{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9657142857142857,
  "eval_steps": 500,
  "global_step": 86,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 6.666666666666667e-06,
      "loss": 3.0025,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.3344,
      "step": 2
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 2.8488,
      "step": 3
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9992837548163315e-05,
      "loss": 2.6912,
      "step": 4
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9971360452796523e-05,
      "loss": 2.6867,
      "step": 5
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.993559947963185e-05,
      "loss": 2.5857,
      "step": 6
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9885605855918887e-05,
      "loss": 2.6284,
      "step": 7
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9821451197042028e-05,
      "loss": 2.5126,
      "step": 8
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9743227403932135e-05,
      "loss": 2.2892,
      "step": 9
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9651046531419335e-05,
      "loss": 2.3933,
      "step": 10
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9545040627715554e-05,
      "loss": 2.2902,
      "step": 11
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.942536154525673e-05,
      "loss": 2.256,
      "step": 12
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9292180723175656e-05,
      "loss": 2.2393,
      "step": 13
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9145688941717074e-05,
      "loss": 2.1966,
      "step": 14
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.8986096048946826e-05,
      "loss": 2.1219,
      "step": 15
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.881363066014649e-05,
      "loss": 1.9816,
      "step": 16
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.862853983032423e-05,
      "loss": 2.1136,
      "step": 17
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8431088700310846e-05,
      "loss": 2.0719,
      "step": 18
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8221560116948103e-05,
      "loss": 2.009,
      "step": 19
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8000254227913346e-05,
      "loss": 1.9665,
      "step": 20
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7767488051760858e-05,
      "loss": 1.9006,
      "step": 21
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7523595023795814e-05,
      "loss": 1.9061,
      "step": 22
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7268924518431437e-05,
      "loss": 1.8054,
      "step": 23
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.700384134871351e-05,
      "loss": 1.9808,
      "step": 24
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.672872524372919e-05,
      "loss": 1.9158,
      "step": 25
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.644397030464877e-05,
      "loss": 1.8382,
      "step": 26
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.614998444017954e-05,
      "loss": 1.8274,
      "step": 27
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.5847188782240473e-05,
      "loss": 1.745,
      "step": 28
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.5536017082694846e-05,
      "loss": 1.7769,
      "step": 29
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.5216915092004847e-05,
      "loss": 1.9155,
      "step": 30
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.4890339920698334e-05,
      "loss": 1.7167,
      "step": 31
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.4556759384562418e-05,
      "loss": 1.8109,
      "step": 32
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.421665133450184e-05,
      "loss": 1.6917,
      "step": 33
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.3870502972022175e-05,
      "loss": 1.6803,
      "step": 34
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.351881015131833e-05,
      "loss": 1.6432,
      "step": 35
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.316207666896824e-05,
      "loss": 1.71,
      "step": 36
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2800813542249073e-05,
      "loss": 1.732,
      "step": 37
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.2435538277109919e-05,
      "loss": 1.7514,
      "step": 38
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.206677412684953e-05,
      "loss": 1.7247,
      "step": 39
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1695049342560969e-05,
      "loss": 1.6718,
      "step": 40
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.1320896416417026e-05,
      "loss": 1.7548,
      "step": 41
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0944851318880314e-05,
      "loss": 1.7024,
      "step": 42
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0567452730930743e-05,
      "loss": 1.56,
      "step": 43
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0189241272410191e-05,
      "loss": 1.6043,
      "step": 44
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.810758727589814e-06,
      "loss": 1.69,
      "step": 45
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.43254726906926e-06,
      "loss": 1.5612,
      "step": 46
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.055148681119688e-06,
      "loss": 1.6349,
      "step": 47
    },
    {
      "epoch": 1.1,
      "learning_rate": 8.67910358358298e-06,
      "loss": 1.6196,
      "step": 48
    },
    {
      "epoch": 1.12,
      "learning_rate": 8.304950657439034e-06,
      "loss": 1.6262,
      "step": 49
    },
    {
      "epoch": 1.14,
      "learning_rate": 7.93322587315047e-06,
      "loss": 1.5572,
      "step": 50
    },
    {
      "epoch": 1.17,
      "learning_rate": 7.564461722890082e-06,
      "loss": 1.6005,
      "step": 51
    },
    {
      "epoch": 1.19,
      "learning_rate": 7.199186457750931e-06,
      "loss": 1.3992,
      "step": 52
    },
    {
      "epoch": 1.21,
      "learning_rate": 6.837923331031761e-06,
      "loss": 1.6098,
      "step": 53
    },
    {
      "epoch": 1.23,
      "learning_rate": 6.48118984868167e-06,
      "loss": 1.5493,
      "step": 54
    },
    {
      "epoch": 1.26,
      "learning_rate": 6.129497027977829e-06,
      "loss": 1.5581,
      "step": 55
    },
    {
      "epoch": 1.28,
      "learning_rate": 5.78334866549816e-06,
      "loss": 1.5138,
      "step": 56
    },
    {
      "epoch": 1.3,
      "learning_rate": 5.443240615437586e-06,
      "loss": 1.6091,
      "step": 57
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.109660079301668e-06,
      "loss": 1.5832,
      "step": 58
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.783084907995156e-06,
      "loss": 1.531,
      "step": 59
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.463982917305155e-06,
      "loss": 1.4781,
      "step": 60
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.152811217759529e-06,
      "loss": 1.5776,
      "step": 61
    },
    {
      "epoch": 1.42,
      "learning_rate": 3.850015559820465e-06,
      "loss": 1.617,
      "step": 62
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.5560296953512296e-06,
      "loss": 1.4925,
      "step": 63
    },
    {
      "epoch": 1.46,
      "learning_rate": 3.2712747562708115e-06,
      "loss": 1.538,
      "step": 64
    },
    {
      "epoch": 1.49,
      "learning_rate": 2.9961586512864947e-06,
      "loss": 1.5641,
      "step": 65
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.7310754815685627e-06,
      "loss": 1.4769,
      "step": 66
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.4764049762041874e-06,
      "loss": 1.5378,
      "step": 67
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.2325119482391466e-06,
      "loss": 1.4627,
      "step": 68
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.9997457720866554e-06,
      "loss": 1.5337,
      "step": 69
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.7784398830519002e-06,
      "loss": 1.5069,
      "step": 70
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.5689112996891576e-06,
      "loss": 1.467,
      "step": 71
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3714601696757713e-06,
      "loss": 1.5326,
      "step": 72
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1863693398535115e-06,
      "loss": 1.5425,
      "step": 73
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.01390395105318e-06,
      "loss": 1.5971,
      "step": 74
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.543110582829272e-07,
      "loss": 1.5567,
      "step": 75
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.078192768243486e-07,
      "loss": 1.4339,
      "step": 76
    },
    {
      "epoch": 1.76,
      "learning_rate": 5.746384547432738e-07,
      "loss": 1.4543,
      "step": 77
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.549593722844492e-07,
      "loss": 1.4892,
      "step": 78
    },
    {
      "epoch": 1.81,
      "learning_rate": 3.4895346858066723e-07,
      "loss": 1.4933,
      "step": 79
    },
    {
      "epoch": 1.83,
      "learning_rate": 2.5677259606786686e-07,
      "loss": 1.5602,
      "step": 80
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.7854880295797406e-07,
      "loss": 1.5017,
      "step": 81
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.1439414408111471e-07,
      "loss": 1.5328,
      "step": 82
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.440052036815081e-08,
      "loss": 1.5076,
      "step": 83
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.86395472034795e-08,
      "loss": 1.4469,
      "step": 84
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.162451836685291e-09,
      "loss": 1.4975,
      "step": 85
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0,
      "loss": 1.4956,
      "step": 86
    },
    {
      "epoch": 1.97,
      "step": 86,
      "total_flos": 1.864529779831603e+16,
      "train_loss": 1.8037537461103395,
      "train_runtime": 866.9782,
      "train_samples_per_second": 12.918,
      "train_steps_per_second": 0.099
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 86,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 1.864529779831603e+16,
  "trial_name": null,
  "trial_params": null
}