{
  "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": 19872.2890625,
      "learning_rate": 3e-07,
      "loss": 8.7939,
      "step": 10
    },
    {
      "epoch": 0.00419969552207465,
      "grad_norm": 1458.198974609375,
      "learning_rate": 1.2999999999999998e-06,
      "loss": 8.1117,
      "step": 20
    },
    {
      "epoch": 0.006299543283111974,
      "grad_norm": 297.6234130859375,
      "learning_rate": 2.2999999999999996e-06,
      "loss": 7.3977,
      "step": 30
    },
    {
      "epoch": 0.0083993910441493,
      "grad_norm": 426.92987060546875,
      "learning_rate": 3.2999999999999993e-06,
      "loss": 7.2069,
      "step": 40
    },
    {
      "epoch": 0.010499238805186623,
      "grad_norm": 474.7532653808594,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 7.08,
      "step": 50
    },
    {
      "epoch": 0.012599086566223949,
      "grad_norm": 1569.4381103515625,
      "learning_rate": 5.3e-06,
      "loss": 7.0092,
      "step": 60
    },
    {
      "epoch": 0.014698934327261274,
      "grad_norm": 1407.21142578125,
      "learning_rate": 6.3e-06,
      "loss": 6.9929,
      "step": 70
    },
    {
      "epoch": 0.0167987820882986,
      "grad_norm": 500.49493408203125,
      "learning_rate": 7.299999999999999e-06,
      "loss": 6.9501,
      "step": 80
    },
    {
      "epoch": 0.018898629849335925,
      "grad_norm": 442.69537353515625,
      "learning_rate": 8.299999999999998e-06,
      "loss": 6.9001,
      "step": 90
    },
    {
      "epoch": 0.020998477610373247,
      "grad_norm": 1423.2950439453125,
      "learning_rate": 9.299999999999999e-06,
      "loss": 6.9037,
      "step": 100
    },
    {
      "epoch": 0.023098325371410572,
      "grad_norm": 448.7774963378906,
      "learning_rate": 1.03e-05,
      "loss": 6.8732,
      "step": 110
    },
    {
      "epoch": 0.025198173132447897,
      "grad_norm": 711.8992919921875,
      "learning_rate": 1.1299999999999999e-05,
      "loss": 6.8381,
      "step": 120
    },
    {
      "epoch": 0.027298020893485223,
      "grad_norm": 884.006591796875,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 6.8462,
      "step": 130
    },
    {
      "epoch": 0.029397868654522548,
      "grad_norm": 96.5859375,
      "learning_rate": 1.33e-05,
      "loss": 6.8433,
      "step": 140
    },
    {
      "epoch": 0.03149771641555987,
      "grad_norm": 91.52490997314453,
      "learning_rate": 1.43e-05,
      "loss": 6.8171,
      "step": 150
    },
    {
      "epoch": 0.0335975641765972,
      "grad_norm": 354.9374084472656,
      "learning_rate": 1.53e-05,
      "loss": 6.7899,
      "step": 160
    },
    {
      "epoch": 0.035697411937634524,
      "grad_norm": 189.09506225585938,
      "learning_rate": 1.6299999999999996e-05,
      "loss": 6.7456,
      "step": 170
    },
    {
      "epoch": 0.03779725969867185,
      "grad_norm": 170.39376831054688,
      "learning_rate": 1.7299999999999997e-05,
      "loss": 6.7505,
      "step": 180
    },
    {
      "epoch": 0.03989710745970917,
      "grad_norm": 193.9166259765625,
      "learning_rate": 1.8299999999999998e-05,
      "loss": 6.752,
      "step": 190
    },
    {
      "epoch": 0.04199695522074649,
      "grad_norm": 336.08624267578125,
      "learning_rate": 1.93e-05,
      "loss": 6.7015,
      "step": 200
    },
    {
      "epoch": 0.04409680298178382,
      "grad_norm": 307.40557861328125,
      "learning_rate": 2.03e-05,
      "loss": 6.7024,
      "step": 210
    },
    {
      "epoch": 0.046196650742821144,
      "grad_norm": 175.94061279296875,
      "learning_rate": 2.1299999999999996e-05,
      "loss": 6.6639,
      "step": 220
    },
    {
      "epoch": 0.04829649850385847,
      "grad_norm": 496.3529052734375,
      "learning_rate": 2.23e-05,
      "loss": 6.6309,
      "step": 230
    },
    {
      "epoch": 0.050396346264895794,
      "grad_norm": 112.63114929199219,
      "learning_rate": 2.3299999999999997e-05,
      "loss": 6.6146,
      "step": 240
    },
    {
      "epoch": 0.05249619402593312,
      "grad_norm": 141.9170379638672,
      "learning_rate": 2.4299999999999998e-05,
      "loss": 6.6386,
      "step": 250
    },
    {
      "epoch": 0.054596041786970445,
      "grad_norm": 120.92185974121094,
      "learning_rate": 2.53e-05,
      "loss": 6.6323,
      "step": 260
    },
    {
      "epoch": 0.05669588954800777,
      "grad_norm": 241.84129333496094,
      "learning_rate": 2.63e-05,
      "loss": 6.598,
      "step": 270
    },
    {
      "epoch": 0.058795737309045096,
      "grad_norm": 115.57807159423828,
      "learning_rate": 2.7299999999999996e-05,
      "loss": 6.5549,
      "step": 280
    },
    {
      "epoch": 0.06089558507008242,
      "grad_norm": 99.67350769042969,
      "learning_rate": 2.83e-05,
      "loss": 6.5484,
      "step": 290
    },
    {
      "epoch": 0.06299543283111975,
      "grad_norm": 105.20110321044922,
      "learning_rate": 2.9299999999999997e-05,
      "loss": 6.5416,
      "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
}