{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.98220640569395,
  "eval_steps": 35,
  "global_step": 175,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 3.1716227531433105,
      "learning_rate": 2.380952380952381e-05,
      "loss": 2.4055,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 1.5721473693847656,
      "learning_rate": 4.761904761904762e-05,
      "loss": 2.2398,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 0.49050620198249817,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.9249,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 0.5206955671310425,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.7843,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.3736851215362549,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.7326,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.35366129875183105,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.6923,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.31748637557029724,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.715,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.582451343536377,
      "eval_runtime": 2.5895,
      "eval_samples_per_second": 17.764,
      "eval_steps_per_second": 17.764,
      "step": 35
    },
    {
      "epoch": 1.1387900355871885,
      "grad_norm": 0.33582279086112976,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.6396,
      "step": 40
    },
    {
      "epoch": 1.281138790035587,
      "grad_norm": 0.3968074917793274,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.6017,
      "step": 45
    },
    {
      "epoch": 1.4234875444839858,
      "grad_norm": 0.39966335892677307,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.5959,
      "step": 50
    },
    {
      "epoch": 1.5658362989323842,
      "grad_norm": 0.4648388922214508,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.5805,
      "step": 55
    },
    {
      "epoch": 1.708185053380783,
      "grad_norm": 0.5196627378463745,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.579,
      "step": 60
    },
    {
      "epoch": 1.8505338078291815,
      "grad_norm": 0.4826229214668274,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.5391,
      "step": 65
    },
    {
      "epoch": 1.99288256227758,
      "grad_norm": 0.5155557990074158,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.5599,
      "step": 70
    },
    {
      "epoch": 1.99288256227758,
      "eval_loss": 1.508989691734314,
      "eval_runtime": 2.5928,
      "eval_samples_per_second": 17.742,
      "eval_steps_per_second": 17.742,
      "step": 70
    },
    {
      "epoch": 2.135231316725979,
      "grad_norm": 0.5166239142417908,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.4277,
      "step": 75
    },
    {
      "epoch": 2.277580071174377,
      "grad_norm": 0.6423954367637634,
      "learning_rate": 7.782168677883206e-05,
      "loss": 1.4388,
      "step": 80
    },
    {
      "epoch": 2.419928825622776,
      "grad_norm": 0.6830139756202698,
      "learning_rate": 7.427681785900761e-05,
      "loss": 1.4763,
      "step": 85
    },
    {
      "epoch": 2.562277580071174,
      "grad_norm": 0.7132399082183838,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.4306,
      "step": 90
    },
    {
      "epoch": 2.704626334519573,
      "grad_norm": 0.7900845408439636,
      "learning_rate": 6.670992746965938e-05,
      "loss": 1.4139,
      "step": 95
    },
    {
      "epoch": 2.8469750889679717,
      "grad_norm": 0.750454306602478,
      "learning_rate": 6.274014364473274e-05,
      "loss": 1.4257,
      "step": 100
    },
    {
      "epoch": 2.9893238434163703,
      "grad_norm": 0.8368040919303894,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4363,
      "step": 105
    },
    {
      "epoch": 2.9893238434163703,
      "eval_loss": 1.5067311525344849,
      "eval_runtime": 2.5943,
      "eval_samples_per_second": 17.731,
      "eval_steps_per_second": 17.731,
      "step": 105
    },
    {
      "epoch": 3.131672597864769,
      "grad_norm": 0.8382311463356018,
      "learning_rate": 5.456473555193242e-05,
      "loss": 1.3086,
      "step": 110
    },
    {
      "epoch": 3.2740213523131674,
      "grad_norm": 0.96103435754776,
      "learning_rate": 5.041554979980486e-05,
      "loss": 1.2949,
      "step": 115
    },
    {
      "epoch": 3.416370106761566,
      "grad_norm": 1.064074158668518,
      "learning_rate": 4.626349532067879e-05,
      "loss": 1.2955,
      "step": 120
    },
    {
      "epoch": 3.5587188612099645,
      "grad_norm": 1.0585801601409912,
      "learning_rate": 4.213723561238074e-05,
      "loss": 1.2972,
      "step": 125
    },
    {
      "epoch": 3.701067615658363,
      "grad_norm": 1.1173142194747925,
      "learning_rate": 3.806525609984312e-05,
      "loss": 1.2759,
      "step": 130
    },
    {
      "epoch": 3.8434163701067616,
      "grad_norm": 1.1911710500717163,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 1.282,
      "step": 135
    },
    {
      "epoch": 3.98576512455516,
      "grad_norm": 1.1372343301773071,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.2383,
      "step": 140
    },
    {
      "epoch": 3.98576512455516,
      "eval_loss": 1.5461146831512451,
      "eval_runtime": 2.6004,
      "eval_samples_per_second": 17.689,
      "eval_steps_per_second": 17.689,
      "step": 140
    },
    {
      "epoch": 4.128113879003559,
      "grad_norm": 1.0997605323791504,
      "learning_rate": 2.645307173898901e-05,
      "loss": 1.1755,
      "step": 145
    },
    {
      "epoch": 4.270462633451958,
      "grad_norm": 1.2735544443130493,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 1.1929,
      "step": 150
    },
    {
      "epoch": 4.412811387900356,
      "grad_norm": 1.4365166425704956,
      "learning_rate": 1.947957390727185e-05,
      "loss": 1.1538,
      "step": 155
    },
    {
      "epoch": 4.555160142348754,
      "grad_norm": 1.2868629693984985,
      "learning_rate": 1.629715722373423e-05,
      "loss": 1.1815,
      "step": 160
    },
    {
      "epoch": 4.697508896797153,
      "grad_norm": 1.2928595542907715,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 1.1403,
      "step": 165
    },
    {
      "epoch": 4.839857651245552,
      "grad_norm": 1.3798590898513794,
      "learning_rate": 1.0650684916965559e-05,
      "loss": 1.1399,
      "step": 170
    },
    {
      "epoch": 4.98220640569395,
      "grad_norm": 1.324832797050476,
      "learning_rate": 8.225609429353187e-06,
      "loss": 1.1633,
      "step": 175
    },
    {
      "epoch": 4.98220640569395,
      "eval_loss": 1.6059898138046265,
      "eval_runtime": 2.6253,
      "eval_samples_per_second": 17.522,
      "eval_steps_per_second": 17.522,
      "step": 175
    }
  ],
  "logging_steps": 5,
  "max_steps": 210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0496735416328192e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}