{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.992481203007518,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 4.7948,
      "step": 5
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.882352941176471e-05,
      "loss": 4.6565,
      "step": 10
    },
    {
      "epoch": 0.45,
      "learning_rate": 8.823529411764706e-05,
      "loss": 4.2672,
      "step": 15
    },
    {
      "epoch": 0.6,
      "learning_rate": 9.997733473639876e-05,
      "loss": 3.8103,
      "step": 20
    },
    {
      "epoch": 0.75,
      "learning_rate": 9.983889919973586e-05,
      "loss": 3.4219,
      "step": 25
    },
    {
      "epoch": 0.9,
      "learning_rate": 9.957496810072027e-05,
      "loss": 3.2189,
      "step": 30
    },
    {
      "epoch": 0.99,
      "eval_loss": 3.00506591796875,
      "eval_runtime": 5.8168,
      "eval_samples_per_second": 76.331,
      "eval_steps_per_second": 19.083,
      "step": 33
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.918620602428915e-05,
      "loss": 3.1568,
      "step": 35
    },
    {
      "epoch": 1.21,
      "learning_rate": 9.867359188282192e-05,
      "loss": 2.8976,
      "step": 40
    },
    {
      "epoch": 1.36,
      "learning_rate": 9.803841645121504e-05,
      "loss": 2.8159,
      "step": 45
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.728227911667934e-05,
      "loss": 2.7279,
      "step": 50
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.640708385144403e-05,
      "loss": 2.6442,
      "step": 55
    },
    {
      "epoch": 1.81,
      "learning_rate": 9.541503441850843e-05,
      "loss": 2.5975,
      "step": 60
    },
    {
      "epoch": 1.96,
      "learning_rate": 9.430862882251278e-05,
      "loss": 2.5466,
      "step": 65
    },
    {
      "epoch": 1.99,
      "eval_loss": 2.5214502811431885,
      "eval_runtime": 5.9909,
      "eval_samples_per_second": 74.113,
      "eval_steps_per_second": 18.528,
      "step": 66
    },
    {
      "epoch": 2.12,
      "learning_rate": 9.309065301970193e-05,
      "loss": 2.6158,
      "step": 70
    },
    {
      "epoch": 2.27,
      "learning_rate": 9.176417390281944e-05,
      "loss": 2.4248,
      "step": 75
    },
    {
      "epoch": 2.42,
      "learning_rate": 9.033253157859714e-05,
      "loss": 2.3915,
      "step": 80
    },
    {
      "epoch": 2.57,
      "learning_rate": 8.879933095728485e-05,
      "loss": 2.3519,
      "step": 85
    },
    {
      "epoch": 2.72,
      "learning_rate": 8.716843267539869e-05,
      "loss": 2.3216,
      "step": 90
    },
    {
      "epoch": 2.87,
      "learning_rate": 8.544394337454409e-05,
      "loss": 2.2791,
      "step": 95
    },
    {
      "epoch": 2.99,
      "eval_loss": 2.2881205081939697,
      "eval_runtime": 6.1549,
      "eval_samples_per_second": 72.138,
      "eval_steps_per_second": 18.034,
      "step": 99
    },
    {
      "epoch": 3.03,
      "learning_rate": 8.363020536079239e-05,
      "loss": 2.3846,
      "step": 100
    },
    {
      "epoch": 3.18,
      "learning_rate": 8.17317856706482e-05,
      "loss": 2.2154,
      "step": 105
    },
    {
      "epoch": 3.33,
      "learning_rate": 7.975346457114034e-05,
      "loss": 2.1769,
      "step": 110
    },
    {
      "epoch": 3.48,
      "learning_rate": 7.770022352299293e-05,
      "loss": 2.1613,
      "step": 115
    },
    {
      "epoch": 3.63,
      "learning_rate": 7.557723263718596e-05,
      "loss": 2.1198,
      "step": 120
    },
    {
      "epoch": 3.78,
      "learning_rate": 7.338983765648985e-05,
      "loss": 2.1125,
      "step": 125
    },
    {
      "epoch": 3.93,
      "learning_rate": 7.114354649475499e-05,
      "loss": 2.107,
      "step": 130
    },
    {
      "epoch": 3.99,
      "eval_loss": 2.1322436332702637,
      "eval_runtime": 5.9353,
      "eval_samples_per_second": 74.807,
      "eval_steps_per_second": 18.702,
      "step": 132
    },
    {
      "epoch": 4.09,
      "learning_rate": 6.884401536785045e-05,
      "loss": 2.1638,
      "step": 135
    },
    {
      "epoch": 4.24,
      "learning_rate": 6.649703455117458e-05,
      "loss": 2.0297,
      "step": 140
    },
    {
      "epoch": 4.39,
      "learning_rate": 6.41085137996006e-05,
      "loss": 1.9982,
      "step": 145
    },
    {
      "epoch": 4.54,
      "learning_rate": 6.168446746656973e-05,
      "loss": 1.9981,
      "step": 150
    },
    {
      "epoch": 4.69,
      "learning_rate": 5.9230999359802784e-05,
      "loss": 1.9916,
      "step": 155
    },
    {
      "epoch": 4.84,
      "learning_rate": 5.675428737176367e-05,
      "loss": 1.9654,
      "step": 160
    },
    {
      "epoch": 4.99,
      "learning_rate": 5.426056792357551e-05,
      "loss": 1.9458,
      "step": 165
    },
    {
      "epoch": 4.99,
      "eval_loss": 2.02701735496521,
      "eval_runtime": 6.09,
      "eval_samples_per_second": 72.906,
      "eval_steps_per_second": 18.227,
      "step": 165
    },
    {
      "epoch": 5.15,
      "learning_rate": 5.1756120261560446e-05,
      "loss": 2.0128,
      "step": 170
    },
    {
      "epoch": 5.3,
      "learning_rate": 4.924725064594447e-05,
      "loss": 1.9078,
      "step": 175
    },
    {
      "epoch": 5.45,
      "learning_rate": 4.674027647154037e-05,
      "loss": 1.8843,
      "step": 180
    },
    {
      "epoch": 5.6,
      "learning_rate": 4.4241510360393804e-05,
      "loss": 1.8944,
      "step": 185
    },
    {
      "epoch": 5.75,
      "learning_rate": 4.1757244266447245e-05,
      "loss": 1.8812,
      "step": 190
    },
    {
      "epoch": 5.9,
      "learning_rate": 3.9293733632246544e-05,
      "loss": 1.8664,
      "step": 195
    },
    {
      "epoch": 5.99,
      "eval_loss": 1.9580020904541016,
      "eval_runtime": 5.9675,
      "eval_samples_per_second": 74.403,
      "eval_steps_per_second": 18.601,
      "step": 198
    },
    {
      "epoch": 6.06,
      "learning_rate": 3.685718163758427e-05,
      "loss": 1.9469,
      "step": 200
    },
    {
      "epoch": 6.21,
      "learning_rate": 3.445372357974194e-05,
      "loss": 1.8484,
      "step": 205
    },
    {
      "epoch": 6.36,
      "learning_rate": 3.208941142466187e-05,
      "loss": 1.8128,
      "step": 210
    },
    {
      "epoch": 6.51,
      "learning_rate": 2.9770198567949546e-05,
      "loss": 1.8096,
      "step": 215
    },
    {
      "epoch": 6.66,
      "learning_rate": 2.7501924844078534e-05,
      "loss": 1.8189,
      "step": 220
    },
    {
      "epoch": 6.81,
      "learning_rate": 2.5290301821544825e-05,
      "loss": 1.8172,
      "step": 225
    },
    {
      "epoch": 6.96,
      "learning_rate": 2.3140898420998426e-05,
      "loss": 1.8083,
      "step": 230
    },
    {
      "epoch": 6.99,
      "eval_loss": 1.9176976680755615,
      "eval_runtime": 6.163,
      "eval_samples_per_second": 72.043,
      "eval_steps_per_second": 18.011,
      "step": 231
    },
    {
      "epoch": 7.12,
      "learning_rate": 2.105912689256533e-05,
      "loss": 1.8905,
      "step": 235
    },
    {
      "epoch": 7.27,
      "learning_rate": 1.905022918766995e-05,
      "loss": 1.7894,
      "step": 240
    },
    {
      "epoch": 7.42,
      "learning_rate": 1.7119263759673675e-05,
      "loss": 1.7816,
      "step": 245
    },
    {
      "epoch": 7.57,
      "learning_rate": 1.527109282656611e-05,
      "loss": 1.7818,
      "step": 250
    },
    {
      "epoch": 7.72,
      "learning_rate": 1.3510370127781635e-05,
      "loss": 1.7792,
      "step": 255
    },
    {
      "epoch": 7.87,
      "learning_rate": 1.184152920597028e-05,
      "loss": 1.7631,
      "step": 260
    },
    {
      "epoch": 7.99,
      "eval_loss": 1.896404504776001,
      "eval_runtime": 6.0238,
      "eval_samples_per_second": 73.708,
      "eval_steps_per_second": 18.427,
      "step": 264
    },
    {
      "epoch": 8.03,
      "learning_rate": 1.026877224322923e-05,
      "loss": 1.8595,
      "step": 265
    },
    {
      "epoch": 8.18,
      "learning_rate": 8.7960594799059e-06,
      "loss": 1.7476,
      "step": 270
    },
    {
      "epoch": 8.33,
      "learning_rate": 7.427099242616348e-06,
      "loss": 1.7775,
      "step": 275
    },
    {
      "epoch": 8.48,
      "learning_rate": 6.1653386065885165e-06,
      "loss": 1.7544,
      "step": 280
    },
    {
      "epoch": 8.63,
      "learning_rate": 5.0139547158427e-06,
      "loss": 1.7617,
      "step": 285
    },
    {
      "epoch": 8.78,
      "learning_rate": 3.975846783065662e-06,
      "loss": 1.7706,
      "step": 290
    },
    {
      "epoch": 8.93,
      "learning_rate": 3.0536287893223604e-06,
      "loss": 1.7369,
      "step": 295
    },
    {
      "epoch": 8.99,
      "eval_loss": 1.8884940147399902,
      "eval_runtime": 5.932,
      "eval_samples_per_second": 74.849,
      "eval_steps_per_second": 18.712,
      "step": 297
    },
    {
      "epoch": 9.09,
      "learning_rate": 2.249622901987963e-06,
      "loss": 1.8462,
      "step": 300
    },
    {
      "epoch": 9.24,
      "learning_rate": 1.5658536274738621e-06,
      "loss": 1.7371,
      "step": 305
    },
    {
      "epoch": 9.39,
      "learning_rate": 1.004042713471165e-06,
      "loss": 1.7526,
      "step": 310
    },
    {
      "epoch": 9.54,
      "learning_rate": 5.656048135480763e-07,
      "loss": 1.7684,
      "step": 315
    },
    {
      "epoch": 9.69,
      "learning_rate": 2.5164392501777487e-07,
      "loss": 1.7508,
      "step": 320
    },
    {
      "epoch": 9.84,
      "learning_rate": 6.295060904623617e-08,
      "loss": 1.7465,
      "step": 325
    },
    {
      "epoch": 9.99,
      "learning_rate": 0.0,
      "loss": 1.766,
      "step": 330
    },
    {
      "epoch": 9.99,
      "eval_loss": 1.887495756149292,
      "eval_runtime": 6.0398,
      "eval_samples_per_second": 73.513,
      "eval_steps_per_second": 18.378,
      "step": 330
    },
    {
      "epoch": 9.99,
      "step": 330,
      "total_flos": 2.2217230871691264e+16,
      "train_loss": 2.230022551796653,
      "train_runtime": 1073.0912,
      "train_samples_per_second": 79.36,
      "train_steps_per_second": 0.308
    }
  ],
  "max_steps": 330,
  "num_train_epochs": 10,
  "total_flos": 2.2217230871691264e+16,
  "trial_name": null,
  "trial_params": null
}