{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008624035186063559,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017248070372127117,
      "eval_loss": 6.329273700714111,
      "eval_runtime": 37.2306,
      "eval_samples_per_second": 65.591,
      "eval_steps_per_second": 32.796,
      "step": 1
    },
    {
      "epoch": 0.0008624035186063559,
      "grad_norm": 2.544393539428711,
      "learning_rate": 5e-05,
      "loss": 6.2995,
      "step": 5
    },
    {
      "epoch": 0.0017248070372127117,
      "grad_norm": 2.786011219024658,
      "learning_rate": 0.0001,
      "loss": 6.2716,
      "step": 10
    },
    {
      "epoch": 0.0017248070372127117,
      "eval_loss": 6.270487308502197,
      "eval_runtime": 38.5696,
      "eval_samples_per_second": 63.314,
      "eval_steps_per_second": 31.657,
      "step": 10
    },
    {
      "epoch": 0.002587210555819068,
      "grad_norm": 3.6353487968444824,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.0843,
      "step": 15
    },
    {
      "epoch": 0.0034496140744254234,
      "grad_norm": 2.0951130390167236,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.8982,
      "step": 20
    },
    {
      "epoch": 0.0034496140744254234,
      "eval_loss": 5.9787092208862305,
      "eval_runtime": 37.6929,
      "eval_samples_per_second": 64.787,
      "eval_steps_per_second": 32.393,
      "step": 20
    },
    {
      "epoch": 0.0043120175930317795,
      "grad_norm": 3.2061691284179688,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.0776,
      "step": 25
    },
    {
      "epoch": 0.005174421111638136,
      "grad_norm": 2.500523328781128,
      "learning_rate": 5e-05,
      "loss": 5.8464,
      "step": 30
    },
    {
      "epoch": 0.005174421111638136,
      "eval_loss": 5.717452049255371,
      "eval_runtime": 39.253,
      "eval_samples_per_second": 62.212,
      "eval_steps_per_second": 31.106,
      "step": 30
    },
    {
      "epoch": 0.006036824630244492,
      "grad_norm": 1.5522089004516602,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.6319,
      "step": 35
    },
    {
      "epoch": 0.006899228148850847,
      "grad_norm": 1.5637425184249878,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.5491,
      "step": 40
    },
    {
      "epoch": 0.006899228148850847,
      "eval_loss": 5.575439929962158,
      "eval_runtime": 37.6254,
      "eval_samples_per_second": 64.903,
      "eval_steps_per_second": 32.451,
      "step": 40
    },
    {
      "epoch": 0.007761631667457203,
      "grad_norm": 1.783243179321289,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.4637,
      "step": 45
    },
    {
      "epoch": 0.008624035186063559,
      "grad_norm": 2.0012452602386475,
      "learning_rate": 0.0,
      "loss": 5.6158,
      "step": 50
    },
    {
      "epoch": 0.008624035186063559,
      "eval_loss": 5.548293113708496,
      "eval_runtime": 37.6341,
      "eval_samples_per_second": 64.888,
      "eval_steps_per_second": 32.444,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 171463252377600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}