{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006101281269066504,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006101281269066504,
      "grad_norm": 7.992586612701416,
      "learning_rate": 2e-05,
      "loss": 17.599,
      "step": 1
    },
    {
      "epoch": 0.0006101281269066504,
      "eval_loss": 4.343548774719238,
      "eval_runtime": 23.6333,
      "eval_samples_per_second": 29.238,
      "eval_steps_per_second": 14.64,
      "step": 1
    },
    {
      "epoch": 0.0012202562538133007,
      "grad_norm": 8.22298526763916,
      "learning_rate": 4e-05,
      "loss": 16.3537,
      "step": 2
    },
    {
      "epoch": 0.0018303843807199512,
      "grad_norm": 7.006322383880615,
      "learning_rate": 6e-05,
      "loss": 15.9738,
      "step": 3
    },
    {
      "epoch": 0.0018303843807199512,
      "eval_loss": 4.333251953125,
      "eval_runtime": 23.578,
      "eval_samples_per_second": 29.307,
      "eval_steps_per_second": 14.675,
      "step": 3
    },
    {
      "epoch": 0.0024405125076266015,
      "grad_norm": 5.18002986907959,
      "learning_rate": 8e-05,
      "loss": 17.4367,
      "step": 4
    },
    {
      "epoch": 0.003050640634533252,
      "grad_norm": 5.2810797691345215,
      "learning_rate": 0.0001,
      "loss": 16.3759,
      "step": 5
    },
    {
      "epoch": 0.0036607687614399025,
      "grad_norm": 5.569629192352295,
      "learning_rate": 0.00012,
      "loss": 17.2472,
      "step": 6
    },
    {
      "epoch": 0.0036607687614399025,
      "eval_loss": 4.224027633666992,
      "eval_runtime": 23.7984,
      "eval_samples_per_second": 29.036,
      "eval_steps_per_second": 14.539,
      "step": 6
    },
    {
      "epoch": 0.004270896888346553,
      "grad_norm": 7.013412952423096,
      "learning_rate": 0.00014,
      "loss": 16.8971,
      "step": 7
    },
    {
      "epoch": 0.004881025015253203,
      "grad_norm": 7.767675876617432,
      "learning_rate": 0.00016,
      "loss": 15.7784,
      "step": 8
    },
    {
      "epoch": 0.005491153142159854,
      "grad_norm": 7.345594882965088,
      "learning_rate": 0.00018,
      "loss": 15.7105,
      "step": 9
    },
    {
      "epoch": 0.005491153142159854,
      "eval_loss": 3.943946599960327,
      "eval_runtime": 23.7857,
      "eval_samples_per_second": 29.051,
      "eval_steps_per_second": 14.547,
      "step": 9
    },
    {
      "epoch": 0.006101281269066504,
      "grad_norm": 6.60803747177124,
      "learning_rate": 0.0002,
      "loss": 15.7592,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}