{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06299543283111975,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002099847761037325,
      "grad_norm": 22925.884765625,
      "learning_rate": 1.9999999999999996e-07,
      "loss": 9.5004,
      "step": 10
    },
    {
      "epoch": 0.00419969552207465,
      "grad_norm": 1589.221435546875,
      "learning_rate": 1.2e-06,
      "loss": 8.7173,
      "step": 20
    },
    {
      "epoch": 0.006299543283111974,
      "grad_norm": 577.2943115234375,
      "learning_rate": 2.1999999999999997e-06,
      "loss": 7.6284,
      "step": 30
    },
    {
      "epoch": 0.0083993910441493,
      "grad_norm": 308.8800048828125,
      "learning_rate": 3.1999999999999994e-06,
      "loss": 7.2988,
      "step": 40
    },
    {
      "epoch": 0.010499238805186623,
      "grad_norm": 458.5738220214844,
      "learning_rate": 4.2e-06,
      "loss": 7.1397,
      "step": 50
    },
    {
      "epoch": 0.012599086566223949,
      "grad_norm": 2117.726806640625,
      "learning_rate": 5.199999999999999e-06,
      "loss": 7.0424,
      "step": 60
    },
    {
      "epoch": 0.014698934327261274,
      "grad_norm": 784.7866821289062,
      "learning_rate": 6.199999999999999e-06,
      "loss": 6.9896,
      "step": 70
    },
    {
      "epoch": 0.0167987820882986,
      "grad_norm": 719.2965087890625,
      "learning_rate": 7.2e-06,
      "loss": 6.9514,
      "step": 80
    },
    {
      "epoch": 0.018898629849335925,
      "grad_norm": 887.7239379882812,
      "learning_rate": 8.2e-06,
      "loss": 6.9188,
      "step": 90
    },
    {
      "epoch": 0.020998477610373247,
      "grad_norm": 657.1996459960938,
      "learning_rate": 9.199999999999998e-06,
      "loss": 6.9113,
      "step": 100
    },
    {
      "epoch": 0.023098325371410572,
      "grad_norm": 1241.19482421875,
      "learning_rate": 1.02e-05,
      "loss": 6.8953,
      "step": 110
    },
    {
      "epoch": 0.025198173132447897,
      "grad_norm": 411.5585021972656,
      "learning_rate": 1.12e-05,
      "loss": 6.8474,
      "step": 120
    },
    {
      "epoch": 0.027298020893485223,
      "grad_norm": 1062.7774658203125,
      "learning_rate": 1.2199999999999998e-05,
      "loss": 6.8514,
      "step": 130
    },
    {
      "epoch": 0.029397868654522548,
      "grad_norm": 148.0970001220703,
      "learning_rate": 1.3199999999999997e-05,
      "loss": 6.8698,
      "step": 140
    },
    {
      "epoch": 0.03149771641555987,
      "grad_norm": 280.5868835449219,
      "learning_rate": 1.4199999999999998e-05,
      "loss": 6.8395,
      "step": 150
    },
    {
      "epoch": 0.0335975641765972,
      "grad_norm": 407.1022644042969,
      "learning_rate": 1.5199999999999998e-05,
      "loss": 6.8029,
      "step": 160
    },
    {
      "epoch": 0.035697411937634524,
      "grad_norm": 166.18153381347656,
      "learning_rate": 1.6199999999999997e-05,
      "loss": 6.7946,
      "step": 170
    },
    {
      "epoch": 0.03779725969867185,
      "grad_norm": 234.69805908203125,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 6.7898,
      "step": 180
    },
    {
      "epoch": 0.03989710745970917,
      "grad_norm": 917.2261352539062,
      "learning_rate": 1.82e-05,
      "loss": 6.7996,
      "step": 190
    },
    {
      "epoch": 0.04199695522074649,
      "grad_norm": 237.35519409179688,
      "learning_rate": 1.92e-05,
      "loss": 6.7733,
      "step": 200
    },
    {
      "epoch": 0.04409680298178382,
      "grad_norm": 49.55766296386719,
      "learning_rate": 2.0199999999999996e-05,
      "loss": 6.7318,
      "step": 210
    },
    {
      "epoch": 0.046196650742821144,
      "grad_norm": 152.66554260253906,
      "learning_rate": 2.12e-05,
      "loss": 6.6867,
      "step": 220
    },
    {
      "epoch": 0.04829649850385847,
      "grad_norm": 284.306640625,
      "learning_rate": 2.2199999999999998e-05,
      "loss": 6.6555,
      "step": 230
    },
    {
      "epoch": 0.050396346264895794,
      "grad_norm": 127.93234252929688,
      "learning_rate": 2.3199999999999998e-05,
      "loss": 6.6263,
      "step": 240
    },
    {
      "epoch": 0.05249619402593312,
      "grad_norm": 119.77033996582031,
      "learning_rate": 2.42e-05,
      "loss": 6.649,
      "step": 250
    },
    {
      "epoch": 0.054596041786970445,
      "grad_norm": 389.56536865234375,
      "learning_rate": 2.52e-05,
      "loss": 6.6383,
      "step": 260
    },
    {
      "epoch": 0.05669588954800777,
      "grad_norm": 427.01580810546875,
      "learning_rate": 2.6199999999999996e-05,
      "loss": 6.593,
      "step": 270
    },
    {
      "epoch": 0.058795737309045096,
      "grad_norm": 222.83114624023438,
      "learning_rate": 2.72e-05,
      "loss": 6.5701,
      "step": 280
    },
    {
      "epoch": 0.06089558507008242,
      "grad_norm": 92.09854125976562,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 6.5495,
      "step": 290
    },
    {
      "epoch": 0.06299543283111975,
      "grad_norm": 137.1016082763672,
      "learning_rate": 2.9199999999999995e-05,
      "loss": 6.5433,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 21,
  "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": 1.96087582224384e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}