{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00390625,
      "grad_norm": 1.2192516326904297,
      "learning_rate": 1.1538461538461538e-05,
      "loss": 1.9628,
      "step": 1
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 1.938663125038147,
      "learning_rate": 5.769230769230769e-05,
      "loss": 1.9381,
      "step": 5
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 0.9491540193557739,
      "learning_rate": 0.00011538461538461538,
      "loss": 1.8744,
      "step": 10
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 1.3879050016403198,
      "learning_rate": 0.00017307692307692304,
      "loss": 1.6648,
      "step": 15
    },
    {
      "epoch": 0.078125,
      "grad_norm": 1.1502411365509033,
      "learning_rate": 0.00023076923076923076,
      "loss": 1.2614,
      "step": 20
    },
    {
      "epoch": 0.09765625,
      "grad_norm": 0.38527828454971313,
      "learning_rate": 0.00028846153846153843,
      "loss": 1.1411,
      "step": 25
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 0.4007408022880554,
      "learning_rate": 0.00029977617052242417,
      "loss": 1.0619,
      "step": 30
    },
    {
      "epoch": 0.13671875,
      "grad_norm": 0.3242458403110504,
      "learning_rate": 0.0002988680080036802,
      "loss": 1.0099,
      "step": 35
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.3080570697784424,
      "learning_rate": 0.00029726575411133377,
      "loss": 0.9607,
      "step": 40
    },
    {
      "epoch": 0.17578125,
      "grad_norm": 0.2255689948797226,
      "learning_rate": 0.0002949768792926617,
      "loss": 0.9286,
      "step": 45
    },
    {
      "epoch": 0.1953125,
      "grad_norm": 0.18936823308467865,
      "learning_rate": 0.00029201205533865653,
      "loss": 0.9191,
      "step": 50
    },
    {
      "epoch": 0.21484375,
      "grad_norm": 0.182436004281044,
      "learning_rate": 0.00028838510562721075,
      "loss": 0.9273,
      "step": 55
    },
    {
      "epoch": 0.234375,
      "grad_norm": 0.2115677148103714,
      "learning_rate": 0.00028411294067214764,
      "loss": 0.9015,
      "step": 60
    },
    {
      "epoch": 0.25390625,
      "grad_norm": 0.15843912959098816,
      "learning_rate": 0.00027921547927859996,
      "loss": 0.8852,
      "step": 65
    },
    {
      "epoch": 0.2734375,
      "grad_norm": 0.1501840054988861,
      "learning_rate": 0.0002737155556723452,
      "loss": 0.8745,
      "step": 70
    },
    {
      "epoch": 0.29296875,
      "grad_norm": 0.1954830437898636,
      "learning_rate": 0.0002676388130361047,
      "loss": 0.8919,
      "step": 75
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.15817204117774963,
      "learning_rate": 0.00026101358394918777,
      "loss": 0.8734,
      "step": 80
    },
    {
      "epoch": 0.33203125,
      "grad_norm": 0.14839860796928406,
      "learning_rate": 0.0002538707582879288,
      "loss": 0.8636,
      "step": 85
    },
    {
      "epoch": 0.3515625,
      "grad_norm": 0.1690932661294937,
      "learning_rate": 0.00024624363920282413,
      "loss": 0.8827,
      "step": 90
    },
    {
      "epoch": 0.37109375,
      "grad_norm": 0.1796758621931076,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.8527,
      "step": 95
    },
    {
      "epoch": 0.390625,
      "grad_norm": 0.1769869029521942,
      "learning_rate": 0.0002296808575580705,
      "loss": 0.8605,
      "step": 100
    },
    {
      "epoch": 0.41015625,
      "grad_norm": 0.1564176380634308,
      "learning_rate": 0.0002208224183321428,
      "loss": 0.8553,
      "step": 105
    },
    {
      "epoch": 0.4296875,
      "grad_norm": 0.17047332227230072,
      "learning_rate": 0.00021163377229898225,
      "loss": 0.845,
      "step": 110
    },
    {
      "epoch": 0.44921875,
      "grad_norm": 0.17671431601047516,
      "learning_rate": 0.00020215776116804833,
      "loss": 0.8482,
      "step": 115
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.16975820064544678,
      "learning_rate": 0.00019243856647753948,
      "loss": 0.852,
      "step": 120
    },
    {
      "epoch": 0.48828125,
      "grad_norm": 0.16823889315128326,
      "learning_rate": 0.00018252150359966712,
      "loss": 0.85,
      "step": 125
    },
    {
      "epoch": 0.5078125,
      "grad_norm": 0.171301007270813,
      "learning_rate": 0.00017245281045947164,
      "loss": 0.8467,
      "step": 130
    },
    {
      "epoch": 0.52734375,
      "grad_norm": 0.17747431993484497,
      "learning_rate": 0.00016227943195227197,
      "loss": 0.8487,
      "step": 135
    },
    {
      "epoch": 0.546875,
      "grad_norm": 0.17524904012680054,
      "learning_rate": 0.00015204880106489262,
      "loss": 0.8462,
      "step": 140
    },
    {
      "epoch": 0.56640625,
      "grad_norm": 0.19776172935962677,
      "learning_rate": 0.0001418086177211835,
      "loss": 0.8403,
      "step": 145
    },
    {
      "epoch": 0.5859375,
      "grad_norm": 0.21995167434215546,
      "learning_rate": 0.00013160662638295526,
      "loss": 0.8287,
      "step": 150
    },
    {
      "epoch": 0.60546875,
      "grad_norm": 0.18319962918758392,
      "learning_rate": 0.00012149039344325893,
      "loss": 0.8337,
      "step": 155
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.22341905534267426,
      "learning_rate": 0.00011150708544990398,
      "loss": 0.8403,
      "step": 160
    },
    {
      "epoch": 0.64453125,
      "grad_norm": 0.1881171315908432,
      "learning_rate": 0.00010170324919323928,
      "loss": 0.8369,
      "step": 165
    },
    {
      "epoch": 0.6640625,
      "grad_norm": 0.1862991750240326,
      "learning_rate": 9.212459468352966e-05,
      "loss": 0.8246,
      "step": 170
    },
    {
      "epoch": 0.68359375,
      "grad_norm": 0.18749593198299408,
      "learning_rate": 8.281578202978773e-05,
      "loss": 0.8247,
      "step": 175
    },
    {
      "epoch": 0.703125,
      "grad_norm": 0.17886489629745483,
      "learning_rate": 7.382021321372908e-05,
      "loss": 0.8304,
      "step": 180
    },
    {
      "epoch": 0.72265625,
      "grad_norm": 0.18453623354434967,
      "learning_rate": 6.517982972969911e-05,
      "loss": 0.8342,
      "step": 185
    },
    {
      "epoch": 0.7421875,
      "grad_norm": 0.24199417233467102,
      "learning_rate": 5.693491703406478e-05,
      "loss": 0.8229,
      "step": 190
    },
    {
      "epoch": 0.76171875,
      "grad_norm": 0.18054385483264923,
      "learning_rate": 4.912391671582092e-05,
      "loss": 0.8397,
      "step": 195
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.1749253273010254,
      "learning_rate": 4.178324726415664e-05,
      "loss": 0.8263,
      "step": 200
    },
    {
      "epoch": 0.80078125,
      "grad_norm": 0.1956775188446045,
      "learning_rate": 3.494713426864761e-05,
      "loss": 0.8267,
      "step": 205
    },
    {
      "epoch": 0.8203125,
      "grad_norm": 0.18122443556785583,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.8382,
      "step": 210
    },
    {
      "epoch": 0.83984375,
      "grad_norm": 0.20789818465709686,
      "learning_rate": 2.291356902166746e-05,
      "loss": 0.8195,
      "step": 215
    },
    {
      "epoch": 0.859375,
      "grad_norm": 0.1800765097141266,
      "learning_rate": 1.7772222806299264e-05,
      "loss": 0.8234,
      "step": 220
    },
    {
      "epoch": 0.87890625,
      "grad_norm": 0.18312864005565643,
      "learning_rate": 1.3247383527051985e-05,
      "loss": 0.8279,
      "step": 225
    },
    {
      "epoch": 0.8984375,
      "grad_norm": 0.17430664598941803,
      "learning_rate": 9.360148073396962e-06,
      "loss": 0.8229,
      "step": 230
    },
    {
      "epoch": 0.91796875,
      "grad_norm": 0.19079521298408508,
      "learning_rate": 6.128640531440515e-06,
      "loss": 0.839,
      "step": 235
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.18069963157176971,
      "learning_rate": 3.5679276810683167e-06,
      "loss": 0.8181,
      "step": 240
    },
    {
      "epoch": 0.95703125,
      "grad_norm": 0.18298819661140442,
      "learning_rate": 1.6899487476622898e-06,
      "loss": 0.8298,
      "step": 245
    },
    {
      "epoch": 0.9765625,
      "grad_norm": 0.16638913750648499,
      "learning_rate": 5.034597359205639e-07,
      "loss": 0.8299,
      "step": 250
    },
    {
      "epoch": 0.99609375,
      "grad_norm": 0.1831548511981964,
      "learning_rate": 1.3992605321688776e-08,
      "loss": 0.8262,
      "step": 255
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9340308904647827,
      "eval_runtime": 1.1048,
      "eval_samples_per_second": 5.431,
      "eval_steps_per_second": 0.905,
      "step": 256
    },
    {
      "epoch": 1.0,
      "step": 256,
      "total_flos": 7.558142991332803e+17,
      "train_loss": 0.9300689545925707,
      "train_runtime": 2745.9778,
      "train_samples_per_second": 5.956,
      "train_steps_per_second": 0.093
    }
  ],
  "logging_steps": 5,
  "max_steps": 256,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.558142991332803e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}