{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4153686396677051,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_entropy": 1.202019446364073,
      "eval_loss": 1.0483194589614868,
      "eval_mean_token_accuracy": 0.7420558578500124,
      "eval_num_tokens": 0.0,
      "eval_runtime": 129.0837,
      "eval_samples_per_second": 0.829,
      "eval_steps_per_second": 0.829,
      "step": 0
    },
    {
      "entropy": 0.8833672893047333,
      "epoch": 0.05192107995846314,
      "grad_norm": 10.9375,
      "learning_rate": 9.785867237687366e-06,
      "loss": 0.7974,
      "mean_token_accuracy": 0.7731659519672394,
      "num_tokens": 117579.0,
      "step": 50
    },
    {
      "epoch": 0.05192107995846314,
      "eval_entropy": 0.6945631228317725,
      "eval_loss": 0.661672055721283,
      "eval_mean_token_accuracy": 0.7917334231260781,
      "eval_num_tokens": 117579.0,
      "eval_runtime": 3670.0079,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 50
    },
    {
      "entropy": 0.6754305803775787,
      "epoch": 0.10384215991692627,
      "grad_norm": 10.375,
      "learning_rate": 9.250535331905782e-06,
      "loss": 0.6539,
      "mean_token_accuracy": 0.7942240250110626,
      "num_tokens": 234762.0,
      "step": 100
    },
    {
      "epoch": 0.10384215991692627,
      "eval_entropy": 0.6633974996125587,
      "eval_loss": 0.6503159999847412,
      "eval_mean_token_accuracy": 0.7945662413802103,
      "eval_num_tokens": 234762.0,
      "eval_runtime": 3639.4734,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 100
    },
    {
      "entropy": 0.673185322880745,
      "epoch": 0.1557632398753894,
      "grad_norm": 10.75,
      "learning_rate": 8.715203426124197e-06,
      "loss": 0.654,
      "mean_token_accuracy": 0.7920358991622924,
      "num_tokens": 340474.0,
      "step": 150
    },
    {
      "epoch": 0.1557632398753894,
      "eval_entropy": 0.6714856841853846,
      "eval_loss": 0.6473907232284546,
      "eval_mean_token_accuracy": 0.7945645585238377,
      "eval_num_tokens": 340474.0,
      "eval_runtime": 3648.7713,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 150
    },
    {
      "entropy": 0.6565037113428116,
      "epoch": 0.20768431983385255,
      "grad_norm": 15.875,
      "learning_rate": 8.179871520342612e-06,
      "loss": 0.6425,
      "mean_token_accuracy": 0.7962384045124054,
      "num_tokens": 457598.0,
      "step": 200
    },
    {
      "epoch": 0.20768431983385255,
      "eval_entropy": 0.6561593619462486,
      "eval_loss": 0.6449708342552185,
      "eval_mean_token_accuracy": 0.795283340405081,
      "eval_num_tokens": 457598.0,
      "eval_runtime": 3483.4231,
      "eval_samples_per_second": 0.031,
      "eval_steps_per_second": 0.031,
      "step": 200
    },
    {
      "entropy": 0.6419710898399353,
      "epoch": 0.25960539979231567,
      "grad_norm": 12.0,
      "learning_rate": 7.644539614561029e-06,
      "loss": 0.6278,
      "mean_token_accuracy": 0.7990661442279816,
      "num_tokens": 575217.0,
      "step": 250
    },
    {
      "epoch": 0.25960539979231567,
      "eval_entropy": 0.6565199853660905,
      "eval_loss": 0.6442670226097107,
      "eval_mean_token_accuracy": 0.7952453271250859,
      "eval_num_tokens": 575217.0,
      "eval_runtime": 3485.0746,
      "eval_samples_per_second": 0.031,
      "eval_steps_per_second": 0.031,
      "step": 250
    },
    {
      "entropy": 0.6925940608978272,
      "epoch": 0.3115264797507788,
      "grad_norm": 14.125,
      "learning_rate": 7.109207708779444e-06,
      "loss": 0.6782,
      "mean_token_accuracy": 0.7854274523258209,
      "num_tokens": 690541.0,
      "step": 300
    },
    {
      "epoch": 0.3115264797507788,
      "eval_entropy": 0.64524694051698,
      "eval_loss": 0.6422281265258789,
      "eval_mean_token_accuracy": 0.7960561396919679,
      "eval_num_tokens": 690541.0,
      "eval_runtime": 3645.789,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 300
    },
    {
      "entropy": 0.6548466223478318,
      "epoch": 0.363447559709242,
      "grad_norm": 10.375,
      "learning_rate": 6.573875802997859e-06,
      "loss": 0.6461,
      "mean_token_accuracy": 0.7949914515018464,
      "num_tokens": 811130.0,
      "step": 350
    },
    {
      "epoch": 0.363447559709242,
      "eval_entropy": 0.6484908422577047,
      "eval_loss": 0.6409919261932373,
      "eval_mean_token_accuracy": 0.7962207621503099,
      "eval_num_tokens": 811130.0,
      "eval_runtime": 3645.1814,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 350
    },
    {
      "entropy": 0.6180817884206772,
      "epoch": 0.4153686396677051,
      "grad_norm": 10.9375,
      "learning_rate": 6.038543897216275e-06,
      "loss": 0.6089,
      "mean_token_accuracy": 0.8053069579601287,
      "num_tokens": 923200.0,
      "step": 400
    },
    {
      "epoch": 0.4153686396677051,
      "eval_entropy": 0.6479496045090328,
      "eval_loss": 0.6389999985694885,
      "eval_mean_token_accuracy": 0.7966728973611493,
      "eval_num_tokens": 923200.0,
      "eval_runtime": 3638.2153,
      "eval_samples_per_second": 0.029,
      "eval_steps_per_second": 0.029,
      "step": 400
    }
  ],
  "logging_steps": 50,
  "max_steps": 963,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.126430870427648e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}