{
  "best_metric": 1.4297349452972412,
  "best_model_checkpoint": "./outputs/checkpoint-1000",
  "epoch": 1.3333333333333333,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4574,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.5645889043807983,
      "eval_runtime": 93.6488,
      "eval_samples_per_second": 15.494,
      "eval_steps_per_second": 1.943,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2971,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.5321934223175049,
      "eval_runtime": 93.3383,
      "eval_samples_per_second": 15.546,
      "eval_steps_per_second": 1.95,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.2756,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.5133259296417236,
      "eval_runtime": 93.2652,
      "eval_samples_per_second": 15.558,
      "eval_steps_per_second": 1.951,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.2661,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.500829815864563,
      "eval_runtime": 93.3122,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.2493,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.4804445505142212,
      "eval_runtime": 93.3662,
      "eval_samples_per_second": 15.541,
      "eval_steps_per_second": 1.949,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.2327,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.4673335552215576,
      "eval_runtime": 93.4173,
      "eval_samples_per_second": 15.532,
      "eval_steps_per_second": 1.948,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.2216,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.456375241279602,
      "eval_runtime": 93.4236,
      "eval_samples_per_second": 15.531,
      "eval_steps_per_second": 1.948,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.2086,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.4467251300811768,
      "eval_runtime": 93.3142,
      "eval_samples_per_second": 15.55,
      "eval_steps_per_second": 1.95,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.1922,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.4370195865631104,
      "eval_runtime": 93.2407,
      "eval_samples_per_second": 15.562,
      "eval_steps_per_second": 1.952,
      "step": 900
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.1859,
      "step": 1000
    },
    {
      "epoch": 1.33,
      "eval_loss": 1.4297349452972412,
      "eval_runtime": 93.4112,
      "eval_samples_per_second": 15.533,
      "eval_steps_per_second": 1.948,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.844782394372096e+16,
  "trial_name": null,
  "trial_params": null
}