{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 47.05882352941177,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.20885063707828522,
      "learning_rate": 4.9980725906018074e-05,
      "loss": 0.8318,
      "num_input_tokens_seen": 121824,
      "step": 5
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.21794493496418,
      "learning_rate": 4.99229333433282e-05,
      "loss": 0.7891,
      "num_input_tokens_seen": 239760,
      "step": 10
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.20168891549110413,
      "learning_rate": 4.982671142387316e-05,
      "loss": 0.7678,
      "num_input_tokens_seen": 364912,
      "step": 15
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.20661190152168274,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.728,
      "num_input_tokens_seen": 487440,
      "step": 20
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.2073347568511963,
      "learning_rate": 4.951963201008076e-05,
      "loss": 0.7364,
      "num_input_tokens_seen": 607888,
      "step": 25
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.19631442427635193,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 0.7217,
      "num_input_tokens_seen": 728656,
      "step": 30
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.22293810546398163,
      "learning_rate": 4.906138091134118e-05,
      "loss": 0.6901,
      "num_input_tokens_seen": 849216,
      "step": 35
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.2156902402639389,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.6761,
      "num_input_tokens_seen": 971440,
      "step": 40
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.22460030019283295,
      "learning_rate": 4.8454783398062106e-05,
      "loss": 0.6601,
      "num_input_tokens_seen": 1091264,
      "step": 45
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.2591679096221924,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.6439,
      "num_input_tokens_seen": 1211184,
      "step": 50
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.26881489157676697,
      "learning_rate": 4.7703579345627035e-05,
      "loss": 0.6181,
      "num_input_tokens_seen": 1334112,
      "step": 55
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.3284054100513458,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.6145,
      "num_input_tokens_seen": 1454512,
      "step": 60
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 0.2977285385131836,
      "learning_rate": 4.681240017681993e-05,
      "loss": 0.5834,
      "num_input_tokens_seen": 1576640,
      "step": 65
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.3388771116733551,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.5632,
      "num_input_tokens_seen": 1698624,
      "step": 70
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.3815699815750122,
      "learning_rate": 4.5786740307563636e-05,
      "loss": 0.5549,
      "num_input_tokens_seen": 1818688,
      "step": 75
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.37038519978523254,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.5151,
      "num_input_tokens_seen": 1942112,
      "step": 80
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4679271876811981,
      "learning_rate": 4.463292327201862e-05,
      "loss": 0.5147,
      "num_input_tokens_seen": 2061552,
      "step": 85
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.4134647846221924,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.4635,
      "num_input_tokens_seen": 2185344,
      "step": 90
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 0.45239707827568054,
      "learning_rate": 4.335806273589214e-05,
      "loss": 0.4585,
      "num_input_tokens_seen": 2306256,
      "step": 95
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 0.5336123704910278,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.4291,
      "num_input_tokens_seen": 2426592,
      "step": 100
    },
    {
      "epoch": 12.352941176470589,
      "grad_norm": 0.5823401212692261,
      "learning_rate": 4.197001863832355e-05,
      "loss": 0.3997,
      "num_input_tokens_seen": 2548672,
      "step": 105
    },
    {
      "epoch": 12.941176470588236,
      "grad_norm": 0.5824088454246521,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.3797,
      "num_input_tokens_seen": 2667984,
      "step": 110
    },
    {
      "epoch": 13.529411764705882,
      "grad_norm": 0.7273723483085632,
      "learning_rate": 4.047734873274586e-05,
      "loss": 0.3412,
      "num_input_tokens_seen": 2791904,
      "step": 115
    },
    {
      "epoch": 14.117647058823529,
      "grad_norm": 0.6384756565093994,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.3298,
      "num_input_tokens_seen": 2910560,
      "step": 120
    },
    {
      "epoch": 14.705882352941176,
      "grad_norm": 0.684781014919281,
      "learning_rate": 3.888925582549006e-05,
      "loss": 0.2863,
      "num_input_tokens_seen": 3034368,
      "step": 125
    },
    {
      "epoch": 15.294117647058824,
      "grad_norm": 0.7853628396987915,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.2738,
      "num_input_tokens_seen": 3153984,
      "step": 130
    },
    {
      "epoch": 15.882352941176471,
      "grad_norm": 0.7987646460533142,
      "learning_rate": 3.721553103742388e-05,
      "loss": 0.2367,
      "num_input_tokens_seen": 3278336,
      "step": 135
    },
    {
      "epoch": 16.470588235294116,
      "grad_norm": 0.74590665102005,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.2189,
      "num_input_tokens_seen": 3398224,
      "step": 140
    },
    {
      "epoch": 17.058823529411764,
      "grad_norm": 0.8422712683677673,
      "learning_rate": 3.54664934384357e-05,
      "loss": 0.1971,
      "num_input_tokens_seen": 3519168,
      "step": 145
    },
    {
      "epoch": 17.647058823529413,
      "grad_norm": 0.8479442000389099,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.1705,
      "num_input_tokens_seen": 3641392,
      "step": 150
    },
    {
      "epoch": 18.235294117647058,
      "grad_norm": 0.8197467923164368,
      "learning_rate": 3.365292642693732e-05,
      "loss": 0.1454,
      "num_input_tokens_seen": 3764240,
      "step": 155
    },
    {
      "epoch": 18.823529411764707,
      "grad_norm": 1.0131207704544067,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.1387,
      "num_input_tokens_seen": 3882896,
      "step": 160
    },
    {
      "epoch": 19.41176470588235,
      "grad_norm": 0.858586311340332,
      "learning_rate": 3.178601124662686e-05,
      "loss": 0.1191,
      "num_input_tokens_seen": 4004560,
      "step": 165
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.9852003455162048,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.1101,
      "num_input_tokens_seen": 4127360,
      "step": 170
    },
    {
      "epoch": 20.58823529411765,
      "grad_norm": 0.885619580745697,
      "learning_rate": 2.9877258050403212e-05,
      "loss": 0.0885,
      "num_input_tokens_seen": 4248640,
      "step": 175
    },
    {
      "epoch": 21.176470588235293,
      "grad_norm": 0.6304395794868469,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.0865,
      "num_input_tokens_seen": 4369872,
      "step": 180
    },
    {
      "epoch": 21.764705882352942,
      "grad_norm": 0.7621514797210693,
      "learning_rate": 2.7938434936445945e-05,
      "loss": 0.0708,
      "num_input_tokens_seen": 4490688,
      "step": 185
    },
    {
      "epoch": 22.352941176470587,
      "grad_norm": 0.8263904452323914,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.0715,
      "num_input_tokens_seen": 4612144,
      "step": 190
    },
    {
      "epoch": 22.941176470588236,
      "grad_norm": 0.5912930965423584,
      "learning_rate": 2.598149539397672e-05,
      "loss": 0.0584,
      "num_input_tokens_seen": 4733632,
      "step": 195
    },
    {
      "epoch": 23.529411764705884,
      "grad_norm": 0.6392534971237183,
      "learning_rate": 2.5e-05,
      "loss": 0.0517,
      "num_input_tokens_seen": 4854048,
      "step": 200
    },
    {
      "epoch": 24.11764705882353,
      "grad_norm": 0.44309210777282715,
      "learning_rate": 2.4018504606023293e-05,
      "loss": 0.0518,
      "num_input_tokens_seen": 4976208,
      "step": 205
    },
    {
      "epoch": 24.705882352941178,
      "grad_norm": 0.5509380102157593,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.0416,
      "num_input_tokens_seen": 5096976,
      "step": 210
    },
    {
      "epoch": 25.294117647058822,
      "grad_norm": 0.47966495156288147,
      "learning_rate": 2.2061565063554064e-05,
      "loss": 0.0425,
      "num_input_tokens_seen": 5217056,
      "step": 215
    },
    {
      "epoch": 25.88235294117647,
      "grad_norm": 0.5966067910194397,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.0377,
      "num_input_tokens_seen": 5337440,
      "step": 220
    },
    {
      "epoch": 26.470588235294116,
      "grad_norm": 0.37054604291915894,
      "learning_rate": 2.0122741949596797e-05,
      "loss": 0.0396,
      "num_input_tokens_seen": 5457008,
      "step": 225
    },
    {
      "epoch": 27.058823529411764,
      "grad_norm": 0.40190204977989197,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.0322,
      "num_input_tokens_seen": 5582160,
      "step": 230
    },
    {
      "epoch": 27.647058823529413,
      "grad_norm": 0.34666651487350464,
      "learning_rate": 1.8213988753373146e-05,
      "loss": 0.0341,
      "num_input_tokens_seen": 5702928,
      "step": 235
    },
    {
      "epoch": 28.235294117647058,
      "grad_norm": 0.27824667096138,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.028,
      "num_input_tokens_seen": 5824768,
      "step": 240
    },
    {
      "epoch": 28.823529411764707,
      "grad_norm": 0.32425612211227417,
      "learning_rate": 1.6347073573062672e-05,
      "loss": 0.027,
      "num_input_tokens_seen": 5946656,
      "step": 245
    },
    {
      "epoch": 29.41176470588235,
      "grad_norm": 0.3999980092048645,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0258,
      "num_input_tokens_seen": 6070048,
      "step": 250
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.6484708189964294,
      "learning_rate": 1.4533506561564306e-05,
      "loss": 0.0247,
      "num_input_tokens_seen": 6191376,
      "step": 255
    },
    {
      "epoch": 30.58823529411765,
      "grad_norm": 0.28348207473754883,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0233,
      "num_input_tokens_seen": 6312544,
      "step": 260
    },
    {
      "epoch": 31.176470588235293,
      "grad_norm": 0.28730762004852295,
      "learning_rate": 1.2784468962576136e-05,
      "loss": 0.0229,
      "num_input_tokens_seen": 6435232,
      "step": 265
    },
    {
      "epoch": 31.764705882352942,
      "grad_norm": 0.23221123218536377,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.0243,
      "num_input_tokens_seen": 6558816,
      "step": 270
    },
    {
      "epoch": 32.35294117647059,
      "grad_norm": 0.21052616834640503,
      "learning_rate": 1.1110744174509952e-05,
      "loss": 0.0221,
      "num_input_tokens_seen": 6681456,
      "step": 275
    },
    {
      "epoch": 32.94117647058823,
      "grad_norm": 0.2625516355037689,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0189,
      "num_input_tokens_seen": 6800352,
      "step": 280
    },
    {
      "epoch": 33.529411764705884,
      "grad_norm": 0.267925500869751,
      "learning_rate": 9.522651267254149e-06,
      "loss": 0.0188,
      "num_input_tokens_seen": 6923584,
      "step": 285
    },
    {
      "epoch": 34.11764705882353,
      "grad_norm": 0.3179719150066376,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.0198,
      "num_input_tokens_seen": 7041648,
      "step": 290
    },
    {
      "epoch": 34.705882352941174,
      "grad_norm": 0.22515079379081726,
      "learning_rate": 8.029981361676456e-06,
      "loss": 0.0195,
      "num_input_tokens_seen": 7166416,
      "step": 295
    },
    {
      "epoch": 35.294117647058826,
      "grad_norm": 0.22048750519752502,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0222,
      "num_input_tokens_seen": 7283072,
      "step": 300
    },
    {
      "epoch": 35.88235294117647,
      "grad_norm": 0.3719558119773865,
      "learning_rate": 6.641937264107867e-06,
      "loss": 0.015,
      "num_input_tokens_seen": 7405936,
      "step": 305
    },
    {
      "epoch": 36.470588235294116,
      "grad_norm": 0.244638592004776,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.0162,
      "num_input_tokens_seen": 7526224,
      "step": 310
    },
    {
      "epoch": 37.05882352941177,
      "grad_norm": 0.20829229056835175,
      "learning_rate": 5.367076727981382e-06,
      "loss": 0.0191,
      "num_input_tokens_seen": 7648896,
      "step": 315
    },
    {
      "epoch": 37.64705882352941,
      "grad_norm": 0.18424373865127563,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.0173,
      "num_input_tokens_seen": 7768768,
      "step": 320
    },
    {
      "epoch": 38.23529411764706,
      "grad_norm": 0.17650990188121796,
      "learning_rate": 4.213259692436367e-06,
      "loss": 0.0185,
      "num_input_tokens_seen": 7892064,
      "step": 325
    },
    {
      "epoch": 38.8235294117647,
      "grad_norm": 0.2193550169467926,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.0164,
      "num_input_tokens_seen": 8011552,
      "step": 330
    },
    {
      "epoch": 39.411764705882355,
      "grad_norm": 0.18098759651184082,
      "learning_rate": 3.187599823180071e-06,
      "loss": 0.0167,
      "num_input_tokens_seen": 8137664,
      "step": 335
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.14081740379333496,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.0163,
      "num_input_tokens_seen": 8256400,
      "step": 340
    },
    {
      "epoch": 40.588235294117645,
      "grad_norm": 0.15283998847007751,
      "learning_rate": 2.296420654372966e-06,
      "loss": 0.0162,
      "num_input_tokens_seen": 8379376,
      "step": 345
    },
    {
      "epoch": 41.1764705882353,
      "grad_norm": 0.16390979290008545,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.0158,
      "num_input_tokens_seen": 8499712,
      "step": 350
    },
    {
      "epoch": 41.76470588235294,
      "grad_norm": 0.1703239530324936,
      "learning_rate": 1.5452166019378989e-06,
      "loss": 0.0169,
      "num_input_tokens_seen": 8620768,
      "step": 355
    },
    {
      "epoch": 42.35294117647059,
      "grad_norm": 0.1654016375541687,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.015,
      "num_input_tokens_seen": 8744400,
      "step": 360
    },
    {
      "epoch": 42.94117647058823,
      "grad_norm": 0.18267235159873962,
      "learning_rate": 9.386190886588208e-07,
      "loss": 0.0167,
      "num_input_tokens_seen": 8863312,
      "step": 365
    },
    {
      "epoch": 43.529411764705884,
      "grad_norm": 0.17041648924350739,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.0153,
      "num_input_tokens_seen": 8986880,
      "step": 370
    },
    {
      "epoch": 44.11764705882353,
      "grad_norm": 0.16261689364910126,
      "learning_rate": 4.803679899192392e-07,
      "loss": 0.0157,
      "num_input_tokens_seen": 9104640,
      "step": 375
    },
    {
      "epoch": 44.705882352941174,
      "grad_norm": 0.1600603610277176,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.0167,
      "num_input_tokens_seen": 9225360,
      "step": 380
    },
    {
      "epoch": 45.294117647058826,
      "grad_norm": 0.14950668811798096,
      "learning_rate": 1.732885761268427e-07,
      "loss": 0.0146,
      "num_input_tokens_seen": 9345008,
      "step": 385
    },
    {
      "epoch": 45.88235294117647,
      "grad_norm": 0.1505534052848816,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.0154,
      "num_input_tokens_seen": 9465872,
      "step": 390
    },
    {
      "epoch": 46.470588235294116,
      "grad_norm": 0.1543729603290558,
      "learning_rate": 1.9274093981927478e-08,
      "loss": 0.0173,
      "num_input_tokens_seen": 9589456,
      "step": 395
    },
    {
      "epoch": 47.05882352941177,
      "grad_norm": 0.2318650335073471,
      "learning_rate": 0.0,
      "loss": 0.0163,
      "num_input_tokens_seen": 9708528,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 9708528,
  "num_train_epochs": 50,
  "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": 1.1615729589682176e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}