{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "global_step": 35000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 1.5146,
      "step": 500
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.1216,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.88e-05,
      "loss": 1.0414,
      "step": 1500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.0385,
      "step": 2000
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.8e-05,
      "loss": 1.0463,
      "step": 2500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.76e-05,
      "loss": 1.0464,
      "step": 3000
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.72e-05,
      "loss": 1.0343,
      "step": 3500
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.0375,
      "step": 4000
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.64e-05,
      "loss": 1.0389,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0303,
      "step": 5000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9517383575439453,
      "eval_runtime": 520.9725,
      "eval_samples_per_second": 19.195,
      "eval_steps_per_second": 2.399,
      "step": 5000
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 1.0216,
      "step": 5500
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.0131,
      "step": 6000
    },
    {
      "epoch": 1.3,
      "learning_rate": 1.48e-05,
      "loss": 1.0193,
      "step": 6500
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.0079,
      "step": 7000
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.4e-05,
      "loss": 1.0117,
      "step": 7500
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.0169,
      "step": 8000
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 1.0274,
      "step": 8500
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.0096,
      "step": 9000
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 1.009,
      "step": 9500
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 1.01,
      "step": 10000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9439992308616638,
      "eval_runtime": 529.1205,
      "eval_samples_per_second": 18.899,
      "eval_steps_per_second": 2.362,
      "step": 10000
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.16e-05,
      "loss": 0.9979,
      "step": 10500
    },
    {
      "epoch": 2.2,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.9961,
      "step": 11000
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 0.9941,
      "step": 11500
    },
    {
      "epoch": 2.4,
      "learning_rate": 1.04e-05,
      "loss": 0.9823,
      "step": 12000
    },
    {
      "epoch": 2.5,
      "learning_rate": 1e-05,
      "loss": 0.9886,
      "step": 12500
    },
    {
      "epoch": 2.6,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.9784,
      "step": 13000
    },
    {
      "epoch": 2.7,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.9931,
      "step": 13500
    },
    {
      "epoch": 2.8,
      "learning_rate": 8.8e-06,
      "loss": 0.9944,
      "step": 14000
    },
    {
      "epoch": 2.9,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.9873,
      "step": 14500
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9898,
      "step": 15000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9317747950553894,
      "eval_runtime": 529.6801,
      "eval_samples_per_second": 18.879,
      "eval_steps_per_second": 2.36,
      "step": 15000
    },
    {
      "epoch": 3.1,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.9791,
      "step": 15500
    },
    {
      "epoch": 3.2,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.9821,
      "step": 16000
    },
    {
      "epoch": 3.3,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.9809,
      "step": 16500
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.9701,
      "step": 17000
    },
    {
      "epoch": 3.5,
      "learning_rate": 6e-06,
      "loss": 0.9783,
      "step": 17500
    },
    {
      "epoch": 3.6,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.9763,
      "step": 18000
    },
    {
      "epoch": 3.7,
      "learning_rate": 5.2e-06,
      "loss": 0.9631,
      "step": 18500
    },
    {
      "epoch": 3.8,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.973,
      "step": 19000
    },
    {
      "epoch": 3.9,
      "learning_rate": 4.4e-06,
      "loss": 0.9688,
      "step": 19500
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.9788,
      "step": 20000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9208911061286926,
      "eval_runtime": 528.6017,
      "eval_samples_per_second": 18.918,
      "eval_steps_per_second": 2.365,
      "step": 20000
    },
    {
      "epoch": 4.1,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.9695,
      "step": 20500
    },
    {
      "epoch": 4.2,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.9725,
      "step": 21000
    },
    {
      "epoch": 4.3,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.9606,
      "step": 21500
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.9611,
      "step": 22000
    },
    {
      "epoch": 4.5,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9511,
      "step": 22500
    },
    {
      "epoch": 4.6,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.9571,
      "step": 23000
    },
    {
      "epoch": 4.7,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.9661,
      "step": 23500
    },
    {
      "epoch": 4.8,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.9566,
      "step": 24000
    },
    {
      "epoch": 4.9,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.9647,
      "step": 24500
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.9692,
      "step": 25000
    },
    {
      "epoch": 5.1,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.9756,
      "step": 25500
    },
    {
      "epoch": 5.2,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.9775,
      "step": 26000
    },
    {
      "epoch": 5.3,
      "learning_rate": 9.4e-06,
      "loss": 0.9843,
      "step": 26500
    },
    {
      "epoch": 5.4,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.9883,
      "step": 27000
    },
    {
      "epoch": 5.5,
      "learning_rate": 9e-06,
      "loss": 0.976,
      "step": 27500
    },
    {
      "epoch": 5.6,
      "learning_rate": 8.8e-06,
      "loss": 0.98,
      "step": 28000
    },
    {
      "epoch": 5.7,
      "learning_rate": 8.6e-06,
      "loss": 0.9807,
      "step": 28500
    },
    {
      "epoch": 5.8,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.985,
      "step": 29000
    },
    {
      "epoch": 5.9,
      "learning_rate": 8.2e-06,
      "loss": 0.9655,
      "step": 29500
    },
    {
      "epoch": 6.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.974,
      "step": 30000
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.8957818150520325,
      "eval_runtime": 248.7642,
      "eval_samples_per_second": 40.199,
      "eval_steps_per_second": 5.025,
      "step": 30000
    },
    {
      "epoch": 6.1,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.976,
      "step": 30500
    },
    {
      "epoch": 6.2,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.9739,
      "step": 31000
    },
    {
      "epoch": 6.3,
      "learning_rate": 7.4e-06,
      "loss": 0.9668,
      "step": 31500
    },
    {
      "epoch": 6.4,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.9691,
      "step": 32000
    },
    {
      "epoch": 6.5,
      "learning_rate": 7e-06,
      "loss": 0.9734,
      "step": 32500
    },
    {
      "epoch": 6.6,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.9722,
      "step": 33000
    },
    {
      "epoch": 6.7,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.9738,
      "step": 33500
    },
    {
      "epoch": 6.8,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.9701,
      "step": 34000
    },
    {
      "epoch": 6.9,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.9596,
      "step": 34500
    },
    {
      "epoch": 7.0,
      "learning_rate": 6e-06,
      "loss": 0.9628,
      "step": 35000
    }
  ],
  "max_steps": 50000,
  "num_train_epochs": 10,
  "total_flos": 7.371432972288e+16,
  "trial_name": null,
  "trial_params": null
}