239474839e-05,
      "loss": 1.2013,
      "step": 71
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.26456528902053833,
      "learning_rate": 9.251475720321848e-05,
      "loss": 1.2101,
      "step": 72
    },
    {
      "epoch": 0.9125,
      "grad_norm": 0.24198457598686218,
      "learning_rate": 9.096098733455746e-05,
      "loss": 1.1889,
      "step": 73
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.2521977424621582,
      "learning_rate": 8.940299179662703e-05,
      "loss": 1.1915,
      "step": 74
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.22842273116111755,
      "learning_rate": 8.784137122636488e-05,
      "loss": 1.2018,
      "step": 75
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.21817852556705475,
      "learning_rate": 8.627672765822762e-05,
      "loss": 1.188,
      "step": 76
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.1990320086479187,
      "learning_rate": 8.470966429209512e-05,
      "loss": 1.1821,
      "step": 77
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.20685255527496338,
      "learning_rate": 8.31407852607255e-05,
      "loss": 1.1687,
      "step": 78
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.20527754724025726,
      "learning_rate": 8.157069539685026e-05,
      "loss": 1.2024,
      "step": 79
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20712077617645264,
      "learning_rate": 8e-05,
      "loss": 1.1721,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6380640896784794e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}