{
  "best_metric": 2.439748525619507,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 0.8014571948998178,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.8176,
      "step": 100
    },
    {
      "epoch": 0.07,
      "eval_loss": 2.7248005867004395,
      "eval_runtime": 204.526,
      "eval_samples_per_second": 30.676,
      "eval_steps_per_second": 3.838,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 2.6959,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 2.6743462085723877,
      "eval_runtime": 205.6888,
      "eval_samples_per_second": 30.502,
      "eval_steps_per_second": 3.816,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.6512,
      "step": 300
    },
    {
      "epoch": 0.22,
      "eval_loss": 2.6400036811828613,
      "eval_runtime": 204.5763,
      "eval_samples_per_second": 30.668,
      "eval_steps_per_second": 3.837,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 2.6241,
      "step": 400
    },
    {
      "epoch": 0.29,
      "eval_loss": 2.6055357456207275,
      "eval_runtime": 204.4295,
      "eval_samples_per_second": 30.69,
      "eval_steps_per_second": 3.84,
      "step": 400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.5812,
      "step": 500
    },
    {
      "epoch": 0.36,
      "eval_loss": 2.5787856578826904,
      "eval_runtime": 204.1968,
      "eval_samples_per_second": 30.725,
      "eval_steps_per_second": 3.844,
      "step": 500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.553,
      "step": 600
    },
    {
      "epoch": 0.44,
      "eval_loss": 2.552586555480957,
      "eval_runtime": 204.5367,
      "eval_samples_per_second": 30.674,
      "eval_steps_per_second": 3.838,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.5368,
      "step": 700
    },
    {
      "epoch": 0.51,
      "eval_loss": 2.527393341064453,
      "eval_runtime": 204.8117,
      "eval_samples_per_second": 30.633,
      "eval_steps_per_second": 3.833,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.5124,
      "step": 800
    },
    {
      "epoch": 0.58,
      "eval_loss": 2.506849527359009,
      "eval_runtime": 204.0454,
      "eval_samples_per_second": 30.748,
      "eval_steps_per_second": 3.847,
      "step": 800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.4756,
      "step": 900
    },
    {
      "epoch": 0.66,
      "eval_loss": 2.4826207160949707,
      "eval_runtime": 204.4447,
      "eval_samples_per_second": 30.688,
      "eval_steps_per_second": 3.84,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 2.4724,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "eval_loss": 2.463895559310913,
      "eval_runtime": 204.6362,
      "eval_samples_per_second": 30.659,
      "eval_steps_per_second": 3.836,
      "step": 1000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.4666,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "eval_loss": 2.439748525619507,
      "eval_runtime": 204.5892,
      "eval_samples_per_second": 30.666,
      "eval_steps_per_second": 3.837,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 4116,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 3.13118620803072e+16,
  "trial_name": null,
  "trial_params": null
}