{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010350181128169742,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003450060376056581,
      "eval_loss": 1.377044916152954,
      "eval_runtime": 114.1445,
      "eval_samples_per_second": 10.697,
      "eval_steps_per_second": 5.353,
      "step": 1
    },
    {
      "epoch": 0.0010350181128169743,
      "grad_norm": 4.938549041748047,
      "learning_rate": 6e-05,
      "loss": 1.1608,
      "step": 3
    },
    {
      "epoch": 0.0020700362256339485,
      "grad_norm": 2.8106095790863037,
      "learning_rate": 0.00012,
      "loss": 1.2213,
      "step": 6
    },
    {
      "epoch": 0.0027600483008452647,
      "eval_loss": 0.5112046599388123,
      "eval_runtime": 115.649,
      "eval_samples_per_second": 10.558,
      "eval_steps_per_second": 5.283,
      "step": 8
    },
    {
      "epoch": 0.003105054338450923,
      "grad_norm": 2.465625524520874,
      "learning_rate": 0.00018,
      "loss": 0.5964,
      "step": 9
    },
    {
      "epoch": 0.004140072451267897,
      "grad_norm": 2.3001599311828613,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.3384,
      "step": 12
    },
    {
      "epoch": 0.005175090564084871,
      "grad_norm": 1.6452058553695679,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6674,
      "step": 15
    },
    {
      "epoch": 0.005520096601690529,
      "eval_loss": 0.3198825418949127,
      "eval_runtime": 115.0968,
      "eval_samples_per_second": 10.608,
      "eval_steps_per_second": 5.309,
      "step": 16
    },
    {
      "epoch": 0.006210108676901846,
      "grad_norm": 1.4537681341171265,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5395,
      "step": 18
    },
    {
      "epoch": 0.00724512678971882,
      "grad_norm": 1.662941336631775,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.3747,
      "step": 21
    },
    {
      "epoch": 0.008280144902535794,
      "grad_norm": 1.672710657119751,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.3137,
      "step": 24
    },
    {
      "epoch": 0.008280144902535794,
      "eval_loss": 0.279544860124588,
      "eval_runtime": 116.0751,
      "eval_samples_per_second": 10.519,
      "eval_steps_per_second": 5.264,
      "step": 24
    },
    {
      "epoch": 0.009315163015352769,
      "grad_norm": 1.0861223936080933,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.2541,
      "step": 27
    },
    {
      "epoch": 0.010350181128169742,
      "grad_norm": 1.507712483406067,
      "learning_rate": 0.0,
      "loss": 0.2888,
      "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": 5140226179596288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}