{
  "best_metric": 2.080679416656494,
  "best_model_checkpoint": "experiments/checkpoint-30",
  "epoch": 7.529411764705882,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 3.069,
      "step": 10
    },
    {
      "epoch": 0.75,
      "eval_loss": 2.506248712539673,
      "eval_runtime": 36.514,
      "eval_samples_per_second": 5.477,
      "eval_steps_per_second": 0.685,
      "step": 10
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002666666666666666,
      "loss": 2.2982,
      "step": 20
    },
    {
      "epoch": 1.51,
      "eval_loss": 2.081218957901001,
      "eval_runtime": 36.5059,
      "eval_samples_per_second": 5.479,
      "eval_steps_per_second": 0.685,
      "step": 20
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002333333333333333,
      "loss": 2.1043,
      "step": 30
    },
    {
      "epoch": 2.26,
      "eval_loss": 2.080679416656494,
      "eval_runtime": 36.4738,
      "eval_samples_per_second": 5.483,
      "eval_steps_per_second": 0.685,
      "step": 30
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00019999999999999998,
      "loss": 2.1125,
      "step": 40
    },
    {
      "epoch": 3.01,
      "eval_loss": 2.0814473628997803,
      "eval_runtime": 36.4244,
      "eval_samples_per_second": 5.491,
      "eval_steps_per_second": 0.686,
      "step": 40
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.00016666666666666666,
      "loss": 2.1094,
      "step": 50
    },
    {
      "epoch": 3.76,
      "eval_loss": 2.081106662750244,
      "eval_runtime": 36.5033,
      "eval_samples_per_second": 5.479,
      "eval_steps_per_second": 0.685,
      "step": 50
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0001333333333333333,
      "loss": 2.1128,
      "step": 60
    },
    {
      "epoch": 4.52,
      "eval_loss": 2.0811569690704346,
      "eval_runtime": 36.4577,
      "eval_samples_per_second": 5.486,
      "eval_steps_per_second": 0.686,
      "step": 60
    },
    {
      "epoch": 5.27,
      "learning_rate": 9.999999999999999e-05,
      "loss": 2.1102,
      "step": 70
    },
    {
      "epoch": 5.27,
      "eval_loss": 2.0808606147766113,
      "eval_runtime": 36.4061,
      "eval_samples_per_second": 5.494,
      "eval_steps_per_second": 0.687,
      "step": 70
    },
    {
      "epoch": 6.02,
      "learning_rate": 6.666666666666666e-05,
      "loss": 2.1057,
      "step": 80
    },
    {
      "epoch": 6.02,
      "eval_loss": 2.081094741821289,
      "eval_runtime": 36.535,
      "eval_samples_per_second": 5.474,
      "eval_steps_per_second": 0.684,
      "step": 80
    },
    {
      "epoch": 6.78,
      "learning_rate": 3.333333333333333e-05,
      "loss": 2.1069,
      "step": 90
    },
    {
      "epoch": 6.78,
      "eval_loss": 2.0808064937591553,
      "eval_runtime": 36.4018,
      "eval_samples_per_second": 5.494,
      "eval_steps_per_second": 0.687,
      "step": 90
    },
    {
      "epoch": 7.53,
      "learning_rate": 0.0,
      "loss": 2.1147,
      "step": 100
    },
    {
      "epoch": 7.53,
      "eval_loss": 2.0808823108673096,
      "eval_runtime": 36.4455,
      "eval_samples_per_second": 5.488,
      "eval_steps_per_second": 0.686,
      "step": 100
    }
  ],
  "max_steps": 100,
  "num_train_epochs": 8,
  "total_flos": 6.900128905592832e+16,
  "trial_name": null,
  "trial_params": null
}