{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 1e-05,
      "loss": 3.6939,
      "step": 1
    },
    {
      "epoch": 0.11,
      "learning_rate": 2e-05,
      "loss": 3.8426,
      "step": 2
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9957341762950346e-05,
      "loss": 1.1646,
      "step": 3
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.982973099683902e-05,
      "loss": 0.2849,
      "step": 4
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.961825643172819e-05,
      "loss": 0.3653,
      "step": 5
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.932472229404356e-05,
      "loss": 0.2641,
      "step": 6
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.8951632913550625e-05,
      "loss": 0.4845,
      "step": 7
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8502171357296144e-05,
      "loss": 1.9868,
      "step": 8
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.7980172272802398e-05,
      "loss": 0.1946,
      "step": 9
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7390089172206594e-05,
      "loss": 0.1418,
      "step": 10
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.6736956436465573e-05,
      "loss": 0.2751,
      "step": 11
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6026346363792565e-05,
      "loss": 0.1859,
      "step": 12
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.526432162877356e-05,
      "loss": 0.1168,
      "step": 13
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4457383557765385e-05,
      "loss": 0.1149,
      "step": 14
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.3612416661871532e-05,
      "loss": 0.1141,
      "step": 15
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.2736629900720832e-05,
      "loss": 0.0735,
      "step": 16
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.1837495178165706e-05,
      "loss": 0.0877,
      "step": 17
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.092268359463302e-05,
      "loss": 0.2009,
      "step": 18
    },
    {
      "epoch": 1.06,
      "learning_rate": 1e-05,
      "loss": 0.1289,
      "step": 19
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.07731640536698e-06,
      "loss": 0.0915,
      "step": 20
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.162504821834296e-06,
      "loss": 0.0985,
      "step": 21
    },
    {
      "epoch": 1.22,
      "learning_rate": 7.263370099279173e-06,
      "loss": 0.0483,
      "step": 22
    },
    {
      "epoch": 1.28,
      "learning_rate": 6.387583338128471e-06,
      "loss": 0.0905,
      "step": 23
    },
    {
      "epoch": 1.33,
      "learning_rate": 5.542616442234618e-06,
      "loss": 0.0742,
      "step": 24
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.7356783712264405e-06,
      "loss": 0.0742,
      "step": 25
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.973653636207437e-06,
      "loss": 0.0803,
      "step": 26
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.2630435635344283e-06,
      "loss": 0.1247,
      "step": 27
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.6099108277934105e-06,
      "loss": 0.0839,
      "step": 28
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.019827727197605e-06,
      "loss": 0.058,
      "step": 29
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.4978286427038602e-06,
      "loss": 0.0682,
      "step": 30
    },
    {
      "epoch": 1.72,
      "learning_rate": 1.0483670864493777e-06,
      "loss": 0.0987,
      "step": 31
    },
    {
      "epoch": 1.78,
      "learning_rate": 6.752777059564431e-07,
      "loss": 0.1137,
      "step": 32
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.817435682718096e-07,
      "loss": 0.0906,
      "step": 33
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.7026900316098217e-07,
      "loss": 0.0815,
      "step": 34
    },
    {
      "epoch": 1.94,
      "learning_rate": 4.2658237049655325e-08,
      "loss": 0.0845,
      "step": 35
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 0.0489,
      "step": 36
    },
    {
      "epoch": 2.0,
      "step": 36,
      "total_flos": 2.425367272288665e+21,
      "train_loss": 0.4203104440950685,
      "train_runtime": 335.7646,
      "train_samples_per_second": 1.686,
      "train_steps_per_second": 0.107
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 2.425367272288665e+21,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}