{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 50.074012756347656,
      "learning_rate": 0.0,
      "loss": 1.40986967086792,
      "step": 1
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 53.68495559692383,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.4964791536331177,
      "step": 2
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 43.420005798339844,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.3421201705932617,
      "step": 3
    },
    {
      "epoch": 0.2831858407079646,
      "grad_norm": 18.960111618041992,
      "learning_rate": 5e-06,
      "loss": 1.118983507156372,
      "step": 4
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 6.306451797485352,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.9437508583068848,
      "step": 5
    },
    {
      "epoch": 0.4247787610619469,
      "grad_norm": 9.622514724731445,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.9040769338607788,
      "step": 6
    },
    {
      "epoch": 0.49557522123893805,
      "grad_norm": 6.888988971710205,
      "learning_rate": 1e-05,
      "loss": 0.8478146195411682,
      "step": 7
    },
    {
      "epoch": 0.5663716814159292,
      "grad_norm": 2.924564838409424,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.760687530040741,
      "step": 8
    },
    {
      "epoch": 0.6371681415929203,
      "grad_norm": 2.7066144943237305,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.8113027811050415,
      "step": 9
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 1.9081557989120483,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.7258458137512207,
      "step": 10
    },
    {
      "epoch": 0.7787610619469026,
      "grad_norm": 1.6245616674423218,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.7298057079315186,
      "step": 11
    },
    {
      "epoch": 0.8495575221238938,
      "grad_norm": 1.6821726560592651,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.7588151693344116,
      "step": 12
    },
    {
      "epoch": 0.9203539823008849,
      "grad_norm": 1.4290574789047241,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.7416592836380005,
      "step": 13
    },
    {
      "epoch": 0.9911504424778761,
      "grad_norm": 1.4913954734802246,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.7269161939620972,
      "step": 14
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.807140827178955,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.6428764462471008,
      "step": 15
    },
    {
      "epoch": 1.0707964601769913,
      "grad_norm": 1.5311468839645386,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.6173319816589355,
      "step": 16
    },
    {
      "epoch": 1.1415929203539823,
      "grad_norm": 1.5018333196640015,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.6359413266181946,
      "step": 17
    },
    {
      "epoch": 1.2123893805309733,
      "grad_norm": 1.2993215322494507,
      "learning_rate": 9.01061596377522e-06,
      "loss": 0.6308578252792358,
      "step": 18
    },
    {
      "epoch": 1.2831858407079646,
      "grad_norm": 1.2826988697052002,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.5893546342849731,
      "step": 19
    },
    {
      "epoch": 1.3539823008849559,
      "grad_norm": 1.3179434537887573,
      "learning_rate": 8.636868207865244e-06,
      "loss": 0.6160678267478943,
      "step": 20
    },
    {
      "epoch": 1.424778761061947,
      "grad_norm": 1.3196086883544922,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.6084617972373962,
      "step": 21
    },
    {
      "epoch": 1.495575221238938,
      "grad_norm": 1.3763041496276855,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.5884666442871094,
      "step": 22
    },
    {
      "epoch": 1.5663716814159292,
      "grad_norm": 1.3341829776763916,
      "learning_rate": 7.985792958513932e-06,
      "loss": 0.5703476667404175,
      "step": 23
    },
    {
      "epoch": 1.6371681415929205,
      "grad_norm": 1.229111671447754,
      "learning_rate": 7.747544890354031e-06,
      "loss": 0.572840690612793,
      "step": 24
    },
    {
      "epoch": 1.7079646017699115,
      "grad_norm": 1.2158163785934448,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.550726056098938,
      "step": 25
    },
    {
      "epoch": 1.7787610619469025,
      "grad_norm": 1.1939095258712769,
      "learning_rate": 7.243995901002312e-06,
      "loss": 0.5565768480300903,
      "step": 26
    },
    {
      "epoch": 1.8495575221238938,
      "grad_norm": 1.1766549348831177,
      "learning_rate": 6.980398830195785e-06,
      "loss": 0.5552008152008057,
      "step": 27
    },
    {
      "epoch": 1.920353982300885,
      "grad_norm": 1.2779844999313354,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.6178507804870605,
      "step": 28
    },
    {
      "epoch": 1.991150442477876,
      "grad_norm": 1.2303086519241333,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.5532016754150391,
      "step": 29
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.10593843460083,
      "learning_rate": 6.153079353712201e-06,
      "loss": 0.4448966383934021,
      "step": 30
    },
    {
      "epoch": 2.0707964601769913,
      "grad_norm": 1.401031494140625,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.4768362045288086,
      "step": 31
    },
    {
      "epoch": 2.1415929203539825,
      "grad_norm": 1.2902497053146362,
      "learning_rate": 5.5804645706261515e-06,
      "loss": 0.4592363238334656,
      "step": 32
    },
    {
      "epoch": 2.2123893805309733,
      "grad_norm": 1.1970809698104858,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.47542697191238403,
      "step": 33
    },
    {
      "epoch": 2.2831858407079646,
      "grad_norm": 1.1806858777999878,
      "learning_rate": 5e-06,
      "loss": 0.4710686206817627,
      "step": 34
    },
    {
      "epoch": 2.353982300884956,
      "grad_norm": 1.3289209604263306,
      "learning_rate": 4.7092758554476215e-06,
      "loss": 0.46914583444595337,
      "step": 35
    },
    {
      "epoch": 2.4247787610619467,
      "grad_norm": 1.1916477680206299,
      "learning_rate": 4.4195354293738484e-06,
      "loss": 0.4385316073894501,
      "step": 36
    },
    {
      "epoch": 2.495575221238938,
      "grad_norm": 1.228267788887024,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.4495742917060852,
      "step": 37
    },
    {
      "epoch": 2.566371681415929,
      "grad_norm": 1.3644487857818604,
      "learning_rate": 3.8469206462878e-06,
      "loss": 0.46654635667800903,
      "step": 38
    },
    {
      "epoch": 2.6371681415929205,
      "grad_norm": 1.2453330755233765,
      "learning_rate": 3.5659838364445505e-06,
      "loss": 0.42036041617393494,
      "step": 39
    },
    {
      "epoch": 2.7079646017699117,
      "grad_norm": 1.2439433336257935,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.4493784010410309,
      "step": 40
    },
    {
      "epoch": 2.7787610619469025,
      "grad_norm": 1.2308580875396729,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.44434070587158203,
      "step": 41
    },
    {
      "epoch": 2.849557522123894,
      "grad_norm": 1.1945712566375732,
      "learning_rate": 2.7560040989976894e-06,
      "loss": 0.42155495285987854,
      "step": 42
    },
    {
      "epoch": 2.920353982300885,
      "grad_norm": 1.1859475374221802,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.40417200326919556,
      "step": 43
    },
    {
      "epoch": 2.991150442477876,
      "grad_norm": 1.2516086101531982,
      "learning_rate": 2.2524551096459703e-06,
      "loss": 0.40475600957870483,
      "step": 44
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.868532419204712,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.3524181544780731,
      "step": 45
    },
    {
      "epoch": 3.0707964601769913,
      "grad_norm": 1.1654366254806519,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.3934929370880127,
      "step": 46
    },
    {
      "epoch": 3.1415929203539825,
      "grad_norm": 1.2486796379089355,
      "learning_rate": 1.5687918106563326e-06,
      "loss": 0.35962843894958496,
      "step": 47
    },
    {
      "epoch": 3.2123893805309733,
      "grad_norm": 1.229835033416748,
      "learning_rate": 1.3631317921347564e-06,
      "loss": 0.3938334584236145,
      "step": 48
    },
    {
      "epoch": 3.2831858407079646,
      "grad_norm": 1.2063524723052979,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.3707515597343445,
      "step": 49
    },
    {
      "epoch": 3.353982300884956,
      "grad_norm": 1.1336451768875122,
      "learning_rate": 9.893840362247809e-07,
      "loss": 0.38788312673568726,
      "step": 50
    },
    {
      "epoch": 3.4247787610619467,
      "grad_norm": 1.1350209712982178,
      "learning_rate": 8.225609429353187e-07,
      "loss": 0.36757567524909973,
      "step": 51
    },
    {
      "epoch": 3.495575221238938,
      "grad_norm": 1.0958055257797241,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.375740110874176,
      "step": 52
    },
    {
      "epoch": 3.566371681415929,
      "grad_norm": 1.083740234375,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.34685075283050537,
      "step": 53
    },
    {
      "epoch": 3.6371681415929205,
      "grad_norm": 1.1857285499572754,
      "learning_rate": 4.089194655986306e-07,
      "loss": 0.3674459457397461,
      "step": 54
    },
    {
      "epoch": 3.7079646017699117,
      "grad_norm": 1.1642030477523804,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.37284308671951294,
      "step": 55
    },
    {
      "epoch": 3.7787610619469025,
      "grad_norm": 1.1457759141921997,
      "learning_rate": 2.1005243842255552e-07,
      "loss": 0.3796018958091736,
      "step": 56
    },
    {
      "epoch": 3.849557522123894,
      "grad_norm": 1.1166174411773682,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 0.36435168981552124,
      "step": 57
    },
    {
      "epoch": 3.920353982300885,
      "grad_norm": 1.2060168981552124,
      "learning_rate": 7.59612349389599e-08,
      "loss": 0.361666202545166,
      "step": 58
    },
    {
      "epoch": 3.991150442477876,
      "grad_norm": 1.080897569656372,
      "learning_rate": 3.3808211290284886e-08,
      "loss": 0.37428635358810425,
      "step": 59
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.897923231124878,
      "learning_rate": 8.459208643659122e-09,
      "loss": 0.35041147470474243,
      "step": 60
    },
    {
      "epoch": 4.0,
      "step": 60,
      "total_flos": 2.0582894662372557e+17,
      "train_loss": 0.5806472768386205,
      "train_runtime": 493.9678,
      "train_samples_per_second": 7.264,
      "train_steps_per_second": 0.121
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0582894662372557e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}