{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009216377502822516,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001843275500564503,
      "grad_norm": 0.025917736813426018,
      "learning_rate": 1e-05,
      "loss": 10.3735,
      "step": 1
    },
    {
      "epoch": 0.0001843275500564503,
      "eval_loss": 10.371116638183594,
      "eval_runtime": 71.5372,
      "eval_samples_per_second": 127.724,
      "eval_steps_per_second": 63.869,
      "step": 1
    },
    {
      "epoch": 0.0003686551001129006,
      "grad_norm": 0.028988244011998177,
      "learning_rate": 2e-05,
      "loss": 10.372,
      "step": 2
    },
    {
      "epoch": 0.0003686551001129006,
      "eval_loss": 10.371111869812012,
      "eval_runtime": 44.6427,
      "eval_samples_per_second": 204.67,
      "eval_steps_per_second": 102.346,
      "step": 2
    },
    {
      "epoch": 0.0005529826501693509,
      "grad_norm": 0.025734927505254745,
      "learning_rate": 3e-05,
      "loss": 10.3693,
      "step": 3
    },
    {
      "epoch": 0.0007373102002258012,
      "grad_norm": 0.026525335386395454,
      "learning_rate": 4e-05,
      "loss": 10.3682,
      "step": 4
    },
    {
      "epoch": 0.0007373102002258012,
      "eval_loss": 10.37109088897705,
      "eval_runtime": 37.2642,
      "eval_samples_per_second": 245.195,
      "eval_steps_per_second": 122.611,
      "step": 4
    },
    {
      "epoch": 0.0009216377502822516,
      "grad_norm": 0.025096556171774864,
      "learning_rate": 5e-05,
      "loss": 10.3669,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}