{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14367816091954022,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 2.5367,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.3695,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.2916,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7865,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.4162,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.3012,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.2177,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.1726,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.1367,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012857142857142858,
      "loss": 1.105,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.0671,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.0583,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.0278,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.0297,
      "step": 65
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.0224,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001999685197404432,
      "loss": 1.0077,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019987409878190752,
      "loss": 1.0135,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019971679657231872,
      "loss": 0.9836,
      "step": 85
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019949671214996445,
      "loss": 1.0012,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019921398408113955,
      "loss": 0.9927,
      "step": 95
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019886879037290384,
      "loss": 0.9966,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 696,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7.003463853749043e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}