{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.5484622716903687,
      "epoch": 0.2,
      "grad_norm": 4.228063106536865,
      "learning_rate": 0.0,
      "loss": 1.4888970851898193,
      "mean_token_accuracy": 0.7744107842445374,
      "num_tokens": 11224.0,
      "step": 1
    },
    {
      "entropy": 0.42378363013267517,
      "epoch": 0.4,
      "grad_norm": 5.219785690307617,
      "learning_rate": 0.0002,
      "loss": 1.1912707090377808,
      "mean_token_accuracy": 0.82523512840271,
      "num_tokens": 22945.0,
      "step": 2
    },
    {
      "epoch": 0.4,
      "eval_entropy": 0.5992160042126974,
      "eval_loss": 1.226914644241333,
      "eval_mean_token_accuracy": 0.757758637269338,
      "eval_num_tokens": 22945.0,
      "eval_runtime": 1.6104,
      "eval_samples_per_second": 45.951,
      "eval_steps_per_second": 1.863,
      "step": 2
    },
    {
      "entropy": 0.4446622431278229,
      "epoch": 0.6,
      "grad_norm": 3.786647319793701,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.0181313753128052,
      "mean_token_accuracy": 0.8030408024787903,
      "num_tokens": 33789.0,
      "step": 3
    },
    {
      "entropy": 0.7599555850028992,
      "epoch": 0.8,
      "grad_norm": 1.5579856634140015,
      "learning_rate": 0.0001,
      "loss": 1.2033650875091553,
      "mean_token_accuracy": 0.7513405084609985,
      "num_tokens": 45381.0,
      "step": 4
    },
    {
      "epoch": 0.8,
      "eval_entropy": 0.6641819675763448,
      "eval_loss": 1.0074481964111328,
      "eval_mean_token_accuracy": 0.7918139894803365,
      "eval_num_tokens": 45381.0,
      "eval_runtime": 1.6119,
      "eval_samples_per_second": 45.908,
      "eval_steps_per_second": 1.861,
      "step": 4
    },
    {
      "entropy": 0.5738851428031921,
      "epoch": 1.0,
      "grad_norm": 1.8575931787490845,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.0246576070785522,
      "mean_token_accuracy": 0.8115941882133484,
      "num_tokens": 49937.0,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_entropy": 0.6727284789085388,
      "eval_loss": 0.999213457107544,
      "eval_mean_token_accuracy": 0.7922166585922241,
      "eval_num_tokens": 49937.0,
      "eval_runtime": 1.612,
      "eval_samples_per_second": 45.907,
      "eval_steps_per_second": 1.861,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "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": 194982543360000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}