{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04595669465311533,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017675651789659744,
      "eval_loss": 1.5736385583877563,
      "eval_runtime": 18.5113,
      "eval_samples_per_second": 12.911,
      "eval_steps_per_second": 6.483,
      "step": 1
    },
    {
      "epoch": 0.008837825894829872,
      "grad_norm": 1.6883810758590698,
      "learning_rate": 5e-05,
      "loss": 1.4734,
      "step": 5
    },
    {
      "epoch": 0.017675651789659744,
      "grad_norm": 1.110305666923523,
      "learning_rate": 0.0001,
      "loss": 1.4599,
      "step": 10
    },
    {
      "epoch": 0.017675651789659744,
      "eval_loss": 1.436456561088562,
      "eval_runtime": 18.9204,
      "eval_samples_per_second": 12.632,
      "eval_steps_per_second": 6.342,
      "step": 10
    },
    {
      "epoch": 0.026513477684489615,
      "grad_norm": 1.0780854225158691,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.3273,
      "step": 15
    },
    {
      "epoch": 0.03535130357931949,
      "grad_norm": 1.3645310401916504,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2836,
      "step": 20
    },
    {
      "epoch": 0.03535130357931949,
      "eval_loss": 1.2428770065307617,
      "eval_runtime": 18.9823,
      "eval_samples_per_second": 12.591,
      "eval_steps_per_second": 6.322,
      "step": 20
    },
    {
      "epoch": 0.04418912947414936,
      "grad_norm": 0.8436744213104248,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2168,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5733649169252352.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}