{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9872340425531915,
  "eval_steps": 5,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 1.9849,
      "step": 1
    },
    {
      "epoch": 0.03,
      "eval_loss": 2.0810964107513428,
      "eval_runtime": 6.2278,
      "eval_samples_per_second": 44.96,
      "eval_steps_per_second": 5.62,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 4e-05,
      "loss": 1.8931,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 6e-05,
      "loss": 1.763,
      "step": 3
    },
    {
      "epoch": 0.14,
      "learning_rate": 8e-05,
      "loss": 1.6688,
      "step": 4
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.3107,
      "step": 5
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.1991726160049438,
      "eval_runtime": 6.3173,
      "eval_samples_per_second": 44.322,
      "eval_steps_per_second": 5.54,
      "step": 5
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012,
      "loss": 1.1899,
      "step": 6
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00014,
      "loss": 1.041,
      "step": 7
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016,
      "loss": 0.9779,
      "step": 8
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018,
      "loss": 0.7671,
      "step": 9
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.6399,
      "step": 10
    },
    {
      "epoch": 0.34,
      "eval_loss": 0.6359391212463379,
      "eval_runtime": 6.2721,
      "eval_samples_per_second": 44.642,
      "eval_steps_per_second": 5.58,
      "step": 10
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001999167799344583,
      "loss": 0.6777,
      "step": 11
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019966725824941932,
      "loss": 0.492,
      "step": 12
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019925185024910277,
      "loss": 0.3781,
      "step": 13
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001986712473391289,
      "loss": 0.4503,
      "step": 14
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019792641587574212,
      "loss": 0.2779,
      "step": 15
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.28619876503944397,
      "eval_runtime": 6.3023,
      "eval_samples_per_second": 44.428,
      "eval_steps_per_second": 5.554,
      "step": 15
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019701859555740648,
      "loss": 0.2658,
      "step": 16
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.2282,
      "step": 17
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000194720301029191,
      "loss": 0.2149,
      "step": 18
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001933336521037367,
      "loss": 0.1792,
      "step": 19
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019179165852537596,
      "loss": 0.1807,
      "step": 20
    },
    {
      "epoch": 0.68,
      "eval_loss": 0.1634436696767807,
      "eval_runtime": 6.2724,
      "eval_samples_per_second": 44.64,
      "eval_steps_per_second": 5.58,
      "step": 20
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.1425,
      "step": 21
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00018825215767863214,
      "loss": 0.1377,
      "step": 22
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018626054156009806,
      "loss": 0.1173,
      "step": 23
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.1338,
      "step": 24
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018185014665785936,
      "loss": 0.1256,
      "step": 25
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.1177145466208458,
      "eval_runtime": 6.2558,
      "eval_samples_per_second": 44.758,
      "eval_steps_per_second": 5.595,
      "step": 25
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00017943870854121124,
      "loss": 0.1234,
      "step": 26
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001768950525339362,
      "loss": 0.1164,
      "step": 27
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000174223412300427,
      "loss": 0.1077,
      "step": 28
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00017142823452219038,
      "loss": 0.0877,
      "step": 29
    }
  ],
  "logging_steps": 1,
  "max_steps": 87,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.9186990286320435e+17,
  "trial_name": null,
  "trial_params": null
}