{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05974607916355489,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01194921583271098,
      "grad_norm": 0.6119192242622375,
      "learning_rate": 1e-05,
      "loss": 3.9169,
      "step": 1
    },
    {
      "epoch": 0.01194921583271098,
      "eval_loss": 7.03106164932251,
      "eval_runtime": 55.2186,
      "eval_samples_per_second": 2.553,
      "eval_steps_per_second": 1.286,
      "step": 1
    },
    {
      "epoch": 0.02389843166542196,
      "grad_norm": 0.5197845697402954,
      "learning_rate": 2e-05,
      "loss": 3.8108,
      "step": 2
    },
    {
      "epoch": 0.02389843166542196,
      "eval_loss": 7.0233612060546875,
      "eval_runtime": 0.6142,
      "eval_samples_per_second": 229.583,
      "eval_steps_per_second": 115.605,
      "step": 2
    },
    {
      "epoch": 0.035847647498132934,
      "grad_norm": 0.6395890712738037,
      "learning_rate": 3e-05,
      "loss": 3.4104,
      "step": 3
    },
    {
      "epoch": 0.04779686333084392,
      "grad_norm": 0.5496344566345215,
      "learning_rate": 4e-05,
      "loss": 3.6741,
      "step": 4
    },
    {
      "epoch": 0.04779686333084392,
      "eval_loss": 7.012506484985352,
      "eval_runtime": 0.6312,
      "eval_samples_per_second": 223.391,
      "eval_steps_per_second": 112.488,
      "step": 4
    },
    {
      "epoch": 0.05974607916355489,
      "grad_norm": 0.4691571891307831,
      "learning_rate": 5e-05,
      "loss": 3.5595,
      "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": 100306002640896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}