{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.473520249221184,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12461059190031153,
      "grad_norm": 2.996091481245303,
      "learning_rate": 2.5e-06,
      "loss": 0.441,
      "step": 10
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 1.509457164389346,
      "learning_rate": 5e-06,
      "loss": 0.3384,
      "step": 20
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 1.5540882760833508,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.2443,
      "step": 30
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 0.5837019331950773,
      "learning_rate": 1e-05,
      "loss": 0.2139,
      "step": 40
    },
    {
      "epoch": 0.6230529595015576,
      "grad_norm": 0.25066734190038364,
      "learning_rate": 9.980973490458728e-06,
      "loss": 0.1431,
      "step": 50
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.3847855364487568,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.1575,
      "step": 60
    },
    {
      "epoch": 0.8722741433021807,
      "grad_norm": 0.5863140592759178,
      "learning_rate": 9.829629131445342e-06,
      "loss": 0.1293,
      "step": 70
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 0.24163113888653256,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.1275,
      "step": 80
    },
    {
      "epoch": 1.1121495327102804,
      "grad_norm": 0.17545609714785104,
      "learning_rate": 9.531538935183252e-06,
      "loss": 0.1211,
      "step": 90
    },
    {
      "epoch": 1.236760124610592,
      "grad_norm": 0.4129092473453207,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.1112,
      "step": 100
    },
    {
      "epoch": 1.3613707165109035,
      "grad_norm": 0.17027543196447287,
      "learning_rate": 9.09576022144496e-06,
      "loss": 0.0986,
      "step": 110
    },
    {
      "epoch": 1.485981308411215,
      "grad_norm": 0.38351119544670076,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.099,
      "step": 120
    },
    {
      "epoch": 1.6105919003115265,
      "grad_norm": 0.35022981475765697,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.1018,
      "step": 130
    },
    {
      "epoch": 1.735202492211838,
      "grad_norm": 0.21063308126485916,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.108,
      "step": 140
    },
    {
      "epoch": 1.8598130841121496,
      "grad_norm": 0.320753628121036,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.0896,
      "step": 150
    },
    {
      "epoch": 1.9844236760124612,
      "grad_norm": 0.17394262959246917,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0899,
      "step": 160
    },
    {
      "epoch": 2.0996884735202492,
      "grad_norm": 0.1604164195468027,
      "learning_rate": 7.113091308703498e-06,
      "loss": 0.0743,
      "step": 170
    },
    {
      "epoch": 2.2242990654205608,
      "grad_norm": 0.1653097854719759,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.0698,
      "step": 180
    },
    {
      "epoch": 2.3489096573208723,
      "grad_norm": 0.17110336957386751,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.0642,
      "step": 190
    },
    {
      "epoch": 2.473520249221184,
      "grad_norm": 0.19194873459564457,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.0768,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.557969321852928e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}