{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.055645722235103175,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009274287039183863,
      "grad_norm": 1.411400556564331,
      "learning_rate": 0.0,
      "loss": 4.3229,
      "step": 1
    },
    {
      "epoch": 0.0018548574078367725,
      "grad_norm": 2.266972064971924,
      "learning_rate": 5e-06,
      "loss": 4.4344,
      "step": 2
    },
    {
      "epoch": 0.0027822861117551586,
      "grad_norm": 0.6068131923675537,
      "learning_rate": 1e-05,
      "loss": 3.2018,
      "step": 3
    },
    {
      "epoch": 0.003709714815673545,
      "grad_norm": 0.9275912642478943,
      "learning_rate": 1.5e-05,
      "loss": 4.0208,
      "step": 4
    },
    {
      "epoch": 0.004637143519591932,
      "grad_norm": 0.9753095507621765,
      "learning_rate": 2e-05,
      "loss": 3.7113,
      "step": 5
    },
    {
      "epoch": 0.005564572223510317,
      "grad_norm": 2.6469643115997314,
      "learning_rate": 2.5e-05,
      "loss": 5.2115,
      "step": 6
    },
    {
      "epoch": 0.006492000927428704,
      "grad_norm": 1.4554330110549927,
      "learning_rate": 3e-05,
      "loss": 4.2436,
      "step": 7
    },
    {
      "epoch": 0.00741942963134709,
      "grad_norm": 0.5066649913787842,
      "learning_rate": 3.5e-05,
      "loss": 3.5398,
      "step": 8
    },
    {
      "epoch": 0.008346858335265477,
      "grad_norm": 2.082305908203125,
      "learning_rate": 4e-05,
      "loss": 4.8127,
      "step": 9
    },
    {
      "epoch": 0.009274287039183864,
      "grad_norm": 0.4055868983268738,
      "learning_rate": 4.5e-05,
      "loss": 3.3663,
      "step": 10
    },
    {
      "epoch": 0.010201715743102248,
      "grad_norm": 0.363479882478714,
      "learning_rate": 5e-05,
      "loss": 3.2632,
      "step": 11
    },
    {
      "epoch": 0.011129144447020635,
      "grad_norm": 1.7619837522506714,
      "learning_rate": 4.9e-05,
      "loss": 4.7703,
      "step": 12
    },
    {
      "epoch": 0.012056573150939021,
      "grad_norm": 0.48136666417121887,
      "learning_rate": 4.8e-05,
      "loss": 3.1614,
      "step": 13
    },
    {
      "epoch": 0.012984001854857407,
      "grad_norm": 0.48472875356674194,
      "learning_rate": 4.7e-05,
      "loss": 3.3447,
      "step": 14
    },
    {
      "epoch": 0.013911430558775794,
      "grad_norm": 0.5840467214584351,
      "learning_rate": 4.600000000000001e-05,
      "loss": 3.3037,
      "step": 15
    },
    {
      "epoch": 0.01483885926269418,
      "grad_norm": 1.9077085256576538,
      "learning_rate": 4.5e-05,
      "loss": 4.614,
      "step": 16
    },
    {
      "epoch": 0.015766287966612568,
      "grad_norm": 0.5734739899635315,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 3.1754,
      "step": 17
    },
    {
      "epoch": 0.016693716670530954,
      "grad_norm": 1.8598120212554932,
      "learning_rate": 4.3e-05,
      "loss": 4.3064,
      "step": 18
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 0.5264394283294678,
      "learning_rate": 4.2e-05,
      "loss": 3.2004,
      "step": 19
    },
    {
      "epoch": 0.018548574078367727,
      "grad_norm": 0.6078647375106812,
      "learning_rate": 4.1e-05,
      "loss": 3.3305,
      "step": 20
    },
    {
      "epoch": 0.01947600278228611,
      "grad_norm": 0.49842751026153564,
      "learning_rate": 4e-05,
      "loss": 3.4103,
      "step": 21
    },
    {
      "epoch": 0.020403431486204496,
      "grad_norm": 0.6825811862945557,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 3.4553,
      "step": 22
    },
    {
      "epoch": 0.021330860190122883,
      "grad_norm": 1.0185341835021973,
      "learning_rate": 3.8e-05,
      "loss": 3.6376,
      "step": 23
    },
    {
      "epoch": 0.02225828889404127,
      "grad_norm": 0.3887212574481964,
      "learning_rate": 3.7e-05,
      "loss": 2.9089,
      "step": 24
    },
    {
      "epoch": 0.023185717597959656,
      "grad_norm": 1.5926904678344727,
      "learning_rate": 3.6e-05,
      "loss": 3.6112,
      "step": 25
    },
    {
      "epoch": 0.024113146301878042,
      "grad_norm": 1.4020466804504395,
      "learning_rate": 3.5e-05,
      "loss": 3.8137,
      "step": 26
    },
    {
      "epoch": 0.025040575005796428,
      "grad_norm": 0.8697665929794312,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 3.3651,
      "step": 27
    },
    {
      "epoch": 0.025968003709714815,
      "grad_norm": 1.1937010288238525,
      "learning_rate": 3.3e-05,
      "loss": 3.7935,
      "step": 28
    },
    {
      "epoch": 0.0268954324136332,
      "grad_norm": 0.583304762840271,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.279,
      "step": 29
    },
    {
      "epoch": 0.027822861117551587,
      "grad_norm": 2.1346917152404785,
      "learning_rate": 3.1e-05,
      "loss": 4.1021,
      "step": 30
    },
    {
      "epoch": 0.028750289821469974,
      "grad_norm": 0.7281085848808289,
      "learning_rate": 3e-05,
      "loss": 3.3558,
      "step": 31
    },
    {
      "epoch": 0.02967771852538836,
      "grad_norm": 1.7035914659500122,
      "learning_rate": 2.9e-05,
      "loss": 3.5765,
      "step": 32
    },
    {
      "epoch": 0.030605147229306746,
      "grad_norm": 1.3239504098892212,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 3.6181,
      "step": 33
    },
    {
      "epoch": 0.031532575933225136,
      "grad_norm": 0.9565314650535583,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 3.5135,
      "step": 34
    },
    {
      "epoch": 0.03246000463714352,
      "grad_norm": 1.0347371101379395,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 3.2434,
      "step": 35
    },
    {
      "epoch": 0.03338743334106191,
      "grad_norm": 0.54816734790802,
      "learning_rate": 2.5e-05,
      "loss": 3.1409,
      "step": 36
    },
    {
      "epoch": 0.03431486204498029,
      "grad_norm": 0.4945932626724243,
      "learning_rate": 2.4e-05,
      "loss": 2.9236,
      "step": 37
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 0.48317691683769226,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 3.3575,
      "step": 38
    },
    {
      "epoch": 0.036169719452817065,
      "grad_norm": 1.2033950090408325,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 3.6258,
      "step": 39
    },
    {
      "epoch": 0.037097148156735454,
      "grad_norm": 1.137432336807251,
      "learning_rate": 2.1e-05,
      "loss": 3.5354,
      "step": 40
    },
    {
      "epoch": 0.03802457686065384,
      "grad_norm": 1.494925856590271,
      "learning_rate": 2e-05,
      "loss": 3.6365,
      "step": 41
    },
    {
      "epoch": 0.03895200556457222,
      "grad_norm": 1.1683684587478638,
      "learning_rate": 1.9e-05,
      "loss": 3.7584,
      "step": 42
    },
    {
      "epoch": 0.03987943426849061,
      "grad_norm": 1.5439304113388062,
      "learning_rate": 1.8e-05,
      "loss": 3.7813,
      "step": 43
    },
    {
      "epoch": 0.04080686297240899,
      "grad_norm": 1.4335922002792358,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 3.5158,
      "step": 44
    },
    {
      "epoch": 0.04173429167632738,
      "grad_norm": 1.0030946731567383,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.4701,
      "step": 45
    },
    {
      "epoch": 0.042661720380245766,
      "grad_norm": 0.8070414662361145,
      "learning_rate": 1.5e-05,
      "loss": 3.259,
      "step": 46
    },
    {
      "epoch": 0.043589149084164155,
      "grad_norm": 1.9914580583572388,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 4.3585,
      "step": 47
    },
    {
      "epoch": 0.04451657778808254,
      "grad_norm": 0.6409067511558533,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 3.3393,
      "step": 48
    },
    {
      "epoch": 0.04544400649200093,
      "grad_norm": 0.910348117351532,
      "learning_rate": 1.2e-05,
      "loss": 3.4981,
      "step": 49
    },
    {
      "epoch": 0.04637143519591931,
      "grad_norm": 1.3223044872283936,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 3.6996,
      "step": 50
    },
    {
      "epoch": 0.0472988638998377,
      "grad_norm": 0.3819347620010376,
      "learning_rate": 1e-05,
      "loss": 2.9741,
      "step": 51
    },
    {
      "epoch": 0.048226292603756084,
      "grad_norm": 1.3223705291748047,
      "learning_rate": 9e-06,
      "loss": 3.7789,
      "step": 52
    },
    {
      "epoch": 0.049153721307674474,
      "grad_norm": 0.6920037865638733,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.1836,
      "step": 53
    },
    {
      "epoch": 0.050081150011592857,
      "grad_norm": 0.6605297923088074,
      "learning_rate": 7.000000000000001e-06,
      "loss": 2.998,
      "step": 54
    },
    {
      "epoch": 0.051008578715511246,
      "grad_norm": 0.8535223603248596,
      "learning_rate": 6e-06,
      "loss": 3.1944,
      "step": 55
    },
    {
      "epoch": 0.05193600741942963,
      "grad_norm": 1.4277936220169067,
      "learning_rate": 5e-06,
      "loss": 3.6891,
      "step": 56
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 3.182830572128296,
      "learning_rate": 4.000000000000001e-06,
      "loss": 5.1859,
      "step": 57
    },
    {
      "epoch": 0.0537908648272664,
      "grad_norm": 0.6000503301620483,
      "learning_rate": 3e-06,
      "loss": 3.3717,
      "step": 58
    },
    {
      "epoch": 0.05471829353118479,
      "grad_norm": 1.301562786102295,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.4226,
      "step": 59
    },
    {
      "epoch": 0.055645722235103175,
      "grad_norm": 0.7561865448951721,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.0751,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 951810432098304.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}