{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08587376556462001,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021468441391155,
      "grad_norm": 1.7282733917236328,
      "learning_rate": 0.0004989265779304422,
      "loss": 1.4129,
      "step": 10
    },
    {
      "epoch": 0.004293688278231,
      "grad_norm": 2.1508498191833496,
      "learning_rate": 0.0004978531558608846,
      "loss": 1.2225,
      "step": 20
    },
    {
      "epoch": 0.006440532417346501,
      "grad_norm": 1.6386512517929077,
      "learning_rate": 0.0004967797337913268,
      "loss": 1.1663,
      "step": 30
    },
    {
      "epoch": 0.008587376556462,
      "grad_norm": 1.2367421388626099,
      "learning_rate": 0.000495706311721769,
      "loss": 1.1373,
      "step": 40
    },
    {
      "epoch": 0.010734220695577501,
      "grad_norm": 1.2300989627838135,
      "learning_rate": 0.0004946328896522112,
      "loss": 1.1143,
      "step": 50
    },
    {
      "epoch": 0.012881064834693002,
      "grad_norm": 1.1807990074157715,
      "learning_rate": 0.0004935594675826536,
      "loss": 1.0937,
      "step": 60
    },
    {
      "epoch": 0.015027908973808502,
      "grad_norm": 0.9375188946723938,
      "learning_rate": 0.0004924860455130958,
      "loss": 1.0732,
      "step": 70
    },
    {
      "epoch": 0.017174753112924,
      "grad_norm": 0.9801538586616516,
      "learning_rate": 0.000491412623443538,
      "loss": 1.0369,
      "step": 80
    },
    {
      "epoch": 0.019321597252039503,
      "grad_norm": 0.9229792356491089,
      "learning_rate": 0.0004903392013739802,
      "loss": 1.0093,
      "step": 90
    },
    {
      "epoch": 0.021468441391155002,
      "grad_norm": 1.011305570602417,
      "learning_rate": 0.0004892657793044225,
      "loss": 1.0161,
      "step": 100
    },
    {
      "epoch": 0.0236152855302705,
      "grad_norm": 0.9356452822685242,
      "learning_rate": 0.00048819235723486477,
      "loss": 0.9939,
      "step": 110
    },
    {
      "epoch": 0.025762129669386003,
      "grad_norm": 1.0092449188232422,
      "learning_rate": 0.00048711893516530704,
      "loss": 0.9647,
      "step": 120
    },
    {
      "epoch": 0.027908973808501502,
      "grad_norm": 0.9663442373275757,
      "learning_rate": 0.0004860455130957492,
      "loss": 0.9595,
      "step": 130
    },
    {
      "epoch": 0.030055817947617004,
      "grad_norm": 1.1502243280410767,
      "learning_rate": 0.0004849720910261915,
      "loss": 0.9422,
      "step": 140
    },
    {
      "epoch": 0.0322026620867325,
      "grad_norm": 0.970102846622467,
      "learning_rate": 0.00048389866895663376,
      "loss": 0.945,
      "step": 150
    },
    {
      "epoch": 0.034349506225848,
      "grad_norm": 1.2466392517089844,
      "learning_rate": 0.00048282524688707604,
      "loss": 0.9385,
      "step": 160
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 1.0010186433792114,
      "learning_rate": 0.00048175182481751826,
      "loss": 0.9301,
      "step": 170
    },
    {
      "epoch": 0.038643194504079006,
      "grad_norm": 1.2516905069351196,
      "learning_rate": 0.0004806784027479605,
      "loss": 0.919,
      "step": 180
    },
    {
      "epoch": 0.040790038643194505,
      "grad_norm": 0.8497525453567505,
      "learning_rate": 0.00047960498067840275,
      "loss": 0.9054,
      "step": 190
    },
    {
      "epoch": 0.042936882782310004,
      "grad_norm": 1.0371205806732178,
      "learning_rate": 0.00047853155860884503,
      "loss": 0.9109,
      "step": 200
    },
    {
      "epoch": 0.0450837269214255,
      "grad_norm": 1.3313541412353516,
      "learning_rate": 0.00047745813653928725,
      "loss": 0.9131,
      "step": 210
    },
    {
      "epoch": 0.047230571060541,
      "grad_norm": 0.9448315501213074,
      "learning_rate": 0.0004763847144697295,
      "loss": 0.9014,
      "step": 220
    },
    {
      "epoch": 0.04937741519965651,
      "grad_norm": 1.274882435798645,
      "learning_rate": 0.00047531129240017175,
      "loss": 0.8786,
      "step": 230
    },
    {
      "epoch": 0.051524259338772006,
      "grad_norm": 1.3116368055343628,
      "learning_rate": 0.000474237870330614,
      "loss": 0.9075,
      "step": 240
    },
    {
      "epoch": 0.053671103477887505,
      "grad_norm": 0.9970440864562988,
      "learning_rate": 0.00047316444826105624,
      "loss": 0.8932,
      "step": 250
    },
    {
      "epoch": 0.055817947617003004,
      "grad_norm": 1.698472499847412,
      "learning_rate": 0.0004720910261914985,
      "loss": 0.8838,
      "step": 260
    },
    {
      "epoch": 0.0579647917561185,
      "grad_norm": 1.0129982233047485,
      "learning_rate": 0.0004710176041219408,
      "loss": 0.8779,
      "step": 270
    },
    {
      "epoch": 0.06011163589523401,
      "grad_norm": 1.0594947338104248,
      "learning_rate": 0.00046994418205238296,
      "loss": 0.8631,
      "step": 280
    },
    {
      "epoch": 0.06225848003434951,
      "grad_norm": 0.7768178582191467,
      "learning_rate": 0.00046887075998282524,
      "loss": 0.8666,
      "step": 290
    },
    {
      "epoch": 0.064405324173465,
      "grad_norm": 0.9108049869537354,
      "learning_rate": 0.0004677973379132675,
      "loss": 0.8676,
      "step": 300
    },
    {
      "epoch": 0.06655216831258051,
      "grad_norm": 1.4127992391586304,
      "learning_rate": 0.0004667239158437098,
      "loss": 0.8951,
      "step": 310
    },
    {
      "epoch": 0.068699012451696,
      "grad_norm": 1.1507939100265503,
      "learning_rate": 0.000465650493774152,
      "loss": 0.863,
      "step": 320
    },
    {
      "epoch": 0.07084585659081151,
      "grad_norm": 1.1579265594482422,
      "learning_rate": 0.00046457707170459423,
      "loss": 0.8716,
      "step": 330
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.9873006343841553,
      "learning_rate": 0.0004635036496350365,
      "loss": 0.8569,
      "step": 340
    },
    {
      "epoch": 0.07513954486904251,
      "grad_norm": 1.1990203857421875,
      "learning_rate": 0.0004624302275654788,
      "loss": 0.8776,
      "step": 350
    },
    {
      "epoch": 0.07728638900815801,
      "grad_norm": 1.1173065900802612,
      "learning_rate": 0.000461356805495921,
      "loss": 0.865,
      "step": 360
    },
    {
      "epoch": 0.0794332331472735,
      "grad_norm": 1.2493510246276855,
      "learning_rate": 0.0004602833834263633,
      "loss": 0.8609,
      "step": 370
    },
    {
      "epoch": 0.08158007728638901,
      "grad_norm": 1.1254737377166748,
      "learning_rate": 0.0004592099613568055,
      "loss": 0.8697,
      "step": 380
    },
    {
      "epoch": 0.0837269214255045,
      "grad_norm": 1.1009331941604614,
      "learning_rate": 0.0004581365392872477,
      "loss": 0.8653,
      "step": 390
    },
    {
      "epoch": 0.08587376556462001,
      "grad_norm": 1.3970990180969238,
      "learning_rate": 0.00045706311721769,
      "loss": 0.8542,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 4658,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 2.976872891771059e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}