{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8501594048884166,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.3227437630295753,
      "epoch": 0.08501594048884166,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.518,
      "mean_token_accuracy": 0.7175316952168942,
      "num_tokens": 48910.0,
      "step": 10
    },
    {
      "entropy": 0.7062680356204509,
      "epoch": 0.17003188097768332,
      "grad_norm": 0.439453125,
      "learning_rate": 0.00019973167127614215,
      "loss": 0.7921,
      "mean_token_accuracy": 0.8361715286970138,
      "num_tokens": 96994.0,
      "step": 20
    },
    {
      "entropy": 0.6654534563422203,
      "epoch": 0.255047821466525,
      "grad_norm": 0.46875,
      "learning_rate": 0.00019864405334538517,
      "loss": 0.6723,
      "mean_token_accuracy": 0.848845011740923,
      "num_tokens": 144332.0,
      "step": 30
    },
    {
      "entropy": 0.5781836319714785,
      "epoch": 0.34006376195536664,
      "grad_norm": 0.447265625,
      "learning_rate": 0.00019672948630390294,
      "loss": 0.6044,
      "mean_token_accuracy": 0.8551476895809174,
      "num_tokens": 192719.0,
      "step": 40
    },
    {
      "entropy": 0.5426878597587347,
      "epoch": 0.4250797024442083,
      "grad_norm": 0.466796875,
      "learning_rate": 0.00019400402027796955,
      "loss": 0.5788,
      "mean_token_accuracy": 0.8572557404637337,
      "num_tokens": 241632.0,
      "step": 50
    },
    {
      "entropy": 0.5355116073042154,
      "epoch": 0.51009564293305,
      "grad_norm": 0.5625,
      "learning_rate": 0.00019049050329166778,
      "loss": 0.5629,
      "mean_token_accuracy": 0.862634701281786,
      "num_tokens": 291116.0,
      "step": 60
    },
    {
      "entropy": 0.5224194105714559,
      "epoch": 0.5951115834218916,
      "grad_norm": 0.55078125,
      "learning_rate": 0.00018621838972819458,
      "loss": 0.551,
      "mean_token_accuracy": 0.8659204967319966,
      "num_tokens": 340898.0,
      "step": 70
    },
    {
      "entropy": 0.4716725114732981,
      "epoch": 0.6801275239107333,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00018122349340898595,
      "loss": 0.5116,
      "mean_token_accuracy": 0.8745670169591904,
      "num_tokens": 386799.0,
      "step": 80
    },
    {
      "entropy": 0.4831196520477533,
      "epoch": 0.7651434643995749,
      "grad_norm": 0.54296875,
      "learning_rate": 0.00017554768736063859,
      "loss": 0.5071,
      "mean_token_accuracy": 0.8737691469490528,
      "num_tokens": 436798.0,
      "step": 90
    },
    {
      "entropy": 0.44570639468729495,
      "epoch": 0.8501594048884166,
      "grad_norm": 0.515625,
      "learning_rate": 0.00016923855278653114,
      "loss": 0.465,
      "mean_token_accuracy": 0.8849786855280399,
      "num_tokens": 485573.0,
      "step": 100
    },
    {
      "epoch": 0.8501594048884166,
      "eval_entropy": 0.48599471364702496,
      "eval_loss": 0.475477933883667,
      "eval_mean_token_accuracy": 0.8784565641766503,
      "eval_num_tokens": 485573.0,
      "eval_runtime": 17.16,
      "eval_samples_per_second": 9.732,
      "eval_steps_per_second": 4.895,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 354,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.1536876749848576e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}