{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3232758620689655,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021551724137931036,
      "grad_norm": 20.742843627929688,
      "learning_rate": 1.002155172413793e-06,
      "loss": 2.152,
      "step": 100
    },
    {
      "epoch": 0.04310344827586207,
      "grad_norm": 7.82145357131958,
      "learning_rate": 2.079741379310345e-06,
      "loss": 0.677,
      "step": 200
    },
    {
      "epoch": 0.06465517241379311,
      "grad_norm": 51.326385498046875,
      "learning_rate": 3.157327586206897e-06,
      "loss": 0.5383,
      "step": 300
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 22.487550735473633,
      "learning_rate": 4.234913793103448e-06,
      "loss": 0.481,
      "step": 400
    },
    {
      "epoch": 0.10775862068965517,
      "grad_norm": 37.75484085083008,
      "learning_rate": 5.3125e-06,
      "loss": 0.4856,
      "step": 500
    },
    {
      "epoch": 0.12931034482758622,
      "grad_norm": 27.280712127685547,
      "learning_rate": 6.3900862068965515e-06,
      "loss": 0.4785,
      "step": 600
    },
    {
      "epoch": 0.15086206896551724,
      "grad_norm": 38.151546478271484,
      "learning_rate": 7.467672413793104e-06,
      "loss": 0.4623,
      "step": 700
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 25.77330780029297,
      "learning_rate": 8.545258620689656e-06,
      "loss": 0.4584,
      "step": 800
    },
    {
      "epoch": 0.1939655172413793,
      "grad_norm": 22.47431755065918,
      "learning_rate": 9.622844827586207e-06,
      "loss": 0.4572,
      "step": 900
    },
    {
      "epoch": 0.21551724137931033,
      "grad_norm": 9.425881385803223,
      "learning_rate": 9.922174329501917e-06,
      "loss": 0.4247,
      "step": 1000
    },
    {
      "epoch": 0.23706896551724138,
      "grad_norm": 19.910789489746094,
      "learning_rate": 9.802442528735633e-06,
      "loss": 0.4208,
      "step": 1100
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 16.591716766357422,
      "learning_rate": 9.68271072796935e-06,
      "loss": 0.4366,
      "step": 1200
    },
    {
      "epoch": 0.2801724137931034,
      "grad_norm": 20.817670822143555,
      "learning_rate": 9.562978927203065e-06,
      "loss": 0.3789,
      "step": 1300
    },
    {
      "epoch": 0.3017241379310345,
      "grad_norm": 18.30855369567871,
      "learning_rate": 9.443247126436782e-06,
      "loss": 0.4443,
      "step": 1400
    },
    {
      "epoch": 0.3232758620689655,
      "grad_norm": 26.79413414001465,
      "learning_rate": 9.3235153256705e-06,
      "loss": 0.4019,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 9280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}