{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.9984,
  "global_step": 6240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.4537074565887451,
      "eval_mse": 0.45370742678642273,
      "eval_runtime": 6.2981,
      "eval_samples_per_second": 158.779,
      "eval_steps_per_second": 19.847,
      "step": 312
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.3457813907586236e-05,
      "loss": 0.6153,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.19009532034397125,
      "eval_mse": 0.19009532034397125,
      "eval_runtime": 6.3224,
      "eval_samples_per_second": 158.167,
      "eval_steps_per_second": 19.771,
      "step": 624
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2025919258594513,
      "eval_mse": 0.2025919258594513,
      "eval_runtime": 6.3503,
      "eval_samples_per_second": 157.472,
      "eval_steps_per_second": 19.684,
      "step": 936
    },
    {
      "epoch": 3.2,
      "learning_rate": 1.2285530466158863e-05,
      "loss": 0.1584,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.2967708110809326,
      "eval_mse": 0.2967708110809326,
      "eval_runtime": 6.3822,
      "eval_samples_per_second": 156.686,
      "eval_steps_per_second": 19.586,
      "step": 1248
    },
    {
      "epoch": 4.81,
      "learning_rate": 1.1113247024731491e-05,
      "loss": 0.0958,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.2692314684391022,
      "eval_mse": 0.2692314386367798,
      "eval_runtime": 6.3165,
      "eval_samples_per_second": 158.314,
      "eval_steps_per_second": 19.789,
      "step": 1560
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.2646154761314392,
      "eval_mse": 0.2646154761314392,
      "eval_runtime": 6.321,
      "eval_samples_per_second": 158.204,
      "eval_steps_per_second": 19.775,
      "step": 1872
    },
    {
      "epoch": 6.41,
      "learning_rate": 9.940963583304119e-06,
      "loss": 0.0605,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.3655566871166229,
      "eval_mse": 0.3655566871166229,
      "eval_runtime": 6.4015,
      "eval_samples_per_second": 156.213,
      "eval_steps_per_second": 19.527,
      "step": 2184
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.3432270586490631,
      "eval_mse": 0.3432270586490631,
      "eval_runtime": 6.4193,
      "eval_samples_per_second": 155.78,
      "eval_steps_per_second": 19.473,
      "step": 2496
    },
    {
      "epoch": 8.01,
      "learning_rate": 8.768680141876746e-06,
      "loss": 0.0448,
      "step": 2500
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.29013848304748535,
      "eval_mse": 0.29013848304748535,
      "eval_runtime": 6.369,
      "eval_samples_per_second": 157.01,
      "eval_steps_per_second": 19.626,
      "step": 2808
    },
    {
      "epoch": 9.61,
      "learning_rate": 7.596396700449374e-06,
      "loss": 0.0328,
      "step": 3000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.23616179823875427,
      "eval_mse": 0.23616181313991547,
      "eval_runtime": 6.3278,
      "eval_samples_per_second": 158.032,
      "eval_steps_per_second": 19.754,
      "step": 3120
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.23755905032157898,
      "eval_mse": 0.23755905032157898,
      "eval_runtime": 6.3847,
      "eval_samples_per_second": 156.626,
      "eval_steps_per_second": 19.578,
      "step": 3432
    },
    {
      "epoch": 11.22,
      "learning_rate": 6.424113259022001e-06,
      "loss": 0.0286,
      "step": 3500
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.23381923139095306,
      "eval_mse": 0.23381923139095306,
      "eval_runtime": 6.3781,
      "eval_samples_per_second": 156.787,
      "eval_steps_per_second": 19.598,
      "step": 3744
    },
    {
      "epoch": 12.82,
      "learning_rate": 5.2518298175946285e-06,
      "loss": 0.0243,
      "step": 4000
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.2918383777141571,
      "eval_mse": 0.2918383777141571,
      "eval_runtime": 6.3488,
      "eval_samples_per_second": 157.51,
      "eval_steps_per_second": 19.689,
      "step": 4056
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.26574844121932983,
      "eval_mse": 0.26574844121932983,
      "eval_runtime": 6.3063,
      "eval_samples_per_second": 158.572,
      "eval_steps_per_second": 19.822,
      "step": 4368
    },
    {
      "epoch": 14.42,
      "learning_rate": 4.079546376167256e-06,
      "loss": 0.021,
      "step": 4500
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.2649979293346405,
      "eval_mse": 0.2649979293346405,
      "eval_runtime": 6.3763,
      "eval_samples_per_second": 156.832,
      "eval_steps_per_second": 19.604,
      "step": 4680
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.2675020396709442,
      "eval_mse": 0.2675020396709442,
      "eval_runtime": 6.2951,
      "eval_samples_per_second": 158.855,
      "eval_steps_per_second": 19.857,
      "step": 4992
    },
    {
      "epoch": 16.03,
      "learning_rate": 2.9072629347398834e-06,
      "loss": 0.019,
      "step": 5000
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.2602880895137787,
      "eval_mse": 0.2602880895137787,
      "eval_runtime": 6.3892,
      "eval_samples_per_second": 156.515,
      "eval_steps_per_second": 19.564,
      "step": 5304
    },
    {
      "epoch": 17.63,
      "learning_rate": 1.734979493312511e-06,
      "loss": 0.0165,
      "step": 5500
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.2324579656124115,
      "eval_mse": 0.2324579656124115,
      "eval_runtime": 6.3476,
      "eval_samples_per_second": 157.541,
      "eval_steps_per_second": 19.693,
      "step": 5616
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.24971328675746918,
      "eval_mse": 0.24971328675746918,
      "eval_runtime": 6.3218,
      "eval_samples_per_second": 158.182,
      "eval_steps_per_second": 19.773,
      "step": 5928
    },
    {
      "epoch": 19.23,
      "learning_rate": 5.626960518851388e-07,
      "loss": 0.015,
      "step": 6000
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.24272866547107697,
      "eval_mse": 0.24272866547107697,
      "eval_runtime": 6.3685,
      "eval_samples_per_second": 157.022,
      "eval_steps_per_second": 19.628,
      "step": 6240
    },
    {
      "epoch": 20.0,
      "step": 6240,
      "total_flos": 6577309062776832.0,
      "train_loss": 0.09126096031604669,
      "train_runtime": 4399.0118,
      "train_samples_per_second": 22.732,
      "train_steps_per_second": 1.419
    }
  ],
  "max_steps": 6240,
  "num_train_epochs": 20,
  "total_flos": 6577309062776832.0,
  "trial_name": null,
  "trial_params": null
}