{
  "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": 1.3645844459533691,
      "learning_rate": 0.0,
      "loss": 2.5037,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.660995602607727,
      "learning_rate": 4e-05,
      "loss": 2.6031,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6392755508422852,
      "learning_rate": 8e-05,
      "loss": 2.9118,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.710063099861145,
      "learning_rate": 0.00012,
      "loss": 2.7714,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.6210428476333618,
      "learning_rate": 0.00016,
      "loss": 2.1514,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.3645424842834473,
      "learning_rate": 0.0002,
      "loss": 2.5283,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.700213670730591,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7241,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8606327772140503,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.2173,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.842186450958252,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3338,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.0317293405532837,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.5118,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8248395919799805,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.0751,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5275245308876038,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0938,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.45801183581352234,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1561,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5454519987106323,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.2234,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.46795782446861267,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.126,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5097053050994873,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8651,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.39326727390289307,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.102,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4550538659095764,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.2287,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.36811986565589905,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9848,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.36873698234558105,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0985,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40543392300605774,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0776,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3196291923522949,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1498,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.31376779079437256,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0388,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2825721502304077,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0112,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.41585949063301086,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8182,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.30083444714546204,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8058,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3621577322483063,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.2748,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2544698119163513,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8783,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3715449869632721,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1229,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.39372724294662476,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1051,
      "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": 4861948661121024.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}