{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07386888273314866,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014773776546629732,
      "grad_norm": 21.582956314086914,
      "learning_rate": 1e-05,
      "loss": 56.1173,
      "step": 1
    },
    {
      "epoch": 0.014773776546629732,
      "eval_loss": 3.5129828453063965,
      "eval_runtime": 17.298,
      "eval_samples_per_second": 6.59,
      "eval_steps_per_second": 3.295,
      "step": 1
    },
    {
      "epoch": 0.029547553093259463,
      "grad_norm": 18.17387580871582,
      "learning_rate": 2e-05,
      "loss": 55.3658,
      "step": 2
    },
    {
      "epoch": 0.029547553093259463,
      "eval_loss": 3.4767634868621826,
      "eval_runtime": 4.1027,
      "eval_samples_per_second": 27.787,
      "eval_steps_per_second": 13.893,
      "step": 2
    },
    {
      "epoch": 0.0443213296398892,
      "grad_norm": 25.863922119140625,
      "learning_rate": 3e-05,
      "loss": 55.8648,
      "step": 3
    },
    {
      "epoch": 0.05909510618651893,
      "grad_norm": 20.992795944213867,
      "learning_rate": 4e-05,
      "loss": 57.1646,
      "step": 4
    },
    {
      "epoch": 0.05909510618651893,
      "eval_loss": 3.442988872528076,
      "eval_runtime": 4.1559,
      "eval_samples_per_second": 27.431,
      "eval_steps_per_second": 13.716,
      "step": 4
    },
    {
      "epoch": 0.07386888273314866,
      "grad_norm": 22.0677547454834,
      "learning_rate": 5e-05,
      "loss": 53.4174,
      "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": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}