{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002127885945313331,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021278859453133312,
      "grad_norm": 1.1664152145385742,
      "learning_rate": 2e-05,
      "loss": 2.008,
      "step": 1
    },
    {
      "epoch": 0.00021278859453133312,
      "eval_loss": 2.0041871070861816,
      "eval_runtime": 75.2173,
      "eval_samples_per_second": 26.31,
      "eval_steps_per_second": 13.162,
      "step": 1
    },
    {
      "epoch": 0.00042557718906266625,
      "grad_norm": 1.2407472133636475,
      "learning_rate": 4e-05,
      "loss": 2.2227,
      "step": 2
    },
    {
      "epoch": 0.0006383657835939994,
      "grad_norm": 1.261441707611084,
      "learning_rate": 6e-05,
      "loss": 1.785,
      "step": 3
    },
    {
      "epoch": 0.0006383657835939994,
      "eval_loss": 1.9936246871948242,
      "eval_runtime": 75.2505,
      "eval_samples_per_second": 26.299,
      "eval_steps_per_second": 13.156,
      "step": 3
    },
    {
      "epoch": 0.0008511543781253325,
      "grad_norm": 1.1903585195541382,
      "learning_rate": 8e-05,
      "loss": 1.9018,
      "step": 4
    },
    {
      "epoch": 0.0010639429726566655,
      "grad_norm": 1.007890224456787,
      "learning_rate": 0.0001,
      "loss": 1.8362,
      "step": 5
    },
    {
      "epoch": 0.0012767315671879987,
      "grad_norm": 1.1920151710510254,
      "learning_rate": 0.00012,
      "loss": 2.002,
      "step": 6
    },
    {
      "epoch": 0.0012767315671879987,
      "eval_loss": 1.8736934661865234,
      "eval_runtime": 75.3093,
      "eval_samples_per_second": 26.278,
      "eval_steps_per_second": 13.146,
      "step": 6
    },
    {
      "epoch": 0.0014895201617193318,
      "grad_norm": 1.2574443817138672,
      "learning_rate": 0.00014,
      "loss": 1.8933,
      "step": 7
    },
    {
      "epoch": 0.001702308756250665,
      "grad_norm": 1.0934723615646362,
      "learning_rate": 0.00016,
      "loss": 2.0618,
      "step": 8
    },
    {
      "epoch": 0.001915097350781998,
      "grad_norm": 0.88877934217453,
      "learning_rate": 0.00018,
      "loss": 1.5823,
      "step": 9
    },
    {
      "epoch": 0.001915097350781998,
      "eval_loss": 1.7316648960113525,
      "eval_runtime": 75.2991,
      "eval_samples_per_second": 26.282,
      "eval_steps_per_second": 13.148,
      "step": 9
    },
    {
      "epoch": 0.002127885945313331,
      "grad_norm": 1.0102648735046387,
      "learning_rate": 0.0002,
      "loss": 1.7388,
      "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": 1000194661416960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}