{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005689900426742532,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "grad_norm": 0.9915525317192078,
      "learning_rate": 2e-05,
      "loss": 1.7135,
      "step": 1
    },
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 1.6752992868423462,
      "eval_runtime": 48.0066,
      "eval_samples_per_second": 15.415,
      "eval_steps_per_second": 7.707,
      "step": 1
    },
    {
      "epoch": 0.0011379800853485065,
      "grad_norm": 1.1231664419174194,
      "learning_rate": 4e-05,
      "loss": 1.7942,
      "step": 2
    },
    {
      "epoch": 0.0017069701280227596,
      "grad_norm": 1.0703914165496826,
      "learning_rate": 6e-05,
      "loss": 1.698,
      "step": 3
    },
    {
      "epoch": 0.0017069701280227596,
      "eval_loss": 1.6628438234329224,
      "eval_runtime": 48.0132,
      "eval_samples_per_second": 15.412,
      "eval_steps_per_second": 7.706,
      "step": 3
    },
    {
      "epoch": 0.002275960170697013,
      "grad_norm": 0.8998307585716248,
      "learning_rate": 8e-05,
      "loss": 1.602,
      "step": 4
    },
    {
      "epoch": 0.002844950213371266,
      "grad_norm": 0.9879723787307739,
      "learning_rate": 0.0001,
      "loss": 1.6726,
      "step": 5
    },
    {
      "epoch": 0.0034139402560455193,
      "grad_norm": 0.9408596754074097,
      "learning_rate": 0.00012,
      "loss": 1.5864,
      "step": 6
    },
    {
      "epoch": 0.0034139402560455193,
      "eval_loss": 1.5575608015060425,
      "eval_runtime": 48.0656,
      "eval_samples_per_second": 15.396,
      "eval_steps_per_second": 7.698,
      "step": 6
    },
    {
      "epoch": 0.003982930298719772,
      "grad_norm": 0.8321022391319275,
      "learning_rate": 0.00014,
      "loss": 1.6618,
      "step": 7
    },
    {
      "epoch": 0.004551920341394026,
      "grad_norm": 1.18330717086792,
      "learning_rate": 0.00016,
      "loss": 1.6162,
      "step": 8
    },
    {
      "epoch": 0.005120910384068279,
      "grad_norm": 1.5175787210464478,
      "learning_rate": 0.00018,
      "loss": 1.4511,
      "step": 9
    },
    {
      "epoch": 0.005120910384068279,
      "eval_loss": 1.5452752113342285,
      "eval_runtime": 48.0543,
      "eval_samples_per_second": 15.399,
      "eval_steps_per_second": 7.7,
      "step": 9
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 1.3251971006393433,
      "learning_rate": 0.0002,
      "loss": 1.6569,
      "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": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}