{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.442070857435465,
      "epoch": 0.2014098690835851,
      "grad_norm": 0.048095703125,
      "learning_rate": 0.0001868180920098644,
      "loss": 2.5606924438476564,
      "mean_token_accuracy": 0.5233748442679643,
      "num_tokens": 153496.0,
      "step": 25
    },
    {
      "entropy": 1.7652787639200687,
      "epoch": 0.4028197381671702,
      "grad_norm": 0.11083984375,
      "learning_rate": 0.00013916603579471705,
      "loss": 1.7991661071777343,
      "mean_token_accuracy": 0.6229101818054914,
      "num_tokens": 302161.0,
      "step": 50
    },
    {
      "entropy": 1.7339335941150784,
      "epoch": 0.6042296072507553,
      "grad_norm": 0.083984375,
      "learning_rate": 7.558394309716088e-05,
      "loss": 1.7994984436035155,
      "mean_token_accuracy": 0.6460683711618185,
      "num_tokens": 449627.0,
      "step": 75
    },
    {
      "entropy": 1.5877810321189463,
      "epoch": 0.8056394763343404,
      "grad_norm": 0.083984375,
      "learning_rate": 2.1932614882827197e-05,
      "loss": 1.6731886291503906,
      "mean_token_accuracy": 0.6800274739414454,
      "num_tokens": 599747.0,
      "step": 100
    },
    {
      "entropy": 1.7318128037213352,
      "epoch": 1.0,
      "grad_norm": 0.1669921875,
      "learning_rate": 3.370346964876036e-08,
      "loss": 1.7769248962402344,
      "mean_token_accuracy": 0.6527638324184121,
      "num_tokens": 746252.0,
      "step": 125
    }
  ],
  "logging_steps": 25,
  "max_steps": 125,
  "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": 3.1839539976351744e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}