{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013021237017516665,
  "eval_steps": 3,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006200589055960316,
      "grad_norm": 0.7607094645500183,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.1893,
      "step": 1
    },
    {
      "epoch": 0.0012401178111920632,
      "grad_norm": 0.3518824279308319,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9752,
      "step": 2
    },
    {
      "epoch": 0.0018601767167880949,
      "grad_norm": 0.4024870693683624,
      "learning_rate": 1.2e-05,
      "loss": 0.8467,
      "step": 3
    },
    {
      "epoch": 0.0018601767167880949,
      "eval_loss": 1.0757174491882324,
      "eval_runtime": 26.414,
      "eval_samples_per_second": 3.786,
      "eval_steps_per_second": 3.786,
      "step": 3
    },
    {
      "epoch": 0.0024802356223841263,
      "grad_norm": 0.36653462052345276,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0056,
      "step": 4
    },
    {
      "epoch": 0.0031002945279801583,
      "grad_norm": 0.47098514437675476,
      "learning_rate": 2e-05,
      "loss": 0.8545,
      "step": 5
    },
    {
      "epoch": 0.0037203534335761897,
      "grad_norm": 0.5030912160873413,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.9553,
      "step": 6
    },
    {
      "epoch": 0.0037203534335761897,
      "eval_loss": 1.0662517547607422,
      "eval_runtime": 26.7124,
      "eval_samples_per_second": 3.744,
      "eval_steps_per_second": 3.744,
      "step": 6
    },
    {
      "epoch": 0.004340412339172222,
      "grad_norm": 0.4823940694332123,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.9266,
      "step": 7
    },
    {
      "epoch": 0.004960471244768253,
      "grad_norm": 0.5647093653678894,
      "learning_rate": 1.76e-05,
      "loss": 1.0013,
      "step": 8
    },
    {
      "epoch": 0.005580530150364285,
      "grad_norm": 0.4058099687099457,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.9206,
      "step": 9
    },
    {
      "epoch": 0.005580530150364285,
      "eval_loss": 1.0476710796356201,
      "eval_runtime": 26.7708,
      "eval_samples_per_second": 3.735,
      "eval_steps_per_second": 3.735,
      "step": 9
    },
    {
      "epoch": 0.0062005890559603165,
      "grad_norm": 0.44608208537101746,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0937,
      "step": 10
    },
    {
      "epoch": 0.0068206479615563476,
      "grad_norm": 0.7088199853897095,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.8915,
      "step": 11
    },
    {
      "epoch": 0.0074407068671523795,
      "grad_norm": 0.5858705639839172,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.186,
      "step": 12
    },
    {
      "epoch": 0.0074407068671523795,
      "eval_loss": 1.0301631689071655,
      "eval_runtime": 27.1639,
      "eval_samples_per_second": 3.681,
      "eval_steps_per_second": 3.681,
      "step": 12
    },
    {
      "epoch": 0.008060765772748411,
      "grad_norm": 0.5912883281707764,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.0082,
      "step": 13
    },
    {
      "epoch": 0.008680824678344443,
      "grad_norm": 0.42219021916389465,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.865,
      "step": 14
    },
    {
      "epoch": 0.009300883583940475,
      "grad_norm": 0.4253869652748108,
      "learning_rate": 1.2e-05,
      "loss": 0.8849,
      "step": 15
    },
    {
      "epoch": 0.009300883583940475,
      "eval_loss": 1.012740135192871,
      "eval_runtime": 27.032,
      "eval_samples_per_second": 3.699,
      "eval_steps_per_second": 3.699,
      "step": 15
    },
    {
      "epoch": 0.009920942489536505,
      "grad_norm": 0.5621253252029419,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.8289,
      "step": 16
    },
    {
      "epoch": 0.010541001395132537,
      "grad_norm": 0.37459954619407654,
      "learning_rate": 1.04e-05,
      "loss": 0.9139,
      "step": 17
    },
    {
      "epoch": 0.01116106030072857,
      "grad_norm": 0.448284387588501,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.8571,
      "step": 18
    },
    {
      "epoch": 0.01116106030072857,
      "eval_loss": 0.99790358543396,
      "eval_runtime": 26.9342,
      "eval_samples_per_second": 3.713,
      "eval_steps_per_second": 3.713,
      "step": 18
    },
    {
      "epoch": 0.011781119206324601,
      "grad_norm": 0.5347204208374023,
      "learning_rate": 8.8e-06,
      "loss": 0.8396,
      "step": 19
    },
    {
      "epoch": 0.012401178111920633,
      "grad_norm": 0.36863428354263306,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6704,
      "step": 20
    },
    {
      "epoch": 0.013021237017516665,
      "grad_norm": 0.4834197163581848,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.9445,
      "step": 21
    },
    {
      "epoch": 0.013021237017516665,
      "eval_loss": 0.9843659996986389,
      "eval_runtime": 27.0084,
      "eval_samples_per_second": 3.703,
      "eval_steps_per_second": 3.703,
      "step": 21
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4221253993578496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}