{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 361,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013869625520110958,
      "grad_norm": 4.510591983795166,
      "learning_rate": 1.111111111111111e-06,
      "loss": 4.4401,
      "step": 5
    },
    {
      "epoch": 0.027739251040221916,
      "grad_norm": 3.330329418182373,
      "learning_rate": 2.5e-06,
      "loss": 4.3997,
      "step": 10
    },
    {
      "epoch": 0.04160887656033287,
      "grad_norm": 2.752856731414795,
      "learning_rate": 3.88888888888889e-06,
      "loss": 4.3407,
      "step": 15
    },
    {
      "epoch": 0.05547850208044383,
      "grad_norm": 1.670164704322815,
      "learning_rate": 5.2777777777777785e-06,
      "loss": 4.2228,
      "step": 20
    },
    {
      "epoch": 0.06934812760055478,
      "grad_norm": 1.4805010557174683,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.1725,
      "step": 25
    },
    {
      "epoch": 0.08321775312066575,
      "grad_norm": 1.4973056316375732,
      "learning_rate": 8.055555555555557e-06,
      "loss": 4.0898,
      "step": 30
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 1.232718586921692,
      "learning_rate": 9.444444444444445e-06,
      "loss": 4.0469,
      "step": 35
    },
    {
      "epoch": 0.11095700416088766,
      "grad_norm": 1.0980631113052368,
      "learning_rate": 1.0833333333333334e-05,
      "loss": 4.0108,
      "step": 40
    },
    {
      "epoch": 0.12482662968099861,
      "grad_norm": 1.0764951705932617,
      "learning_rate": 1.2222222222222224e-05,
      "loss": 3.9719,
      "step": 45
    },
    {
      "epoch": 0.13869625520110956,
      "grad_norm": 1.2205593585968018,
      "learning_rate": 1.3611111111111113e-05,
      "loss": 3.8779,
      "step": 50
    },
    {
      "epoch": 0.13869625520110956,
      "eval_loss": 3.850510597229004,
      "eval_runtime": 33.5856,
      "eval_samples_per_second": 59.549,
      "eval_steps_per_second": 14.887,
      "step": 50
    },
    {
      "epoch": 0.15256588072122051,
      "grad_norm": 0.9968748688697815,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 3.8635,
      "step": 55
    },
    {
      "epoch": 0.1664355062413315,
      "grad_norm": 0.8354158401489258,
      "learning_rate": 1.638888888888889e-05,
      "loss": 3.8142,
      "step": 60
    },
    {
      "epoch": 0.18030513176144244,
      "grad_norm": 1.072789192199707,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 3.764,
      "step": 65
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.8747042417526245,
      "learning_rate": 1.916666666666667e-05,
      "loss": 3.7425,
      "step": 70
    },
    {
      "epoch": 0.20804438280166435,
      "grad_norm": 0.8491944074630737,
      "learning_rate": 2e-05,
      "loss": 3.7508,
      "step": 75
    },
    {
      "epoch": 0.22191400832177532,
      "grad_norm": 1.2049877643585205,
      "learning_rate": 2e-05,
      "loss": 3.7437,
      "step": 80
    },
    {
      "epoch": 0.23578363384188628,
      "grad_norm": 0.8578179478645325,
      "learning_rate": 2e-05,
      "loss": 3.7026,
      "step": 85
    },
    {
      "epoch": 0.24965325936199723,
      "grad_norm": 0.926129937171936,
      "learning_rate": 2e-05,
      "loss": 3.6973,
      "step": 90
    },
    {
      "epoch": 0.2635228848821082,
      "grad_norm": 0.8127467632293701,
      "learning_rate": 2e-05,
      "loss": 3.6644,
      "step": 95
    },
    {
      "epoch": 0.27739251040221913,
      "grad_norm": 0.8188264966011047,
      "learning_rate": 2e-05,
      "loss": 3.7131,
      "step": 100
    },
    {
      "epoch": 0.27739251040221913,
      "eval_loss": 3.662523031234741,
      "eval_runtime": 21.6908,
      "eval_samples_per_second": 92.205,
      "eval_steps_per_second": 23.051,
      "step": 100
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.8815653920173645,
      "learning_rate": 2e-05,
      "loss": 3.698,
      "step": 105
    },
    {
      "epoch": 0.30513176144244103,
      "grad_norm": 0.8444380164146423,
      "learning_rate": 2e-05,
      "loss": 3.7047,
      "step": 110
    },
    {
      "epoch": 0.31900138696255204,
      "grad_norm": 0.8192554712295532,
      "learning_rate": 2e-05,
      "loss": 3.6493,
      "step": 115
    },
    {
      "epoch": 0.332871012482663,
      "grad_norm": 0.7751811146736145,
      "learning_rate": 2e-05,
      "loss": 3.6687,
      "step": 120
    },
    {
      "epoch": 0.34674063800277394,
      "grad_norm": 0.8989075422286987,
      "learning_rate": 2e-05,
      "loss": 3.6364,
      "step": 125
    },
    {
      "epoch": 0.3606102635228849,
      "grad_norm": 0.8365870118141174,
      "learning_rate": 2e-05,
      "loss": 3.638,
      "step": 130
    },
    {
      "epoch": 0.37447988904299584,
      "grad_norm": 0.8214474320411682,
      "learning_rate": 2e-05,
      "loss": 3.6234,
      "step": 135
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.8589164018630981,
      "learning_rate": 2e-05,
      "loss": 3.6011,
      "step": 140
    },
    {
      "epoch": 0.40221914008321774,
      "grad_norm": 0.7401110529899597,
      "learning_rate": 2e-05,
      "loss": 3.6116,
      "step": 145
    },
    {
      "epoch": 0.4160887656033287,
      "grad_norm": 0.9119060635566711,
      "learning_rate": 2e-05,
      "loss": 3.66,
      "step": 150
    },
    {
      "epoch": 0.4160887656033287,
      "eval_loss": 3.6079025268554688,
      "eval_runtime": 21.5551,
      "eval_samples_per_second": 92.786,
      "eval_steps_per_second": 23.196,
      "step": 150
    },
    {
      "epoch": 0.42995839112343964,
      "grad_norm": 0.7333055138587952,
      "learning_rate": 2e-05,
      "loss": 3.6081,
      "step": 155
    },
    {
      "epoch": 0.44382801664355065,
      "grad_norm": 0.9201464653015137,
      "learning_rate": 2e-05,
      "loss": 3.5902,
      "step": 160
    },
    {
      "epoch": 0.4576976421636616,
      "grad_norm": 0.8326563835144043,
      "learning_rate": 2e-05,
      "loss": 3.616,
      "step": 165
    },
    {
      "epoch": 0.47156726768377255,
      "grad_norm": 0.7910550236701965,
      "learning_rate": 2e-05,
      "loss": 3.5961,
      "step": 170
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 0.7993020415306091,
      "learning_rate": 2e-05,
      "loss": 3.6279,
      "step": 175
    },
    {
      "epoch": 0.49930651872399445,
      "grad_norm": 0.7476230263710022,
      "learning_rate": 2e-05,
      "loss": 3.6089,
      "step": 180
    },
    {
      "epoch": 0.5131761442441054,
      "grad_norm": 0.8083401322364807,
      "learning_rate": 2e-05,
      "loss": 3.5774,
      "step": 185
    },
    {
      "epoch": 0.5270457697642164,
      "grad_norm": 0.8746952414512634,
      "learning_rate": 2e-05,
      "loss": 3.5767,
      "step": 190
    },
    {
      "epoch": 0.5409153952843273,
      "grad_norm": 0.7660844326019287,
      "learning_rate": 2e-05,
      "loss": 3.5744,
      "step": 195
    },
    {
      "epoch": 0.5547850208044383,
      "grad_norm": 0.9199999570846558,
      "learning_rate": 2e-05,
      "loss": 3.5692,
      "step": 200
    },
    {
      "epoch": 0.5547850208044383,
      "eval_loss": 3.57633113861084,
      "eval_runtime": 21.5806,
      "eval_samples_per_second": 92.676,
      "eval_steps_per_second": 23.169,
      "step": 200
    },
    {
      "epoch": 0.5686546463245492,
      "grad_norm": 0.7814918756484985,
      "learning_rate": 2e-05,
      "loss": 3.5922,
      "step": 205
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.8722035884857178,
      "learning_rate": 2e-05,
      "loss": 3.566,
      "step": 210
    },
    {
      "epoch": 0.5963938973647711,
      "grad_norm": 0.7965853214263916,
      "learning_rate": 2e-05,
      "loss": 3.5569,
      "step": 215
    },
    {
      "epoch": 0.6102635228848821,
      "grad_norm": 0.7837920188903809,
      "learning_rate": 1.9586206896551725e-05,
      "loss": 3.5482,
      "step": 220
    },
    {
      "epoch": 0.624133148404993,
      "grad_norm": 0.8320760726928711,
      "learning_rate": 1.8896551724137934e-05,
      "loss": 3.574,
      "step": 225
    },
    {
      "epoch": 0.6380027739251041,
      "grad_norm": 0.8384792804718018,
      "learning_rate": 1.820689655172414e-05,
      "loss": 3.559,
      "step": 230
    },
    {
      "epoch": 0.651872399445215,
      "grad_norm": 0.8892226219177246,
      "learning_rate": 1.7517241379310347e-05,
      "loss": 3.592,
      "step": 235
    },
    {
      "epoch": 0.665742024965326,
      "grad_norm": 0.7530568838119507,
      "learning_rate": 1.6827586206896552e-05,
      "loss": 3.5113,
      "step": 240
    },
    {
      "epoch": 0.6796116504854369,
      "grad_norm": 0.7810556292533875,
      "learning_rate": 1.613793103448276e-05,
      "loss": 3.5498,
      "step": 245
    },
    {
      "epoch": 0.6934812760055479,
      "grad_norm": 0.8023419380187988,
      "learning_rate": 1.5448275862068965e-05,
      "loss": 3.5663,
      "step": 250
    },
    {
      "epoch": 0.6934812760055479,
      "eval_loss": 3.5521113872528076,
      "eval_runtime": 21.6583,
      "eval_samples_per_second": 92.343,
      "eval_steps_per_second": 23.086,
      "step": 250
    },
    {
      "epoch": 0.7073509015256588,
      "grad_norm": 0.816082775592804,
      "learning_rate": 1.4758620689655172e-05,
      "loss": 3.5967,
      "step": 255
    },
    {
      "epoch": 0.7212205270457698,
      "grad_norm": 0.7597996592521667,
      "learning_rate": 1.4068965517241382e-05,
      "loss": 3.5758,
      "step": 260
    },
    {
      "epoch": 0.7350901525658807,
      "grad_norm": 0.7658893465995789,
      "learning_rate": 1.3379310344827587e-05,
      "loss": 3.5614,
      "step": 265
    },
    {
      "epoch": 0.7489597780859917,
      "grad_norm": 0.8528255224227905,
      "learning_rate": 1.2689655172413794e-05,
      "loss": 3.5871,
      "step": 270
    },
    {
      "epoch": 0.7628294036061026,
      "grad_norm": 0.8154652714729309,
      "learning_rate": 1.2e-05,
      "loss": 3.5798,
      "step": 275
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.7679687142372131,
      "learning_rate": 1.1310344827586209e-05,
      "loss": 3.5735,
      "step": 280
    },
    {
      "epoch": 0.7905686546463245,
      "grad_norm": 0.8223329782485962,
      "learning_rate": 1.0620689655172414e-05,
      "loss": 3.5398,
      "step": 285
    },
    {
      "epoch": 0.8044382801664355,
      "grad_norm": 0.7668578624725342,
      "learning_rate": 9.931034482758622e-06,
      "loss": 3.5625,
      "step": 290
    },
    {
      "epoch": 0.8183079056865464,
      "grad_norm": 0.7521477937698364,
      "learning_rate": 9.241379310344829e-06,
      "loss": 3.5387,
      "step": 295
    },
    {
      "epoch": 0.8321775312066574,
      "grad_norm": 0.7685747742652893,
      "learning_rate": 8.551724137931035e-06,
      "loss": 3.5442,
      "step": 300
    },
    {
      "epoch": 0.8321775312066574,
      "eval_loss": 3.5378079414367676,
      "eval_runtime": 21.7896,
      "eval_samples_per_second": 91.787,
      "eval_steps_per_second": 22.947,
      "step": 300
    },
    {
      "epoch": 0.8460471567267683,
      "grad_norm": 0.7819119691848755,
      "learning_rate": 7.862068965517242e-06,
      "loss": 3.4996,
      "step": 305
    },
    {
      "epoch": 0.8599167822468793,
      "grad_norm": 0.7009981274604797,
      "learning_rate": 7.1724137931034495e-06,
      "loss": 3.5478,
      "step": 310
    },
    {
      "epoch": 0.8737864077669902,
      "grad_norm": 0.7951462268829346,
      "learning_rate": 6.482758620689655e-06,
      "loss": 3.5395,
      "step": 315
    },
    {
      "epoch": 0.8876560332871013,
      "grad_norm": 0.8697261810302734,
      "learning_rate": 5.793103448275863e-06,
      "loss": 3.5568,
      "step": 320
    },
    {
      "epoch": 0.9015256588072122,
      "grad_norm": 0.7426744103431702,
      "learning_rate": 5.103448275862069e-06,
      "loss": 3.5467,
      "step": 325
    },
    {
      "epoch": 0.9153952843273232,
      "grad_norm": 0.8066877126693726,
      "learning_rate": 4.413793103448276e-06,
      "loss": 3.533,
      "step": 330
    },
    {
      "epoch": 0.9292649098474342,
      "grad_norm": 0.8604612946510315,
      "learning_rate": 3.7241379310344837e-06,
      "loss": 3.5227,
      "step": 335
    },
    {
      "epoch": 0.9431345353675451,
      "grad_norm": 0.7136410474777222,
      "learning_rate": 3.0344827586206895e-06,
      "loss": 3.5113,
      "step": 340
    },
    {
      "epoch": 0.957004160887656,
      "grad_norm": 0.701519250869751,
      "learning_rate": 2.344827586206897e-06,
      "loss": 3.5372,
      "step": 345
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.8079059720039368,
      "learning_rate": 1.6551724137931047e-06,
      "loss": 3.5555,
      "step": 350
    },
    {
      "epoch": 0.970873786407767,
      "eval_loss": 3.5296669006347656,
      "eval_runtime": 21.758,
      "eval_samples_per_second": 91.92,
      "eval_steps_per_second": 22.98,
      "step": 350
    },
    {
      "epoch": 0.984743411927878,
      "grad_norm": 0.8491346836090088,
      "learning_rate": 9.655172413793101e-07,
      "loss": 3.5319,
      "step": 355
    },
    {
      "epoch": 0.9986130374479889,
      "grad_norm": 0.7234743237495422,
      "learning_rate": 2.758620689655178e-07,
      "loss": 3.5472,
      "step": 360
    }
  ],
  "logging_steps": 5,
  "max_steps": 361,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}