{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02264192020900234,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001741686169923257,
      "grad_norm": 3.0921738147735596,
      "learning_rate": 5e-05,
      "loss": 1.9628,
      "step": 1
    },
    {
      "epoch": 0.001741686169923257,
      "eval_loss": 2.522160053253174,
      "eval_runtime": 351.8165,
      "eval_samples_per_second": 10.994,
      "eval_steps_per_second": 2.749,
      "step": 1
    },
    {
      "epoch": 0.003483372339846514,
      "grad_norm": 2.935767412185669,
      "learning_rate": 0.0001,
      "loss": 1.9583,
      "step": 2
    },
    {
      "epoch": 0.005225058509769771,
      "grad_norm": 2.823258399963379,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.834,
      "step": 3
    },
    {
      "epoch": 0.006966744679693028,
      "grad_norm": 2.366340160369873,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.4925,
      "step": 4
    },
    {
      "epoch": 0.008708430849616285,
      "grad_norm": 1.9907324314117432,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.1095,
      "step": 5
    },
    {
      "epoch": 0.010450117019539542,
      "grad_norm": 1.629361867904663,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7857,
      "step": 6
    },
    {
      "epoch": 0.012191803189462799,
      "grad_norm": 1.6523230075836182,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.6975,
      "step": 7
    },
    {
      "epoch": 0.013933489359386056,
      "grad_norm": 1.8730814456939697,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5556,
      "step": 8
    },
    {
      "epoch": 0.01567517552930931,
      "grad_norm": 1.6527363061904907,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.3817,
      "step": 9
    },
    {
      "epoch": 0.01741686169923257,
      "grad_norm": 1.103572964668274,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2157,
      "step": 10
    },
    {
      "epoch": 0.019158547869155825,
      "grad_norm": 1.1308457851409912,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2139,
      "step": 11
    },
    {
      "epoch": 0.020900234039079084,
      "grad_norm": 1.191890001296997,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.1758,
      "step": 12
    },
    {
      "epoch": 0.02264192020900234,
      "grad_norm": 0.7013289928436279,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.149,
      "step": 13
    },
    {
      "epoch": 0.02264192020900234,
      "eval_loss": 0.14659395813941956,
      "eval_runtime": 352.1285,
      "eval_samples_per_second": 10.985,
      "eval_steps_per_second": 2.746,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.086251099611464e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}