{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06336884629094222,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0031684423145471106,
      "grad_norm": 0.19819921255111694,
      "learning_rate": 1.08e-05,
      "loss": 4.8784,
      "step": 10
    },
    {
      "epoch": 0.006336884629094221,
      "grad_norm": 0.34108418226242065,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 5.0786,
      "step": 20
    },
    {
      "epoch": 0.009505326943641333,
      "grad_norm": 0.2952434718608856,
      "learning_rate": 3.48e-05,
      "loss": 5.0088,
      "step": 30
    },
    {
      "epoch": 0.012673769258188443,
      "grad_norm": 0.41625794768333435,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 4.8262,
      "step": 40
    },
    {
      "epoch": 0.015842211572735555,
      "grad_norm": 1.1918175220489502,
      "learning_rate": 5.88e-05,
      "loss": 5.459,
      "step": 50
    },
    {
      "epoch": 0.019010653887282666,
      "grad_norm": 0.47633519768714905,
      "learning_rate": 5.999969438702549e-05,
      "loss": 5.6355,
      "step": 60
    },
    {
      "epoch": 0.022179096201829774,
      "grad_norm": 0.4251032769680023,
      "learning_rate": 5.999863795510765e-05,
      "loss": 5.5395,
      "step": 70
    },
    {
      "epoch": 0.025347538516376885,
      "grad_norm": 0.3730669617652893,
      "learning_rate": 5.999682695781323e-05,
      "loss": 5.539,
      "step": 80
    },
    {
      "epoch": 0.028515980830923996,
      "grad_norm": 0.3352891504764557,
      "learning_rate": 5.9994261440694826e-05,
      "loss": 5.5067,
      "step": 90
    },
    {
      "epoch": 0.03168442314547111,
      "grad_norm": 0.5066033005714417,
      "learning_rate": 5.9990941468283724e-05,
      "loss": 5.6052,
      "step": 100
    },
    {
      "epoch": 0.03485286546001822,
      "grad_norm": 0.4155944585800171,
      "learning_rate": 5.998686712408824e-05,
      "loss": 5.2992,
      "step": 110
    },
    {
      "epoch": 0.03802130777456533,
      "grad_norm": 0.4713999927043915,
      "learning_rate": 5.998203851059168e-05,
      "loss": 5.4492,
      "step": 120
    },
    {
      "epoch": 0.04118975008911244,
      "grad_norm": 0.32726186513900757,
      "learning_rate": 5.99764557492497e-05,
      "loss": 5.3036,
      "step": 130
    },
    {
      "epoch": 0.04435819240365955,
      "grad_norm": 0.4011114537715912,
      "learning_rate": 5.99701189804873e-05,
      "loss": 5.3122,
      "step": 140
    },
    {
      "epoch": 0.04752663471820666,
      "grad_norm": 0.46287617087364197,
      "learning_rate": 5.9963028363695244e-05,
      "loss": 5.3803,
      "step": 150
    },
    {
      "epoch": 0.05069507703275377,
      "grad_norm": 0.4292086660861969,
      "learning_rate": 5.995518407722611e-05,
      "loss": 5.1361,
      "step": 160
    },
    {
      "epoch": 0.05386351934730088,
      "grad_norm": 0.46384045481681824,
      "learning_rate": 5.994658631838974e-05,
      "loss": 5.226,
      "step": 170
    },
    {
      "epoch": 0.05703196166184799,
      "grad_norm": 0.41396230459213257,
      "learning_rate": 5.993723530344834e-05,
      "loss": 5.1451,
      "step": 180
    },
    {
      "epoch": 0.0602004039763951,
      "grad_norm": 0.5476190447807312,
      "learning_rate": 5.9927131267610975e-05,
      "loss": 5.1318,
      "step": 190
    },
    {
      "epoch": 0.06336884629094222,
      "grad_norm": 0.6672335267066956,
      "learning_rate": 5.991627446502772e-05,
      "loss": 5.188,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 6314,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.476117904556032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}