{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.936936936936937,
  "eval_steps": 500,
  "global_step": 65,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.9883,
      "step": 1
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.4609,
      "step": 2
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.4512,
      "step": 3
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.1406,
      "step": 4
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6152,
      "step": 5
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.1738,
      "step": 6
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.5547,
      "step": 7
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.459,
      "step": 8
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.123,
      "step": 9
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.6152,
      "step": 10
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6719,
      "step": 11
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.877,
      "step": 12
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.459,
      "step": 13
    },
    {
      "epoch": 1.072072072072072,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 124.793,
      "step": 14
    },
    {
      "epoch": 1.1441441441441442,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.0137,
      "step": 15
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.7871,
      "step": 16
    },
    {
      "epoch": 1.2882882882882882,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6484,
      "step": 17
    },
    {
      "epoch": 1.3603603603603602,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6309,
      "step": 18
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 121.69364311021961,
      "learning_rate": 0.0001,
      "loss": 111.0137,
      "step": 19
    },
    {
      "epoch": 1.5045045045045045,
      "grad_norm": 121.82811999006017,
      "learning_rate": 9.993977281025862e-05,
      "loss": 102.374,
      "step": 20
    },
    {
      "epoch": 1.5765765765765765,
      "grad_norm": 43.762035174980724,
      "learning_rate": 9.975923633360985e-05,
      "loss": 37.7349,
      "step": 21
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 43.762035174980724,
      "learning_rate": 9.975923633360985e-05,
      "loss": 23.8311,
      "step": 22
    },
    {
      "epoch": 1.7207207207207207,
      "grad_norm": 43.762035174980724,
      "learning_rate": 9.975923633360985e-05,
      "loss": 23.6587,
      "step": 23
    },
    {
      "epoch": 1.7927927927927927,
      "grad_norm": 67.60606900572056,
      "learning_rate": 9.945882549823906e-05,
      "loss": 23.4604,
      "step": 24
    },
    {
      "epoch": 1.864864864864865,
      "grad_norm": 47.84182107476679,
      "learning_rate": 9.903926402016153e-05,
      "loss": 22.4585,
      "step": 25
    },
    {
      "epoch": 1.936936936936937,
      "grad_norm": 97.3110950444501,
      "learning_rate": 9.850156265972721e-05,
      "loss": 15.5953,
      "step": 26
    },
    {
      "epoch": 2.0720720720720722,
      "grad_norm": 13.359584588085475,
      "learning_rate": 9.784701678661045e-05,
      "loss": 5.8495,
      "step": 27
    },
    {
      "epoch": 2.144144144144144,
      "grad_norm": 15.499340904743185,
      "learning_rate": 9.707720325915104e-05,
      "loss": 3.2645,
      "step": 28
    },
    {
      "epoch": 2.2162162162162162,
      "grad_norm": 5.2516204512990035,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7318,
      "step": 29
    },
    {
      "epoch": 2.2882882882882885,
      "grad_norm": 6.351586523632304,
      "learning_rate": 9.519946465617218e-05,
      "loss": 0.8066,
      "step": 30
    },
    {
      "epoch": 2.3603603603603602,
      "grad_norm": 4.296773347519179,
      "learning_rate": 9.409606321741775e-05,
      "loss": 0.389,
      "step": 31
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 3.7567276687430526,
      "learning_rate": 9.288643050001361e-05,
      "loss": 0.238,
      "step": 32
    },
    {
      "epoch": 2.5045045045045047,
      "grad_norm": 0.8841967237890292,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.1217,
      "step": 33
    },
    {
      "epoch": 2.5765765765765765,
      "grad_norm": 2.065381666847204,
      "learning_rate": 9.016037657403224e-05,
      "loss": 0.7948,
      "step": 34
    },
    {
      "epoch": 2.6486486486486487,
      "grad_norm": 36.57744419486038,
      "learning_rate": 8.865052266813685e-05,
      "loss": 1.8392,
      "step": 35
    },
    {
      "epoch": 2.7207207207207205,
      "grad_norm": 6.098258360827327,
      "learning_rate": 8.704755626774796e-05,
      "loss": 0.4845,
      "step": 36
    },
    {
      "epoch": 2.7927927927927927,
      "grad_norm": 4.902366899534486,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2728,
      "step": 37
    },
    {
      "epoch": 2.864864864864865,
      "grad_norm": 3.3005947444072987,
      "learning_rate": 8.357794774235092e-05,
      "loss": 0.2294,
      "step": 38
    },
    {
      "epoch": 2.936936936936937,
      "grad_norm": 0.5713662641479601,
      "learning_rate": 8.171966420818228e-05,
      "loss": 0.0271,
      "step": 39
    },
    {
      "epoch": 3.0720720720720722,
      "grad_norm": 0.3093144415337581,
      "learning_rate": 7.978496522462167e-05,
      "loss": 0.0544,
      "step": 40
    },
    {
      "epoch": 3.144144144144144,
      "grad_norm": 6.086269384303536,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0918,
      "step": 41
    },
    {
      "epoch": 3.2162162162162162,
      "grad_norm": 0.8619135383139304,
      "learning_rate": 7.570513720966108e-05,
      "loss": 0.0149,
      "step": 42
    },
    {
      "epoch": 3.2882882882882885,
      "grad_norm": 0.170124990369711,
      "learning_rate": 7.35698368412999e-05,
      "loss": 0.0106,
      "step": 43
    },
    {
      "epoch": 3.3603603603603602,
      "grad_norm": 0.2984404823393874,
      "learning_rate": 7.137775467151411e-05,
      "loss": 0.1274,
      "step": 44
    },
    {
      "epoch": 3.4324324324324325,
      "grad_norm": 2.7538582006280317,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8402,
      "step": 45
    },
    {
      "epoch": 3.5045045045045047,
      "grad_norm": 2.7538582006280317,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.0066,
      "step": 46
    },
    {
      "epoch": 3.5765765765765765,
      "grad_norm": 243.24225964046624,
      "learning_rate": 6.6844492669611e-05,
      "loss": 2.8196,
      "step": 47
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 4.988008998052072,
      "learning_rate": 6.451423386272312e-05,
      "loss": 0.377,
      "step": 48
    },
    {
      "epoch": 3.7207207207207205,
      "grad_norm": 0.2693118570806549,
      "learning_rate": 6.21490089951632e-05,
      "loss": 0.0247,
      "step": 49
    },
    {
      "epoch": 3.7927927927927927,
      "grad_norm": 0.05521830464606099,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0091,
      "step": 50
    },
    {
      "epoch": 3.864864864864865,
      "grad_norm": 0.6910149711748117,
      "learning_rate": 5.733652372276809e-05,
      "loss": 0.0199,
      "step": 51
    },
    {
      "epoch": 3.936936936936937,
      "grad_norm": 0.10849567725705088,
      "learning_rate": 5.490085701647805e-05,
      "loss": 0.0033,
      "step": 52
    },
    {
      "epoch": 4.072072072072072,
      "grad_norm": 0.10809313247991727,
      "learning_rate": 5.245338371637091e-05,
      "loss": 0.0146,
      "step": 53
    },
    {
      "epoch": 4.1441441441441444,
      "grad_norm": 0.05128671267400455,
      "learning_rate": 5e-05,
      "loss": 0.0023,
      "step": 54
    },
    {
      "epoch": 4.216216216216216,
      "grad_norm": 0.04446616393871321,
      "learning_rate": 4.7546616283629105e-05,
      "loss": 0.0706,
      "step": 55
    },
    {
      "epoch": 4.288288288288288,
      "grad_norm": 92.7258697131631,
      "learning_rate": 4.509914298352197e-05,
      "loss": 0.0734,
      "step": 56
    },
    {
      "epoch": 4.36036036036036,
      "grad_norm": 0.10509705390750478,
      "learning_rate": 4.2663476277231915e-05,
      "loss": 0.0052,
      "step": 57
    },
    {
      "epoch": 4.4324324324324325,
      "grad_norm": 0.05685107825836915,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0009,
      "step": 58
    },
    {
      "epoch": 4.504504504504505,
      "grad_norm": 0.0071402069274671244,
      "learning_rate": 3.785099100483681e-05,
      "loss": 0.0004,
      "step": 59
    },
    {
      "epoch": 4.576576576576577,
      "grad_norm": 0.007037629263124771,
      "learning_rate": 3.5485766137276894e-05,
      "loss": 0.0033,
      "step": 60
    },
    {
      "epoch": 4.648648648648649,
      "grad_norm": 0.07795566744834063,
      "learning_rate": 3.3155507330389e-05,
      "loss": 0.0067,
      "step": 61
    },
    {
      "epoch": 4.7207207207207205,
      "grad_norm": 0.21346197540898718,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0008,
      "step": 62
    },
    {
      "epoch": 4.792792792792793,
      "grad_norm": 0.07957365304285995,
      "learning_rate": 2.8622245328485907e-05,
      "loss": 0.005,
      "step": 63
    },
    {
      "epoch": 4.864864864864865,
      "grad_norm": 0.0022461733078342535,
      "learning_rate": 2.6430163158700115e-05,
      "loss": 0.0076,
      "step": 64
    },
    {
      "epoch": 4.936936936936937,
      "grad_norm": 0.06343292790647254,
      "learning_rate": 2.4294862790338917e-05,
      "loss": 0.0001,
      "step": 65
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 65,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.90161235112362e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}