{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 200,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.31015893816947937,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.38761081695556643,
      "step": 10
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 0.21577006578445435,
      "learning_rate": 1.9946749853292233e-05,
      "loss": 0.3502843379974365,
      "step": 20
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.22367797791957855,
      "learning_rate": 1.9687297122400952e-05,
      "loss": 0.3208463191986084,
      "step": 30
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 0.20365038514137268,
      "learning_rate": 1.9217488001088784e-05,
      "loss": 0.3184423685073853,
      "step": 40
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 0.2231130301952362,
      "learning_rate": 1.8547524236003675e-05,
      "loss": 0.3126647472381592,
      "step": 50
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.209013894200325,
      "learning_rate": 1.7691953864390208e-05,
      "loss": 0.3156299591064453,
      "step": 60
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 0.1777929961681366,
      "learning_rate": 1.666935530836651e-05,
      "loss": 0.2766378402709961,
      "step": 70
    },
    {
      "epoch": 1.0673400673400673,
      "grad_norm": 0.17185629904270172,
      "learning_rate": 1.5501933950752655e-05,
      "loss": 0.24300642013549806,
      "step": 80
    },
    {
      "epoch": 1.202020202020202,
      "grad_norm": 0.18560396134853363,
      "learning_rate": 1.4215039952670482e-05,
      "loss": 0.20093803405761718,
      "step": 90
    },
    {
      "epoch": 1.3367003367003367,
      "grad_norm": 0.17960919439792633,
      "learning_rate": 1.2836617783342968e-05,
      "loss": 0.19915937185287474,
      "step": 100
    },
    {
      "epoch": 1.4713804713804715,
      "grad_norm": 0.17622533440589905,
      "learning_rate": 1.1396599415368062e-05,
      "loss": 0.19454092979431153,
      "step": 110
    },
    {
      "epoch": 1.606060606060606,
      "grad_norm": 0.1789940446615219,
      "learning_rate": 9.926254362026875e-06,
      "loss": 0.19552748203277587,
      "step": 120
    },
    {
      "epoch": 1.7407407407407407,
      "grad_norm": 0.1863929182291031,
      "learning_rate": 8.457510670346976e-06,
      "loss": 0.19949347972869874,
      "step": 130
    },
    {
      "epoch": 1.8754208754208754,
      "grad_norm": 0.16495266556739807,
      "learning_rate": 7.022261614327448e-06,
      "loss": 0.20035164356231688,
      "step": 140
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3942849636077881,
      "learning_rate": 5.651673143248509e-06,
      "loss": 0.19270834922790528,
      "step": 150
    },
    {
      "epoch": 2.1346801346801345,
      "grad_norm": 0.17539165914058685,
      "learning_rate": 4.375507123592194e-06,
      "loss": 0.1418288230895996,
      "step": 160
    },
    {
      "epoch": 2.2693602693602695,
      "grad_norm": 0.18225708603858948,
      "learning_rate": 3.2214750701474875e-06,
      "loss": 0.13898892402648927,
      "step": 170
    },
    {
      "epoch": 2.404040404040404,
      "grad_norm": 0.172335684299469,
      "learning_rate": 2.2146363998111077e-06,
      "loss": 0.14039983749389648,
      "step": 180
    },
    {
      "epoch": 2.538720538720539,
      "grad_norm": 0.1543879359960556,
      "learning_rate": 1.3768542747997215e-06,
      "loss": 0.13042680025100709,
      "step": 190
    },
    {
      "epoch": 2.6734006734006734,
      "grad_norm": 0.16937494277954102,
      "learning_rate": 7.263208514547548e-07,
      "loss": 0.12810491323471068,
      "step": 200
    },
    {
      "epoch": 2.808080808080808,
      "grad_norm": 0.17165407538414001,
      "learning_rate": 2.7716224370188836e-07,
      "loss": 0.1331431746482849,
      "step": 210
    },
    {
      "epoch": 2.942760942760943,
      "grad_norm": 0.14236703515052795,
      "learning_rate": 3.913177925055189e-08,
      "loss": 0.12828856706619263,
      "step": 220
    }
  ],
  "logging_steps": 10,
  "max_steps": 225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2113763633135616e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}