{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996631862579993,
  "eval_steps": 500,
  "global_step": 371,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002694509936005389,
      "grad_norm": 12.76484489440918,
      "learning_rate": 5.263157894736842e-06,
      "loss": 3.5442,
      "step": 1
    },
    {
      "epoch": 0.02694509936005389,
      "grad_norm": 1.225385308265686,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 3.4136,
      "step": 10
    },
    {
      "epoch": 0.05389019872010778,
      "grad_norm": 0.22818362712860107,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.5345,
      "step": 20
    },
    {
      "epoch": 0.08083529808016167,
      "grad_norm": 0.11801251769065857,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.4693,
      "step": 30
    },
    {
      "epoch": 0.10778039744021556,
      "grad_norm": 0.12770982086658478,
      "learning_rate": 0.0001987987987987988,
      "loss": 1.3288,
      "step": 40
    },
    {
      "epoch": 0.13472549680026946,
      "grad_norm": 0.1819867640733719,
      "learning_rate": 0.00019279279279279282,
      "loss": 1.2308,
      "step": 50
    },
    {
      "epoch": 0.16167059616032334,
      "grad_norm": 0.09357380867004395,
      "learning_rate": 0.0001867867867867868,
      "loss": 1.0072,
      "step": 60
    },
    {
      "epoch": 0.18861569552037724,
      "grad_norm": 0.07331203669309616,
      "learning_rate": 0.00018078078078078078,
      "loss": 0.9502,
      "step": 70
    },
    {
      "epoch": 0.21556079488043112,
      "grad_norm": 0.045368436723947525,
      "learning_rate": 0.00017477477477477476,
      "loss": 0.9393,
      "step": 80
    },
    {
      "epoch": 0.24250589424048502,
      "grad_norm": 0.04616931825876236,
      "learning_rate": 0.00016876876876876877,
      "loss": 0.9084,
      "step": 90
    },
    {
      "epoch": 0.2694509936005389,
      "grad_norm": 0.04786905273795128,
      "learning_rate": 0.00016276276276276275,
      "loss": 0.9046,
      "step": 100
    },
    {
      "epoch": 0.29639609296059277,
      "grad_norm": 0.03197158873081207,
      "learning_rate": 0.00015675675675675676,
      "loss": 0.8554,
      "step": 110
    },
    {
      "epoch": 0.3233411923206467,
      "grad_norm": 0.02612409181892872,
      "learning_rate": 0.00015075075075075077,
      "loss": 0.833,
      "step": 120
    },
    {
      "epoch": 0.3502862916807006,
      "grad_norm": 0.028117205947637558,
      "learning_rate": 0.00014474474474474475,
      "loss": 0.8364,
      "step": 130
    },
    {
      "epoch": 0.3772313910407545,
      "grad_norm": 0.018981853500008583,
      "learning_rate": 0.00013873873873873876,
      "loss": 0.8246,
      "step": 140
    },
    {
      "epoch": 0.40417649040080833,
      "grad_norm": 0.04023918882012367,
      "learning_rate": 0.00013273273273273274,
      "loss": 0.8511,
      "step": 150
    },
    {
      "epoch": 0.43112158976086223,
      "grad_norm": 0.03793207183480263,
      "learning_rate": 0.00012672672672672675,
      "loss": 0.8217,
      "step": 160
    },
    {
      "epoch": 0.45806668912091614,
      "grad_norm": 0.02019081450998783,
      "learning_rate": 0.00012072072072072073,
      "loss": 0.8001,
      "step": 170
    },
    {
      "epoch": 0.48501178848097004,
      "grad_norm": 0.031807586550712585,
      "learning_rate": 0.00011471471471471471,
      "loss": 0.8019,
      "step": 180
    },
    {
      "epoch": 0.5119568878410239,
      "grad_norm": 0.02062528021633625,
      "learning_rate": 0.0001087087087087087,
      "loss": 0.8047,
      "step": 190
    },
    {
      "epoch": 0.5389019872010778,
      "grad_norm": 0.03914797678589821,
      "learning_rate": 0.0001027027027027027,
      "loss": 0.8178,
      "step": 200
    },
    {
      "epoch": 0.5658470865611317,
      "grad_norm": 0.04694194346666336,
      "learning_rate": 9.66966966966967e-05,
      "loss": 0.7934,
      "step": 210
    },
    {
      "epoch": 0.5927921859211855,
      "grad_norm": 0.023888826370239258,
      "learning_rate": 9.069069069069069e-05,
      "loss": 0.7794,
      "step": 220
    },
    {
      "epoch": 0.6197372852812395,
      "grad_norm": 0.034731291234493256,
      "learning_rate": 8.468468468468469e-05,
      "loss": 0.7799,
      "step": 230
    },
    {
      "epoch": 0.6466823846412934,
      "grad_norm": 0.022078100591897964,
      "learning_rate": 7.867867867867868e-05,
      "loss": 0.7779,
      "step": 240
    },
    {
      "epoch": 0.6736274840013473,
      "grad_norm": 0.04586014896631241,
      "learning_rate": 7.267267267267268e-05,
      "loss": 0.7906,
      "step": 250
    },
    {
      "epoch": 0.7005725833614012,
      "grad_norm": 0.04206414520740509,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7768,
      "step": 260
    },
    {
      "epoch": 0.727517682721455,
      "grad_norm": 0.024432417005300522,
      "learning_rate": 6.0660660660660665e-05,
      "loss": 0.7691,
      "step": 270
    },
    {
      "epoch": 0.754462782081509,
      "grad_norm": 0.03391208499670029,
      "learning_rate": 5.465465465465466e-05,
      "loss": 0.7629,
      "step": 280
    },
    {
      "epoch": 0.7814078814415628,
      "grad_norm": 0.018352922052145004,
      "learning_rate": 4.8648648648648654e-05,
      "loss": 0.7625,
      "step": 290
    },
    {
      "epoch": 0.8083529808016167,
      "grad_norm": 0.04901178553700447,
      "learning_rate": 4.264264264264264e-05,
      "loss": 0.7778,
      "step": 300
    },
    {
      "epoch": 0.8352980801616706,
      "grad_norm": 0.0407499223947525,
      "learning_rate": 3.663663663663664e-05,
      "loss": 0.7657,
      "step": 310
    },
    {
      "epoch": 0.8622431795217245,
      "grad_norm": 0.031635917723178864,
      "learning_rate": 3.063063063063063e-05,
      "loss": 0.7621,
      "step": 320
    },
    {
      "epoch": 0.8891882788817784,
      "grad_norm": 0.020033176988363266,
      "learning_rate": 2.4624624624624627e-05,
      "loss": 0.7571,
      "step": 330
    },
    {
      "epoch": 0.9161333782418323,
      "grad_norm": 0.045810870826244354,
      "learning_rate": 1.8618618618618618e-05,
      "loss": 0.7539,
      "step": 340
    },
    {
      "epoch": 0.9430784776018861,
      "grad_norm": 0.07599364966154099,
      "learning_rate": 1.2612612612612611e-05,
      "loss": 0.7684,
      "step": 350
    },
    {
      "epoch": 0.9700235769619401,
      "grad_norm": 0.01792909763753414,
      "learning_rate": 6.606606606606607e-06,
      "loss": 0.7643,
      "step": 360
    },
    {
      "epoch": 0.9969686763219939,
      "grad_norm": 0.02676345966756344,
      "learning_rate": 6.006006006006006e-07,
      "loss": 0.7515,
      "step": 370
    }
  ],
  "logging_steps": 10,
  "max_steps": 371,
  "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": 2.331323573248983e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}