{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002108777787540638,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.029259291802126e-05,
      "eval_loss": 3.169178009033203,
      "eval_runtime": 833.4399,
      "eval_samples_per_second": 7.187,
      "eval_steps_per_second": 3.594,
      "step": 1
    },
    {
      "epoch": 0.00021087777875406378,
      "grad_norm": 0.8639353513717651,
      "learning_rate": 6e-05,
      "loss": 3.3445,
      "step": 3
    },
    {
      "epoch": 0.00042175555750812756,
      "grad_norm": 0.8548085689544678,
      "learning_rate": 0.00012,
      "loss": 3.0563,
      "step": 6
    },
    {
      "epoch": 0.0005623407433441701,
      "eval_loss": 3.0698280334472656,
      "eval_runtime": 838.0796,
      "eval_samples_per_second": 7.147,
      "eval_steps_per_second": 3.574,
      "step": 8
    },
    {
      "epoch": 0.0006326333362621913,
      "grad_norm": 1.4002740383148193,
      "learning_rate": 0.00018,
      "loss": 3.0132,
      "step": 9
    },
    {
      "epoch": 0.0008435111150162551,
      "grad_norm": 1.371001124382019,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.2445,
      "step": 12
    },
    {
      "epoch": 0.001054388893770319,
      "grad_norm": 1.2849618196487427,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.1236,
      "step": 15
    },
    {
      "epoch": 0.0011246814866883402,
      "eval_loss": 2.9972784519195557,
      "eval_runtime": 837.1059,
      "eval_samples_per_second": 7.156,
      "eval_steps_per_second": 3.578,
      "step": 16
    },
    {
      "epoch": 0.0012652666725243827,
      "grad_norm": 1.2119725942611694,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.0935,
      "step": 18
    },
    {
      "epoch": 0.0014761444512784464,
      "grad_norm": 1.326536774635315,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.8801,
      "step": 21
    },
    {
      "epoch": 0.0016870222300325102,
      "grad_norm": 0.9740743041038513,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.9518,
      "step": 24
    },
    {
      "epoch": 0.0016870222300325102,
      "eval_loss": 2.976255416870117,
      "eval_runtime": 836.7561,
      "eval_samples_per_second": 7.159,
      "eval_steps_per_second": 3.579,
      "step": 24
    },
    {
      "epoch": 0.001897900008786574,
      "grad_norm": 1.1573619842529297,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.8076,
      "step": 27
    },
    {
      "epoch": 0.002108777787540638,
      "grad_norm": 1.2271376848220825,
      "learning_rate": 0.0,
      "loss": 3.0403,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1499252895186944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}