{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7590132827324478,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07590132827324478,
      "grad_norm": 22.0,
      "learning_rate": 9e-08,
      "loss": 1.0496648788452148,
      "step": 10
    },
    {
      "epoch": 0.15180265654648956,
      "grad_norm": 21.5,
      "learning_rate": 1.8999999999999998e-07,
      "loss": 1.0672600746154786,
      "step": 20
    },
    {
      "epoch": 0.22770398481973433,
      "grad_norm": 23.375,
      "learning_rate": 2.9e-07,
      "loss": 1.074104118347168,
      "step": 30
    },
    {
      "epoch": 0.3036053130929791,
      "grad_norm": 19.0,
      "learning_rate": 3.8999999999999997e-07,
      "loss": 1.0784456253051757,
      "step": 40
    },
    {
      "epoch": 0.3795066413662239,
      "grad_norm": 21.25,
      "learning_rate": 4.9e-07,
      "loss": 1.0631229400634765,
      "step": 50
    },
    {
      "epoch": 0.45540796963946867,
      "grad_norm": 18.625,
      "learning_rate": 5.9e-07,
      "loss": 1.0021364212036132,
      "step": 60
    },
    {
      "epoch": 0.5313092979127134,
      "grad_norm": 19.625,
      "learning_rate": 6.9e-07,
      "loss": 1.0368730545043945,
      "step": 70
    },
    {
      "epoch": 0.6072106261859582,
      "grad_norm": 13.1875,
      "learning_rate": 7.9e-07,
      "loss": 0.9585152626037597,
      "step": 80
    },
    {
      "epoch": 0.683111954459203,
      "grad_norm": 10.4375,
      "learning_rate": 8.9e-07,
      "loss": 0.8780872344970703,
      "step": 90
    },
    {
      "epoch": 0.7590132827324478,
      "grad_norm": 6.84375,
      "learning_rate": 9.9e-07,
      "loss": 0.8695860862731933,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 396,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7.816482044765798e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}