{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.050505050505050504,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00202020202020202,
      "grad_norm": 3.2531862258911133,
      "learning_rate": 1e-05,
      "loss": 2.8443,
      "step": 1
    },
    {
      "epoch": 0.00202020202020202,
      "eval_loss": 2.722517490386963,
      "eval_runtime": 71.2115,
      "eval_samples_per_second": 5.856,
      "eval_steps_per_second": 0.744,
      "step": 1
    },
    {
      "epoch": 0.00404040404040404,
      "grad_norm": 3.208575487136841,
      "learning_rate": 2e-05,
      "loss": 2.4447,
      "step": 2
    },
    {
      "epoch": 0.006060606060606061,
      "grad_norm": 3.1579270362854004,
      "learning_rate": 3e-05,
      "loss": 2.6445,
      "step": 3
    },
    {
      "epoch": 0.00808080808080808,
      "grad_norm": 3.14211106300354,
      "learning_rate": 4e-05,
      "loss": 3.2089,
      "step": 4
    },
    {
      "epoch": 0.00808080808080808,
      "eval_loss": 2.6330459117889404,
      "eval_runtime": 71.1609,
      "eval_samples_per_second": 5.86,
      "eval_steps_per_second": 0.745,
      "step": 4
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 3.2041547298431396,
      "learning_rate": 5e-05,
      "loss": 2.6533,
      "step": 5
    },
    {
      "epoch": 0.012121212121212121,
      "grad_norm": 2.867931365966797,
      "learning_rate": 6e-05,
      "loss": 2.6047,
      "step": 6
    },
    {
      "epoch": 0.014141414141414142,
      "grad_norm": 2.7501237392425537,
      "learning_rate": 7e-05,
      "loss": 2.4092,
      "step": 7
    },
    {
      "epoch": 0.01616161616161616,
      "grad_norm": 2.407280921936035,
      "learning_rate": 8e-05,
      "loss": 2.1781,
      "step": 8
    },
    {
      "epoch": 0.01616161616161616,
      "eval_loss": 2.065152406692505,
      "eval_runtime": 71.1604,
      "eval_samples_per_second": 5.86,
      "eval_steps_per_second": 0.745,
      "step": 8
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 2.6464085578918457,
      "learning_rate": 9e-05,
      "loss": 1.7503,
      "step": 9
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 2.112260103225708,
      "learning_rate": 0.0001,
      "loss": 1.9686,
      "step": 10
    },
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 2.9698574542999268,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.2787,
      "step": 11
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 2.5725059509277344,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.9672,
      "step": 12
    },
    {
      "epoch": 0.024242424242424242,
      "eval_loss": 1.8361198902130127,
      "eval_runtime": 71.1339,
      "eval_samples_per_second": 5.862,
      "eval_steps_per_second": 0.745,
      "step": 12
    },
    {
      "epoch": 0.026262626262626262,
      "grad_norm": 2.842247724533081,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0942,
      "step": 13
    },
    {
      "epoch": 0.028282828282828285,
      "grad_norm": 3.114049196243286,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.767,
      "step": 14
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.9104647636413574,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.8602,
      "step": 15
    },
    {
      "epoch": 0.03232323232323232,
      "grad_norm": 2.5403757095336914,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.6854,
      "step": 16
    },
    {
      "epoch": 0.03232323232323232,
      "eval_loss": 1.7266491651535034,
      "eval_runtime": 71.413,
      "eval_samples_per_second": 5.839,
      "eval_steps_per_second": 0.742,
      "step": 16
    },
    {
      "epoch": 0.03434343434343434,
      "grad_norm": 2.6109960079193115,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.8352,
      "step": 17
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 2.0346593856811523,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.8479,
      "step": 18
    },
    {
      "epoch": 0.03838383838383838,
      "grad_norm": 2.0290637016296387,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.6687,
      "step": 19
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 2.3762779235839844,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.4567,
      "step": 20
    },
    {
      "epoch": 0.04040404040404041,
      "eval_loss": 1.6859194040298462,
      "eval_runtime": 71.1426,
      "eval_samples_per_second": 5.861,
      "eval_steps_per_second": 0.745,
      "step": 20
    },
    {
      "epoch": 0.04242424242424243,
      "grad_norm": 3.23976993560791,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.9274,
      "step": 21
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 2.0082623958587646,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5061,
      "step": 22
    },
    {
      "epoch": 0.046464646464646465,
      "grad_norm": 2.2136764526367188,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.8406,
      "step": 23
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 2.6426143646240234,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5735,
      "step": 24
    },
    {
      "epoch": 0.048484848484848485,
      "eval_loss": 1.6703355312347412,
      "eval_runtime": 71.1291,
      "eval_samples_per_second": 5.863,
      "eval_steps_per_second": 0.745,
      "step": 24
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.1712427139282227,
      "learning_rate": 0.0,
      "loss": 1.7482,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.05903135506432e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}