{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004,
      "grad_norm": 0.21889594197273254,
      "learning_rate": 0.0,
      "loss": 1.3922,
      "step": 1
    },
    {
      "epoch": 0.0008,
      "grad_norm": 0.281279057264328,
      "learning_rate": 4e-05,
      "loss": 1.4108,
      "step": 2
    },
    {
      "epoch": 0.0012,
      "grad_norm": 0.3023129999637604,
      "learning_rate": 8e-05,
      "loss": 1.3522,
      "step": 3
    },
    {
      "epoch": 0.0016,
      "grad_norm": 0.2667141556739807,
      "learning_rate": 0.00012,
      "loss": 1.3634,
      "step": 4
    },
    {
      "epoch": 0.002,
      "grad_norm": 0.25083309412002563,
      "learning_rate": 0.00016,
      "loss": 1.3984,
      "step": 5
    },
    {
      "epoch": 0.0024,
      "grad_norm": 0.24728843569755554,
      "learning_rate": 0.0002,
      "loss": 1.2984,
      "step": 6
    },
    {
      "epoch": 0.0028,
      "grad_norm": 0.19864429533481598,
      "learning_rate": 0.000192,
      "loss": 1.2225,
      "step": 7
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.20911765098571777,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.1594,
      "step": 8
    },
    {
      "epoch": 0.0036,
      "grad_norm": 0.3918673098087311,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.0998,
      "step": 9
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.2317754626274109,
      "learning_rate": 0.000168,
      "loss": 1.0553,
      "step": 10
    },
    {
      "epoch": 0.0044,
      "grad_norm": 0.2284780591726303,
      "learning_rate": 0.00016,
      "loss": 1.0439,
      "step": 11
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.23215815424919128,
      "learning_rate": 0.000152,
      "loss": 0.9784,
      "step": 12
    },
    {
      "epoch": 0.0052,
      "grad_norm": 0.24038466811180115,
      "learning_rate": 0.000144,
      "loss": 1.0631,
      "step": 13
    },
    {
      "epoch": 0.0056,
      "grad_norm": 0.3637539744377136,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.062,
      "step": 14
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.2320483773946762,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.0589,
      "step": 15
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.22827845811843872,
      "learning_rate": 0.00012,
      "loss": 1.0331,
      "step": 16
    },
    {
      "epoch": 0.0068,
      "grad_norm": 0.22989106178283691,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.024,
      "step": 17
    },
    {
      "epoch": 0.0072,
      "grad_norm": 0.2284201979637146,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.0054,
      "step": 18
    },
    {
      "epoch": 0.0076,
      "grad_norm": 0.23722527921199799,
      "learning_rate": 9.6e-05,
      "loss": 1.0607,
      "step": 19
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.25204116106033325,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.1038,
      "step": 20
    },
    {
      "epoch": 0.0084,
      "grad_norm": 0.23097504675388336,
      "learning_rate": 8e-05,
      "loss": 0.9563,
      "step": 21
    },
    {
      "epoch": 0.0088,
      "grad_norm": 0.21278901398181915,
      "learning_rate": 7.2e-05,
      "loss": 0.9815,
      "step": 22
    },
    {
      "epoch": 0.0092,
      "grad_norm": 0.3004467785358429,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.9571,
      "step": 23
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.24711133539676666,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.0638,
      "step": 24
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.2166084498167038,
      "learning_rate": 4.8e-05,
      "loss": 1.0215,
      "step": 25
    },
    {
      "epoch": 0.0104,
      "grad_norm": 0.21120785176753998,
      "learning_rate": 4e-05,
      "loss": 0.9826,
      "step": 26
    },
    {
      "epoch": 0.0108,
      "grad_norm": 0.19642344117164612,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.9539,
      "step": 27
    },
    {
      "epoch": 0.0112,
      "grad_norm": 0.2176462709903717,
      "learning_rate": 2.4e-05,
      "loss": 0.884,
      "step": 28
    },
    {
      "epoch": 0.0116,
      "grad_norm": 0.20913571119308472,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9816,
      "step": 29
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.1878669112920761,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9465,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.665233697510195e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}