{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07467330429371499,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002489110143123833,
      "eval_loss": 1.071514368057251,
      "eval_runtime": 50.9836,
      "eval_samples_per_second": 3.334,
      "eval_steps_per_second": 1.667,
      "step": 1
    },
    {
      "epoch": 0.0074673304293715,
      "grad_norm": 1.1518806219100952,
      "learning_rate": 6e-05,
      "loss": 4.1572,
      "step": 3
    },
    {
      "epoch": 0.014934660858743,
      "grad_norm": 1.2009766101837158,
      "learning_rate": 0.00012,
      "loss": 4.1314,
      "step": 6
    },
    {
      "epoch": 0.019912881144990666,
      "eval_loss": 0.979844331741333,
      "eval_runtime": 50.7333,
      "eval_samples_per_second": 3.351,
      "eval_steps_per_second": 1.675,
      "step": 8
    },
    {
      "epoch": 0.0224019912881145,
      "grad_norm": 1.3134205341339111,
      "learning_rate": 0.00018,
      "loss": 3.9208,
      "step": 9
    },
    {
      "epoch": 0.029869321717486,
      "grad_norm": 1.7839148044586182,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.8047,
      "step": 12
    },
    {
      "epoch": 0.037336652146857496,
      "grad_norm": 1.2594926357269287,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.5741,
      "step": 15
    },
    {
      "epoch": 0.03982576228998133,
      "eval_loss": 0.8886153101921082,
      "eval_runtime": 50.8044,
      "eval_samples_per_second": 3.346,
      "eval_steps_per_second": 1.673,
      "step": 16
    },
    {
      "epoch": 0.044803982576229,
      "grad_norm": 1.2804442644119263,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.4823,
      "step": 18
    },
    {
      "epoch": 0.0522713130056005,
      "grad_norm": 1.293418288230896,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.5683,
      "step": 21
    },
    {
      "epoch": 0.059738643434972,
      "grad_norm": 1.1531097888946533,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.4569,
      "step": 24
    },
    {
      "epoch": 0.059738643434972,
      "eval_loss": 0.8627409338951111,
      "eval_runtime": 50.8163,
      "eval_samples_per_second": 3.345,
      "eval_steps_per_second": 1.673,
      "step": 24
    },
    {
      "epoch": 0.0672059738643435,
      "grad_norm": 1.2184909582138062,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.4258,
      "step": 27
    },
    {
      "epoch": 0.07467330429371499,
      "grad_norm": 1.494885802268982,
      "learning_rate": 0.0,
      "loss": 3.3277,
      "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": 1.71516213854208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}