{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.820512820512821,
  "eval_steps": 100,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 81.8341293334961,
      "learning_rate": 9.990900000000001e-06,
      "loss": 3.5606,
      "step": 100
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 2.2667126655578613,
      "eval_runtime": 33.7385,
      "eval_samples_per_second": 11.648,
      "eval_steps_per_second": 1.482,
      "step": 100
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 30.16681671142578,
      "learning_rate": 9.980900000000001e-06,
      "loss": 2.1841,
      "step": 200
    },
    {
      "epoch": 1.0256410256410255,
      "eval_loss": 2.059685230255127,
      "eval_runtime": 33.6897,
      "eval_samples_per_second": 11.665,
      "eval_steps_per_second": 1.484,
      "step": 200
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 67.16844177246094,
      "learning_rate": 9.970900000000001e-06,
      "loss": 2.0949,
      "step": 300
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 1.9054155349731445,
      "eval_runtime": 33.6472,
      "eval_samples_per_second": 11.68,
      "eval_steps_per_second": 1.486,
      "step": 300
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 46.190330505371094,
      "learning_rate": 9.960900000000001e-06,
      "loss": 1.9236,
      "step": 400
    },
    {
      "epoch": 2.051282051282051,
      "eval_loss": 1.8464823961257935,
      "eval_runtime": 33.8143,
      "eval_samples_per_second": 11.622,
      "eval_steps_per_second": 1.479,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 42.82326889038086,
      "learning_rate": 9.950900000000002e-06,
      "loss": 1.937,
      "step": 500
    },
    {
      "epoch": 2.564102564102564,
      "eval_loss": 1.8186373710632324,
      "eval_runtime": 33.9112,
      "eval_samples_per_second": 11.589,
      "eval_steps_per_second": 1.474,
      "step": 500
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 68.72016906738281,
      "learning_rate": 9.940900000000002e-06,
      "loss": 1.8648,
      "step": 600
    },
    {
      "epoch": 3.076923076923077,
      "eval_loss": 1.7807129621505737,
      "eval_runtime": 33.4957,
      "eval_samples_per_second": 11.733,
      "eval_steps_per_second": 1.493,
      "step": 600
    },
    {
      "epoch": 3.58974358974359,
      "grad_norm": 51.390071868896484,
      "learning_rate": 9.930900000000002e-06,
      "loss": 1.8162,
      "step": 700
    },
    {
      "epoch": 3.58974358974359,
      "eval_loss": 1.7275961637496948,
      "eval_runtime": 33.6095,
      "eval_samples_per_second": 11.693,
      "eval_steps_per_second": 1.488,
      "step": 700
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 33.017948150634766,
      "learning_rate": 9.920900000000002e-06,
      "loss": 1.7331,
      "step": 800
    },
    {
      "epoch": 4.102564102564102,
      "eval_loss": 1.701725959777832,
      "eval_runtime": 33.9602,
      "eval_samples_per_second": 11.572,
      "eval_steps_per_second": 1.472,
      "step": 800
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 43.55423355102539,
      "learning_rate": 9.9109e-06,
      "loss": 1.7091,
      "step": 900
    },
    {
      "epoch": 4.615384615384615,
      "eval_loss": 1.6944857835769653,
      "eval_runtime": 33.6785,
      "eval_samples_per_second": 11.669,
      "eval_steps_per_second": 1.485,
      "step": 900
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 67.6618881225586,
      "learning_rate": 9.9009e-06,
      "loss": 1.7258,
      "step": 1000
    },
    {
      "epoch": 5.128205128205128,
      "eval_loss": 1.65646493434906,
      "eval_runtime": 33.8316,
      "eval_samples_per_second": 11.616,
      "eval_steps_per_second": 1.478,
      "step": 1000
    },
    {
      "epoch": 5.641025641025641,
      "grad_norm": 35.863487243652344,
      "learning_rate": 9.8909e-06,
      "loss": 1.661,
      "step": 1100
    },
    {
      "epoch": 5.641025641025641,
      "eval_loss": 1.6175495386123657,
      "eval_runtime": 33.57,
      "eval_samples_per_second": 11.707,
      "eval_steps_per_second": 1.489,
      "step": 1100
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 56.98338317871094,
      "learning_rate": 9.8809e-06,
      "loss": 1.6368,
      "step": 1200
    },
    {
      "epoch": 6.153846153846154,
      "eval_loss": 1.6185818910598755,
      "eval_runtime": 33.6954,
      "eval_samples_per_second": 11.663,
      "eval_steps_per_second": 1.484,
      "step": 1200
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 90.9850845336914,
      "learning_rate": 9.8709e-06,
      "loss": 1.6771,
      "step": 1300
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.597514033317566,
      "eval_runtime": 33.5635,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 1.49,
      "step": 1300
    },
    {
      "epoch": 7.17948717948718,
      "grad_norm": 83.6468276977539,
      "learning_rate": 9.8609e-06,
      "loss": 1.5796,
      "step": 1400
    },
    {
      "epoch": 7.17948717948718,
      "eval_loss": 1.57249116897583,
      "eval_runtime": 33.6053,
      "eval_samples_per_second": 11.695,
      "eval_steps_per_second": 1.488,
      "step": 1400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 42.52065658569336,
      "learning_rate": 9.8509e-06,
      "loss": 1.6012,
      "step": 1500
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 1.5940505266189575,
      "eval_runtime": 33.6416,
      "eval_samples_per_second": 11.682,
      "eval_steps_per_second": 1.486,
      "step": 1500
    },
    {
      "epoch": 8.205128205128204,
      "grad_norm": 64.46149444580078,
      "learning_rate": 9.840900000000001e-06,
      "loss": 1.6107,
      "step": 1600
    },
    {
      "epoch": 8.205128205128204,
      "eval_loss": 1.57711923122406,
      "eval_runtime": 33.8072,
      "eval_samples_per_second": 11.625,
      "eval_steps_per_second": 1.479,
      "step": 1600
    },
    {
      "epoch": 8.717948717948717,
      "grad_norm": 47.13843536376953,
      "learning_rate": 9.830900000000001e-06,
      "loss": 1.6094,
      "step": 1700
    },
    {
      "epoch": 8.717948717948717,
      "eval_loss": 1.5567021369934082,
      "eval_runtime": 33.6256,
      "eval_samples_per_second": 11.688,
      "eval_steps_per_second": 1.487,
      "step": 1700
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 60.96649932861328,
      "learning_rate": 9.820900000000001e-06,
      "loss": 1.5679,
      "step": 1800
    },
    {
      "epoch": 9.23076923076923,
      "eval_loss": 1.5404459238052368,
      "eval_runtime": 33.5651,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 1.49,
      "step": 1800
    },
    {
      "epoch": 9.743589743589745,
      "grad_norm": 48.0488395690918,
      "learning_rate": 9.810900000000001e-06,
      "loss": 1.541,
      "step": 1900
    },
    {
      "epoch": 9.743589743589745,
      "eval_loss": 1.5000860691070557,
      "eval_runtime": 33.729,
      "eval_samples_per_second": 11.652,
      "eval_steps_per_second": 1.482,
      "step": 1900
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 21.072124481201172,
      "learning_rate": 9.800900000000001e-06,
      "loss": 1.4747,
      "step": 2000
    },
    {
      "epoch": 10.256410256410255,
      "eval_loss": 1.4845048189163208,
      "eval_runtime": 33.6789,
      "eval_samples_per_second": 11.669,
      "eval_steps_per_second": 1.485,
      "step": 2000
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 60.55208969116211,
      "learning_rate": 9.790900000000001e-06,
      "loss": 1.5105,
      "step": 2100
    },
    {
      "epoch": 10.76923076923077,
      "eval_loss": 1.4587421417236328,
      "eval_runtime": 33.4313,
      "eval_samples_per_second": 11.755,
      "eval_steps_per_second": 1.496,
      "step": 2100
    },
    {
      "epoch": 11.282051282051283,
      "grad_norm": 26.457704544067383,
      "learning_rate": 9.780900000000002e-06,
      "loss": 1.4769,
      "step": 2200
    },
    {
      "epoch": 11.282051282051283,
      "eval_loss": 1.4588648080825806,
      "eval_runtime": 33.5978,
      "eval_samples_per_second": 11.697,
      "eval_steps_per_second": 1.488,
      "step": 2200
    },
    {
      "epoch": 11.794871794871796,
      "grad_norm": 23.801916122436523,
      "learning_rate": 9.770900000000002e-06,
      "loss": 1.4555,
      "step": 2300
    },
    {
      "epoch": 11.794871794871796,
      "eval_loss": 1.4805899858474731,
      "eval_runtime": 33.4947,
      "eval_samples_per_second": 11.733,
      "eval_steps_per_second": 1.493,
      "step": 2300
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 24.780275344848633,
      "learning_rate": 9.760900000000002e-06,
      "loss": 1.4537,
      "step": 2400
    },
    {
      "epoch": 12.307692307692308,
      "eval_loss": 1.4648451805114746,
      "eval_runtime": 33.6877,
      "eval_samples_per_second": 11.666,
      "eval_steps_per_second": 1.484,
      "step": 2400
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 65.28894805908203,
      "learning_rate": 9.7509e-06,
      "loss": 1.4788,
      "step": 2500
    },
    {
      "epoch": 12.820512820512821,
      "eval_loss": 1.4453215599060059,
      "eval_runtime": 33.972,
      "eval_samples_per_second": 11.568,
      "eval_steps_per_second": 1.472,
      "step": 2500
    }
  ],
  "logging_steps": 100,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 513,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.5560791552e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}