{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02577873254564984,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 2.911787986755371,
      "eval_runtime": 41.3304,
      "eval_samples_per_second": 11.856,
      "eval_steps_per_second": 5.928,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 1.9756550788879395,
      "learning_rate": 6e-05,
      "loss": 2.9415,
      "step": 3
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 1.293572187423706,
      "learning_rate": 0.00012,
      "loss": 2.8196,
      "step": 6
    },
    {
      "epoch": 0.006874328678839957,
      "eval_loss": 2.6146702766418457,
      "eval_runtime": 41.2297,
      "eval_samples_per_second": 11.885,
      "eval_steps_per_second": 5.942,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 1.6168307065963745,
      "learning_rate": 0.00018,
      "loss": 2.5556,
      "step": 9
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 1.1966177225112915,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.3944,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 1.1105034351348877,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.4451,
      "step": 15
    },
    {
      "epoch": 0.013748657357679914,
      "eval_loss": 2.342407703399658,
      "eval_runtime": 41.2779,
      "eval_samples_per_second": 11.871,
      "eval_steps_per_second": 5.935,
      "step": 16
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 0.9284036159515381,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.3047,
      "step": 18
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 1.0800807476043701,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.3978,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.9313790798187256,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.1733,
      "step": 24
    },
    {
      "epoch": 0.02062298603651987,
      "eval_loss": 2.262237310409546,
      "eval_runtime": 41.339,
      "eval_samples_per_second": 11.853,
      "eval_steps_per_second": 5.927,
      "step": 24
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 0.9361584782600403,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.1214,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 1.0451148748397827,
      "learning_rate": 0.0,
      "loss": 2.2597,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}