{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6567009687423706,
      "learning_rate": 0.0,
      "loss": 2.767,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.3838800191879272,
      "learning_rate": 4e-05,
      "loss": 2.2945,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.9234319925308228,
      "learning_rate": 8e-05,
      "loss": 2.9474,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.9659762382507324,
      "learning_rate": 0.00012,
      "loss": 2.9853,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.1689095497131348,
      "learning_rate": 0.00016,
      "loss": 2.7449,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.7526321411132812,
      "learning_rate": 0.0002,
      "loss": 2.4316,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.216229200363159,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5923,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.076944589614868,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4113,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8331300020217896,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1678,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4564743041992188,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.4995,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.923876166343689,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2383,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8946003317832947,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.153,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5039580464363098,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1056,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5277471542358398,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0161,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4442140460014343,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9613,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.38263705372810364,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8934,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.42776256799697876,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0797,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.43527865409851074,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.8707,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.32646483182907104,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0146,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.40627530217170715,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9273,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.46039798855781555,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8705,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.41969212889671326,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0961,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4023812413215637,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1031,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3344135284423828,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8892,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3448273241519928,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8705,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.2724474370479584,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8999,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.40961214900016785,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.2188,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3562145531177521,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9201,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3152042031288147,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.936,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.27859261631965637,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8427,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5078477163184128.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}