{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 34028,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.46e-06,
      "loss": 1.4943,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.96e-06,
      "loss": 1.4172,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.4600000000000006e-06,
      "loss": 1.3694,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.96e-06,
      "loss": 1.3653,
      "step": 2000
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2460000000000001e-05,
      "loss": 1.3572,
      "step": 2500
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.4960000000000002e-05,
      "loss": 1.3499,
      "step": 3000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.7460000000000002e-05,
      "loss": 1.347,
      "step": 3500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9960000000000002e-05,
      "loss": 1.3345,
      "step": 4000
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.2460000000000002e-05,
      "loss": 1.3558,
      "step": 4500
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.496e-05,
      "loss": 1.3837,
      "step": 5000
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.746e-05,
      "loss": 1.3784,
      "step": 5500
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.9959999999999998e-05,
      "loss": 1.3708,
      "step": 6000
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.2460000000000004e-05,
      "loss": 1.3762,
      "step": 6500
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.4960000000000004e-05,
      "loss": 1.3771,
      "step": 7000
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.7460000000000004e-05,
      "loss": 1.391,
      "step": 7500
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.9960000000000004e-05,
      "loss": 1.3875,
      "step": 8000
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.246e-05,
      "loss": 1.3885,
      "step": 8500
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.496e-05,
      "loss": 1.4058,
      "step": 9000
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.746e-05,
      "loss": 1.4011,
      "step": 9500
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.996e-05,
      "loss": 1.4199,
      "step": 10000
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.897619443982021e-05,
      "loss": 1.427,
      "step": 10500
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.793782254036957e-05,
      "loss": 1.4302,
      "step": 11000
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.689736973530881e-05,
      "loss": 1.4189,
      "step": 11500
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.585899783585817e-05,
      "loss": 1.4264,
      "step": 12000
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.482062593640753e-05,
      "loss": 1.4302,
      "step": 12500
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.378017313134676e-05,
      "loss": 1.4285,
      "step": 13000
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.2739720326286004e-05,
      "loss": 1.4212,
      "step": 13500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.169926752122524e-05,
      "loss": 1.4084,
      "step": 14000
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.0662976527384723e-05,
      "loss": 1.4326,
      "step": 14500
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.962252372232396e-05,
      "loss": 1.4097,
      "step": 15000
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.8582070917263196e-05,
      "loss": 1.4176,
      "step": 15500
    },
    {
      "epoch": 0.47,
      "learning_rate": 3.754161811220243e-05,
      "loss": 1.5707,
      "step": 16000
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.650324621275179e-05,
      "loss": 2.1501,
      "step": 16500
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.546279340769103e-05,
      "loss": 1.8142,
      "step": 17000
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.4422340602630264e-05,
      "loss": 1.744,
      "step": 17500
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.338188779756951e-05,
      "loss": 1.6689,
      "step": 18000
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.234143499250874e-05,
      "loss": 1.5661,
      "step": 18500
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.130098218744798e-05,
      "loss": 1.4991,
      "step": 19000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.0260529382387215e-05,
      "loss": 1.4968,
      "step": 19500
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.9220076577326455e-05,
      "loss": 1.4586,
      "step": 20000
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.817962377226569e-05,
      "loss": 1.4327,
      "step": 20500
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.713917096720493e-05,
      "loss": 1.4172,
      "step": 21000
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.6098718162144163e-05,
      "loss": 1.4046,
      "step": 21500
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5058265357083406e-05,
      "loss": 1.3867,
      "step": 22000
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.4017812552022643e-05,
      "loss": 1.3841,
      "step": 22500
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.297735974696188e-05,
      "loss": 1.4225,
      "step": 23000
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.1936906941901118e-05,
      "loss": 1.3852,
      "step": 23500
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.0896454136840354e-05,
      "loss": 1.3934,
      "step": 24000
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.985600133177959e-05,
      "loss": 1.3885,
      "step": 24500
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.881554852671883e-05,
      "loss": 1.3587,
      "step": 25000
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.7775095721658066e-05,
      "loss": 1.3546,
      "step": 25500
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6734642916597302e-05,
      "loss": 1.3435,
      "step": 26000
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.5694190111536542e-05,
      "loss": 1.3399,
      "step": 26500
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4657899117696022e-05,
      "loss": 1.3495,
      "step": 27000
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.361744631263526e-05,
      "loss": 1.3294,
      "step": 27500
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2576993507574498e-05,
      "loss": 1.3455,
      "step": 28000
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1536540702513734e-05,
      "loss": 1.3348,
      "step": 28500
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0496087897452972e-05,
      "loss": 1.3474,
      "step": 29000
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.45563509239221e-06,
      "loss": 1.3358,
      "step": 29500
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.415182287331448e-06,
      "loss": 1.3323,
      "step": 30000
    },
    {
      "epoch": 0.9,
      "learning_rate": 7.3747294822706845e-06,
      "loss": 1.3319,
      "step": 30500
    },
    {
      "epoch": 0.91,
      "learning_rate": 6.336357582820044e-06,
      "loss": 1.3203,
      "step": 31000
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.297985683369403e-06,
      "loss": 1.3158,
      "step": 31500
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.259613783918762e-06,
      "loss": 1.3217,
      "step": 32000
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.219160978857999e-06,
      "loss": 1.3124,
      "step": 32500
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.1787081737972366e-06,
      "loss": 1.3074,
      "step": 33000
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1382553687364742e-06,
      "loss": 1.3234,
      "step": 33500
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.780256367571167e-08,
      "loss": 1.3078,
      "step": 34000
    },
    {
      "epoch": 1.0,
      "step": 34028,
      "total_flos": 3.4984777600575e+16,
      "train_loss": 1.4148471605151356,
      "train_runtime": 9789.6511,
      "train_samples_per_second": 27.807,
      "train_steps_per_second": 3.476
    }
  ],
  "max_steps": 34028,
  "num_train_epochs": 1,
  "total_flos": 3.4984777600575e+16,
  "trial_name": null,
  "trial_params": null
}