{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 17799,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08427439743805831,
      "grad_norm": 2.7859835624694824,
      "learning_rate": 4.85954267093657e-05,
      "loss": 1.5305,
      "step": 500
    },
    {
      "epoch": 0.16854879487611663,
      "grad_norm": 2.8764379024505615,
      "learning_rate": 4.719085341873139e-05,
      "loss": 1.392,
      "step": 1000
    },
    {
      "epoch": 0.25282319231417494,
      "grad_norm": 2.9515156745910645,
      "learning_rate": 4.578628012809709e-05,
      "loss": 1.3312,
      "step": 1500
    },
    {
      "epoch": 0.33709758975223325,
      "grad_norm": 2.6709630489349365,
      "learning_rate": 4.438170683746278e-05,
      "loss": 1.294,
      "step": 2000
    },
    {
      "epoch": 0.42137198719029156,
      "grad_norm": 2.601968765258789,
      "learning_rate": 4.2977133546828475e-05,
      "loss": 1.2561,
      "step": 2500
    },
    {
      "epoch": 0.5056463846283499,
      "grad_norm": 2.6964409351348877,
      "learning_rate": 4.157256025619417e-05,
      "loss": 1.2364,
      "step": 3000
    },
    {
      "epoch": 0.5899207820664082,
      "grad_norm": 2.479663610458374,
      "learning_rate": 4.016798696555987e-05,
      "loss": 1.215,
      "step": 3500
    },
    {
      "epoch": 0.6741951795044665,
      "grad_norm": 2.6350433826446533,
      "learning_rate": 3.876341367492556e-05,
      "loss": 1.1925,
      "step": 4000
    },
    {
      "epoch": 0.7584695769425248,
      "grad_norm": 2.7347450256347656,
      "learning_rate": 3.7358840384291254e-05,
      "loss": 1.1831,
      "step": 4500
    },
    {
      "epoch": 0.8427439743805831,
      "grad_norm": 2.7404720783233643,
      "learning_rate": 3.5954267093656953e-05,
      "loss": 1.1657,
      "step": 5000
    },
    {
      "epoch": 0.9270183718186416,
      "grad_norm": 2.71294903755188,
      "learning_rate": 3.454969380302264e-05,
      "loss": 1.1629,
      "step": 5500
    },
    {
      "epoch": 1.0112927692566998,
      "grad_norm": 2.6705377101898193,
      "learning_rate": 3.314512051238834e-05,
      "loss": 1.1435,
      "step": 6000
    },
    {
      "epoch": 1.0955671666947582,
      "grad_norm": 2.524048089981079,
      "learning_rate": 3.174054722175403e-05,
      "loss": 1.1304,
      "step": 6500
    },
    {
      "epoch": 1.1798415641328164,
      "grad_norm": 2.6250593662261963,
      "learning_rate": 3.0335973931119726e-05,
      "loss": 1.1167,
      "step": 7000
    },
    {
      "epoch": 1.2641159615708748,
      "grad_norm": 2.3546817302703857,
      "learning_rate": 2.8931400640485422e-05,
      "loss": 1.1121,
      "step": 7500
    },
    {
      "epoch": 1.348390359008933,
      "grad_norm": 2.7167067527770996,
      "learning_rate": 2.7526827349851115e-05,
      "loss": 1.1065,
      "step": 8000
    },
    {
      "epoch": 1.4326647564469914,
      "grad_norm": 2.4628195762634277,
      "learning_rate": 2.6122254059216812e-05,
      "loss": 1.0953,
      "step": 8500
    },
    {
      "epoch": 1.5169391538850499,
      "grad_norm": 2.47514009475708,
      "learning_rate": 2.4717680768582505e-05,
      "loss": 1.0898,
      "step": 9000
    },
    {
      "epoch": 1.601213551323108,
      "grad_norm": 2.240252733230591,
      "learning_rate": 2.33131074779482e-05,
      "loss": 1.0734,
      "step": 9500
    },
    {
      "epoch": 1.6854879487611663,
      "grad_norm": 2.6827552318573,
      "learning_rate": 2.1908534187313894e-05,
      "loss": 1.0771,
      "step": 10000
    },
    {
      "epoch": 1.7697623461992247,
      "grad_norm": 2.446568012237549,
      "learning_rate": 2.0503960896679587e-05,
      "loss": 1.0727,
      "step": 10500
    },
    {
      "epoch": 1.854036743637283,
      "grad_norm": 2.437731981277466,
      "learning_rate": 1.9099387606045284e-05,
      "loss": 1.0573,
      "step": 11000
    },
    {
      "epoch": 1.9383111410753413,
      "grad_norm": 2.6201038360595703,
      "learning_rate": 1.769481431541098e-05,
      "loss": 1.0561,
      "step": 11500
    },
    {
      "epoch": 2.0225855385133995,
      "grad_norm": 2.4613335132598877,
      "learning_rate": 1.6290241024776673e-05,
      "loss": 1.0531,
      "step": 12000
    },
    {
      "epoch": 2.106859935951458,
      "grad_norm": 2.459319591522217,
      "learning_rate": 1.488566773414237e-05,
      "loss": 1.0409,
      "step": 12500
    },
    {
      "epoch": 2.1911343333895164,
      "grad_norm": 2.536198616027832,
      "learning_rate": 1.3481094443508063e-05,
      "loss": 1.0388,
      "step": 13000
    },
    {
      "epoch": 2.2754087308275746,
      "grad_norm": 2.503535270690918,
      "learning_rate": 1.2076521152873758e-05,
      "loss": 1.0326,
      "step": 13500
    },
    {
      "epoch": 2.3596831282656328,
      "grad_norm": 2.47710919380188,
      "learning_rate": 1.0671947862239452e-05,
      "loss": 1.0246,
      "step": 14000
    },
    {
      "epoch": 2.4439575257036914,
      "grad_norm": 2.4275453090667725,
      "learning_rate": 9.267374571605147e-06,
      "loss": 1.0228,
      "step": 14500
    },
    {
      "epoch": 2.5282319231417496,
      "grad_norm": 2.4777779579162598,
      "learning_rate": 7.862801280970842e-06,
      "loss": 1.029,
      "step": 15000
    },
    {
      "epoch": 2.612506320579808,
      "grad_norm": 2.574960470199585,
      "learning_rate": 6.458227990336537e-06,
      "loss": 1.0215,
      "step": 15500
    },
    {
      "epoch": 2.696780718017866,
      "grad_norm": 2.5446507930755615,
      "learning_rate": 5.053654699702231e-06,
      "loss": 1.0206,
      "step": 16000
    },
    {
      "epoch": 2.7810551154559247,
      "grad_norm": 2.7360856533050537,
      "learning_rate": 3.6490814090679254e-06,
      "loss": 1.0215,
      "step": 16500
    },
    {
      "epoch": 2.865329512893983,
      "grad_norm": 2.4522464275360107,
      "learning_rate": 2.2445081184336198e-06,
      "loss": 1.017,
      "step": 17000
    },
    {
      "epoch": 2.949603910332041,
      "grad_norm": 2.5468955039978027,
      "learning_rate": 8.399348277993145e-07,
      "loss": 1.0105,
      "step": 17500
    }
  ],
  "logging_steps": 500,
  "max_steps": 17799,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4989245699264307e+17,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}