{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 6.0,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.4753,
      "mean_token_accuracy": 0.6514762923121452,
      "num_tokens": 9165.0,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.84375,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.3604,
      "mean_token_accuracy": 0.6717274159193038,
      "num_tokens": 19130.0,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.90625,
      "learning_rate": 1.18e-05,
      "loss": 1.2917,
      "mean_token_accuracy": 0.691003431379795,
      "num_tokens": 30279.0,
      "step": 60
    },
    {
      "epoch": 0.08,
      "grad_norm": 30.625,
      "learning_rate": 1.58e-05,
      "loss": 0.9447,
      "mean_token_accuracy": 0.7457822680473327,
      "num_tokens": 42533.0,
      "step": 80
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.875,
      "learning_rate": 1.98e-05,
      "loss": 1.3137,
      "mean_token_accuracy": 0.6690018624067307,
      "num_tokens": 48242.0,
      "step": 100
    },
    {
      "epoch": 0.12,
      "grad_norm": 18.0,
      "learning_rate": 1.988886498744505e-05,
      "loss": 1.0214,
      "mean_token_accuracy": 0.7285905957221985,
      "num_tokens": 59331.0,
      "step": 120
    },
    {
      "epoch": 0.14,
      "grad_norm": 3.515625,
      "learning_rate": 1.953454172319001e-05,
      "loss": 1.0517,
      "mean_token_accuracy": 0.7213401407003402,
      "num_tokens": 68979.0,
      "step": 140
    },
    {
      "epoch": 0.16,
      "grad_norm": 5.9375,
      "learning_rate": 1.894544639838025e-05,
      "loss": 1.1587,
      "mean_token_accuracy": 0.7021817207336426,
      "num_tokens": 76070.0,
      "step": 160
    },
    {
      "epoch": 0.18,
      "grad_norm": 7.0625,
      "learning_rate": 1.8136084495007874e-05,
      "loss": 1.0255,
      "mean_token_accuracy": 0.7250557497143746,
      "num_tokens": 85738.0,
      "step": 180
    },
    {
      "epoch": 0.2,
      "grad_norm": 18.875,
      "learning_rate": 1.7126385189252055e-05,
      "loss": 1.1949,
      "mean_token_accuracy": 0.6837209314107895,
      "num_tokens": 94928.0,
      "step": 200
    },
    {
      "epoch": 0.22,
      "grad_norm": 7.5,
      "learning_rate": 1.594121062902039e-05,
      "loss": 1.0857,
      "mean_token_accuracy": 0.7113691180944443,
      "num_tokens": 104773.0,
      "step": 220
    },
    {
      "epoch": 0.24,
      "grad_norm": 6.625,
      "learning_rate": 1.4609743745354625e-05,
      "loss": 0.9951,
      "mean_token_accuracy": 0.7261969804763794,
      "num_tokens": 114064.0,
      "step": 240
    },
    {
      "epoch": 0.26,
      "grad_norm": 19.125,
      "learning_rate": 1.3164769671815862e-05,
      "loss": 1.0099,
      "mean_token_accuracy": 0.7223263427615165,
      "num_tokens": 123805.0,
      "step": 260
    },
    {
      "epoch": 0.28,
      "grad_norm": 5.03125,
      "learning_rate": 1.164186846568863e-05,
      "loss": 1.0713,
      "mean_token_accuracy": 0.7073337942361831,
      "num_tokens": 134324.0,
      "step": 280
    },
    {
      "epoch": 0.3,
      "grad_norm": 11.5,
      "learning_rate": 1.0078539008887114e-05,
      "loss": 0.9601,
      "mean_token_accuracy": 0.7360554546117782,
      "num_tokens": 143153.0,
      "step": 300
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.9375,
      "learning_rate": 8.51327566103077e-06,
      "loss": 0.9354,
      "mean_token_accuracy": 0.7383034735918045,
      "num_tokens": 154603.0,
      "step": 320
    },
    {
      "epoch": 0.34,
      "grad_norm": 6.875,
      "learning_rate": 6.984620400555044e-06,
      "loss": 0.9676,
      "mean_token_accuracy": 0.7273150086402893,
      "num_tokens": 167175.0,
      "step": 340
    },
    {
      "epoch": 0.36,
      "grad_norm": 17.625,
      "learning_rate": 5.53021379328879e-06,
      "loss": 1.085,
      "mean_token_accuracy": 0.715969854593277,
      "num_tokens": 176751.0,
      "step": 360
    },
    {
      "epoch": 0.38,
      "grad_norm": 6.0625,
      "learning_rate": 4.185868156801695e-06,
      "loss": 1.0635,
      "mean_token_accuracy": 0.7170247107744216,
      "num_tokens": 185233.0,
      "step": 380
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.25,
      "learning_rate": 2.9846857422914434e-06,
      "loss": 1.0838,
      "mean_token_accuracy": 0.7044813245534897,
      "num_tokens": 193072.0,
      "step": 400
    },
    {
      "epoch": 0.42,
      "grad_norm": 6.21875,
      "learning_rate": 1.956243647299155e-06,
      "loss": 1.006,
      "mean_token_accuracy": 0.7172566086053849,
      "num_tokens": 204372.0,
      "step": 420
    },
    {
      "epoch": 0.44,
      "grad_norm": 11.8125,
      "learning_rate": 1.1258655294071686e-06,
      "loss": 0.9791,
      "mean_token_accuracy": 0.727970740199089,
      "num_tokens": 216681.0,
      "step": 440
    },
    {
      "epoch": 0.46,
      "grad_norm": 5.5,
      "learning_rate": 5.13998053744954e-07,
      "loss": 1.0866,
      "mean_token_accuracy": 0.7147636383771896,
      "num_tokens": 226708.0,
      "step": 460
    },
    {
      "epoch": 0.48,
      "grad_norm": 11.5,
      "learning_rate": 1.357074282350457e-07,
      "loss": 1.01,
      "mean_token_accuracy": 0.7146593451499939,
      "num_tokens": 237866.0,
      "step": 480
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.90625,
      "learning_rate": 3.0842355210336515e-10,
      "loss": 1.1541,
      "mean_token_accuracy": 0.68363136947155,
      "num_tokens": 245487.0,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.0414470479035392e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}