{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1042,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04798464491362764,
      "grad_norm": 2.3414368629455566,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.1543,
      "step": 50
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 2.155992269515991,
      "learning_rate": 4.714285714285714e-05,
      "loss": 0.6884,
      "step": 100
    },
    {
      "epoch": 0.14395393474088292,
      "grad_norm": 2.1222732067108154,
      "learning_rate": 4.765208110992529e-05,
      "loss": 0.5902,
      "step": 150
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 1.771121859550476,
      "learning_rate": 4.4983991462113126e-05,
      "loss": 0.5362,
      "step": 200
    },
    {
      "epoch": 0.2399232245681382,
      "grad_norm": 1.8430039882659912,
      "learning_rate": 4.231590181430096e-05,
      "loss": 0.5196,
      "step": 250
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 1.9631397724151611,
      "learning_rate": 3.9647812166488794e-05,
      "loss": 0.4757,
      "step": 300
    },
    {
      "epoch": 0.33589251439539347,
      "grad_norm": 1.9073326587677002,
      "learning_rate": 3.697972251867663e-05,
      "loss": 0.477,
      "step": 350
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 1.7632094621658325,
      "learning_rate": 3.431163287086446e-05,
      "loss": 0.4604,
      "step": 400
    },
    {
      "epoch": 0.43186180422264875,
      "grad_norm": 1.7176055908203125,
      "learning_rate": 3.16435432230523e-05,
      "loss": 0.4363,
      "step": 450
    },
    {
      "epoch": 0.4798464491362764,
      "grad_norm": 1.6267833709716797,
      "learning_rate": 2.897545357524013e-05,
      "loss": 0.4291,
      "step": 500
    },
    {
      "epoch": 0.527831094049904,
      "grad_norm": 1.6887868642807007,
      "learning_rate": 2.6307363927427965e-05,
      "loss": 0.4192,
      "step": 550
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 1.4798693656921387,
      "learning_rate": 2.3639274279615796e-05,
      "loss": 0.4287,
      "step": 600
    },
    {
      "epoch": 0.6238003838771593,
      "grad_norm": 1.5440646409988403,
      "learning_rate": 2.097118463180363e-05,
      "loss": 0.4093,
      "step": 650
    },
    {
      "epoch": 0.6717850287907869,
      "grad_norm": 1.4985594749450684,
      "learning_rate": 1.830309498399146e-05,
      "loss": 0.4118,
      "step": 700
    },
    {
      "epoch": 0.7197696737044146,
      "grad_norm": 1.6520227193832397,
      "learning_rate": 1.5635005336179295e-05,
      "loss": 0.3923,
      "step": 750
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 1.6517823934555054,
      "learning_rate": 1.2966915688367129e-05,
      "loss": 0.4183,
      "step": 800
    },
    {
      "epoch": 0.8157389635316699,
      "grad_norm": 1.7299295663833618,
      "learning_rate": 1.0298826040554963e-05,
      "loss": 0.3991,
      "step": 850
    },
    {
      "epoch": 0.8637236084452975,
      "grad_norm": 1.717519998550415,
      "learning_rate": 7.630736392742796e-06,
      "loss": 0.3947,
      "step": 900
    },
    {
      "epoch": 0.9117082533589251,
      "grad_norm": 1.5044348239898682,
      "learning_rate": 4.96264674493063e-06,
      "loss": 0.3777,
      "step": 950
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 1.5577826499938965,
      "learning_rate": 2.294557097118463e-06,
      "loss": 0.3942,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1042,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}