{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9009009009009009,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.7490966856479644,
      "epoch": 0.09009009009009009,
      "grad_norm": 4.318613052368164,
      "learning_rate": 9e-05,
      "loss": 6.8516,
      "mean_token_accuracy": 0.31817560344934465,
      "num_tokens": 5273.0,
      "step": 10
    },
    {
      "entropy": 2.358074116706848,
      "epoch": 0.18018018018018017,
      "grad_norm": 2.591895341873169,
      "learning_rate": 0.00019,
      "loss": 4.7791,
      "mean_token_accuracy": 0.4064402043819427,
      "num_tokens": 10323.0,
      "step": 20
    },
    {
      "entropy": 2.7442060232162477,
      "epoch": 0.2702702702702703,
      "grad_norm": 2.085822105407715,
      "learning_rate": 0.00019424920127795528,
      "loss": 2.528,
      "mean_token_accuracy": 0.6114133253693581,
      "num_tokens": 15657.0,
      "step": 30
    },
    {
      "entropy": 1.6624038934707641,
      "epoch": 0.36036036036036034,
      "grad_norm": 1.898437261581421,
      "learning_rate": 0.0001878594249201278,
      "loss": 1.5967,
      "mean_token_accuracy": 0.75713110268116,
      "num_tokens": 20566.0,
      "step": 40
    },
    {
      "entropy": 1.3454128205776215,
      "epoch": 0.45045045045045046,
      "grad_norm": 2.2532074451446533,
      "learning_rate": 0.00018146964856230032,
      "loss": 1.3224,
      "mean_token_accuracy": 0.7765294492244721,
      "num_tokens": 25625.0,
      "step": 50
    },
    {
      "entropy": 1.1165625154972076,
      "epoch": 0.5405405405405406,
      "grad_norm": 2.300675868988037,
      "learning_rate": 0.00017507987220447287,
      "loss": 1.0734,
      "mean_token_accuracy": 0.803844365477562,
      "num_tokens": 30624.0,
      "step": 60
    },
    {
      "entropy": 0.975060197710991,
      "epoch": 0.6306306306306306,
      "grad_norm": 1.954689383506775,
      "learning_rate": 0.00016869009584664536,
      "loss": 0.9733,
      "mean_token_accuracy": 0.818100169301033,
      "num_tokens": 35746.0,
      "step": 70
    },
    {
      "entropy": 0.8530668556690216,
      "epoch": 0.7207207207207207,
      "grad_norm": 2.083409309387207,
      "learning_rate": 0.0001623003194888179,
      "loss": 0.8131,
      "mean_token_accuracy": 0.8403199791908265,
      "num_tokens": 41031.0,
      "step": 80
    },
    {
      "entropy": 0.8242652952671051,
      "epoch": 0.8108108108108109,
      "grad_norm": 2.1543054580688477,
      "learning_rate": 0.00015591054313099042,
      "loss": 0.7285,
      "mean_token_accuracy": 0.8522787302732467,
      "num_tokens": 45910.0,
      "step": 90
    },
    {
      "entropy": 0.7216496258974076,
      "epoch": 0.9009009009009009,
      "grad_norm": 1.8068711757659912,
      "learning_rate": 0.00014952076677316297,
      "loss": 0.632,
      "mean_token_accuracy": 0.8595692455768585,
      "num_tokens": 51027.0,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 333,
  "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": 561296602595328.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}